diff options
1821 files changed, 37781 insertions, 14033 deletions
@@ -364,6 +364,11 @@ Nicolas Pitre <nico@fluxnic.net> <nico@linaro.org> Nicolas Saenz Julienne <nsaenz@kernel.org> <nsaenzjulienne@suse.de> Nicolas Saenz Julienne <nsaenz@kernel.org> <nsaenzjulienne@suse.com> Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se> +Nikolay Aleksandrov <razor@blackwall.org> <naleksan@redhat.com> +Nikolay Aleksandrov <razor@blackwall.org> <nikolay@redhat.com> +Nikolay Aleksandrov <razor@blackwall.org> <nikolay@cumulusnetworks.com> +Nikolay Aleksandrov <razor@blackwall.org> <nikolay@nvidia.com> +Nikolay Aleksandrov <razor@blackwall.org> <nikolay@isovalent.com> Oleksandr Natalenko <oleksandr@natalenko.name> <oleksandr@redhat.com> Oleksij Rempel <linux@rempel-privat.de> <bug-track@fisher-privat.net> Oleksij Rempel <linux@rempel-privat.de> <external.Oleksij.Rempel@de.bosch.com> @@ -1706,6 +1706,10 @@ S: Panoramastrasse 18 S: D-69126 Heidelberg S: Germany +N: Neil Horman +M: nhorman@tuxdriver.com +D: SCTP protocol maintainer. + N: Simon Horman M: horms@verge.net.au D: Renesas ARM/ARM64 SoC maintainer diff --git a/Documentation/admin-guide/cifs/changes.rst b/Documentation/admin-guide/cifs/changes.rst index 3147bbae9c43..8c42c4de510b 100644 --- a/Documentation/admin-guide/cifs/changes.rst +++ b/Documentation/admin-guide/cifs/changes.rst @@ -5,5 +5,5 @@ Changes See https://wiki.samba.org/index.php/LinuxCIFSKernel for summary information about fixes/improvements to CIFS/SMB2/SMB3 support (changes to cifs.ko module) by kernel version (and cifs internal module version). -This may be easier to read than parsing the output of "git log fs/cifs" -by release. +This may be easier to read than parsing the output of +"git log fs/smb/client" by release. diff --git a/Documentation/admin-guide/cifs/usage.rst b/Documentation/admin-guide/cifs/usage.rst index 2e151cd8c2e4..5f936b4b6018 100644 --- a/Documentation/admin-guide/cifs/usage.rst +++ b/Documentation/admin-guide/cifs/usage.rst @@ -45,7 +45,7 @@ Installation instructions If you have built the CIFS vfs as module (successfully) simply type ``make modules_install`` (or if you prefer, manually copy the file to -the modules directory e.g. /lib/modules/2.4.10-4GB/kernel/fs/cifs/cifs.ko). +the modules directory e.g. /lib/modules/6.3.0-060300-generic/kernel/fs/smb/client/cifs.ko). If you have built the CIFS vfs into the kernel itself, follow the instructions for your distribution on how to install a new kernel (usually you @@ -66,15 +66,15 @@ If cifs is built as a module, then the size and number of network buffers and maximum number of simultaneous requests to one server can be configured. Changing these from their defaults is not recommended. By executing modinfo:: - modinfo kernel/fs/cifs/cifs.ko + modinfo <path to cifs.ko> -on kernel/fs/cifs/cifs.ko the list of configuration changes that can be made +on kernel/fs/smb/client/cifs.ko the list of configuration changes that can be made at module initialization time (by running insmod cifs.ko) can be seen. Recommendations =============== -To improve security the SMB2.1 dialect or later (usually will get SMB3) is now +To improve security the SMB2.1 dialect or later (usually will get SMB3.1.1) is now the new default. To use old dialects (e.g. to mount Windows XP) use "vers=1.0" on mount (or vers=2.0 for Windows Vista). Note that the CIFS (vers=1.0) is much older and less secure than the default dialect SMB3 which includes diff --git a/Documentation/admin-guide/quickly-build-trimmed-linux.rst b/Documentation/admin-guide/quickly-build-trimmed-linux.rst index ff4f4cc8522b..f08149bc53f8 100644 --- a/Documentation/admin-guide/quickly-build-trimmed-linux.rst +++ b/Documentation/admin-guide/quickly-build-trimmed-linux.rst @@ -215,12 +215,14 @@ again. reduce the compile time enormously, especially if you are running an universal kernel from a commodity Linux distribution. - There is a catch: the make target 'localmodconfig' will disable kernel - features you have not directly or indirectly through some program utilized - since you booted the system. You can reduce or nearly eliminate that risk by - using tricks outlined in the reference section; for quick testing purposes - that risk is often negligible, but it is an aspect you want to keep in mind - in case your kernel behaves oddly. + There is a catch: 'localmodconfig' is likely to disable kernel features you + did not use since you booted your Linux -- like drivers for currently + disconnected peripherals or a virtualization software not haven't used yet. + You can reduce or nearly eliminate that risk with tricks the reference + section outlines; but when building a kernel just for quick testing purposes + it is often negligible if such features are missing. But you should keep that + aspect in mind when using a kernel built with this make target, as it might + be the reason why something you only use occasionally stopped working. [:ref:`details<configuration>`] @@ -271,6 +273,9 @@ again. does nothing at all; in that case you have to manually install your kernel, as outlined in the reference section. + If you are running a immutable Linux distribution, check its documentation + and the web to find out how to install your own kernel there. + [:ref:`details<install>`] .. _another_sbs: @@ -291,29 +296,29 @@ again. version you care about, as git otherwise might retrieve the entire commit history:: - git fetch --shallow-exclude=v6.1 origin - - If you modified the sources (for example by applying a patch), you now need - to discard those modifications; that's because git otherwise will not be able - to switch to the sources of another version due to potential conflicting - changes:: - - git reset --hard + git fetch --shallow-exclude=v6.0 origin - Now checkout the version you are interested in, as explained above:: + Now switch to the version you are interested in -- but be aware the command + used here will discard any modifications you performed, as they would + conflict with the sources you want to checkout:: - git checkout --detach origin/master + git checkout --force --detach origin/master At this point you might want to patch the sources again or set/modify a build - tag, as explained earlier; afterwards adjust the build configuration to the - new codebase and build your next kernel:: + tag, as explained earlier. Afterwards adjust the build configuration to the + new codebase using olddefconfig, which will now adjust the configuration file + you prepared earlier using localmodconfig (~/linux/.config) for your next + kernel:: # reminder: if you want to apply patches, do it at this point # reminder: you might want to update your build tag at this point make olddefconfig + + Now build your kernel:: + make -j $(nproc --all) - Install the kernel as outlined above:: + Afterwards install the kernel as outlined above:: command -v installkernel && sudo make modules_install install @@ -584,11 +589,11 @@ versions and individual commits at hand at any time:: curl -L \ https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/clone.bundle \ -o linux-stable.git.bundle - git clone clone.bundle ~/linux/ + git clone linux-stable.git.bundle ~/linux/ rm linux-stable.git.bundle cd ~/linux/ - git remote set-url origin - https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git + git remote set-url origin \ + https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git git fetch origin git checkout --detach origin/master diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst index 466c560b0c30..4877563241f3 100644 --- a/Documentation/admin-guide/sysctl/net.rst +++ b/Documentation/admin-guide/sysctl/net.rst @@ -386,8 +386,8 @@ Default : 0 (for compatibility reasons) txrehash -------- -Controls default hash rethink behaviour on listening socket when SO_TXREHASH -option is set to SOCK_TXREHASH_DEFAULT (i. e. not overridden by setsockopt). +Controls default hash rethink behaviour on socket when SO_TXREHASH option is set +to SOCK_TXREHASH_DEFAULT (i. e. not overridden by setsockopt). If set to 1 (default), hash rethink is performed on listening socket. If set to 0, hash rethink is not performed. diff --git a/Documentation/block/index.rst b/Documentation/block/index.rst index 102953166429..9fea696f9daa 100644 --- a/Documentation/block/index.rst +++ b/Documentation/block/index.rst @@ -18,7 +18,6 @@ Block kyber-iosched null_blk pr - request stat switching-sched writeback_cache_control diff --git a/Documentation/block/request.rst b/Documentation/block/request.rst deleted file mode 100644 index 747021e1ffdb..000000000000 --- a/Documentation/block/request.rst +++ /dev/null @@ -1,99 +0,0 @@ -============================ -struct request documentation -============================ - -Jens Axboe <jens.axboe@oracle.com> 27/05/02 - - -.. FIXME: - No idea about what does mean - seems just some noise, so comment it - - 1.0 - Index - - 2.0 Struct request members classification - - 2.1 struct request members explanation - - 3.0 - - - 2.0 - - - -Short explanation of request members -==================================== - -Classification flags: - - = ==================== - D driver member - B block layer member - I I/O scheduler member - = ==================== - -Unless an entry contains a D classification, a device driver must not access -this member. Some members may contain D classifications, but should only be -access through certain macros or functions (eg ->flags). - -<linux/blkdev.h> - -=============================== ======= ======================================= -Member Flag Comment -=============================== ======= ======================================= -struct list_head queuelist BI Organization on various internal - queues - -``void *elevator_private`` I I/O scheduler private data - -unsigned char cmd[16] D Driver can use this for setting up - a cdb before execution, see - blk_queue_prep_rq - -unsigned long flags DBI Contains info about data direction, - request type, etc. - -int rq_status D Request status bits - -kdev_t rq_dev DBI Target device - -int errors DB Error counts - -sector_t sector DBI Target location - -unsigned long hard_nr_sectors B Used to keep sector sane - -unsigned long nr_sectors DBI Total number of sectors in request - -unsigned long hard_nr_sectors B Used to keep nr_sectors sane - -unsigned short nr_phys_segments DB Number of physical scatter gather - segments in a request - -unsigned short nr_hw_segments DB Number of hardware scatter gather - segments in a request - -unsigned int current_nr_sectors DB Number of sectors in first segment - of request - -unsigned int hard_cur_sectors B Used to keep current_nr_sectors sane - -int tag DB TCQ tag, if assigned - -``void *special`` D Free to be used by driver - -``char *buffer`` D Map of first segment, also see - section on bouncing SECTION - -``struct completion *waiting`` D Can be used by driver to get signalled - on request completion - -``struct bio *bio`` DBI First bio in request - -``struct bio *biotail`` DBI Last bio in request - -``struct request_queue *q`` DB Request queue this request belongs to - -``struct request_list *rl`` B Request list this request came from -=============================== ======= ======================================= diff --git a/Documentation/bpf/instruction-set.rst b/Documentation/bpf/instruction-set.rst index 492980ece1ab..6644842cd3ea 100644 --- a/Documentation/bpf/instruction-set.rst +++ b/Documentation/bpf/instruction-set.rst @@ -163,13 +163,13 @@ BPF_MUL 0x20 dst \*= src BPF_DIV 0x30 dst = (src != 0) ? (dst / src) : 0 BPF_OR 0x40 dst \|= src BPF_AND 0x50 dst &= src -BPF_LSH 0x60 dst <<= src -BPF_RSH 0x70 dst >>= src +BPF_LSH 0x60 dst <<= (src & mask) +BPF_RSH 0x70 dst >>= (src & mask) BPF_NEG 0x80 dst = ~src BPF_MOD 0x90 dst = (src != 0) ? (dst % src) : dst BPF_XOR 0xa0 dst ^= src BPF_MOV 0xb0 dst = src -BPF_ARSH 0xc0 sign extending shift right +BPF_ARSH 0xc0 sign extending dst >>= (src & mask) BPF_END 0xd0 byte swap operations (see `Byte swap instructions`_ below) ======== ===== ========================================================== @@ -204,6 +204,9 @@ for ``BPF_ALU64``, 'imm' is first sign extended to 64 bits and the result interpreted as an unsigned 64-bit value. There are no instructions for signed division or modulo. +Shift operations use a mask of 0x3F (63) for 64-bit operations and 0x1F (31) +for 32-bit operations. + Byte swap instructions ~~~~~~~~~~~~~~~~~~~~~~ diff --git a/Documentation/bpf/kfuncs.rst b/Documentation/bpf/kfuncs.rst index ea2516374d92..7a3d9de5f315 100644 --- a/Documentation/bpf/kfuncs.rst +++ b/Documentation/bpf/kfuncs.rst @@ -100,7 +100,7 @@ Hence, whenever a constant scalar argument is accepted by a kfunc which is not a size parameter, and the value of the constant matters for program safety, __k suffix should be used. -2.2.2 __uninit Annotation +2.2.3 __uninit Annotation ------------------------- This annotation is used to indicate that the argument will be treated as @@ -117,6 +117,27 @@ Here, the dynptr will be treated as an uninitialized dynptr. Without this annotation, the verifier will reject the program if the dynptr passed in is not initialized. +2.2.4 __opt Annotation +------------------------- + +This annotation is used to indicate that the buffer associated with an __sz or __szk +argument may be null. If the function is passed a nullptr in place of the buffer, +the verifier will not check that length is appropriate for the buffer. The kfunc is +responsible for checking if this buffer is null before using it. + +An example is given below:: + + __bpf_kfunc void *bpf_dynptr_slice(..., void *buffer__opt, u32 buffer__szk) + { + ... + } + +Here, the buffer may be null. If buffer is not null, it at least of size buffer_szk. +Either way, the returned buffer is either NULL, or of size buffer_szk. Without this +annotation, the verifier will reject the program if a null pointer is passed in with +a nonzero size. + + .. _BPF_kfunc_nodef: 2.3 Using an existing kernel function diff --git a/Documentation/bpf/llvm_reloc.rst b/Documentation/bpf/llvm_reloc.rst index ca8957d5b671..e4a777a6a3a2 100644 --- a/Documentation/bpf/llvm_reloc.rst +++ b/Documentation/bpf/llvm_reloc.rst @@ -48,7 +48,7 @@ the code with ``llvm-objdump -dr test.o``:: 14: 0f 10 00 00 00 00 00 00 r0 += r1 15: 95 00 00 00 00 00 00 00 exit -There are four relations in the above for four ``LD_imm64`` instructions. +There are four relocations in the above for four ``LD_imm64`` instructions. The following ``llvm-readelf -r test.o`` shows the binary values of the four relocations:: @@ -79,14 +79,16 @@ The following is the symbol table with ``llvm-readelf -s test.o``:: The 6th entry is global variable ``g1`` with value 0. Similarly, the second relocation is at ``.text`` offset ``0x18``, instruction 3, -for global variable ``g2`` which has a symbol value 4, the offset -from the start of ``.data`` section. - -The third and fourth relocations refers to static variables ``l1`` -and ``l2``. From ``.rel.text`` section above, it is not clear -which symbols they really refers to as they both refers to +has a type of ``R_BPF_64_64`` and refers to entry 7 in the symbol table. +The second relocation resolves to global variable ``g2`` which has a symbol +value 4. The symbol value represents the offset from the start of ``.data`` +section where the initial value of the global variable ``g2`` is stored. + +The third and fourth relocations refer to static variables ``l1`` +and ``l2``. From the ``.rel.text`` section above, it is not clear +to which symbols they really refer as they both refer to symbol table entry 4, symbol ``sec``, which has ``STT_SECTION`` type -and represents a section. So for static variable or function, +and represents a section. So for a static variable or function, the section offset is written to the original insn buffer, which is called ``A`` (addend). Looking at above insn ``7`` and ``11``, they have section offset ``8`` and ``12``. diff --git a/Documentation/bpf/map_hash.rst b/Documentation/bpf/map_hash.rst index 8669426264c6..d2343952f2cb 100644 --- a/Documentation/bpf/map_hash.rst +++ b/Documentation/bpf/map_hash.rst @@ -1,5 +1,6 @@ .. SPDX-License-Identifier: GPL-2.0-only .. Copyright (C) 2022 Red Hat, Inc. +.. Copyright (C) 2022-2023 Isovalent, Inc. =============================================== BPF_MAP_TYPE_HASH, with PERCPU and LRU Variants @@ -29,7 +30,16 @@ will automatically evict the least recently used entries when the hash table reaches capacity. An LRU hash maintains an internal LRU list that is used to select elements for eviction. This internal LRU list is shared across CPUs but it is possible to request a per CPU LRU list with -the ``BPF_F_NO_COMMON_LRU`` flag when calling ``bpf_map_create``. +the ``BPF_F_NO_COMMON_LRU`` flag when calling ``bpf_map_create``. The +following table outlines the properties of LRU maps depending on the a +map type and the flags used to create the map. + +======================== ========================= ================================ +Flag ``BPF_MAP_TYPE_LRU_HASH`` ``BPF_MAP_TYPE_LRU_PERCPU_HASH`` +======================== ========================= ================================ +**BPF_F_NO_COMMON_LRU** Per-CPU LRU, global map Per-CPU LRU, per-cpu map +**!BPF_F_NO_COMMON_LRU** Global LRU, global map Global LRU, per-cpu map +======================== ========================= ================================ Usage ===== @@ -206,3 +216,44 @@ Userspace walking the map elements from the map declared above: cur_key = &next_key; } } + +Internals +========= + +This section of the document is targeted at Linux developers and describes +aspects of the map implementations that are not considered stable ABI. The +following details are subject to change in future versions of the kernel. + +``BPF_MAP_TYPE_LRU_HASH`` and variants +-------------------------------------- + +Updating elements in LRU maps may trigger eviction behaviour when the capacity +of the map is reached. There are various steps that the update algorithm +attempts in order to enforce the LRU property which have increasing impacts on +other CPUs involved in the following operation attempts: + +- Attempt to use CPU-local state to batch operations +- Attempt to fetch free nodes from global lists +- Attempt to pull any node from a global list and remove it from the hashmap +- Attempt to pull any node from any CPU's list and remove it from the hashmap + +This algorithm is described visually in the following diagram. See the +description in commit 3a08c2fd7634 ("bpf: LRU List") for a full explanation of +the corresponding operations: + +.. kernel-figure:: map_lru_hash_update.dot + :alt: Diagram outlining the LRU eviction steps taken during map update. + + LRU hash eviction during map update for ``BPF_MAP_TYPE_LRU_HASH`` and + variants. See the dot file source for kernel function name code references. + +Map updates start from the oval in the top right "begin ``bpf_map_update()``" +and progress through the graph towards the bottom where the result may be +either a successful update or a failure with various error codes. The key in +the top right provides indicators for which locks may be involved in specific +operations. This is intended as a visual hint for reasoning about how map +contention may impact update operations, though the map type and flags may +impact the actual contention on those locks, based on the logic described in +the table above. For instance, if the map is created with type +``BPF_MAP_TYPE_LRU_PERCPU_HASH`` and flags ``BPF_F_NO_COMMON_LRU`` then all map +properties would be per-cpu. diff --git a/Documentation/bpf/map_lru_hash_update.dot b/Documentation/bpf/map_lru_hash_update.dot new file mode 100644 index 000000000000..a0fee349d29c --- /dev/null +++ b/Documentation/bpf/map_lru_hash_update.dot @@ -0,0 +1,172 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (C) 2022-2023 Isovalent, Inc. +digraph { + node [colorscheme=accent4,style=filled] # Apply colorscheme to all nodes + graph [splines=ortho, nodesep=1] + + subgraph cluster_key { + label = "Key\n(locks held during operation)"; + rankdir = TB; + + remote_lock [shape=rectangle,fillcolor=4,label="remote CPU LRU lock"] + hash_lock [shape=rectangle,fillcolor=3,label="hashtab lock"] + lru_lock [shape=rectangle,fillcolor=2,label="LRU lock"] + local_lock [shape=rectangle,fillcolor=1,label="local CPU LRU lock"] + no_lock [shape=rectangle,label="no locks held"] + } + + begin [shape=oval,label="begin\nbpf_map_update()"] + + // Nodes below with an 'fn_' prefix are roughly labeled by the C function + // names that initiate the corresponding logic in kernel/bpf/bpf_lru_list.c. + // Number suffixes and errno suffixes handle subsections of the corresponding + // logic in the function as of the writing of this dot. + + // cf. __local_list_pop_free() / bpf_percpu_lru_pop_free() + local_freelist_check [shape=diamond,fillcolor=1, + label="Local freelist\nnode available?"]; + use_local_node [shape=rectangle, + label="Use node owned\nby this CPU"] + + // cf. bpf_lru_pop_free() + common_lru_check [shape=diamond, + label="Map created with\ncommon LRU?\n(!BPF_F_NO_COMMON_LRU)"]; + + fn_bpf_lru_list_pop_free_to_local [shape=rectangle,fillcolor=2, + label="Flush local pending, + Rotate Global list, move + LOCAL_FREE_TARGET + from global -> local"] + // Also corresponds to: + // fn__local_list_flush() + // fn_bpf_lru_list_rotate() + fn___bpf_lru_node_move_to_free[shape=diamond,fillcolor=2, + label="Able to free\nLOCAL_FREE_TARGET\nnodes?"] + + fn___bpf_lru_list_shrink_inactive [shape=rectangle,fillcolor=3, + label="Shrink inactive list + up to remaining + LOCAL_FREE_TARGET + (global LRU -> local)"] + fn___bpf_lru_list_shrink [shape=diamond,fillcolor=2, + label="> 0 entries in\nlocal free list?"] + fn___bpf_lru_list_shrink2 [shape=rectangle,fillcolor=2, + label="Steal one node from + inactive, or if empty, + from active global list"] + fn___bpf_lru_list_shrink3 [shape=rectangle,fillcolor=3, + label="Try to remove\nnode from hashtab"] + + local_freelist_check2 [shape=diamond,label="Htab removal\nsuccessful?"] + common_lru_check2 [shape=diamond, + label="Map created with\ncommon LRU?\n(!BPF_F_NO_COMMON_LRU)"]; + + subgraph cluster_remote_lock { + label = "Iterate through CPUs\n(start from current)"; + style = dashed; + rankdir=LR; + + local_freelist_check5 [shape=diamond,fillcolor=4, + label="Steal a node from\nper-cpu freelist?"] + local_freelist_check6 [shape=rectangle,fillcolor=4, + label="Steal a node from + (1) Unreferenced pending, or + (2) Any pending node"] + local_freelist_check7 [shape=rectangle,fillcolor=3, + label="Try to remove\nnode from hashtab"] + fn_htab_lru_map_update_elem [shape=diamond, + label="Stole node\nfrom remote\nCPU?"] + fn_htab_lru_map_update_elem2 [shape=diamond,label="Iterated\nall CPUs?"] + // Also corresponds to: + // use_local_node() + // fn__local_list_pop_pending() + } + + fn_bpf_lru_list_pop_free_to_local2 [shape=rectangle, + label="Use node that was\nnot recently referenced"] + local_freelist_check4 [shape=rectangle, + label="Use node that was\nactively referenced\nin global list"] + fn_htab_lru_map_update_elem_ENOMEM [shape=oval,label="return -ENOMEM"] + fn_htab_lru_map_update_elem3 [shape=rectangle, + label="Use node that was\nactively referenced\nin (another?) CPU's cache"] + fn_htab_lru_map_update_elem4 [shape=rectangle,fillcolor=3, + label="Update hashmap\nwith new element"] + fn_htab_lru_map_update_elem5 [shape=oval,label="return 0"] + fn_htab_lru_map_update_elem_EBUSY [shape=oval,label="return -EBUSY"] + fn_htab_lru_map_update_elem_EEXIST [shape=oval,label="return -EEXIST"] + fn_htab_lru_map_update_elem_ENOENT [shape=oval,label="return -ENOENT"] + + begin -> local_freelist_check + local_freelist_check -> use_local_node [xlabel="Y"] + local_freelist_check -> common_lru_check [xlabel="N"] + common_lru_check -> fn_bpf_lru_list_pop_free_to_local [xlabel="Y"] + common_lru_check -> fn___bpf_lru_list_shrink_inactive [xlabel="N"] + fn_bpf_lru_list_pop_free_to_local -> fn___bpf_lru_node_move_to_free + fn___bpf_lru_node_move_to_free -> + fn_bpf_lru_list_pop_free_to_local2 [xlabel="Y"] + fn___bpf_lru_node_move_to_free -> + fn___bpf_lru_list_shrink_inactive [xlabel="N"] + fn___bpf_lru_list_shrink_inactive -> fn___bpf_lru_list_shrink + fn___bpf_lru_list_shrink -> fn_bpf_lru_list_pop_free_to_local2 [xlabel = "Y"] + fn___bpf_lru_list_shrink -> fn___bpf_lru_list_shrink2 [xlabel="N"] + fn___bpf_lru_list_shrink2 -> fn___bpf_lru_list_shrink3 + fn___bpf_lru_list_shrink3 -> local_freelist_check2 + local_freelist_check2 -> local_freelist_check4 [xlabel = "Y"] + local_freelist_check2 -> common_lru_check2 [xlabel = "N"] + common_lru_check2 -> local_freelist_check5 [xlabel = "Y"] + common_lru_check2 -> fn_htab_lru_map_update_elem_ENOMEM [xlabel = "N"] + local_freelist_check5 -> fn_htab_lru_map_update_elem [xlabel = "Y"] + local_freelist_check5 -> local_freelist_check6 [xlabel = "N"] + local_freelist_check6 -> local_freelist_check7 + local_freelist_check7 -> fn_htab_lru_map_update_elem + + fn_htab_lru_map_update_elem -> fn_htab_lru_map_update_elem3 [xlabel = "Y"] + fn_htab_lru_map_update_elem -> fn_htab_lru_map_update_elem2 [xlabel = "N"] + fn_htab_lru_map_update_elem2 -> + fn_htab_lru_map_update_elem_ENOMEM [xlabel = "Y"] + fn_htab_lru_map_update_elem2 -> local_freelist_check5 [xlabel = "N"] + fn_htab_lru_map_update_elem3 -> fn_htab_lru_map_update_elem4 + + use_local_node -> fn_htab_lru_map_update_elem4 + fn_bpf_lru_list_pop_free_to_local2 -> fn_htab_lru_map_update_elem4 + local_freelist_check4 -> fn_htab_lru_map_update_elem4 + + fn_htab_lru_map_update_elem4 -> fn_htab_lru_map_update_elem5 [headlabel="Success"] + fn_htab_lru_map_update_elem4 -> + fn_htab_lru_map_update_elem_EBUSY [xlabel="Hashtab lock failed"] + fn_htab_lru_map_update_elem4 -> + fn_htab_lru_map_update_elem_EEXIST [xlabel="BPF_EXIST set and\nkey already exists"] + fn_htab_lru_map_update_elem4 -> + fn_htab_lru_map_update_elem_ENOENT [headlabel="BPF_NOEXIST set\nand no such entry"] + + // Create invisible pad nodes to line up various nodes + pad0 [style=invis] + pad1 [style=invis] + pad2 [style=invis] + pad3 [style=invis] + pad4 [style=invis] + + // Line up the key with the top of the graph + no_lock -> local_lock [style=invis] + local_lock -> lru_lock [style=invis] + lru_lock -> hash_lock [style=invis] + hash_lock -> remote_lock [style=invis] + remote_lock -> local_freelist_check5 [style=invis] + remote_lock -> fn___bpf_lru_list_shrink [style=invis] + + // Line up return code nodes at the bottom of the graph + fn_htab_lru_map_update_elem -> pad0 [style=invis] + pad0 -> pad1 [style=invis] + pad1 -> pad2 [style=invis] + //pad2-> fn_htab_lru_map_update_elem_ENOMEM [style=invis] + fn_htab_lru_map_update_elem4 -> pad3 [style=invis] + pad3 -> fn_htab_lru_map_update_elem5 [style=invis] + pad3 -> fn_htab_lru_map_update_elem_EBUSY [style=invis] + pad3 -> fn_htab_lru_map_update_elem_EEXIST [style=invis] + pad3 -> fn_htab_lru_map_update_elem_ENOENT [style=invis] + + // Reduce diagram width by forcing some nodes to appear above others + local_freelist_check4 -> fn_htab_lru_map_update_elem3 [style=invis] + common_lru_check2 -> pad4 [style=invis] + pad4 -> local_freelist_check5 [style=invis] +} diff --git a/Documentation/bpf/prog_cgroup_sockopt.rst b/Documentation/bpf/prog_cgroup_sockopt.rst index 172f957204bf..1226a94af07a 100644 --- a/Documentation/bpf/prog_cgroup_sockopt.rst +++ b/Documentation/bpf/prog_cgroup_sockopt.rst @@ -98,10 +98,65 @@ can access only the first ``PAGE_SIZE`` of that data. So it has to options: indicates that the kernel should use BPF's trimmed ``optval``. When the BPF program returns with the ``optlen`` greater than -``PAGE_SIZE``, the userspace will receive ``EFAULT`` errno. +``PAGE_SIZE``, the userspace will receive original kernel +buffers without any modifications that the BPF program might have +applied. Example ======= +Recommended way to handle BPF programs is as follows: + +.. code-block:: c + + SEC("cgroup/getsockopt") + int getsockopt(struct bpf_sockopt *ctx) + { + /* Custom socket option. */ + if (ctx->level == MY_SOL && ctx->optname == MY_OPTNAME) { + ctx->retval = 0; + optval[0] = ...; + ctx->optlen = 1; + return 1; + } + + /* Modify kernel's socket option. */ + if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) { + ctx->retval = 0; + optval[0] = ...; + ctx->optlen = 1; + return 1; + } + + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > PAGE_SIZE) + ctx->optlen = 0; + + return 1; + } + + SEC("cgroup/setsockopt") + int setsockopt(struct bpf_sockopt *ctx) + { + /* Custom socket option. */ + if (ctx->level == MY_SOL && ctx->optname == MY_OPTNAME) { + /* do something */ + ctx->optlen = -1; + return 1; + } + + /* Modify kernel's socket option. */ + if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) { + optval[0] = ...; + return 1; + } + + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > PAGE_SIZE) + ctx->optlen = 0; + + return 1; + } + See ``tools/testing/selftests/bpf/progs/sockopt_sk.c`` for an example of BPF program that handles socket options. diff --git a/Documentation/cdrom/index.rst b/Documentation/cdrom/index.rst index e87a8785bc1a..e9b022d70939 100644 --- a/Documentation/cdrom/index.rst +++ b/Documentation/cdrom/index.rst @@ -1,8 +1,8 @@ .. SPDX-License-Identifier: GPL-2.0 -===== -cdrom -===== +====== +CD-ROM +====== .. toctree:: :maxdepth: 1 diff --git a/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml b/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml index 9b31f864e071..71364c6081ff 100644 --- a/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml +++ b/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml @@ -32,7 +32,7 @@ properties: maxItems: 1 iommus: - maxItems: 1 + maxItems: 4 power-domains: maxItems: 1 diff --git a/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml b/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml index e6c1ebfe8a32..130e16d025bc 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml +++ b/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml @@ -82,6 +82,18 @@ properties: Indicates if the DSI controller is driving a panel which needs 2 DSI links. + qcom,master-dsi: + type: boolean + description: | + Indicates if the DSI controller is the master DSI controller when + qcom,dual-dsi-mode enabled. + + qcom,sync-dual-dsi: + type: boolean + description: | + Indicates if the DSI controller needs to sync the other DSI controller + with MIPI DCS commands when qcom,dual-dsi-mode enabled. + assigned-clocks: minItems: 2 maxItems: 4 diff --git a/Documentation/devicetree/bindings/fpga/lattice,sysconfig.yaml b/Documentation/devicetree/bindings/fpga/lattice,sysconfig.yaml index 4fb05eb84e2a..164331eb6275 100644 --- a/Documentation/devicetree/bindings/fpga/lattice,sysconfig.yaml +++ b/Documentation/devicetree/bindings/fpga/lattice,sysconfig.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Lattice Slave SPI sysCONFIG FPGA manager maintainers: - - Ivan Bornyakov <i.bornyakov@metrotek.ru> + - Vladimir Georgiev <v.georgiev@metrotek.ru> description: | Lattice sysCONFIG port, which is used for FPGA configuration, among others, diff --git a/Documentation/devicetree/bindings/fpga/microchip,mpf-spi-fpga-mgr.yaml b/Documentation/devicetree/bindings/fpga/microchip,mpf-spi-fpga-mgr.yaml index 527532f039ce..a157eecfb5fc 100644 --- a/Documentation/devicetree/bindings/fpga/microchip,mpf-spi-fpga-mgr.yaml +++ b/Documentation/devicetree/bindings/fpga/microchip,mpf-spi-fpga-mgr.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Microchip Polarfire FPGA manager. maintainers: - - Ivan Bornyakov <i.bornyakov@metrotek.ru> + - Vladimir Georgiev <v.georgiev@metrotek.ru> description: Device Tree Bindings for Microchip Polarfire FPGA Manager using slave SPI to diff --git a/Documentation/devicetree/bindings/iio/adc/nxp,imx8qxp-adc.yaml b/Documentation/devicetree/bindings/iio/adc/nxp,imx8qxp-adc.yaml index 63369ba388e4..0a192ca192c5 100644 --- a/Documentation/devicetree/bindings/iio/adc/nxp,imx8qxp-adc.yaml +++ b/Documentation/devicetree/bindings/iio/adc/nxp,imx8qxp-adc.yaml @@ -39,6 +39,12 @@ properties: power-domains: maxItems: 1 + vref-supply: + description: | + External ADC reference voltage supply on VREFH pad. If VERID[MVI] is + set, there are additional, internal reference voltages selectable. + VREFH1 is always from VREFH pad. + "#io-channel-cells": const: 1 @@ -72,6 +78,7 @@ examples: assigned-clocks = <&clk IMX_SC_R_ADC_0>; assigned-clock-rates = <24000000>; power-domains = <&pd IMX_SC_R_ADC_0>; + vref-supply = <®_1v8>; #io-channel-cells = <1>; }; }; diff --git a/Documentation/devicetree/bindings/iio/adc/renesas,rcar-gyroadc.yaml b/Documentation/devicetree/bindings/iio/adc/renesas,rcar-gyroadc.yaml index 1c7aee5ed3e0..36dff3250ea7 100644 --- a/Documentation/devicetree/bindings/iio/adc/renesas,rcar-gyroadc.yaml +++ b/Documentation/devicetree/bindings/iio/adc/renesas,rcar-gyroadc.yaml @@ -90,7 +90,7 @@ patternProperties: of the MAX chips to the GyroADC, while MISO line of each Maxim ADC connects to a shared input pin of the GyroADC. enum: - - adi,7476 + - adi,ad7476 - fujitsu,mb88101a - maxim,max1162 - maxim,max11100 diff --git a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml index 92117261e1e1..39e64c7f6360 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml @@ -166,6 +166,12 @@ properties: resets: maxItems: 1 + mediatek,broken-save-restore-fw: + type: boolean + description: + Asserts that the firmware on this device has issues saving and restoring + GICR registers when the GIC redistributors are powered off. + dependencies: mbi-ranges: [ msi-controller ] msi-controller: [ mbi-ranges ] diff --git a/Documentation/devicetree/bindings/media/i2c/ovti,ov2685.yaml b/Documentation/devicetree/bindings/media/i2c/ovti,ov2685.yaml index 8b389314c352..e2ffe0a9c26b 100644 --- a/Documentation/devicetree/bindings/media/i2c/ovti,ov2685.yaml +++ b/Documentation/devicetree/bindings/media/i2c/ovti,ov2685.yaml @@ -49,6 +49,7 @@ properties: properties: data-lanes: + minItems: 1 maxItems: 2 required: diff --git a/Documentation/devicetree/bindings/net/can/st,stm32-bxcan.yaml b/Documentation/devicetree/bindings/net/can/st,stm32-bxcan.yaml index 769fa5c27b76..de1d4298893b 100644 --- a/Documentation/devicetree/bindings/net/can/st,stm32-bxcan.yaml +++ b/Documentation/devicetree/bindings/net/can/st,stm32-bxcan.yaml @@ -21,11 +21,22 @@ properties: st,can-primary: description: - Primary and secondary mode of the bxCAN peripheral is only relevant - if the chip has two CAN peripherals. In that case they share some - of the required logic. + Primary mode of the bxCAN peripheral is only relevant if the chip has + two CAN peripherals in dual CAN configuration. In that case they share + some of the required logic. + Not to be used if the peripheral is in single CAN configuration. To avoid misunderstandings, it should be noted that ST documentation - uses the terms master/slave instead of primary/secondary. + uses the terms master instead of primary. + type: boolean + + st,can-secondary: + description: + Secondary mode of the bxCAN peripheral is only relevant if the chip + has two CAN peripherals in dual CAN configuration. In that case they + share some of the required logic. + Not to be used if the peripheral is in single CAN configuration. + To avoid misunderstandings, it should be noted that ST documentation + uses the terms slave instead of secondary. type: boolean reg: diff --git a/Documentation/devicetree/bindings/net/dsa/marvell.txt b/Documentation/devicetree/bindings/net/dsa/marvell.txt index 2363b412410c..33726134f5c9 100644 --- a/Documentation/devicetree/bindings/net/dsa/marvell.txt +++ b/Documentation/devicetree/bindings/net/dsa/marvell.txt @@ -20,7 +20,7 @@ which is at a different MDIO base address in different switch families. 6171, 6172, 6175, 6176, 6185, 6240, 6320, 6321, 6341, 6350, 6351, 6352 - "marvell,mv88e6190" : Switch has base address 0x00. Use with models: - 6190, 6190X, 6191, 6290, 6390, 6390X + 6163, 6190, 6190X, 6191, 6290, 6390, 6390X - "marvell,mv88e6250" : Switch has base address 0x08 or 0x18. Use with model: 6220, 6250 diff --git a/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml b/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml index 9a64ed658745..4d5f5cc6d031 100644 --- a/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml +++ b/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml @@ -12,10 +12,6 @@ description: cs_sck_delay of 500ns. Ensuring that this SPI timing requirement is observed depends on the SPI bus master driver. -allOf: - - $ref: dsa.yaml#/$defs/ethernet-ports - - $ref: /schemas/spi/spi-peripheral-props.yaml# - maintainers: - Vladimir Oltean <vladimir.oltean@nxp.com> @@ -36,6 +32,9 @@ properties: reg: maxItems: 1 + spi-cpha: true + spi-cpol: true + # Optional container node for the 2 internal MDIO buses of the SJA1110 # (one for the internal 100base-T1 PHYs and the other for the single # 100base-TX PHY). The "reg" property does not have physical significance. @@ -109,6 +108,30 @@ $defs: 1860, 1880, 1900, 1920, 1940, 1960, 1980, 2000, 2020, 2040, 2060, 2080, 2100, 2120, 2140, 2160, 2180, 2200, 2220, 2240, 2260] +allOf: + - $ref: dsa.yaml#/$defs/ethernet-ports + - $ref: /schemas/spi/spi-peripheral-props.yaml# + - if: + properties: + compatible: + enum: + - nxp,sja1105e + - nxp,sja1105p + - nxp,sja1105q + - nxp,sja1105r + - nxp,sja1105s + - nxp,sja1105t + then: + properties: + spi-cpol: false + required: + - spi-cpha + else: + properties: + spi-cpha: false + required: + - spi-cpol + unevaluatedProperties: false examples: @@ -120,6 +143,7 @@ examples: ethernet-switch@1 { reg = <0x1>; compatible = "nxp,sja1105t"; + spi-cpha; ethernet-ports { #address-cells = <1>; diff --git a/Documentation/devicetree/bindings/net/ethernet-phy.yaml b/Documentation/devicetree/bindings/net/ethernet-phy.yaml index 4f574532ee13..c1241c8a3b77 100644 --- a/Documentation/devicetree/bindings/net/ethernet-phy.yaml +++ b/Documentation/devicetree/bindings/net/ethernet-phy.yaml @@ -93,6 +93,12 @@ properties: the turn around line low at end of the control phase of the MDIO transaction. + clocks: + maxItems: 1 + description: + External clock connected to the PHY. If not specified it is assumed + that the PHY uses a fixed crystal or an internal oscillator. + enet-phy-lane-swap: $ref: /schemas/types.yaml#/definitions/flag description: diff --git a/Documentation/devicetree/bindings/net/pse-pd/pse-controller.yaml b/Documentation/devicetree/bindings/net/pse-pd/pse-controller.yaml index b110abb42597..2d382faca0e6 100644 --- a/Documentation/devicetree/bindings/net/pse-pd/pse-controller.yaml +++ b/Documentation/devicetree/bindings/net/pse-pd/pse-controller.yaml @@ -16,7 +16,7 @@ maintainers: properties: $nodename: - pattern: "^ethernet-pse(@.*)?$" + pattern: "^ethernet-pse(@.*|-([0-9]|[1-9][0-9]+))?$" "#pse-cells": description: diff --git a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-common.yaml b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-common.yaml index 9bff8ecb653c..d91b639ae7ae 100644 --- a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-common.yaml +++ b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-common.yaml @@ -17,20 +17,11 @@ description: properties: clocks: minItems: 3 - items: - - description: PCIe bridge clock. - - description: PCIe bus clock. - - description: PCIe PHY clock. - - description: Additional required clock entry for imx6sx-pcie, - imx6sx-pcie-ep, imx8mq-pcie, imx8mq-pcie-ep. + maxItems: 4 clock-names: minItems: 3 - items: - - const: pcie - - const: pcie_bus - - enum: [ pcie_phy, pcie_aux ] - - enum: [ pcie_inbound_axi, pcie_aux ] + maxItems: 4 num-lanes: const: 1 diff --git a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-ep.yaml b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-ep.yaml index f4a328ec1daa..ee155ed5f181 100644 --- a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-ep.yaml +++ b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-ep.yaml @@ -31,6 +31,19 @@ properties: - const: dbi - const: addr_space + clocks: + minItems: 3 + items: + - description: PCIe bridge clock. + - description: PCIe bus clock. + - description: PCIe PHY clock. + - description: Additional required clock entry for imx6sx-pcie, + imx6sx-pcie-ep, imx8mq-pcie, imx8mq-pcie-ep. + + clock-names: + minItems: 3 + maxItems: 4 + interrupts: items: - description: builtin eDMA interrupter. @@ -49,6 +62,31 @@ required: allOf: - $ref: /schemas/pci/snps,dw-pcie-ep.yaml# - $ref: /schemas/pci/fsl,imx6q-pcie-common.yaml# + - if: + properties: + compatible: + enum: + - fsl,imx8mq-pcie-ep + then: + properties: + clocks: + minItems: 4 + clock-names: + items: + - const: pcie + - const: pcie_bus + - const: pcie_phy + - const: pcie_aux + else: + properties: + clocks: + maxItems: 3 + clock-names: + items: + - const: pcie + - const: pcie_bus + - const: pcie_aux + unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.yaml b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.yaml index 2443641754d3..81bbb8728f0f 100644 --- a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.yaml +++ b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.yaml @@ -40,6 +40,19 @@ properties: - const: dbi - const: config + clocks: + minItems: 3 + items: + - description: PCIe bridge clock. + - description: PCIe bus clock. + - description: PCIe PHY clock. + - description: Additional required clock entry for imx6sx-pcie, + imx6sx-pcie-ep, imx8mq-pcie, imx8mq-pcie-ep. + + clock-names: + minItems: 3 + maxItems: 4 + interrupts: items: - description: builtin MSI controller. @@ -77,6 +90,70 @@ required: allOf: - $ref: /schemas/pci/snps,dw-pcie.yaml# - $ref: /schemas/pci/fsl,imx6q-pcie-common.yaml# + - if: + properties: + compatible: + enum: + - fsl,imx6sx-pcie + then: + properties: + clocks: + minItems: 4 + clock-names: + items: + - const: pcie + - const: pcie_bus + - const: pcie_phy + - const: pcie_inbound_axi + + - if: + properties: + compatible: + enum: + - fsl,imx8mq-pcie + then: + properties: + clocks: + minItems: 4 + clock-names: + items: + - const: pcie + - const: pcie_bus + - const: pcie_phy + - const: pcie_aux + + - if: + properties: + compatible: + enum: + - fsl,imx6q-pcie + - fsl,imx6qp-pcie + - fsl,imx7d-pcie + then: + properties: + clocks: + maxItems: 3 + clock-names: + items: + - const: pcie + - const: pcie_bus + - const: pcie_phy + + - if: + properties: + compatible: + enum: + - fsl,imx8mm-pcie + - fsl,imx8mp-pcie + then: + properties: + clocks: + maxItems: 3 + clock-names: + items: + - const: pcie + - const: pcie_bus + - const: pcie_aux unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/serial/8250_omap.yaml b/Documentation/devicetree/bindings/serial/8250_omap.yaml index eb3488d8f9ee..6a7be42da523 100644 --- a/Documentation/devicetree/bindings/serial/8250_omap.yaml +++ b/Documentation/devicetree/bindings/serial/8250_omap.yaml @@ -70,6 +70,7 @@ properties: dsr-gpios: true rng-gpios: true dcd-gpios: true + rs485-rts-active-high: true rts-gpio: true power-domains: true clock-frequency: true diff --git a/Documentation/devicetree/bindings/sound/tas2562.yaml b/Documentation/devicetree/bindings/sound/tas2562.yaml index a5bb561bfcfb..31a3024ea789 100644 --- a/Documentation/devicetree/bindings/sound/tas2562.yaml +++ b/Documentation/devicetree/bindings/sound/tas2562.yaml @@ -55,7 +55,9 @@ properties: description: TDM TX current sense time slot. '#sound-dai-cells': - const: 1 + # The codec has a single DAI, the #sound-dai-cells=<1>; case is left in for backward + # compatibility but is deprecated. + enum: [0, 1] required: - compatible @@ -72,7 +74,7 @@ examples: codec: codec@4c { compatible = "ti,tas2562"; reg = <0x4c>; - #sound-dai-cells = <1>; + #sound-dai-cells = <0>; interrupt-parent = <&gpio1>; interrupts = <14>; shutdown-gpios = <&gpio1 15 0>; diff --git a/Documentation/devicetree/bindings/sound/tas2770.yaml b/Documentation/devicetree/bindings/sound/tas2770.yaml index 26088adb9dc2..8908bf1122e9 100644 --- a/Documentation/devicetree/bindings/sound/tas2770.yaml +++ b/Documentation/devicetree/bindings/sound/tas2770.yaml @@ -57,7 +57,9 @@ properties: - 1 # Falling edge '#sound-dai-cells': - const: 1 + # The codec has a single DAI, the #sound-dai-cells=<1>; case is left in for backward + # compatibility but is deprecated. + enum: [0, 1] required: - compatible @@ -74,7 +76,7 @@ examples: codec: codec@41 { compatible = "ti,tas2770"; reg = <0x41>; - #sound-dai-cells = <1>; + #sound-dai-cells = <0>; interrupt-parent = <&gpio1>; interrupts = <14>; reset-gpio = <&gpio1 15 0>; diff --git a/Documentation/devicetree/bindings/sound/tas27xx.yaml b/Documentation/devicetree/bindings/sound/tas27xx.yaml index 8cba01316855..a876545ec87d 100644 --- a/Documentation/devicetree/bindings/sound/tas27xx.yaml +++ b/Documentation/devicetree/bindings/sound/tas27xx.yaml @@ -50,7 +50,9 @@ properties: description: TDM TX voltage sense time slot. '#sound-dai-cells': - const: 1 + # The codec has a single DAI, the #sound-dai-cells=<1>; case is left in for backward + # compatibility but is deprecated. + enum: [0, 1] required: - compatible @@ -67,7 +69,7 @@ examples: codec: codec@38 { compatible = "ti,tas2764"; reg = <0x38>; - #sound-dai-cells = <1>; + #sound-dai-cells = <0>; interrupt-parent = <&gpio1>; interrupts = <14>; reset-gpios = <&gpio1 15 0>; diff --git a/Documentation/devicetree/bindings/sound/tlv320aic32x4.txt b/Documentation/devicetree/bindings/sound/tlv320aic32x4.txt index f59125bc79d1..0b4e21bde5bc 100644 --- a/Documentation/devicetree/bindings/sound/tlv320aic32x4.txt +++ b/Documentation/devicetree/bindings/sound/tlv320aic32x4.txt @@ -8,7 +8,7 @@ Required properties: "ti,tlv320aic32x6" TLV320AIC3206, TLV320AIC3256 "ti,tas2505" TAS2505, TAS2521 - reg: I2C slave address - - supply-*: Required supply regulators are: + - *-supply: Required supply regulators are: "iov" - digital IO power supply "ldoin" - LDO power supply "dv" - Digital core power supply diff --git a/Documentation/devicetree/bindings/usb/cdns,usb3.yaml b/Documentation/devicetree/bindings/usb/cdns,usb3.yaml index cae46c4982ad..69a93a0722f0 100644 --- a/Documentation/devicetree/bindings/usb/cdns,usb3.yaml +++ b/Documentation/devicetree/bindings/usb/cdns,usb3.yaml @@ -64,7 +64,7 @@ properties: description: size of memory intended as internal memory for endpoints buffers expressed in KB - $ref: /schemas/types.yaml#/definitions/uint32 + $ref: /schemas/types.yaml#/definitions/uint16 cdns,phyrst-a-enable: description: Enable resetting of PHY if Rx fail is detected diff --git a/Documentation/devicetree/bindings/usb/snps,dwc3.yaml b/Documentation/devicetree/bindings/usb/snps,dwc3.yaml index 50edc4da780e..4f7625955ccc 100644 --- a/Documentation/devicetree/bindings/usb/snps,dwc3.yaml +++ b/Documentation/devicetree/bindings/usb/snps,dwc3.yaml @@ -287,7 +287,7 @@ properties: description: High-Speed PHY interface selection between UTMI+ and ULPI when the DWC_USB3_HSPHY_INTERFACE has value 3. - $ref: /schemas/types.yaml#/definitions/uint8 + $ref: /schemas/types.yaml#/definitions/string enum: [utmi, ulpi] snps,quirk-frame-length-adjustment: diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst index fbb2b5ada95b..eb252fc972aa 100644 --- a/Documentation/filesystems/index.rst +++ b/Documentation/filesystems/index.rst @@ -72,7 +72,6 @@ Documentation for filesystem implementations. befs bfs btrfs - cifs/index ceph coda configfs @@ -111,6 +110,7 @@ Documentation for filesystem implementations. ramfs-rootfs-initramfs relay romfs + smb/index spufs/index squashfs sysfs diff --git a/Documentation/filesystems/ramfs-rootfs-initramfs.rst b/Documentation/filesystems/ramfs-rootfs-initramfs.rst index 164960631925..447f767c6462 100644 --- a/Documentation/filesystems/ramfs-rootfs-initramfs.rst +++ b/Documentation/filesystems/ramfs-rootfs-initramfs.rst @@ -6,8 +6,7 @@ Ramfs, rootfs and initramfs October 17, 2005 -Rob Landley <rob@landley.net> -============================= +:Author: Rob Landley <rob@landley.net> What is ramfs? -------------- diff --git a/Documentation/filesystems/sharedsubtree.rst b/Documentation/filesystems/sharedsubtree.rst index d83395354250..1cf56489ed48 100644 --- a/Documentation/filesystems/sharedsubtree.rst +++ b/Documentation/filesystems/sharedsubtree.rst @@ -147,6 +147,7 @@ replicas continue to be exactly same. 3) Setting mount states +----------------------- The mount command (util-linux package) can be used to set mount states:: @@ -612,6 +613,7 @@ replicas continue to be exactly same. 6) Quiz +------- A. What is the result of the following command sequence? @@ -673,6 +675,7 @@ replicas continue to be exactly same. /mnt/1/test be? 7) FAQ +------ Q1. Why is bind mount needed? How is it different from symbolic links? symbolic links can get stale if the destination mount gets @@ -841,6 +844,7 @@ replicas continue to be exactly same. tmp usr tmp usr tmp usr 8) Implementation +----------------- 8A) Datastructure diff --git a/Documentation/filesystems/cifs/cifsroot.rst b/Documentation/filesystems/smb/cifsroot.rst index 4930bb443134..bf2d9db3acb9 100644 --- a/Documentation/filesystems/cifs/cifsroot.rst +++ b/Documentation/filesystems/smb/cifsroot.rst @@ -59,7 +59,7 @@ the root file system via SMB protocol. Enables the kernel to mount the root file system via SMB that are located in the <server-ip> and <share> specified in this option. -The default mount options are set in fs/cifs/cifsroot.c. +The default mount options are set in fs/smb/client/cifsroot.c. server-ip IPv4 address of the server. diff --git a/Documentation/filesystems/cifs/index.rst b/Documentation/filesystems/smb/index.rst index 1c8597a679ab..1c8597a679ab 100644 --- a/Documentation/filesystems/cifs/index.rst +++ b/Documentation/filesystems/smb/index.rst diff --git a/Documentation/filesystems/cifs/ksmbd.rst b/Documentation/filesystems/smb/ksmbd.rst index 7bed96d794fc..7bed96d794fc 100644 --- a/Documentation/filesystems/cifs/ksmbd.rst +++ b/Documentation/filesystems/smb/ksmbd.rst diff --git a/Documentation/fpga/index.rst b/Documentation/fpga/index.rst index f80f95667ca2..43c968871d99 100644 --- a/Documentation/fpga/index.rst +++ b/Documentation/fpga/index.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 ==== -fpga +FPGA ==== .. toctree:: diff --git a/Documentation/leds/leds-class.rst b/Documentation/leds/leds-class.rst index cd155ead8703..5db620ed27aa 100644 --- a/Documentation/leds/leds-class.rst +++ b/Documentation/leds/leds-class.rst @@ -169,6 +169,87 @@ Setting the brightness to zero with brightness_set() callback function should completely turn off the LED and cancel the previously programmed hardware blinking function, if any. +Hardware driven LEDs +==================== + +Some LEDs can be programmed to be driven by hardware. This is not +limited to blink but also to turn off or on autonomously. +To support this feature, a LED needs to implement various additional +ops and needs to declare specific support for the supported triggers. + +With hw control we refer to the LED driven by hardware. + +LED driver must define the following value to support hw control: + + - hw_control_trigger: + unique trigger name supported by the LED in hw control + mode. + +LED driver must implement the following API to support hw control: + - hw_control_is_supported: + check if the flags passed by the supported trigger can + be parsed and activate hw control on the LED. + + Return 0 if the passed flags mask is supported and + can be set with hw_control_set(). + + If the passed flags mask is not supported -EOPNOTSUPP + must be returned, the LED trigger will use software + fallback in this case. + + Return a negative error in case of any other error like + device not ready or timeouts. + + - hw_control_set: + activate hw control. LED driver will use the provided + flags passed from the supported trigger, parse them to + a set of mode and setup the LED to be driven by hardware + following the requested modes. + + Set LED_OFF via the brightness_set to deactivate hw control. + + Return 0 on success, a negative error number on failing to + apply flags. + + - hw_control_get: + get active modes from a LED already in hw control, parse + them and set in flags the current active flags for the + supported trigger. + + Return 0 on success, a negative error number on failing + parsing the initial mode. + Error from this function is NOT FATAL as the device may + be in a not supported initial state by the attached LED + trigger. + + - hw_control_get_device: + return the device associated with the LED driver in + hw control. A trigger might use this to match the + returned device from this function with a configured + device for the trigger as the source for blinking + events and correctly enable hw control. + (example a netdev trigger configured to blink for a + particular dev match the returned dev from get_device + to set hw control) + + Returns a pointer to a struct device or NULL if nothing + is currently attached. + +LED driver can activate additional modes by default to workaround the +impossibility of supporting each different mode on the supported trigger. +Examples are hardcoding the blink speed to a set interval, enable special +feature like bypassing blink if some requirements are not met. + +A trigger should first check if the hw control API are supported by the LED +driver and check if the trigger is supported to verify if hw control is possible, +use hw_control_is_supported to check if the flags are supported and only at +the end use hw_control_set to activate hw control. + +A trigger can use hw_control_get to check if a LED is already in hw control +and init their flags. + +When the LED is in hw control, no software blink is possible and doing so +will effectively disable hw control. Known Issues ============ diff --git a/Documentation/locking/index.rst b/Documentation/locking/index.rst index 7003bd5aeff4..6a9ea96c8bcb 100644 --- a/Documentation/locking/index.rst +++ b/Documentation/locking/index.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 ======= -locking +Locking ======= .. toctree:: diff --git a/Documentation/mm/page_table_check.rst b/Documentation/mm/page_table_check.rst index cfd8f4117cf3..c12838ce6b8d 100644 --- a/Documentation/mm/page_table_check.rst +++ b/Documentation/mm/page_table_check.rst @@ -52,3 +52,22 @@ Build kernel with: Optionally, build kernel with PAGE_TABLE_CHECK_ENFORCED in order to have page table support without extra kernel parameter. + +Implementation notes +==================== + +We specifically decided not to use VMA information in order to avoid relying on +MM states (except for limited "struct page" info). The page table check is a +separate from Linux-MM state machine that verifies that the user accessible +pages are not falsely shared. + +PAGE_TABLE_CHECK depends on EXCLUSIVE_SYSTEM_RAM. The reason is that without +EXCLUSIVE_SYSTEM_RAM, users are allowed to map arbitrary physical memory +regions into the userspace via /dev/mem. At the same time, pages may change +their properties (e.g., from anonymous pages to named pages) while they are +still being mapped in the userspace, leading to "corruption" detected by the +page table check. + +Even with EXCLUSIVE_SYSTEM_RAM, I/O pages may be still allowed to be mapped via +/dev/mem. However, these pages are always considered as named pages, so they +won't break the logic used in the page table check. diff --git a/Documentation/netlink/genetlink-legacy.yaml b/Documentation/netlink/genetlink-legacy.yaml index b33541a51d6b..ac4350498f5e 100644 --- a/Documentation/netlink/genetlink-legacy.yaml +++ b/Documentation/netlink/genetlink-legacy.yaml @@ -122,6 +122,14 @@ properties: enum: [ u8, u16, u32, u64, s8, s16, s32, s64, string ] len: $ref: '#/$defs/len-or-define' + byte-order: + enum: [ little-endian, big-endian ] + doc: + description: Documentation for the struct member attribute. + type: string + enum: + description: Name of the enum type used for the attribute. + type: string # End genetlink-legacy attribute-sets: diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml index 90641668232e..5d46ca966979 100644 --- a/Documentation/netlink/specs/devlink.yaml +++ b/Documentation/netlink/specs/devlink.yaml @@ -9,6 +9,7 @@ doc: Partial family for Devlink. attribute-sets: - name: devlink + name-prefix: devlink-attr- attributes: - name: bus-name @@ -95,10 +96,12 @@ attribute-sets: - name: reload-action-info type: nest + multi-attr: true nested-attributes: dl-reload-act-info - name: reload-action-stats type: nest + multi-attr: true nested-attributes: dl-reload-act-stats - name: dl-dev-stats @@ -196,3 +199,8 @@ operations: attributes: - bus-name - dev-name + - info-driver-name + - info-serial-number + - info-version-fixed + - info-version-running + - info-version-stored diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 129f413ea349..4846345bade4 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -61,22 +61,6 @@ attribute-sets: nested-attributes: bitset-bits - - name: u64-array - attributes: - - - name: u64 - type: nest - multi-attr: true - nested-attributes: u64 - - - name: s32-array - attributes: - - - name: s32 - type: nest - multi-attr: true - nested-attributes: s32 - - name: string attributes: - @@ -239,7 +223,7 @@ attribute-sets: name: tx-min-frag-size type: u32 - - name: tx-min-frag-size + name: rx-min-frag-size type: u32 - name: verify-enabled @@ -310,7 +294,7 @@ attribute-sets: name: master-slave-state type: u8 - - name: master-slave-lanes + name: lanes type: u32 - name: rate-matching @@ -338,7 +322,7 @@ attribute-sets: name: ext-substate type: u8 - - name: down-cnt + name: ext-down-cnt type: u32 - name: debug @@ -593,7 +577,7 @@ attribute-sets: name: phc-index type: u32 - - name: cable-test-nft-nest-result + name: cable-test-ntf-nest-result attributes: - name: pair @@ -602,7 +586,7 @@ attribute-sets: name: code type: u8 - - name: cable-test-nft-nest-fault-length + name: cable-test-ntf-nest-fault-length attributes: - name: pair @@ -611,16 +595,16 @@ attribute-sets: name: cm type: u32 - - name: cable-test-nft-nest + name: cable-test-ntf-nest attributes: - name: result type: nest - nested-attributes: cable-test-nft-nest-result + nested-attributes: cable-test-ntf-nest-result - name: fault-length type: nest - nested-attributes: cable-test-nft-nest-fault-length + nested-attributes: cable-test-ntf-nest-fault-length - name: cable-test attributes: @@ -634,7 +618,7 @@ attribute-sets: - name: nest type: nest - nested-attributes: cable-test-nft-nest + nested-attributes: cable-test-ntf-nest - name: cable-test-tdr-cfg attributes: @@ -705,16 +689,16 @@ attribute-sets: type: u8 - name: corrected - type: nest - nested-attributes: u64-array + type: binary + sub-type: u64 - name: uncorr - type: nest - nested-attributes: u64-array + type: binary + sub-type: u64 - name: corr-bits - type: nest - nested-attributes: u64-array + type: binary + sub-type: u64 - name: fec attributes: @@ -792,7 +776,7 @@ attribute-sets: name: hist-bkt-hi type: u32 - - name: hist-bkt-val + name: hist-val type: u64 - name: stats @@ -827,8 +811,8 @@ attribute-sets: type: u32 - name: index - type: nest - nested-attributes: s32-array + type: binary + sub-type: s32 - name: module attributes: @@ -981,7 +965,7 @@ operations: - duplex - master-slave-cfg - master-slave-state - - master-slave-lanes + - lanes - rate-matching dump: *linkmodes-get-op - @@ -1015,7 +999,7 @@ operations: - sqi-max - ext-state - ext-substate - - down-cnt + - ext-down-cnt dump: *linkstate-get-op - name: debug-get @@ -1367,7 +1351,7 @@ operations: reply: attributes: - header - - cable-test-nft-nest + - cable-test-ntf-nest - name: cable-test-tdr-act doc: Cable test TDR. @@ -1555,7 +1539,7 @@ operations: - hkey dump: *rss-get-op - - name: plca-get + name: plca-get-cfg doc: Get PLCA params. attribute-set: plca @@ -1577,7 +1561,7 @@ operations: - burst-tmr dump: *plca-get-op - - name: plca-set + name: plca-set-cfg doc: Set PLCA params. attribute-set: plca @@ -1601,7 +1585,7 @@ operations: - name: plca-ntf doc: Notification for change in PLCA params. - notify: plca-get + notify: plca-get-cfg - name: mm-get doc: Get MAC Merge configuration and state diff --git a/Documentation/netlink/specs/ovs_flow.yaml b/Documentation/netlink/specs/ovs_flow.yaml new file mode 100644 index 000000000000..3b0624c87074 --- /dev/null +++ b/Documentation/netlink/specs/ovs_flow.yaml @@ -0,0 +1,831 @@ +# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) + +name: ovs_flow +version: 1 +protocol: genetlink-legacy + +doc: + OVS flow configuration over generic netlink. + +definitions: + - + name: ovs-header + type: struct + doc: | + Header for OVS Generic Netlink messages. + members: + - + name: dp-ifindex + type: u32 + doc: | + ifindex of local port for datapath (0 to make a request not specific + to a datapath). + - + name: ovs-flow-stats + type: struct + members: + - + name: n-packets + type: u64 + doc: Number of matched packets. + - + name: n-bytes + type: u64 + doc: Number of matched bytes. + - + name: ovs-key-mpls + type: struct + members: + - + name: mpls-lse + type: u32 + byte-order: big-endian + - + name: ovs-key-ipv4 + type: struct + members: + - + name: ipv4-src + type: u32 + byte-order: big-endian + - + name: ipv4-dst + type: u32 + byte-order: big-endian + - + name: ipv4-proto + type: u8 + - + name: ipv4-tos + type: u8 + - + name: ipv4-ttl + type: u8 + - + name: ipv4-frag + type: u8 + enum: ovs-frag-type + - + name: ovs-frag-type + type: enum + entries: + - + name: none + doc: Packet is not a fragment. + - + name: first + doc: Packet is a fragment with offset 0. + - + name: later + doc: Packet is a fragment with nonzero offset. + - + name: any + value: 255 + - + name: ovs-key-tcp + type: struct + members: + - + name: tcp-src + type: u16 + byte-order: big-endian + - + name: tcp-dst + type: u16 + byte-order: big-endian + - + name: ovs-key-udp + type: struct + members: + - + name: udp-src + type: u16 + byte-order: big-endian + - + name: udp-dst + type: u16 + byte-order: big-endian + - + name: ovs-key-sctp + type: struct + members: + - + name: sctp-src + type: u16 + byte-order: big-endian + - + name: sctp-dst + type: u16 + byte-order: big-endian + - + name: ovs-key-icmp + type: struct + members: + - + name: icmp-type + type: u8 + - + name: icmp-code + type: u8 + - + name: ovs-key-ct-tuple-ipv4 + type: struct + members: + - + name: ipv4-src + type: u32 + byte-order: big-endian + - + name: ipv4-dst + type: u32 + byte-order: big-endian + - + name: src-port + type: u16 + byte-order: big-endian + - + name: dst-port + type: u16 + byte-order: big-endian + - + name: ipv4-proto + type: u8 + - + name: ovs-action-push-vlan + type: struct + members: + - + name: vlan_tpid + type: u16 + byte-order: big-endian + doc: Tag protocol identifier (TPID) to push. + - + name: vlan_tci + type: u16 + byte-order: big-endian + doc: Tag control identifier (TCI) to push. + - + name: ovs-ufid-flags + type: flags + entries: + - omit-key + - omit-mask + - omit-actions + - + name: ovs-action-hash + type: struct + members: + - + name: hash-algorithm + type: u32 + doc: Algorithm used to compute hash prior to recirculation. + - + name: hash-basis + type: u32 + doc: Basis used for computing hash. + - + name: ovs-hash-alg + type: enum + doc: | + Data path hash algorithm for computing Datapath hash. The algorithm type only specifies + the fields in a flow will be used as part of the hash. Each datapath is free to use its + own hash algorithm. The hash value will be opaque to the user space daemon. + entries: + - ovs-hash-alg-l4 + + - + name: ovs-action-push-mpls + type: struct + members: + - + name: lse + type: u32 + byte-order: big-endian + doc: | + MPLS label stack entry to push + - + name: ethertype + type: u32 + byte-order: big-endian + doc: | + Ethertype to set in the encapsulating ethernet frame. The only values + ethertype should ever be given are ETH_P_MPLS_UC and ETH_P_MPLS_MC, + indicating MPLS unicast or multicast. Other are rejected. + - + name: ovs-action-add-mpls + type: struct + members: + - + name: lse + type: u32 + byte-order: big-endian + doc: | + MPLS label stack entry to push + - + name: ethertype + type: u32 + byte-order: big-endian + doc: | + Ethertype to set in the encapsulating ethernet frame. The only values + ethertype should ever be given are ETH_P_MPLS_UC and ETH_P_MPLS_MC, + indicating MPLS unicast or multicast. Other are rejected. + - + name: tun-flags + type: u16 + doc: | + MPLS tunnel attributes. + - + name: ct-state-flags + type: flags + entries: + - + name: new + doc: Beginning of a new connection. + - + name: established + doc: Part of an existing connenction + - + name: related + doc: Related to an existing connection. + - + name: reply-dir + doc: Flow is in the reply direction. + - + name: invalid + doc: Could not track the connection. + - + name: tracked + doc: Conntrack has occurred. + - + name: src-nat + doc: Packet's source address/port was mangled by NAT. + - + name: dst-nat + doc: Packet's destination address/port was mangled by NAT. + +attribute-sets: + - + name: flow-attrs + attributes: + - + name: key + type: nest + nested-attributes: key-attrs + doc: | + Nested attributes specifying the flow key. Always present in + notifications. Required for all requests (except dumps). + - + name: actions + type: nest + nested-attributes: action-attrs + doc: | + Nested attributes specifying the actions to take for packets that + match the key. Always present in notifications. Required for + OVS_FLOW_CMD_NEW requests, optional for OVS_FLOW_CMD_SET requests. An + OVS_FLOW_CMD_SET without OVS_FLOW_ATTR_ACTIONS will not modify the + actions. To clear the actions, an OVS_FLOW_ATTR_ACTIONS without any + nested attributes must be given. + - + name: stats + type: binary + struct: ovs-flow-stats + doc: | + Statistics for this flow. Present in notifications if the stats would + be nonzero. Ignored in requests. + - + name: tcp-flags + type: u8 + doc: | + An 8-bit value giving the ORed value of all of the TCP flags seen on + packets in this flow. Only present in notifications for TCP flows, and + only if it would be nonzero. Ignored in requests. + - + name: used + type: u64 + doc: | + A 64-bit integer giving the time, in milliseconds on the system + monotonic clock, at which a packet was last processed for this + flow. Only present in notifications if a packet has been processed for + this flow. Ignored in requests. + - + name: clear + type: flag + doc: | + If present in a OVS_FLOW_CMD_SET request, clears the last-used time, + accumulated TCP flags, and statistics for this flow. Otherwise + ignored in requests. Never present in notifications. + - + name: mask + type: nest + nested-attributes: key-attrs + doc: | + Nested attributes specifying the mask bits for wildcarded flow + match. Mask bit value '1' specifies exact match with corresponding + flow key bit, while mask bit value '0' specifies a wildcarded + match. Omitting attribute is treated as wildcarding all corresponding + fields. Optional for all requests. If not present, all flow key bits + are exact match bits. + - + name: probe + type: binary + doc: | + Flow operation is a feature probe, error logging should be suppressed. + - + name: ufid + type: binary + doc: | + A value between 1-16 octets specifying a unique identifier for the + flow. Causes the flow to be indexed by this value rather than the + value of the OVS_FLOW_ATTR_KEY attribute. Optional for all + requests. Present in notifications if the flow was created with this + attribute. + - + name: ufid-flags + type: u32 + enum: ovs-ufid-flags + doc: | + A 32-bit value of ORed flags that provide alternative semantics for + flow installation and retrieval. Optional for all requests. + - + name: pad + type: binary + + - + name: key-attrs + attributes: + - + name: encap + type: nest + nested-attributes: key-attrs + - + name: priority + type: u32 + - + name: in-port + type: u32 + - + name: ethernet + type: binary + doc: struct ovs_key_ethernet + - + name: vlan + type: u16 + byte-order: big-endian + - + name: ethertype + type: u16 + byte-order: big-endian + - + name: ipv4 + type: binary + struct: ovs-key-ipv4 + - + name: ipv6 + type: binary + doc: struct ovs_key_ipv6 + - + name: tcp + type: binary + struct: ovs-key-tcp + - + name: udp + type: binary + struct: ovs-key-udp + - + name: icmp + type: binary + struct: ovs-key-icmp + - + name: icmpv6 + type: binary + struct: ovs-key-icmp + - + name: arp + type: binary + doc: struct ovs_key_arp + - + name: nd + type: binary + doc: struct ovs_key_nd + - + name: skb-mark + type: u32 + - + name: tunnel + type: nest + nested-attributes: tunnel-key-attrs + - + name: sctp + type: binary + struct: ovs-key-sctp + - + name: tcp-flags + type: u16 + byte-order: big-endian + - + name: dp-hash + type: u32 + doc: Value 0 indicates the hash is not computed by the datapath. + - + name: recirc-id + type: u32 + - + name: mpls + type: binary + struct: ovs-key-mpls + - + name: ct-state + type: u32 + enum: ct-state-flags + enum-as-flags: true + - + name: ct-zone + type: u16 + doc: connection tracking zone + - + name: ct-mark + type: u32 + doc: connection tracking mark + - + name: ct-labels + type: binary + doc: 16-octet connection tracking label + - + name: ct-orig-tuple-ipv4 + type: binary + struct: ovs-key-ct-tuple-ipv4 + - + name: ct-orig-tuple-ipv6 + type: binary + doc: struct ovs_key_ct_tuple_ipv6 + - + name: nsh + type: nest + nested-attributes: ovs-nsh-key-attrs + - + name: packet-type + type: u32 + byte-order: big-endian + doc: Should not be sent to the kernel + - + name: nd-extensions + type: binary + doc: Should not be sent to the kernel + - + name: tunnel-info + type: binary + doc: struct ip_tunnel_info + - + name: ipv6-exthdrs + type: binary + doc: struct ovs_key_ipv6_exthdr + - + name: action-attrs + attributes: + - + name: output + type: u32 + doc: ovs port number in datapath + - + name: userspace + type: nest + nested-attributes: userspace-attrs + - + name: set + type: nest + nested-attributes: key-attrs + doc: Replaces the contents of an existing header. The single nested attribute specifies a header to modify and its value. + - + name: push-vlan + type: binary + struct: ovs-action-push-vlan + doc: Push a new outermost 802.1Q or 802.1ad header onto the packet. + - + name: pop-vlan + type: flag + doc: Pop the outermost 802.1Q or 802.1ad header from the packet. + - + name: sample + type: nest + nested-attributes: sample-attrs + doc: | + Probabilistically executes actions, as specified in the nested attributes. + - + name: recirc + type: u32 + doc: recirc id + - + name: hash + type: binary + struct: ovs-action-hash + - + name: push-mpls + type: binary + struct: ovs-action-push-mpls + doc: | + Push a new MPLS label stack entry onto the top of the packets MPLS + label stack. Set the ethertype of the encapsulating frame to either + ETH_P_MPLS_UC or ETH_P_MPLS_MC to indicate the new packet contents. + - + name: pop-mpls + type: u16 + byte-order: big-endian + doc: ethertype + - + name: set-masked + type: nest + nested-attributes: key-attrs + doc: | + Replaces the contents of an existing header. A nested attribute + specifies a header to modify, its value, and a mask. For every bit set + in the mask, the corresponding bit value is copied from the value to + the packet header field, rest of the bits are left unchanged. The + non-masked value bits must be passed in as zeroes. Masking is not + supported for the OVS_KEY_ATTR_TUNNEL attribute. + - + name: ct + type: nest + nested-attributes: ct-attrs + doc: | + Track the connection. Populate the conntrack-related entries + in the flow key. + - + name: trunc + type: u32 + doc: struct ovs_action_trunc is a u32 max length + - + name: push-eth + type: binary + doc: struct ovs_action_push_eth + - + name: pop-eth + type: flag + - + name: ct-clear + type: flag + - + name: push-nsh + type: nest + nested-attributes: ovs-nsh-key-attrs + doc: | + Push NSH header to the packet. + - + name: pop-nsh + type: flag + doc: | + Pop the outermost NSH header off the packet. + - + name: meter + type: u32 + doc: | + Run packet through a meter, which may drop the packet, or modify the + packet (e.g., change the DSCP field) + - + name: clone + type: nest + nested-attributes: action-attrs + doc: | + Make a copy of the packet and execute a list of actions without + affecting the original packet and key. + - + name: check-pkt-len + type: nest + nested-attributes: check-pkt-len-attrs + doc: | + Check the packet length and execute a set of actions if greater than + the specified packet length, else execute another set of actions. + - + name: add-mpls + type: binary + struct: ovs-action-add-mpls + doc: | + Push a new MPLS label stack entry at the start of the packet or at the + start of the l3 header depending on the value of l3 tunnel flag in the + tun_flags field of this OVS_ACTION_ATTR_ADD_MPLS argument. + - + name: dec-ttl + type: nest + nested-attributes: dec-ttl-attrs + - + name: tunnel-key-attrs + attributes: + - + name: id + type: u64 + byte-order: big-endian + value: 0 + - + name: ipv4-src + type: u32 + byte-order: big-endian + - + name: ipv4-dst + type: u32 + byte-order: big-endian + - + name: tos + type: u8 + - + name: ttl + type: u8 + - + name: dont-fragment + type: flag + - + name: csum + type: flag + - + name: oam + type: flag + - + name: geneve-opts + type: binary + sub-type: u32 + - + name: tp-src + type: u16 + byte-order: big-endian + - + name: tp-dst + type: u16 + byte-order: big-endian + - + name: vxlan-opts + type: nest + nested-attributes: vxlan-ext-attrs + - + name: ipv6-src + type: binary + doc: | + struct in6_addr source IPv6 address + - + name: ipv6-dst + type: binary + doc: | + struct in6_addr destination IPv6 address + - + name: pad + type: binary + - + name: erspan-opts + type: binary + doc: | + struct erspan_metadata + - + name: ipv4-info-bridge + type: flag + - + name: check-pkt-len-attrs + attributes: + - + name: pkt-len + type: u16 + - + name: actions-if-greater + type: nest + nested-attributes: action-attrs + - + name: actions-if-less-equal + type: nest + nested-attributes: action-attrs + - + name: sample-attrs + attributes: + - + name: probability + type: u32 + - + name: actions + type: nest + nested-attributes: action-attrs + - + name: userspace-attrs + attributes: + - + name: pid + type: u32 + - + name: userdata + type: binary + - + name: egress-tun-port + type: u32 + - + name: actions + type: flag + - + name: ovs-nsh-key-attrs + attributes: + - + name: base + type: binary + - + name: md1 + type: binary + - + name: md2 + type: binary + - + name: ct-attrs + attributes: + - + name: commit + type: flag + - + name: zone + type: u16 + - + name: mark + type: binary + - + name: labels + type: binary + - + name: helper + type: string + - + name: nat + type: nest + nested-attributes: nat-attrs + - + name: force-commit + type: flag + - + name: eventmask + type: u32 + - + name: timeout + type: string + - + name: nat-attrs + attributes: + - + name: src + type: binary + - + name: dst + type: binary + - + name: ip-min + type: binary + - + name: ip-max + type: binary + - + name: proto-min + type: binary + - + name: proto-max + type: binary + - + name: persistent + type: binary + - + name: proto-hash + type: binary + - + name: proto-random + type: binary + - + name: dec-ttl-attrs + attributes: + - + name: action + type: nest + nested-attributes: action-attrs + - + name: vxlan-ext-attrs + attributes: + - + name: gbp + type: u32 + +operations: + fixed-header: ovs-header + list: + - + name: flow-get + doc: Get / dump OVS flow configuration and state + value: 3 + attribute-set: flow-attrs + do: &flow-get-op + request: + attributes: + - dp-ifindex + - key + - ufid + - ufid-flags + reply: + attributes: + - dp-ifindex + - key + - ufid + - mask + - stats + - actions + dump: *flow-get-op + +mcast-groups: + list: + - + name: ovs_flow diff --git a/Documentation/networking/device_drivers/ethernet/intel/ice.rst b/Documentation/networking/device_drivers/ethernet/intel/ice.rst index 69695e5511f4..e4d065c55ea8 100644 --- a/Documentation/networking/device_drivers/ethernet/intel/ice.rst +++ b/Documentation/networking/device_drivers/ethernet/intel/ice.rst @@ -84,24 +84,6 @@ Once the VM shuts down, or otherwise releases the VF, the command will complete. -Important notes for SR-IOV and Link Aggregation ------------------------------------------------ -Link Aggregation is mutually exclusive with SR-IOV. - -- If Link Aggregation is active, SR-IOV VFs cannot be created on the PF. -- If SR-IOV is active, you cannot set up Link Aggregation on the interface. - -Bridging and MACVLAN are also affected by this. If you wish to use bridging or -MACVLAN with SR-IOV, you must set up bridging or MACVLAN before enabling -SR-IOV. If you are using bridging or MACVLAN in conjunction with SR-IOV, and -you want to remove the interface from the bridge or MACVLAN, you must follow -these steps: - -1. Destroy SR-IOV VFs if they exist -2. Remove the interface from the bridge or MACVLAN -3. Recreate SRIOV VFs as needed - - Additional Features and Configurations ====================================== diff --git a/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst b/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst index 5ba9015336e2..bfd233cfac35 100644 --- a/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst +++ b/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst @@ -13,6 +13,7 @@ Contents - `Drivers`_ - `Basic packet flow`_ - `Devlink health reporters`_ +- `Quality of service`_ Overview ======== @@ -287,3 +288,47 @@ For example:: NIX_AF_ERR: NIX Error Interrupt Reg : 64 Rx on unmapped PF_FUNC + + +Quality of service +================== + + +Hardware algorithms used in scheduling +-------------------------------------- + +octeontx2 silicon and CN10K transmit interface consists of five transmit levels +starting from SMQ/MDQ, TL4 to TL1. Each packet will traverse MDQ, TL4 to TL1 +levels. Each level contains an array of queues to support scheduling and shaping. +The hardware uses the below algorithms depending on the priority of scheduler queues. +once the usercreates tc classes with different priorities, the driver configures +schedulers allocated to the class with specified priority along with rate-limiting +configuration. + +1. Strict Priority + + - Once packets are submitted to MDQ, hardware picks all active MDQs having different priority + using strict priority. + +2. Round Robin + + - Active MDQs having the same priority level are chosen using round robin. + + +Setup HTB offload +----------------- + +1. Enable HW TC offload on the interface:: + + # ethtool -K <interface> hw-tc-offload on + +2. Crate htb root:: + + # tc qdisc add dev <interface> clsact + # tc qdisc replace dev <interface> root handle 1: htb offload + +3. Create tc classes with different priorities:: + + # tc class add dev <interface> parent 1: classid 1:1 htb rate 10Gbit prio 1 + + # tc class add dev <interface> parent 1: classid 1:2 htb rate 10Gbit prio 7 diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/devlink.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/devlink.rst index 3a7a714cc08f..a4edf908b707 100644 --- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/devlink.rst +++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/devlink.rst @@ -40,6 +40,7 @@ flow_steering_mode: Device flow steering mode --------------------------------------------- The flow steering mode parameter controls the flow steering mode of the driver. Two modes are supported: + 1. 'dmfs' - Device managed flow steering. 2. 'smfs' - Software/Driver managed flow steering. @@ -99,6 +100,7 @@ between representors and stacked devices. By default metadata is enabled on the supported devices in E-switch. Metadata is applicable only for E-switch in switchdev mode and users may disable it when NONE of the below use cases will be in use: + 1. HCA is in Dual/multi-port RoCE mode. 2. VF/SF representor bonding (Usually used for Live migration) 3. Stacked devices @@ -180,7 +182,8 @@ User commands examples: $ devlink health diagnose pci/0000:82:00.0 reporter tx -NOTE: This command has valid output only when interface is up, otherwise the command has empty output. +.. note:: + This command has valid output only when interface is up, otherwise the command has empty output. - Show number of tx errors indicated, number of recover flows ended successfully, is autorecover enabled and graceful period from last recover:: @@ -232,8 +235,9 @@ User commands examples: $ devlink health dump show pci/0000:82:00.0 reporter fw -NOTE: This command can run only on the PF which has fw tracer ownership, -running it on other PF or any VF will return "Operation not permitted". +.. note:: + This command can run only on the PF which has fw tracer ownership, + running it on other PF or any VF will return "Operation not permitted". fw fatal reporter ----------------- @@ -256,7 +260,8 @@ User commands examples: $ devlink health dump show pci/0000:82:00.1 reporter fw_fatal -NOTE: This command can run only on PF. +.. note:: + This command can run only on PF. vnic reporter ------------- @@ -265,28 +270,44 @@ It is responsible for querying the vnic diagnostic counters from fw and displayi them in realtime. Description of the vnic counters: -total_q_under_processor_handle: number of queues in an error state due to -an async error or errored command. -send_queue_priority_update_flow: number of QP/SQ priority/SL update -events. -cq_overrun: number of times CQ entered an error state due to an -overflow. -async_eq_overrun: number of times an EQ mapped to async events was -overrun. -comp_eq_overrun: number of times an EQ mapped to completion events was -overrun. -quota_exceeded_command: number of commands issued and failed due to quota -exceeded. -invalid_command: number of commands issued and failed dues to any reason -other than quota exceeded. -nic_receive_steering_discard: number of packets that completed RX flow -steering but were discarded due to a mismatch in flow table. + +- total_q_under_processor_handle + number of queues in an error state due to + an async error or errored command. +- send_queue_priority_update_flow + number of QP/SQ priority/SL update events. +- cq_overrun + number of times CQ entered an error state due to an overflow. +- async_eq_overrun + number of times an EQ mapped to async events was overrun. + comp_eq_overrun number of times an EQ mapped to completion events was + overrun. +- quota_exceeded_command + number of commands issued and failed due to quota exceeded. +- invalid_command + number of commands issued and failed dues to any reason other than quota + exceeded. +- nic_receive_steering_discard + number of packets that completed RX flow + steering but were discarded due to a mismatch in flow table. +- generated_pkt_steering_fail + number of packets generated by the VNIC experiencing unexpected steering + failure (at any point in steering flow). +- handled_pkt_steering_fail + number of packets handled by the VNIC experiencing unexpected steering + failure (at any point in steering flow owned by the VNIC, including the FDB + for the eswitch owner). User commands examples: -- Diagnose PF/VF vnic counters + +- Diagnose PF/VF vnic counters:: + $ devlink health diagnose pci/0000:82:00.1 reporter vnic + - Diagnose representor vnic counters (performed by supplying devlink port of the - representor, which can be obtained via devlink port command) + representor, which can be obtained via devlink port command):: + $ devlink health diagnose pci/0000:82:00.1/65537 reporter vnic -NOTE: This command can run over all interfaces such as PF/VF and representor ports. +.. note:: + This command can run over all interfaces such as PF/VF and representor ports. diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 3f6d3d5f5626..366e2a5097d9 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -1363,8 +1363,8 @@ ping_group_range - 2 INTEGERS Restrict ICMP_PROTO datagram sockets to users in the group range. The default is "1 0", meaning, that nobody (not even root) may create ping sockets. Setting it to "100 100" would grant permissions - to the single group. "0 4294967295" would enable it for the world, "100 - 4294967295" would enable it for the users, but not daemons. + to the single group. "0 4294967294" would enable it for the world, "100 + 4294967294" would enable it for the users, but not daemons. tcp_early_demux - BOOLEAN Enable early demux for established TCP sockets. diff --git a/Documentation/networking/nf_conntrack-sysctl.rst b/Documentation/networking/nf_conntrack-sysctl.rst index 9ca356bc7217..8b1045c3b59e 100644 --- a/Documentation/networking/nf_conntrack-sysctl.rst +++ b/Documentation/networking/nf_conntrack-sysctl.rst @@ -55,7 +55,6 @@ nf_conntrack_frag6_high_thresh - INTEGER nf_conntrack_frag6_low_thresh is reached. nf_conntrack_frag6_low_thresh - INTEGER - (Obsolete since linux-4.17) default 196608 See nf_conntrack_frag6_low_thresh diff --git a/Documentation/pcmcia/index.rst b/Documentation/pcmcia/index.rst index 7ae1f62fca14..8067236c51ab 100644 --- a/Documentation/pcmcia/index.rst +++ b/Documentation/pcmcia/index.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 ====== -pcmcia +PCMCIA ====== .. toctree:: diff --git a/Documentation/process/maintainer-netdev.rst b/Documentation/process/maintainer-netdev.rst index f73ac9e175a8..83614cec9328 100644 --- a/Documentation/process/maintainer-netdev.rst +++ b/Documentation/process/maintainer-netdev.rst @@ -127,13 +127,32 @@ the value of ``Message-ID`` to the URL above. Updating patch status ~~~~~~~~~~~~~~~~~~~~~ -It may be tempting to help the maintainers and update the state of your -own patches when you post a new version or spot a bug. Please **do not** -do that. -Interfering with the patch status on patchwork will only cause confusion. Leave -it to the maintainer to figure out what is the most recent and current -version that should be applied. If there is any doubt, the maintainer -will reply and ask what should be done. +Contributors and reviewers do not have the permissions to update patch +state directly in patchwork. Patchwork doesn't expose much information +about the history of the state of patches, therefore having multiple +people update the state leads to confusion. + +Instead of delegating patchwork permissions netdev uses a simple mail +bot which looks for special commands/lines within the emails sent to +the mailing list. For example to mark a series as Changes Requested +one needs to send the following line anywhere in the email thread:: + + pw-bot: changes-requested + +As a result the bot will set the entire series to Changes Requested. +This may be useful when author discovers a bug in their own series +and wants to prevent it from getting applied. + +The use of the bot is entirely optional, if in doubt ignore its existence +completely. Maintainers will classify and update the state of the patches +themselves. No email should ever be sent to the list with the main purpose +of communicating with the bot, the bot commands should be seen as metadata. + +The use of the bot is restricted to authors of the patches (the ``From:`` +header on patch submission and command must match!), maintainers themselves +and a handful of senior reviewers. Bot records its activity here: + + https://patchwork.hopto.org/pw-bot.html Review timelines ~~~~~~~~~~~~~~~~ diff --git a/Documentation/s390/vfio-ap.rst b/Documentation/s390/vfio-ap.rst index d46e98c7c1ec..bb3f4c4e2885 100644 --- a/Documentation/s390/vfio-ap.rst +++ b/Documentation/s390/vfio-ap.rst @@ -551,7 +551,6 @@ These are the steps: * IOMMU_SUPPORT * S390 * ZCRYPT - * S390_AP_IOMMU * VFIO * KVM diff --git a/Documentation/staging/crc32.rst b/Documentation/staging/crc32.rst index 8a6860f33b4e..7542220967cb 100644 --- a/Documentation/staging/crc32.rst +++ b/Documentation/staging/crc32.rst @@ -1,5 +1,5 @@ ================================= -brief tutorial on CRC computation +Brief tutorial on CRC computation ================================= A CRC is a long-division remainder. You add the CRC to the message, diff --git a/Documentation/timers/index.rst b/Documentation/timers/index.rst index df510ad0c989..983f91f8f023 100644 --- a/Documentation/timers/index.rst +++ b/Documentation/timers/index.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 ====== -timers +Timers ====== .. toctree:: diff --git a/Documentation/trace/histogram.rst b/Documentation/trace/histogram.rst index 479c9eac6335..3c9b263de9c2 100644 --- a/Documentation/trace/histogram.rst +++ b/Documentation/trace/histogram.rst @@ -35,7 +35,7 @@ Documentation written by Tom Zanussi in place of an explicit value field - this is simply a count of event hits. If 'values' isn't specified, an implicit 'hitcount' value will be automatically created and used as the only value. - Keys can be any field, or the special string 'stacktrace', which + Keys can be any field, or the special string 'common_stacktrace', which will use the event's kernel stacktrace as the key. The keywords 'keys' or 'key' can be used to specify keys, and the keywords 'values', 'vals', or 'val' can be used to specify values. Compound @@ -54,7 +54,7 @@ Documentation written by Tom Zanussi 'compatible' if the fields named in the trigger share the same number and type of fields and those fields also have the same names. Note that any two events always share the compatible 'hitcount' and - 'stacktrace' fields and can therefore be combined using those + 'common_stacktrace' fields and can therefore be combined using those fields, however pointless that may be. 'hist' triggers add a 'hist' file to each event's subdirectory. @@ -547,9 +547,9 @@ Extended error information the hist trigger display symbolic call_sites, we can have the hist trigger additionally display the complete set of kernel stack traces that led to each call_site. To do that, we simply use the special - value 'stacktrace' for the key parameter:: + value 'common_stacktrace' for the key parameter:: - # echo 'hist:keys=stacktrace:values=bytes_req,bytes_alloc:sort=bytes_alloc' > \ + # echo 'hist:keys=common_stacktrace:values=bytes_req,bytes_alloc:sort=bytes_alloc' > \ /sys/kernel/tracing/events/kmem/kmalloc/trigger The above trigger will use the kernel stack trace in effect when an @@ -561,9 +561,9 @@ Extended error information every callpath to a kmalloc for a kernel compile):: # cat /sys/kernel/tracing/events/kmem/kmalloc/hist - # trigger info: hist:keys=stacktrace:vals=bytes_req,bytes_alloc:sort=bytes_alloc:size=2048 [active] + # trigger info: hist:keys=common_stacktrace:vals=bytes_req,bytes_alloc:sort=bytes_alloc:size=2048 [active] - { stacktrace: + { common_stacktrace: __kmalloc_track_caller+0x10b/0x1a0 kmemdup+0x20/0x50 hidraw_report_event+0x8a/0x120 [hid] @@ -581,7 +581,7 @@ Extended error information cpu_startup_entry+0x315/0x3e0 rest_init+0x7c/0x80 } hitcount: 3 bytes_req: 21 bytes_alloc: 24 - { stacktrace: + { common_stacktrace: __kmalloc_track_caller+0x10b/0x1a0 kmemdup+0x20/0x50 hidraw_report_event+0x8a/0x120 [hid] @@ -596,7 +596,7 @@ Extended error information do_IRQ+0x5a/0xf0 ret_from_intr+0x0/0x30 } hitcount: 3 bytes_req: 21 bytes_alloc: 24 - { stacktrace: + { common_stacktrace: kmem_cache_alloc_trace+0xeb/0x150 aa_alloc_task_context+0x27/0x40 apparmor_cred_prepare+0x1f/0x50 @@ -608,7 +608,7 @@ Extended error information . . . - { stacktrace: + { common_stacktrace: __kmalloc+0x11b/0x1b0 i915_gem_execbuffer2+0x6c/0x2c0 [i915] drm_ioctl+0x349/0x670 [drm] @@ -616,7 +616,7 @@ Extended error information SyS_ioctl+0x81/0xa0 system_call_fastpath+0x12/0x6a } hitcount: 17726 bytes_req: 13944120 bytes_alloc: 19593808 - { stacktrace: + { common_stacktrace: __kmalloc+0x11b/0x1b0 load_elf_phdrs+0x76/0xa0 load_elf_binary+0x102/0x1650 @@ -625,7 +625,7 @@ Extended error information SyS_execve+0x3a/0x50 return_from_execve+0x0/0x23 } hitcount: 33348 bytes_req: 17152128 bytes_alloc: 20226048 - { stacktrace: + { common_stacktrace: kmem_cache_alloc_trace+0xeb/0x150 apparmor_file_alloc_security+0x27/0x40 security_file_alloc+0x16/0x20 @@ -636,7 +636,7 @@ Extended error information SyS_open+0x1e/0x20 system_call_fastpath+0x12/0x6a } hitcount: 4766422 bytes_req: 9532844 bytes_alloc: 38131376 - { stacktrace: + { common_stacktrace: __kmalloc+0x11b/0x1b0 seq_buf_alloc+0x1b/0x50 seq_read+0x2cc/0x370 @@ -1026,7 +1026,7 @@ Extended error information First we set up an initially paused stacktrace trigger on the netif_receive_skb event:: - # echo 'hist:key=stacktrace:vals=len:pause' > \ + # echo 'hist:key=common_stacktrace:vals=len:pause' > \ /sys/kernel/tracing/events/net/netif_receive_skb/trigger Next, we set up an 'enable_hist' trigger on the sched_process_exec @@ -1060,9 +1060,9 @@ Extended error information $ wget https://www.kernel.org/pub/linux/kernel/v3.x/patch-3.19.xz # cat /sys/kernel/tracing/events/net/netif_receive_skb/hist - # trigger info: hist:keys=stacktrace:vals=len:sort=hitcount:size=2048 [paused] + # trigger info: hist:keys=common_stacktrace:vals=len:sort=hitcount:size=2048 [paused] - { stacktrace: + { common_stacktrace: __netif_receive_skb_core+0x46d/0x990 __netif_receive_skb+0x18/0x60 netif_receive_skb_internal+0x23/0x90 @@ -1079,7 +1079,7 @@ Extended error information kthread+0xd2/0xf0 ret_from_fork+0x42/0x70 } hitcount: 85 len: 28884 - { stacktrace: + { common_stacktrace: __netif_receive_skb_core+0x46d/0x990 __netif_receive_skb+0x18/0x60 netif_receive_skb_internal+0x23/0x90 @@ -1097,7 +1097,7 @@ Extended error information irq_thread+0x11f/0x150 kthread+0xd2/0xf0 } hitcount: 98 len: 664329 - { stacktrace: + { common_stacktrace: __netif_receive_skb_core+0x46d/0x990 __netif_receive_skb+0x18/0x60 process_backlog+0xa8/0x150 @@ -1115,7 +1115,7 @@ Extended error information inet_sendmsg+0x64/0xa0 sock_sendmsg+0x3d/0x50 } hitcount: 115 len: 13030 - { stacktrace: + { common_stacktrace: __netif_receive_skb_core+0x46d/0x990 __netif_receive_skb+0x18/0x60 netif_receive_skb_internal+0x23/0x90 @@ -1142,14 +1142,14 @@ Extended error information into the histogram. In order to avoid having to set everything up again, we can just clear the histogram first:: - # echo 'hist:key=stacktrace:vals=len:clear' >> \ + # echo 'hist:key=common_stacktrace:vals=len:clear' >> \ /sys/kernel/tracing/events/net/netif_receive_skb/trigger Just to verify that it is in fact cleared, here's what we now see in the hist file:: # cat /sys/kernel/tracing/events/net/netif_receive_skb/hist - # trigger info: hist:keys=stacktrace:vals=len:sort=hitcount:size=2048 [paused] + # trigger info: hist:keys=common_stacktrace:vals=len:sort=hitcount:size=2048 [paused] Totals: Hits: 0 @@ -1485,12 +1485,12 @@ Extended error information And here's an example that shows how to combine histogram data from any two events even if they don't share any 'compatible' fields - other than 'hitcount' and 'stacktrace'. These commands create a + other than 'hitcount' and 'common_stacktrace'. These commands create a couple of triggers named 'bar' using those fields:: - # echo 'hist:name=bar:key=stacktrace:val=hitcount' > \ + # echo 'hist:name=bar:key=common_stacktrace:val=hitcount' > \ /sys/kernel/tracing/events/sched/sched_process_fork/trigger - # echo 'hist:name=bar:key=stacktrace:val=hitcount' > \ + # echo 'hist:name=bar:key=common_stacktrace:val=hitcount' > \ /sys/kernel/tracing/events/net/netif_rx/trigger And displaying the output of either shows some interesting if @@ -1501,16 +1501,16 @@ Extended error information # event histogram # - # trigger info: hist:name=bar:keys=stacktrace:vals=hitcount:sort=hitcount:size=2048 [active] + # trigger info: hist:name=bar:keys=common_stacktrace:vals=hitcount:sort=hitcount:size=2048 [active] # - { stacktrace: + { common_stacktrace: kernel_clone+0x18e/0x330 kernel_thread+0x29/0x30 kthreadd+0x154/0x1b0 ret_from_fork+0x3f/0x70 } hitcount: 1 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx_ni+0x20/0x70 dev_loopback_xmit+0xaa/0xd0 @@ -1528,7 +1528,7 @@ Extended error information call_cpuidle+0x3b/0x60 cpu_startup_entry+0x22d/0x310 } hitcount: 1 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx_ni+0x20/0x70 dev_loopback_xmit+0xaa/0xd0 @@ -1543,7 +1543,7 @@ Extended error information SyS_sendto+0xe/0x10 entry_SYSCALL_64_fastpath+0x12/0x6a } hitcount: 2 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx+0x1c/0x60 loopback_xmit+0x6c/0xb0 @@ -1561,7 +1561,7 @@ Extended error information sock_sendmsg+0x38/0x50 ___sys_sendmsg+0x14e/0x270 } hitcount: 76 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx+0x1c/0x60 loopback_xmit+0x6c/0xb0 @@ -1579,7 +1579,7 @@ Extended error information sock_sendmsg+0x38/0x50 ___sys_sendmsg+0x269/0x270 } hitcount: 77 - { stacktrace: + { common_stacktrace: netif_rx_internal+0xb2/0xd0 netif_rx+0x1c/0x60 loopback_xmit+0x6c/0xb0 @@ -1597,7 +1597,7 @@ Extended error information sock_sendmsg+0x38/0x50 SYSC_sendto+0xef/0x170 } hitcount: 88 - { stacktrace: + { common_stacktrace: kernel_clone+0x18e/0x330 SyS_clone+0x19/0x20 entry_SYSCALL_64_fastpath+0x12/0x6a @@ -1949,7 +1949,7 @@ uninterruptible state:: # cd /sys/kernel/tracing # echo 's:block_lat pid_t pid; u64 delta; unsigned long[] stack;' > dynamic_events - # echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=stacktrace if prev_state == 2' >> events/sched/sched_switch/trigger + # echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=common_stacktrace if prev_state == 2' >> events/sched/sched_switch/trigger # echo 'hist:keys=prev_pid:delta=common_timestamp.usecs-$ts,s=$st:onmax($delta).trace(block_lat,prev_pid,$delta,$s)' >> events/sched/sched_switch/trigger # echo 1 > events/synthetic/block_lat/enable # cat trace diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index 176e8fc3f31b..4f7b23faebb9 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -363,7 +363,7 @@ Code Seq# Include File Comments 0xCC 00-0F drivers/misc/ibmvmc.h pseries VMC driver 0xCD 01 linux/reiserfs_fs.h 0xCE 01-02 uapi/linux/cxl_mem.h Compute Express Link Memory Devices -0xCF 02 fs/cifs/ioctl.c +0xCF 02 fs/smb/client/cifs_ioctl.h 0xDB 00-0F drivers/char/mwave/mwavepub.h 0xDD 00-3F ZFCP device driver see drivers/s390/scsi/ <mailto:aherrman@de.ibm.com> diff --git a/Documentation/userspace-api/netlink/intro-specs.rst b/Documentation/userspace-api/netlink/intro-specs.rst index a3b847eafff7..bada89699455 100644 --- a/Documentation/userspace-api/netlink/intro-specs.rst +++ b/Documentation/userspace-api/netlink/intro-specs.rst @@ -78,3 +78,82 @@ to see other examples. The code generation itself is performed by ``tools/net/ynl/ynl-gen-c.py`` but it takes a few arguments so calling it directly for each file quickly becomes tedious. + +YNL lib +======= + +``tools/net/ynl/lib/`` contains an implementation of a C library +(based on libmnl) which integrates with code generated by +``tools/net/ynl/ynl-gen-c.py`` to create easy to use netlink wrappers. + +YNL basics +---------- + +The YNL library consists of two parts - the generic code (functions +prefix by ``ynl_``) and per-family auto-generated code (prefixed +with the name of the family). + +To create a YNL socket call ynl_sock_create() passing the family +struct (family structs are exported by the auto-generated code). +ynl_sock_destroy() closes the socket. + +YNL requests +------------ + +Steps for issuing YNL requests are best explained on an example. +All the functions and types in this example come from the auto-generated +code (for the netdev family in this case): + +.. code-block:: c + + // 0. Request and response pointers + struct netdev_dev_get_req *req; + struct netdev_dev_get_rsp *d; + + // 1. Allocate a request + req = netdev_dev_get_req_alloc(); + // 2. Set request parameters (as needed) + netdev_dev_get_req_set_ifindex(req, ifindex); + + // 3. Issues the request + d = netdev_dev_get(ys, req); + // 4. Free the request arguments + netdev_dev_get_req_free(req); + // 5. Error check (the return value from step 3) + if (!d) { + // 6. Print the YNL-generated error + fprintf(stderr, "YNL: %s\n", ys->err.msg); + return -1; + } + + // ... do stuff with the response @d + + // 7. Free response + netdev_dev_get_rsp_free(d); + +YNL dumps +--------- + +Performing dumps follows similar pattern as requests. +Dumps return a list of objects terminated by a special marker, +or NULL on error. Use ``ynl_dump_foreach()`` to iterate over +the result. + +YNL notifications +----------------- + +YNL lib supports using the same socket for notifications and +requests. In case notifications arrive during processing of a request +they are queued internally and can be retrieved at a later time. + +To subscribed to notifications use ``ynl_subscribe()``. +The notifications have to be read out from the socket, +``ynl_socket_get_fd()`` returns the underlying socket fd which can +be plugged into appropriate asynchronous IO API like ``poll``, +or ``select``. + +Notifications can be retrieved using ``ynl_ntf_dequeue()`` and have +to be freed using ``ynl_ntf_free()``. Since we don't know the notification +type upfront the notifications are returned as ``struct ynl_ntf_base_type *`` +and user is expected to cast them to the appropriate full type based +on the ``cmd`` member. diff --git a/MAINTAINERS b/MAINTAINERS index e2fd64c2ebdc..0971854323a7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -909,13 +909,6 @@ L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/altera/ -ALTERA TSE PCS -M: Maxime Chevallier <maxime.chevallier@bootlin.com> -L: netdev@vger.kernel.org -S: Supported -F: drivers/net/pcs/pcs-altera-tse.c -F: include/linux/pcs-altera-tse.h - ALTERA UART/JTAG UART SERIAL DRIVERS M: Tobias Klauser <tklauser@distanz.ch> L: linux-serial@vger.kernel.org @@ -956,7 +949,8 @@ F: Documentation/networking/device_drivers/ethernet/amazon/ena.rst F: drivers/net/ethernet/amazon/ AMAZON RDMA EFA DRIVER -M: Gal Pressman <galpress@amazon.com> +M: Michael Margolin <mrgolin@amazon.com> +R: Gal Pressman <gal.pressman@linux.dev> R: Yossi Leybovich <sleybo@amazon.com> L: linux-rdma@vger.kernel.org S: Supported @@ -1600,7 +1594,7 @@ F: drivers/media/i2c/ar0521.c ARASAN NAND CONTROLLER DRIVER M: Miquel Raynal <miquel.raynal@bootlin.com> -M: Naga Sureshkumar Relli <nagasure@xilinx.com> +R: Michal Simek <michal.simek@amd.com> L: linux-mtd@lists.infradead.org S: Maintained F: Documentation/devicetree/bindings/mtd/arasan,nand-controller.yaml @@ -1677,10 +1671,7 @@ F: drivers/power/reset/arm-versatile-reboot.c F: drivers/soc/versatile/ ARM KOMEDA DRM-KMS DRIVER -M: James (Qian) Wang <james.qian.wang@arm.com> M: Liviu Dudau <liviu.dudau@arm.com> -M: Mihail Atanassov <mihail.atanassov@arm.com> -L: Mali DP Maintainers <malidp@foss.arm.com> S: Supported T: git git://anongit.freedesktop.org/drm/drm-misc F: Documentation/devicetree/bindings/display/arm,komeda.yaml @@ -1701,8 +1692,6 @@ F: include/uapi/drm/panfrost_drm.h ARM MALI-DP DRM DRIVER M: Liviu Dudau <liviu.dudau@arm.com> -M: Brian Starkey <brian.starkey@arm.com> -L: Mali DP Maintainers <malidp@foss.arm.com> S: Supported T: git git://anongit.freedesktop.org/drm/drm-misc F: Documentation/devicetree/bindings/display/arm,malidp.yaml @@ -1768,7 +1757,7 @@ F: include/linux/amba/mmci.h ARM PRIMECELL PL35X NAND CONTROLLER DRIVER M: Miquel Raynal <miquel.raynal@bootlin.com> -M: Naga Sureshkumar Relli <nagasure@xilinx.com> +R: Michal Simek <michal.simek@amd.com> L: linux-mtd@lists.infradead.org S: Maintained F: Documentation/devicetree/bindings/mtd/arm,pl353-nand-r2p1.yaml @@ -1776,7 +1765,7 @@ F: drivers/mtd/nand/raw/pl35x-nand-controller.c ARM PRIMECELL PL35X SMC DRIVER M: Miquel Raynal <miquel.raynal@bootlin.com> -M: Naga Sureshkumar Relli <nagasure@xilinx.com> +R: Michal Simek <michal.simek@amd.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: Documentation/devicetree/bindings/memory-controllers/arm,pl35x-smc.yaml @@ -1970,7 +1959,7 @@ F: Documentation/devicetree/bindings/nvmem/apple,efuses.yaml F: Documentation/devicetree/bindings/pci/apple,pcie.yaml F: Documentation/devicetree/bindings/pinctrl/apple,pinctrl.yaml F: Documentation/devicetree/bindings/power/apple* -F: Documentation/devicetree/bindings/pwm/pwm-apple.yaml +F: Documentation/devicetree/bindings/pwm/apple,s5l-fpwm.yaml F: Documentation/devicetree/bindings/watchdog/apple,wdt.yaml F: arch/arm64/boot/dts/apple/ F: drivers/bluetooth/hci_bcm4377.c @@ -2434,6 +2423,15 @@ X: drivers/net/wireless/atmel/ N: at91 N: atmel +ARM/MICROCHIP (ARM64) SoC support +M: Conor Dooley <conor@kernel.org> +M: Nicolas Ferre <nicolas.ferre@microchip.com> +M: Claudiu Beznea <claudiu.beznea@microchip.com> +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +S: Supported +T: git https://git.kernel.org/pub/scm/linux/kernel/git/at91/linux.git +F: arch/arm64/boot/dts/microchip/ + ARM/Microchip Sparx5 SoC support M: Lars Povlsen <lars.povlsen@microchip.com> M: Steen Hegelund <Steen.Hegelund@microchip.com> @@ -2441,8 +2439,7 @@ M: Daniel Machon <daniel.machon@microchip.com> M: UNGLinuxDriver@microchip.com L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported -T: git git://github.com/microchip-ung/linux-upstream.git -F: arch/arm64/boot/dts/microchip/ +F: arch/arm64/boot/dts/microchip/sparx* F: drivers/net/ethernet/microchip/vcap/ F: drivers/pinctrl/pinctrl-microchip-sgpio.c N: sparx5 @@ -3541,7 +3538,7 @@ F: Documentation/filesystems/befs.rst F: fs/befs/ BFQ I/O SCHEDULER -M: Paolo Valente <paolo.valente@linaro.org> +M: Paolo Valente <paolo.valente@unimore.it> M: Jens Axboe <axboe@kernel.dk> L: linux-block@vger.kernel.org S: Maintained @@ -4914,7 +4911,6 @@ F: drivers/media/cec/i2c/ch7322.c CIRRUS LOGIC AUDIO CODEC DRIVERS M: James Schulman <james.schulman@cirrus.com> M: David Rhodes <david.rhodes@cirrus.com> -M: Lucas Tanure <tanureal@opensource.cirrus.com> M: Richard Fitzgerald <rf@opensource.cirrus.com> L: alsa-devel@alsa-project.org (moderated for non-subscribers) L: patches@opensource.cirrus.com @@ -5136,7 +5132,7 @@ X: drivers/clk/clkdev.c COMMON INTERNET FILE SYSTEM CLIENT (CIFS and SMB3) M: Steve French <sfrench@samba.org> -R: Paulo Alcantara <pc@cjr.nz> (DFS, global name space) +R: Paulo Alcantara <pc@manguebit.com> (DFS, global name space) R: Ronnie Sahlberg <lsahlber@redhat.com> (directory leases, sparse files) R: Shyam Prasad N <sprasad@microsoft.com> (multichannel) R: Tom Talpey <tom@talpey.com> (RDMA, smbdirect) @@ -5146,8 +5142,8 @@ S: Supported W: https://wiki.samba.org/index.php/LinuxCIFS T: git git://git.samba.org/sfrench/cifs-2.6.git F: Documentation/admin-guide/cifs/ -F: fs/cifs/ -F: fs/smbfs_common/ +F: fs/smb/client/ +F: fs/smb/common/ F: include/uapi/linux/cifs COMPACTPCI HOTPLUG CORE @@ -5725,6 +5721,14 @@ F: include/linux/tfrc.h F: include/uapi/linux/dccp.h F: net/dccp/ +DEBUGOBJECTS: +M: Thomas Gleixner <tglx@linutronix.de> +L: linux-kernel@vger.kernel.org +S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core/debugobjects +F: lib/debugobjects.c +F: include/linux/debugobjects.h + DECSTATION PLATFORM SUPPORT M: "Maciej W. Rozycki" <macro@orcam.me.uk> L: linux-mips@vger.kernel.org @@ -6012,7 +6016,7 @@ W: http://www.dialog-semiconductor.com/products F: Documentation/devicetree/bindings/input/da90??-onkey.txt F: Documentation/devicetree/bindings/input/dlg,da72??.txt F: Documentation/devicetree/bindings/mfd/da90*.txt -F: Documentation/devicetree/bindings/mfd/da90*.yaml +F: Documentation/devicetree/bindings/mfd/dlg,da90*.yaml F: Documentation/devicetree/bindings/regulator/da92*.txt F: Documentation/devicetree/bindings/regulator/dlg,da9*.yaml F: Documentation/devicetree/bindings/regulator/slg51000.txt @@ -6211,6 +6215,7 @@ X: Documentation/devicetree/ X: Documentation/driver-api/media/ X: Documentation/firmware-guide/acpi/ X: Documentation/i2c/ +X: Documentation/netlink/ X: Documentation/power/ X: Documentation/spi/ X: Documentation/userspace-api/media/ @@ -7966,6 +7971,12 @@ S: Maintained F: drivers/hwmon/f75375s.c F: include/linux/f75375s.h +FINTEK F81604 USB to 2xCANBUS DEVICE DRIVER +M: Ji-Ze Hong (Peter Hong) <peter_hong@fintek.com.tw> +L: linux-can@vger.kernel.org +S: Maintained +F: drivers/net/can/usb/f81604.c + FIREWIRE AUDIO DRIVERS and IEC 61883-1/6 PACKET STREAMING ENGINE M: Clemens Ladisch <clemens@ladisch.de> M: Takashi Sakamoto <o-takashi@sakamocchi.jp> @@ -8158,6 +8169,7 @@ F: include/linux/spi/spi-fsl-dspi.h FREESCALE ENETC ETHERNET DRIVERS M: Claudiu Manoil <claudiu.manoil@nxp.com> +M: Vladimir Oltean <vladimir.oltean@nxp.com> L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/freescale/enetc/ @@ -9339,7 +9351,7 @@ F: include/linux/hisi_acc_qm.h HISILICON ROCE DRIVER M: Haoyue Xu <xuhaoyue1@hisilicon.com> -M: Wenpeng Liang <liangwenpeng@huawei.com> +M: Junxian Huang <huangjunxian6@hisilicon.com> L: linux-rdma@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/infiniband/hisilicon-hns-roce.txt @@ -10110,7 +10122,7 @@ S: Maintained F: Documentation/process/kernel-docs.rst INDUSTRY PACK SUBSYSTEM (IPACK) -M: Samuel Iglesias Gonsalvez <siglesias@igalia.com> +M: Vaibhav Gupta <vaibhavgupta40@gmail.com> M: Jens Taprogge <jens.taprogge@taprogge.org> M: Greg Kroah-Hartman <gregkh@linuxfoundation.org> L: industrypack-devel@lists.sourceforge.net @@ -10330,9 +10342,8 @@ M: Jesse Brandeburg <jesse.brandeburg@intel.com> M: Tony Nguyen <anthony.l.nguyen@intel.com> L: intel-wired-lan@lists.osuosl.org (moderated for non-subscribers) S: Supported -W: http://www.intel.com/support/feedback.htm -W: http://e1000.sourceforge.net/ -Q: http://patchwork.ozlabs.org/project/intel-wired-lan/list/ +W: https://www.intel.com/content/www/us/en/support.html +Q: https://patchwork.ozlabs.org/project/intel-wired-lan/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/net-queue.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue.git F: Documentation/networking/device_drivers/ethernet/intel/ @@ -11305,9 +11316,9 @@ R: Tom Talpey <tom@talpey.com> L: linux-cifs@vger.kernel.org S: Maintained T: git git://git.samba.org/ksmbd.git -F: Documentation/filesystems/cifs/ksmbd.rst -F: fs/ksmbd/ -F: fs/smbfs_common/ +F: Documentation/filesystems/smb/ksmbd.rst +F: fs/smb/common/ +F: fs/smb/server/ KERNEL UNIT TESTING FRAMEWORK (KUnit) M: Brendan Higgins <brendanhiggins@google.com> @@ -12834,6 +12845,13 @@ F: Documentation/devicetree/bindings/net/ieee802154/mcr20a.txt F: drivers/net/ieee802154/mcr20a.c F: drivers/net/ieee802154/mcr20a.h +MDIO REGMAP DRIVER +M: Maxime Chevallier <maxime.chevallier@bootlin.com> +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/mdio/mdio-regmap.c +F: include/linux/mdio/mdio-regmap.h + MEASUREMENT COMPUTING CIO-DAC IIO DRIVER M: William Breathitt Gray <william.gray@linaro.org> L: linux-iio@vger.kernel.org @@ -13832,7 +13850,7 @@ F: drivers/tty/serial/8250/8250_pci1xxxx.c MICROCHIP POLARFIRE FPGA DRIVERS M: Conor Dooley <conor.dooley@microchip.com> -R: Ivan Bornyakov <i.bornyakov@metrotek.ru> +R: Vladimir Georgiev <v.georgiev@metrotek.ru> L: linux-fpga@vger.kernel.org S: Supported F: Documentation/devicetree/bindings/fpga/microchip,mpf-spi-fpga-mgr.yaml @@ -14566,6 +14584,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git F: Documentation/devicetree/bindings/net/ F: drivers/connector/ F: drivers/net/ +X: drivers/net/wireless/ F: include/dt-bindings/net/ F: include/linux/etherdevice.h F: include/linux/fcdevice.h @@ -14615,6 +14634,7 @@ B: mailto:netdev@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git F: Documentation/core-api/netlink.rst +F: Documentation/netlink/ F: Documentation/networking/ F: Documentation/process/maintainer-netdev.rst F: Documentation/userspace-api/netlink/ @@ -14629,6 +14649,7 @@ F: include/uapi/linux/netdevice.h F: lib/net_utils.c F: lib/random32.c F: net/ +X: net/bluetooth/ F: tools/net/ F: tools/testing/selftests/net/ @@ -14928,6 +14949,7 @@ F: drivers/ntb/hw/intel/ NTFS FILESYSTEM M: Anton Altaparmakov <anton@tuxera.com> +R: Namjae Jeon <linkinjeon@kernel.org> L: linux-ntfs-dev@lists.sourceforge.net S: Supported W: http://www.tuxera.com/ @@ -18575,10 +18597,9 @@ F: Documentation/admin-guide/LSM/SafeSetID.rst F: security/safesetid/ SAMSUNG AUDIO (ASoC) DRIVERS -M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Sylwester Nawrocki <s.nawrocki@samsung.com> L: alsa-devel@alsa-project.org (moderated for non-subscribers) -S: Supported +S: Maintained B: mailto:linux-samsung-soc@vger.kernel.org F: Documentation/devicetree/bindings/sound/samsung* F: sound/soc/samsung/ @@ -18706,7 +18727,6 @@ F: include/dt-bindings/clock/samsung,*.h F: include/linux/clk/samsung.h SAMSUNG SPI DRIVERS -M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> M: Andi Shyti <andi.shyti@kernel.org> L: linux-spi@vger.kernel.org L: linux-samsung-soc@vger.kernel.org @@ -18842,12 +18862,11 @@ F: drivers/target/ F: include/target/ SCTP PROTOCOL -M: Neil Horman <nhorman@tuxdriver.com> M: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> M: Xin Long <lucien.xin@gmail.com> L: linux-sctp@vger.kernel.org S: Maintained -W: http://lksctp.sourceforge.net +W: https://github.com/sctp/lksctp-tools/wiki F: Documentation/networking/sctp.rst F: include/linux/sctp.h F: include/net/sctp/ @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 4 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc5 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/imx6qdl-mba6.dtsi b/arch/arm/boot/dts/imx6qdl-mba6.dtsi index 78555a618851..7b7e6c2ad190 100644 --- a/arch/arm/boot/dts/imx6qdl-mba6.dtsi +++ b/arch/arm/boot/dts/imx6qdl-mba6.dtsi @@ -209,6 +209,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pcie>; reset-gpio = <&gpio6 7 GPIO_ACTIVE_LOW>; + vpcie-supply = <®_pcie>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6ull-dhcor-som.dtsi b/arch/arm/boot/dts/imx6ull-dhcor-som.dtsi index 5882c7565f64..32a6022625d9 100644 --- a/arch/arm/boot/dts/imx6ull-dhcor-som.dtsi +++ b/arch/arm/boot/dts/imx6ull-dhcor-som.dtsi @@ -8,6 +8,7 @@ #include <dt-bindings/input/input.h> #include <dt-bindings/leds/common.h> #include <dt-bindings/pwm/pwm.h> +#include <dt-bindings/regulator/dlg,da9063-regulator.h> #include "imx6ull.dtsi" / { @@ -84,16 +85,20 @@ regulators { vdd_soc_in_1v4: buck1 { + regulator-allowed-modes = <DA9063_BUCK_MODE_SLEEP>; /* PFM */ regulator-always-on; regulator-boot-on; + regulator-initial-mode = <DA9063_BUCK_MODE_SLEEP>; regulator-max-microvolt = <1400000>; regulator-min-microvolt = <1400000>; regulator-name = "vdd_soc_in_1v4"; }; vcc_3v3: buck2 { + regulator-allowed-modes = <DA9063_BUCK_MODE_SYNC>; /* PWM */ regulator-always-on; regulator-boot-on; + regulator-initial-mode = <DA9063_BUCK_MODE_SYNC>; regulator-max-microvolt = <3300000>; regulator-min-microvolt = <3300000>; regulator-name = "vcc_3v3"; @@ -106,8 +111,10 @@ * the voltage is set to 1.5V. */ vcc_ddr_1v35: buck3 { + regulator-allowed-modes = <DA9063_BUCK_MODE_SYNC>; /* PWM */ regulator-always-on; regulator-boot-on; + regulator-initial-mode = <DA9063_BUCK_MODE_SYNC>; regulator-max-microvolt = <1500000>; regulator-min-microvolt = <1500000>; regulator-name = "vcc_ddr_1v35"; diff --git a/arch/arm/boot/dts/stm32f429.dtsi b/arch/arm/boot/dts/stm32f429.dtsi index c9e05e3540d6..00bf53f99c29 100644 --- a/arch/arm/boot/dts/stm32f429.dtsi +++ b/arch/arm/boot/dts/stm32f429.dtsi @@ -387,6 +387,7 @@ interrupt-names = "tx", "rx0", "rx1", "sce"; resets = <&rcc STM32F4_APB1_RESET(CAN2)>; clocks = <&rcc 0 STM32F4_APB1_CLOCK(CAN2)>; + st,can-secondary; st,gcan = <&gcan>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/stm32f7-pinctrl.dtsi b/arch/arm/boot/dts/stm32f7-pinctrl.dtsi index c8e6c52fb248..9f65403295ca 100644 --- a/arch/arm/boot/dts/stm32f7-pinctrl.dtsi +++ b/arch/arm/boot/dts/stm32f7-pinctrl.dtsi @@ -283,6 +283,88 @@ slew-rate = <2>; }; }; + + can1_pins_a: can1-0 { + pins1 { + pinmux = <STM32_PINMUX('A', 12, AF9)>; /* CAN1_TX */ + }; + pins2 { + pinmux = <STM32_PINMUX('A', 11, AF9)>; /* CAN1_RX */ + bias-pull-up; + }; + }; + + can1_pins_b: can1-1 { + pins1 { + pinmux = <STM32_PINMUX('B', 9, AF9)>; /* CAN1_TX */ + }; + pins2 { + pinmux = <STM32_PINMUX('B', 8, AF9)>; /* CAN1_RX */ + bias-pull-up; + }; + }; + + can1_pins_c: can1-2 { + pins1 { + pinmux = <STM32_PINMUX('D', 1, AF9)>; /* CAN1_TX */ + }; + pins2 { + pinmux = <STM32_PINMUX('D', 0, AF9)>; /* CAN1_RX */ + bias-pull-up; + + }; + }; + + can1_pins_d: can1-3 { + pins1 { + pinmux = <STM32_PINMUX('H', 13, AF9)>; /* CAN1_TX */ + }; + pins2 { + pinmux = <STM32_PINMUX('H', 14, AF9)>; /* CAN1_RX */ + bias-pull-up; + + }; + }; + + can2_pins_a: can2-0 { + pins1 { + pinmux = <STM32_PINMUX('B', 6, AF9)>; /* CAN2_TX */ + }; + pins2 { + pinmux = <STM32_PINMUX('B', 5, AF9)>; /* CAN2_RX */ + bias-pull-up; + }; + }; + + can2_pins_b: can2-1 { + pins1 { + pinmux = <STM32_PINMUX('B', 13, AF9)>; /* CAN2_TX */ + }; + pins2 { + pinmux = <STM32_PINMUX('B', 12, AF9)>; /* CAN2_RX */ + bias-pull-up; + }; + }; + + can3_pins_a: can3-0 { + pins1 { + pinmux = <STM32_PINMUX('A', 15, AF11)>; /* CAN3_TX */ + }; + pins2 { + pinmux = <STM32_PINMUX('A', 8, AF11)>; /* CAN3_RX */ + bias-pull-up; + }; + }; + + can3_pins_b: can3-1 { + pins1 { + pinmux = <STM32_PINMUX('B', 4, AF11)>; /* CAN3_TX */ + }; + pins2 { + pinmux = <STM32_PINMUX('B', 3, AF11)>; /* CAN3_RX */ + bias-pull-up; + }; + }; }; }; }; diff --git a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts index 3b88209bacea..ff1f9a1bcfcf 100644 --- a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts +++ b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts @@ -132,6 +132,7 @@ reg = <0x2c0f0000 0x1000>; interrupts = <0 84 4>; cache-level = <2>; + cache-unified; }; pmu { diff --git a/arch/arm/include/asm/arm_pmuv3.h b/arch/arm/include/asm/arm_pmuv3.h index 78d3d4b82c6c..f4db3e75d75f 100644 --- a/arch/arm/include/asm/arm_pmuv3.h +++ b/arch/arm/include/asm/arm_pmuv3.h @@ -92,7 +92,7 @@ #define RETURN_READ_PMEVCNTRN(n) \ return read_sysreg(PMEVCNTR##n) -static unsigned long read_pmevcntrn(int n) +static inline unsigned long read_pmevcntrn(int n) { PMEVN_SWITCH(n, RETURN_READ_PMEVCNTRN); return 0; @@ -100,14 +100,14 @@ static unsigned long read_pmevcntrn(int n) #define WRITE_PMEVCNTRN(n) \ write_sysreg(val, PMEVCNTR##n) -static void write_pmevcntrn(int n, unsigned long val) +static inline void write_pmevcntrn(int n, unsigned long val) { PMEVN_SWITCH(n, WRITE_PMEVCNTRN); } #define WRITE_PMEVTYPERN(n) \ write_sysreg(val, PMEVTYPER##n) -static void write_pmevtypern(int n, unsigned long val) +static inline void write_pmevtypern(int n, unsigned long val) { PMEVN_SWITCH(n, WRITE_PMEVTYPERN); } diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c index 53be7ea6181b..9d2192156087 100644 --- a/arch/arm/kernel/unwind.c +++ b/arch/arm/kernel/unwind.c @@ -308,6 +308,29 @@ static int unwind_exec_pop_subset_r0_to_r3(struct unwind_ctrl_block *ctrl, return URC_OK; } +static unsigned long unwind_decode_uleb128(struct unwind_ctrl_block *ctrl) +{ + unsigned long bytes = 0; + unsigned long insn; + unsigned long result = 0; + + /* + * unwind_get_byte() will advance `ctrl` one instruction at a time, so + * loop until we get an instruction byte where bit 7 is not set. + * + * Note: This decodes a maximum of 4 bytes to output 28 bits data where + * max is 0xfffffff: that will cover a vsp increment of 1073742336, hence + * it is sufficient for unwinding the stack. + */ + do { + insn = unwind_get_byte(ctrl); + result |= (insn & 0x7f) << (bytes * 7); + bytes++; + } while (!!(insn & 0x80) && (bytes != sizeof(result))); + + return result; +} + /* * Execute the current unwind instruction. */ @@ -361,7 +384,7 @@ static int unwind_exec_insn(struct unwind_ctrl_block *ctrl) if (ret) goto error; } else if (insn == 0xb2) { - unsigned long uleb128 = unwind_get_byte(ctrl); + unsigned long uleb128 = unwind_decode_uleb128(ctrl); ctrl->vrs[SP] += 0x204 + (uleb128 << 2); } else { diff --git a/arch/arm/mach-sa1100/jornada720_ssp.c b/arch/arm/mach-sa1100/jornada720_ssp.c index 67f72ca984b2..1956b095e699 100644 --- a/arch/arm/mach-sa1100/jornada720_ssp.c +++ b/arch/arm/mach-sa1100/jornada720_ssp.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * arch/arm/mac-sa1100/jornada720_ssp.c * * Copyright (C) 2006/2007 Kristoffer Ericson <Kristoffer.Ericson@gmail.com> @@ -26,6 +26,7 @@ static unsigned long jornada_ssp_flags; /** * jornada_ssp_reverse - reverses input byte + * @byte: input byte to reverse * * we need to reverse all data we receive from the mcu due to its physical location * returns : 01110111 -> 11101110 @@ -46,6 +47,7 @@ EXPORT_SYMBOL(jornada_ssp_reverse); /** * jornada_ssp_byte - waits for ready ssp bus and sends byte + * @byte: input byte to transmit * * waits for fifo buffer to clear and then transmits, if it doesn't then we will * timeout after <timeout> rounds. Needs mcu running before its called. @@ -77,6 +79,7 @@ EXPORT_SYMBOL(jornada_ssp_byte); /** * jornada_ssp_inout - decide if input is command or trading byte + * @byte: input byte to send (may be %TXDUMMY) * * returns : (jornada_ssp_byte(byte)) on success * : %-ETIMEDOUT on timeout failure diff --git a/arch/arm/vfp/entry.S b/arch/arm/vfp/entry.S index 7483ef8bccda..62206ef25037 100644 --- a/arch/arm/vfp/entry.S +++ b/arch/arm/vfp/entry.S @@ -23,6 +23,9 @@ @ ENTRY(do_vfp) mov r1, r10 - mov r3, r9 - b vfp_entry + str lr, [sp, #-8]! + add r3, sp, #4 + str r9, [r3] + bl vfp_entry + ldr pc, [sp], #8 ENDPROC(do_vfp) diff --git a/arch/arm/vfp/vfphw.S b/arch/arm/vfp/vfphw.S index 4d8478264d82..a4610d0f3215 100644 --- a/arch/arm/vfp/vfphw.S +++ b/arch/arm/vfp/vfphw.S @@ -172,13 +172,14 @@ vfp_hw_state_valid: @ out before setting an FPEXC that @ stops us reading stuff VFPFMXR FPEXC, r1 @ Restore FPEXC last + mov sp, r3 @ we think we have handled things + pop {lr} sub r2, r2, #4 @ Retry current instruction - if Thumb str r2, [sp, #S_PC] @ mode it's two 16-bit instructions, @ else it's one 32-bit instruction, so @ always subtract 4 from the following @ instruction address. - mov lr, r3 @ we think we have handled things local_bh_enable_and_ret: adr r0, . mov r1, #SOFTIRQ_DISABLE_OFFSET @@ -209,8 +210,9 @@ skip: process_exception: DBGSTR "bounce" + mov sp, r3 @ setup for a return to the user code. + pop {lr} mov r2, sp @ nothing stacked - regdump is at TOS - mov lr, r3 @ setup for a return to the user code. @ Now call the C code to package up the bounce to the support code @ r0 holds the trigger instruction diff --git a/arch/arm64/boot/dts/arm/foundation-v8.dtsi b/arch/arm64/boot/dts/arm/foundation-v8.dtsi index 029578072d8f..7b41537731a6 100644 --- a/arch/arm64/boot/dts/arm/foundation-v8.dtsi +++ b/arch/arm64/boot/dts/arm/foundation-v8.dtsi @@ -59,6 +59,7 @@ L2_0: l2-cache0 { compatible = "cache"; cache-level = <2>; + cache-unified; }; }; diff --git a/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts b/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts index ef68f5aae7dd..afdf954206f1 100644 --- a/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts +++ b/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts @@ -72,6 +72,7 @@ L2_0: l2-cache0 { compatible = "cache"; cache-level = <2>; + cache-unified; }; }; diff --git a/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts b/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts index 796cd7d02eb5..7bdeb965f0a9 100644 --- a/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts +++ b/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts @@ -58,6 +58,7 @@ L2_0: l2-cache0 { compatible = "cache"; cache-level = <2>; + cache-unified; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi index 2209c1ac6e9b..e62a43591361 100644 --- a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi @@ -171,6 +171,7 @@ conn_subsys: bus@5b000000 { interrupt-names = "host", "peripheral", "otg", "wakeup"; phys = <&usb3_phy>; phy-names = "cdns3,usb3-phy"; + cdns,on-chip-buff-size = /bits/ 16 <18>; status = "disabled"; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi index 67072e6c77d5..cbd9d124c80d 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi @@ -98,11 +98,17 @@ #address-cells = <1>; #size-cells = <0>; - ethphy: ethernet-phy@4 { + ethphy: ethernet-phy@4 { /* AR8033 or ADIN1300 */ compatible = "ethernet-phy-ieee802.3-c22"; reg = <4>; reset-gpios = <&gpio1 9 GPIO_ACTIVE_LOW>; reset-assert-us = <10000>; + /* + * Deassert delay: + * ADIN1300 requires 5ms. + * AR8033 requires 1ms. + */ + reset-deassert-us = <20000>; }; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi index bd84db550053..8be8f090e8b8 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi @@ -1069,13 +1069,6 @@ <&clk IMX8MN_CLK_DISP_APB_ROOT>, <&clk IMX8MN_CLK_DISP_AXI_ROOT>; clock-names = "pix", "axi", "disp_axi"; - assigned-clocks = <&clk IMX8MN_CLK_DISP_PIXEL_ROOT>, - <&clk IMX8MN_CLK_DISP_AXI>, - <&clk IMX8MN_CLK_DISP_APB>; - assigned-clock-parents = <&clk IMX8MN_CLK_DISP_PIXEL>, - <&clk IMX8MN_SYS_PLL2_1000M>, - <&clk IMX8MN_SYS_PLL1_800M>; - assigned-clock-rates = <594000000>, <500000000>, <200000000>; interrupts = <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>; power-domains = <&disp_blk_ctrl IMX8MN_DISPBLK_PD_LCDIF>; status = "disabled"; @@ -1093,12 +1086,6 @@ clocks = <&clk IMX8MN_CLK_DSI_CORE>, <&clk IMX8MN_CLK_DSI_PHY_REF>; clock-names = "bus_clk", "sclk_mipi"; - assigned-clocks = <&clk IMX8MN_CLK_DSI_CORE>, - <&clk IMX8MN_CLK_DSI_PHY_REF>; - assigned-clock-parents = <&clk IMX8MN_SYS_PLL1_266M>, - <&clk IMX8MN_CLK_24M>; - assigned-clock-rates = <266000000>, <24000000>; - samsung,pll-clock-frequency = <24000000>; interrupts = <GIC_SPI 18 IRQ_TYPE_LEVEL_HIGH>; power-domains = <&disp_blk_ctrl IMX8MN_DISPBLK_PD_MIPI_DSI>; status = "disabled"; @@ -1142,6 +1129,21 @@ "lcdif-axi", "lcdif-apb", "lcdif-pix", "dsi-pclk", "dsi-ref", "csi-aclk", "csi-pclk"; + assigned-clocks = <&clk IMX8MN_CLK_DSI_CORE>, + <&clk IMX8MN_CLK_DSI_PHY_REF>, + <&clk IMX8MN_CLK_DISP_PIXEL>, + <&clk IMX8MN_CLK_DISP_AXI>, + <&clk IMX8MN_CLK_DISP_APB>; + assigned-clock-parents = <&clk IMX8MN_SYS_PLL1_266M>, + <&clk IMX8MN_CLK_24M>, + <&clk IMX8MN_VIDEO_PLL1_OUT>, + <&clk IMX8MN_SYS_PLL2_1000M>, + <&clk IMX8MN_SYS_PLL1_800M>; + assigned-clock-rates = <266000000>, + <24000000>, + <594000000>, + <500000000>, + <200000000>; #power-domain-cells = <1>; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi index f81391993354..428c60462e3d 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi @@ -1211,13 +1211,6 @@ <&clk IMX8MP_CLK_MEDIA_APB_ROOT>, <&clk IMX8MP_CLK_MEDIA_AXI_ROOT>; clock-names = "pix", "axi", "disp_axi"; - assigned-clocks = <&clk IMX8MP_CLK_MEDIA_DISP1_PIX_ROOT>, - <&clk IMX8MP_CLK_MEDIA_AXI>, - <&clk IMX8MP_CLK_MEDIA_APB>; - assigned-clock-parents = <&clk IMX8MP_CLK_MEDIA_DISP1_PIX>, - <&clk IMX8MP_SYS_PLL2_1000M>, - <&clk IMX8MP_SYS_PLL1_800M>; - assigned-clock-rates = <594000000>, <500000000>, <200000000>; interrupts = <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>; power-domains = <&media_blk_ctrl IMX8MP_MEDIABLK_PD_LCDIF_1>; status = "disabled"; @@ -1237,11 +1230,6 @@ <&clk IMX8MP_CLK_MEDIA_APB_ROOT>, <&clk IMX8MP_CLK_MEDIA_AXI_ROOT>; clock-names = "pix", "axi", "disp_axi"; - assigned-clocks = <&clk IMX8MP_CLK_MEDIA_DISP2_PIX>, - <&clk IMX8MP_VIDEO_PLL1>; - assigned-clock-parents = <&clk IMX8MP_VIDEO_PLL1_OUT>, - <&clk IMX8MP_VIDEO_PLL1_REF_SEL>; - assigned-clock-rates = <0>, <1039500000>; power-domains = <&media_blk_ctrl IMX8MP_MEDIABLK_PD_LCDIF_2>; status = "disabled"; @@ -1296,11 +1284,16 @@ "disp1", "disp2", "isp", "phy"; assigned-clocks = <&clk IMX8MP_CLK_MEDIA_AXI>, - <&clk IMX8MP_CLK_MEDIA_APB>; + <&clk IMX8MP_CLK_MEDIA_APB>, + <&clk IMX8MP_CLK_MEDIA_DISP1_PIX>, + <&clk IMX8MP_CLK_MEDIA_DISP2_PIX>, + <&clk IMX8MP_VIDEO_PLL1>; assigned-clock-parents = <&clk IMX8MP_SYS_PLL2_1000M>, - <&clk IMX8MP_SYS_PLL1_800M>; - assigned-clock-rates = <500000000>, <200000000>; - + <&clk IMX8MP_SYS_PLL1_800M>, + <&clk IMX8MP_VIDEO_PLL1_OUT>, + <&clk IMX8MP_VIDEO_PLL1_OUT>; + assigned-clock-rates = <500000000>, <200000000>, + <0>, <0>, <1039500000>; #power-domain-cells = <1>; lvds_bridge: bridge@5c { diff --git a/arch/arm64/boot/dts/freescale/imx8x-colibri-eval-v3.dtsi b/arch/arm64/boot/dts/freescale/imx8x-colibri-eval-v3.dtsi index 7264d784ae72..9af769ab8ceb 100644 --- a/arch/arm64/boot/dts/freescale/imx8x-colibri-eval-v3.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8x-colibri-eval-v3.dtsi @@ -33,6 +33,12 @@ }; }; +&iomuxc { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_ext_io0>, <&pinctrl_hog0>, <&pinctrl_hog1>, + <&pinctrl_lpspi2_cs2>; +}; + /* Colibri SPI */ &lpspi2 { status = "okay"; diff --git a/arch/arm64/boot/dts/freescale/imx8x-colibri-iris.dtsi b/arch/arm64/boot/dts/freescale/imx8x-colibri-iris.dtsi index 5f30c88855e7..f8953067bc3b 100644 --- a/arch/arm64/boot/dts/freescale/imx8x-colibri-iris.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8x-colibri-iris.dtsi @@ -48,8 +48,7 @@ <IMX8QXP_SAI0_TXFS_LSIO_GPIO0_IO28 0x20>, /* SODIMM 101 */ <IMX8QXP_SAI0_RXD_LSIO_GPIO0_IO27 0x20>, /* SODIMM 97 */ <IMX8QXP_ENET0_RGMII_RXC_LSIO_GPIO5_IO03 0x06000020>, /* SODIMM 85 */ - <IMX8QXP_SAI0_TXC_LSIO_GPIO0_IO26 0x20>, /* SODIMM 79 */ - <IMX8QXP_QSPI0A_DATA1_LSIO_GPIO3_IO10 0x06700041>; /* SODIMM 45 */ + <IMX8QXP_SAI0_TXC_LSIO_GPIO0_IO26 0x20>; /* SODIMM 79 */ }; pinctrl_uart1_forceoff: uart1forceoffgrp { diff --git a/arch/arm64/boot/dts/freescale/imx8x-colibri.dtsi b/arch/arm64/boot/dts/freescale/imx8x-colibri.dtsi index 7cad79102e1a..49d105eb4769 100644 --- a/arch/arm64/boot/dts/freescale/imx8x-colibri.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8x-colibri.dtsi @@ -363,10 +363,6 @@ /* TODO VPU Encoder/Decoder */ &iomuxc { - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_ext_io0>, <&pinctrl_hog0>, <&pinctrl_hog1>, - <&pinctrl_hog2>, <&pinctrl_lpspi2_cs2>; - /* On-module touch pen-down interrupt */ pinctrl_ad7879_int: ad7879intgrp { fsl,pins = <IMX8QXP_MIPI_CSI0_I2C0_SCL_LSIO_GPIO3_IO05 0x21>; @@ -499,8 +495,7 @@ }; pinctrl_hog1: hog1grp { - fsl,pins = <IMX8QXP_CSI_MCLK_LSIO_GPIO3_IO01 0x20>, /* SODIMM 75 */ - <IMX8QXP_QSPI0A_SCLK_LSIO_GPIO3_IO16 0x20>; /* SODIMM 93 */ + fsl,pins = <IMX8QXP_QSPI0A_SCLK_LSIO_GPIO3_IO16 0x20>; /* SODIMM 93 */ }; pinctrl_hog2: hog2grp { @@ -774,3 +769,10 @@ fsl,pins = <IMX8QXP_SCU_BOOT_MODE3_SCU_DSC_RTC_CLOCK_OUTPUT_32K 0x20>; }; }; + +/* Delete peripherals which are not present on SOC, but are defined in imx8-ss-*.dtsi */ + +/delete-node/ &adc1; +/delete-node/ &adc1_lpcg; +/delete-node/ &dsp; +/delete-node/ &dsp_lpcg; diff --git a/arch/arm64/include/asm/arm_pmuv3.h b/arch/arm64/include/asm/arm_pmuv3.h index d6b51deb7bf0..18dc2fb3d7b7 100644 --- a/arch/arm64/include/asm/arm_pmuv3.h +++ b/arch/arm64/include/asm/arm_pmuv3.h @@ -13,7 +13,7 @@ #define RETURN_READ_PMEVCNTRN(n) \ return read_sysreg(pmevcntr##n##_el0) -static unsigned long read_pmevcntrn(int n) +static inline unsigned long read_pmevcntrn(int n) { PMEVN_SWITCH(n, RETURN_READ_PMEVCNTRN); return 0; @@ -21,14 +21,14 @@ static unsigned long read_pmevcntrn(int n) #define WRITE_PMEVCNTRN(n) \ write_sysreg(val, pmevcntr##n##_el0) -static void write_pmevcntrn(int n, unsigned long val) +static inline void write_pmevcntrn(int n, unsigned long val) { PMEVN_SWITCH(n, WRITE_PMEVCNTRN); } #define WRITE_PMEVTYPERN(n) \ write_sysreg(val, pmevtyper##n##_el0) -static void write_pmevtypern(int n, unsigned long val) +static inline void write_pmevtypern(int n, unsigned long val) { PMEVN_SWITCH(n, WRITE_PMEVTYPERN); } diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 683ca3af4084..5f6f84837a49 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -126,6 +126,10 @@ #define APPLE_CPU_PART_M1_FIRESTORM_MAX 0x029 #define APPLE_CPU_PART_M2_BLIZZARD 0x032 #define APPLE_CPU_PART_M2_AVALANCHE 0x033 +#define APPLE_CPU_PART_M2_BLIZZARD_PRO 0x034 +#define APPLE_CPU_PART_M2_AVALANCHE_PRO 0x035 +#define APPLE_CPU_PART_M2_BLIZZARD_MAX 0x038 +#define APPLE_CPU_PART_M2_AVALANCHE_MAX 0x039 #define AMPERE_CPU_PART_AMPERE1 0xAC3 @@ -181,6 +185,10 @@ #define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX) #define MIDR_APPLE_M2_BLIZZARD MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD) #define MIDR_APPLE_M2_AVALANCHE MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE) +#define MIDR_APPLE_M2_BLIZZARD_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_PRO) +#define MIDR_APPLE_M2_AVALANCHE_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_PRO) +#define MIDR_APPLE_M2_BLIZZARD_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_MAX) +#define MIDR_APPLE_M2_AVALANCHE_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_MAX) #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index 4cd6762bda80..93bd0975b15f 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -209,6 +209,7 @@ struct kvm_pgtable_visit_ctx { kvm_pte_t old; void *arg; struct kvm_pgtable_mm_ops *mm_ops; + u64 start; u64 addr; u64 end; u32 level; @@ -631,9 +632,9 @@ int kvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size); * * The walker will walk the page-table entries corresponding to the input * address range specified, visiting entries according to the walker flags. - * Invalid entries are treated as leaf entries. Leaf entries are reloaded - * after invoking the walker callback, allowing the walker to descend into - * a newly installed table. + * Invalid entries are treated as leaf entries. The visited page table entry is + * reloaded after invoking the walker callback, allowing the walker to descend + * into a newly installed table. * * Returning a negative error code from the walker callback function will * terminate the walk immediately with the same error code. diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index e72d9aaab6b1..eefd712f2430 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -115,8 +115,14 @@ #define SB_BARRIER_INSN __SYS_BARRIER_INSN(0, 7, 31) #define SYS_DC_ISW sys_insn(1, 0, 7, 6, 2) +#define SYS_DC_IGSW sys_insn(1, 0, 7, 6, 4) +#define SYS_DC_IGDSW sys_insn(1, 0, 7, 6, 6) #define SYS_DC_CSW sys_insn(1, 0, 7, 10, 2) +#define SYS_DC_CGSW sys_insn(1, 0, 7, 10, 4) +#define SYS_DC_CGDSW sys_insn(1, 0, 7, 10, 6) #define SYS_DC_CISW sys_insn(1, 0, 7, 14, 2) +#define SYS_DC_CIGSW sys_insn(1, 0, 7, 14, 4) +#define SYS_DC_CIGDSW sys_insn(1, 0, 7, 14, 6) /* * Automatically generated definitions for system registers, the diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index f5bcb0dc6267..7e89968bd282 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -66,13 +66,10 @@ void mte_sync_tags(pte_t old_pte, pte_t pte) return; /* if PG_mte_tagged is set, tags have already been initialised */ - for (i = 0; i < nr_pages; i++, page++) { - if (!page_mte_tagged(page)) { + for (i = 0; i < nr_pages; i++, page++) + if (!page_mte_tagged(page)) mte_sync_page_tags(page, old_pte, check_swap, pte_is_tagged); - set_page_mte_tagged(page); - } - } /* ensure the tags are visible before the PTE is set */ smp_wmb(); diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 0119dc91abb5..d9e1355730ef 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -288,7 +288,7 @@ static int aarch32_alloc_kuser_vdso_page(void) memcpy((void *)(vdso_page + 0x1000 - kuser_sz), __kuser_helper_start, kuser_sz); - aarch32_vectors_page = virt_to_page(vdso_page); + aarch32_vectors_page = virt_to_page((void *)vdso_page); return 0; } diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 1279949599b5..4c9dcd8fc939 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -81,26 +81,34 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) fpsimd_kvm_prepare(); + /* + * We will check TIF_FOREIGN_FPSTATE just before entering the + * guest in kvm_arch_vcpu_ctxflush_fp() and override this to + * FP_STATE_FREE if the flag set. + */ vcpu->arch.fp_state = FP_STATE_HOST_OWNED; vcpu_clear_flag(vcpu, HOST_SVE_ENABLED); if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN) vcpu_set_flag(vcpu, HOST_SVE_ENABLED); - /* - * We don't currently support SME guests but if we leave - * things in streaming mode then when the guest starts running - * FPSIMD or SVE code it may generate SME traps so as a - * special case if we are in streaming mode we force the host - * state to be saved now and exit streaming mode so that we - * don't have to handle any SME traps for valid guest - * operations. Do this for ZA as well for now for simplicity. - */ if (system_supports_sme()) { vcpu_clear_flag(vcpu, HOST_SME_ENABLED); if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN) vcpu_set_flag(vcpu, HOST_SME_ENABLED); + /* + * If PSTATE.SM is enabled then save any pending FP + * state and disable PSTATE.SM. If we leave PSTATE.SM + * enabled and the guest does not enable SME via + * CPACR_EL1.SMEN then operations that should be valid + * may generate SME traps from EL1 to EL1 which we + * can't intercept and which would confuse the guest. + * + * Do the same for PSTATE.ZA in the case where there + * is state in the registers which has not already + * been saved, this is very unlikely to happen. + */ if (read_sysreg_s(SYS_SVCR) & (SVCR_SM_MASK | SVCR_ZA_MASK)) { vcpu->arch.fp_state = FP_STATE_FREE; fpsimd_save_and_flush_cpu_state(); diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index c41166f1a1dd..5c15c58f90cc 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -177,9 +177,17 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) sve_guest = vcpu_has_sve(vcpu); esr_ec = kvm_vcpu_trap_get_class(vcpu); - /* Don't handle SVE traps for non-SVE vcpus here: */ - if (!sve_guest && esr_ec != ESR_ELx_EC_FP_ASIMD) + /* Only handle traps the vCPU can support here: */ + switch (esr_ec) { + case ESR_ELx_EC_FP_ASIMD: + break; + case ESR_ELx_EC_SVE: + if (!sve_guest) + return false; + break; + default: return false; + } /* Valid trap. Switch the context: */ @@ -404,17 +412,21 @@ static bool kvm_hyp_handle_cp15_32(struct kvm_vcpu *vcpu, u64 *exit_code) return false; } -static bool kvm_hyp_handle_iabt_low(struct kvm_vcpu *vcpu, u64 *exit_code) +static bool kvm_hyp_handle_memory_fault(struct kvm_vcpu *vcpu, u64 *exit_code) { if (!__populate_fault_info(vcpu)) return true; return false; } +static bool kvm_hyp_handle_iabt_low(struct kvm_vcpu *vcpu, u64 *exit_code) + __alias(kvm_hyp_handle_memory_fault); +static bool kvm_hyp_handle_watchpt_low(struct kvm_vcpu *vcpu, u64 *exit_code) + __alias(kvm_hyp_handle_memory_fault); static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code) { - if (!__populate_fault_info(vcpu)) + if (kvm_hyp_handle_memory_fault(vcpu, exit_code)) return true; if (static_branch_unlikely(&vgic_v2_cpuif_trap)) { diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index 2e9ec4a2a4a3..a8813b212996 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -575,7 +575,7 @@ struct pkvm_mem_donation { struct check_walk_data { enum pkvm_page_state desired; - enum pkvm_page_state (*get_page_state)(kvm_pte_t pte); + enum pkvm_page_state (*get_page_state)(kvm_pte_t pte, u64 addr); }; static int __check_page_state_visitor(const struct kvm_pgtable_visit_ctx *ctx, @@ -583,10 +583,7 @@ static int __check_page_state_visitor(const struct kvm_pgtable_visit_ctx *ctx, { struct check_walk_data *d = ctx->arg; - if (kvm_pte_valid(ctx->old) && !addr_is_allowed_memory(kvm_pte_to_phys(ctx->old))) - return -EINVAL; - - return d->get_page_state(ctx->old) == d->desired ? 0 : -EPERM; + return d->get_page_state(ctx->old, ctx->addr) == d->desired ? 0 : -EPERM; } static int check_page_state_range(struct kvm_pgtable *pgt, u64 addr, u64 size, @@ -601,8 +598,11 @@ static int check_page_state_range(struct kvm_pgtable *pgt, u64 addr, u64 size, return kvm_pgtable_walk(pgt, addr, size, &walker); } -static enum pkvm_page_state host_get_page_state(kvm_pte_t pte) +static enum pkvm_page_state host_get_page_state(kvm_pte_t pte, u64 addr) { + if (!addr_is_allowed_memory(addr)) + return PKVM_NOPAGE; + if (!kvm_pte_valid(pte) && pte) return PKVM_NOPAGE; @@ -709,7 +709,7 @@ static int host_complete_donation(u64 addr, const struct pkvm_mem_transition *tx return host_stage2_set_owner_locked(addr, size, host_id); } -static enum pkvm_page_state hyp_get_page_state(kvm_pte_t pte) +static enum pkvm_page_state hyp_get_page_state(kvm_pte_t pte, u64 addr) { if (!kvm_pte_valid(pte)) return PKVM_NOPAGE; diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 71fa16a0dc77..77791495c995 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -186,6 +186,7 @@ static const exit_handler_fn hyp_exit_handlers[] = { [ESR_ELx_EC_FP_ASIMD] = kvm_hyp_handle_fpsimd, [ESR_ELx_EC_IABT_LOW] = kvm_hyp_handle_iabt_low, [ESR_ELx_EC_DABT_LOW] = kvm_hyp_handle_dabt_low, + [ESR_ELx_EC_WATCHPT_LOW] = kvm_hyp_handle_watchpt_low, [ESR_ELx_EC_PAC] = kvm_hyp_handle_ptrauth, }; @@ -196,6 +197,7 @@ static const exit_handler_fn pvm_exit_handlers[] = { [ESR_ELx_EC_FP_ASIMD] = kvm_hyp_handle_fpsimd, [ESR_ELx_EC_IABT_LOW] = kvm_hyp_handle_iabt_low, [ESR_ELx_EC_DABT_LOW] = kvm_hyp_handle_dabt_low, + [ESR_ELx_EC_WATCHPT_LOW] = kvm_hyp_handle_watchpt_low, [ESR_ELx_EC_PAC] = kvm_hyp_handle_ptrauth, }; diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 3d61bd3e591d..95dae02ccc2e 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -58,8 +58,9 @@ struct kvm_pgtable_walk_data { struct kvm_pgtable_walker *walker; + const u64 start; u64 addr; - u64 end; + const u64 end; }; static bool kvm_phys_is_valid(u64 phys) @@ -201,20 +202,33 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, .old = READ_ONCE(*ptep), .arg = data->walker->arg, .mm_ops = mm_ops, + .start = data->start, .addr = data->addr, .end = data->end, .level = level, .flags = flags, }; int ret = 0; + bool reload = false; kvm_pteref_t childp; bool table = kvm_pte_table(ctx.old, level); - if (table && (ctx.flags & KVM_PGTABLE_WALK_TABLE_PRE)) + if (table && (ctx.flags & KVM_PGTABLE_WALK_TABLE_PRE)) { ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_TABLE_PRE); + reload = true; + } if (!table && (ctx.flags & KVM_PGTABLE_WALK_LEAF)) { ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_LEAF); + reload = true; + } + + /* + * Reload the page table after invoking the walker callback for leaf + * entries or after pre-order traversal, to allow the walker to descend + * into a newly installed or replaced table. + */ + if (reload) { ctx.old = READ_ONCE(*ptep); table = kvm_pte_table(ctx.old, level); } @@ -293,6 +307,7 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size, struct kvm_pgtable_walker *walker) { struct kvm_pgtable_walk_data walk_data = { + .start = ALIGN_DOWN(addr, PAGE_SIZE), .addr = ALIGN_DOWN(addr, PAGE_SIZE), .end = PAGE_ALIGN(walk_data.addr + size), .walker = walker, @@ -349,7 +364,7 @@ int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr, } struct hyp_map_data { - u64 phys; + const u64 phys; kvm_pte_t attr; }; @@ -407,13 +422,12 @@ enum kvm_pgtable_prot kvm_pgtable_hyp_pte_prot(kvm_pte_t pte) static bool hyp_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, struct hyp_map_data *data) { + u64 phys = data->phys + (ctx->addr - ctx->start); kvm_pte_t new; - u64 granule = kvm_granule_size(ctx->level), phys = data->phys; if (!kvm_block_mapping_supported(ctx, phys)) return false; - data->phys += granule; new = kvm_init_valid_leaf_pte(phys, data->attr, ctx->level); if (ctx->old == new) return true; @@ -576,7 +590,7 @@ void kvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt) } struct stage2_map_data { - u64 phys; + const u64 phys; kvm_pte_t attr; u8 owner_id; @@ -794,20 +808,43 @@ static bool stage2_pte_executable(kvm_pte_t pte) return !(pte & KVM_PTE_LEAF_ATTR_HI_S2_XN); } +static u64 stage2_map_walker_phys_addr(const struct kvm_pgtable_visit_ctx *ctx, + const struct stage2_map_data *data) +{ + u64 phys = data->phys; + + /* + * Stage-2 walks to update ownership data are communicated to the map + * walker using an invalid PA. Avoid offsetting an already invalid PA, + * which could overflow and make the address valid again. + */ + if (!kvm_phys_is_valid(phys)) + return phys; + + /* + * Otherwise, work out the correct PA based on how far the walk has + * gotten. + */ + return phys + (ctx->addr - ctx->start); +} + static bool stage2_leaf_mapping_allowed(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { + u64 phys = stage2_map_walker_phys_addr(ctx, data); + if (data->force_pte && (ctx->level < (KVM_PGTABLE_MAX_LEVELS - 1))) return false; - return kvm_block_mapping_supported(ctx, data->phys); + return kvm_block_mapping_supported(ctx, phys); } static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { kvm_pte_t new; - u64 granule = kvm_granule_size(ctx->level), phys = data->phys; + u64 phys = stage2_map_walker_phys_addr(ctx, data); + u64 granule = kvm_granule_size(ctx->level); struct kvm_pgtable *pgt = data->mmu->pgt; struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; @@ -841,8 +878,6 @@ static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, stage2_make_pte(ctx, new); - if (kvm_phys_is_valid(phys)) - data->phys += granule; return 0; } @@ -1297,4 +1332,7 @@ void kvm_pgtable_stage2_free_removed(struct kvm_pgtable_mm_ops *mm_ops, void *pg }; WARN_ON(__kvm_pgtable_walk(&data, mm_ops, ptep, level + 1)); + + WARN_ON(mm_ops->page_count(pgtable) != 1); + mm_ops->put_page(pgtable); } diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 3d868e84c7a0..7a1aa511e7da 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -110,6 +110,7 @@ static const exit_handler_fn hyp_exit_handlers[] = { [ESR_ELx_EC_FP_ASIMD] = kvm_hyp_handle_fpsimd, [ESR_ELx_EC_IABT_LOW] = kvm_hyp_handle_iabt_low, [ESR_ELx_EC_DABT_LOW] = kvm_hyp_handle_dabt_low, + [ESR_ELx_EC_WATCHPT_LOW] = kvm_hyp_handle_watchpt_low, [ESR_ELx_EC_PAC] = kvm_hyp_handle_ptrauth, }; diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c index 64c3aec0d937..0bd93a5f21ce 100644 --- a/arch/arm64/kvm/inject_fault.c +++ b/arch/arm64/kvm/inject_fault.c @@ -204,7 +204,7 @@ void kvm_inject_size_fault(struct kvm_vcpu *vcpu) * Size Fault at level 0, as if exceeding PARange. * * Non-LPAE guests will only get the external abort, as there - * is no way to to describe the ASF. + * is no way to describe the ASF. */ if (vcpu_el1_is_32bit(vcpu) && !(vcpu_read_sys_reg(vcpu, TCR_EL1) & TTBCR_EAE)) diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 45727d50d18d..491ca7eb2a4c 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -694,45 +694,23 @@ out_unlock: static struct arm_pmu *kvm_pmu_probe_armpmu(void) { - struct perf_event_attr attr = { }; - struct perf_event *event; - struct arm_pmu *pmu = NULL; - - /* - * Create a dummy event that only counts user cycles. As we'll never - * leave this function with the event being live, it will never - * count anything. But it allows us to probe some of the PMU - * details. Yes, this is terrible. - */ - attr.type = PERF_TYPE_RAW; - attr.size = sizeof(attr); - attr.pinned = 1; - attr.disabled = 0; - attr.exclude_user = 0; - attr.exclude_kernel = 1; - attr.exclude_hv = 1; - attr.exclude_host = 1; - attr.config = ARMV8_PMUV3_PERFCTR_CPU_CYCLES; - attr.sample_period = GENMASK(63, 0); + struct arm_pmu *tmp, *pmu = NULL; + struct arm_pmu_entry *entry; + int cpu; - event = perf_event_create_kernel_counter(&attr, -1, current, - kvm_pmu_perf_overflow, &attr); + mutex_lock(&arm_pmus_lock); - if (IS_ERR(event)) { - pr_err_once("kvm: pmu event creation failed %ld\n", - PTR_ERR(event)); - return NULL; - } + cpu = smp_processor_id(); + list_for_each_entry(entry, &arm_pmus, entry) { + tmp = entry->arm_pmu; - if (event->pmu) { - pmu = to_arm_pmu(event->pmu); - if (pmu->pmuver == ID_AA64DFR0_EL1_PMUVer_NI || - pmu->pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF) - pmu = NULL; + if (cpumask_test_cpu(cpu, &tmp->supported_cpus)) { + pmu = tmp; + break; + } } - perf_event_disable(event); - perf_event_release_kernel(event); + mutex_unlock(&arm_pmus_lock); return pmu; } @@ -912,7 +890,17 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) return -EBUSY; if (!kvm->arch.arm_pmu) { - /* No PMU set, get the default one */ + /* + * No PMU set, get the default one. + * + * The observant among you will notice that the supported_cpus + * mask does not get updated for the default PMU even though it + * is quite possible the selected instance supports only a + * subset of cores in the system. This is intentional, and + * upholds the preexisting behavior on heterogeneous systems + * where vCPUs can be scheduled on any core but the guest + * counters could stop working. + */ kvm->arch.arm_pmu = kvm_pmu_probe_armpmu(); if (!kvm->arch.arm_pmu) return -ENODEV; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 71b12094d613..753aa7418149 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -211,6 +211,19 @@ static bool access_dcsw(struct kvm_vcpu *vcpu, return true; } +static bool access_dcgsw(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (!kvm_has_mte(vcpu->kvm)) { + kvm_inject_undefined(vcpu); + return false; + } + + /* Treat MTE S/W ops as we treat the classic ones: with contempt */ + return access_dcsw(vcpu, p, r); +} + static void get_access_mask(const struct sys_reg_desc *r, u64 *mask, u64 *shift) { switch (r->aarch32_map) { @@ -1756,8 +1769,14 @@ static bool access_spsr(struct kvm_vcpu *vcpu, */ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_DC_ISW), access_dcsw }, + { SYS_DESC(SYS_DC_IGSW), access_dcgsw }, + { SYS_DESC(SYS_DC_IGDSW), access_dcgsw }, { SYS_DESC(SYS_DC_CSW), access_dcsw }, + { SYS_DESC(SYS_DC_CGSW), access_dcgsw }, + { SYS_DESC(SYS_DC_CGDSW), access_dcgsw }, { SYS_DESC(SYS_DC_CISW), access_dcsw }, + { SYS_DESC(SYS_DC_CIGSW), access_dcgsw }, + { SYS_DESC(SYS_DC_CIGDSW), access_dcgsw }, DBG_BCR_BVR_WCR_WVR_EL1(0), DBG_BCR_BVR_WCR_WVR_EL1(1), diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index 9d42c7cb2b58..6eafc2c45cfc 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -235,9 +235,9 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) * KVM io device for the redistributor that belongs to this VCPU. */ if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { - mutex_lock(&vcpu->kvm->arch.config_lock); + mutex_lock(&vcpu->kvm->slots_lock); ret = vgic_register_redist_iodev(vcpu); - mutex_unlock(&vcpu->kvm->arch.config_lock); + mutex_unlock(&vcpu->kvm->slots_lock); } return ret; } @@ -406,7 +406,7 @@ void kvm_vgic_destroy(struct kvm *kvm) /** * vgic_lazy_init: Lazy init is only allowed if the GIC exposed to the guest - * is a GICv2. A GICv3 must be explicitly initialized by the guest using the + * is a GICv2. A GICv3 must be explicitly initialized by userspace using the * KVM_DEV_ARM_VGIC_GRP_CTRL KVM_DEVICE group. * @kvm: kvm struct pointer */ @@ -446,11 +446,13 @@ int vgic_lazy_init(struct kvm *kvm) int kvm_vgic_map_resources(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; + gpa_t dist_base; int ret = 0; if (likely(vgic_ready(kvm))) return 0; + mutex_lock(&kvm->slots_lock); mutex_lock(&kvm->arch.config_lock); if (vgic_ready(kvm)) goto out; @@ -463,13 +465,26 @@ int kvm_vgic_map_resources(struct kvm *kvm) else ret = vgic_v3_map_resources(kvm); - if (ret) + if (ret) { __kvm_vgic_destroy(kvm); - else - dist->ready = true; + goto out; + } + dist->ready = true; + dist_base = dist->vgic_dist_base; + mutex_unlock(&kvm->arch.config_lock); + + ret = vgic_register_dist_iodev(kvm, dist_base, + kvm_vgic_global_state.type); + if (ret) { + kvm_err("Unable to register VGIC dist MMIO regions\n"); + kvm_vgic_destroy(kvm); + } + mutex_unlock(&kvm->slots_lock); + return ret; out: mutex_unlock(&kvm->arch.config_lock); + mutex_unlock(&kvm->slots_lock); return ret; } diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 750e51e3779a..5fe2365a629f 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -1936,6 +1936,7 @@ void vgic_lpi_translation_cache_destroy(struct kvm *kvm) static int vgic_its_create(struct kvm_device *dev, u32 type) { + int ret; struct vgic_its *its; if (type != KVM_DEV_TYPE_ARM_VGIC_ITS) @@ -1945,9 +1946,12 @@ static int vgic_its_create(struct kvm_device *dev, u32 type) if (!its) return -ENOMEM; + mutex_lock(&dev->kvm->arch.config_lock); + if (vgic_initialized(dev->kvm)) { - int ret = vgic_v4_init(dev->kvm); + ret = vgic_v4_init(dev->kvm); if (ret < 0) { + mutex_unlock(&dev->kvm->arch.config_lock); kfree(its); return ret; } @@ -1960,12 +1964,10 @@ static int vgic_its_create(struct kvm_device *dev, u32 type) /* Yep, even more trickery for lock ordering... */ #ifdef CONFIG_LOCKDEP - mutex_lock(&dev->kvm->arch.config_lock); mutex_lock(&its->cmd_lock); mutex_lock(&its->its_lock); mutex_unlock(&its->its_lock); mutex_unlock(&its->cmd_lock); - mutex_unlock(&dev->kvm->arch.config_lock); #endif its->vgic_its_base = VGIC_ADDR_UNDEF; @@ -1986,7 +1988,11 @@ static int vgic_its_create(struct kvm_device *dev, u32 type) dev->private = its; - return vgic_its_set_abi(its, NR_ITS_ABIS - 1); + ret = vgic_its_set_abi(its, NR_ITS_ABIS - 1); + + mutex_unlock(&dev->kvm->arch.config_lock); + + return ret; } static void vgic_its_destroy(struct kvm_device *kvm_dev) diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c index 35cfa268fd5d..212b73a715c1 100644 --- a/arch/arm64/kvm/vgic/vgic-kvm-device.c +++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c @@ -102,7 +102,11 @@ static int kvm_vgic_addr(struct kvm *kvm, struct kvm_device_attr *attr, bool wri if (get_user(addr, uaddr)) return -EFAULT; - mutex_lock(&kvm->arch.config_lock); + /* + * Since we can't hold config_lock while registering the redistributor + * iodevs, take the slots_lock immediately. + */ + mutex_lock(&kvm->slots_lock); switch (attr->attr) { case KVM_VGIC_V2_ADDR_TYPE_DIST: r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); @@ -182,6 +186,7 @@ static int kvm_vgic_addr(struct kvm *kvm, struct kvm_device_attr *attr, bool wri if (r) goto out; + mutex_lock(&kvm->arch.config_lock); if (write) { r = vgic_check_iorange(kvm, *addr_ptr, addr, alignment, size); if (!r) @@ -189,9 +194,10 @@ static int kvm_vgic_addr(struct kvm *kvm, struct kvm_device_attr *attr, bool wri } else { addr = *addr_ptr; } + mutex_unlock(&kvm->arch.config_lock); out: - mutex_unlock(&kvm->arch.config_lock); + mutex_unlock(&kvm->slots_lock); if (!r && !write) r = put_user(addr, uaddr); diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c index 472b18ac92a2..188d2187eede 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c @@ -769,10 +769,13 @@ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu) struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev; struct vgic_redist_region *rdreg; gpa_t rd_base; - int ret; + int ret = 0; + + lockdep_assert_held(&kvm->slots_lock); + mutex_lock(&kvm->arch.config_lock); if (!IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr)) - return 0; + goto out_unlock; /* * We may be creating VCPUs before having set the base address for the @@ -782,10 +785,12 @@ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu) */ rdreg = vgic_v3_rdist_free_slot(&vgic->rd_regions); if (!rdreg) - return 0; + goto out_unlock; - if (!vgic_v3_check_base(kvm)) - return -EINVAL; + if (!vgic_v3_check_base(kvm)) { + ret = -EINVAL; + goto out_unlock; + } vgic_cpu->rdreg = rdreg; vgic_cpu->rdreg_index = rdreg->free_index; @@ -799,16 +804,20 @@ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu) rd_dev->nr_regions = ARRAY_SIZE(vgic_v3_rd_registers); rd_dev->redist_vcpu = vcpu; - mutex_lock(&kvm->slots_lock); + mutex_unlock(&kvm->arch.config_lock); + ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, rd_base, 2 * SZ_64K, &rd_dev->dev); - mutex_unlock(&kvm->slots_lock); - if (ret) return ret; + /* Protected by slots_lock */ rdreg->free_index++; return 0; + +out_unlock: + mutex_unlock(&kvm->arch.config_lock); + return ret; } static void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu) @@ -834,12 +843,10 @@ static int vgic_register_all_redist_iodevs(struct kvm *kvm) /* The current c failed, so iterate over the previous ones. */ int i; - mutex_lock(&kvm->slots_lock); for (i = 0; i < c; i++) { vcpu = kvm_get_vcpu(kvm, i); vgic_unregister_redist_iodev(vcpu); } - mutex_unlock(&kvm->slots_lock); } return ret; @@ -938,7 +945,9 @@ int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count) { int ret; + mutex_lock(&kvm->arch.config_lock); ret = vgic_v3_alloc_redist_region(kvm, index, addr, count); + mutex_unlock(&kvm->arch.config_lock); if (ret) return ret; @@ -950,8 +959,10 @@ int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count) if (ret) { struct vgic_redist_region *rdreg; + mutex_lock(&kvm->arch.config_lock); rdreg = vgic_v3_rdist_region_from_index(kvm, index); vgic_v3_free_redist_region(rdreg); + mutex_unlock(&kvm->arch.config_lock); return ret; } diff --git a/arch/arm64/kvm/vgic/vgic-mmio.c b/arch/arm64/kvm/vgic/vgic-mmio.c index 1939c94e0b24..ff558c05e990 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio.c +++ b/arch/arm64/kvm/vgic/vgic-mmio.c @@ -1096,7 +1096,6 @@ int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address, enum vgic_type type) { struct vgic_io_device *io_device = &kvm->arch.vgic.dist_iodev; - int ret = 0; unsigned int len; switch (type) { @@ -1114,10 +1113,6 @@ int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address, io_device->iodev_type = IODEV_DIST; io_device->redist_vcpu = NULL; - mutex_lock(&kvm->slots_lock); - ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, dist_base_address, - len, &io_device->dev); - mutex_unlock(&kvm->slots_lock); - - return ret; + return kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, dist_base_address, + len, &io_device->dev); } diff --git a/arch/arm64/kvm/vgic/vgic-v2.c b/arch/arm64/kvm/vgic/vgic-v2.c index 645648349c99..7e9cdb78f7ce 100644 --- a/arch/arm64/kvm/vgic/vgic-v2.c +++ b/arch/arm64/kvm/vgic/vgic-v2.c @@ -312,12 +312,6 @@ int vgic_v2_map_resources(struct kvm *kvm) return ret; } - ret = vgic_register_dist_iodev(kvm, dist->vgic_dist_base, VGIC_V2); - if (ret) { - kvm_err("Unable to register VGIC MMIO regions\n"); - return ret; - } - if (!static_branch_unlikely(&vgic_v2_cpuif_trap)) { ret = kvm_phys_addr_ioremap(kvm, dist->vgic_cpu_base, kvm_vgic_global_state.vcpu_base, diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 469d816f356f..c3b8e132d599 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -539,7 +539,6 @@ int vgic_v3_map_resources(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; - int ret = 0; unsigned long c; kvm_for_each_vcpu(c, vcpu, kvm) { @@ -569,12 +568,6 @@ int vgic_v3_map_resources(struct kvm *kvm) return -EBUSY; } - ret = vgic_register_dist_iodev(kvm, dist->vgic_dist_base, VGIC_V3); - if (ret) { - kvm_err("Unable to register VGICv3 dist MMIO regions\n"); - return ret; - } - if (kvm_vgic_global_state.has_gicv4_1) vgic_v4_configure_vsgis(kvm); @@ -616,6 +609,10 @@ static const struct midr_range broken_seis[] = { MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_MAX), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_PRO), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_PRO), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_MAX), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_MAX), {}, }; diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c index 3bb003478060..c1c28fe680ba 100644 --- a/arch/arm64/kvm/vgic/vgic-v4.c +++ b/arch/arm64/kvm/vgic/vgic-v4.c @@ -184,13 +184,14 @@ static void vgic_v4_disable_vsgis(struct kvm_vcpu *vcpu) } } -/* Must be called with the kvm lock held */ void vgic_v4_configure_vsgis(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; unsigned long i; + lockdep_assert_held(&kvm->arch.config_lock); + kvm_arm_halt_guest(kvm); kvm_for_each_vcpu(i, vcpu, kvm) { diff --git a/arch/arm64/kvm/vmid.c b/arch/arm64/kvm/vmid.c index 08978d0672e7..7fe8ba1a2851 100644 --- a/arch/arm64/kvm/vmid.c +++ b/arch/arm64/kvm/vmid.c @@ -47,7 +47,7 @@ static void flush_context(void) int cpu; u64 vmid; - bitmap_clear(vmid_map, 0, NUM_USER_VMIDS); + bitmap_zero(vmid_map, NUM_USER_VMIDS); for_each_possible_cpu(cpu) { vmid = atomic64_xchg_relaxed(&per_cpu(active_vmids, cpu), 0); @@ -182,8 +182,7 @@ int __init kvm_arm_vmid_alloc_init(void) */ WARN_ON(NUM_USER_VMIDS - 1 <= num_possible_cpus()); atomic64_set(&vmid_generation, VMID_FIRST_VERSION); - vmid_map = kcalloc(BITS_TO_LONGS(NUM_USER_VMIDS), - sizeof(*vmid_map), GFP_KERNEL); + vmid_map = bitmap_zalloc(NUM_USER_VMIDS, GFP_KERNEL); if (!vmid_map) return -ENOMEM; @@ -192,5 +191,5 @@ int __init kvm_arm_vmid_alloc_init(void) void __init kvm_arm_vmid_alloc_free(void) { - kfree(vmid_map); + bitmap_free(vmid_map); } diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c index 4aadcfb01754..a7bb20055ce0 100644 --- a/arch/arm64/mm/copypage.c +++ b/arch/arm64/mm/copypage.c @@ -21,9 +21,10 @@ void copy_highpage(struct page *to, struct page *from) copy_page(kto, kfrom); + if (kasan_hw_tags_enabled()) + page_kasan_tag_reset(to); + if (system_supports_mte() && page_mte_tagged(from)) { - if (kasan_hw_tags_enabled()) - page_kasan_tag_reset(to); /* It's a new page, shouldn't have been tagged yet */ WARN_ON_ONCE(!try_page_mte_tagging(to)); mte_copy_page_tags(kto, kfrom); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 9e0db5c387e3..cb21ccd7940d 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -480,8 +480,8 @@ static void do_bad_area(unsigned long far, unsigned long esr, } } -#define VM_FAULT_BADMAP 0x010000 -#define VM_FAULT_BADACCESS 0x020000 +#define VM_FAULT_BADMAP ((__force vm_fault_t)0x010000) +#define VM_FAULT_BADACCESS ((__force vm_fault_t)0x020000) static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int mm_flags, unsigned long vm_flags, diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index b26da8efa616..145b540ec34f 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -1731,21 +1731,21 @@ static void invoke_bpf_mod_ret(struct jit_ctx *ctx, struct bpf_tramp_links *tl, } } -static void save_args(struct jit_ctx *ctx, int args_off, int nargs) +static void save_args(struct jit_ctx *ctx, int args_off, int nregs) { int i; - for (i = 0; i < nargs; i++) { + for (i = 0; i < nregs; i++) { emit(A64_STR64I(i, A64_SP, args_off), ctx); args_off += 8; } } -static void restore_args(struct jit_ctx *ctx, int args_off, int nargs) +static void restore_args(struct jit_ctx *ctx, int args_off, int nregs) { int i; - for (i = 0; i < nargs; i++) { + for (i = 0; i < nregs; i++) { emit(A64_LDR64I(i, A64_SP, args_off), ctx); args_off += 8; } @@ -1764,7 +1764,7 @@ static void restore_args(struct jit_ctx *ctx, int args_off, int nargs) */ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, struct bpf_tramp_links *tlinks, void *orig_call, - int nargs, u32 flags) + int nregs, u32 flags) { int i; int stack_size; @@ -1772,7 +1772,7 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, int regs_off; int retval_off; int args_off; - int nargs_off; + int nregs_off; int ip_off; int run_ctx_off; struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY]; @@ -1795,11 +1795,11 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, * SP + retval_off [ return value ] BPF_TRAMP_F_CALL_ORIG or * BPF_TRAMP_F_RET_FENTRY_RET * - * [ argN ] + * [ arg reg N ] * [ ... ] - * SP + args_off [ arg1 ] + * SP + args_off [ arg reg 1 ] * - * SP + nargs_off [ args count ] + * SP + nregs_off [ arg regs count ] * * SP + ip_off [ traced function ] BPF_TRAMP_F_IP_ARG flag * @@ -1816,13 +1816,13 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, if (flags & BPF_TRAMP_F_IP_ARG) stack_size += 8; - nargs_off = stack_size; + nregs_off = stack_size; /* room for args count */ stack_size += 8; args_off = stack_size; /* room for args */ - stack_size += nargs * 8; + stack_size += nregs * 8; /* room for return value */ retval_off = stack_size; @@ -1865,12 +1865,12 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, emit(A64_STR64I(A64_R(10), A64_SP, ip_off), ctx); } - /* save args count*/ - emit(A64_MOVZ(1, A64_R(10), nargs, 0), ctx); - emit(A64_STR64I(A64_R(10), A64_SP, nargs_off), ctx); + /* save arg regs count*/ + emit(A64_MOVZ(1, A64_R(10), nregs, 0), ctx); + emit(A64_STR64I(A64_R(10), A64_SP, nregs_off), ctx); - /* save args */ - save_args(ctx, args_off, nargs); + /* save arg regs */ + save_args(ctx, args_off, nregs); /* save callee saved registers */ emit(A64_STR64I(A64_R(19), A64_SP, regs_off), ctx); @@ -1897,7 +1897,7 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, } if (flags & BPF_TRAMP_F_CALL_ORIG) { - restore_args(ctx, args_off, nargs); + restore_args(ctx, args_off, nregs); /* call original func */ emit(A64_LDR64I(A64_R(10), A64_SP, retaddr_off), ctx); emit(A64_ADR(A64_LR, AARCH64_INSN_SIZE * 2), ctx); @@ -1926,7 +1926,7 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, } if (flags & BPF_TRAMP_F_RESTORE_REGS) - restore_args(ctx, args_off, nargs); + restore_args(ctx, args_off, nregs); /* restore callee saved register x19 and x20 */ emit(A64_LDR64I(A64_R(19), A64_SP, regs_off), ctx); @@ -1967,24 +1967,25 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *orig_call) { int i, ret; - int nargs = m->nr_args; + int nregs = m->nr_args; int max_insns = ((long)image_end - (long)image) / AARCH64_INSN_SIZE; struct jit_ctx ctx = { .image = NULL, .idx = 0, }; - /* the first 8 arguments are passed by registers */ - if (nargs > 8) - return -ENOTSUPP; - - /* don't support struct argument */ + /* extra registers needed for struct argument */ for (i = 0; i < MAX_BPF_FUNC_ARGS; i++) { + /* The arg_size is at most 16 bytes, enforced by the verifier. */ if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG) - return -ENOTSUPP; + nregs += (m->arg_size[i] + 7) / 8 - 1; } - ret = prepare_trampoline(&ctx, im, tlinks, orig_call, nargs, flags); + /* the first 8 registers are used for arguments */ + if (nregs > 8) + return -ENOTSUPP; + + ret = prepare_trampoline(&ctx, im, tlinks, orig_call, nregs, flags); if (ret < 0) return ret; @@ -1995,7 +1996,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, ctx.idx = 0; jit_fill_hole(image, (unsigned int)(image_end - image)); - ret = prepare_trampoline(&ctx, im, tlinks, orig_call, nargs, flags); + ret = prepare_trampoline(&ctx, im, tlinks, orig_call, nregs, flags); if (ret > 0 && validate_code(&ctx) < 0) ret = -EINVAL; diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c index b9f6908a31bc..ba468b5f3f0b 100644 --- a/arch/m68k/kernel/signal.c +++ b/arch/m68k/kernel/signal.c @@ -858,11 +858,17 @@ static inline int rt_setup_ucontext(struct ucontext __user *uc, struct pt_regs * } static inline void __user * -get_sigframe(struct ksignal *ksig, size_t frame_size) +get_sigframe(struct ksignal *ksig, struct pt_regs *tregs, size_t frame_size) { unsigned long usp = sigsp(rdusp(), ksig); + unsigned long gap = 0; - return (void __user *)((usp - frame_size) & -8UL); + if (CPU_IS_020_OR_030 && tregs->format == 0xb) { + /* USP is unreliable so use worst-case value */ + gap = 256; + } + + return (void __user *)((usp - gap - frame_size) & -8UL); } static int setup_frame(struct ksignal *ksig, sigset_t *set, @@ -880,7 +886,7 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set, return -EFAULT; } - frame = get_sigframe(ksig, sizeof(*frame) + fsize); + frame = get_sigframe(ksig, tregs, sizeof(*frame) + fsize); if (fsize) err |= copy_to_user (frame + 1, regs + 1, fsize); @@ -952,7 +958,7 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, return -EFAULT; } - frame = get_sigframe(ksig, sizeof(*frame)); + frame = get_sigframe(ksig, tregs, sizeof(*frame)); if (fsize) err |= copy_to_user (&frame->uc.uc_extra, regs + 1, fsize); diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index c2f5498d207f..675a8660cb85 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -79,6 +79,7 @@ config MIPS select HAVE_LD_DEAD_CODE_DATA_ELIMINATION select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI + select HAVE_PATA_PLATFORM select HAVE_PERF_EVENTS select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP diff --git a/arch/mips/alchemy/common/dbdma.c b/arch/mips/alchemy/common/dbdma.c index 5ab043000409..6a3c890f7bbf 100644 --- a/arch/mips/alchemy/common/dbdma.c +++ b/arch/mips/alchemy/common/dbdma.c @@ -30,6 +30,7 @@ * */ +#include <linux/dma-map-ops.h> /* for dma_default_coherent */ #include <linux/init.h> #include <linux/kernel.h> #include <linux/slab.h> @@ -623,17 +624,18 @@ u32 au1xxx_dbdma_put_source(u32 chanid, dma_addr_t buf, int nbytes, u32 flags) dp->dscr_cmd0 &= ~DSCR_CMD0_IE; /* - * There is an errata on the Au1200/Au1550 parts that could result - * in "stale" data being DMA'ed. It has to do with the snoop logic on - * the cache eviction buffer. DMA_NONCOHERENT is on by default for - * these parts. If it is fixed in the future, these dma_cache_inv will - * just be nothing more than empty macros. See io.h. + * There is an erratum on certain Au1200/Au1550 revisions that could + * result in "stale" data being DMA'ed. It has to do with the snoop + * logic on the cache eviction buffer. dma_default_coherent is set + * to false on these parts. */ - dma_cache_wback_inv((unsigned long)buf, nbytes); + if (!dma_default_coherent) + dma_cache_wback_inv(KSEG0ADDR(buf), nbytes); dp->dscr_cmd0 |= DSCR_CMD0_V; /* Let it rip */ wmb(); /* drain writebuffer */ dma_cache_wback_inv((unsigned long)dp, sizeof(*dp)); ctp->chan_ptr->ddma_dbell = 0; + wmb(); /* force doorbell write out to dma engine */ /* Get next descriptor pointer. */ ctp->put_ptr = phys_to_virt(DSCR_GET_NXTPTR(dp->dscr_nxtptr)); @@ -685,17 +687,18 @@ u32 au1xxx_dbdma_put_dest(u32 chanid, dma_addr_t buf, int nbytes, u32 flags) dp->dscr_source1, dp->dscr_dest0, dp->dscr_dest1); #endif /* - * There is an errata on the Au1200/Au1550 parts that could result in - * "stale" data being DMA'ed. It has to do with the snoop logic on the - * cache eviction buffer. DMA_NONCOHERENT is on by default for these - * parts. If it is fixed in the future, these dma_cache_inv will just - * be nothing more than empty macros. See io.h. + * There is an erratum on certain Au1200/Au1550 revisions that could + * result in "stale" data being DMA'ed. It has to do with the snoop + * logic on the cache eviction buffer. dma_default_coherent is set + * to false on these parts. */ - dma_cache_inv((unsigned long)buf, nbytes); + if (!dma_default_coherent) + dma_cache_inv(KSEG0ADDR(buf), nbytes); dp->dscr_cmd0 |= DSCR_CMD0_V; /* Let it rip */ wmb(); /* drain writebuffer */ dma_cache_wback_inv((unsigned long)dp, sizeof(*dp)); ctp->chan_ptr->ddma_dbell = 0; + wmb(); /* force doorbell write out to dma engine */ /* Get next descriptor pointer. */ ctp->put_ptr = phys_to_virt(DSCR_GET_NXTPTR(dp->dscr_nxtptr)); diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index 6d15a398d389..e79adcb128e6 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -1502,6 +1502,10 @@ static inline void cpu_probe_alchemy(struct cpuinfo_mips *c, unsigned int cpu) break; } break; + case PRID_IMP_NETLOGIC_AU13XX: + c->cputype = CPU_ALCHEMY; + __cpu_name[cpu] = "Au1300"; + break; } } @@ -1863,6 +1867,7 @@ void cpu_probe(void) cpu_probe_mips(c, cpu); break; case PRID_COMP_ALCHEMY: + case PRID_COMP_NETLOGIC: cpu_probe_alchemy(c, cpu); break; case PRID_COMP_SIBYTE: diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index febdc5564638..c0e65135481b 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -158,10 +158,6 @@ static unsigned long __init init_initrd(void) pr_err("initrd start must be page aligned\n"); goto disable; } - if (initrd_start < PAGE_OFFSET) { - pr_err("initrd start < PAGE_OFFSET\n"); - goto disable; - } /* * Sanitize initrd addresses. For example firmware @@ -174,6 +170,11 @@ static unsigned long __init init_initrd(void) initrd_end = (unsigned long)__va(end); initrd_start = (unsigned long)__va(__pa(initrd_start)); + if (initrd_start < PAGE_OFFSET) { + pr_err("initrd start < PAGE_OFFSET\n"); + goto disable; + } + ROOT_DEV = Root_RAM0; return PFN_UP(end); disable: diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 466a25525364..967bde65dd0e 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -130,6 +130,10 @@ config PM config STACKTRACE_SUPPORT def_bool y +config LOCKDEP_SUPPORT + bool + default y + config ISA_DMA_API bool diff --git a/arch/parisc/Kconfig.debug b/arch/parisc/Kconfig.debug index f66554cd5c45..3a059cb5e112 100644 --- a/arch/parisc/Kconfig.debug +++ b/arch/parisc/Kconfig.debug @@ -1 +1,12 @@ # SPDX-License-Identifier: GPL-2.0 +# +config LIGHTWEIGHT_SPINLOCK_CHECK + bool "Enable lightweight spinlock checks" + depends on SMP && !DEBUG_SPINLOCK + default y + help + Add checks with low performance impact to the spinlock functions + to catch memory overwrites at runtime. For more advanced + spinlock debugging you should choose the DEBUG_SPINLOCK option + which will detect unitialized spinlocks too. + If unsure say Y here. diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index 0bdee6724132..c8b6928cee1e 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -48,6 +48,10 @@ void flush_dcache_page(struct page *page); #define flush_dcache_mmap_lock(mapping) xa_lock_irq(&mapping->i_pages) #define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&mapping->i_pages) +#define flush_dcache_mmap_lock_irqsave(mapping, flags) \ + xa_lock_irqsave(&mapping->i_pages, flags) +#define flush_dcache_mmap_unlock_irqrestore(mapping, flags) \ + xa_unlock_irqrestore(&mapping->i_pages, flags) #define flush_icache_page(vma,page) do { \ flush_kernel_dcache_page_addr(page_address(page)); \ diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index e2950f5db7c9..e715df5385d6 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -413,12 +413,12 @@ extern void paging_init (void); * For the 64bit version, the offset is extended by 32bit. */ #define __swp_type(x) ((x).val & 0x1f) -#define __swp_offset(x) ( (((x).val >> 6) & 0x7) | \ - (((x).val >> 8) & ~0x7) ) +#define __swp_offset(x) ( (((x).val >> 5) & 0x7) | \ + (((x).val >> 10) << 3) ) #define __swp_entry(type, offset) ((swp_entry_t) { \ ((type) & 0x1f) | \ - ((offset & 0x7) << 6) | \ - ((offset & ~0x7) << 8) }) + ((offset & 0x7) << 5) | \ + ((offset >> 3) << 10) }) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h index a6e5d66a7656..edfcb9858bcb 100644 --- a/arch/parisc/include/asm/spinlock.h +++ b/arch/parisc/include/asm/spinlock.h @@ -7,10 +7,26 @@ #include <asm/processor.h> #include <asm/spinlock_types.h> +#define SPINLOCK_BREAK_INSN 0x0000c006 /* break 6,6 */ + +static inline void arch_spin_val_check(int lock_val) +{ + if (IS_ENABLED(CONFIG_LIGHTWEIGHT_SPINLOCK_CHECK)) + asm volatile( "andcm,= %0,%1,%%r0\n" + ".word %2\n" + : : "r" (lock_val), "r" (__ARCH_SPIN_LOCK_UNLOCKED_VAL), + "i" (SPINLOCK_BREAK_INSN)); +} + static inline int arch_spin_is_locked(arch_spinlock_t *x) { - volatile unsigned int *a = __ldcw_align(x); - return READ_ONCE(*a) == 0; + volatile unsigned int *a; + int lock_val; + + a = __ldcw_align(x); + lock_val = READ_ONCE(*a); + arch_spin_val_check(lock_val); + return (lock_val == 0); } static inline void arch_spin_lock(arch_spinlock_t *x) @@ -18,9 +34,18 @@ static inline void arch_spin_lock(arch_spinlock_t *x) volatile unsigned int *a; a = __ldcw_align(x); - while (__ldcw(a) == 0) + do { + int lock_val_old; + + lock_val_old = __ldcw(a); + arch_spin_val_check(lock_val_old); + if (lock_val_old) + return; /* got lock */ + + /* wait until we should try to get lock again */ while (*a == 0) continue; + } while (1); } static inline void arch_spin_unlock(arch_spinlock_t *x) @@ -29,15 +54,19 @@ static inline void arch_spin_unlock(arch_spinlock_t *x) a = __ldcw_align(x); /* Release with ordered store. */ - __asm__ __volatile__("stw,ma %0,0(%1)" : : "r"(1), "r"(a) : "memory"); + __asm__ __volatile__("stw,ma %0,0(%1)" + : : "r"(__ARCH_SPIN_LOCK_UNLOCKED_VAL), "r"(a) : "memory"); } static inline int arch_spin_trylock(arch_spinlock_t *x) { volatile unsigned int *a; + int lock_val; a = __ldcw_align(x); - return __ldcw(a) != 0; + lock_val = __ldcw(a); + arch_spin_val_check(lock_val); + return lock_val != 0; } /* diff --git a/arch/parisc/include/asm/spinlock_types.h b/arch/parisc/include/asm/spinlock_types.h index ca39ee350c3f..d65934079ebd 100644 --- a/arch/parisc/include/asm/spinlock_types.h +++ b/arch/parisc/include/asm/spinlock_types.h @@ -2,13 +2,17 @@ #ifndef __ASM_SPINLOCK_TYPES_H #define __ASM_SPINLOCK_TYPES_H +#define __ARCH_SPIN_LOCK_UNLOCKED_VAL 0x1a46 + typedef struct { #ifdef CONFIG_PA20 volatile unsigned int slock; -# define __ARCH_SPIN_LOCK_UNLOCKED { 1 } +# define __ARCH_SPIN_LOCK_UNLOCKED { __ARCH_SPIN_LOCK_UNLOCKED_VAL } #else volatile unsigned int lock[4]; -# define __ARCH_SPIN_LOCK_UNLOCKED { { 1, 1, 1, 1 } } +# define __ARCH_SPIN_LOCK_UNLOCKED \ + { { __ARCH_SPIN_LOCK_UNLOCKED_VAL, __ARCH_SPIN_LOCK_UNLOCKED_VAL, \ + __ARCH_SPIN_LOCK_UNLOCKED_VAL, __ARCH_SPIN_LOCK_UNLOCKED_VAL } } #endif } arch_spinlock_t; diff --git a/arch/parisc/kernel/alternative.c b/arch/parisc/kernel/alternative.c index 66f5672c70bd..25c4d6c3375d 100644 --- a/arch/parisc/kernel/alternative.c +++ b/arch/parisc/kernel/alternative.c @@ -25,7 +25,7 @@ void __init_or_module apply_alternatives(struct alt_instr *start, { struct alt_instr *entry; int index = 0, applied = 0; - int num_cpus = num_online_cpus(); + int num_cpus = num_present_cpus(); u16 cond_check; cond_check = ALT_COND_ALWAYS | diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 1d3b8bc8a623..ca4a302d4365 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -399,6 +399,7 @@ void flush_dcache_page(struct page *page) unsigned long offset; unsigned long addr, old_addr = 0; unsigned long count = 0; + unsigned long flags; pgoff_t pgoff; if (mapping && !mapping_mapped(mapping)) { @@ -420,7 +421,7 @@ void flush_dcache_page(struct page *page) * to flush one address here for them all to become coherent * on machines that support equivalent aliasing */ - flush_dcache_mmap_lock(mapping); + flush_dcache_mmap_lock_irqsave(mapping, flags); vma_interval_tree_foreach(mpnt, &mapping->i_mmap, pgoff, pgoff) { offset = (pgoff - mpnt->vm_pgoff) << PAGE_SHIFT; addr = mpnt->vm_start + offset; @@ -460,7 +461,7 @@ void flush_dcache_page(struct page *page) } WARN_ON(++count == 4096); } - flush_dcache_mmap_unlock(mapping); + flush_dcache_mmap_unlock_irqrestore(mapping, flags); } EXPORT_SYMBOL(flush_dcache_page); diff --git a/arch/parisc/kernel/kexec.c b/arch/parisc/kernel/kexec.c index 5eb7f30edc1f..db57345a9daf 100644 --- a/arch/parisc/kernel/kexec.c +++ b/arch/parisc/kernel/kexec.c @@ -4,6 +4,8 @@ #include <linux/console.h> #include <linux/kexec.h> #include <linux/delay.h> +#include <linux/reboot.h> + #include <asm/cacheflush.h> #include <asm/sections.h> diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c index ba87f791323b..71ed5391f29d 100644 --- a/arch/parisc/kernel/pci-dma.c +++ b/arch/parisc/kernel/pci-dma.c @@ -446,11 +446,27 @@ void arch_dma_free(struct device *dev, size_t size, void *vaddr, void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, enum dma_data_direction dir) { + /* + * fdc: The data cache line is written back to memory, if and only if + * it is dirty, and then invalidated from the data cache. + */ flush_kernel_dcache_range((unsigned long)phys_to_virt(paddr), size); } void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, enum dma_data_direction dir) { - flush_kernel_dcache_range((unsigned long)phys_to_virt(paddr), size); + unsigned long addr = (unsigned long) phys_to_virt(paddr); + + switch (dir) { + case DMA_TO_DEVICE: + case DMA_BIDIRECTIONAL: + flush_kernel_dcache_range(addr, size); + return; + case DMA_FROM_DEVICE: + purge_kernel_dcache_range_asm(addr, addr + size); + return; + default: + BUG(); + } } diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 97c6f875bd0e..24411ab79c30 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -122,13 +122,18 @@ void machine_power_off(void) /* It seems we have no way to power the system off via * software. The user has to press the button himself. */ - printk(KERN_EMERG "System shut down completed.\n" - "Please power this system off now."); + printk("Power off or press RETURN to reboot.\n"); /* prevent soft lockup/stalled CPU messages for endless loop. */ rcu_sysrq_start(); lockup_detector_soft_poweroff(); - for (;;); + while (1) { + /* reboot if user presses RETURN key */ + if (pdc_iodc_getc() == 13) { + printk("Rebooting...\n"); + machine_restart(NULL); + } + } } void (*pm_power_off)(void); diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index f9696fbf646c..304eebd1c83e 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -47,6 +47,10 @@ #include <linux/kgdb.h> #include <linux/kprobes.h> +#if defined(CONFIG_LIGHTWEIGHT_SPINLOCK_CHECK) +#include <asm/spinlock.h> +#endif + #include "../math-emu/math-emu.h" /* for handle_fpe() */ static void parisc_show_stack(struct task_struct *task, @@ -291,24 +295,30 @@ static void handle_break(struct pt_regs *regs) } #ifdef CONFIG_KPROBES - if (unlikely(iir == PARISC_KPROBES_BREAK_INSN)) { + if (unlikely(iir == PARISC_KPROBES_BREAK_INSN && !user_mode(regs))) { parisc_kprobe_break_handler(regs); return; } - if (unlikely(iir == PARISC_KPROBES_BREAK_INSN2)) { + if (unlikely(iir == PARISC_KPROBES_BREAK_INSN2 && !user_mode(regs))) { parisc_kprobe_ss_handler(regs); return; } #endif #ifdef CONFIG_KGDB - if (unlikely(iir == PARISC_KGDB_COMPILED_BREAK_INSN || - iir == PARISC_KGDB_BREAK_INSN)) { + if (unlikely((iir == PARISC_KGDB_COMPILED_BREAK_INSN || + iir == PARISC_KGDB_BREAK_INSN)) && !user_mode(regs)) { kgdb_handle_exception(9, SIGTRAP, 0, regs); return; } #endif +#ifdef CONFIG_LIGHTWEIGHT_SPINLOCK_CHECK + if ((iir == SPINLOCK_BREAK_INSN) && !user_mode(regs)) { + die_if_kernel("Spinlock was trashed", regs, 1); + } +#endif + if (unlikely(iir != GDB_BREAK_INSN)) parisc_printk_ratelimited(0, regs, KERN_DEBUG "break %d,%d: pid=%d command='%s'\n", diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 539d1f03ff42..bff5820b7cda 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -906,11 +906,17 @@ config DATA_SHIFT config ARCH_FORCE_MAX_ORDER int "Order of maximal physically contiguous allocations" + range 7 8 if PPC64 && PPC_64K_PAGES default "8" if PPC64 && PPC_64K_PAGES + range 12 12 if PPC64 && !PPC_64K_PAGES default "12" if PPC64 && !PPC_64K_PAGES + range 8 10 if PPC32 && PPC_16K_PAGES default "8" if PPC32 && PPC_16K_PAGES + range 6 10 if PPC32 && PPC_64K_PAGES default "6" if PPC32 && PPC_64K_PAGES + range 4 10 if PPC32 && PPC_256K_PAGES default "4" if PPC32 && PPC_256K_PAGES + range 10 10 default "10" help The kernel page allocator limits the size of maximal physically diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 85cde5bf04b7..771b79423bbc 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -34,8 +34,6 @@ endif BOOTCFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ -fno-strict-aliasing -O2 -msoft-float -mno-altivec -mno-vsx \ - $(call cc-option,-mno-prefixed) $(call cc-option,-mno-pcrel) \ - $(call cc-option,-mno-mma) \ $(call cc-option,-mno-spe) $(call cc-option,-mspe=no) \ -pipe -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \ $(LINUXINCLUDE) @@ -71,6 +69,10 @@ BOOTAFLAGS := -D__ASSEMBLY__ $(BOOTCFLAGS) -nostdinc BOOTARFLAGS := -crD +BOOTCFLAGS += $(call cc-option,-mno-prefixed) \ + $(call cc-option,-mno-pcrel) \ + $(call cc-option,-mno-mma) + ifdef CONFIG_CC_IS_CLANG BOOTCFLAGS += $(CLANG_FLAGS) BOOTAFLAGS += $(CLANG_FLAGS) diff --git a/arch/powerpc/crypto/Kconfig b/arch/powerpc/crypto/Kconfig index 7113f9355165..ad1872518992 100644 --- a/arch/powerpc/crypto/Kconfig +++ b/arch/powerpc/crypto/Kconfig @@ -96,7 +96,7 @@ config CRYPTO_AES_PPC_SPE config CRYPTO_AES_GCM_P10 tristate "Stitched AES/GCM acceleration support on P10 or later CPU (PPC)" - depends on PPC64 && CPU_LITTLE_ENDIAN + depends on PPC64 && CPU_LITTLE_ENDIAN && VSX select CRYPTO_LIB_AES select CRYPTO_ALGAPI select CRYPTO_AEAD diff --git a/arch/powerpc/crypto/Makefile b/arch/powerpc/crypto/Makefile index 05c7486f42c5..7b4f516abec1 100644 --- a/arch/powerpc/crypto/Makefile +++ b/arch/powerpc/crypto/Makefile @@ -22,15 +22,15 @@ sha1-ppc-spe-y := sha1-spe-asm.o sha1-spe-glue.o sha256-ppc-spe-y := sha256-spe-asm.o sha256-spe-glue.o crc32c-vpmsum-y := crc32c-vpmsum_asm.o crc32c-vpmsum_glue.o crct10dif-vpmsum-y := crct10dif-vpmsum_asm.o crct10dif-vpmsum_glue.o -aes-gcm-p10-crypto-y := aes-gcm-p10-glue.o aes-gcm-p10.o ghashp8-ppc.o aesp8-ppc.o +aes-gcm-p10-crypto-y := aes-gcm-p10-glue.o aes-gcm-p10.o ghashp10-ppc.o aesp10-ppc.o quiet_cmd_perl = PERL $@ cmd_perl = $(PERL) $< $(if $(CONFIG_CPU_LITTLE_ENDIAN), linux-ppc64le, linux-ppc64) > $@ -targets += aesp8-ppc.S ghashp8-ppc.S +targets += aesp10-ppc.S ghashp10-ppc.S -$(obj)/aesp8-ppc.S $(obj)/ghashp8-ppc.S: $(obj)/%.S: $(src)/%.pl FORCE +$(obj)/aesp10-ppc.S $(obj)/ghashp10-ppc.S: $(obj)/%.S: $(src)/%.pl FORCE $(call if_changed,perl) -OBJECT_FILES_NON_STANDARD_aesp8-ppc.o := y -OBJECT_FILES_NON_STANDARD_ghashp8-ppc.o := y +OBJECT_FILES_NON_STANDARD_aesp10-ppc.o := y +OBJECT_FILES_NON_STANDARD_ghashp10-ppc.o := y diff --git a/arch/powerpc/crypto/aes-gcm-p10-glue.c b/arch/powerpc/crypto/aes-gcm-p10-glue.c index bd3475f5348d..4b6e899895e7 100644 --- a/arch/powerpc/crypto/aes-gcm-p10-glue.c +++ b/arch/powerpc/crypto/aes-gcm-p10-glue.c @@ -30,15 +30,15 @@ MODULE_AUTHOR("Danny Tsen <dtsen@linux.ibm.com"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS_CRYPTO("aes"); -asmlinkage int aes_p8_set_encrypt_key(const u8 *userKey, const int bits, +asmlinkage int aes_p10_set_encrypt_key(const u8 *userKey, const int bits, void *key); -asmlinkage void aes_p8_encrypt(const u8 *in, u8 *out, const void *key); +asmlinkage void aes_p10_encrypt(const u8 *in, u8 *out, const void *key); asmlinkage void aes_p10_gcm_encrypt(u8 *in, u8 *out, size_t len, void *rkey, u8 *iv, void *Xi); asmlinkage void aes_p10_gcm_decrypt(u8 *in, u8 *out, size_t len, void *rkey, u8 *iv, void *Xi); asmlinkage void gcm_init_htable(unsigned char htable[256], unsigned char Xi[16]); -asmlinkage void gcm_ghash_p8(unsigned char *Xi, unsigned char *Htable, +asmlinkage void gcm_ghash_p10(unsigned char *Xi, unsigned char *Htable, unsigned char *aad, unsigned int alen); struct aes_key { @@ -93,7 +93,7 @@ static void set_aad(struct gcm_ctx *gctx, struct Hash_ctx *hash, gctx->aadLen = alen; i = alen & ~0xf; if (i) { - gcm_ghash_p8(nXi, hash->Htable+32, aad, i); + gcm_ghash_p10(nXi, hash->Htable+32, aad, i); aad += i; alen -= i; } @@ -102,7 +102,7 @@ static void set_aad(struct gcm_ctx *gctx, struct Hash_ctx *hash, nXi[i] ^= aad[i]; memset(gctx->aad_hash, 0, 16); - gcm_ghash_p8(gctx->aad_hash, hash->Htable+32, nXi, 16); + gcm_ghash_p10(gctx->aad_hash, hash->Htable+32, nXi, 16); } else { memcpy(gctx->aad_hash, nXi, 16); } @@ -115,7 +115,7 @@ static void gcmp10_init(struct gcm_ctx *gctx, u8 *iv, unsigned char *rdkey, { __be32 counter = cpu_to_be32(1); - aes_p8_encrypt(hash->H, hash->H, rdkey); + aes_p10_encrypt(hash->H, hash->H, rdkey); set_subkey(hash->H); gcm_init_htable(hash->Htable+32, hash->H); @@ -126,7 +126,7 @@ static void gcmp10_init(struct gcm_ctx *gctx, u8 *iv, unsigned char *rdkey, /* * Encrypt counter vector as iv tag and increment counter. */ - aes_p8_encrypt(iv, gctx->ivtag, rdkey); + aes_p10_encrypt(iv, gctx->ivtag, rdkey); counter = cpu_to_be32(2); *((__be32 *)(iv+12)) = counter; @@ -160,7 +160,7 @@ static void finish_tag(struct gcm_ctx *gctx, struct Hash_ctx *hash, int len) /* * hash (AAD len and len) */ - gcm_ghash_p8(hash->Htable, hash->Htable+32, aclen, 16); + gcm_ghash_p10(hash->Htable, hash->Htable+32, aclen, 16); for (i = 0; i < 16; i++) hash->Htable[i] ^= gctx->ivtag[i]; @@ -192,7 +192,7 @@ static int p10_aes_gcm_setkey(struct crypto_aead *aead, const u8 *key, int ret; vsx_begin(); - ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key); + ret = aes_p10_set_encrypt_key(key, keylen * 8, &ctx->enc_key); vsx_end(); return ret ? -EINVAL : 0; diff --git a/arch/powerpc/crypto/aesp8-ppc.pl b/arch/powerpc/crypto/aesp10-ppc.pl index 1f22aec27d79..2c06ce2a2c7c 100644 --- a/arch/powerpc/crypto/aesp8-ppc.pl +++ b/arch/powerpc/crypto/aesp10-ppc.pl @@ -110,7 +110,7 @@ die "can't locate ppc-xlate.pl"; open STDOUT,"| $^X $xlate $flavour ".shift || die "can't call $xlate: $!"; $FRAME=8*$SIZE_T; -$prefix="aes_p8"; +$prefix="aes_p10"; $sp="r1"; $vrsave="r12"; diff --git a/arch/powerpc/crypto/ghashp8-ppc.pl b/arch/powerpc/crypto/ghashp10-ppc.pl index b56603b4a893..27a6b0bec645 100644 --- a/arch/powerpc/crypto/ghashp8-ppc.pl +++ b/arch/powerpc/crypto/ghashp10-ppc.pl @@ -64,7 +64,7 @@ $code=<<___; .text -.globl .gcm_init_p8 +.globl .gcm_init_p10 lis r0,0xfff0 li r8,0x10 mfspr $vrsave,256 @@ -110,7 +110,7 @@ $code=<<___; .long 0 .byte 0,12,0x14,0,0,0,2,0 .long 0 -.size .gcm_init_p8,.-.gcm_init_p8 +.size .gcm_init_p10,.-.gcm_init_p10 .globl .gcm_init_htable lis r0,0xfff0 @@ -237,7 +237,7 @@ $code=<<___; .long 0 .size .gcm_init_htable,.-.gcm_init_htable -.globl .gcm_gmult_p8 +.globl .gcm_gmult_p10 lis r0,0xfff8 li r8,0x10 mfspr $vrsave,256 @@ -283,9 +283,9 @@ $code=<<___; .long 0 .byte 0,12,0x14,0,0,0,2,0 .long 0 -.size .gcm_gmult_p8,.-.gcm_gmult_p8 +.size .gcm_gmult_p10,.-.gcm_gmult_p10 -.globl .gcm_ghash_p8 +.globl .gcm_ghash_p10 lis r0,0xfff8 li r8,0x10 mfspr $vrsave,256 @@ -350,7 +350,7 @@ Loop: .long 0 .byte 0,12,0x14,0,0,0,4,0 .long 0 -.size .gcm_ghash_p8,.-.gcm_ghash_p8 +.size .gcm_ghash_p10,.-.gcm_ghash_p10 .asciz "GHASH for PowerISA 2.07, CRYPTOGAMS by <appro\@openssl.org>" .align 2 diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 678b5bdc79b1..34e14dfd8e04 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -205,7 +205,6 @@ extern void iommu_register_group(struct iommu_table_group *table_group, int pci_domain_number, unsigned long pe_num); extern int iommu_add_device(struct iommu_table_group *table_group, struct device *dev); -extern void iommu_del_device(struct device *dev); extern long iommu_tce_xchg(struct mm_struct *mm, struct iommu_table *tbl, unsigned long entry, unsigned long *hpa, enum dma_data_direction *direction); @@ -229,10 +228,6 @@ static inline int iommu_add_device(struct iommu_table_group *table_group, { return 0; } - -static inline void iommu_del_device(struct device *dev) -{ -} #endif /* !CONFIG_IOMMU_API */ u64 dma_iommu_get_required_mask(struct device *dev); diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index 038ce8d9061d..8920862ffd79 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -144,7 +144,7 @@ static bool dma_iommu_bypass_supported(struct device *dev, u64 mask) /* We support DMA to/from any memory page via the iommu */ int dma_iommu_dma_supported(struct device *dev, u64 mask) { - struct iommu_table *tbl = get_iommu_table_base(dev); + struct iommu_table *tbl; if (dev_is_pci(dev) && dma_iommu_bypass_supported(dev, mask)) { /* @@ -162,6 +162,8 @@ int dma_iommu_dma_supported(struct device *dev, u64 mask) return 1; } + tbl = get_iommu_table_base(dev); + if (!tbl) { dev_err(dev, "Warning: IOMMU dma not supported: mask 0x%08llx, table unavailable\n", mask); return 0; diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 0089dd49b4cb..67f0b01e6ff5 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -518,7 +518,7 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl, /* Convert entry to a dma_addr_t */ entry += tbl->it_offset; dma_addr = entry << tbl->it_page_shift; - dma_addr |= (s->offset & ~IOMMU_PAGE_MASK(tbl)); + dma_addr |= (vaddr & ~IOMMU_PAGE_MASK(tbl)); DBG(" - %lu pages, entry: %lx, dma_addr: %lx\n", npages, entry, dma_addr); @@ -905,6 +905,7 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, unsigned int order; unsigned int nio_pages, io_order; struct page *page; + int tcesize = (1 << tbl->it_page_shift); size = PAGE_ALIGN(size); order = get_order(size); @@ -931,7 +932,8 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, memset(ret, 0, size); /* Set up tces to cover the allocated range */ - nio_pages = size >> tbl->it_page_shift; + nio_pages = IOMMU_PAGE_ALIGN(size, tbl) >> tbl->it_page_shift; + io_order = get_iommu_order(size, tbl); mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL, mask >> tbl->it_page_shift, io_order, 0); @@ -939,7 +941,8 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, free_pages((unsigned long)ret, order); return NULL; } - *dma_handle = mapping; + + *dma_handle = mapping | ((u64)ret & (tcesize - 1)); return ret; } @@ -950,7 +953,7 @@ void iommu_free_coherent(struct iommu_table *tbl, size_t size, unsigned int nio_pages; size = PAGE_ALIGN(size); - nio_pages = size >> tbl->it_page_shift; + nio_pages = IOMMU_PAGE_ALIGN(size, tbl) >> tbl->it_page_shift; iommu_free(tbl, dma_handle, nio_pages); size = PAGE_ALIGN(size); free_pages((unsigned long)vaddr, get_order(size)); @@ -1168,23 +1171,6 @@ int iommu_add_device(struct iommu_table_group *table_group, struct device *dev) } EXPORT_SYMBOL_GPL(iommu_add_device); -void iommu_del_device(struct device *dev) -{ - /* - * Some devices might not have IOMMU table and group - * and we needn't detach them from the associated - * IOMMU groups - */ - if (!device_iommu_mapped(dev)) { - pr_debug("iommu_tce: skipping device %s with no tbl\n", - dev_name(dev)); - return; - } - - iommu_group_remove_device(dev); -} -EXPORT_SYMBOL_GPL(iommu_del_device); - /* * A simple iommu_table_group_ops which only allows reusing the existing * iommu_table. This handles VFIO for POWER7 or the nested KVM. diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c index 85bdd7d3652f..48e0eaf1ad61 100644 --- a/arch/powerpc/kernel/isa-bridge.c +++ b/arch/powerpc/kernel/isa-bridge.c @@ -93,11 +93,12 @@ static int process_ISA_OF_ranges(struct device_node *isa_node, } inval_range: - if (!phb_io_base_phys) { + if (phb_io_base_phys) { pr_err("no ISA IO ranges or unexpected isa range, mapping 64k\n"); remap_isa_base(phb_io_base_phys, 0x10000); + return 0; } - return 0; + return -EINVAL; } diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index 26245aaf12b8..2297aa764ecd 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -1040,8 +1040,8 @@ void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep, pte_t entry, unsigned long address, int psize) { struct mm_struct *mm = vma->vm_mm; - unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_ACCESSED | - _PAGE_RW | _PAGE_EXEC); + unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_SOFT_DIRTY | + _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); unsigned long change = pte_val(entry) ^ pte_val(*ptep); /* diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index e93aefcfb83f..37043dfc1add 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -101,6 +101,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) bpf_hdr = jit_data->header; proglen = jit_data->proglen; extra_pass = true; + /* During extra pass, ensure index is reset before repopulating extable entries */ + cgctx.exentry_idx = 0; goto skip_init_ctx; } diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index 0d9b7609c7d5..3e2e252016f7 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -265,6 +265,7 @@ config CPM2 config FSL_ULI1575 bool "ULI1575 PCIe south bridge support" depends on FSL_SOC_BOOKE || PPC_86xx + depends on PCI select FSL_PCI select GENERIC_ISA_DMA help diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 233a50e65fce..7725492097b6 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -865,28 +865,3 @@ void __init pnv_pci_init(void) /* Configure IOMMU DMA hooks */ set_pci_dma_ops(&dma_iommu_ops); } - -static int pnv_tce_iommu_bus_notifier(struct notifier_block *nb, - unsigned long action, void *data) -{ - struct device *dev = data; - - switch (action) { - case BUS_NOTIFY_DEL_DEVICE: - iommu_del_device(dev); - return 0; - default: - return 0; - } -} - -static struct notifier_block pnv_tce_iommu_bus_nb = { - .notifier_call = pnv_tce_iommu_bus_notifier, -}; - -static int __init pnv_tce_iommu_bus_notifier_init(void) -{ - bus_register_notifier(&pci_bus_type, &pnv_tce_iommu_bus_nb); - return 0; -} -machine_subsys_initcall_sync(powernv, pnv_tce_iommu_bus_notifier_init); diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 7464fa6e4145..d59e8a98a200 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -91,19 +91,24 @@ static struct iommu_table_group *iommu_pseries_alloc_group(int node) static void iommu_pseries_free_group(struct iommu_table_group *table_group, const char *node_name) { - struct iommu_table *tbl; - if (!table_group) return; - tbl = table_group->tables[0]; #ifdef CONFIG_IOMMU_API if (table_group->group) { iommu_group_put(table_group->group); BUG_ON(table_group->group); } #endif - iommu_tce_table_put(tbl); + + /* Default DMA window table is at index 0, while DDW at 1. SR-IOV + * adapters only have table on index 1. + */ + if (table_group->tables[0]) + iommu_tce_table_put(table_group->tables[0]); + + if (table_group->tables[1]) + iommu_tce_table_put(table_group->tables[1]); kfree(table_group); } @@ -312,13 +317,22 @@ static void tce_free_pSeriesLP(unsigned long liobn, long tcenum, long tceshift, static void tce_freemulti_pSeriesLP(struct iommu_table *tbl, long tcenum, long npages) { u64 rc; + long rpages = npages; + unsigned long limit; if (!firmware_has_feature(FW_FEATURE_STUFF_TCE)) return tce_free_pSeriesLP(tbl->it_index, tcenum, tbl->it_page_shift, npages); - rc = plpar_tce_stuff((u64)tbl->it_index, - (u64)tcenum << tbl->it_page_shift, 0, npages); + do { + limit = min_t(unsigned long, rpages, 512); + + rc = plpar_tce_stuff((u64)tbl->it_index, + (u64)tcenum << tbl->it_page_shift, 0, limit); + + rpages -= limit; + tcenum += limit; + } while (rpages > 0 && !rc); if (rc && printk_ratelimit()) { printk("tce_freemulti_pSeriesLP: plpar_tce_stuff failed\n"); @@ -1695,31 +1709,6 @@ static int __init disable_multitce(char *str) __setup("multitce=", disable_multitce); -static int tce_iommu_bus_notifier(struct notifier_block *nb, - unsigned long action, void *data) -{ - struct device *dev = data; - - switch (action) { - case BUS_NOTIFY_DEL_DEVICE: - iommu_del_device(dev); - return 0; - default: - return 0; - } -} - -static struct notifier_block tce_iommu_bus_nb = { - .notifier_call = tce_iommu_bus_notifier, -}; - -static int __init tce_iommu_bus_notifier_init(void) -{ - bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb); - return 0; -} -machine_subsys_initcall_sync(pseries, tce_iommu_bus_notifier_init); - #ifdef CONFIG_SPAPR_TCE_IOMMU struct iommu_group *pSeries_pci_device_group(struct pci_controller *hose, struct pci_dev *pdev) diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 728d3c257e4a..70c4c59a1a8f 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -88,7 +88,7 @@ static unsigned long ndump = 64; static unsigned long nidump = 16; static unsigned long ncsum = 4096; static int termch; -static char tmpstr[128]; +static char tmpstr[KSYM_NAME_LEN]; static int tracing_enabled; static long bus_error_jmp[JMP_BUF_LEN]; diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 348c0fa1fc8c..2bb0c38419ff 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -799,8 +799,11 @@ menu "Power management options" source "kernel/power/Kconfig" +# Hibernation is only possible on systems where the SBI implementation has +# marked its reserved memory as not accessible from, or does not run +# from the same memory as, Linux config ARCH_HIBERNATION_POSSIBLE - def_bool y + def_bool NONPORTABLE config ARCH_HIBERNATION_HEADER def_bool HIBERNATION diff --git a/arch/riscv/errata/Makefile b/arch/riscv/errata/Makefile index a1055965fbee..7b2637c8c332 100644 --- a/arch/riscv/errata/Makefile +++ b/arch/riscv/errata/Makefile @@ -1,2 +1,6 @@ +ifdef CONFIG_RELOCATABLE +KBUILD_CFLAGS += -fno-pie +endif + obj-$(CONFIG_ERRATA_SIFIVE) += sifive/ obj-$(CONFIG_ERRATA_THEAD) += thead/ diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h index fe6f23006641..ce1ebda1a49a 100644 --- a/arch/riscv/include/asm/hugetlb.h +++ b/arch/riscv/include/asm/hugetlb.h @@ -36,6 +36,9 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte, int dirty); +#define __HAVE_ARCH_HUGE_PTEP_GET +pte_t huge_ptep_get(pte_t *ptep); + pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags); #define arch_make_huge_pte arch_make_huge_pte diff --git a/arch/riscv/include/asm/perf_event.h b/arch/riscv/include/asm/perf_event.h index d42c901f9a97..665bbc9b2f84 100644 --- a/arch/riscv/include/asm/perf_event.h +++ b/arch/riscv/include/asm/perf_event.h @@ -10,4 +10,11 @@ #include <linux/perf_event.h> #define perf_arch_bpf_user_pt_regs(regs) (struct user_regs_struct *)regs + +#define perf_arch_fetch_caller_regs(regs, __ip) { \ + (regs)->epc = (__ip); \ + (regs)->s0 = (unsigned long) __builtin_frame_address(0); \ + (regs)->sp = current_stack_pointer; \ + (regs)->status = SR_PP; \ +} #endif /* _ASM_RISCV_PERF_EVENT_H */ diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index fbdccc21418a..153864e4f399 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -23,6 +23,10 @@ ifdef CONFIG_FTRACE CFLAGS_REMOVE_alternative.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_cpufeature.o = $(CC_FLAGS_FTRACE) endif +ifdef CONFIG_RELOCATABLE +CFLAGS_alternative.o += -fno-pie +CFLAGS_cpufeature.o += -fno-pie +endif ifdef CONFIG_KASAN KASAN_SANITIZE_alternative.o := n KASAN_SANITIZE_cpufeature.o := n diff --git a/arch/riscv/kernel/pi/Makefile b/arch/riscv/kernel/pi/Makefile index 5d7cb991f2b8..7b593d44c712 100644 --- a/arch/riscv/kernel/pi/Makefile +++ b/arch/riscv/kernel/pi/Makefile @@ -22,7 +22,7 @@ KCOV_INSTRUMENT := n $(obj)/%.pi.o: OBJCOPYFLAGS := --prefix-symbols=__pi_ \ --remove-section=.note.gnu.property \ - --prefix-alloc-sections=.init + --prefix-alloc-sections=.init.pi $(obj)/%.pi.o: $(obj)/%.o FORCE $(call if_changed,objcopy) diff --git a/arch/riscv/kernel/probes/Makefile b/arch/riscv/kernel/probes/Makefile index c40139e9ca47..8265ff497977 100644 --- a/arch/riscv/kernel/probes/Makefile +++ b/arch/riscv/kernel/probes/Makefile @@ -4,3 +4,5 @@ obj-$(CONFIG_RETHOOK) += rethook.o rethook_trampoline.o obj-$(CONFIG_KPROBES_ON_FTRACE) += ftrace.o obj-$(CONFIG_UPROBES) += uprobes.o decode-insn.o simulate-insn.o CFLAGS_REMOVE_simulate-insn.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_rethook.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_rethook_trampoline.o = $(CC_FLAGS_FTRACE) diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S index f03b5697f8e0..e5f9f4677bbf 100644 --- a/arch/riscv/kernel/vmlinux.lds.S +++ b/arch/riscv/kernel/vmlinux.lds.S @@ -84,11 +84,8 @@ SECTIONS __init_data_begin = .; INIT_DATA_SECTION(16) - /* Those sections result from the compilation of kernel/pi/string.c */ - .init.pidata : { - *(.init.srodata.cst8*) - *(.init__bug_table*) - *(.init.sdata*) + .init.pi : { + *(.init.pi*) } .init.bss : { diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c index a163a3e0f0d4..e0ef56dc57b9 100644 --- a/arch/riscv/mm/hugetlbpage.c +++ b/arch/riscv/mm/hugetlbpage.c @@ -3,6 +3,30 @@ #include <linux/err.h> #ifdef CONFIG_RISCV_ISA_SVNAPOT +pte_t huge_ptep_get(pte_t *ptep) +{ + unsigned long pte_num; + int i; + pte_t orig_pte = ptep_get(ptep); + + if (!pte_present(orig_pte) || !pte_napot(orig_pte)) + return orig_pte; + + pte_num = napot_pte_num(napot_cont_order(orig_pte)); + + for (i = 0; i < pte_num; i++, ptep++) { + pte_t pte = ptep_get(ptep); + + if (pte_dirty(pte)) + orig_pte = pte_mkdirty(orig_pte); + + if (pte_young(pte)) + orig_pte = pte_mkyoung(orig_pte); + } + + return orig_pte; +} + pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, @@ -218,6 +242,7 @@ void huge_ptep_set_wrprotect(struct mm_struct *mm, { pte_t pte = ptep_get(ptep); unsigned long order; + pte_t orig_pte; int i, pte_num; if (!pte_napot(pte)) { @@ -228,9 +253,12 @@ void huge_ptep_set_wrprotect(struct mm_struct *mm, order = napot_cont_order(pte); pte_num = napot_pte_num(order); ptep = huge_pte_offset(mm, addr, napot_cont_size(order)); + orig_pte = get_clear_contig_flush(mm, addr, ptep, pte_num); + + orig_pte = pte_wrprotect(orig_pte); for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++) - ptep_set_wrprotect(mm, addr, ptep); + set_pte_at(mm, addr, ptep, orig_pte); } pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 747e5b1ef02d..c6bb966e4123 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -922,9 +922,9 @@ static void __init create_kernel_page_table(pgd_t *pgdir, bool early) static void __init create_fdt_early_page_table(uintptr_t fix_fdt_va, uintptr_t dtb_pa) { +#ifndef CONFIG_BUILTIN_DTB uintptr_t pa = dtb_pa & ~(PMD_SIZE - 1); -#ifndef CONFIG_BUILTIN_DTB /* Make sure the fdt fixmap address is always aligned on PMD size */ BUILD_BUG_ON(FIX_FDT % (PMD_SIZE / PAGE_SIZE)); diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index db20c1589a98..6dab9c1be508 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -469,19 +469,11 @@ config SCHED_SMT config SCHED_MC def_bool n -config SCHED_BOOK - def_bool n - -config SCHED_DRAWER - def_bool n - config SCHED_TOPOLOGY def_bool y prompt "Topology scheduler support" select SCHED_SMT select SCHED_MC - select SCHED_BOOK - select SCHED_DRAWER help Topology scheduler support improves the CPU scheduler's decision making when dealing with machines that have multi-threading, @@ -716,7 +708,6 @@ config EADM_SCH config VFIO_CCW def_tristate n prompt "Support for VFIO-CCW subchannels" - depends on S390_CCW_IOMMU depends on VFIO select VFIO_MDEV help @@ -728,7 +719,7 @@ config VFIO_CCW config VFIO_AP def_tristate n prompt "VFIO support for AP devices" - depends on S390_AP_IOMMU && KVM + depends on KVM depends on VFIO depends on ZCRYPT select VFIO_MDEV diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 4ccf66d29fc2..be3bf03bf361 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -591,8 +591,6 @@ CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m -CONFIG_S390_CCW_IOMMU=y -CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y @@ -703,6 +701,7 @@ CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" +CONFIG_INIT_STACK_NONE=y CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set CONFIG_CRYPTO_PCRYPT=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 693297a2e897..769c7eed8b6a 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -580,8 +580,6 @@ CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m -CONFIG_S390_CCW_IOMMU=y -CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y @@ -686,6 +684,7 @@ CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" +CONFIG_INIT_STACK_NONE=y CONFIG_CRYPTO_FIPS=y CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index 33a232bb68af..6f68b39817ef 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -67,6 +67,7 @@ CONFIG_ZFCP=y # CONFIG_MISC_FILESYSTEMS is not set # CONFIG_NETWORK_FILESYSTEMS is not set CONFIG_LSM="yama,loadpin,safesetid,integrity" +CONFIG_INIT_STACK_NONE=y # CONFIG_ZLIB_DFLTCC is not set CONFIG_XZ_DEC_MICROLZMA=y CONFIG_PRINTK_TIME=y diff --git a/arch/s390/crypto/chacha-glue.c b/arch/s390/crypto/chacha-glue.c index 7752bd314558..5fae187f947a 100644 --- a/arch/s390/crypto/chacha-glue.c +++ b/arch/s390/crypto/chacha-glue.c @@ -82,7 +82,7 @@ void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, * it cannot handle a block of data or less, but otherwise * it can handle data of arbitrary size */ - if (bytes <= CHACHA_BLOCK_SIZE || nrounds != 20) + if (bytes <= CHACHA_BLOCK_SIZE || nrounds != 20 || !MACHINE_HAS_VX) chacha_crypt_generic(state, dst, src, bytes, nrounds); else chacha20_crypt_s390(state, dst, src, bytes, diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h index a386070f1d56..3cb9d813f022 100644 --- a/arch/s390/include/asm/compat.h +++ b/arch/s390/include/asm/compat.h @@ -112,7 +112,7 @@ struct compat_statfs64 { u32 f_namelen; u32 f_frsize; u32 f_flags; - u32 f_spare[4]; + u32 f_spare[5]; }; /* diff --git a/arch/s390/include/uapi/asm/statfs.h b/arch/s390/include/uapi/asm/statfs.h index 72604f7792c3..f85b50723dd3 100644 --- a/arch/s390/include/uapi/asm/statfs.h +++ b/arch/s390/include/uapi/asm/statfs.h @@ -30,7 +30,7 @@ struct statfs { unsigned int f_namelen; unsigned int f_frsize; unsigned int f_flags; - unsigned int f_spare[4]; + unsigned int f_spare[5]; }; struct statfs64 { @@ -45,7 +45,7 @@ struct statfs64 { unsigned int f_namelen; unsigned int f_frsize; unsigned int f_flags; - unsigned int f_spare[4]; + unsigned int f_spare[5]; }; #endif diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 8983837b3565..6b2a051e1f8a 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -10,6 +10,7 @@ CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) # Do not trace early setup code CFLAGS_REMOVE_early.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_rethook.o = $(CC_FLAGS_FTRACE) endif diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 43de939b7af1..f44f70de9661 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -1935,14 +1935,13 @@ static struct shutdown_action __refdata dump_action = { static void dump_reipl_run(struct shutdown_trigger *trigger) { - unsigned long ipib = (unsigned long) reipl_block_actual; struct lowcore *abs_lc; unsigned int csum; csum = (__force unsigned int) csum_partial(reipl_block_actual, reipl_block_actual->hdr.len, 0); abs_lc = get_abs_lowcore(); - abs_lc->ipib = ipib; + abs_lc->ipib = __pa(reipl_block_actual); abs_lc->ipib_checksum = csum; put_abs_lowcore(abs_lc); dump_run(trigger); diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 9fd19530c9a5..68adf1de8888 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -95,7 +95,7 @@ out: static void cpu_thread_map(cpumask_t *dst, unsigned int cpu) { static cpumask_t mask; - int i; + unsigned int max_cpu; cpumask_clear(&mask); if (!cpumask_test_cpu(cpu, &cpu_setup_mask)) @@ -104,9 +104,10 @@ static void cpu_thread_map(cpumask_t *dst, unsigned int cpu) if (topology_mode != TOPOLOGY_MODE_HW) goto out; cpu -= cpu % (smp_cpu_mtid + 1); - for (i = 0; i <= smp_cpu_mtid; i++) { - if (cpumask_test_cpu(cpu + i, &cpu_setup_mask)) - cpumask_set_cpu(cpu + i, &mask); + max_cpu = min(cpu + smp_cpu_mtid, nr_cpu_ids - 1); + for (; cpu <= max_cpu; cpu++) { + if (cpumask_test_cpu(cpu, &cpu_setup_mask)) + cpumask_set_cpu(cpu, &mask); } out: cpumask_copy(dst, &mask); @@ -123,25 +124,26 @@ static void add_cpus_to_mask(struct topology_core *tl_core, unsigned int core; for_each_set_bit(core, &tl_core->mask, TOPOLOGY_CORE_BITS) { - unsigned int rcore; - int lcpu, i; + unsigned int max_cpu, rcore; + int cpu; rcore = TOPOLOGY_CORE_BITS - 1 - core + tl_core->origin; - lcpu = smp_find_processor_id(rcore << smp_cpu_mt_shift); - if (lcpu < 0) + cpu = smp_find_processor_id(rcore << smp_cpu_mt_shift); + if (cpu < 0) continue; - for (i = 0; i <= smp_cpu_mtid; i++) { - topo = &cpu_topology[lcpu + i]; + max_cpu = min(cpu + smp_cpu_mtid, nr_cpu_ids - 1); + for (; cpu <= max_cpu; cpu++) { + topo = &cpu_topology[cpu]; topo->drawer_id = drawer->id; topo->book_id = book->id; topo->socket_id = socket->id; topo->core_id = rcore; - topo->thread_id = lcpu + i; + topo->thread_id = cpu; topo->dedicated = tl_core->d; - cpumask_set_cpu(lcpu + i, &drawer->mask); - cpumask_set_cpu(lcpu + i, &book->mask); - cpumask_set_cpu(lcpu + i, &socket->mask); - smp_cpu_set_polarization(lcpu + i, tl_core->pp); + cpumask_set_cpu(cpu, &drawer->mask); + cpumask_set_cpu(cpu, &book->mask); + cpumask_set_cpu(cpu, &socket->mask); + smp_cpu_set_polarization(cpu, tl_core->pp); } } } diff --git a/arch/um/drivers/Makefile b/arch/um/drivers/Makefile index dee6f66353b3..a461a950f051 100644 --- a/arch/um/drivers/Makefile +++ b/arch/um/drivers/Makefile @@ -16,7 +16,8 @@ mconsole-objs := mconsole_kern.o mconsole_user.o hostaudio-objs := hostaudio_kern.o ubd-objs := ubd_kern.o ubd_user.o port-objs := port_kern.o port_user.o -harddog-objs := harddog_kern.o harddog_user.o +harddog-objs := harddog_kern.o +harddog-builtin-$(CONFIG_UML_WATCHDOG) := harddog_user.o harddog_user_exp.o rtc-objs := rtc_kern.o rtc_user.o LDFLAGS_pcap.o = $(shell $(CC) $(KBUILD_CFLAGS) -print-file-name=libpcap.a) @@ -60,6 +61,7 @@ obj-$(CONFIG_PTY_CHAN) += pty.o obj-$(CONFIG_TTY_CHAN) += tty.o obj-$(CONFIG_XTERM_CHAN) += xterm.o xterm_kern.o obj-$(CONFIG_UML_WATCHDOG) += harddog.o +obj-y += $(harddog-builtin-y) $(harddog-builtin-m) obj-$(CONFIG_BLK_DEV_COW_COMMON) += cow_user.o obj-$(CONFIG_UML_RANDOM) += random.o obj-$(CONFIG_VIRTIO_UML) += virtio_uml.o diff --git a/arch/um/drivers/harddog.h b/arch/um/drivers/harddog.h new file mode 100644 index 000000000000..6d9ea60e7133 --- /dev/null +++ b/arch/um/drivers/harddog.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef UM_WATCHDOG_H +#define UM_WATCHDOG_H + +int start_watchdog(int *in_fd_ret, int *out_fd_ret, char *sock); +void stop_watchdog(int in_fd, int out_fd); +int ping_watchdog(int fd); + +#endif /* UM_WATCHDOG_H */ diff --git a/arch/um/drivers/harddog_kern.c b/arch/um/drivers/harddog_kern.c index e6d4f43deba8..60d1c6cab8a9 100644 --- a/arch/um/drivers/harddog_kern.c +++ b/arch/um/drivers/harddog_kern.c @@ -47,6 +47,7 @@ #include <linux/spinlock.h> #include <linux/uaccess.h> #include "mconsole.h" +#include "harddog.h" MODULE_LICENSE("GPL"); @@ -60,8 +61,6 @@ static int harddog_out_fd = -1; * Allow only one person to hold it open */ -extern int start_watchdog(int *in_fd_ret, int *out_fd_ret, char *sock); - static int harddog_open(struct inode *inode, struct file *file) { int err = -EBUSY; @@ -92,8 +91,6 @@ err: return err; } -extern void stop_watchdog(int in_fd, int out_fd); - static int harddog_release(struct inode *inode, struct file *file) { /* @@ -112,8 +109,6 @@ static int harddog_release(struct inode *inode, struct file *file) return 0; } -extern int ping_watchdog(int fd); - static ssize_t harddog_write(struct file *file, const char __user *data, size_t len, loff_t *ppos) { diff --git a/arch/um/drivers/harddog_user.c b/arch/um/drivers/harddog_user.c index 070468d22e39..9ed89304975e 100644 --- a/arch/um/drivers/harddog_user.c +++ b/arch/um/drivers/harddog_user.c @@ -7,6 +7,7 @@ #include <unistd.h> #include <errno.h> #include <os.h> +#include "harddog.h" struct dog_data { int stdin_fd; diff --git a/arch/um/drivers/harddog_user_exp.c b/arch/um/drivers/harddog_user_exp.c new file mode 100644 index 000000000000..c74d4b815d14 --- /dev/null +++ b/arch/um/drivers/harddog_user_exp.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/export.h> +#include "harddog.h" + +#if IS_MODULE(CONFIG_UML_WATCHDOG) +EXPORT_SYMBOL(start_watchdog); +EXPORT_SYMBOL(stop_watchdog); +EXPORT_SYMBOL(ping_watchdog); +#endif diff --git a/arch/x86/crypto/aria-aesni-avx-asm_64.S b/arch/x86/crypto/aria-aesni-avx-asm_64.S index 7c1abc513f34..9556dacd9841 100644 --- a/arch/x86/crypto/aria-aesni-avx-asm_64.S +++ b/arch/x86/crypto/aria-aesni-avx-asm_64.S @@ -773,8 +773,6 @@ .octa 0x3F893781E95FE1576CDA64D2BA0CB204 #ifdef CONFIG_AS_GFNI -.section .rodata.cst8, "aM", @progbits, 8 -.align 8 /* AES affine: */ #define tf_aff_const BV8(1, 1, 0, 0, 0, 1, 1, 0) .Ltf_aff_bitmatrix: diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index d096b04bf80e..9d248703cbdd 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1703,10 +1703,8 @@ int x86_pmu_handle_irq(struct pt_regs *regs) perf_sample_data_init(&data, 0, event->hw.last_period); - if (has_branch_stack(event)) { - data.br_stack = &cpuc->lbr_stack; - data.sample_flags |= PERF_SAMPLE_BRANCH_STACK; - } + if (has_branch_stack(event)) + perf_sample_save_brstack(&data, event, &cpuc->lbr_stack); if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 070cc4ef2672..89b9c1cebb61 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4074,7 +4074,7 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data) if (x86_pmu.intel_cap.pebs_baseline) { arr[(*nr)++] = (struct perf_guest_switch_msr){ .msr = MSR_PEBS_DATA_CFG, - .host = cpuc->pebs_data_cfg, + .host = cpuc->active_pebs_data_cfg, .guest = kvm_pmu->pebs_data_cfg, }; } diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index a2e566e53076..df88576d6b2a 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1229,12 +1229,14 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct perf_event *event, bool add) { struct pmu *pmu = event->pmu; + /* * Make sure we get updated with the first PEBS * event. It will trigger also during removal, but * that does not hurt: */ - bool update = cpuc->n_pebs == 1; + if (cpuc->n_pebs == 1) + cpuc->pebs_data_cfg = PEBS_UPDATE_DS_SW; if (needed_cb != pebs_needs_sched_cb(cpuc)) { if (!needed_cb) @@ -1242,7 +1244,7 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, else perf_sched_cb_dec(pmu); - update = true; + cpuc->pebs_data_cfg |= PEBS_UPDATE_DS_SW; } /* @@ -1252,24 +1254,13 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, if (x86_pmu.intel_cap.pebs_baseline && add) { u64 pebs_data_cfg; - /* Clear pebs_data_cfg and pebs_record_size for first PEBS. */ - if (cpuc->n_pebs == 1) { - cpuc->pebs_data_cfg = 0; - cpuc->pebs_record_size = sizeof(struct pebs_basic); - } - pebs_data_cfg = pebs_update_adaptive_cfg(event); - - /* Update pebs_record_size if new event requires more data. */ - if (pebs_data_cfg & ~cpuc->pebs_data_cfg) { - cpuc->pebs_data_cfg |= pebs_data_cfg; - adaptive_pebs_record_size_update(); - update = true; - } + /* + * Be sure to update the thresholds when we change the record. + */ + if (pebs_data_cfg & ~cpuc->pebs_data_cfg) + cpuc->pebs_data_cfg |= pebs_data_cfg | PEBS_UPDATE_DS_SW; } - - if (update) - pebs_update_threshold(cpuc); } void intel_pmu_pebs_add(struct perf_event *event) @@ -1326,9 +1317,17 @@ static void intel_pmu_pebs_via_pt_enable(struct perf_event *event) wrmsrl(base + idx, value); } +static inline void intel_pmu_drain_large_pebs(struct cpu_hw_events *cpuc) +{ + if (cpuc->n_pebs == cpuc->n_large_pebs && + cpuc->n_pebs != cpuc->n_pebs_via_pt) + intel_pmu_drain_pebs_buffer(); +} + void intel_pmu_pebs_enable(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + u64 pebs_data_cfg = cpuc->pebs_data_cfg & ~PEBS_UPDATE_DS_SW; struct hw_perf_event *hwc = &event->hw; struct debug_store *ds = cpuc->ds; unsigned int idx = hwc->idx; @@ -1344,11 +1343,22 @@ void intel_pmu_pebs_enable(struct perf_event *event) if (x86_pmu.intel_cap.pebs_baseline) { hwc->config |= ICL_EVENTSEL_ADAPTIVE; - if (cpuc->pebs_data_cfg != cpuc->active_pebs_data_cfg) { - wrmsrl(MSR_PEBS_DATA_CFG, cpuc->pebs_data_cfg); - cpuc->active_pebs_data_cfg = cpuc->pebs_data_cfg; + if (pebs_data_cfg != cpuc->active_pebs_data_cfg) { + /* + * drain_pebs() assumes uniform record size; + * hence we need to drain when changing said + * size. + */ + intel_pmu_drain_large_pebs(cpuc); + adaptive_pebs_record_size_update(); + wrmsrl(MSR_PEBS_DATA_CFG, pebs_data_cfg); + cpuc->active_pebs_data_cfg = pebs_data_cfg; } } + if (cpuc->pebs_data_cfg & PEBS_UPDATE_DS_SW) { + cpuc->pebs_data_cfg = pebs_data_cfg; + pebs_update_threshold(cpuc); + } if (idx >= INTEL_PMC_IDX_FIXED) { if (x86_pmu.intel_cap.pebs_format < 5) @@ -1391,9 +1401,7 @@ void intel_pmu_pebs_disable(struct perf_event *event) struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; - if (cpuc->n_pebs == cpuc->n_large_pebs && - cpuc->n_pebs != cpuc->n_pebs_via_pt) - intel_pmu_drain_pebs_buffer(); + intel_pmu_drain_large_pebs(cpuc); cpuc->pebs_enabled &= ~(1ULL << hwc->idx); diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index fa9b209a11fa..d49e90dc04a4 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -6150,6 +6150,7 @@ static struct intel_uncore_type spr_uncore_mdf = { }; #define UNCORE_SPR_NUM_UNCORE_TYPES 12 +#define UNCORE_SPR_CHA 0 #define UNCORE_SPR_IIO 1 #define UNCORE_SPR_IMC 6 #define UNCORE_SPR_UPI 8 @@ -6460,12 +6461,22 @@ static int uncore_type_max_boxes(struct intel_uncore_type **types, return max + 1; } +#define SPR_MSR_UNC_CBO_CONFIG 0x2FFE + void spr_uncore_cpu_init(void) { + struct intel_uncore_type *type; + u64 num_cbo; + uncore_msr_uncores = uncore_get_uncores(UNCORE_ACCESS_MSR, UNCORE_SPR_MSR_EXTRA_UNCORES, spr_msr_uncores); + type = uncore_find_type_by_id(uncore_msr_uncores, UNCORE_SPR_CHA); + if (type) { + rdmsrl(SPR_MSR_UNC_CBO_CONFIG, num_cbo); + type->num_boxes = num_cbo; + } spr_uncore_iio_free_running.num_boxes = uncore_type_max_boxes(uncore_msr_uncores, UNCORE_SPR_IIO); } diff --git a/arch/x86/include/asm/fpu/sched.h b/arch/x86/include/asm/fpu/sched.h index c2d6cd78ed0c..78fcde7b1f07 100644 --- a/arch/x86/include/asm/fpu/sched.h +++ b/arch/x86/include/asm/fpu/sched.h @@ -39,7 +39,7 @@ extern void fpu_flush_thread(void); static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu) { if (cpu_feature_enabled(X86_FEATURE_FPU) && - !(current->flags & (PF_KTHREAD | PF_IO_WORKER))) { + !(current->flags & (PF_KTHREAD | PF_USER_WORKER))) { save_fpregs_to_fpstate(old_fpu); /* * The save operation preserved register state, so the diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 8fc15ed5e60b..abf09882f58b 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -121,6 +121,9 @@ #define PEBS_DATACFG_LBRS BIT_ULL(3) #define PEBS_DATACFG_LBR_SHIFT 24 +/* Steal the highest bit of pebs_data_cfg for SW usage */ +#define PEBS_UPDATE_DS_SW BIT_ULL(63) + /* * Intel "Architectural Performance Monitoring" CPUID * detection/enumeration details: diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 498dc600bd5c..0d02c4aafa6f 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -13,7 +13,9 @@ #include <linux/bitops.h> +#include <linux/bug.h> #include <linux/types.h> + #include <uapi/asm/vmx.h> #include <asm/vmxfeatures.h> diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index dd61752f4c96..4070a01c11b7 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -17,6 +17,7 @@ CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg CFLAGS_REMOVE_head64.o = -pg CFLAGS_REMOVE_sev.o = -pg +CFLAGS_REMOVE_rethook.o = -pg endif KASAN_SANITIZE_head$(BITS).o := n diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 4266b64631a4..7e331e8f3692 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -36,6 +36,7 @@ #define PCI_DEVICE_ID_AMD_19H_M50H_DF_F4 0x166e #define PCI_DEVICE_ID_AMD_19H_M60H_DF_F4 0x14e4 #define PCI_DEVICE_ID_AMD_19H_M70H_DF_F4 0x14f4 +#define PCI_DEVICE_ID_AMD_19H_M78H_DF_F4 0x12fc /* Protect the PCI config register pairs used for SMN. */ static DEFINE_MUTEX(smn_mutex); @@ -79,6 +80,7 @@ static const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M50H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M60H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M70H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F3) }, {} }; diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 5e868b62a7c4..0270925fe013 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -79,7 +79,7 @@ int detect_extended_topology_early(struct cpuinfo_x86 *c) * initial apic id, which also represents 32-bit extended x2apic id. */ c->initial_apicid = edx; - smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx); + smp_num_siblings = max_t(int, smp_num_siblings, LEVEL_MAX_SIBLINGS(ebx)); #endif return 0; } @@ -109,7 +109,8 @@ int detect_extended_topology(struct cpuinfo_x86 *c) */ cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx); c->initial_apicid = edx; - core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx); + core_level_siblings = LEVEL_MAX_SIBLINGS(ebx); + smp_num_siblings = max_t(int, smp_num_siblings, LEVEL_MAX_SIBLINGS(ebx)); core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); die_level_siblings = LEVEL_MAX_SIBLINGS(ebx); pkg_mask_width = die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 0bf6779187dd..f18ca44c904b 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -195,7 +195,6 @@ static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, printk("%sCall Trace:\n", log_lvl); unwind_start(&state, task, regs, stack); - stack = stack ? : get_stack_pointer(task, regs); regs = unwind_get_entry_regs(&state, &partial); /* @@ -214,9 +213,13 @@ static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, * - hardirq stack * - entry stack */ - for ( ; stack; stack = PTR_ALIGN(stack_info.next_sp, sizeof(long))) { + for (stack = stack ?: get_stack_pointer(task, regs); + stack; + stack = stack_info.next_sp) { const char *stack_name; + stack = PTR_ALIGN(stack, sizeof(long)); + if (get_stack_info(stack, task, &stack_info, &visit_mask)) { /* * We weren't on a valid stack. It's possible that diff --git a/arch/x86/kernel/fpu/context.h b/arch/x86/kernel/fpu/context.h index 9fcfa5c4dad7..af5cbdd9bd29 100644 --- a/arch/x86/kernel/fpu/context.h +++ b/arch/x86/kernel/fpu/context.h @@ -57,7 +57,7 @@ static inline void fpregs_restore_userregs(void) struct fpu *fpu = ¤t->thread.fpu; int cpu = smp_processor_id(); - if (WARN_ON_ONCE(current->flags & (PF_KTHREAD | PF_IO_WORKER))) + if (WARN_ON_ONCE(current->flags & (PF_KTHREAD | PF_USER_WORKER))) return; if (!fpregs_state_valid(fpu, cpu)) { diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index caf33486dc5e..1015af1ae562 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -426,7 +426,7 @@ void kernel_fpu_begin_mask(unsigned int kfpu_mask) this_cpu_write(in_kernel_fpu, true); - if (!(current->flags & (PF_KTHREAD | PF_IO_WORKER)) && + if (!(current->flags & (PF_KTHREAD | PF_USER_WORKER)) && !test_thread_flag(TIF_NEED_FPU_LOAD)) { set_thread_flag(TIF_NEED_FPU_LOAD); save_fpregs_to_fpstate(¤t->thread.fpu); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 123bf8b97a4b..0c9660a07b23 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -253,7 +253,6 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e int nent) { struct kvm_cpuid_entry2 *best; - u64 guest_supported_xcr0 = cpuid_get_supported_xcr0(entries, nent); best = cpuid_entry2_find(entries, nent, 1, KVM_CPUID_INDEX_NOT_SIGNIFICANT); if (best) { @@ -292,21 +291,6 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e vcpu->arch.ia32_misc_enable_msr & MSR_IA32_MISC_ENABLE_MWAIT); } - - /* - * Bits 127:0 of the allowed SECS.ATTRIBUTES (CPUID.0x12.0x1) enumerate - * the supported XSAVE Feature Request Mask (XFRM), i.e. the enclave's - * requested XCR0 value. The enclave's XFRM must be a subset of XCRO - * at the time of EENTER, thus adjust the allowed XFRM by the guest's - * supported XCR0. Similar to XCR0 handling, FP and SSE are forced to - * '1' even on CPUs that don't support XSAVE. - */ - best = cpuid_entry2_find(entries, nent, 0x12, 0x1); - if (best) { - best->ecx &= guest_supported_xcr0 & 0xffffffff; - best->edx &= guest_supported_xcr0 >> 32; - best->ecx |= XFEATURE_MASK_FPSSE; - } } void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index e542cf285b51..3c300a196bdf 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -229,6 +229,23 @@ static int kvm_recalculate_phys_map(struct kvm_apic_map *new, u32 physical_id; /* + * For simplicity, KVM always allocates enough space for all possible + * xAPIC IDs. Yell, but don't kill the VM, as KVM can continue on + * without the optimized map. + */ + if (WARN_ON_ONCE(xapic_id > new->max_apic_id)) + return -EINVAL; + + /* + * Bail if a vCPU was added and/or enabled its APIC between allocating + * the map and doing the actual calculations for the map. Note, KVM + * hardcodes the x2APIC ID to vcpu_id, i.e. there's no TOCTOU bug if + * the compiler decides to reload x2apic_id after this check. + */ + if (x2apic_id > new->max_apic_id) + return -E2BIG; + + /* * Deliberately truncate the vCPU ID when detecting a mismatched APIC * ID to avoid false positives if the vCPU ID, i.e. x2APIC ID, is a * 32-bit value. Any unwanted aliasing due to truncation results will @@ -253,8 +270,7 @@ static int kvm_recalculate_phys_map(struct kvm_apic_map *new, */ if (vcpu->kvm->arch.x2apic_format) { /* See also kvm_apic_match_physical_addr(). */ - if ((apic_x2apic_mode(apic) || x2apic_id > 0xff) && - x2apic_id <= new->max_apic_id) + if (apic_x2apic_mode(apic) || x2apic_id > 0xff) new->phys_map[x2apic_id] = apic; if (!apic_x2apic_mode(apic) && !new->phys_map[xapic_id]) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index c8961f45e3b1..6eaa3d6994ae 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -7091,7 +7091,10 @@ static void kvm_recover_nx_huge_pages(struct kvm *kvm) */ slot = NULL; if (atomic_read(&kvm->nr_memslots_dirty_logging)) { - slot = gfn_to_memslot(kvm, sp->gfn); + struct kvm_memslots *slots; + + slots = kvm_memslots_for_spte_role(kvm, sp->role); + slot = __gfn_to_memslot(slots, sp->gfn); WARN_ON_ONCE(!slot); } diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index ca32389f3c36..54089f990c8f 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3510,7 +3510,7 @@ static bool svm_is_vnmi_pending(struct kvm_vcpu *vcpu) if (!is_vnmi_enabled(svm)) return false; - return !!(svm->vmcb->control.int_ctl & V_NMI_BLOCKING_MASK); + return !!(svm->vmcb->control.int_ctl & V_NMI_PENDING_MASK); } static bool svm_set_vnmi_pending(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c index 0574030b071f..2261b684a7d4 100644 --- a/arch/x86/kvm/vmx/sgx.c +++ b/arch/x86/kvm/vmx/sgx.c @@ -170,12 +170,19 @@ static int __handle_encls_ecreate(struct kvm_vcpu *vcpu, return 1; } - /* Enforce CPUID restrictions on MISCSELECT, ATTRIBUTES and XFRM. */ + /* + * Enforce CPUID restrictions on MISCSELECT, ATTRIBUTES and XFRM. Note + * that the allowed XFRM (XFeature Request Mask) isn't strictly bound + * by the supported XCR0. FP+SSE *must* be set in XFRM, even if XSAVE + * is unsupported, i.e. even if XCR0 itself is completely unsupported. + */ if ((u32)miscselect & ~sgx_12_0->ebx || (u32)attributes & ~sgx_12_1->eax || (u32)(attributes >> 32) & ~sgx_12_1->ebx || (u32)xfrm & ~sgx_12_1->ecx || - (u32)(xfrm >> 32) & ~sgx_12_1->edx) { + (u32)(xfrm >> 32) & ~sgx_12_1->edx || + xfrm & ~(vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FPSSE) || + (xfrm & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) { kvm_inject_gp(vcpu, 0); return 1; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ceb7c5e9cf9e..04b57a336b34 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1446,7 +1446,7 @@ static const u32 msrs_to_save_base[] = { #endif MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, MSR_IA32_FEAT_CTL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, - MSR_IA32_SPEC_CTRL, + MSR_IA32_SPEC_CTRL, MSR_IA32_TSX_CTRL, MSR_IA32_RTIT_CTL, MSR_IA32_RTIT_STATUS, MSR_IA32_RTIT_CR3_MATCH, MSR_IA32_RTIT_OUTPUT_BASE, MSR_IA32_RTIT_OUTPUT_MASK, MSR_IA32_RTIT_ADDR0_A, MSR_IA32_RTIT_ADDR0_B, @@ -7155,6 +7155,10 @@ static void kvm_probe_msr_to_save(u32 msr_index) if (!kvm_cpu_cap_has(X86_FEATURE_XFD)) return; break; + case MSR_IA32_TSX_CTRL: + if (!(kvm_get_arch_capabilities() & ARCH_CAP_TSX_CTRL_MSR)) + return; + break; default: break; } @@ -10754,6 +10758,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED; break; } + + /* Note, VM-Exits that go down the "slow" path are accounted below. */ + ++vcpu->stat.exits; } /* diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 4fc5c2de2de4..01c5de4c279b 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -7,6 +7,8 @@ */ #include <linux/linkage.h> +#include <asm/cpufeatures.h> +#include <asm/alternative.h> #include <asm/asm.h> #include <asm/export.h> @@ -29,7 +31,7 @@ */ SYM_FUNC_START(rep_movs_alternative) cmpq $64,%rcx - jae .Lunrolled + jae .Llarge cmp $8,%ecx jae .Lword @@ -65,6 +67,12 @@ SYM_FUNC_START(rep_movs_alternative) _ASM_EXTABLE_UA( 2b, .Lcopy_user_tail) _ASM_EXTABLE_UA( 3b, .Lcopy_user_tail) +.Llarge: +0: ALTERNATIVE "jmp .Lunrolled", "rep movsb", X86_FEATURE_ERMS +1: RET + + _ASM_EXTABLE_UA( 0b, 1b) + .p2align 4 .Lunrolled: 10: movq (%rsi),%r8 diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 27ef53fab6bd..b3b1e376dce8 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -144,8 +144,8 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array) */ .align 64 .skip 63, 0xcc -SYM_FUNC_START_NOALIGN(zen_untrain_ret); - +SYM_START(zen_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) + ANNOTATE_NOENDBR /* * As executed from zen_untrain_ret, this is: * diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 3cdac0f0055d..8192452d1d2d 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -9,6 +9,7 @@ #include <linux/sched/task.h> #include <asm/set_memory.h> +#include <asm/cpu_device_id.h> #include <asm/e820/api.h> #include <asm/init.h> #include <asm/page.h> @@ -261,6 +262,24 @@ static void __init probe_page_size_mask(void) } } +#define INTEL_MATCH(_model) { .vendor = X86_VENDOR_INTEL, \ + .family = 6, \ + .model = _model, \ + } +/* + * INVLPG may not properly flush Global entries + * on these CPUs when PCIDs are enabled. + */ +static const struct x86_cpu_id invlpg_miss_ids[] = { + INTEL_MATCH(INTEL_FAM6_ALDERLAKE ), + INTEL_MATCH(INTEL_FAM6_ALDERLAKE_L ), + INTEL_MATCH(INTEL_FAM6_ALDERLAKE_N ), + INTEL_MATCH(INTEL_FAM6_RAPTORLAKE ), + INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_P), + INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_S), + {} +}; + static void setup_pcid(void) { if (!IS_ENABLED(CONFIG_X86_64)) @@ -269,6 +288,12 @@ static void setup_pcid(void) if (!boot_cpu_has(X86_FEATURE_PCID)) return; + if (x86_match_cpu(invlpg_miss_ids)) { + pr_info("Incomplete global flushes, disabling PCID"); + setup_clear_cpu_cap(X86_FEATURE_PCID); + return; + } + if (boot_cpu_has(X86_FEATURE_PGE)) { /* * This can't be cr4_set_bits_and_update_boot() -- the diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 8babce71915f..014c508e914d 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -198,7 +198,7 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) i++; } kfree(v); - return 0; + return msi_device_populate_sysfs(&dev->dev); error: if (ret == -ENOSYS) @@ -254,7 +254,7 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) dev_dbg(&dev->dev, "xen: msi --> pirq=%d --> irq=%d\n", pirq, irq); } - return 0; + return msi_device_populate_sysfs(&dev->dev); error: dev_err(&dev->dev, "Failed to create MSI%s! ret=%d!\n", @@ -346,7 +346,7 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) if (ret < 0) goto out; } - ret = 0; + ret = msi_device_populate_sysfs(&dev->dev); out: return ret; } @@ -394,6 +394,8 @@ static void xen_teardown_msi_irqs(struct pci_dev *dev) xen_destroy_irq(msidesc->irq + i); msidesc->irq = 0; } + + msi_device_destroy_sysfs(&dev->dev); } static void xen_pv_teardown_msi_irqs(struct pci_dev *dev) diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c index 876d5df157ed..5c01d7e70d90 100644 --- a/arch/xtensa/kernel/signal.c +++ b/arch/xtensa/kernel/signal.c @@ -343,7 +343,19 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set, struct rt_sigframe *frame; int err = 0, sig = ksig->sig; unsigned long sp, ra, tp, ps; + unsigned long handler = (unsigned long)ksig->ka.sa.sa_handler; + unsigned long handler_fdpic_GOT = 0; unsigned int base; + bool fdpic = IS_ENABLED(CONFIG_BINFMT_ELF_FDPIC) && + (current->personality & FDPIC_FUNCPTRS); + + if (fdpic) { + unsigned long __user *fdpic_func_desc = + (unsigned long __user *)handler; + if (__get_user(handler, &fdpic_func_desc[0]) || + __get_user(handler_fdpic_GOT, &fdpic_func_desc[1])) + return -EFAULT; + } sp = regs->areg[1]; @@ -373,20 +385,26 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set, err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); if (ksig->ka.sa.sa_flags & SA_RESTORER) { - ra = (unsigned long)ksig->ka.sa.sa_restorer; + if (fdpic) { + unsigned long __user *fdpic_func_desc = + (unsigned long __user *)ksig->ka.sa.sa_restorer; + + err |= __get_user(ra, fdpic_func_desc); + } else { + ra = (unsigned long)ksig->ka.sa.sa_restorer; + } } else { /* Create sys_rt_sigreturn syscall in stack frame */ err |= gen_return_code(frame->retcode); - - if (err) { - return -EFAULT; - } ra = (unsigned long) frame->retcode; } - /* + if (err) + return -EFAULT; + + /* * Create signal handler execution context. * Return context not modified until this point. */ @@ -394,8 +412,7 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set, /* Set up registers for signal handler; preserve the threadptr */ tp = regs->threadptr; ps = regs->ps; - start_thread(regs, (unsigned long) ksig->ka.sa.sa_handler, - (unsigned long) frame); + start_thread(regs, handler, (unsigned long)frame); /* Set up a stack frame for a call4 if userspace uses windowed ABI */ if (ps & PS_WOE_MASK) { @@ -413,6 +430,8 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set, regs->areg[base + 4] = (unsigned long) &frame->uc; regs->threadptr = tp; regs->ps = ps; + if (fdpic) + regs->areg[base + 11] = handler_fdpic_GOT; pr_debug("SIG rt deliver (%s:%d): signal=%d sp=%p pc=%08lx\n", current->comm, current->pid, sig, frame, regs->pc); diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c index 2a31b1ab0c9f..17a7ef86fd0d 100644 --- a/arch/xtensa/kernel/xtensa_ksyms.c +++ b/arch/xtensa/kernel/xtensa_ksyms.c @@ -56,6 +56,8 @@ EXPORT_SYMBOL(empty_zero_page); */ extern long long __ashrdi3(long long, int); extern long long __ashldi3(long long, int); +extern long long __bswapdi2(long long); +extern int __bswapsi2(int); extern long long __lshrdi3(long long, int); extern int __divsi3(int, int); extern int __modsi3(int, int); @@ -66,6 +68,8 @@ extern unsigned long long __umulsidi3(unsigned int, unsigned int); EXPORT_SYMBOL(__ashldi3); EXPORT_SYMBOL(__ashrdi3); +EXPORT_SYMBOL(__bswapdi2); +EXPORT_SYMBOL(__bswapsi2); EXPORT_SYMBOL(__lshrdi3); EXPORT_SYMBOL(__divsi3); EXPORT_SYMBOL(__modsi3); diff --git a/arch/xtensa/lib/Makefile b/arch/xtensa/lib/Makefile index 7ecef0519a27..c9c2614188f7 100644 --- a/arch/xtensa/lib/Makefile +++ b/arch/xtensa/lib/Makefile @@ -4,7 +4,7 @@ # lib-y += memcopy.o memset.o checksum.o \ - ashldi3.o ashrdi3.o lshrdi3.o \ + ashldi3.o ashrdi3.o bswapdi2.o bswapsi2.o lshrdi3.o \ divsi3.o udivsi3.o modsi3.o umodsi3.o mulsi3.o umulsidi3.o \ usercopy.o strncpy_user.o strnlen_user.o lib-$(CONFIG_PCI) += pci-auto.o diff --git a/arch/xtensa/lib/bswapdi2.S b/arch/xtensa/lib/bswapdi2.S new file mode 100644 index 000000000000..d8e52e05eba6 --- /dev/null +++ b/arch/xtensa/lib/bswapdi2.S @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later WITH GCC-exception-2.0 */ +#include <linux/linkage.h> +#include <asm/asmmacro.h> +#include <asm/core.h> + +ENTRY(__bswapdi2) + + abi_entry_default + ssai 8 + srli a4, a2, 16 + src a4, a4, a2 + src a4, a4, a4 + src a4, a2, a4 + srli a2, a3, 16 + src a2, a2, a3 + src a2, a2, a2 + src a2, a3, a2 + mov a3, a4 + abi_ret_default + +ENDPROC(__bswapdi2) diff --git a/arch/xtensa/lib/bswapsi2.S b/arch/xtensa/lib/bswapsi2.S new file mode 100644 index 000000000000..9c1de1344f79 --- /dev/null +++ b/arch/xtensa/lib/bswapsi2.S @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later WITH GCC-exception-2.0 */ +#include <linux/linkage.h> +#include <asm/asmmacro.h> +#include <asm/core.h> + +ENTRY(__bswapsi2) + + abi_entry_default + ssai 8 + srli a3, a2, 16 + src a3, a3, a2 + src a3, a3, a3 + src a2, a2, a3 + abi_ret_default + +ENDPROC(__bswapsi2) diff --git a/block/blk-core.c b/block/blk-core.c index 00c74330fa92..1da77e7d6289 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -520,7 +520,7 @@ static inline int bio_check_eod(struct bio *bio) sector_t maxsector = bdev_nr_sectors(bio->bi_bdev); unsigned int nr_sectors = bio_sectors(bio); - if (nr_sectors && maxsector && + if (nr_sectors && (nr_sectors > maxsector || bio->bi_iter.bi_sector > maxsector - nr_sectors)) { pr_info_ratelimited("%s: attempt to access beyond end of device\n" diff --git a/block/blk-map.c b/block/blk-map.c index 04c55f1c492e..46eed2e627c3 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -248,7 +248,7 @@ static struct bio *blk_rq_map_bio_alloc(struct request *rq, { struct bio *bio; - if (rq->cmd_flags & REQ_ALLOC_CACHE) { + if (rq->cmd_flags & REQ_ALLOC_CACHE && (nr_vecs <= BIO_INLINE_VECS)) { bio = bio_alloc_bioset(NULL, nr_vecs, rq->cmd_flags, gfp_mask, &fs_bio_set); if (!bio) diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index d6af9d431dc6..dfd81cab5788 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -39,16 +39,20 @@ void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) { unsigned int users; + /* + * calling test_bit() prior to test_and_set_bit() is intentional, + * it avoids dirtying the cacheline if the queue is already active. + */ if (blk_mq_is_shared_tags(hctx->flags)) { struct request_queue *q = hctx->queue; - if (test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) + if (test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags) || + test_and_set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) return; - set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags); } else { - if (test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) + if (test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) || + test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) return; - set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state); } users = atomic_inc_return(&hctx->tags->active_queues); diff --git a/block/blk-settings.c b/block/blk-settings.c index 896b4654ab00..4dd59059b788 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -915,6 +915,7 @@ static bool disk_has_partitions(struct gendisk *disk) void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model) { struct request_queue *q = disk->queue; + unsigned int old_model = q->limits.zoned; switch (model) { case BLK_ZONED_HM: @@ -952,7 +953,7 @@ void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model) */ blk_queue_zone_write_granularity(q, queue_logical_block_size(q)); - } else { + } else if (old_model != BLK_ZONED_NONE) { disk_clear_zone_settings(disk); } } diff --git a/block/blk-wbt.c b/block/blk-wbt.c index e49a48684532..9ec2a2f1eda3 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -730,14 +730,16 @@ void wbt_enable_default(struct gendisk *disk) { struct request_queue *q = disk->queue; struct rq_qos *rqos; - bool disable_flag = q->elevator && - test_bit(ELEVATOR_FLAG_DISABLE_WBT, &q->elevator->flags); + bool enable = IS_ENABLED(CONFIG_BLK_WBT_MQ); + + if (q->elevator && + test_bit(ELEVATOR_FLAG_DISABLE_WBT, &q->elevator->flags)) + enable = false; /* Throttling already enabled? */ rqos = wbt_rq_qos(q); if (rqos) { - if (!disable_flag && - RQWB(rqos)->enable_state == WBT_STATE_OFF_DEFAULT) + if (enable && RQWB(rqos)->enable_state == WBT_STATE_OFF_DEFAULT) RQWB(rqos)->enable_state = WBT_STATE_ON_DEFAULT; return; } @@ -746,7 +748,7 @@ void wbt_enable_default(struct gendisk *disk) if (!blk_queue_registered(q)) return; - if (queue_is_mq(q) && !disable_flag) + if (queue_is_mq(q) && enable) wbt_init(disk); } EXPORT_SYMBOL_GPL(wbt_enable_default); diff --git a/block/fops.c b/block/fops.c index d2e6be4e3d1c..58d0aebc7313 100644 --- a/block/fops.c +++ b/block/fops.c @@ -678,6 +678,16 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start, return error; } +static int blkdev_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct inode *bd_inode = bdev_file_inode(file); + + if (bdev_read_only(I_BDEV(bd_inode))) + return generic_file_readonly_mmap(file, vma); + + return generic_file_mmap(file, vma); +} + const struct file_operations def_blk_fops = { .open = blkdev_open, .release = blkdev_close, @@ -685,7 +695,7 @@ const struct file_operations def_blk_fops = { .read_iter = blkdev_read_iter, .write_iter = blkdev_write_iter, .iopoll = iocb_bio_iopoll, - .mmap = generic_file_mmap, + .mmap = blkdev_mmap, .fsync = blkdev_fsync, .unlocked_ioctl = blkdev_ioctl, #ifdef CONFIG_COMPAT diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 5f7252a5b7b4..7d4b6016b83d 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -531,50 +531,25 @@ static const struct net_proto_family alg_family = { .owner = THIS_MODULE, }; -int af_alg_make_sg(struct af_alg_sgl *sgl, struct iov_iter *iter, int len) -{ - size_t off; - ssize_t n; - int npages, i; - - n = iov_iter_get_pages2(iter, sgl->pages, len, ALG_MAX_PAGES, &off); - if (n < 0) - return n; - - npages = DIV_ROUND_UP(off + n, PAGE_SIZE); - if (WARN_ON(npages == 0)) - return -EINVAL; - /* Add one extra for linking */ - sg_init_table(sgl->sg, npages + 1); - - for (i = 0, len = n; i < npages; i++) { - int plen = min_t(int, len, PAGE_SIZE - off); - - sg_set_page(sgl->sg + i, sgl->pages[i], plen, off); - - off = 0; - len -= plen; - } - sg_mark_end(sgl->sg + npages - 1); - sgl->npages = npages; - - return n; -} -EXPORT_SYMBOL_GPL(af_alg_make_sg); - static void af_alg_link_sg(struct af_alg_sgl *sgl_prev, struct af_alg_sgl *sgl_new) { - sg_unmark_end(sgl_prev->sg + sgl_prev->npages - 1); - sg_chain(sgl_prev->sg, sgl_prev->npages + 1, sgl_new->sg); + sg_unmark_end(sgl_prev->sgt.sgl + sgl_prev->sgt.nents - 1); + sg_chain(sgl_prev->sgt.sgl, sgl_prev->sgt.nents + 1, sgl_new->sgt.sgl); } void af_alg_free_sg(struct af_alg_sgl *sgl) { int i; - for (i = 0; i < sgl->npages; i++) - put_page(sgl->pages[i]); + if (sgl->sgt.sgl) { + if (sgl->need_unpin) + for (i = 0; i < sgl->sgt.nents; i++) + unpin_user_page(sg_page(&sgl->sgt.sgl[i])); + if (sgl->sgt.sgl != sgl->sgl) + kvfree(sgl->sgt.sgl); + sgl->sgt.sgl = NULL; + } } EXPORT_SYMBOL_GPL(af_alg_free_sg); @@ -1015,7 +990,7 @@ int af_alg_sendmsg(struct socket *sock, struct msghdr *msg, size_t size, while (size) { struct scatterlist *sg; size_t len = size; - size_t plen; + ssize_t plen; /* use the existing memory in an allocated page */ if (ctx->merge) { @@ -1060,35 +1035,58 @@ int af_alg_sendmsg(struct socket *sock, struct msghdr *msg, size_t size, if (sgl->cur) sg_unmark_end(sg + sgl->cur - 1); - do { - struct page *pg; - unsigned int i = sgl->cur; - - plen = min_t(size_t, len, PAGE_SIZE); - - pg = alloc_page(GFP_KERNEL); - if (!pg) { - err = -ENOMEM; + if (msg->msg_flags & MSG_SPLICE_PAGES) { + struct sg_table sgtable = { + .sgl = sg, + .nents = sgl->cur, + .orig_nents = sgl->cur, + }; + + plen = extract_iter_to_sg(&msg->msg_iter, len, &sgtable, + MAX_SGL_ENTS, 0); + if (plen < 0) { + err = plen; goto unlock; } - sg_assign_page(sg + i, pg); - - err = memcpy_from_msg(page_address(sg_page(sg + i)), - msg, plen); - if (err) { - __free_page(sg_page(sg + i)); - sg_assign_page(sg + i, NULL); - goto unlock; - } - - sg[i].length = plen; + for (; sgl->cur < sgtable.nents; sgl->cur++) + get_page(sg_page(&sg[sgl->cur])); len -= plen; ctx->used += plen; copied += plen; size -= plen; - sgl->cur++; - } while (len && sgl->cur < MAX_SGL_ENTS); + } else { + do { + struct page *pg; + unsigned int i = sgl->cur; + + plen = min_t(size_t, len, PAGE_SIZE); + + pg = alloc_page(GFP_KERNEL); + if (!pg) { + err = -ENOMEM; + goto unlock; + } + + sg_assign_page(sg + i, pg); + + err = memcpy_from_msg( + page_address(sg_page(sg + i)), + msg, plen); + if (err) { + __free_page(sg_page(sg + i)); + sg_assign_page(sg + i, NULL); + goto unlock; + } + + sg[i].length = plen; + len -= plen; + ctx->used += plen; + copied += plen; + size -= plen; + sgl->cur++; + } while (len && sgl->cur < MAX_SGL_ENTS); + } if (!size) sg_mark_end(sg + sgl->cur - 1); @@ -1121,53 +1119,17 @@ EXPORT_SYMBOL_GPL(af_alg_sendmsg); ssize_t af_alg_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { - struct sock *sk = sock->sk; - struct alg_sock *ask = alg_sk(sk); - struct af_alg_ctx *ctx = ask->private; - struct af_alg_tsgl *sgl; - int err = -EINVAL; + struct bio_vec bvec; + struct msghdr msg = { + .msg_flags = flags | MSG_SPLICE_PAGES, + }; if (flags & MSG_SENDPAGE_NOTLAST) - flags |= MSG_MORE; - - lock_sock(sk); - if (!ctx->more && ctx->used) - goto unlock; - - if (!size) - goto done; - - if (!af_alg_writable(sk)) { - err = af_alg_wait_for_wmem(sk, flags); - if (err) - goto unlock; - } - - err = af_alg_alloc_tsgl(sk); - if (err) - goto unlock; - - ctx->merge = 0; - sgl = list_entry(ctx->tsgl_list.prev, struct af_alg_tsgl, list); - - if (sgl->cur) - sg_unmark_end(sgl->sg + sgl->cur - 1); - - sg_mark_end(sgl->sg + sgl->cur); - - get_page(page); - sg_set_page(sgl->sg + sgl->cur, page, size, offset); - sgl->cur++; - ctx->used += size; + msg.msg_flags |= MSG_MORE; -done: - ctx->more = flags & MSG_MORE; - -unlock: - af_alg_data_wakeup(sk); - release_sock(sk); - - return err ?: size; + bvec_set_page(&bvec, page, size, offset); + iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); + return sock_sendmsg(sock, &msg); } EXPORT_SYMBOL_GPL(af_alg_sendpage); @@ -1288,8 +1250,8 @@ int af_alg_get_rsgl(struct sock *sk, struct msghdr *msg, int flags, while (maxsize > len && msg_data_left(msg)) { struct af_alg_rsgl *rsgl; + ssize_t err; size_t seglen; - int err; /* limit the amount of readable buffers */ if (!af_alg_readable(sk)) @@ -1306,16 +1268,23 @@ int af_alg_get_rsgl(struct sock *sk, struct msghdr *msg, int flags, return -ENOMEM; } - rsgl->sgl.npages = 0; + rsgl->sgl.sgt.sgl = rsgl->sgl.sgl; + rsgl->sgl.sgt.nents = 0; + rsgl->sgl.sgt.orig_nents = 0; list_add_tail(&rsgl->list, &areq->rsgl_list); - /* make one iovec available as scatterlist */ - err = af_alg_make_sg(&rsgl->sgl, &msg->msg_iter, seglen); + sg_init_table(rsgl->sgl.sgt.sgl, ALG_MAX_PAGES); + err = extract_iter_to_sg(&msg->msg_iter, seglen, &rsgl->sgl.sgt, + ALG_MAX_PAGES, 0); if (err < 0) { rsgl->sg_num_bytes = 0; return err; } + sg_mark_end(rsgl->sgl.sgt.sgl + rsgl->sgl.sgt.nents - 1); + rsgl->sgl.need_unpin = + iov_iter_extract_will_pin(&msg->msg_iter); + /* chain the new scatterlist with previous one */ if (areq->last_rsgl) af_alg_link_sg(&areq->last_rsgl->sgl, &rsgl->sgl); diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c index 42493b4d8ce4..35bfa283748d 100644 --- a/crypto/algif_aead.c +++ b/crypto/algif_aead.c @@ -9,8 +9,8 @@ * The following concept of the memory management is used: * * The kernel maintains two SGLs, the TX SGL and the RX SGL. The TX SGL is - * filled by user space with the data submitted via sendpage/sendmsg. Filling - * up the TX SGL does not cause a crypto operation -- the data will only be + * filled by user space with the data submitted via sendpage. Filling up + * the TX SGL does not cause a crypto operation -- the data will only be * tracked by the kernel. Upon receipt of one recvmsg call, the caller must * provide a buffer which is tracked with the RX SGL. * @@ -113,19 +113,19 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg, } /* - * Data length provided by caller via sendmsg/sendpage that has not - * yet been processed. + * Data length provided by caller via sendmsg that has not yet been + * processed. */ used = ctx->used; /* - * Make sure sufficient data is present -- note, the same check is - * also present in sendmsg/sendpage. The checks in sendpage/sendmsg - * shall provide an information to the data sender that something is - * wrong, but they are irrelevant to maintain the kernel integrity. - * We need this check here too in case user space decides to not honor - * the error message in sendmsg/sendpage and still call recvmsg. This - * check here protects the kernel integrity. + * Make sure sufficient data is present -- note, the same check is also + * present in sendmsg. The checks in sendmsg shall provide an + * information to the data sender that something is wrong, but they are + * irrelevant to maintain the kernel integrity. We need this check + * here too in case user space decides to not honor the error message + * in sendmsg and still call recvmsg. This check here protects the + * kernel integrity. */ if (!aead_sufficient_data(sk)) return -EINVAL; @@ -210,7 +210,7 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg, */ /* Use the RX SGL as source (and destination) for crypto op. */ - rsgl_src = areq->first_rsgl.sgl.sg; + rsgl_src = areq->first_rsgl.sgl.sgt.sgl; if (ctx->enc) { /* @@ -224,7 +224,8 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg, * RX SGL: AAD || PT || Tag */ err = crypto_aead_copy_sgl(null_tfm, tsgl_src, - areq->first_rsgl.sgl.sg, processed); + areq->first_rsgl.sgl.sgt.sgl, + processed); if (err) goto free; af_alg_pull_tsgl(sk, processed, NULL, 0); @@ -242,7 +243,8 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg, /* Copy AAD || CT to RX SGL buffer for in-place operation. */ err = crypto_aead_copy_sgl(null_tfm, tsgl_src, - areq->first_rsgl.sgl.sg, outlen); + areq->first_rsgl.sgl.sgt.sgl, + outlen); if (err) goto free; @@ -267,10 +269,10 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg, if (usedpages) { /* RX SGL present */ struct af_alg_sgl *sgl_prev = &areq->last_rsgl->sgl; + struct scatterlist *sg = sgl_prev->sgt.sgl; - sg_unmark_end(sgl_prev->sg + sgl_prev->npages - 1); - sg_chain(sgl_prev->sg, sgl_prev->npages + 1, - areq->tsgl); + sg_unmark_end(sg + sgl_prev->sgt.nents - 1); + sg_chain(sg, sgl_prev->sgt.nents + 1, areq->tsgl); } else /* no RX SGL present (e.g. authentication only) */ rsgl_src = areq->tsgl; @@ -278,7 +280,7 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg, /* Initialize the crypto operation */ aead_request_set_crypt(&areq->cra_u.aead_req, rsgl_src, - areq->first_rsgl.sgl.sg, used, ctx->iv); + areq->first_rsgl.sgl.sgt.sgl, used, ctx->iv); aead_request_set_ad(&areq->cra_u.aead_req, ctx->aead_assoclen); aead_request_set_tfm(&areq->cra_u.aead_req, tfm); diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c index 63af72e19fa8..1a2d80c6c91a 100644 --- a/crypto/algif_hash.c +++ b/crypto/algif_hash.c @@ -63,70 +63,102 @@ static void hash_free_result(struct sock *sk, struct hash_ctx *ctx) static int hash_sendmsg(struct socket *sock, struct msghdr *msg, size_t ignored) { - int limit = ALG_MAX_PAGES * PAGE_SIZE; struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); struct hash_ctx *ctx = ask->private; - long copied = 0; + ssize_t copied = 0; + size_t len, max_pages, npages; + bool continuing = ctx->more, need_init = false; int err; - if (limit > sk->sk_sndbuf) - limit = sk->sk_sndbuf; + max_pages = min_t(size_t, ALG_MAX_PAGES, + DIV_ROUND_UP(sk->sk_sndbuf, PAGE_SIZE)); lock_sock(sk); - if (!ctx->more) { + if (!continuing) { if ((msg->msg_flags & MSG_MORE)) hash_free_result(sk, ctx); - - err = crypto_wait_req(crypto_ahash_init(&ctx->req), &ctx->wait); - if (err) - goto unlock; + need_init = true; } ctx->more = false; while (msg_data_left(msg)) { - int len = msg_data_left(msg); - - if (len > limit) - len = limit; - - len = af_alg_make_sg(&ctx->sgl, &msg->msg_iter, len); - if (len < 0) { - err = copied ? 0 : len; - goto unlock; + ctx->sgl.sgt.sgl = ctx->sgl.sgl; + ctx->sgl.sgt.nents = 0; + ctx->sgl.sgt.orig_nents = 0; + + err = -EIO; + npages = iov_iter_npages(&msg->msg_iter, max_pages); + if (npages == 0) + goto unlock_free; + + if (npages > ARRAY_SIZE(ctx->sgl.sgl)) { + err = -ENOMEM; + ctx->sgl.sgt.sgl = + kvmalloc(array_size(npages, + sizeof(*ctx->sgl.sgt.sgl)), + GFP_KERNEL); + if (!ctx->sgl.sgt.sgl) + goto unlock_free; } + sg_init_table(ctx->sgl.sgl, npages); - ahash_request_set_crypt(&ctx->req, ctx->sgl.sg, NULL, len); + ctx->sgl.need_unpin = iov_iter_extract_will_pin(&msg->msg_iter); - err = crypto_wait_req(crypto_ahash_update(&ctx->req), - &ctx->wait); - af_alg_free_sg(&ctx->sgl); - if (err) { - iov_iter_revert(&msg->msg_iter, len); - goto unlock; + err = extract_iter_to_sg(&msg->msg_iter, LONG_MAX, + &ctx->sgl.sgt, npages, 0); + if (err < 0) + goto unlock_free; + len = err; + sg_mark_end(ctx->sgl.sgt.sgl + ctx->sgl.sgt.nents - 1); + + if (!msg_data_left(msg)) { + err = hash_alloc_result(sk, ctx); + if (err) + goto unlock_free; } - copied += len; - } + ahash_request_set_crypt(&ctx->req, ctx->sgl.sgt.sgl, + ctx->result, len); - err = 0; + if (!msg_data_left(msg) && !continuing && + !(msg->msg_flags & MSG_MORE)) { + err = crypto_ahash_digest(&ctx->req); + } else { + if (need_init) { + err = crypto_wait_req( + crypto_ahash_init(&ctx->req), + &ctx->wait); + if (err) + goto unlock_free; + need_init = false; + } + + if (msg_data_left(msg) || (msg->msg_flags & MSG_MORE)) + err = crypto_ahash_update(&ctx->req); + else + err = crypto_ahash_finup(&ctx->req); + continuing = true; + } - ctx->more = msg->msg_flags & MSG_MORE; - if (!ctx->more) { - err = hash_alloc_result(sk, ctx); + err = crypto_wait_req(err, &ctx->wait); if (err) - goto unlock; + goto unlock_free; - ahash_request_set_crypt(&ctx->req, NULL, ctx->result, 0); - err = crypto_wait_req(crypto_ahash_final(&ctx->req), - &ctx->wait); + copied += len; + af_alg_free_sg(&ctx->sgl); } + ctx->more = msg->msg_flags & MSG_MORE; + err = 0; unlock: release_sock(sk); + return copied ?: err; - return err ?: copied; +unlock_free: + af_alg_free_sg(&ctx->sgl); + goto unlock; } static ssize_t hash_sendpage(struct socket *sock, struct page *page, @@ -141,8 +173,8 @@ static ssize_t hash_sendpage(struct socket *sock, struct page *page, flags |= MSG_MORE; lock_sock(sk); - sg_init_table(ctx->sgl.sg, 1); - sg_set_page(ctx->sgl.sg, page, size, offset); + sg_init_table(ctx->sgl.sgl, 1); + sg_set_page(ctx->sgl.sgl, page, size, offset); if (!(flags & MSG_MORE)) { err = hash_alloc_result(sk, ctx); @@ -151,7 +183,7 @@ static ssize_t hash_sendpage(struct socket *sock, struct page *page, } else if (!ctx->more) hash_free_result(sk, ctx); - ahash_request_set_crypt(&ctx->req, ctx->sgl.sg, ctx->result, size); + ahash_request_set_crypt(&ctx->req, ctx->sgl.sgl, ctx->result, size); if (!(flags & MSG_MORE)) { if (ctx->more) diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index ee8890ee8f33..b1f321b9f846 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -9,10 +9,10 @@ * The following concept of the memory management is used: * * The kernel maintains two SGLs, the TX SGL and the RX SGL. The TX SGL is - * filled by user space with the data submitted via sendpage/sendmsg. Filling - * up the TX SGL does not cause a crypto operation -- the data will only be - * tracked by the kernel. Upon receipt of one recvmsg call, the caller must - * provide a buffer which is tracked with the RX SGL. + * filled by user space with the data submitted via sendmsg. Filling up the TX + * SGL does not cause a crypto operation -- the data will only be tracked by + * the kernel. Upon receipt of one recvmsg call, the caller must provide a + * buffer which is tracked with the RX SGL. * * During the processing of the recvmsg operation, the cipher request is * allocated and prepared. As part of the recvmsg operation, the processed @@ -105,7 +105,7 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg, /* Initialize the crypto operation */ skcipher_request_set_tfm(&areq->cra_u.skcipher_req, tfm); skcipher_request_set_crypt(&areq->cra_u.skcipher_req, areq->tsgl, - areq->first_rsgl.sgl.sg, len, ctx->iv); + areq->first_rsgl.sgl.sgt.sgl, len, ctx->iv); if (msg->msg_iocb && !is_sync_kiocb(msg->msg_iocb)) { /* AIO operation */ diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c index eca5671ad3f2..50c933f86b21 100644 --- a/crypto/asymmetric_keys/public_key.c +++ b/crypto/asymmetric_keys/public_key.c @@ -380,9 +380,10 @@ int public_key_verify_signature(const struct public_key *pkey, struct crypto_wait cwait; struct crypto_akcipher *tfm; struct akcipher_request *req; - struct scatterlist src_sg[2]; + struct scatterlist src_sg; char alg_name[CRYPTO_MAX_ALG_NAME]; - char *key, *ptr; + char *buf, *ptr; + size_t buf_len; int ret; pr_devel("==>%s()\n", __func__); @@ -420,34 +421,37 @@ int public_key_verify_signature(const struct public_key *pkey, if (!req) goto error_free_tfm; - key = kmalloc(pkey->keylen + sizeof(u32) * 2 + pkey->paramlen, - GFP_KERNEL); - if (!key) + buf_len = max_t(size_t, pkey->keylen + sizeof(u32) * 2 + pkey->paramlen, + sig->s_size + sig->digest_size); + + buf = kmalloc(buf_len, GFP_KERNEL); + if (!buf) goto error_free_req; - memcpy(key, pkey->key, pkey->keylen); - ptr = key + pkey->keylen; + memcpy(buf, pkey->key, pkey->keylen); + ptr = buf + pkey->keylen; ptr = pkey_pack_u32(ptr, pkey->algo); ptr = pkey_pack_u32(ptr, pkey->paramlen); memcpy(ptr, pkey->params, pkey->paramlen); if (pkey->key_is_private) - ret = crypto_akcipher_set_priv_key(tfm, key, pkey->keylen); + ret = crypto_akcipher_set_priv_key(tfm, buf, pkey->keylen); else - ret = crypto_akcipher_set_pub_key(tfm, key, pkey->keylen); + ret = crypto_akcipher_set_pub_key(tfm, buf, pkey->keylen); if (ret) - goto error_free_key; + goto error_free_buf; if (strcmp(pkey->pkey_algo, "sm2") == 0 && sig->data_size) { ret = cert_sig_digest_update(sig, tfm); if (ret) - goto error_free_key; + goto error_free_buf; } - sg_init_table(src_sg, 2); - sg_set_buf(&src_sg[0], sig->s, sig->s_size); - sg_set_buf(&src_sg[1], sig->digest, sig->digest_size); - akcipher_request_set_crypt(req, src_sg, NULL, sig->s_size, + memcpy(buf, sig->s, sig->s_size); + memcpy(buf + sig->s_size, sig->digest, sig->digest_size); + + sg_init_one(&src_sg, buf, sig->s_size + sig->digest_size); + akcipher_request_set_crypt(req, &src_sg, NULL, sig->s_size, sig->digest_size); crypto_init_wait(&cwait); akcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | @@ -455,8 +459,8 @@ int public_key_verify_signature(const struct public_key *pkey, crypto_req_done, &cwait); ret = crypto_wait_req(crypto_akcipher_verify(req), &cwait); -error_free_key: - kfree(key); +error_free_buf: + kfree(buf); error_free_req: akcipher_request_free(req); error_free_tfm: diff --git a/drivers/accel/qaic/qaic_control.c b/drivers/accel/qaic/qaic_control.c index 9f216eb6f76e..5c57f7b4494e 100644 --- a/drivers/accel/qaic/qaic_control.c +++ b/drivers/accel/qaic/qaic_control.c @@ -997,14 +997,34 @@ static void *msg_xfer(struct qaic_device *qdev, struct wrapper_list *wrappers, u struct xfer_queue_elem elem; struct wire_msg *out_buf; struct wrapper_msg *w; + long ret = -EAGAIN; + int xfer_count = 0; int retry_count; - long ret; if (qdev->in_reset) { mutex_unlock(&qdev->cntl_mutex); return ERR_PTR(-ENODEV); } + /* Attempt to avoid a partial commit of a message */ + list_for_each_entry(w, &wrappers->list, list) + xfer_count++; + + for (retry_count = 0; retry_count < QAIC_MHI_RETRY_MAX; retry_count++) { + if (xfer_count <= mhi_get_free_desc_count(qdev->cntl_ch, DMA_TO_DEVICE)) { + ret = 0; + break; + } + msleep_interruptible(QAIC_MHI_RETRY_WAIT_MS); + if (signal_pending(current)) + break; + } + + if (ret) { + mutex_unlock(&qdev->cntl_mutex); + return ERR_PTR(ret); + } + elem.seq_num = seq_num; elem.buf = NULL; init_completion(&elem.xfer_done); @@ -1038,16 +1058,9 @@ static void *msg_xfer(struct qaic_device *qdev, struct wrapper_list *wrappers, u list_for_each_entry(w, &wrappers->list, list) { kref_get(&w->ref_count); retry_count = 0; -retry: ret = mhi_queue_buf(qdev->cntl_ch, DMA_TO_DEVICE, &w->msg, w->len, list_is_last(&w->list, &wrappers->list) ? MHI_EOT : MHI_CHAIN); if (ret) { - if (ret == -EAGAIN && retry_count++ < QAIC_MHI_RETRY_MAX) { - msleep_interruptible(QAIC_MHI_RETRY_WAIT_MS); - if (!signal_pending(current)) - goto retry; - } - qdev->cntl_lost_buf = true; kref_put(&w->ref_count, free_wrapper); mutex_unlock(&qdev->cntl_mutex); @@ -1249,7 +1262,7 @@ dma_cont_failed: int qaic_manage_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { - struct qaic_manage_msg *user_msg; + struct qaic_manage_msg *user_msg = data; struct qaic_device *qdev; struct manage_msg *msg; struct qaic_user *usr; @@ -1258,6 +1271,9 @@ int qaic_manage_ioctl(struct drm_device *dev, void *data, struct drm_file *file_ int usr_rcu_id; int ret; + if (user_msg->len > QAIC_MANAGE_MAX_MSG_LENGTH) + return -EINVAL; + usr = file_priv->driver_priv; usr_rcu_id = srcu_read_lock(&usr->qddev_lock); @@ -1275,13 +1291,6 @@ int qaic_manage_ioctl(struct drm_device *dev, void *data, struct drm_file *file_ return -ENODEV; } - user_msg = data; - - if (user_msg->len > QAIC_MANAGE_MAX_MSG_LENGTH) { - ret = -EINVAL; - goto out; - } - msg = kzalloc(QAIC_MANAGE_MAX_MSG_LENGTH + sizeof(*msg), GFP_KERNEL); if (!msg) { ret = -ENOMEM; diff --git a/drivers/accel/qaic/qaic_data.c b/drivers/accel/qaic/qaic_data.c index c0a574cd1b35..e42c1f9ffff8 100644 --- a/drivers/accel/qaic/qaic_data.c +++ b/drivers/accel/qaic/qaic_data.c @@ -591,7 +591,7 @@ static int qaic_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_struc struct qaic_bo *bo = to_qaic_bo(obj); unsigned long offset = 0; struct scatterlist *sg; - int ret; + int ret = 0; if (obj->import_attach) return -EINVAL; @@ -663,6 +663,10 @@ int qaic_create_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *fi if (args->pad) return -EINVAL; + size = PAGE_ALIGN(args->size); + if (size == 0) + return -EINVAL; + usr = file_priv->driver_priv; usr_rcu_id = srcu_read_lock(&usr->qddev_lock); if (!usr->qddev) { @@ -677,12 +681,6 @@ int qaic_create_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *fi goto unlock_dev_srcu; } - size = PAGE_ALIGN(args->size); - if (size == 0) { - ret = -EINVAL; - goto unlock_dev_srcu; - } - bo = qaic_alloc_init_bo(); if (IS_ERR(bo)) { ret = PTR_ERR(bo); @@ -926,8 +924,8 @@ int qaic_attach_slice_bo_ioctl(struct drm_device *dev, void *data, struct drm_fi { struct qaic_attach_slice_entry *slice_ent; struct qaic_attach_slice *args = data; + int rcu_id, usr_rcu_id, qdev_rcu_id; struct dma_bridge_chan *dbc; - int usr_rcu_id, qdev_rcu_id; struct drm_gem_object *obj; struct qaic_device *qdev; unsigned long arg_size; @@ -936,6 +934,22 @@ int qaic_attach_slice_bo_ioctl(struct drm_device *dev, void *data, struct drm_fi struct qaic_bo *bo; int ret; + if (args->hdr.count == 0) + return -EINVAL; + + arg_size = args->hdr.count * sizeof(*slice_ent); + if (arg_size / args->hdr.count != sizeof(*slice_ent)) + return -EINVAL; + + if (args->hdr.size == 0) + return -EINVAL; + + if (!(args->hdr.dir == DMA_TO_DEVICE || args->hdr.dir == DMA_FROM_DEVICE)) + return -EINVAL; + + if (args->data == 0) + return -EINVAL; + usr = file_priv->driver_priv; usr_rcu_id = srcu_read_lock(&usr->qddev_lock); if (!usr->qddev) { @@ -950,43 +964,11 @@ int qaic_attach_slice_bo_ioctl(struct drm_device *dev, void *data, struct drm_fi goto unlock_dev_srcu; } - if (args->hdr.count == 0) { - ret = -EINVAL; - goto unlock_dev_srcu; - } - - arg_size = args->hdr.count * sizeof(*slice_ent); - if (arg_size / args->hdr.count != sizeof(*slice_ent)) { - ret = -EINVAL; - goto unlock_dev_srcu; - } - if (args->hdr.dbc_id >= qdev->num_dbc) { ret = -EINVAL; goto unlock_dev_srcu; } - if (args->hdr.size == 0) { - ret = -EINVAL; - goto unlock_dev_srcu; - } - - if (!(args->hdr.dir == DMA_TO_DEVICE || args->hdr.dir == DMA_FROM_DEVICE)) { - ret = -EINVAL; - goto unlock_dev_srcu; - } - - dbc = &qdev->dbc[args->hdr.dbc_id]; - if (dbc->usr != usr) { - ret = -EINVAL; - goto unlock_dev_srcu; - } - - if (args->data == 0) { - ret = -EINVAL; - goto unlock_dev_srcu; - } - user_data = u64_to_user_ptr(args->data); slice_ent = kzalloc(arg_size, GFP_KERNEL); @@ -1013,9 +995,21 @@ int qaic_attach_slice_bo_ioctl(struct drm_device *dev, void *data, struct drm_fi bo = to_qaic_bo(obj); + if (bo->sliced) { + ret = -EINVAL; + goto put_bo; + } + + dbc = &qdev->dbc[args->hdr.dbc_id]; + rcu_id = srcu_read_lock(&dbc->ch_lock); + if (dbc->usr != usr) { + ret = -EINVAL; + goto unlock_ch_srcu; + } + ret = qaic_prepare_bo(qdev, bo, &args->hdr); if (ret) - goto put_bo; + goto unlock_ch_srcu; ret = qaic_attach_slicing_bo(qdev, bo, &args->hdr, slice_ent); if (ret) @@ -1025,6 +1019,7 @@ int qaic_attach_slice_bo_ioctl(struct drm_device *dev, void *data, struct drm_fi dma_sync_sgtable_for_cpu(&qdev->pdev->dev, bo->sgt, args->hdr.dir); bo->dbc = dbc; + srcu_read_unlock(&dbc->ch_lock, rcu_id); drm_gem_object_put(obj); srcu_read_unlock(&qdev->dev_lock, qdev_rcu_id); srcu_read_unlock(&usr->qddev_lock, usr_rcu_id); @@ -1033,6 +1028,8 @@ int qaic_attach_slice_bo_ioctl(struct drm_device *dev, void *data, struct drm_fi unprepare_bo: qaic_unprepare_bo(qdev, bo); +unlock_ch_srcu: + srcu_read_unlock(&dbc->ch_lock, rcu_id); put_bo: drm_gem_object_put(obj); free_slice_ent: @@ -1316,7 +1313,6 @@ static int __qaic_execute_bo_ioctl(struct drm_device *dev, void *data, struct dr received_ts = ktime_get_ns(); size = is_partial ? sizeof(*pexec) : sizeof(*exec); - n = (unsigned long)size * args->hdr.count; if (args->hdr.count == 0 || n / args->hdr.count != size) return -EINVAL; @@ -1665,6 +1661,9 @@ int qaic_wait_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *file int rcu_id; int ret; + if (args->pad != 0) + return -EINVAL; + usr = file_priv->driver_priv; usr_rcu_id = srcu_read_lock(&usr->qddev_lock); if (!usr->qddev) { @@ -1679,11 +1678,6 @@ int qaic_wait_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *file goto unlock_dev_srcu; } - if (args->pad != 0) { - ret = -EINVAL; - goto unlock_dev_srcu; - } - if (args->dbc_id >= qdev->num_dbc) { ret = -EINVAL; goto unlock_dev_srcu; @@ -1855,6 +1849,11 @@ void wakeup_dbc(struct qaic_device *qdev, u32 dbc_id) dbc->usr = NULL; empty_xfer_list(qdev, dbc); synchronize_srcu(&dbc->ch_lock); + /* + * Threads holding channel lock, may add more elements in the xfer_list. + * Flush out these elements from xfer_list. + */ + empty_xfer_list(qdev, dbc); } void release_dbc(struct qaic_device *qdev, u32 dbc_id) diff --git a/drivers/accel/qaic/qaic_drv.c b/drivers/accel/qaic/qaic_drv.c index ff80eb571729..2d0828db28d8 100644 --- a/drivers/accel/qaic/qaic_drv.c +++ b/drivers/accel/qaic/qaic_drv.c @@ -262,8 +262,8 @@ static void qaic_destroy_drm_device(struct qaic_device *qdev, s32 partition_id) static int qaic_mhi_probe(struct mhi_device *mhi_dev, const struct mhi_device_id *id) { + u16 major = -1, minor = -1; struct qaic_device *qdev; - u16 major, minor; int ret; /* diff --git a/drivers/acpi/apei/apei-internal.h b/drivers/acpi/apei/apei-internal.h index 1d6ef9654725..67c2c3b959e1 100644 --- a/drivers/acpi/apei/apei-internal.h +++ b/drivers/acpi/apei/apei-internal.h @@ -7,7 +7,6 @@ #ifndef APEI_INTERNAL_H #define APEI_INTERNAL_H -#include <linux/cper.h> #include <linux/acpi.h> struct apei_exec_context; @@ -130,10 +129,5 @@ static inline u32 cper_estatus_len(struct acpi_hest_generic_status *estatus) return sizeof(*estatus) + estatus->data_length; } -void cper_estatus_print(const char *pfx, - const struct acpi_hest_generic_status *estatus); -int cper_estatus_check_header(const struct acpi_hest_generic_status *estatus); -int cper_estatus_check(const struct acpi_hest_generic_status *estatus); - int apei_osc_setup(void); #endif diff --git a/drivers/acpi/apei/bert.c b/drivers/acpi/apei/bert.c index c23eb75866d0..7514e38d5640 100644 --- a/drivers/acpi/apei/bert.c +++ b/drivers/acpi/apei/bert.c @@ -23,6 +23,7 @@ #include <linux/module.h> #include <linux/init.h> #include <linux/acpi.h> +#include <linux/cper.h> #include <linux/io.h> #include "apei-internal.h" diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index e8492b3a393a..0800a9d77558 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -516,6 +516,17 @@ static const struct dmi_system_id maingear_laptop[] = { { } }; +static const struct dmi_system_id lg_laptop[] = { + { + .ident = "LG Electronics 17U70P", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LG Electronics"), + DMI_MATCH(DMI_BOARD_NAME, "17U70P"), + }, + }, + { } +}; + struct irq_override_cmp { const struct dmi_system_id *system; unsigned char irq; @@ -532,6 +543,7 @@ static const struct irq_override_cmp override_table[] = { { lenovo_laptop, 10, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, true }, { tongfang_gm_rg, 1, ACPI_EDGE_SENSITIVE, ACPI_ACTIVE_LOW, 1, true }, { maingear_laptop, 1, ACPI_EDGE_SENSITIVE, ACPI_ACTIVE_LOW, 1, true }, + { lg_laptop, 1, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, false }, }; static bool acpi_dev_irq_override(u32 gsi, u8 triggering, u8 polarity, diff --git a/drivers/android/binder.c b/drivers/android/binder.c index fb56bfc45096..8fb7672021ee 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -1934,24 +1934,23 @@ static void binder_deferred_fd_close(int fd) static void binder_transaction_buffer_release(struct binder_proc *proc, struct binder_thread *thread, struct binder_buffer *buffer, - binder_size_t failed_at, + binder_size_t off_end_offset, bool is_failure) { int debug_id = buffer->debug_id; - binder_size_t off_start_offset, buffer_offset, off_end_offset; + binder_size_t off_start_offset, buffer_offset; binder_debug(BINDER_DEBUG_TRANSACTION, "%d buffer release %d, size %zd-%zd, failed at %llx\n", proc->pid, buffer->debug_id, buffer->data_size, buffer->offsets_size, - (unsigned long long)failed_at); + (unsigned long long)off_end_offset); if (buffer->target_node) binder_dec_node(buffer->target_node, 1, 0); off_start_offset = ALIGN(buffer->data_size, sizeof(void *)); - off_end_offset = is_failure && failed_at ? failed_at : - off_start_offset + buffer->offsets_size; + for (buffer_offset = off_start_offset; buffer_offset < off_end_offset; buffer_offset += sizeof(binder_size_t)) { struct binder_object_header *hdr; @@ -2111,6 +2110,21 @@ static void binder_transaction_buffer_release(struct binder_proc *proc, } } +/* Clean up all the objects in the buffer */ +static inline void binder_release_entire_buffer(struct binder_proc *proc, + struct binder_thread *thread, + struct binder_buffer *buffer, + bool is_failure) +{ + binder_size_t off_end_offset; + + off_end_offset = ALIGN(buffer->data_size, sizeof(void *)); + off_end_offset += buffer->offsets_size; + + binder_transaction_buffer_release(proc, thread, buffer, + off_end_offset, is_failure); +} + static int binder_translate_binder(struct flat_binder_object *fp, struct binder_transaction *t, struct binder_thread *thread) @@ -2806,7 +2820,7 @@ static int binder_proc_transaction(struct binder_transaction *t, t_outdated->buffer = NULL; buffer->transaction = NULL; trace_binder_transaction_update_buffer_release(buffer); - binder_transaction_buffer_release(proc, NULL, buffer, 0, 0); + binder_release_entire_buffer(proc, NULL, buffer, false); binder_alloc_free_buf(&proc->alloc, buffer); kfree(t_outdated); binder_stats_deleted(BINDER_STAT_TRANSACTION); @@ -3775,7 +3789,7 @@ binder_free_buf(struct binder_proc *proc, binder_node_inner_unlock(buf_node); } trace_binder_transaction_buffer_release(buffer); - binder_transaction_buffer_release(proc, thread, buffer, 0, is_failure); + binder_release_entire_buffer(proc, thread, buffer, is_failure); binder_alloc_free_buf(&proc->alloc, buffer); } diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index 55a3c3c2409f..662a2a2e2e84 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -212,8 +212,8 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate, mm = alloc->mm; if (mm) { - mmap_read_lock(mm); - vma = vma_lookup(mm, alloc->vma_addr); + mmap_write_lock(mm); + vma = alloc->vma; } if (!vma && need_mm) { @@ -270,7 +270,7 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate, trace_binder_alloc_page_end(alloc, index); } if (mm) { - mmap_read_unlock(mm); + mmap_write_unlock(mm); mmput(mm); } return 0; @@ -303,21 +303,24 @@ err_page_ptr_cleared: } err_no_vma: if (mm) { - mmap_read_unlock(mm); + mmap_write_unlock(mm); mmput(mm); } return vma ? -ENOMEM : -ESRCH; } +static inline void binder_alloc_set_vma(struct binder_alloc *alloc, + struct vm_area_struct *vma) +{ + /* pairs with smp_load_acquire in binder_alloc_get_vma() */ + smp_store_release(&alloc->vma, vma); +} + static inline struct vm_area_struct *binder_alloc_get_vma( struct binder_alloc *alloc) { - struct vm_area_struct *vma = NULL; - - if (alloc->vma_addr) - vma = vma_lookup(alloc->mm, alloc->vma_addr); - - return vma; + /* pairs with smp_store_release in binder_alloc_set_vma() */ + return smp_load_acquire(&alloc->vma); } static bool debug_low_async_space_locked(struct binder_alloc *alloc, int pid) @@ -380,15 +383,13 @@ static struct binder_buffer *binder_alloc_new_buf_locked( size_t size, data_offsets_size; int ret; - mmap_read_lock(alloc->mm); + /* Check binder_alloc is fully initialized */ if (!binder_alloc_get_vma(alloc)) { - mmap_read_unlock(alloc->mm); binder_alloc_debug(BINDER_DEBUG_USER_ERROR, "%d: binder_alloc_buf, no vma\n", alloc->pid); return ERR_PTR(-ESRCH); } - mmap_read_unlock(alloc->mm); data_offsets_size = ALIGN(data_size, sizeof(void *)) + ALIGN(offsets_size, sizeof(void *)); @@ -778,7 +779,9 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc, buffer->free = 1; binder_insert_free_buffer(alloc, buffer); alloc->free_async_space = alloc->buffer_size / 2; - alloc->vma_addr = vma->vm_start; + + /* Signal binder_alloc is fully initialized */ + binder_alloc_set_vma(alloc, vma); return 0; @@ -808,8 +811,7 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc) buffers = 0; mutex_lock(&alloc->mutex); - BUG_ON(alloc->vma_addr && - vma_lookup(alloc->mm, alloc->vma_addr)); + BUG_ON(alloc->vma); while ((n = rb_first(&alloc->allocated_buffers))) { buffer = rb_entry(n, struct binder_buffer, rb_node); @@ -916,25 +918,17 @@ void binder_alloc_print_pages(struct seq_file *m, * Make sure the binder_alloc is fully initialized, otherwise we might * read inconsistent state. */ - - mmap_read_lock(alloc->mm); - if (binder_alloc_get_vma(alloc) == NULL) { - mmap_read_unlock(alloc->mm); - goto uninitialized; - } - - mmap_read_unlock(alloc->mm); - for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) { - page = &alloc->pages[i]; - if (!page->page_ptr) - free++; - else if (list_empty(&page->lru)) - active++; - else - lru++; + if (binder_alloc_get_vma(alloc) != NULL) { + for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) { + page = &alloc->pages[i]; + if (!page->page_ptr) + free++; + else if (list_empty(&page->lru)) + active++; + else + lru++; + } } - -uninitialized: mutex_unlock(&alloc->mutex); seq_printf(m, " pages: %d:%d:%d\n", active, lru, free); seq_printf(m, " pages high watermark: %zu\n", alloc->pages_high); @@ -969,7 +963,7 @@ int binder_alloc_get_allocated_count(struct binder_alloc *alloc) */ void binder_alloc_vma_close(struct binder_alloc *alloc) { - alloc->vma_addr = 0; + binder_alloc_set_vma(alloc, NULL); } /** diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h index 0f811ac4bcff..138d1d5af9ce 100644 --- a/drivers/android/binder_alloc.h +++ b/drivers/android/binder_alloc.h @@ -75,7 +75,7 @@ struct binder_lru_page { /** * struct binder_alloc - per-binder proc state for binder allocator * @mutex: protects binder_alloc fields - * @vma_addr: vm_area_struct->vm_start passed to mmap_handler + * @vma: vm_area_struct passed to mmap_handler * (invariant after mmap) * @mm: copy of task->mm (invariant after open) * @buffer: base of per-proc address space mapped via mmap @@ -99,7 +99,7 @@ struct binder_lru_page { */ struct binder_alloc { struct mutex mutex; - unsigned long vma_addr; + struct vm_area_struct *vma; struct mm_struct *mm; void __user *buffer; struct list_head buffers; diff --git a/drivers/android/binder_alloc_selftest.c b/drivers/android/binder_alloc_selftest.c index 43a881073a42..c2b323bc3b3a 100644 --- a/drivers/android/binder_alloc_selftest.c +++ b/drivers/android/binder_alloc_selftest.c @@ -287,7 +287,7 @@ void binder_selftest_alloc(struct binder_alloc *alloc) if (!binder_selftest_run) return; mutex_lock(&binder_selftest_lock); - if (!binder_selftest_run || !alloc->vma_addr) + if (!binder_selftest_run || !alloc->vma) goto done; pr_info("STARTED\n"); binder_selftest_alloc_offset(alloc, end_offset, 0); diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 7bb12deab70c..8ce90284eb34 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -2694,18 +2694,36 @@ static unsigned int atapi_xlat(struct ata_queued_cmd *qc) return 0; } -static struct ata_device *ata_find_dev(struct ata_port *ap, int devno) +static struct ata_device *ata_find_dev(struct ata_port *ap, unsigned int devno) { - if (!sata_pmp_attached(ap)) { - if (likely(devno >= 0 && - devno < ata_link_max_devices(&ap->link))) + /* + * For the non-PMP case, ata_link_max_devices() returns 1 (SATA case), + * or 2 (IDE master + slave case). However, the former case includes + * libsas hosted devices which are numbered per scsi host, leading + * to devno potentially being larger than 0 but with each struct + * ata_device having its own struct ata_port and struct ata_link. + * To accommodate these, ignore devno and always use device number 0. + */ + if (likely(!sata_pmp_attached(ap))) { + int link_max_devices = ata_link_max_devices(&ap->link); + + if (link_max_devices == 1) + return &ap->link.device[0]; + + if (devno < link_max_devices) return &ap->link.device[devno]; - } else { - if (likely(devno >= 0 && - devno < ap->nr_pmp_links)) - return &ap->pmp_link[devno].device[0]; + + return NULL; } + /* + * For PMP-attached devices, the device number corresponds to C + * (channel) of SCSI [H:C:I:L], indicating the port pmp link + * for the device. + */ + if (devno < ap->nr_pmp_links) + return &ap->pmp_link[devno].device[0]; + return NULL; } diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c index bba3482ddeb8..cbae8be1fe52 100644 --- a/drivers/base/cacheinfo.c +++ b/drivers/base/cacheinfo.c @@ -388,6 +388,16 @@ static int cache_shared_cpu_map_setup(unsigned int cpu) continue;/* skip if itself or no cacheinfo */ for (sib_index = 0; sib_index < cache_leaves(i); sib_index++) { sib_leaf = per_cpu_cacheinfo_idx(i, sib_index); + + /* + * Comparing cache IDs only makes sense if the leaves + * belong to the same cache level of same type. Skip + * the check if level and type do not match. + */ + if (sib_leaf->level != this_leaf->level || + sib_leaf->type != this_leaf->type) + continue; + if (cache_leaves_are_shared(this_leaf, sib_leaf)) { cpumask_set_cpu(cpu, &sib_leaf->shared_cpu_map); cpumask_set_cpu(i, &this_leaf->shared_cpu_map); @@ -400,11 +410,14 @@ static int cache_shared_cpu_map_setup(unsigned int cpu) coherency_max_size = this_leaf->coherency_line_size; } + /* shared_cpu_map is now populated for the cpu */ + this_cpu_ci->cpu_map_populated = true; return 0; } static void cache_shared_cpu_map_remove(unsigned int cpu) { + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); struct cacheinfo *this_leaf, *sib_leaf; unsigned int sibling, index, sib_index; @@ -419,6 +432,16 @@ static void cache_shared_cpu_map_remove(unsigned int cpu) for (sib_index = 0; sib_index < cache_leaves(sibling); sib_index++) { sib_leaf = per_cpu_cacheinfo_idx(sibling, sib_index); + + /* + * Comparing cache IDs only makes sense if the leaves + * belong to the same cache level of same type. Skip + * the check if level and type do not match. + */ + if (sib_leaf->level != this_leaf->level || + sib_leaf->type != this_leaf->type) + continue; + if (cache_leaves_are_shared(this_leaf, sib_leaf)) { cpumask_clear_cpu(cpu, &sib_leaf->shared_cpu_map); cpumask_clear_cpu(sibling, &this_leaf->shared_cpu_map); @@ -427,6 +450,9 @@ static void cache_shared_cpu_map_remove(unsigned int cpu) } } } + + /* cpu is no longer populated in the shared map */ + this_cpu_ci->cpu_map_populated = false; } static void free_cache_attributes(unsigned int cpu) diff --git a/drivers/base/class.c b/drivers/base/class.c index ac1808d1a2e8..05d9df90f621 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -320,6 +320,7 @@ void class_dev_iter_init(struct class_dev_iter *iter, const struct class *class, start_knode = &start->p->knode_class; klist_iter_init_node(&sp->klist_devices, &iter->ki, start_knode); iter->type = type; + iter->sp = sp; } EXPORT_SYMBOL_GPL(class_dev_iter_init); @@ -361,6 +362,7 @@ EXPORT_SYMBOL_GPL(class_dev_iter_next); void class_dev_iter_exit(struct class_dev_iter *iter) { klist_iter_exit(&iter->ki); + subsys_put(iter->sp); } EXPORT_SYMBOL_GPL(class_dev_iter_exit); diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c index 9d79d5ad9102..b58c42f1b1ce 100644 --- a/drivers/base/firmware_loader/main.c +++ b/drivers/base/firmware_loader/main.c @@ -812,7 +812,7 @@ static void fw_log_firmware_info(const struct firmware *fw, const char *name, st char *outbuf; alg = crypto_alloc_shash("sha256", 0, 0); - if (!alg) + if (IS_ERR(alg)) return; sha256buf = kmalloc(SHA256_DIGEST_SIZE, GFP_KERNEL); diff --git a/drivers/base/regmap/Kconfig b/drivers/base/regmap/Kconfig index 33a8366e22a5..0db2021f7477 100644 --- a/drivers/base/regmap/Kconfig +++ b/drivers/base/regmap/Kconfig @@ -4,16 +4,23 @@ # subsystems should select the appropriate symbols. config REGMAP + bool "Register Map support" if KUNIT_ALL_TESTS default y if (REGMAP_I2C || REGMAP_SPI || REGMAP_SPMI || REGMAP_W1 || REGMAP_AC97 || REGMAP_MMIO || REGMAP_IRQ || REGMAP_SOUNDWIRE || REGMAP_SOUNDWIRE_MBQ || REGMAP_SCCB || REGMAP_I3C || REGMAP_SPI_AVMM || REGMAP_MDIO || REGMAP_FSI) select IRQ_DOMAIN if REGMAP_IRQ select MDIO_BUS if REGMAP_MDIO - bool + help + Enable support for the Register Map (regmap) access API. + + Usually, this option is automatically selected when needed. + However, you may want to enable it manually for running the regmap + KUnit tests. + + If unsure, say N. config REGMAP_KUNIT tristate "KUnit tests for regmap" - depends on KUNIT + depends on KUNIT && REGMAP default KUNIT_ALL_TESTS - select REGMAP select REGMAP_RAM config REGMAP_AC97 diff --git a/drivers/base/regmap/regcache-maple.c b/drivers/base/regmap/regcache-maple.c index 9b1b559107ef..c2e3a0f6c218 100644 --- a/drivers/base/regmap/regcache-maple.c +++ b/drivers/base/regmap/regcache-maple.c @@ -203,15 +203,18 @@ static int regcache_maple_sync(struct regmap *map, unsigned int min, mas_for_each(&mas, entry, max) { for (r = max(mas.index, lmin); r <= min(mas.last, lmax); r++) { + mas_pause(&mas); + rcu_read_unlock(); ret = regcache_sync_val(map, r, entry[r - mas.index]); if (ret != 0) goto out; + rcu_read_lock(); } } -out: rcu_read_unlock(); +out: map->cache_bypass = false; return ret; diff --git a/drivers/base/regmap/regmap-sdw.c b/drivers/base/regmap/regmap-sdw.c index 09899ae99fc1..159c0b740b00 100644 --- a/drivers/base/regmap/regmap-sdw.c +++ b/drivers/base/regmap/regmap-sdw.c @@ -59,6 +59,10 @@ static int regmap_sdw_config_check(const struct regmap_config *config) if (config->pad_bits != 0) return -ENOTSUPP; + /* Only bulk writes are supported not multi-register writes */ + if (config->can_multi_write) + return -ENOTSUPP; + return 0; } diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index db7851f0e3b8..fa2d3fba6ac9 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -2082,6 +2082,8 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg, size_t val_count = val_len / val_bytes; size_t chunk_count, chunk_bytes; size_t chunk_regs = val_count; + size_t max_data = map->max_raw_write - map->format.reg_bytes - + map->format.pad_bytes; int ret, i; if (!val_count) @@ -2089,8 +2091,8 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg, if (map->use_single_write) chunk_regs = 1; - else if (map->max_raw_write && val_len > map->max_raw_write) - chunk_regs = map->max_raw_write / val_bytes; + else if (map->max_raw_write && val_len > max_data) + chunk_regs = max_data / val_bytes; chunk_count = val_count / chunk_regs; chunk_bytes = chunk_regs * val_bytes; diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 9c35c958f2c8..65ecde3e2a5b 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1666,7 +1666,7 @@ static int nbd_dev_dbg_init(struct nbd_device *nbd) return -EIO; dir = debugfs_create_dir(nbd_name(nbd), nbd_dbg_dir); - if (!dir) { + if (IS_ERR(dir)) { dev_err(nbd_to_dev(nbd), "Failed to create debugfs dir for '%s'\n", nbd_name(nbd)); return -EIO; @@ -1692,7 +1692,7 @@ static int nbd_dbg_init(void) struct dentry *dbg_dir; dbg_dir = debugfs_create_dir("nbd", NULL); - if (!dbg_dir) + if (IS_ERR(dbg_dir)) return -EIO; nbd_dbg_dir = dbg_dir; diff --git a/drivers/block/rnbd/rnbd-proto.h b/drivers/block/rnbd/rnbd-proto.h index ea7ac8bca63c..da1d0542d7e2 100644 --- a/drivers/block/rnbd/rnbd-proto.h +++ b/drivers/block/rnbd/rnbd-proto.h @@ -241,7 +241,7 @@ static inline blk_opf_t rnbd_to_bio_flags(u32 rnbd_opf) bio_opf = REQ_OP_WRITE; break; case RNBD_OP_FLUSH: - bio_opf = REQ_OP_FLUSH | REQ_PREFLUSH; + bio_opf = REQ_OP_WRITE | REQ_PREFLUSH; break; case RNBD_OP_DISCARD: bio_opf = REQ_OP_DISCARD; diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index c7331f519750..33d3298a0da1 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -1120,6 +1120,11 @@ static inline bool ublk_queue_ready(struct ublk_queue *ubq) return ubq->nr_io_ready == ubq->q_depth; } +static void ublk_cmd_cancel_cb(struct io_uring_cmd *cmd, unsigned issue_flags) +{ + io_uring_cmd_done(cmd, UBLK_IO_RES_ABORT, 0, issue_flags); +} + static void ublk_cancel_queue(struct ublk_queue *ubq) { int i; @@ -1131,8 +1136,8 @@ static void ublk_cancel_queue(struct ublk_queue *ubq) struct ublk_io *io = &ubq->ios[i]; if (io->flags & UBLK_IO_FLAG_ACTIVE) - io_uring_cmd_done(io->cmd, UBLK_IO_RES_ABORT, 0, - IO_URING_F_UNLOCKED); + io_uring_cmd_complete_in_task(io->cmd, + ublk_cmd_cancel_cb); } /* all io commands are canceled */ @@ -1281,7 +1286,7 @@ static inline int ublk_check_cmd_op(u32 cmd_op) { u32 ioc_type = _IOC_TYPE(cmd_op); - if (IS_ENABLED(CONFIG_BLKDEV_UBLK_LEGACY_OPCODES) && ioc_type != 'u') + if (!IS_ENABLED(CONFIG_BLKDEV_UBLK_LEGACY_OPCODES) && ioc_type != 'u') return -EOPNOTSUPP; if (ioc_type != 'u' && ioc_type != 0) diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 23ed258b57f0..c1890c8a9f6e 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -780,7 +780,8 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri ring_req->u.rw.handle = info->handle; ring_req->operation = rq_data_dir(req) ? BLKIF_OP_WRITE : BLKIF_OP_READ; - if (req_op(req) == REQ_OP_FLUSH || req->cmd_flags & REQ_FUA) { + if (req_op(req) == REQ_OP_FLUSH || + (req_op(req) == REQ_OP_WRITE && (req->cmd_flags & REQ_FUA))) { /* * Ideally we can do an unordered flush-to-disk. * In case the backend onlysupports barriers, use that. diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c index 3a34d7c1475b..52ef44688d38 100644 --- a/drivers/bluetooth/btnxpuart.c +++ b/drivers/bluetooth/btnxpuart.c @@ -1319,17 +1319,17 @@ static void nxp_serdev_remove(struct serdev_device *serdev) hci_free_dev(hdev); } -static struct btnxpuart_data w8987_data = { +static struct btnxpuart_data w8987_data __maybe_unused = { .helper_fw_name = NULL, .fw_name = FIRMWARE_W8987, }; -static struct btnxpuart_data w8997_data = { +static struct btnxpuart_data w8997_data __maybe_unused = { .helper_fw_name = FIRMWARE_HELPER, .fw_name = FIRMWARE_W8997, }; -static const struct of_device_id nxpuart_of_match_table[] = { +static const struct of_device_id nxpuart_of_match_table[] __maybe_unused = { { .compatible = "nxp,88w8987-bt", .data = &w8987_data }, { .compatible = "nxp,88w8997-bt", .data = &w8997_data }, { } diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 1b064504b388..e30c979535b1 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -78,7 +78,8 @@ enum qca_flags { QCA_HW_ERROR_EVENT, QCA_SSR_TRIGGERED, QCA_BT_OFF, - QCA_ROM_FW + QCA_ROM_FW, + QCA_DEBUGFS_CREATED, }; enum qca_capabilities { @@ -635,6 +636,9 @@ static void qca_debugfs_init(struct hci_dev *hdev) if (!hdev->debugfs) return; + if (test_and_set_bit(QCA_DEBUGFS_CREATED, &qca->flags)) + return; + ibs_dir = debugfs_create_dir("ibs", hdev->debugfs); /* read only */ diff --git a/drivers/char/agp/parisc-agp.c b/drivers/char/agp/parisc-agp.c index d68d05d5d383..514f9f287a78 100644 --- a/drivers/char/agp/parisc-agp.c +++ b/drivers/char/agp/parisc-agp.c @@ -90,6 +90,9 @@ parisc_agp_tlbflush(struct agp_memory *mem) { struct _parisc_agp_info *info = &parisc_agp_info; + /* force fdc ops to be visible to IOMMU */ + asm_io_sync(); + writeq(info->gart_base | ilog2(info->gart_size), info->ioc_regs+IOC_PCOM); readq(info->ioc_regs+IOC_PCOM); /* flush */ } @@ -158,6 +161,7 @@ parisc_agp_insert_memory(struct agp_memory *mem, off_t pg_start, int type) info->gatt[j] = parisc_agp_mask_memory(agp_bridge, paddr, type); + asm_io_fdc(&info->gatt[j]); } } @@ -191,7 +195,16 @@ static unsigned long parisc_agp_mask_memory(struct agp_bridge_data *bridge, dma_addr_t addr, int type) { - return SBA_PDIR_VALID_BIT | addr; + unsigned ci; /* coherent index */ + dma_addr_t pa; + + pa = addr & IOVP_MASK; + asm("lci 0(%1), %0" : "=r" (ci) : "r" (phys_to_virt(pa))); + + pa |= (ci >> PAGE_SHIFT) & 0xff;/* move CI (8 bits) into lowest byte */ + pa |= SBA_PDIR_VALID_BIT; /* set "valid" bit */ + + return cpu_to_le64(pa); } static void diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index c10a4aa97373..cd48033b804a 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -571,6 +571,10 @@ static int tpm_hwrng_read(struct hwrng *rng, void *data, size_t max, bool wait) { struct tpm_chip *chip = container_of(rng, struct tpm_chip, hwrng); + /* Give back zero bytes, as TPM chip has not yet fully resumed: */ + if (chip->flags & TPM_CHIP_FLAG_SUSPENDED) + return 0; + return tpm_get_random(chip, data, max); } diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index 4463d0018290..586ca10b0d72 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -412,6 +412,8 @@ int tpm_pm_suspend(struct device *dev) } suspended: + chip->flags |= TPM_CHIP_FLAG_SUSPENDED; + if (rc) dev_err(dev, "Ignoring error %d while suspending\n", rc); return 0; @@ -429,6 +431,14 @@ int tpm_pm_resume(struct device *dev) if (chip == NULL) return -ENODEV; + chip->flags &= ~TPM_CHIP_FLAG_SUSPENDED; + + /* + * Guarantee that SUSPENDED is written last, so that hwrng does not + * activate before the chip has been fully resumed. + */ + wmb(); + return 0; } EXPORT_SYMBOL_GPL(tpm_pm_resume); diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c index 7af389806643..7db3593941ea 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -122,6 +122,29 @@ static const struct dmi_system_id tpm_tis_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T490s"), }, }, + { + .callback = tpm_tis_disable_irq, + .ident = "ThinkStation P360 Tiny", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkStation P360 Tiny"), + }, + }, + { + .callback = tpm_tis_disable_irq, + .ident = "ThinkPad L490", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L490"), + }, + }, + { + .callback = tpm_tis_disable_irq, + .ident = "UPX-TGL", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "AAEON"), + }, + }, {} }; diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index 02945d53fcef..558144fa707a 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -1209,25 +1209,20 @@ static void tpm_tis_reenable_interrupts(struct tpm_chip *chip) u32 intmask; int rc; - if (chip->ops->clk_enable != NULL) - chip->ops->clk_enable(chip, true); - - /* reenable interrupts that device may have lost or - * BIOS/firmware may have disabled + /* + * Re-enable interrupts that device may have lost or BIOS/firmware may + * have disabled. */ rc = tpm_tis_write8(priv, TPM_INT_VECTOR(priv->locality), priv->irq); - if (rc < 0) - goto out; + if (rc < 0) { + dev_err(&chip->dev, "Setting IRQ failed.\n"); + return; + } intmask = priv->int_mask | TPM_GLOBAL_INT_ENABLE; - - tpm_tis_write32(priv, TPM_INT_ENABLE(priv->locality), intmask); - -out: - if (chip->ops->clk_enable != NULL) - chip->ops->clk_enable(chip, false); - - return; + rc = tpm_tis_write32(priv, TPM_INT_ENABLE(priv->locality), intmask); + if (rc < 0) + dev_err(&chip->dev, "Enabling interrupts failed.\n"); } int tpm_tis_resume(struct device *dev) @@ -1235,27 +1230,27 @@ int tpm_tis_resume(struct device *dev) struct tpm_chip *chip = dev_get_drvdata(dev); int ret; - ret = tpm_tis_request_locality(chip, 0); - if (ret < 0) + ret = tpm_chip_start(chip); + if (ret) return ret; if (chip->flags & TPM_CHIP_FLAG_IRQ) tpm_tis_reenable_interrupts(chip); - ret = tpm_pm_resume(dev); - if (ret) - goto out; - /* * TPM 1.2 requires self-test on resume. This function actually returns * an error code but for unknown reason it isn't handled. */ if (!(chip->flags & TPM_CHIP_FLAG_TPM2)) tpm1_do_selftest(chip); -out: - tpm_tis_relinquish_locality(chip, 0); - return ret; + tpm_chip_stop(chip); + + ret = tpm_pm_resume(dev); + if (ret) + return ret; + + return 0; } EXPORT_SYMBOL_GPL(tpm_tis_resume); #endif diff --git a/drivers/char/tpm/tpm_tis_core.h b/drivers/char/tpm/tpm_tis_core.h index e978f457fd4d..610bfadb6acf 100644 --- a/drivers/char/tpm/tpm_tis_core.h +++ b/drivers/char/tpm/tpm_tis_core.h @@ -84,10 +84,10 @@ enum tis_defaults { #define ILB_REMAP_SIZE 0x100 enum tpm_tis_flags { - TPM_TIS_ITPM_WORKAROUND = BIT(0), - TPM_TIS_INVALID_STATUS = BIT(1), - TPM_TIS_DEFAULT_CANCELLATION = BIT(2), - TPM_TIS_IRQ_TESTED = BIT(3), + TPM_TIS_ITPM_WORKAROUND = 0, + TPM_TIS_INVALID_STATUS = 1, + TPM_TIS_DEFAULT_CANCELLATION = 2, + TPM_TIS_IRQ_TESTED = 3, }; struct tpm_tis_data { diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index 29904395e95f..b2f05d27167e 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -975,7 +975,7 @@ static int __init acpi_cpufreq_probe(struct platform_device *pdev) /* don't keep reloading if cpufreq_driver exists */ if (cpufreq_get_current_driver()) - return -EEXIST; + return -ENODEV; pr_debug("%s\n", __func__); diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 5a3d4aa0f45a..ddd346a239e0 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -444,9 +444,8 @@ static int amd_pstate_verify(struct cpufreq_policy_data *policy) return 0; } -static int amd_pstate_target(struct cpufreq_policy *policy, - unsigned int target_freq, - unsigned int relation) +static int amd_pstate_update_freq(struct cpufreq_policy *policy, + unsigned int target_freq, bool fast_switch) { struct cpufreq_freqs freqs; struct amd_cpudata *cpudata = policy->driver_data; @@ -465,26 +464,51 @@ static int amd_pstate_target(struct cpufreq_policy *policy, des_perf = DIV_ROUND_CLOSEST(target_freq * cap_perf, cpudata->max_freq); - cpufreq_freq_transition_begin(policy, &freqs); + WARN_ON(fast_switch && !policy->fast_switch_enabled); + /* + * If fast_switch is desired, then there aren't any registered + * transition notifiers. See comment for + * cpufreq_enable_fast_switch(). + */ + if (!fast_switch) + cpufreq_freq_transition_begin(policy, &freqs); + amd_pstate_update(cpudata, min_perf, des_perf, - max_perf, false, policy->governor->flags); - cpufreq_freq_transition_end(policy, &freqs, false); + max_perf, fast_switch, policy->governor->flags); + + if (!fast_switch) + cpufreq_freq_transition_end(policy, &freqs, false); return 0; } +static int amd_pstate_target(struct cpufreq_policy *policy, + unsigned int target_freq, + unsigned int relation) +{ + return amd_pstate_update_freq(policy, target_freq, false); +} + +static unsigned int amd_pstate_fast_switch(struct cpufreq_policy *policy, + unsigned int target_freq) +{ + return amd_pstate_update_freq(policy, target_freq, true); +} + static void amd_pstate_adjust_perf(unsigned int cpu, unsigned long _min_perf, unsigned long target_perf, unsigned long capacity) { unsigned long max_perf, min_perf, des_perf, - cap_perf, lowest_nonlinear_perf; + cap_perf, lowest_nonlinear_perf, max_freq; struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); struct amd_cpudata *cpudata = policy->driver_data; + unsigned int target_freq; cap_perf = READ_ONCE(cpudata->highest_perf); lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf); + max_freq = READ_ONCE(cpudata->max_freq); des_perf = cap_perf; if (target_perf < capacity) @@ -501,6 +525,10 @@ static void amd_pstate_adjust_perf(unsigned int cpu, if (max_perf < min_perf) max_perf = min_perf; + des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf); + target_freq = div_u64(des_perf * max_freq, max_perf); + policy->cur = target_freq; + amd_pstate_update(cpudata, min_perf, des_perf, max_perf, true, policy->governor->flags); cpufreq_cpu_put(policy); @@ -715,6 +743,7 @@ static int amd_pstate_cpu_exit(struct cpufreq_policy *policy) freq_qos_remove_request(&cpudata->req[1]); freq_qos_remove_request(&cpudata->req[0]); + policy->fast_switch_possible = false; kfree(cpudata); return 0; @@ -1079,7 +1108,6 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy) policy->policy = CPUFREQ_POLICY_POWERSAVE; if (boot_cpu_has(X86_FEATURE_CPPC)) { - policy->fast_switch_possible = true; ret = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, &value); if (ret) return ret; @@ -1102,7 +1130,6 @@ free_cpudata1: static int amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy) { pr_debug("CPU %d exiting\n", policy->cpu); - policy->fast_switch_possible = false; return 0; } @@ -1309,6 +1336,7 @@ static struct cpufreq_driver amd_pstate_driver = { .flags = CPUFREQ_CONST_LOOPS | CPUFREQ_NEED_UPDATE_LIMITS, .verify = amd_pstate_verify, .target = amd_pstate_target, + .fast_switch = amd_pstate_fast_switch, .init = amd_pstate_cpu_init, .exit = amd_pstate_cpu_exit, .suspend = amd_pstate_cpu_suspend, diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c index 1d2cfea9858a..73efbcf5513b 100644 --- a/drivers/cpufreq/pcc-cpufreq.c +++ b/drivers/cpufreq/pcc-cpufreq.c @@ -583,7 +583,7 @@ static int __init pcc_cpufreq_probe(struct platform_device *pdev) /* Skip initialization if another cpufreq driver is there. */ if (cpufreq_get_current_driver()) - return -EEXIST; + return -ENODEV; if (acpi_disabled) return -ENODEV; diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 23b9ff920d7e..bea9cf31a12d 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -1028,7 +1028,7 @@ static int cxl_mem_get_partition_info(struct cxl_dev_state *cxlds) * cxl_dev_state_identify() - Send the IDENTIFY command to the device. * @cxlds: The device data for the operation * - * Return: 0 if identify was executed successfully. + * Return: 0 if identify was executed successfully or media not ready. * * This will dispatch the identify command to the device and on success populate * structures to be exported to sysfs. @@ -1041,6 +1041,9 @@ int cxl_dev_state_identify(struct cxl_dev_state *cxlds) u32 val; int rc; + if (!cxlds->media_ready) + return 0; + mbox_cmd = (struct cxl_mbox_cmd) { .opcode = CXL_MBOX_OP_IDENTIFY, .size_out = sizeof(id), @@ -1102,6 +1105,13 @@ int cxl_mem_create_range_info(struct cxl_dev_state *cxlds) struct device *dev = cxlds->dev; int rc; + if (!cxlds->media_ready) { + cxlds->dpa_res = DEFINE_RES_MEM(0, 0); + cxlds->ram_res = DEFINE_RES_MEM(0, 0); + cxlds->pmem_res = DEFINE_RES_MEM(0, 0); + return 0; + } + cxlds->dpa_res = (struct resource)DEFINE_RES_MEM(0, cxlds->total_bytes); diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index bdbd907884ce..67f4ab6daa34 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -101,23 +101,57 @@ int devm_cxl_port_enumerate_dports(struct cxl_port *port) } EXPORT_SYMBOL_NS_GPL(devm_cxl_port_enumerate_dports, CXL); -/* - * Wait up to @media_ready_timeout for the device to report memory - * active. - */ -int cxl_await_media_ready(struct cxl_dev_state *cxlds) +static int cxl_dvsec_mem_range_valid(struct cxl_dev_state *cxlds, int id) +{ + struct pci_dev *pdev = to_pci_dev(cxlds->dev); + int d = cxlds->cxl_dvsec; + bool valid = false; + int rc, i; + u32 temp; + + if (id > CXL_DVSEC_RANGE_MAX) + return -EINVAL; + + /* Check MEM INFO VALID bit first, give up after 1s */ + i = 1; + do { + rc = pci_read_config_dword(pdev, + d + CXL_DVSEC_RANGE_SIZE_LOW(id), + &temp); + if (rc) + return rc; + + valid = FIELD_GET(CXL_DVSEC_MEM_INFO_VALID, temp); + if (valid) + break; + msleep(1000); + } while (i--); + + if (!valid) { + dev_err(&pdev->dev, + "Timeout awaiting memory range %d valid after 1s.\n", + id); + return -ETIMEDOUT; + } + + return 0; +} + +static int cxl_dvsec_mem_range_active(struct cxl_dev_state *cxlds, int id) { struct pci_dev *pdev = to_pci_dev(cxlds->dev); int d = cxlds->cxl_dvsec; bool active = false; - u64 md_status; int rc, i; + u32 temp; - for (i = media_ready_timeout; i; i--) { - u32 temp; + if (id > CXL_DVSEC_RANGE_MAX) + return -EINVAL; + /* Check MEM ACTIVE bit, up to 60s timeout by default */ + for (i = media_ready_timeout; i; i--) { rc = pci_read_config_dword( - pdev, d + CXL_DVSEC_RANGE_SIZE_LOW(0), &temp); + pdev, d + CXL_DVSEC_RANGE_SIZE_LOW(id), &temp); if (rc) return rc; @@ -134,6 +168,39 @@ int cxl_await_media_ready(struct cxl_dev_state *cxlds) return -ETIMEDOUT; } + return 0; +} + +/* + * Wait up to @media_ready_timeout for the device to report memory + * active. + */ +int cxl_await_media_ready(struct cxl_dev_state *cxlds) +{ + struct pci_dev *pdev = to_pci_dev(cxlds->dev); + int d = cxlds->cxl_dvsec; + int rc, i, hdm_count; + u64 md_status; + u16 cap; + + rc = pci_read_config_word(pdev, + d + CXL_DVSEC_CAP_OFFSET, &cap); + if (rc) + return rc; + + hdm_count = FIELD_GET(CXL_DVSEC_HDM_COUNT_MASK, cap); + for (i = 0; i < hdm_count; i++) { + rc = cxl_dvsec_mem_range_valid(cxlds, i); + if (rc) + return rc; + } + + for (i = 0; i < hdm_count; i++) { + rc = cxl_dvsec_mem_range_active(cxlds, i); + if (rc) + return rc; + } + md_status = readq(cxlds->regs.memdev + CXLMDEV_STATUS_OFFSET); if (!CXLMDEV_READY(md_status)) return -EIO; @@ -241,17 +308,36 @@ static void disable_hdm(void *_cxlhdm) hdm + CXL_HDM_DECODER_CTRL_OFFSET); } -static int devm_cxl_enable_hdm(struct device *host, struct cxl_hdm *cxlhdm) +int devm_cxl_enable_hdm(struct cxl_port *port, struct cxl_hdm *cxlhdm) { - void __iomem *hdm = cxlhdm->regs.hdm_decoder; + void __iomem *hdm; u32 global_ctrl; + /* + * If the hdm capability was not mapped there is nothing to enable and + * the caller is responsible for what happens next. For example, + * emulate a passthrough decoder. + */ + if (IS_ERR(cxlhdm)) + return 0; + + hdm = cxlhdm->regs.hdm_decoder; global_ctrl = readl(hdm + CXL_HDM_DECODER_CTRL_OFFSET); + + /* + * If the HDM decoder capability was enabled on entry, skip + * registering disable_hdm() since this decode capability may be + * owned by platform firmware. + */ + if (global_ctrl & CXL_HDM_DECODER_ENABLE) + return 0; + writel(global_ctrl | CXL_HDM_DECODER_ENABLE, hdm + CXL_HDM_DECODER_CTRL_OFFSET); - return devm_add_action_or_reset(host, disable_hdm, cxlhdm); + return devm_add_action_or_reset(&port->dev, disable_hdm, cxlhdm); } +EXPORT_SYMBOL_NS_GPL(devm_cxl_enable_hdm, CXL); int cxl_dvsec_rr_decode(struct device *dev, int d, struct cxl_endpoint_dvsec_info *info) @@ -425,7 +511,7 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm, if (info->mem_enabled) return 0; - rc = devm_cxl_enable_hdm(&port->dev, cxlhdm); + rc = devm_cxl_enable_hdm(port, cxlhdm); if (rc) return rc; @@ -571,6 +657,7 @@ void read_cdat_data(struct cxl_port *port) /* Don't leave table data allocated on error */ devm_kfree(dev, cdat_table); dev_err(dev, "CDAT data read error\n"); + return; } port->cdat.table = cdat_table + sizeof(__le32); diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index da2068475fa2..e7c284c890bc 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -750,11 +750,10 @@ struct cxl_port *devm_cxl_add_port(struct device *host, struct device *uport, parent_port = parent_dport ? parent_dport->port : NULL; if (IS_ERR(port)) { - dev_dbg(uport, "Failed to add %s%s%s%s: %ld\n", - dev_name(&port->dev), - parent_port ? " to " : "", + dev_dbg(uport, "Failed to add%s%s%s: %ld\n", + parent_port ? " port to " : "", parent_port ? dev_name(&parent_port->dev) : "", - parent_port ? "" : " (root port)", + parent_port ? "" : " root port", PTR_ERR(port)); } else { dev_dbg(uport, "%s added%s%s%s\n", diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index 044a92d9813e..f93a28538962 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -710,6 +710,7 @@ struct cxl_endpoint_dvsec_info { struct cxl_hdm; struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port, struct cxl_endpoint_dvsec_info *info); +int devm_cxl_enable_hdm(struct cxl_port *port, struct cxl_hdm *cxlhdm); int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm, struct cxl_endpoint_dvsec_info *info); int devm_cxl_add_passthrough_decoder(struct cxl_port *port); diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index db12b6313afb..a2845a7a69d8 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -266,6 +266,7 @@ struct cxl_poison_state { * @regs: Parsed register blocks * @cxl_dvsec: Offset to the PCIe device DVSEC * @rcd: operating in RCD mode (CXL 3.0 9.11.8 CXL Devices Attached to an RCH) + * @media_ready: Indicate whether the device media is usable * @payload_size: Size of space for payload * (CXL 2.0 8.2.8.4.3 Mailbox Capabilities Register) * @lsa_size: Size of Label Storage Area @@ -303,6 +304,7 @@ struct cxl_dev_state { int cxl_dvsec; bool rcd; + bool media_ready; size_t payload_size; size_t lsa_size; struct mutex mbox_mutex; /* Protects device mailbox and firmware */ diff --git a/drivers/cxl/cxlpci.h b/drivers/cxl/cxlpci.h index 0465ef963cd6..7c02e55b8042 100644 --- a/drivers/cxl/cxlpci.h +++ b/drivers/cxl/cxlpci.h @@ -31,6 +31,8 @@ #define CXL_DVSEC_RANGE_BASE_LOW(i) (0x24 + (i * 0x10)) #define CXL_DVSEC_MEM_BASE_LOW_MASK GENMASK(31, 28) +#define CXL_DVSEC_RANGE_MAX 2 + /* CXL 2.0 8.1.4: Non-CXL Function Map DVSEC */ #define CXL_DVSEC_FUNCTION_MAP 2 diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c index 10caf180b3fa..519edd0eb196 100644 --- a/drivers/cxl/mem.c +++ b/drivers/cxl/mem.c @@ -124,6 +124,9 @@ static int cxl_mem_probe(struct device *dev) struct dentry *dentry; int rc; + if (!cxlds->media_ready) + return -EBUSY; + /* * Someone is trying to reattach this device after it lost its port * connection (an endpoint port previously registered by this memdev was diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index f7a5b8e9c102..0872f2233ed0 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -708,6 +708,12 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (rc) dev_dbg(&pdev->dev, "Failed to map RAS capability.\n"); + rc = cxl_await_media_ready(cxlds); + if (rc == 0) + cxlds->media_ready = true; + else + dev_warn(&pdev->dev, "Media not active (%d)\n", rc); + rc = cxl_pci_setup_mailbox(cxlds); if (rc) return rc; diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c index eb57324c4ad4..c23b6164e1c0 100644 --- a/drivers/cxl/port.c +++ b/drivers/cxl/port.c @@ -60,13 +60,17 @@ static int discover_region(struct device *dev, void *root) static int cxl_switch_port_probe(struct cxl_port *port) { struct cxl_hdm *cxlhdm; - int rc; + int rc, nr_dports; - rc = devm_cxl_port_enumerate_dports(port); - if (rc < 0) - return rc; + nr_dports = devm_cxl_port_enumerate_dports(port); + if (nr_dports < 0) + return nr_dports; cxlhdm = devm_cxl_setup_hdm(port, NULL); + rc = devm_cxl_enable_hdm(port, cxlhdm); + if (rc) + return rc; + if (!IS_ERR(cxlhdm)) return devm_cxl_enumerate_decoders(cxlhdm, NULL); @@ -75,7 +79,7 @@ static int cxl_switch_port_probe(struct cxl_port *port) return PTR_ERR(cxlhdm); } - if (rc == 1) { + if (nr_dports == 1) { dev_dbg(&port->dev, "Fallback to passthrough decoder\n"); return devm_cxl_add_passthrough_decoder(port); } @@ -113,12 +117,6 @@ static int cxl_endpoint_port_probe(struct cxl_port *port) if (rc) return rc; - rc = cxl_await_media_ready(cxlds); - if (rc) { - dev_err(&port->dev, "Media not active (%d)\n", rc); - return rc; - } - rc = devm_cxl_enumerate_decoders(cxlhdm, &info); if (rc) return rc; diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c index 8858470246e1..ee3a219e3a89 100644 --- a/drivers/dma/at_hdmac.c +++ b/drivers/dma/at_hdmac.c @@ -132,7 +132,7 @@ #define ATC_DST_PIP BIT(12) /* Destination Picture-in-Picture enabled */ #define ATC_SRC_DSCR_DIS BIT(16) /* Src Descriptor fetch disable */ #define ATC_DST_DSCR_DIS BIT(20) /* Dst Descriptor fetch disable */ -#define ATC_FC GENMASK(22, 21) /* Choose Flow Controller */ +#define ATC_FC GENMASK(23, 21) /* Choose Flow Controller */ #define ATC_FC_MEM2MEM 0x0 /* Mem-to-Mem (DMA) */ #define ATC_FC_MEM2PER 0x1 /* Mem-to-Periph (DMA) */ #define ATC_FC_PER2MEM 0x2 /* Periph-to-Mem (DMA) */ @@ -153,8 +153,6 @@ #define ATC_AUTO BIT(31) /* Auto multiple buffer tx enable */ /* Bitfields in CFG */ -#define ATC_PER_MSB(h) ((0x30U & (h)) >> 4) /* Extract most significant bits of a handshaking identifier */ - #define ATC_SRC_PER GENMASK(3, 0) /* Channel src rq associated with periph handshaking ifc h */ #define ATC_DST_PER GENMASK(7, 4) /* Channel dst rq associated with periph handshaking ifc h */ #define ATC_SRC_REP BIT(8) /* Source Replay Mod */ @@ -181,10 +179,15 @@ #define ATC_DPIP_HOLE GENMASK(15, 0) #define ATC_DPIP_BOUNDARY GENMASK(25, 16) -#define ATC_SRC_PER_ID(id) (FIELD_PREP(ATC_SRC_PER_MSB, (id)) | \ - FIELD_PREP(ATC_SRC_PER, (id))) -#define ATC_DST_PER_ID(id) (FIELD_PREP(ATC_DST_PER_MSB, (id)) | \ - FIELD_PREP(ATC_DST_PER, (id))) +#define ATC_PER_MSB GENMASK(5, 4) /* Extract MSBs of a handshaking identifier */ +#define ATC_SRC_PER_ID(id) \ + ({ typeof(id) _id = (id); \ + FIELD_PREP(ATC_SRC_PER_MSB, FIELD_GET(ATC_PER_MSB, _id)) | \ + FIELD_PREP(ATC_SRC_PER, _id); }) +#define ATC_DST_PER_ID(id) \ + ({ typeof(id) _id = (id); \ + FIELD_PREP(ATC_DST_PER_MSB, FIELD_GET(ATC_PER_MSB, _id)) | \ + FIELD_PREP(ATC_DST_PER, _id); }) diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 7da6d9b6098e..c3b37168b21f 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -1102,6 +1102,8 @@ at_xdmac_prep_interleaved(struct dma_chan *chan, NULL, src_addr, dst_addr, xt, xt->sgl); + if (!first) + return NULL; /* Length of the block is (BLEN+1) microblocks. */ for (i = 0; i < xt->numf - 1; i++) @@ -1132,8 +1134,9 @@ at_xdmac_prep_interleaved(struct dma_chan *chan, src_addr, dst_addr, xt, chunk); if (!desc) { - list_splice_tail_init(&first->descs_list, - &atchan->free_descs_list); + if (first) + list_splice_tail_init(&first->descs_list, + &atchan->free_descs_list); return NULL; } diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index ecbf67c2ad2b..d32deb9b4e3d 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -277,7 +277,6 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp) if (wq_dedicated(wq)) { rc = idxd_wq_set_pasid(wq, pasid); if (rc < 0) { - iommu_sva_unbind_device(sva); dev_err(dev, "wq set pasid failed: %d\n", rc); goto failed_set_pasid; } diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index 0d9257fbdfb0..b4731fe6bbc1 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -1050,7 +1050,7 @@ static bool _trigger(struct pl330_thread *thrd) return true; } -static bool _start(struct pl330_thread *thrd) +static bool pl330_start_thread(struct pl330_thread *thrd) { switch (_state(thrd)) { case PL330_STATE_FAULT_COMPLETING: @@ -1702,7 +1702,7 @@ static int pl330_update(struct pl330_dmac *pl330) thrd->req_running = -1; /* Get going again ASAP */ - _start(thrd); + pl330_start_thread(thrd); /* For now, just make a list of callbacks to be done */ list_add_tail(&descdone->rqd, &pl330->req_done); @@ -2089,7 +2089,7 @@ static void pl330_tasklet(struct tasklet_struct *t) } else { /* Make sure the PL330 Channel thread is active */ spin_lock(&pch->thread->dmac->lock); - _start(pch->thread); + pl330_start_thread(pch->thread); spin_unlock(&pch->thread->dmac->lock); } @@ -2107,7 +2107,7 @@ static void pl330_tasklet(struct tasklet_struct *t) if (power_down) { pch->active = true; spin_lock(&pch->thread->dmac->lock); - _start(pch->thread); + pl330_start_thread(pch->thread); spin_unlock(&pch->thread->dmac->lock); power_down = false; } diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index fc3a2a05ab7b..b8329a23728d 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -5527,7 +5527,7 @@ static int udma_probe(struct platform_device *pdev) return ret; } -static int udma_pm_suspend(struct device *dev) +static int __maybe_unused udma_pm_suspend(struct device *dev) { struct udma_dev *ud = dev_get_drvdata(dev); struct dma_device *dma_dev = &ud->ddev; @@ -5549,7 +5549,7 @@ static int udma_pm_suspend(struct device *dev) return 0; } -static int udma_pm_resume(struct device *dev) +static int __maybe_unused udma_pm_resume(struct device *dev) { struct udma_dev *ud = dev_get_drvdata(dev); struct dma_device *dma_dev = &ud->ddev; diff --git a/drivers/firewire/net.c b/drivers/firewire/net.c index af22be84034b..538bd677c254 100644 --- a/drivers/firewire/net.c +++ b/drivers/firewire/net.c @@ -706,21 +706,22 @@ static void fwnet_receive_packet(struct fw_card *card, struct fw_request *r, int rcode; if (destination == IEEE1394_ALL_NODES) { - kfree(r); - - return; - } - - if (offset != dev->handler.offset) + // Although the response to the broadcast packet is not necessarily required, the + // fw_send_response() function should still be called to maintain the reference + // counting of the object. In the case, the call of function just releases the + // object as a result to decrease the reference counting. + rcode = RCODE_COMPLETE; + } else if (offset != dev->handler.offset) { rcode = RCODE_ADDRESS_ERROR; - else if (tcode != TCODE_WRITE_BLOCK_REQUEST) + } else if (tcode != TCODE_WRITE_BLOCK_REQUEST) { rcode = RCODE_TYPE_ERROR; - else if (fwnet_incoming_packet(dev, payload, length, - source, generation, false) != 0) { + } else if (fwnet_incoming_packet(dev, payload, length, + source, generation, false) != 0) { dev_err(&dev->netdev->dev, "incoming packet failure\n"); rcode = RCODE_CONFLICT_ERROR; - } else + } else { rcode = RCODE_COMPLETE; + } fw_send_response(card, r, rcode); } diff --git a/drivers/firmware/arm_ffa/bus.c b/drivers/firmware/arm_ffa/bus.c index f29d77ecf72d..2b8bfcd010f5 100644 --- a/drivers/firmware/arm_ffa/bus.c +++ b/drivers/firmware/arm_ffa/bus.c @@ -15,6 +15,8 @@ #include "common.h" +static DEFINE_IDA(ffa_bus_id); + static int ffa_device_match(struct device *dev, struct device_driver *drv) { const struct ffa_device_id *id_table; @@ -53,7 +55,8 @@ static void ffa_device_remove(struct device *dev) { struct ffa_driver *ffa_drv = to_ffa_driver(dev->driver); - ffa_drv->remove(to_ffa_dev(dev)); + if (ffa_drv->remove) + ffa_drv->remove(to_ffa_dev(dev)); } static int ffa_device_uevent(const struct device *dev, struct kobj_uevent_env *env) @@ -130,6 +133,7 @@ static void ffa_release_device(struct device *dev) { struct ffa_device *ffa_dev = to_ffa_dev(dev); + ida_free(&ffa_bus_id, ffa_dev->id); kfree(ffa_dev); } @@ -170,18 +174,24 @@ bool ffa_device_is_valid(struct ffa_device *ffa_dev) struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, const struct ffa_ops *ops) { - int ret; + int id, ret; struct device *dev; struct ffa_device *ffa_dev; + id = ida_alloc_min(&ffa_bus_id, 1, GFP_KERNEL); + if (id < 0) + return NULL; + ffa_dev = kzalloc(sizeof(*ffa_dev), GFP_KERNEL); - if (!ffa_dev) + if (!ffa_dev) { + ida_free(&ffa_bus_id, id); return NULL; + } dev = &ffa_dev->dev; dev->bus = &ffa_bus_type; dev->release = ffa_release_device; - dev_set_name(&ffa_dev->dev, "arm-ffa-%04x", vm_id); + dev_set_name(&ffa_dev->dev, "arm-ffa-%d", id); ffa_dev->vm_id = vm_id; ffa_dev->ops = ops; @@ -217,4 +227,5 @@ void arm_ffa_bus_exit(void) { ffa_devices_unregister(); bus_unregister(&ffa_bus_type); + ida_destroy(&ffa_bus_id); } diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index fa85c64d3ded..e23409138667 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -193,7 +193,8 @@ __ffa_partition_info_get(u32 uuid0, u32 uuid1, u32 uuid2, u32 uuid3, int idx, count, flags = 0, sz, buf_sz; ffa_value_t partition_info; - if (!buffer || !num_partitions) /* Just get the count for now */ + if (drv_info->version > FFA_VERSION_1_0 && + (!buffer || !num_partitions)) /* Just get the count for now */ flags = PARTITION_INFO_GET_RETURN_COUNT_ONLY; mutex_lock(&drv_info->rx_lock); @@ -420,12 +421,17 @@ ffa_setup_and_transmit(u32 func_id, void *buffer, u32 max_fragsize, ep_mem_access->receiver = args->attrs[idx].receiver; ep_mem_access->attrs = args->attrs[idx].attrs; ep_mem_access->composite_off = COMPOSITE_OFFSET(args->nattrs); + ep_mem_access->flag = 0; + ep_mem_access->reserved = 0; } + mem_region->reserved_0 = 0; + mem_region->reserved_1 = 0; mem_region->ep_count = args->nattrs; composite = buffer + COMPOSITE_OFFSET(args->nattrs); composite->total_pg_cnt = ffa_get_num_pages_sg(args->sg); composite->addr_range_cnt = num_entries; + composite->reserved = 0; length = COMPOSITE_CONSTITUENTS_OFFSET(args->nattrs, num_entries); frag_len = COMPOSITE_CONSTITUENTS_OFFSET(args->nattrs, 0); @@ -460,6 +466,7 @@ ffa_setup_and_transmit(u32 func_id, void *buffer, u32 max_fragsize, constituents->address = sg_phys(args->sg); constituents->pg_cnt = args->sg->length / FFA_PAGE_SIZE; + constituents->reserved = 0; constituents++; frag_len += sizeof(struct ffa_mem_region_addr_range); } while ((args->sg = sg_next(args->sg))); diff --git a/drivers/firmware/arm_scmi/raw_mode.c b/drivers/firmware/arm_scmi/raw_mode.c index d40df099fd51..6971dcf72fb9 100644 --- a/drivers/firmware/arm_scmi/raw_mode.c +++ b/drivers/firmware/arm_scmi/raw_mode.c @@ -1066,7 +1066,7 @@ static int scmi_xfer_raw_worker_init(struct scmi_raw_mode_info *raw) raw->wait_wq = alloc_workqueue("scmi-raw-wait-wq-%d", WQ_UNBOUND | WQ_FREEZABLE | - WQ_HIGHPRI, WQ_SYSFS, raw->id); + WQ_HIGHPRI | WQ_SYSFS, 0, raw->id); if (!raw->wait_wq) return -ENOMEM; diff --git a/drivers/firmware/efi/libstub/Makefile.zboot b/drivers/firmware/efi/libstub/Makefile.zboot index 89ef820f3b34..2c489627a807 100644 --- a/drivers/firmware/efi/libstub/Makefile.zboot +++ b/drivers/firmware/efi/libstub/Makefile.zboot @@ -32,7 +32,8 @@ zboot-size-len-$(CONFIG_KERNEL_GZIP) := 0 $(obj)/vmlinuz: $(obj)/vmlinux.bin FORCE $(call if_changed,$(zboot-method-y)) -OBJCOPYFLAGS_vmlinuz.o := -I binary -O $(EFI_ZBOOT_BFD_TARGET) $(EFI_ZBOOT_OBJCOPY_FLAGS) \ +# avoid eager evaluation to prevent references to non-existent build artifacts +OBJCOPYFLAGS_vmlinuz.o = -I binary -O $(EFI_ZBOOT_BFD_TARGET) $(EFI_ZBOOT_OBJCOPY_FLAGS) \ --rename-section .data=.gzdata,load,alloc,readonly,contents $(obj)/vmlinuz.o: $(obj)/vmlinuz FORCE $(call if_changed,objcopy) diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index 67d5a20802e0..54a2822cae77 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -1133,4 +1133,7 @@ const u8 *__efi_get_smbios_string(const struct efi_smbios_record *record, void efi_remap_image(unsigned long image_base, unsigned alloc_size, unsigned long code_size); +asmlinkage efi_status_t __efiapi +efi_zboot_entry(efi_handle_t handle, efi_system_table_t *systab); + #endif diff --git a/drivers/firmware/sysfb_simplefb.c b/drivers/firmware/sysfb_simplefb.c index 82c64cb9f531..74363ed7501f 100644 --- a/drivers/firmware/sysfb_simplefb.c +++ b/drivers/firmware/sysfb_simplefb.c @@ -51,7 +51,8 @@ __init bool sysfb_parse_mode(const struct screen_info *si, * * It's not easily possible to fix this in struct screen_info, * as this could break UAPI. The best solution is to compute - * bits_per_pixel here and ignore lfb_depth. In the loop below, + * bits_per_pixel from the color bits, reserved bits and + * reported lfb_depth, whichever is highest. In the loop below, * ignore simplefb formats with alpha bits, as EFI and VESA * don't specify alpha channels. */ @@ -60,6 +61,7 @@ __init bool sysfb_parse_mode(const struct screen_info *si, si->green_size + si->green_pos, si->blue_size + si->blue_pos), si->rsvd_size + si->rsvd_pos); + bits_per_pixel = max_t(u32, bits_per_pixel, si->lfb_depth); } else { bits_per_pixel = si->lfb_depth; } diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 5521f060d58e..f45c6a36551c 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -897,7 +897,7 @@ config GPIO_F7188X help This option enables support for GPIOs found on Fintek Super-I/O chips F71869, F71869A, F71882FG, F71889F and F81866. - As well as Nuvoton Super-I/O chip NCT6116D. + As well as Nuvoton Super-I/O chip NCT6126D. To compile this driver as a module, choose M here: the module will be called f7188x-gpio. diff --git a/drivers/gpio/gpio-f7188x.c b/drivers/gpio/gpio-f7188x.c index 9effa7769bef..f54ca5a1775e 100644 --- a/drivers/gpio/gpio-f7188x.c +++ b/drivers/gpio/gpio-f7188x.c @@ -48,7 +48,7 @@ /* * Nuvoton devices. */ -#define SIO_NCT6116D_ID 0xD283 /* NCT6116D chipset ID */ +#define SIO_NCT6126D_ID 0xD283 /* NCT6126D chipset ID */ #define SIO_LD_GPIO_NUVOTON 0x07 /* GPIO logical device */ @@ -62,7 +62,7 @@ enum chips { f81866, f81804, f81865, - nct6116d, + nct6126d, }; static const char * const f7188x_names[] = { @@ -74,7 +74,7 @@ static const char * const f7188x_names[] = { "f81866", "f81804", "f81865", - "nct6116d", + "nct6126d", }; struct f7188x_sio { @@ -187,8 +187,8 @@ static int f7188x_gpio_set_config(struct gpio_chip *chip, unsigned offset, /* Output mode register (0:open drain 1:push-pull). */ #define f7188x_gpio_out_mode(base) ((base) + 3) -#define f7188x_gpio_dir_invert(type) ((type) == nct6116d) -#define f7188x_gpio_data_single(type) ((type) == nct6116d) +#define f7188x_gpio_dir_invert(type) ((type) == nct6126d) +#define f7188x_gpio_data_single(type) ((type) == nct6126d) static struct f7188x_gpio_bank f71869_gpio_bank[] = { F7188X_GPIO_BANK(0, 6, 0xF0, DRVNAME "-0"), @@ -274,7 +274,7 @@ static struct f7188x_gpio_bank f81865_gpio_bank[] = { F7188X_GPIO_BANK(60, 5, 0x90, DRVNAME "-6"), }; -static struct f7188x_gpio_bank nct6116d_gpio_bank[] = { +static struct f7188x_gpio_bank nct6126d_gpio_bank[] = { F7188X_GPIO_BANK(0, 8, 0xE0, DRVNAME "-0"), F7188X_GPIO_BANK(10, 8, 0xE4, DRVNAME "-1"), F7188X_GPIO_BANK(20, 8, 0xE8, DRVNAME "-2"), @@ -282,7 +282,7 @@ static struct f7188x_gpio_bank nct6116d_gpio_bank[] = { F7188X_GPIO_BANK(40, 8, 0xF0, DRVNAME "-4"), F7188X_GPIO_BANK(50, 8, 0xF4, DRVNAME "-5"), F7188X_GPIO_BANK(60, 8, 0xF8, DRVNAME "-6"), - F7188X_GPIO_BANK(70, 1, 0xFC, DRVNAME "-7"), + F7188X_GPIO_BANK(70, 8, 0xFC, DRVNAME "-7"), }; static int f7188x_gpio_get_direction(struct gpio_chip *chip, unsigned offset) @@ -490,9 +490,9 @@ static int f7188x_gpio_probe(struct platform_device *pdev) data->nr_bank = ARRAY_SIZE(f81865_gpio_bank); data->bank = f81865_gpio_bank; break; - case nct6116d: - data->nr_bank = ARRAY_SIZE(nct6116d_gpio_bank); - data->bank = nct6116d_gpio_bank; + case nct6126d: + data->nr_bank = ARRAY_SIZE(nct6126d_gpio_bank); + data->bank = nct6126d_gpio_bank; break; default: return -ENODEV; @@ -559,9 +559,9 @@ static int __init f7188x_find(int addr, struct f7188x_sio *sio) case SIO_F81865_ID: sio->type = f81865; break; - case SIO_NCT6116D_ID: + case SIO_NCT6126D_ID: sio->device = SIO_LD_GPIO_NUVOTON; - sio->type = nct6116d; + sio->type = nct6126d; break; default: pr_info("Unsupported Fintek device 0x%04x\n", devid); @@ -569,7 +569,7 @@ static int __init f7188x_find(int addr, struct f7188x_sio *sio) } /* double check manufacturer where possible */ - if (sio->type != nct6116d) { + if (sio->type != nct6126d) { manid = superio_inw(addr, SIO_FINTEK_MANID); if (manid != SIO_FINTEK_ID) { pr_debug("Not a Fintek device at 0x%08x\n", addr); @@ -581,7 +581,7 @@ static int __init f7188x_find(int addr, struct f7188x_sio *sio) err = 0; pr_info("Found %s at %#x\n", f7188x_names[sio->type], (unsigned int)addr); - if (sio->type != nct6116d) + if (sio->type != nct6126d) pr_info(" revision %d\n", superio_inb(addr, SIO_FINTEK_DEVREV)); err: diff --git a/drivers/gpio/gpio-mockup.c b/drivers/gpio/gpio-mockup.c index e6a7049bef64..b32063ac845a 100644 --- a/drivers/gpio/gpio-mockup.c +++ b/drivers/gpio/gpio-mockup.c @@ -369,7 +369,7 @@ static void gpio_mockup_debugfs_setup(struct device *dev, priv->offset = i; priv->desc = gpiochip_get_desc(gc, i); - debugfs_create_file(name, 0200, chip->dbg_dir, priv, + debugfs_create_file(name, 0600, chip->dbg_dir, priv, &gpio_mockup_debugfs_ops); } } diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 04fb05df805b..a7220e04a93e 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -209,6 +209,8 @@ static int gpiochip_find_base(int ngpio) break; /* nope, check the space right after the chip */ base = gdev->base + gdev->ngpio; + if (base < GPIO_DYNAMIC_BASE) + base = GPIO_DYNAMIC_BASE; } if (gpio_is_valid(base)) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 981a9cfb63b5..5c7d40873ee2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3757,6 +3757,12 @@ int amdgpu_device_init(struct amdgpu_device *adev, adev->have_atomics_support = ((struct amd_sriov_msg_pf2vf_info *) adev->virt.fw_reserve.p_pf2vf)->pcie_atomic_ops_support_flags == (PCI_EXP_DEVCAP2_ATOMIC_COMP32 | PCI_EXP_DEVCAP2_ATOMIC_COMP64); + /* APUs w/ gfx9 onwards doesn't reply on PCIe atomics, rather it is a + * internal path natively support atomics, set have_atomics_support to true. + */ + else if ((adev->flags & AMD_IS_APU) && + (adev->ip_versions[GC_HWIP][0] > IP_VERSION(9, 0, 0))) + adev->have_atomics_support = true; else adev->have_atomics_support = !pci_enable_atomic_ops_to_root(adev->pdev, @@ -4506,7 +4512,11 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev) dev_info(adev->dev, "recover vram bo from shadow start\n"); mutex_lock(&adev->shadow_list_lock); list_for_each_entry(vmbo, &adev->shadow_list, shadow_list) { - shadow = &vmbo->bo; + /* If vm is compute context or adev is APU, shadow will be NULL */ + if (!vmbo->shadow) + continue; + shadow = vmbo->shadow; + /* No need to recover an evicted BO */ if (shadow->tbo.resource->mem_type != TTM_PL_TT || shadow->tbo.resource->start == AMDGPU_BO_INVALID_OFFSET || diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index f52d0ba91a77..a7d250809da9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -582,7 +582,8 @@ void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev) if (r) amdgpu_fence_driver_force_completion(ring); - if (ring->fence_drv.irq_src) + if (!drm_dev_is_unplugged(adev_to_drm(adev)) && + ring->fence_drv.irq_src) amdgpu_irq_put(adev, ring->fence_drv.irq_src, ring->fence_drv.irq_type); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index 9d3a0542c996..f3f541ba0aca 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -687,9 +687,11 @@ int amdgpu_gfx_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *r if (r) return r; - r = amdgpu_irq_get(adev, &adev->gfx.cp_ecc_error_irq, 0); - if (r) - goto late_fini; + if (adev->gfx.cp_ecc_error_irq.funcs) { + r = amdgpu_irq_get(adev, &adev->gfx.cp_ecc_error_irq, 0); + if (r) + goto late_fini; + } } else { amdgpu_ras_feature_enable_on_boot(adev, ras_block, 0); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index 4e2531758866..95b0f984acbf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -593,6 +593,8 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev) case IP_VERSION(9, 3, 0): /* GC 10.3.7 */ case IP_VERSION(10, 3, 7): + /* GC 11.0.1 */ + case IP_VERSION(11, 0, 1): if (amdgpu_tmz == 0) { adev->gmc.tmz_enabled = false; dev_info(adev->dev, @@ -616,7 +618,6 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev) case IP_VERSION(10, 3, 1): /* YELLOW_CARP*/ case IP_VERSION(10, 3, 3): - case IP_VERSION(11, 0, 1): case IP_VERSION(11, 0, 4): /* Don't enable it by default yet. */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c index b07c000fc8ba..4fa019c8aefc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c @@ -241,6 +241,31 @@ int amdgpu_jpeg_process_poison_irq(struct amdgpu_device *adev, return 0; } +int amdgpu_jpeg_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block) +{ + int r, i; + + r = amdgpu_ras_block_late_init(adev, ras_block); + if (r) + return r; + + if (amdgpu_ras_is_supported(adev, ras_block->block)) { + for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) { + if (adev->jpeg.harvest_config & (1 << i)) + continue; + + r = amdgpu_irq_get(adev, &adev->jpeg.inst[i].ras_poison_irq, 0); + if (r) + goto late_fini; + } + } + return 0; + +late_fini: + amdgpu_ras_block_late_fini(adev, ras_block); + return r; +} + int amdgpu_jpeg_ras_sw_init(struct amdgpu_device *adev) { int err; @@ -262,7 +287,7 @@ int amdgpu_jpeg_ras_sw_init(struct amdgpu_device *adev) adev->jpeg.ras_if = &ras->ras_block.ras_comm; if (!ras->ras_block.ras_late_init) - ras->ras_block.ras_late_init = amdgpu_ras_block_late_init; + ras->ras_block.ras_late_init = amdgpu_jpeg_ras_late_init; return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h index 0ca76f0f23e9..1471a1ebb034 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h @@ -38,6 +38,7 @@ struct amdgpu_jpeg_reg{ struct amdgpu_jpeg_inst { struct amdgpu_ring ring_dec; struct amdgpu_irq_src irq; + struct amdgpu_irq_src ras_poison_irq; struct amdgpu_jpeg_reg external; }; @@ -72,6 +73,8 @@ int amdgpu_jpeg_dec_ring_test_ib(struct amdgpu_ring *ring, long timeout); int amdgpu_jpeg_process_poison_irq(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry); +int amdgpu_jpeg_ras_late_init(struct amdgpu_device *adev, + struct ras_common_if *ras_block); int amdgpu_jpeg_ras_sw_init(struct amdgpu_device *adev); #endif /*__AMDGPU_JPEG_H__*/ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index e63fcc58e8e0..2d94f1b63bd6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -1181,6 +1181,31 @@ int amdgpu_vcn_process_poison_irq(struct amdgpu_device *adev, return 0; } +int amdgpu_vcn_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block) +{ + int r, i; + + r = amdgpu_ras_block_late_init(adev, ras_block); + if (r) + return r; + + if (amdgpu_ras_is_supported(adev, ras_block->block)) { + for (i = 0; i < adev->vcn.num_vcn_inst; i++) { + if (adev->vcn.harvest_config & (1 << i)) + continue; + + r = amdgpu_irq_get(adev, &adev->vcn.inst[i].ras_poison_irq, 0); + if (r) + goto late_fini; + } + } + return 0; + +late_fini: + amdgpu_ras_block_late_fini(adev, ras_block); + return r; +} + int amdgpu_vcn_ras_sw_init(struct amdgpu_device *adev) { int err; @@ -1202,7 +1227,7 @@ int amdgpu_vcn_ras_sw_init(struct amdgpu_device *adev) adev->vcn.ras_if = &ras->ras_block.ras_comm; if (!ras->ras_block.ras_late_init) - ras->ras_block.ras_late_init = amdgpu_ras_block_late_init; + ras->ras_block.ras_late_init = amdgpu_vcn_ras_late_init; return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h index c730949ece7d..f1397ef66fd7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h @@ -234,6 +234,7 @@ struct amdgpu_vcn_inst { struct amdgpu_ring ring_enc[AMDGPU_VCN_MAX_ENC_RINGS]; atomic_t sched_score; struct amdgpu_irq_src irq; + struct amdgpu_irq_src ras_poison_irq; struct amdgpu_vcn_reg external; struct amdgpu_bo *dpg_sram_bo; struct dpg_pause_state pause_state; @@ -400,6 +401,8 @@ void amdgpu_debugfs_vcn_fwlog_init(struct amdgpu_device *adev, int amdgpu_vcn_process_poison_irq(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry); +int amdgpu_vcn_ras_late_init(struct amdgpu_device *adev, + struct ras_common_if *ras_block); int amdgpu_vcn_ras_sw_init(struct amdgpu_device *adev); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index f5b5ce1051a2..ab44c1391d52 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -6892,8 +6892,10 @@ static int gfx_v10_0_kiq_resume(struct amdgpu_device *adev) return r; r = amdgpu_bo_kmap(ring->mqd_obj, (void **)&ring->mqd_ptr); - if (unlikely(r != 0)) + if (unlikely(r != 0)) { + amdgpu_bo_unreserve(ring->mqd_obj); return r; + } gfx_v10_0_kiq_init_queue(ring); amdgpu_bo_kunmap(ring->mqd_obj); @@ -8152,8 +8154,14 @@ static int gfx_v10_0_set_powergating_state(void *handle, case IP_VERSION(10, 3, 3): case IP_VERSION(10, 3, 6): case IP_VERSION(10, 3, 7): + if (!enable) + amdgpu_gfx_off_ctrl(adev, false); + gfx_v10_cntl_pg(adev, enable); - amdgpu_gfx_off_ctrl(adev, enable); + + if (enable) + amdgpu_gfx_off_ctrl(adev, true); + break; default: break; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index a9da0486467a..c4940b6ea1c4 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -1315,13 +1315,6 @@ static int gfx_v11_0_sw_init(void *handle) if (r) return r; - /* ECC error */ - r = amdgpu_irq_add_id(adev, SOC21_IH_CLIENTID_GRBM_CP, - GFX_11_0_0__SRCID__CP_ECC_ERROR, - &adev->gfx.cp_ecc_error_irq); - if (r) - return r; - /* FED error */ r = amdgpu_irq_add_id(adev, SOC21_IH_CLIENTID_GFX, GFX_11_0_0__SRCID__RLC_GC_FED_INTERRUPT, @@ -4444,7 +4437,6 @@ static int gfx_v11_0_hw_fini(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; int r; - amdgpu_irq_put(adev, &adev->gfx.cp_ecc_error_irq, 0); amdgpu_irq_put(adev, &adev->gfx.priv_reg_irq, 0); amdgpu_irq_put(adev, &adev->gfx.priv_inst_irq, 0); @@ -4675,24 +4667,27 @@ static uint64_t gfx_v11_0_get_gpu_clock_counter(struct amdgpu_device *adev) uint64_t clock; uint64_t clock_counter_lo, clock_counter_hi_pre, clock_counter_hi_after; - amdgpu_gfx_off_ctrl(adev, false); - mutex_lock(&adev->gfx.gpu_clock_mutex); if (amdgpu_sriov_vf(adev)) { + amdgpu_gfx_off_ctrl(adev, false); + mutex_lock(&adev->gfx.gpu_clock_mutex); clock_counter_hi_pre = (uint64_t)RREG32_SOC15(GC, 0, regCP_MES_MTIME_HI); clock_counter_lo = (uint64_t)RREG32_SOC15(GC, 0, regCP_MES_MTIME_LO); clock_counter_hi_after = (uint64_t)RREG32_SOC15(GC, 0, regCP_MES_MTIME_HI); if (clock_counter_hi_pre != clock_counter_hi_after) clock_counter_lo = (uint64_t)RREG32_SOC15(GC, 0, regCP_MES_MTIME_LO); + mutex_unlock(&adev->gfx.gpu_clock_mutex); + amdgpu_gfx_off_ctrl(adev, true); } else { + preempt_disable(); clock_counter_hi_pre = (uint64_t)RREG32_SOC15(SMUIO, 0, regGOLDEN_TSC_COUNT_UPPER); clock_counter_lo = (uint64_t)RREG32_SOC15(SMUIO, 0, regGOLDEN_TSC_COUNT_LOWER); clock_counter_hi_after = (uint64_t)RREG32_SOC15(SMUIO, 0, regGOLDEN_TSC_COUNT_UPPER); if (clock_counter_hi_pre != clock_counter_hi_after) clock_counter_lo = (uint64_t)RREG32_SOC15(SMUIO, 0, regGOLDEN_TSC_COUNT_LOWER); + preempt_enable(); } clock = clock_counter_lo | (clock_counter_hi_after << 32ULL); - mutex_unlock(&adev->gfx.gpu_clock_mutex); - amdgpu_gfx_off_ctrl(adev, true); + return clock; } @@ -5158,8 +5153,14 @@ static int gfx_v11_0_set_powergating_state(void *handle, break; case IP_VERSION(11, 0, 1): case IP_VERSION(11, 0, 4): + if (!enable) + amdgpu_gfx_off_ctrl(adev, false); + gfx_v11_cntl_pg(adev, enable); - amdgpu_gfx_off_ctrl(adev, enable); + + if (enable) + amdgpu_gfx_off_ctrl(adev, true); + break; default: break; @@ -5897,36 +5898,6 @@ static void gfx_v11_0_set_compute_eop_interrupt_state(struct amdgpu_device *adev } } -#define CP_ME1_PIPE_INST_ADDR_INTERVAL 0x1 -#define SET_ECC_ME_PIPE_STATE(reg_addr, state) \ - do { \ - uint32_t tmp = RREG32_SOC15_IP(GC, reg_addr); \ - tmp = REG_SET_FIELD(tmp, CP_ME1_PIPE0_INT_CNTL, CP_ECC_ERROR_INT_ENABLE, state); \ - WREG32_SOC15_IP(GC, reg_addr, tmp); \ - } while (0) - -static int gfx_v11_0_set_cp_ecc_error_state(struct amdgpu_device *adev, - struct amdgpu_irq_src *source, - unsigned type, - enum amdgpu_interrupt_state state) -{ - uint32_t ecc_irq_state = 0; - uint32_t pipe0_int_cntl_addr = 0; - int i = 0; - - ecc_irq_state = (state == AMDGPU_IRQ_STATE_ENABLE) ? 1 : 0; - - pipe0_int_cntl_addr = SOC15_REG_OFFSET(GC, 0, regCP_ME1_PIPE0_INT_CNTL); - - WREG32_FIELD15_PREREG(GC, 0, CP_INT_CNTL_RING0, CP_ECC_ERROR_INT_ENABLE, ecc_irq_state); - - for (i = 0; i < adev->gfx.mec.num_pipe_per_mec; i++) - SET_ECC_ME_PIPE_STATE(pipe0_int_cntl_addr + i * CP_ME1_PIPE_INST_ADDR_INTERVAL, - ecc_irq_state); - - return 0; -} - static int gfx_v11_0_set_eop_interrupt_state(struct amdgpu_device *adev, struct amdgpu_irq_src *src, unsigned type, @@ -6341,11 +6312,6 @@ static const struct amdgpu_irq_src_funcs gfx_v11_0_priv_inst_irq_funcs = { .process = gfx_v11_0_priv_inst_irq, }; -static const struct amdgpu_irq_src_funcs gfx_v11_0_cp_ecc_error_irq_funcs = { - .set = gfx_v11_0_set_cp_ecc_error_state, - .process = amdgpu_gfx_cp_ecc_error_irq, -}; - static const struct amdgpu_irq_src_funcs gfx_v11_0_rlc_gc_fed_irq_funcs = { .process = gfx_v11_0_rlc_gc_fed_irq, }; @@ -6361,9 +6327,6 @@ static void gfx_v11_0_set_irq_funcs(struct amdgpu_device *adev) adev->gfx.priv_inst_irq.num_types = 1; adev->gfx.priv_inst_irq.funcs = &gfx_v11_0_priv_inst_irq_funcs; - adev->gfx.cp_ecc_error_irq.num_types = 1; /* CP ECC error */ - adev->gfx.cp_ecc_error_irq.funcs = &gfx_v11_0_cp_ecc_error_irq_funcs; - adev->gfx.rlc_gc_fed_irq.num_types = 1; /* 0x80 FED error */ adev->gfx.rlc_gc_fed_irq.funcs = &gfx_v11_0_rlc_gc_fed_irq_funcs; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index adbcd8127c82..ce22f7b30416 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -3617,8 +3617,10 @@ static int gfx_v9_0_kiq_resume(struct amdgpu_device *adev) return r; r = amdgpu_bo_kmap(ring->mqd_obj, (void **)&ring->mqd_ptr); - if (unlikely(r != 0)) + if (unlikely(r != 0)) { + amdgpu_bo_unreserve(ring->mqd_obj); return r; + } gfx_v9_0_kiq_init_queue(ring); amdgpu_bo_kunmap(ring->mqd_obj); @@ -3764,7 +3766,8 @@ static int gfx_v9_0_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - amdgpu_irq_put(adev, &adev->gfx.cp_ecc_error_irq, 0); + if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX)) + amdgpu_irq_put(adev, &adev->gfx.cp_ecc_error_irq, 0); amdgpu_irq_put(adev, &adev->gfx.priv_reg_irq, 0); amdgpu_irq_put(adev, &adev->gfx.priv_inst_irq, 0); @@ -4002,30 +4005,25 @@ static uint64_t gfx_v9_0_get_gpu_clock_counter(struct amdgpu_device *adev) clock = clock_lo | (clock_hi << 32ULL); break; case IP_VERSION(9, 1, 0): + case IP_VERSION(9, 2, 2): preempt_disable(); - clock_hi = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven); - clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven); - hi_check = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven); - /* The PWR TSC clock frequency is 100MHz, which sets 32-bit carry over - * roughly every 42 seconds. - */ - if (hi_check != clock_hi) { + if (adev->rev_id >= 0x8) { + clock_hi = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven2); + clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven2); + hi_check = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven2); + } else { + clock_hi = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven); clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven); - clock_hi = hi_check; + hi_check = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven); } - preempt_enable(); - clock = clock_lo | (clock_hi << 32ULL); - break; - case IP_VERSION(9, 2, 2): - preempt_disable(); - clock_hi = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven2); - clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven2); - hi_check = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven2); /* The PWR TSC clock frequency is 100MHz, which sets 32-bit carry over - * roughly every 42 seconds. - */ + * roughly every 42 seconds. + */ if (hi_check != clock_hi) { - clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven2); + if (adev->rev_id >= 0x8) + clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven2); + else + clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven); clock_hi = hi_check; } preempt_enable(); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c index d95f9fe8f1c5..4116c112e8a0 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c @@ -31,6 +31,8 @@ #include "umc_v8_10.h" #include "athub/athub_3_0_0_sh_mask.h" #include "athub/athub_3_0_0_offset.h" +#include "dcn/dcn_3_2_0_offset.h" +#include "dcn/dcn_3_2_0_sh_mask.h" #include "oss/osssys_6_0_0_offset.h" #include "ivsrcid/vmc/irqsrcs_vmc_1_0.h" #include "navi10_enum.h" @@ -546,7 +548,24 @@ static void gmc_v11_0_get_vm_pte(struct amdgpu_device *adev, static unsigned gmc_v11_0_get_vbios_fb_size(struct amdgpu_device *adev) { - return 0; + u32 d1vga_control = RREG32_SOC15(DCE, 0, regD1VGA_CONTROL); + unsigned size; + + if (REG_GET_FIELD(d1vga_control, D1VGA_CONTROL, D1VGA_MODE_ENABLE)) { + size = AMDGPU_VBIOS_VGA_ALLOCATION; + } else { + u32 viewport; + u32 pitch; + + viewport = RREG32_SOC15(DCE, 0, regHUBP0_DCSURF_PRI_VIEWPORT_DIMENSION); + pitch = RREG32_SOC15(DCE, 0, regHUBPREQ0_DCSURF_SURFACE_PITCH); + size = (REG_GET_FIELD(viewport, + HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION, PRI_VIEWPORT_HEIGHT) * + REG_GET_FIELD(pitch, HUBPREQ0_DCSURF_SURFACE_PITCH, PITCH) * + 4); + } + + return size; } static const struct amdgpu_gmc_funcs gmc_v11_0_gmc_funcs = { diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c index b040f51d9aa9..73e0dc5a10cd 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c @@ -102,13 +102,13 @@ static int jpeg_v2_5_sw_init(void *handle) /* JPEG DJPEG POISON EVENT */ r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_jpeg[i], - VCN_2_6__SRCID_DJPEG0_POISON, &adev->jpeg.inst[i].irq); + VCN_2_6__SRCID_DJPEG0_POISON, &adev->jpeg.inst[i].ras_poison_irq); if (r) return r; /* JPEG EJPEG POISON EVENT */ r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_jpeg[i], - VCN_2_6__SRCID_EJPEG0_POISON, &adev->jpeg.inst[i].irq); + VCN_2_6__SRCID_EJPEG0_POISON, &adev->jpeg.inst[i].ras_poison_irq); if (r) return r; } @@ -221,6 +221,9 @@ static int jpeg_v2_5_hw_fini(void *handle) if (adev->jpeg.cur_state != AMD_PG_STATE_GATE && RREG32_SOC15(JPEG, i, mmUVD_JRBC_STATUS)) jpeg_v2_5_set_powergating_state(adev, AMD_PG_STATE_GATE); + + if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__JPEG)) + amdgpu_irq_put(adev, &adev->jpeg.inst[i].ras_poison_irq, 0); } return 0; @@ -569,6 +572,14 @@ static int jpeg_v2_5_set_interrupt_state(struct amdgpu_device *adev, return 0; } +static int jpeg_v2_6_set_ras_interrupt_state(struct amdgpu_device *adev, + struct amdgpu_irq_src *source, + unsigned int type, + enum amdgpu_interrupt_state state) +{ + return 0; +} + static int jpeg_v2_5_process_interrupt(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry) @@ -593,10 +604,6 @@ static int jpeg_v2_5_process_interrupt(struct amdgpu_device *adev, case VCN_2_0__SRCID__JPEG_DECODE: amdgpu_fence_process(&adev->jpeg.inst[ip_instance].ring_dec); break; - case VCN_2_6__SRCID_DJPEG0_POISON: - case VCN_2_6__SRCID_EJPEG0_POISON: - amdgpu_jpeg_process_poison_irq(adev, source, entry); - break; default: DRM_ERROR("Unhandled interrupt: %d %d\n", entry->src_id, entry->src_data[0]); @@ -725,6 +732,11 @@ static const struct amdgpu_irq_src_funcs jpeg_v2_5_irq_funcs = { .process = jpeg_v2_5_process_interrupt, }; +static const struct amdgpu_irq_src_funcs jpeg_v2_6_ras_irq_funcs = { + .set = jpeg_v2_6_set_ras_interrupt_state, + .process = amdgpu_jpeg_process_poison_irq, +}; + static void jpeg_v2_5_set_irq_funcs(struct amdgpu_device *adev) { int i; @@ -735,6 +747,9 @@ static void jpeg_v2_5_set_irq_funcs(struct amdgpu_device *adev) adev->jpeg.inst[i].irq.num_types = 1; adev->jpeg.inst[i].irq.funcs = &jpeg_v2_5_irq_funcs; + + adev->jpeg.inst[i].ras_poison_irq.num_types = 1; + adev->jpeg.inst[i].ras_poison_irq.funcs = &jpeg_v2_6_ras_irq_funcs; } } @@ -800,6 +815,7 @@ const struct amdgpu_ras_block_hw_ops jpeg_v2_6_ras_hw_ops = { static struct amdgpu_jpeg_ras jpeg_v2_6_ras = { .ras_block = { .hw_ops = &jpeg_v2_6_ras_hw_ops, + .ras_late_init = amdgpu_jpeg_ras_late_init, }, }; diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c index c55e09432e26..1c2292cc5f2c 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c @@ -54,6 +54,7 @@ static int jpeg_v3_0_early_init(void *handle) switch (adev->ip_versions[UVD_HWIP][0]) { case IP_VERSION(3, 1, 1): + case IP_VERSION(3, 1, 2): break; default: harvest = RREG32_SOC15(JPEG, 0, mmCC_UVD_HARVESTING); diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c index 77e1e64aa1d1..a3d83c9f2c9a 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c @@ -87,13 +87,13 @@ static int jpeg_v4_0_sw_init(void *handle) /* JPEG DJPEG POISON EVENT */ r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, - VCN_4_0__SRCID_DJPEG0_POISON, &adev->jpeg.inst->irq); + VCN_4_0__SRCID_DJPEG0_POISON, &adev->jpeg.inst->ras_poison_irq); if (r) return r; /* JPEG EJPEG POISON EVENT */ r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, - VCN_4_0__SRCID_EJPEG0_POISON, &adev->jpeg.inst->irq); + VCN_4_0__SRCID_EJPEG0_POISON, &adev->jpeg.inst->ras_poison_irq); if (r) return r; @@ -202,7 +202,8 @@ static int jpeg_v4_0_hw_fini(void *handle) RREG32_SOC15(JPEG, 0, regUVD_JRBC_STATUS)) jpeg_v4_0_set_powergating_state(adev, AMD_PG_STATE_GATE); } - amdgpu_irq_put(adev, &adev->jpeg.inst->irq, 0); + if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__JPEG)) + amdgpu_irq_put(adev, &adev->jpeg.inst->ras_poison_irq, 0); return 0; } @@ -670,6 +671,14 @@ static int jpeg_v4_0_set_interrupt_state(struct amdgpu_device *adev, return 0; } +static int jpeg_v4_0_set_ras_interrupt_state(struct amdgpu_device *adev, + struct amdgpu_irq_src *source, + unsigned int type, + enum amdgpu_interrupt_state state) +{ + return 0; +} + static int jpeg_v4_0_process_interrupt(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry) @@ -680,10 +689,6 @@ static int jpeg_v4_0_process_interrupt(struct amdgpu_device *adev, case VCN_4_0__SRCID__JPEG_DECODE: amdgpu_fence_process(&adev->jpeg.inst->ring_dec); break; - case VCN_4_0__SRCID_DJPEG0_POISON: - case VCN_4_0__SRCID_EJPEG0_POISON: - amdgpu_jpeg_process_poison_irq(adev, source, entry); - break; default: DRM_DEV_ERROR(adev->dev, "Unhandled interrupt: %d %d\n", entry->src_id, entry->src_data[0]); @@ -753,10 +758,18 @@ static const struct amdgpu_irq_src_funcs jpeg_v4_0_irq_funcs = { .process = jpeg_v4_0_process_interrupt, }; +static const struct amdgpu_irq_src_funcs jpeg_v4_0_ras_irq_funcs = { + .set = jpeg_v4_0_set_ras_interrupt_state, + .process = amdgpu_jpeg_process_poison_irq, +}; + static void jpeg_v4_0_set_irq_funcs(struct amdgpu_device *adev) { adev->jpeg.inst->irq.num_types = 1; adev->jpeg.inst->irq.funcs = &jpeg_v4_0_irq_funcs; + + adev->jpeg.inst->ras_poison_irq.num_types = 1; + adev->jpeg.inst->ras_poison_irq.funcs = &jpeg_v4_0_ras_irq_funcs; } const struct amdgpu_ip_block_version jpeg_v4_0_ip_block = { @@ -811,6 +824,7 @@ const struct amdgpu_ras_block_hw_ops jpeg_v4_0_ras_hw_ops = { static struct amdgpu_jpeg_ras jpeg_v4_0_ras = { .ras_block = { .hw_ops = &jpeg_v4_0_ras_hw_ops, + .ras_late_init = amdgpu_jpeg_ras_late_init, }, }; diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index 98c826f1f89b..0fb6013441f0 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -98,6 +98,16 @@ static const struct amdgpu_video_codecs nv_video_codecs_decode = }; /* Sienna Cichlid */ +static const struct amdgpu_video_codec_info sc_video_codecs_encode_array[] = { + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2160, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 7680, 4352, 0)}, +}; + +static const struct amdgpu_video_codecs sc_video_codecs_encode = { + .codec_count = ARRAY_SIZE(sc_video_codecs_encode_array), + .codec_array = sc_video_codecs_encode_array, +}; + static const struct amdgpu_video_codec_info sc_video_codecs_decode_array_vcn0[] = { {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)}, @@ -136,8 +146,8 @@ static const struct amdgpu_video_codecs sc_video_codecs_decode_vcn1 = /* SRIOV Sienna Cichlid, not const since data is controlled by host */ static struct amdgpu_video_codec_info sriov_sc_video_codecs_encode_array[] = { - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2160, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 7680, 4352, 0)}, }; static struct amdgpu_video_codec_info sriov_sc_video_codecs_decode_array_vcn0[] = @@ -237,12 +247,12 @@ static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode, } else { if (adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) { if (encode) - *codecs = &nv_video_codecs_encode; + *codecs = &sc_video_codecs_encode; else *codecs = &sc_video_codecs_decode_vcn1; } else { if (encode) - *codecs = &nv_video_codecs_encode; + *codecs = &sc_video_codecs_encode; else *codecs = &sc_video_codecs_decode_vcn0; } @@ -251,14 +261,14 @@ static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode, case IP_VERSION(3, 0, 16): case IP_VERSION(3, 0, 2): if (encode) - *codecs = &nv_video_codecs_encode; + *codecs = &sc_video_codecs_encode; else *codecs = &sc_video_codecs_decode_vcn0; return 0; case IP_VERSION(3, 1, 1): case IP_VERSION(3, 1, 2): if (encode) - *codecs = &nv_video_codecs_encode; + *codecs = &sc_video_codecs_encode; else *codecs = &yc_video_codecs_decode; return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c index e1b7fca09666..5f10883da6a2 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c @@ -57,7 +57,13 @@ static int psp_v10_0_init_microcode(struct psp_context *psp) if (err) return err; - return psp_init_ta_microcode(psp, ucode_prefix); + err = psp_init_ta_microcode(psp, ucode_prefix); + if ((adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 1, 0)) && + (adev->pdev->revision == 0xa1) && + (psp->securedisplay_context.context.bin_desc.fw_version >= 0x27000008)) { + adev->psp.securedisplay_context.context.bin_desc.size_bytes = 0; + } + return err; } static int psp_v10_0_ring_create(struct psp_context *psp, diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index b3cc04dd8653..9295ac7edd56 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -1917,9 +1917,11 @@ static int sdma_v4_0_hw_fini(void *handle) return 0; } - for (i = 0; i < adev->sdma.num_instances; i++) { - amdgpu_irq_put(adev, &adev->sdma.ecc_irq, - AMDGPU_SDMA_IRQ_INSTANCE0 + i); + if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__SDMA)) { + for (i = 0; i < adev->sdma.num_instances; i++) { + amdgpu_irq_put(adev, &adev->sdma.ecc_irq, + AMDGPU_SDMA_IRQ_INSTANCE0 + i); + } } sdma_v4_0_ctx_switch_enable(adev, false); diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index 744be2a05623..d77162536514 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -711,7 +711,7 @@ static int soc21_common_early_init(void *handle) AMD_PG_SUPPORT_VCN_DPG | AMD_PG_SUPPORT_GFX_PG | AMD_PG_SUPPORT_JPEG; - adev->external_rev_id = adev->rev_id + 0x1; + adev->external_rev_id = adev->rev_id + 0x80; break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c index ab0b45d0ead1..515681c88dcb 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c @@ -143,7 +143,7 @@ static int vcn_v2_5_sw_init(void *handle) /* VCN POISON TRAP */ r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_vcns[j], - VCN_2_6__SRCID_UVD_POISON, &adev->vcn.inst[j].irq); + VCN_2_6__SRCID_UVD_POISON, &adev->vcn.inst[j].ras_poison_irq); if (r) return r; } @@ -354,6 +354,9 @@ static int vcn_v2_5_hw_fini(void *handle) (adev->vcn.cur_state != AMD_PG_STATE_GATE && RREG32_SOC15(VCN, i, mmUVD_STATUS))) vcn_v2_5_set_powergating_state(adev, AMD_PG_STATE_GATE); + + if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__VCN)) + amdgpu_irq_put(adev, &adev->vcn.inst[i].ras_poison_irq, 0); } return 0; @@ -1807,6 +1810,14 @@ static int vcn_v2_5_set_interrupt_state(struct amdgpu_device *adev, return 0; } +static int vcn_v2_6_set_ras_interrupt_state(struct amdgpu_device *adev, + struct amdgpu_irq_src *source, + unsigned int type, + enum amdgpu_interrupt_state state) +{ + return 0; +} + static int vcn_v2_5_process_interrupt(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry) @@ -1837,9 +1848,6 @@ static int vcn_v2_5_process_interrupt(struct amdgpu_device *adev, case VCN_2_0__SRCID__UVD_ENC_LOW_LATENCY: amdgpu_fence_process(&adev->vcn.inst[ip_instance].ring_enc[1]); break; - case VCN_2_6__SRCID_UVD_POISON: - amdgpu_vcn_process_poison_irq(adev, source, entry); - break; default: DRM_ERROR("Unhandled interrupt: %d %d\n", entry->src_id, entry->src_data[0]); @@ -1854,6 +1862,11 @@ static const struct amdgpu_irq_src_funcs vcn_v2_5_irq_funcs = { .process = vcn_v2_5_process_interrupt, }; +static const struct amdgpu_irq_src_funcs vcn_v2_6_ras_irq_funcs = { + .set = vcn_v2_6_set_ras_interrupt_state, + .process = amdgpu_vcn_process_poison_irq, +}; + static void vcn_v2_5_set_irq_funcs(struct amdgpu_device *adev) { int i; @@ -1863,6 +1876,9 @@ static void vcn_v2_5_set_irq_funcs(struct amdgpu_device *adev) continue; adev->vcn.inst[i].irq.num_types = adev->vcn.num_enc_rings + 1; adev->vcn.inst[i].irq.funcs = &vcn_v2_5_irq_funcs; + + adev->vcn.inst[i].ras_poison_irq.num_types = adev->vcn.num_enc_rings + 1; + adev->vcn.inst[i].ras_poison_irq.funcs = &vcn_v2_6_ras_irq_funcs; } } @@ -1965,6 +1981,7 @@ const struct amdgpu_ras_block_hw_ops vcn_v2_6_ras_hw_ops = { static struct amdgpu_vcn_ras vcn_v2_6_ras = { .ras_block = { .hw_ops = &vcn_v2_6_ras_hw_ops, + .ras_late_init = amdgpu_vcn_ras_late_init, }, }; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c index bf0674039598..e5fd1e00914d 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c @@ -139,7 +139,7 @@ static int vcn_v4_0_sw_init(void *handle) /* VCN POISON TRAP */ r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_vcns[i], - VCN_4_0__SRCID_UVD_POISON, &adev->vcn.inst[i].irq); + VCN_4_0__SRCID_UVD_POISON, &adev->vcn.inst[i].ras_poison_irq); if (r) return r; @@ -305,8 +305,8 @@ static int vcn_v4_0_hw_fini(void *handle) vcn_v4_0_set_powergating_state(adev, AMD_PG_STATE_GATE); } } - - amdgpu_irq_put(adev, &adev->vcn.inst[i].irq, 0); + if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__VCN)) + amdgpu_irq_put(adev, &adev->vcn.inst[i].ras_poison_irq, 0); } return 0; @@ -1976,6 +1976,24 @@ static int vcn_v4_0_set_interrupt_state(struct amdgpu_device *adev, struct amdgp } /** + * vcn_v4_0_set_ras_interrupt_state - set VCN block RAS interrupt state + * + * @adev: amdgpu_device pointer + * @source: interrupt sources + * @type: interrupt types + * @state: interrupt states + * + * Set VCN block RAS interrupt state + */ +static int vcn_v4_0_set_ras_interrupt_state(struct amdgpu_device *adev, + struct amdgpu_irq_src *source, + unsigned int type, + enum amdgpu_interrupt_state state) +{ + return 0; +} + +/** * vcn_v4_0_process_interrupt - process VCN block interrupt * * @adev: amdgpu_device pointer @@ -2007,9 +2025,6 @@ static int vcn_v4_0_process_interrupt(struct amdgpu_device *adev, struct amdgpu_ case VCN_4_0__SRCID__UVD_ENC_GENERAL_PURPOSE: amdgpu_fence_process(&adev->vcn.inst[ip_instance].ring_enc[0]); break; - case VCN_4_0__SRCID_UVD_POISON: - amdgpu_vcn_process_poison_irq(adev, source, entry); - break; default: DRM_ERROR("Unhandled interrupt: %d %d\n", entry->src_id, entry->src_data[0]); @@ -2024,6 +2039,11 @@ static const struct amdgpu_irq_src_funcs vcn_v4_0_irq_funcs = { .process = vcn_v4_0_process_interrupt, }; +static const struct amdgpu_irq_src_funcs vcn_v4_0_ras_irq_funcs = { + .set = vcn_v4_0_set_ras_interrupt_state, + .process = amdgpu_vcn_process_poison_irq, +}; + /** * vcn_v4_0_set_irq_funcs - set VCN block interrupt irq functions * @@ -2041,6 +2061,9 @@ static void vcn_v4_0_set_irq_funcs(struct amdgpu_device *adev) adev->vcn.inst[i].irq.num_types = adev->vcn.num_enc_rings + 1; adev->vcn.inst[i].irq.funcs = &vcn_v4_0_irq_funcs; + + adev->vcn.inst[i].ras_poison_irq.num_types = adev->vcn.num_enc_rings + 1; + adev->vcn.inst[i].ras_poison_irq.funcs = &vcn_v4_0_ras_irq_funcs; } } @@ -2114,6 +2137,7 @@ const struct amdgpu_ras_block_hw_ops vcn_v4_0_ras_hw_ops = { static struct amdgpu_vcn_ras vcn_v4_0_ras = { .ras_block = { .hw_ops = &vcn_v4_0_ras_hw_ops, + .ras_late_init = amdgpu_vcn_ras_late_init, }, }; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 8b4b186c57f5..d5cec03eaa8d 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2479,20 +2479,25 @@ static void dm_gpureset_toggle_interrupts(struct amdgpu_device *adev, if (acrtc && state->stream_status[i].plane_count != 0) { irq_source = IRQ_TYPE_PFLIP + acrtc->otg_inst; rc = dc_interrupt_set(adev->dm.dc, irq_source, enable) ? 0 : -EBUSY; - DRM_DEBUG_VBL("crtc %d - vupdate irq %sabling: r=%d\n", - acrtc->crtc_id, enable ? "en" : "dis", rc); if (rc) DRM_WARN("Failed to %s pflip interrupts\n", enable ? "enable" : "disable"); if (enable) { - rc = amdgpu_dm_crtc_enable_vblank(&acrtc->base); - if (rc) - DRM_WARN("Failed to enable vblank interrupts\n"); - } else { - amdgpu_dm_crtc_disable_vblank(&acrtc->base); - } + if (amdgpu_dm_crtc_vrr_active(to_dm_crtc_state(acrtc->base.state))) + rc = amdgpu_dm_crtc_set_vupdate_irq(&acrtc->base, true); + } else + rc = amdgpu_dm_crtc_set_vupdate_irq(&acrtc->base, false); + if (rc) + DRM_WARN("Failed to %sable vupdate interrupt\n", enable ? "en" : "dis"); + + irq_source = IRQ_TYPE_VBLANK + acrtc->otg_inst; + /* During gpu-reset we disable and then enable vblank irq, so + * don't use amdgpu_irq_get/put() to avoid refcount change. + */ + if (!dc_interrupt_set(adev->dm.dc, irq_source, enable)) + DRM_WARN("Failed to %sable vblank interrupt\n", enable ? "en" : "dis"); } } @@ -2852,7 +2857,7 @@ static int dm_resume(void *handle) * this is the case when traversing through already created * MST connectors, should be skipped */ - if (aconnector->dc_link->type == dc_connection_mst_branch) + if (aconnector && aconnector->mst_root) continue; mutex_lock(&aconnector->hpd_lock); @@ -6737,7 +6742,7 @@ static int dm_encoder_helper_atomic_check(struct drm_encoder *encoder, int clock, bpp = 0; bool is_y420 = false; - if (!aconnector->mst_output_port || !aconnector->dc_sink) + if (!aconnector->mst_output_port) return 0; mst_port = aconnector->mst_output_port; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c index e3762e806617..440fc0869a34 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c @@ -146,7 +146,6 @@ static void vblank_control_worker(struct work_struct *work) static inline int dm_set_vblank(struct drm_crtc *crtc, bool enable) { - enum dc_irq_source irq_source; struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc); struct amdgpu_device *adev = drm_to_adev(crtc->dev); struct dm_crtc_state *acrtc_state = to_dm_crtc_state(crtc->state); @@ -169,18 +168,9 @@ static inline int dm_set_vblank(struct drm_crtc *crtc, bool enable) if (rc) return rc; - if (amdgpu_in_reset(adev)) { - irq_source = IRQ_TYPE_VBLANK + acrtc->otg_inst; - /* During gpu-reset we disable and then enable vblank irq, so - * don't use amdgpu_irq_get/put() to avoid refcount change. - */ - if (!dc_interrupt_set(adev->dm.dc, irq_source, enable)) - rc = -EBUSY; - } else { - rc = (enable) - ? amdgpu_irq_get(adev, &adev->crtc_irq, acrtc->crtc_id) - : amdgpu_irq_put(adev, &adev->crtc_irq, acrtc->crtc_id); - } + rc = (enable) + ? amdgpu_irq_get(adev, &adev->crtc_irq, acrtc->crtc_id) + : amdgpu_irq_put(adev, &adev->crtc_irq, acrtc->crtc_id); if (rc) return rc; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index 422fbf79da64..5403e9399a46 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -2113,15 +2113,6 @@ void dcn20_optimize_bandwidth( if (hubbub->funcs->program_compbuf_size) hubbub->funcs->program_compbuf_size(hubbub, context->bw_ctx.bw.dcn.compbuf_size_kb, true); - if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching) { - dc_dmub_srv_p_state_delegate(dc, - true, context); - context->bw_ctx.bw.dcn.clk.p_state_change_support = true; - dc->clk_mgr->clks.fw_based_mclk_switching = true; - } else { - dc->clk_mgr->clks.fw_based_mclk_switching = false; - } - dc->clk_mgr->funcs->update_clocks( dc->clk_mgr, context, diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c index 8263a07f265f..32121db2851e 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c @@ -983,36 +983,13 @@ void dcn30_set_disp_pattern_generator(const struct dc *dc, } void dcn30_prepare_bandwidth(struct dc *dc, - struct dc_state *context) + struct dc_state *context) { - bool p_state_change_support = context->bw_ctx.bw.dcn.clk.p_state_change_support; - /* Any transition into an FPO config should disable MCLK switching first to avoid - * driver and FW P-State synchronization issues. - */ - if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching || dc->clk_mgr->clks.fw_based_mclk_switching) { - dc->optimized_required = true; - context->bw_ctx.bw.dcn.clk.p_state_change_support = false; - } - if (dc->clk_mgr->dc_mode_softmax_enabled) if (dc->clk_mgr->clks.dramclk_khz <= dc->clk_mgr->bw_params->dc_mode_softmax_memclk * 1000 && context->bw_ctx.bw.dcn.clk.dramclk_khz > dc->clk_mgr->bw_params->dc_mode_softmax_memclk * 1000) dc->clk_mgr->funcs->set_max_memclk(dc->clk_mgr, dc->clk_mgr->bw_params->clk_table.entries[dc->clk_mgr->bw_params->clk_table.num_entries - 1].memclk_mhz); dcn20_prepare_bandwidth(dc, context); - /* - * enabled -> enabled: do not disable - * enabled -> disabled: disable - * disabled -> enabled: don't care - * disabled -> disabled: don't care - */ - if (!context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching) - dc_dmub_srv_p_state_delegate(dc, false, context); - - if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching || dc->clk_mgr->clks.fw_based_mclk_switching) { - /* After disabling P-State, restore the original value to ensure we get the correct P-State - * on the next optimize. */ - context->bw_ctx.bw.dcn.clk.p_state_change_support = p_state_change_support; - } } diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c index 40c488b26901..cc3fe9cac5b5 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c @@ -423,3 +423,68 @@ void dcn314_hubp_pg_control(struct dce_hwseq *hws, unsigned int hubp_inst, bool PERF_TRACE(); } +static void apply_symclk_on_tx_off_wa(struct dc_link *link) +{ + /* There are use cases where SYMCLK is referenced by OTG. For instance + * for TMDS signal, OTG relies SYMCLK even if TX video output is off. + * However current link interface will power off PHY when disabling link + * output. This will turn off SYMCLK generated by PHY. The workaround is + * to identify such case where SYMCLK is still in use by OTG when we + * power off PHY. When this is detected, we will temporarily power PHY + * back on and move PHY's SYMCLK state to SYMCLK_ON_TX_OFF by calling + * program_pix_clk interface. When OTG is disabled, we will then power + * off PHY by calling disable link output again. + * + * In future dcn generations, we plan to rework transmitter control + * interface so that we could have an option to set SYMCLK ON TX OFF + * state in one step without this workaround + */ + + struct dc *dc = link->ctx->dc; + struct pipe_ctx *pipe_ctx = NULL; + uint8_t i; + + if (link->phy_state.symclk_ref_cnts.otg > 0) { + for (i = 0; i < MAX_PIPES; i++) { + pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i]; + if (pipe_ctx->stream && pipe_ctx->stream->link == link && pipe_ctx->top_pipe == NULL) { + pipe_ctx->clock_source->funcs->program_pix_clk( + pipe_ctx->clock_source, + &pipe_ctx->stream_res.pix_clk_params, + dc->link_srv->dp_get_encoding_format( + &pipe_ctx->link_config.dp_link_settings), + &pipe_ctx->pll_settings); + link->phy_state.symclk_state = SYMCLK_ON_TX_OFF; + break; + } + } + } +} + +void dcn314_disable_link_output(struct dc_link *link, + const struct link_resource *link_res, + enum signal_type signal) +{ + struct dc *dc = link->ctx->dc; + const struct link_hwss *link_hwss = get_link_hwss(link, link_res); + struct dmcu *dmcu = dc->res_pool->dmcu; + + if (signal == SIGNAL_TYPE_EDP && + link->dc->hwss.edp_backlight_control) + link->dc->hwss.edp_backlight_control(link, false); + else if (dmcu != NULL && dmcu->funcs->lock_phy) + dmcu->funcs->lock_phy(dmcu); + + link_hwss->disable_link_output(link, link_res, signal); + link->phy_state.symclk_state = SYMCLK_OFF_TX_OFF; + /* + * Add the logic to extract BOTH power up and power down sequences + * from enable/disable link output and only call edp panel control + * in enable_link_dp and disable_link_dp once. + */ + if (dmcu != NULL && dmcu->funcs->lock_phy) + dmcu->funcs->unlock_phy(dmcu); + dc->link_srv->dp_trace_source_sequence(link, DPCD_SOURCE_SEQ_AFTER_DISABLE_LINK_PHY); + + apply_symclk_on_tx_off_wa(link); +} diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h index c786d5e6a428..6d0b62503caa 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h @@ -45,4 +45,6 @@ void dcn314_hubp_pg_control(struct dce_hwseq *hws, unsigned int hubp_inst, bool void dcn314_dpp_root_clock_control(struct dce_hwseq *hws, unsigned int dpp_inst, bool clock_on); +void dcn314_disable_link_output(struct dc_link *link, const struct link_resource *link_res, enum signal_type signal); + #endif /* __DC_HWSS_DCN314_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c index 5267e901a35c..a588f46b166f 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c @@ -105,7 +105,7 @@ static const struct hw_sequencer_funcs dcn314_funcs = { .enable_lvds_link_output = dce110_enable_lvds_link_output, .enable_tmds_link_output = dce110_enable_tmds_link_output, .enable_dp_link_output = dce110_enable_dp_link_output, - .disable_link_output = dce110_disable_link_output, + .disable_link_output = dcn314_disable_link_output, .z10_restore = dcn31_z10_restore, .z10_save_init = dcn31_z10_save_init, .set_disp_pattern_generator = dcn30_set_disp_pattern_generator, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c index 13c7e7394b1c..d75248b6cae9 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c @@ -810,7 +810,8 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->SwathHeightY[k], v->SwathHeightC[k], TWait, - v->DRAMSpeedPerState[mode_lib->vba.VoltageLevel] <= MEM_STROBE_FREQ_MHZ ? + (v->DRAMSpeedPerState[mode_lib->vba.VoltageLevel] <= MEM_STROBE_FREQ_MHZ || + v->DCFCLKPerState[mode_lib->vba.VoltageLevel] <= MIN_DCFCLK_FREQ_MHZ) ? mode_lib->vba.ip.min_prefetch_in_strobe_us : 0, /* Output */ &v->DSTXAfterScaler[k], @@ -3310,7 +3311,7 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->swath_width_chroma_ub_this_state[k], v->SwathHeightYThisState[k], v->SwathHeightCThisState[k], v->TWait, - v->DRAMSpeedPerState[i] <= MEM_STROBE_FREQ_MHZ ? + (v->DRAMSpeedPerState[i] <= MEM_STROBE_FREQ_MHZ || v->DCFCLKState[i][j] <= MIN_DCFCLK_FREQ_MHZ) ? mode_lib->vba.ip.min_prefetch_in_strobe_us : 0, /* Output */ diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h index 500b3dd6052d..d98e36a9a09c 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h @@ -53,6 +53,7 @@ #define BPP_BLENDED_PIPE 0xffffffff #define MEM_STROBE_FREQ_MHZ 1600 +#define MIN_DCFCLK_FREQ_MHZ 200 #define MEM_STROBE_MAX_DELIVERY_TIME_US 60.0 struct display_mode_lib; diff --git a/drivers/gpu/drm/amd/display/dc/link/link_validation.c b/drivers/gpu/drm/amd/display/dc/link/link_validation.c index d4b7da526f0a..e8b2fc4002a5 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_validation.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_validation.c @@ -359,5 +359,8 @@ bool link_validate_dpia_bandwidth(const struct dc_stream_state *stream, const un link[i] = stream[i].link; bw_needed[i] = dc_bandwidth_in_kbps_from_timing(&stream[i].timing); } + + ret = dpia_validate_usb4_bw(link, bw_needed, num_streams); + return ret; } diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c index 300e156b924f..078aaaa53162 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c @@ -36,6 +36,8 @@ #define amdgpu_dpm_enable_bapm(adev, e) \ ((adev)->powerplay.pp_funcs->enable_bapm((adev)->powerplay.pp_handle, (e))) +#define amdgpu_dpm_is_legacy_dpm(adev) ((adev)->powerplay.pp_handle == (adev)) + int amdgpu_dpm_get_sclk(struct amdgpu_device *adev, bool low) { const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; @@ -1460,15 +1462,24 @@ int amdgpu_dpm_get_smu_prv_buf_details(struct amdgpu_device *adev, int amdgpu_dpm_is_overdrive_supported(struct amdgpu_device *adev) { - struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle; - struct smu_context *smu = adev->powerplay.pp_handle; + if (is_support_sw_smu(adev)) { + struct smu_context *smu = adev->powerplay.pp_handle; - if ((is_support_sw_smu(adev) && smu->od_enabled) || - (is_support_sw_smu(adev) && smu->is_apu) || - (!is_support_sw_smu(adev) && hwmgr->od_enabled)) - return true; + return (smu->od_enabled || smu->is_apu); + } else { + struct pp_hwmgr *hwmgr; - return false; + /* + * dpm on some legacy asics don't carry od_enabled member + * as its pp_handle is casted directly from adev. + */ + if (amdgpu_dpm_is_legacy_dpm(adev)) + return false; + + hwmgr = (struct pp_hwmgr *)adev->powerplay.pp_handle; + + return hwmgr->od_enabled; + } } int amdgpu_dpm_set_pp_table(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index 58c2246918fd..f4f40459f22b 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -871,13 +871,11 @@ static ssize_t amdgpu_get_pp_od_clk_voltage(struct device *dev, } if (ret == -ENOENT) { size = amdgpu_dpm_print_clock_levels(adev, OD_SCLK, buf); - if (size > 0) { - size += amdgpu_dpm_print_clock_levels(adev, OD_MCLK, buf + size); - size += amdgpu_dpm_print_clock_levels(adev, OD_VDDC_CURVE, buf + size); - size += amdgpu_dpm_print_clock_levels(adev, OD_VDDGFX_OFFSET, buf + size); - size += amdgpu_dpm_print_clock_levels(adev, OD_RANGE, buf + size); - size += amdgpu_dpm_print_clock_levels(adev, OD_CCLK, buf + size); - } + size += amdgpu_dpm_print_clock_levels(adev, OD_MCLK, buf + size); + size += amdgpu_dpm_print_clock_levels(adev, OD_VDDC_CURVE, buf + size); + size += amdgpu_dpm_print_clock_levels(adev, OD_VDDGFX_OFFSET, buf + size); + size += amdgpu_dpm_print_clock_levels(adev, OD_RANGE, buf + size); + size += amdgpu_dpm_print_clock_levels(adev, OD_CCLK, buf + size); } if (size == 0) diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c index d6d9e3b1b2c0..02e69ccff3ba 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c @@ -6925,23 +6925,6 @@ static int si_dpm_enable(struct amdgpu_device *adev) return 0; } -static int si_set_temperature_range(struct amdgpu_device *adev) -{ - int ret; - - ret = si_thermal_enable_alert(adev, false); - if (ret) - return ret; - ret = si_thermal_set_temperature_range(adev, R600_TEMP_RANGE_MIN, R600_TEMP_RANGE_MAX); - if (ret) - return ret; - ret = si_thermal_enable_alert(adev, true); - if (ret) - return ret; - - return ret; -} - static void si_dpm_disable(struct amdgpu_device *adev) { struct rv7xx_power_info *pi = rv770_get_pi(adev); @@ -7626,18 +7609,6 @@ static int si_dpm_process_interrupt(struct amdgpu_device *adev, static int si_dpm_late_init(void *handle) { - int ret; - struct amdgpu_device *adev = (struct amdgpu_device *)handle; - - if (!adev->pm.dpm_enabled) - return 0; - - ret = si_set_temperature_range(adev); - if (ret) - return ret; -#if 0 //TODO ? - si_dpm_powergate_uvd(adev, true); -#endif return 0; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 5633c5797e85..2ddf5198e5c4 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -733,6 +733,24 @@ static int smu_late_init(void *handle) return ret; } + /* + * Explicitly notify PMFW the power mode the system in. Since + * the PMFW may boot the ASIC with a different mode. + * For those supporting ACDC switch via gpio, PMFW will + * handle the switch automatically. Driver involvement + * is unnecessary. + */ + if (!smu->dc_controlled_by_gpio) { + ret = smu_set_power_source(smu, + adev->pm.ac_power ? SMU_POWER_SOURCE_AC : + SMU_POWER_SOURCE_DC); + if (ret) { + dev_err(adev->dev, "Failed to switch to %s mode!\n", + adev->pm.ac_power ? "AC" : "DC"); + return ret; + } + } + if ((adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 1)) || (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 3))) return 0; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c index c4000518dc56..275f708db636 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c @@ -3413,26 +3413,8 @@ static int navi10_post_smu_init(struct smu_context *smu) return 0; ret = navi10_run_umc_cdr_workaround(smu); - if (ret) { + if (ret) dev_err(adev->dev, "Failed to apply umc cdr workaround!\n"); - return ret; - } - - if (!smu->dc_controlled_by_gpio) { - /* - * For Navi1X, manually switch it to AC mode as PMFW - * may boot it with DC mode. - */ - ret = smu_v11_0_set_power_source(smu, - adev->pm.ac_power ? - SMU_POWER_SOURCE_AC : - SMU_POWER_SOURCE_DC); - if (ret) { - dev_err(adev->dev, "Failed to switch to %s mode!\n", - adev->pm.ac_power ? "AC" : "DC"); - return ret; - } - } return ret; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c index 7433dcaa16e0..067b4e0b026c 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c @@ -582,7 +582,7 @@ static int vangogh_print_legacy_clk_levels(struct smu_context *smu, DpmClocks_t *clk_table = smu->smu_table.clocks_table; SmuMetrics_legacy_t metrics; struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm); - int i, size = 0, ret = 0; + int i, idx, size = 0, ret = 0; uint32_t cur_value = 0, value = 0, count = 0; bool cur_value_match_level = false; @@ -656,7 +656,8 @@ static int vangogh_print_legacy_clk_levels(struct smu_context *smu, case SMU_MCLK: case SMU_FCLK: for (i = 0; i < count; i++) { - ret = vangogh_get_dpm_clk_limited(smu, clk_type, i, &value); + idx = (clk_type == SMU_FCLK || clk_type == SMU_MCLK) ? (count - i - 1) : i; + ret = vangogh_get_dpm_clk_limited(smu, clk_type, idx, &value); if (ret) return ret; if (!value) @@ -683,7 +684,7 @@ static int vangogh_print_clk_levels(struct smu_context *smu, DpmClocks_t *clk_table = smu->smu_table.clocks_table; SmuMetrics_t metrics; struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm); - int i, size = 0, ret = 0; + int i, idx, size = 0, ret = 0; uint32_t cur_value = 0, value = 0, count = 0; bool cur_value_match_level = false; uint32_t min, max; @@ -765,7 +766,8 @@ static int vangogh_print_clk_levels(struct smu_context *smu, case SMU_MCLK: case SMU_FCLK: for (i = 0; i < count; i++) { - ret = vangogh_get_dpm_clk_limited(smu, clk_type, i, &value); + idx = (clk_type == SMU_FCLK || clk_type == SMU_MCLK) ? (count - i - 1) : i; + ret = vangogh_get_dpm_clk_limited(smu, clk_type, idx, &value); if (ret) return ret; if (!value) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c index 5cdc07165480..8a8ba25c9ad7 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c @@ -494,7 +494,7 @@ static int renoir_set_fine_grain_gfx_freq_parameters(struct smu_context *smu) static int renoir_print_clk_levels(struct smu_context *smu, enum smu_clk_type clk_type, char *buf) { - int i, size = 0, ret = 0; + int i, idx, size = 0, ret = 0; uint32_t cur_value = 0, value = 0, count = 0, min = 0, max = 0; SmuMetrics_t metrics; struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm); @@ -594,7 +594,8 @@ static int renoir_print_clk_levels(struct smu_context *smu, case SMU_VCLK: case SMU_DCLK: for (i = 0; i < count; i++) { - ret = renoir_get_dpm_clk_limited(smu, clk_type, i, &value); + idx = (clk_type == SMU_FCLK || clk_type == SMU_MCLK) ? (count - i - 1) : i; + ret = renoir_get_dpm_clk_limited(smu, clk_type, idx, &value); if (ret) return ret; if (!value) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c index 8fa9a36c38b6..6d9760eac16d 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c @@ -478,7 +478,7 @@ static int smu_v13_0_4_get_dpm_level_count(struct smu_context *smu, static int smu_v13_0_4_print_clk_levels(struct smu_context *smu, enum smu_clk_type clk_type, char *buf) { - int i, size = 0, ret = 0; + int i, idx, size = 0, ret = 0; uint32_t cur_value = 0, value = 0, count = 0; uint32_t min, max; @@ -512,7 +512,8 @@ static int smu_v13_0_4_print_clk_levels(struct smu_context *smu, break; for (i = 0; i < count; i++) { - ret = smu_v13_0_4_get_dpm_freq_by_index(smu, clk_type, i, &value); + idx = (clk_type == SMU_FCLK || clk_type == SMU_MCLK) ? (count - i - 1) : i; + ret = smu_v13_0_4_get_dpm_freq_by_index(smu, clk_type, idx, &value); if (ret) break; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c index 66445964efbd..0081fa607e02 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c @@ -866,7 +866,7 @@ out: static int smu_v13_0_5_print_clk_levels(struct smu_context *smu, enum smu_clk_type clk_type, char *buf) { - int i, size = 0, ret = 0; + int i, idx, size = 0, ret = 0; uint32_t cur_value = 0, value = 0, count = 0; uint32_t min = 0, max = 0; @@ -898,7 +898,8 @@ static int smu_v13_0_5_print_clk_levels(struct smu_context *smu, goto print_clk_out; for (i = 0; i < count; i++) { - ret = smu_v13_0_5_get_dpm_freq_by_index(smu, clk_type, i, &value); + idx = (clk_type == SMU_MCLK) ? (count - i - 1) : i; + ret = smu_v13_0_5_get_dpm_freq_by_index(smu, clk_type, idx, &value); if (ret) goto print_clk_out; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index 3d9ff46706fb..bba621615abf 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -125,6 +125,7 @@ static struct cmn2asic_msg_mapping smu_v13_0_7_message_map[SMU_MSG_MAX_COUNT] = MSG_MAP(ArmD3, PPSMC_MSG_ArmD3, 0), MSG_MAP(AllowGpo, PPSMC_MSG_SetGpoAllow, 0), MSG_MAP(GetPptLimit, PPSMC_MSG_GetPptLimit, 0), + MSG_MAP(NotifyPowerSource, PPSMC_MSG_NotifyPowerSource, 0), }; static struct cmn2asic_mapping smu_v13_0_7_clk_map[SMU_CLK_COUNT] = { @@ -1770,6 +1771,7 @@ static const struct pptable_funcs smu_v13_0_7_ppt_funcs = { .enable_mgpu_fan_boost = smu_v13_0_7_enable_mgpu_fan_boost, .get_power_limit = smu_v13_0_7_get_power_limit, .set_power_limit = smu_v13_0_set_power_limit, + .set_power_source = smu_v13_0_set_power_source, .get_power_profile_mode = smu_v13_0_7_get_power_profile_mode, .set_power_profile_mode = smu_v13_0_7_set_power_profile_mode, .set_tool_table_location = smu_v13_0_set_tool_table_location, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c index 04e56b0b3033..798f36cfcebd 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c @@ -1000,7 +1000,7 @@ out: static int yellow_carp_print_clk_levels(struct smu_context *smu, enum smu_clk_type clk_type, char *buf) { - int i, size = 0, ret = 0; + int i, idx, size = 0, ret = 0; uint32_t cur_value = 0, value = 0, count = 0; uint32_t min, max; @@ -1033,7 +1033,8 @@ static int yellow_carp_print_clk_levels(struct smu_context *smu, goto print_clk_out; for (i = 0; i < count; i++) { - ret = yellow_carp_get_dpm_freq_by_index(smu, clk_type, i, &value); + idx = (clk_type == SMU_FCLK || clk_type == SMU_MCLK) ? (count - i - 1) : i; + ret = yellow_carp_get_dpm_freq_by_index(smu, clk_type, idx, &value); if (ret) goto print_clk_out; diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c index 794ffd4a29c5..f32ce29edba7 100644 --- a/drivers/gpu/drm/ast/ast_main.c +++ b/drivers/gpu/drm/ast/ast_main.c @@ -425,11 +425,12 @@ struct ast_device *ast_device_create(const struct drm_driver *drv, return ERR_PTR(-EIO); /* - * If we don't have IO space at all, use MMIO now and - * assume the chip has MMIO enabled by default (rev 0x20 - * and higher). + * After AST2500, MMIO is enabled by default, and it should be adopted + * to be compatible with Arm. */ - if (!(pci_resource_flags(pdev, 2) & IORESOURCE_IO)) { + if (pdev->revision >= 0x40) { + ast->ioregs = ast->regs + AST_IO_MM_OFFSET; + } else if (!(pci_resource_flags(pdev, 2) & IORESOURCE_IO)) { drm_info(dev, "platform has no IO space, trying MMIO\n"); ast->ioregs = ast->regs + AST_IO_MM_OFFSET; } diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 64458982be40..6bb1b8b27d7a 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -641,19 +641,27 @@ static void drm_fb_helper_damage(struct drm_fb_helper *helper, u32 x, u32 y, static void drm_fb_helper_memory_range_to_clip(struct fb_info *info, off_t off, size_t len, struct drm_rect *clip) { + u32 line_length = info->fix.line_length; + u32 fb_height = info->var.yres; off_t end = off + len; u32 x1 = 0; - u32 y1 = off / info->fix.line_length; + u32 y1 = off / line_length; u32 x2 = info->var.xres; - u32 y2 = DIV_ROUND_UP(end, info->fix.line_length); + u32 y2 = DIV_ROUND_UP(end, line_length); + + /* Don't allow any of them beyond the bottom bound of display area */ + if (y1 > fb_height) + y1 = fb_height; + if (y2 > fb_height) + y2 = fb_height; if ((y2 - y1) == 1) { /* * We've only written to a single scanline. Try to reduce * the number of horizontal pixels that need an update. */ - off_t bit_off = (off % info->fix.line_length) * 8; - off_t bit_end = (end % info->fix.line_length) * 8; + off_t bit_off = (off % line_length) * 8; + off_t bit_end = (end % line_length) * 8; x1 = bit_off / info->var.bits_per_pixel; x2 = DIV_ROUND_UP(bit_end, info->var.bits_per_pixel); diff --git a/drivers/gpu/drm/drm_managed.c b/drivers/gpu/drm/drm_managed.c index 4cf214de50c4..c21c3f623033 100644 --- a/drivers/gpu/drm/drm_managed.c +++ b/drivers/gpu/drm/drm_managed.c @@ -264,28 +264,10 @@ void drmm_kfree(struct drm_device *dev, void *data) } EXPORT_SYMBOL(drmm_kfree); -static void drmm_mutex_release(struct drm_device *dev, void *res) +void __drmm_mutex_release(struct drm_device *dev, void *res) { struct mutex *lock = res; mutex_destroy(lock); } - -/** - * drmm_mutex_init - &drm_device-managed mutex_init() - * @dev: DRM device - * @lock: lock to be initialized - * - * Returns: - * 0 on success, or a negative errno code otherwise. - * - * This is a &drm_device-managed version of mutex_init(). The initialized - * lock is automatically destroyed on the final drm_dev_put(). - */ -int drmm_mutex_init(struct drm_device *dev, struct mutex *lock) -{ - mutex_init(lock); - - return drmm_add_action_or_reset(dev, drmm_mutex_release, lock); -} -EXPORT_SYMBOL(drmm_mutex_init); +EXPORT_SYMBOL(__drmm_mutex_release); diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c index 295382cd09b0..3fd6c733ff4e 100644 --- a/drivers/gpu/drm/drm_mipi_dsi.c +++ b/drivers/gpu/drm/drm_mipi_dsi.c @@ -221,7 +221,7 @@ mipi_dsi_device_register_full(struct mipi_dsi_host *host, return dsi; } - dsi->dev.of_node = info->node; + device_set_node(&dsi->dev, of_fwnode_handle(info->node)); dsi->channel = info->channel; strlcpy(dsi->name, info->type, sizeof(dsi->name)); diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index b1a38e6ce2f8..0cb646cb04ee 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -179,7 +179,7 @@ static const struct dmi_system_id orientation_data[] = { }, { /* AYA NEO AIR */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "AYANEO"), - DMI_MATCH(DMI_BOARD_NAME, "AIR"), + DMI_MATCH(DMI_PRODUCT_NAME, "AIR"), }, .driver_data = (void *)&lcd1080x1920_leftside_up, }, { /* AYA NEO NEXT */ diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.h b/drivers/gpu/drm/exynos/exynos_drm_g2d.h index 74ea3c26dead..1a5ae781b56c 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.h +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.h @@ -34,11 +34,11 @@ static inline int exynos_g2d_exec_ioctl(struct drm_device *dev, void *data, return -ENODEV; } -int g2d_open(struct drm_device *drm_dev, struct drm_file *file) +static inline int g2d_open(struct drm_device *drm_dev, struct drm_file *file) { return 0; } -void g2d_close(struct drm_device *drm_dev, struct drm_file *file) +static inline void g2d_close(struct drm_device *drm_dev, struct drm_file *file) { } #endif diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig index 06a0ca157e89..e4f4d2e3fdfe 100644 --- a/drivers/gpu/drm/i915/Kconfig +++ b/drivers/gpu/drm/i915/Kconfig @@ -62,10 +62,11 @@ config DRM_I915_FORCE_PROBE This is the default value for the i915.force_probe module parameter. Using the module parameter overrides this option. - Force probe the i915 for Intel graphics devices that are - recognized but not properly supported by this kernel version. It is - recommended to upgrade to a kernel version with proper support as soon - as it is available. + Force probe the i915 driver for Intel graphics devices that are + recognized but not properly supported by this kernel version. Force + probing an unsupported device taints the kernel. It is recommended to + upgrade to a kernel version with proper support as soon as it is + available. It can also be used to block the probe of recognized and fully supported devices. @@ -75,7 +76,8 @@ config DRM_I915_FORCE_PROBE Use "<pci-id>[,<pci-id>,...]" to force probe the i915 for listed devices. For example, "4500" or "4500,4571". - Use "*" to force probe the driver for all known devices. + Use "*" to force probe the driver for all known devices. Not + recommended. Use "!" right before the ID to block the probe of the device. For example, "4500,!4571" forces the probe of 4500 and blocks the probe of diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.c b/drivers/gpu/drm/i915/display/intel_atomic_plane.c index 40de9f0f171b..f33164b10292 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic_plane.c +++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.c @@ -1028,7 +1028,7 @@ intel_prepare_plane_fb(struct drm_plane *_plane, int ret; if (old_obj) { - const struct intel_crtc_state *crtc_state = + const struct intel_crtc_state *new_crtc_state = intel_atomic_get_new_crtc_state(state, to_intel_crtc(old_plane_state->hw.crtc)); @@ -1043,7 +1043,7 @@ intel_prepare_plane_fb(struct drm_plane *_plane, * This should only fail upon a hung GPU, in which case we * can safely continue. */ - if (intel_crtc_needs_modeset(crtc_state)) { + if (new_crtc_state && intel_crtc_needs_modeset(new_crtc_state)) { ret = i915_sw_fence_await_reservation(&state->commit_ready, old_obj->base.resv, false, 0, diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 3c29792137a5..0aae9a1eb3d5 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -1851,9 +1851,17 @@ static void hsw_crtc_disable(struct intel_atomic_state *state, intel_disable_shared_dpll(old_crtc_state); - intel_encoders_post_pll_disable(state, crtc); + if (!intel_crtc_is_bigjoiner_slave(old_crtc_state)) { + struct intel_crtc *slave_crtc; + + intel_encoders_post_pll_disable(state, crtc); - intel_dmc_disable_pipe(i915, crtc->pipe); + intel_dmc_disable_pipe(i915, crtc->pipe); + + for_each_intel_crtc_in_pipe_mask(&i915->drm, slave_crtc, + intel_crtc_bigjoiner_slave_pipes(old_crtc_state)) + intel_dmc_disable_pipe(i915, slave_crtc->pipe); + } } static void i9xx_pfit_enable(const struct intel_crtc_state *crtc_state) diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index f0bace9d98a1..529ee22be872 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -1601,6 +1601,11 @@ int intel_dp_dsc_compute_config(struct intel_dp *intel_dp, pipe_config->dsc.slice_count = drm_dp_dsc_sink_max_slice_count(intel_dp->dsc_dpcd, true); + if (!pipe_config->dsc.slice_count) { + drm_dbg_kms(&dev_priv->drm, "Unsupported Slice Count %d\n", + pipe_config->dsc.slice_count); + return -EINVAL; + } } else { u16 dsc_max_output_bpp = 0; u8 dsc_dp_slice_count; diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c index 650232c4892b..b183efab04a1 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_hdcp.c @@ -204,8 +204,6 @@ bool intel_hdcp2_capable(struct intel_connector *connector) struct intel_digital_port *dig_port = intel_attached_dig_port(connector); struct drm_i915_private *dev_priv = to_i915(connector->base.dev); struct intel_hdcp *hdcp = &connector->hdcp; - struct intel_gt *gt = dev_priv->media_gt; - struct intel_gsc_uc *gsc = >->uc.gsc; bool capable = false; /* I915 support for HDCP2.2 */ @@ -213,9 +211,13 @@ bool intel_hdcp2_capable(struct intel_connector *connector) return false; /* If MTL+ make sure gsc is loaded and proxy is setup */ - if (intel_hdcp_gsc_cs_required(dev_priv)) - if (!intel_uc_fw_is_running(&gsc->fw)) + if (intel_hdcp_gsc_cs_required(dev_priv)) { + struct intel_gt *gt = dev_priv->media_gt; + struct intel_gsc_uc *gsc = gt ? >->uc.gsc : NULL; + + if (!gsc || !intel_uc_fw_is_running(&gsc->fw)) return false; + } /* MEI/GSC interface is solid depending on which is used */ mutex_lock(&dev_priv->display.hdcp.comp_mutex); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c index cf49188db6a6..e0e793167d61 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c @@ -31,12 +31,14 @@ { FORCEWAKE_MT, 0, 0, "FORCEWAKE" } #define COMMON_GEN9BASE_GLOBAL \ - { GEN8_FAULT_TLB_DATA0, 0, 0, "GEN8_FAULT_TLB_DATA0" }, \ - { GEN8_FAULT_TLB_DATA1, 0, 0, "GEN8_FAULT_TLB_DATA1" }, \ { ERROR_GEN6, 0, 0, "ERROR_GEN6" }, \ { DONE_REG, 0, 0, "DONE_REG" }, \ { HSW_GTT_CACHE_EN, 0, 0, "HSW_GTT_CACHE_EN" } +#define GEN9_GLOBAL \ + { GEN8_FAULT_TLB_DATA0, 0, 0, "GEN8_FAULT_TLB_DATA0" }, \ + { GEN8_FAULT_TLB_DATA1, 0, 0, "GEN8_FAULT_TLB_DATA1" } + #define COMMON_GEN12BASE_GLOBAL \ { GEN12_FAULT_TLB_DATA0, 0, 0, "GEN12_FAULT_TLB_DATA0" }, \ { GEN12_FAULT_TLB_DATA1, 0, 0, "GEN12_FAULT_TLB_DATA1" }, \ @@ -142,6 +144,7 @@ static const struct __guc_mmio_reg_descr xe_lpd_gsc_inst_regs[] = { static const struct __guc_mmio_reg_descr default_global_regs[] = { COMMON_BASE_GLOBAL, COMMON_GEN9BASE_GLOBAL, + GEN9_GLOBAL, }; static const struct __guc_mmio_reg_descr default_rc_class_regs[] = { diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index 2a012da8ccfa..edcfb5fe20b2 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -1344,6 +1344,12 @@ static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return -ENODEV; } + if (intel_info->require_force_probe) { + dev_info(&pdev->dev, "Force probing unsupported Device ID %04x, tainting kernel\n", + pdev->device); + add_taint(TAINT_USER, LOCKDEP_STILL_OK); + } + /* Only bind to function 0 of the device. Early generations * used function 1 as a placeholder for multi-head. This causes * us confusion instead, especially on the systems where both diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 050b8ae7b8e7..3035cba2c6a2 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -877,12 +877,17 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, stream->oa_buffer.last_ctx_id = ctx_id; } - /* - * Clear out the report id and timestamp as a means to detect unlanded - * reports. - */ - oa_report_id_clear(stream, report32); - oa_timestamp_clear(stream, report32); + if (is_power_of_2(report_size)) { + /* + * Clear out the report id and timestamp as a means + * to detect unlanded reports. + */ + oa_report_id_clear(stream, report32); + oa_timestamp_clear(stream, report32); + } else { + /* Zero out the entire report */ + memset(report32, 0, report_size); + } } if (start_offset != *offset) { diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c index 0f2dd26755df..af3ce5a6a636 100644 --- a/drivers/gpu/drm/mgag200/mgag200_mode.c +++ b/drivers/gpu/drm/mgag200/mgag200_mode.c @@ -642,6 +642,11 @@ void mgag200_crtc_helper_atomic_enable(struct drm_crtc *crtc, struct drm_atomic_ if (funcs->pixpllc_atomic_update) funcs->pixpllc_atomic_update(crtc, old_state); + if (crtc_state->gamma_lut) + mgag200_crtc_set_gamma(mdev, format, crtc_state->gamma_lut->data); + else + mgag200_crtc_set_gamma_linear(mdev, format); + mgag200_enable_display(mdev); if (funcs->enable_vidrst) diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h index 2b3ae84057df..bdcd554fc8a8 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h @@ -98,17 +98,17 @@ static const struct dpu_sspp_cfg msm8998_sspp[] = { static const struct dpu_lm_cfg msm8998_lm[] = { LM_BLK("lm_0", LM_0, 0x44000, MIXER_MSM8998_MASK, - &msm8998_lm_sblk, PINGPONG_0, LM_2, DSPP_0), + &msm8998_lm_sblk, PINGPONG_0, LM_1, DSPP_0), LM_BLK("lm_1", LM_1, 0x45000, MIXER_MSM8998_MASK, - &msm8998_lm_sblk, PINGPONG_1, LM_5, DSPP_1), + &msm8998_lm_sblk, PINGPONG_1, LM_0, DSPP_1), LM_BLK("lm_2", LM_2, 0x46000, MIXER_MSM8998_MASK, - &msm8998_lm_sblk, PINGPONG_2, LM_0, 0), + &msm8998_lm_sblk, PINGPONG_2, LM_5, 0), LM_BLK("lm_3", LM_3, 0x47000, MIXER_MSM8998_MASK, &msm8998_lm_sblk, PINGPONG_MAX, 0, 0), LM_BLK("lm_4", LM_4, 0x48000, MIXER_MSM8998_MASK, &msm8998_lm_sblk, PINGPONG_MAX, 0, 0), LM_BLK("lm_5", LM_5, 0x49000, MIXER_MSM8998_MASK, - &msm8998_lm_sblk, PINGPONG_3, LM_1, 0), + &msm8998_lm_sblk, PINGPONG_3, LM_2, 0), }; static const struct dpu_pingpong_cfg msm8998_pp[] = { @@ -134,10 +134,10 @@ static const struct dpu_dspp_cfg msm8998_dspp[] = { }; static const struct dpu_intf_cfg msm8998_intf[] = { - INTF_BLK("intf_0", INTF_0, 0x6a000, 0x280, INTF_DP, 0, 25, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 24, 25), - INTF_BLK("intf_1", INTF_1, 0x6a800, 0x280, INTF_DSI, 0, 25, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 26, 27), - INTF_BLK("intf_2", INTF_2, 0x6b000, 0x280, INTF_DSI, 1, 25, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 28, 29), - INTF_BLK("intf_3", INTF_3, 0x6b800, 0x280, INTF_HDMI, 0, 25, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 30, 31), + INTF_BLK("intf_0", INTF_0, 0x6a000, 0x280, INTF_DP, 0, 21, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 24, 25), + INTF_BLK("intf_1", INTF_1, 0x6a800, 0x280, INTF_DSI, 0, 21, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 26, 27), + INTF_BLK("intf_2", INTF_2, 0x6b000, 0x280, INTF_DSI, 1, 21, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 28, 29), + INTF_BLK("intf_3", INTF_3, 0x6b800, 0x280, INTF_HDMI, 0, 21, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 30, 31), }; static const struct dpu_perf_cfg msm8998_perf_data = { diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h index 282d410269ff..42b0e58624d0 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h @@ -128,10 +128,10 @@ static const struct dpu_dspp_cfg sm8150_dspp[] = { }; static const struct dpu_pingpong_cfg sm8150_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_0", PINGPONG_0, 0x70000, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_1", PINGPONG_1, 0x70800, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), PP_BLK("pingpong_2", PINGPONG_2, 0x71000, MERGE_3D_1, sdm845_pp_sblk, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h index c57400265f28..e3bdfe7b30f1 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h @@ -116,10 +116,10 @@ static const struct dpu_lm_cfg sc8180x_lm[] = { }; static const struct dpu_pingpong_cfg sc8180x_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_0", PINGPONG_0, 0x70000, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_1", PINGPONG_1, 0x70800, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), PP_BLK("pingpong_2", PINGPONG_2, 0x71000, MERGE_3D_1, sdm845_pp_sblk, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h index 2c40229ea515..ed130582873c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h @@ -129,10 +129,10 @@ static const struct dpu_dspp_cfg sm8250_dspp[] = { }; static const struct dpu_pingpong_cfg sm8250_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_0", PINGPONG_0, 0x70000, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_1", PINGPONG_1, 0x70800, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), PP_BLK("pingpong_2", PINGPONG_2, 0x71000, MERGE_3D_1, sdm845_pp_sblk, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h index 8799ed757119..a46b11730a4d 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h @@ -80,8 +80,8 @@ static const struct dpu_dspp_cfg sc7180_dspp[] = { }; static const struct dpu_pingpong_cfg sc7180_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000, 0, sdm845_pp_sblk_te, -1, -1), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800, 0, sdm845_pp_sblk_te, -1, -1), + PP_BLK("pingpong_0", PINGPONG_0, 0x70000, 0, sdm845_pp_sblk, -1, -1), + PP_BLK("pingpong_1", PINGPONG_1, 0x70800, 0, sdm845_pp_sblk, -1, -1), }; static const struct dpu_intf_cfg sc7180_intf[] = { diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_3_sm6115.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_3_sm6115.h index 6f04d8f85c92..988d820f7ef2 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_3_sm6115.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_3_sm6115.h @@ -122,7 +122,6 @@ const struct dpu_mdss_cfg dpu_sm6115_cfg = { .mdss_irqs = BIT(MDP_SSPP_TOP0_INTR) | \ BIT(MDP_SSPP_TOP0_INTR2) | \ BIT(MDP_SSPP_TOP0_HIST_INTR) | \ - BIT(MDP_INTF0_INTR) | \ BIT(MDP_INTF1_INTR), }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_5_qcm2290.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_5_qcm2290.h index 303492d62a5c..c9003dcc1a59 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_5_qcm2290.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_5_qcm2290.h @@ -112,7 +112,6 @@ const struct dpu_mdss_cfg dpu_qcm2290_cfg = { .mdss_irqs = BIT(MDP_SSPP_TOP0_INTR) | \ BIT(MDP_SSPP_TOP0_INTR2) | \ BIT(MDP_SSPP_TOP0_HIST_INTR) | \ - BIT(MDP_INTF0_INTR) | \ BIT(MDP_INTF1_INTR), }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h index ca107ca8de46..4f6a965bcd90 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h @@ -127,22 +127,22 @@ static const struct dpu_dspp_cfg sm8350_dspp[] = { }; static const struct dpu_pingpong_cfg sm8350_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK_DITHER("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK_DITHER("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), - PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sdm845_pp_sblk, + PP_BLK_DITHER("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 14)), - PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sdm845_pp_sblk, + PP_BLK_DITHER("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 15)), - PP_BLK("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sdm845_pp_sblk, + PP_BLK_DITHER("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), - PP_BLK("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sdm845_pp_sblk, + PP_BLK_DITHER("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h index 5957de185984..6b2c7eae71d9 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h @@ -87,10 +87,10 @@ static const struct dpu_dspp_cfg sc7280_dspp[] = { }; static const struct dpu_pingpong_cfg sc7280_pp[] = { - PP_BLK("pingpong_0", PINGPONG_0, 0x69000, 0, sc7280_pp_sblk, -1, -1), - PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, 0, sc7280_pp_sblk, -1, -1), - PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, 0, sc7280_pp_sblk, -1, -1), - PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, 0, sc7280_pp_sblk, -1, -1), + PP_BLK_DITHER("pingpong_0", PINGPONG_0, 0x69000, 0, sc7280_pp_sblk, -1, -1), + PP_BLK_DITHER("pingpong_1", PINGPONG_1, 0x6a000, 0, sc7280_pp_sblk, -1, -1), + PP_BLK_DITHER("pingpong_2", PINGPONG_2, 0x6b000, 0, sc7280_pp_sblk, -1, -1), + PP_BLK_DITHER("pingpong_3", PINGPONG_3, 0x6c000, 0, sc7280_pp_sblk, -1, -1), }; static const struct dpu_intf_cfg sc7280_intf[] = { diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h index 9aab110b8c44..706d0f13b598 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h @@ -121,18 +121,18 @@ static const struct dpu_dspp_cfg sc8280xp_dspp[] = { }; static const struct dpu_pingpong_cfg sc8280xp_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sdm845_pp_sblk_te, - DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), -1), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sdm845_pp_sblk_te, - DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), -1), - PP_BLK_TE("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sdm845_pp_sblk_te, - DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), -1), - PP_BLK_TE("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sdm845_pp_sblk_te, - DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), -1), - PP_BLK_TE("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sdm845_pp_sblk_te, - DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), - PP_BLK_TE("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sdm845_pp_sblk_te, - DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), + PP_BLK_DITHER("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, + DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), -1), + PP_BLK_DITHER("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, + DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), -1), + PP_BLK_DITHER("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, + DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), -1), + PP_BLK_DITHER("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, + DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), -1), + PP_BLK_DITHER("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, + DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), + PP_BLK_DITHER("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, + DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), }; static const struct dpu_merge_3d_cfg sc8280xp_merge_3d[] = { diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h index 02a259b6b426..4ecb3df5cbc0 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h @@ -128,28 +128,28 @@ static const struct dpu_dspp_cfg sm8450_dspp[] = { }; /* FIXME: interrupts */ static const struct dpu_pingpong_cfg sm8450_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK_DITHER("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK_DITHER("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), - PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sdm845_pp_sblk, + PP_BLK_DITHER("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 14)), - PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sdm845_pp_sblk, + PP_BLK_DITHER("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 15)), - PP_BLK("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sdm845_pp_sblk, + PP_BLK_DITHER("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), - PP_BLK("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sdm845_pp_sblk, + PP_BLK_DITHER("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), - PP_BLK("pingpong_6", PINGPONG_6, 0x65800, MERGE_3D_3, sdm845_pp_sblk, + PP_BLK_DITHER("pingpong_6", PINGPONG_6, 0x65800, MERGE_3D_3, sc7280_pp_sblk, -1, -1), - PP_BLK("pingpong_7", PINGPONG_7, 0x65c00, MERGE_3D_3, sdm845_pp_sblk, + PP_BLK_DITHER("pingpong_7", PINGPONG_7, 0x65c00, MERGE_3D_3, sc7280_pp_sblk, -1, -1), }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h index 9e403034093f..d0ab351b6a8b 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h @@ -132,28 +132,28 @@ static const struct dpu_dspp_cfg sm8550_dspp[] = { &sm8150_dspp_sblk), }; static const struct dpu_pingpong_cfg sm8550_pp[] = { - PP_BLK_DIPHER("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), -1), - PP_BLK_DIPHER("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), -1), - PP_BLK_DIPHER("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), -1), - PP_BLK_DIPHER("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), -1), - PP_BLK_DIPHER("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), - PP_BLK_DIPHER("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), - PP_BLK_DIPHER("pingpong_6", PINGPONG_6, 0x66000, MERGE_3D_3, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_6", PINGPONG_6, 0x66000, MERGE_3D_3, sc7280_pp_sblk, -1, -1), - PP_BLK_DIPHER("pingpong_7", PINGPONG_7, 0x66400, MERGE_3D_3, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_7", PINGPONG_7, 0x66400, MERGE_3D_3, sc7280_pp_sblk, -1, -1), }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c index 03f162af1a50..5d994bce696f 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -491,7 +491,7 @@ static const struct dpu_pingpong_sub_blks sc7280_pp_sblk = { .len = 0x20, .version = 0x20000}, }; -#define PP_BLK_DIPHER(_name, _id, _base, _merge_3d, _sblk, _done, _rdptr) \ +#define PP_BLK_DITHER(_name, _id, _base, _merge_3d, _sblk, _done, _rdptr) \ {\ .name = _name, .id = _id, \ .base = _base, .len = 0, \ @@ -587,12 +587,12 @@ static const u32 sdm845_nrt_pri_lvl[] = {3, 3, 3, 3, 3, 3, 3, 3}; static const struct dpu_vbif_dynamic_ot_cfg msm8998_ot_rdwr_cfg[] = { { - .pps = 1088 * 1920 * 30, + .pps = 1920 * 1080 * 30, .ot_limit = 2, }, { - .pps = 1088 * 1920 * 60, - .ot_limit = 6, + .pps = 1920 * 1080 * 60, + .ot_limit = 4, }, { .pps = 3840 * 2160 * 30, @@ -705,10 +705,7 @@ static const struct dpu_qos_lut_entry msm8998_qos_linear[] = { {.fl = 10, .lut = 0x1555b}, {.fl = 11, .lut = 0x5555b}, {.fl = 12, .lut = 0x15555b}, - {.fl = 13, .lut = 0x55555b}, - {.fl = 14, .lut = 0}, - {.fl = 1, .lut = 0x1b}, - {.fl = 0, .lut = 0} + {.fl = 0, .lut = 0x55555b} }; static const struct dpu_qos_lut_entry sdm845_qos_linear[] = { @@ -730,9 +727,7 @@ static const struct dpu_qos_lut_entry msm8998_qos_macrotile[] = { {.fl = 10, .lut = 0x1aaff}, {.fl = 11, .lut = 0x5aaff}, {.fl = 12, .lut = 0x15aaff}, - {.fl = 13, .lut = 0x55aaff}, - {.fl = 1, .lut = 0x1aaff}, - {.fl = 0, .lut = 0}, + {.fl = 0, .lut = 0x55aaff}, }; static const struct dpu_qos_lut_entry sc7180_qos_linear[] = { diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c index 53326f25e40e..17f3e7e4f194 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c @@ -15,7 +15,7 @@ /* * Register offsets in MDSS register file for the interrupt registers - * w.r.t. to the MDP base + * w.r.t. the MDP base */ #define MDP_SSPP_TOP0_OFF 0x0 #define MDP_INTF_0_OFF 0x6A000 @@ -24,20 +24,23 @@ #define MDP_INTF_3_OFF 0x6B800 #define MDP_INTF_4_OFF 0x6C000 #define MDP_INTF_5_OFF 0x6C800 +#define INTF_INTR_EN 0x1c0 +#define INTF_INTR_STATUS 0x1c4 +#define INTF_INTR_CLEAR 0x1c8 #define MDP_AD4_0_OFF 0x7C000 #define MDP_AD4_1_OFF 0x7D000 #define MDP_AD4_INTR_EN_OFF 0x41c #define MDP_AD4_INTR_CLEAR_OFF 0x424 #define MDP_AD4_INTR_STATUS_OFF 0x420 -#define MDP_INTF_0_OFF_REV_7xxx 0x34000 -#define MDP_INTF_1_OFF_REV_7xxx 0x35000 -#define MDP_INTF_2_OFF_REV_7xxx 0x36000 -#define MDP_INTF_3_OFF_REV_7xxx 0x37000 -#define MDP_INTF_4_OFF_REV_7xxx 0x38000 -#define MDP_INTF_5_OFF_REV_7xxx 0x39000 -#define MDP_INTF_6_OFF_REV_7xxx 0x3a000 -#define MDP_INTF_7_OFF_REV_7xxx 0x3b000 -#define MDP_INTF_8_OFF_REV_7xxx 0x3c000 +#define MDP_INTF_0_OFF_REV_7xxx 0x34000 +#define MDP_INTF_1_OFF_REV_7xxx 0x35000 +#define MDP_INTF_2_OFF_REV_7xxx 0x36000 +#define MDP_INTF_3_OFF_REV_7xxx 0x37000 +#define MDP_INTF_4_OFF_REV_7xxx 0x38000 +#define MDP_INTF_5_OFF_REV_7xxx 0x39000 +#define MDP_INTF_6_OFF_REV_7xxx 0x3a000 +#define MDP_INTF_7_OFF_REV_7xxx 0x3b000 +#define MDP_INTF_8_OFF_REV_7xxx 0x3c000 /** * struct dpu_intr_reg - array of DPU register sets diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c index 84ee2efa9c66..b9dddf576c02 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c @@ -56,11 +56,6 @@ #define INTF_TPG_RGB_MAPPING 0x11C #define INTF_PROG_FETCH_START 0x170 #define INTF_PROG_ROT_START 0x174 - -#define INTF_FRAME_LINE_COUNT_EN 0x0A8 -#define INTF_FRAME_COUNT 0x0AC -#define INTF_LINE_COUNT 0x0B0 - #define INTF_MUX 0x25C #define INTF_STATUS 0x26C diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c index 2d28afdf860e..a3e413d27717 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c @@ -61,6 +61,7 @@ static const struct dpu_wb_cfg *_wb_offset(enum dpu_wb wb, for (i = 0; i < m->wb_count; i++) { if (wb == m->wb[i].id) { b->blk_addr = addr + m->wb[i].base; + b->log_mask = DPU_DBG_MASK_WB; return &m->wb[i]; } } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h index feb9a729844a..5acd5683d25a 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h @@ -21,9 +21,6 @@ #define HIST_INTR_EN 0x01c #define HIST_INTR_STATUS 0x020 #define HIST_INTR_CLEAR 0x024 -#define INTF_INTR_EN 0x1C0 -#define INTF_INTR_STATUS 0x1C4 -#define INTF_INTR_CLEAR 0x1C8 #define SPLIT_DISPLAY_EN 0x2F4 #define SPLIT_DISPLAY_UPPER_PIPE_CTRL 0x2F8 #define DSPP_IGC_COLOR0_RAM_LUTN 0x300 diff --git a/drivers/gpu/drm/msm/dp/dp_audio.c b/drivers/gpu/drm/msm/dp/dp_audio.c index 6666783e1468..1245c7aa49df 100644 --- a/drivers/gpu/drm/msm/dp/dp_audio.c +++ b/drivers/gpu/drm/msm/dp/dp_audio.c @@ -593,6 +593,18 @@ static struct hdmi_codec_pdata codec_data = { .i2s = 1, }; +void dp_unregister_audio_driver(struct device *dev, struct dp_audio *dp_audio) +{ + struct dp_audio_private *audio_priv; + + audio_priv = container_of(dp_audio, struct dp_audio_private, dp_audio); + + if (audio_priv->audio_pdev) { + platform_device_unregister(audio_priv->audio_pdev); + audio_priv->audio_pdev = NULL; + } +} + int dp_register_audio_driver(struct device *dev, struct dp_audio *dp_audio) { diff --git a/drivers/gpu/drm/msm/dp/dp_audio.h b/drivers/gpu/drm/msm/dp/dp_audio.h index 84e5f4a5d26b..4ab78880af82 100644 --- a/drivers/gpu/drm/msm/dp/dp_audio.h +++ b/drivers/gpu/drm/msm/dp/dp_audio.h @@ -53,6 +53,8 @@ struct dp_audio *dp_audio_get(struct platform_device *pdev, int dp_register_audio_driver(struct device *dev, struct dp_audio *dp_audio); +void dp_unregister_audio_driver(struct device *dev, struct dp_audio *dp_audio); + /** * dp_audio_put() * diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index 3e13acdfa7e5..99a38dbe51c0 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -326,6 +326,7 @@ static void dp_display_unbind(struct device *dev, struct device *master, kthread_stop(dp->ev_tsk); dp_power_client_deinit(dp->power); + dp_unregister_audio_driver(dev, dp->audio); dp_aux_unregister(dp->aux); dp->drm_dev = NULL; dp->aux->drm_dev = NULL; diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c index d77fa9793c54..9c45d641b521 100644 --- a/drivers/gpu/drm/msm/msm_atomic.c +++ b/drivers/gpu/drm/msm/msm_atomic.c @@ -155,6 +155,8 @@ static bool can_do_async(struct drm_atomic_state *state, for_each_new_crtc_in_state(state, crtc, crtc_state, i) { if (drm_atomic_crtc_needs_modeset(crtc_state)) return false; + if (!crtc_state->active) + return false; if (++num_crtcs > 1) return false; *async_crtc = crtc; diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index db6c4e281d75..cd39b9d8abdb 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -219,7 +219,8 @@ static void put_pages(struct drm_gem_object *obj) } } -static struct page **msm_gem_pin_pages_locked(struct drm_gem_object *obj) +static struct page **msm_gem_pin_pages_locked(struct drm_gem_object *obj, + unsigned madv) { struct msm_drm_private *priv = obj->dev->dev_private; struct msm_gem_object *msm_obj = to_msm_bo(obj); @@ -227,7 +228,9 @@ static struct page **msm_gem_pin_pages_locked(struct drm_gem_object *obj) msm_gem_assert_locked(obj); - if (GEM_WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED)) { + if (GEM_WARN_ON(msm_obj->madv > madv)) { + DRM_DEV_ERROR(obj->dev->dev, "Invalid madv state: %u vs %u\n", + msm_obj->madv, madv); return ERR_PTR(-EBUSY); } @@ -248,7 +251,7 @@ struct page **msm_gem_pin_pages(struct drm_gem_object *obj) struct page **p; msm_gem_lock(obj); - p = msm_gem_pin_pages_locked(obj); + p = msm_gem_pin_pages_locked(obj, MSM_MADV_WILLNEED); msm_gem_unlock(obj); return p; @@ -473,10 +476,7 @@ int msm_gem_pin_vma_locked(struct drm_gem_object *obj, struct msm_gem_vma *vma) msm_gem_assert_locked(obj); - if (GEM_WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED)) - return -EBUSY; - - pages = msm_gem_pin_pages_locked(obj); + pages = msm_gem_pin_pages_locked(obj, MSM_MADV_WILLNEED); if (IS_ERR(pages)) return PTR_ERR(pages); @@ -699,13 +699,7 @@ static void *get_vaddr(struct drm_gem_object *obj, unsigned madv) if (obj->import_attach) return ERR_PTR(-ENODEV); - if (GEM_WARN_ON(msm_obj->madv > madv)) { - DRM_DEV_ERROR(obj->dev->dev, "Invalid madv state: %u vs %u\n", - msm_obj->madv, madv); - return ERR_PTR(-EBUSY); - } - - pages = msm_gem_pin_pages_locked(obj); + pages = msm_gem_pin_pages_locked(obj, madv); if (IS_ERR(pages)) return ERR_CAST(pages); diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index aff18c2f600a..9f5933c75e3d 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -722,7 +722,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, struct msm_drm_private *priv = dev->dev_private; struct drm_msm_gem_submit *args = data; struct msm_file_private *ctx = file->driver_priv; - struct msm_gem_submit *submit; + struct msm_gem_submit *submit = NULL; struct msm_gpu *gpu = priv->gpu; struct msm_gpu_submitqueue *queue; struct msm_ringbuffer *ring; @@ -769,13 +769,15 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, out_fence_fd = get_unused_fd_flags(O_CLOEXEC); if (out_fence_fd < 0) { ret = out_fence_fd; - return ret; + goto out_post_unlock; } } submit = submit_create(dev, gpu, queue, args->nr_bos, args->nr_cmds); - if (IS_ERR(submit)) - return PTR_ERR(submit); + if (IS_ERR(submit)) { + ret = PTR_ERR(submit); + goto out_post_unlock; + } trace_msm_gpu_submit(pid_nr(submit->pid), ring->id, submit->ident, args->nr_bos, args->nr_cmds); @@ -962,11 +964,20 @@ out: if (has_ww_ticket) ww_acquire_fini(&submit->ticket); out_unlock: - if (ret && (out_fence_fd >= 0)) - put_unused_fd(out_fence_fd); mutex_unlock(&queue->lock); out_post_unlock: - msm_gem_submit_put(submit); + if (ret && (out_fence_fd >= 0)) + put_unused_fd(out_fence_fd); + + if (!IS_ERR_OR_NULL(submit)) { + msm_gem_submit_put(submit); + } else { + /* + * If the submit hasn't yet taken ownership of the queue + * then we need to drop the reference ourself: + */ + msm_submitqueue_put(queue); + } if (!IS_ERR_OR_NULL(post_deps)) { for (i = 0; i < args->nr_out_syncobjs; ++i) { kfree(post_deps[i].chain); diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index 418e1e06cdde..5cc8d358cc97 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -234,7 +234,12 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent) /* Get the pagetable configuration from the domain */ if (adreno_smmu->cookie) ttbr1_cfg = adreno_smmu->get_ttbr1_cfg(adreno_smmu->cookie); - if (!ttbr1_cfg) + + /* + * If you hit this WARN_ONCE() you are probably missing an entry in + * qcom_smmu_impl_of_match[] in arm-smmu-qcom.c + */ + if (WARN_ONCE(!ttbr1_cfg, "No per-process page tables")) return ERR_PTR(-ENODEV); pagetable = kzalloc(sizeof(*pagetable), GFP_KERNEL); @@ -410,7 +415,7 @@ struct msm_mmu *msm_iommu_gpu_new(struct device *dev, struct msm_gpu *gpu, unsig struct msm_mmu *mmu; mmu = msm_iommu_new(dev, quirks); - if (IS_ERR(mmu)) + if (IS_ERR_OR_NULL(mmu)) return mmu; iommu = to_msm_iommu(mmu); diff --git a/drivers/gpu/drm/nouveau/include/nvif/if0012.h b/drivers/gpu/drm/nouveau/include/nvif/if0012.h index eb99d84eb844..16d4ad5023a3 100644 --- a/drivers/gpu/drm/nouveau/include/nvif/if0012.h +++ b/drivers/gpu/drm/nouveau/include/nvif/if0012.h @@ -2,6 +2,8 @@ #ifndef __NVIF_IF0012_H__ #define __NVIF_IF0012_H__ +#include <drm/display/drm_dp.h> + union nvif_outp_args { struct nvif_outp_v0 { __u8 version; @@ -63,7 +65,7 @@ union nvif_outp_acquire_args { __u8 hda; __u8 mst; __u8 pad04[4]; - __u8 dpcd[16]; + __u8 dpcd[DP_RECEIVER_CAP_SIZE]; } dp; }; } v0; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.h index b7631c1ab242..4e7f873f66e2 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.h @@ -3,6 +3,7 @@ #define __NVKM_DISP_OUTP_H__ #include "priv.h" +#include <drm/display/drm_dp.h> #include <subdev/bios.h> #include <subdev/bios/dcb.h> #include <subdev/bios/dp.h> @@ -42,7 +43,7 @@ struct nvkm_outp { bool aux_pwr_pu; u8 lttpr[6]; u8 lttprs; - u8 dpcd[16]; + u8 dpcd[DP_RECEIVER_CAP_SIZE]; struct { int dpcd; /* -1, or index into SUPPORTED_LINK_RATES table */ diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/uoutp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/uoutp.c index 4f0ca709c85a..fc283a4a1522 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/uoutp.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/uoutp.c @@ -146,7 +146,7 @@ nvkm_uoutp_mthd_release(struct nvkm_outp *outp, void *argv, u32 argc) } static int -nvkm_uoutp_mthd_acquire_dp(struct nvkm_outp *outp, u8 dpcd[16], +nvkm_uoutp_mthd_acquire_dp(struct nvkm_outp *outp, u8 dpcd[DP_RECEIVER_CAP_SIZE], u8 link_nr, u8 link_bw, bool hda, bool mst) { int ret; diff --git a/drivers/gpu/drm/pl111/pl111_display.c b/drivers/gpu/drm/pl111/pl111_display.c index 6afdf260a4e2..b9fe926a49e8 100644 --- a/drivers/gpu/drm/pl111/pl111_display.c +++ b/drivers/gpu/drm/pl111/pl111_display.c @@ -53,7 +53,7 @@ pl111_mode_valid(struct drm_simple_display_pipe *pipe, { struct drm_device *drm = pipe->crtc.dev; struct pl111_drm_dev_private *priv = drm->dev_private; - u32 cpp = priv->variant->fb_bpp / 8; + u32 cpp = DIV_ROUND_UP(priv->variant->fb_depth, 8); u64 bw; /* diff --git a/drivers/gpu/drm/pl111/pl111_drm.h b/drivers/gpu/drm/pl111/pl111_drm.h index 2a46b5bd8576..d1fe756444ee 100644 --- a/drivers/gpu/drm/pl111/pl111_drm.h +++ b/drivers/gpu/drm/pl111/pl111_drm.h @@ -114,7 +114,7 @@ struct drm_minor; * extensions to the control register * @formats: array of supported pixel formats on this variant * @nformats: the length of the array of supported pixel formats - * @fb_bpp: desired bits per pixel on the default framebuffer + * @fb_depth: desired depth per pixel on the default framebuffer */ struct pl111_variant_data { const char *name; @@ -126,7 +126,7 @@ struct pl111_variant_data { bool st_bitmux_control; const u32 *formats; unsigned int nformats; - unsigned int fb_bpp; + unsigned int fb_depth; }; struct pl111_drm_dev_private { diff --git a/drivers/gpu/drm/pl111/pl111_drv.c b/drivers/gpu/drm/pl111/pl111_drv.c index 4b2a9e9753f6..43049c8028b2 100644 --- a/drivers/gpu/drm/pl111/pl111_drv.c +++ b/drivers/gpu/drm/pl111/pl111_drv.c @@ -308,7 +308,7 @@ static int pl111_amba_probe(struct amba_device *amba_dev, if (ret < 0) goto dev_put; - drm_fbdev_dma_setup(drm, priv->variant->fb_bpp); + drm_fbdev_dma_setup(drm, priv->variant->fb_depth); return 0; @@ -351,7 +351,7 @@ static const struct pl111_variant_data pl110_variant = { .is_pl110 = true, .formats = pl110_pixel_formats, .nformats = ARRAY_SIZE(pl110_pixel_formats), - .fb_bpp = 16, + .fb_depth = 16, }; /* RealView, Versatile Express etc use this modern variant */ @@ -376,7 +376,7 @@ static const struct pl111_variant_data pl111_variant = { .name = "PL111", .formats = pl111_pixel_formats, .nformats = ARRAY_SIZE(pl111_pixel_formats), - .fb_bpp = 32, + .fb_depth = 32, }; static const u32 pl110_nomadik_pixel_formats[] = { @@ -405,7 +405,7 @@ static const struct pl111_variant_data pl110_nomadik_variant = { .is_lcdc = true, .st_bitmux_control = true, .broken_vblank = true, - .fb_bpp = 16, + .fb_depth = 16, }; static const struct amba_id pl111_id_table[] = { diff --git a/drivers/gpu/drm/pl111/pl111_versatile.c b/drivers/gpu/drm/pl111/pl111_versatile.c index 1b436b75fd39..00c3ebd32359 100644 --- a/drivers/gpu/drm/pl111/pl111_versatile.c +++ b/drivers/gpu/drm/pl111/pl111_versatile.c @@ -316,7 +316,7 @@ static const struct pl111_variant_data pl110_integrator = { .broken_vblank = true, .formats = pl110_integrator_pixel_formats, .nformats = ARRAY_SIZE(pl110_integrator_pixel_formats), - .fb_bpp = 16, + .fb_depth = 16, }; /* @@ -330,7 +330,7 @@ static const struct pl111_variant_data pl110_impd1 = { .broken_vblank = true, .formats = pl110_integrator_pixel_formats, .nformats = ARRAY_SIZE(pl110_integrator_pixel_formats), - .fb_bpp = 16, + .fb_depth = 15, }; /* @@ -343,7 +343,7 @@ static const struct pl111_variant_data pl110_versatile = { .external_bgr = true, .formats = pl110_versatile_pixel_formats, .nformats = ARRAY_SIZE(pl110_versatile_pixel_formats), - .fb_bpp = 16, + .fb_depth = 16, }; /* @@ -355,7 +355,7 @@ static const struct pl111_variant_data pl111_realview = { .name = "PL111 RealView", .formats = pl111_realview_pixel_formats, .nformats = ARRAY_SIZE(pl111_realview_pixel_formats), - .fb_bpp = 16, + .fb_depth = 16, }; /* @@ -367,7 +367,7 @@ static const struct pl111_variant_data pl111_vexpress = { .name = "PL111 Versatile Express", .formats = pl111_realview_pixel_formats, .nformats = ARRAY_SIZE(pl111_realview_pixel_formats), - .fb_bpp = 16, + .fb_depth = 16, .broken_clockdivider = true, }; diff --git a/drivers/gpu/drm/radeon/radeon_irq_kms.c b/drivers/gpu/drm/radeon/radeon_irq_kms.c index 3377fbc71f65..c4dda908666c 100644 --- a/drivers/gpu/drm/radeon/radeon_irq_kms.c +++ b/drivers/gpu/drm/radeon/radeon_irq_kms.c @@ -99,6 +99,16 @@ static void radeon_hotplug_work_func(struct work_struct *work) static void radeon_dp_work_func(struct work_struct *work) { + struct radeon_device *rdev = container_of(work, struct radeon_device, + dp_work); + struct drm_device *dev = rdev->ddev; + struct drm_mode_config *mode_config = &dev->mode_config; + struct drm_connector *connector; + + mutex_lock(&mode_config->mutex); + list_for_each_entry(connector, &mode_config->connector_list, head) + radeon_connector_hotplug(connector); + mutex_unlock(&mode_config->mutex); } /** diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index fcd5bd7e5e8e..aea5a90ff98b 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -309,7 +309,7 @@ static void drm_sched_start_timeout(struct drm_gpu_scheduler *sched) */ void drm_sched_fault(struct drm_gpu_scheduler *sched) { - if (sched->ready) + if (sched->timeout_wq) mod_delayed_work(sched->timeout_wq, &sched->work_tdr, 0); } EXPORT_SYMBOL(drm_sched_fault); @@ -1141,9 +1141,6 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched) for (i = DRM_SCHED_PRIORITY_COUNT - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) { struct drm_sched_rq *rq = &sched->sched_rq[i]; - if (!rq) - continue; - spin_lock(&rq->lock); list_for_each_entry(s_entity, &rq->entities, list) /* diff --git a/drivers/hid/hid-google-hammer.c b/drivers/hid/hid-google-hammer.c index 7ae5f27df54d..c6bdb9c4ef3e 100644 --- a/drivers/hid/hid-google-hammer.c +++ b/drivers/hid/hid-google-hammer.c @@ -587,6 +587,8 @@ static const struct hid_device_id hammer_devices[] = { { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_HAMMER) }, { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, + USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_JEWEL) }, + { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_MAGNEMITE) }, { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_MASTERBALL) }, diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index d79e946acdcb..5d29abac2300 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -529,6 +529,7 @@ #define USB_DEVICE_ID_GOOGLE_MOONBALL 0x5044 #define USB_DEVICE_ID_GOOGLE_DON 0x5050 #define USB_DEVICE_ID_GOOGLE_EEL 0x5057 +#define USB_DEVICE_ID_GOOGLE_JEWEL 0x5061 #define USB_VENDOR_ID_GOTOP 0x08f2 #define USB_DEVICE_ID_SUPER_Q2 0x007f diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 0fcfd85fea0f..5e1a412fd28f 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -286,7 +286,7 @@ static int hidpp_send_message_sync(struct hidpp_device *hidpp, struct hidpp_report *message, struct hidpp_report *response) { - int ret; + int ret = -1; int max_retries = 3; mutex_lock(&hidpp->send_mutex); @@ -300,13 +300,13 @@ static int hidpp_send_message_sync(struct hidpp_device *hidpp, */ *response = *message; - for (; max_retries != 0; max_retries--) { + for (; max_retries != 0 && ret; max_retries--) { ret = __hidpp_send_report(hidpp->hid_dev, message); if (ret) { dbg_hid("__hidpp_send_report returned err: %d\n", ret); memset(response, 0, sizeof(struct hidpp_report)); - goto exit; + break; } if (!wait_event_timeout(hidpp->wait, hidpp->answer_available, @@ -314,13 +314,14 @@ static int hidpp_send_message_sync(struct hidpp_device *hidpp, dbg_hid("%s:timeout waiting for response\n", __func__); memset(response, 0, sizeof(struct hidpp_report)); ret = -ETIMEDOUT; + break; } if (response->report_id == REPORT_ID_HIDPP_SHORT && response->rap.sub_id == HIDPP_ERROR) { ret = response->rap.params[1]; dbg_hid("%s:got hidpp error %02X\n", __func__, ret); - goto exit; + break; } if ((response->report_id == REPORT_ID_HIDPP_LONG || @@ -329,13 +330,12 @@ static int hidpp_send_message_sync(struct hidpp_device *hidpp, ret = response->fap.params[1]; if (ret != HIDPP20_ERROR_BUSY) { dbg_hid("%s:got hidpp 2.0 error %02X\n", __func__, ret); - goto exit; + break; } dbg_hid("%s:got busy hidpp 2.0 error %02X, retrying\n", __func__, ret); } } -exit: mutex_unlock(&hidpp->send_mutex); return ret; diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index 8214896adada..76e5353aca0c 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -2224,7 +2224,9 @@ static void wacom_update_name(struct wacom *wacom, const char *suffix) } else if (strstr(product_name, "Wacom") || strstr(product_name, "wacom") || strstr(product_name, "WACOM")) { - strscpy(name, product_name, sizeof(name)); + if (strscpy(name, product_name, sizeof(name)) < 0) { + hid_warn(wacom->hdev, "String overflow while assembling device name"); + } } else { snprintf(name, sizeof(name), "Wacom %s", product_name); } @@ -2242,7 +2244,9 @@ static void wacom_update_name(struct wacom *wacom, const char *suffix) if (name[strlen(name)-1] == ' ') name[strlen(name)-1] = '\0'; } else { - strscpy(name, features->name, sizeof(name)); + if (strscpy(name, features->name, sizeof(name)) < 0) { + hid_warn(wacom->hdev, "String overflow while assembling device name"); + } } snprintf(wacom_wac->name, sizeof(wacom_wac->name), "%s%s", @@ -2410,8 +2414,13 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless) goto fail_quirks; } - if (features->device_type & WACOM_DEVICETYPE_WL_MONITOR) + if (features->device_type & WACOM_DEVICETYPE_WL_MONITOR) { error = hid_hw_open(hdev); + if (error) { + hid_err(hdev, "hw open failed\n"); + goto fail_quirks; + } + } wacom_set_shared_values(wacom_wac); devres_close_group(&hdev->dev, wacom); @@ -2500,8 +2509,10 @@ static void wacom_wireless_work(struct work_struct *work) goto fail; } - strscpy(wacom_wac->name, wacom_wac1->name, - sizeof(wacom_wac->name)); + if (strscpy(wacom_wac->name, wacom_wac1->name, + sizeof(wacom_wac->name)) < 0) { + hid_warn(wacom->hdev, "String overflow while assembling device name"); + } } return; diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index dc0f7d9a992c..2ccf83837134 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -831,7 +831,7 @@ static int wacom_intuos_inout(struct wacom_wac *wacom) /* Enter report */ if ((data[1] & 0xfc) == 0xc0) { /* serial number of the tool */ - wacom->serial[idx] = ((data[3] & 0x0f) << 28) + + wacom->serial[idx] = ((__u64)(data[3] & 0x0f) << 28) + (data[4] << 20) + (data[5] << 12) + (data[6] << 4) + (data[7] >> 4); diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c index ba2f6a4f8c16..7b177b9fbb09 100644 --- a/drivers/hwmon/k10temp.c +++ b/drivers/hwmon/k10temp.c @@ -507,6 +507,7 @@ static const struct pci_device_id k10temp_id_table[] = { { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_19H_M50H_DF_F3) }, { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_19H_M60H_DF_F3) }, { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_19H_M70H_DF_F3) }, + { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F3) }, { PCI_VDEVICE(HYGON, PCI_DEVICE_ID_AMD_17H_DF_F3) }, {} }; diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index 711f451b6946..89e8ed214ea4 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -402,6 +402,7 @@ static void *etm_setup_aux(struct perf_event *event, void **pages, trace_id = coresight_trace_id_get_cpu_id(cpu); if (!IS_VALID_CS_TRACE_ID(trace_id)) { cpumask_clear_cpu(cpu, mask); + coresight_release_path(path); continue; } diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index 918d461fcf4a..eaa296ced167 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -942,7 +942,7 @@ tmc_etr_buf_insert_barrier_packet(struct etr_buf *etr_buf, u64 offset) len = tmc_etr_buf_get_data(etr_buf, offset, CORESIGHT_BARRIER_PKT_SIZE, &bufp); - if (WARN_ON(len < CORESIGHT_BARRIER_PKT_SIZE)) + if (WARN_ON(len < 0 || len < CORESIGHT_BARRIER_PKT_SIZE)) return -EINVAL; coresight_insert_barrier_packet(bufp); return offset + CORESIGHT_BARRIER_PKT_SIZE; diff --git a/drivers/iio/accel/kionix-kx022a.c b/drivers/iio/accel/kionix-kx022a.c index f98393d74666..b8636fa8eaeb 100644 --- a/drivers/iio/accel/kionix-kx022a.c +++ b/drivers/iio/accel/kionix-kx022a.c @@ -1048,7 +1048,7 @@ int kx022a_probe_internal(struct device *dev) data->ien_reg = KX022A_REG_INC4; } else { irq = fwnode_irq_get_byname(fwnode, "INT2"); - if (irq <= 0) + if (irq < 0) return dev_err_probe(dev, irq, "No suitable IRQ\n"); data->inc_reg = KX022A_REG_INC5; diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c index 5f7d81b44b1d..282e539157f8 100644 --- a/drivers/iio/accel/st_accel_core.c +++ b/drivers/iio/accel/st_accel_core.c @@ -1291,12 +1291,12 @@ static int apply_acpi_orientation(struct iio_dev *indio_dev) adev = ACPI_COMPANION(indio_dev->dev.parent); if (!adev) - return 0; + return -ENXIO; /* Read _ONT data, which should be a package of 6 integers. */ status = acpi_evaluate_object(adev->handle, "_ONT", NULL, &buffer); if (status == AE_NOT_FOUND) { - return 0; + return -ENXIO; } else if (ACPI_FAILURE(status)) { dev_warn(&indio_dev->dev, "failed to execute _ONT: %d\n", status); diff --git a/drivers/iio/adc/ad4130.c b/drivers/iio/adc/ad4130.c index 38394341fd6e..5a5dd5e87ffc 100644 --- a/drivers/iio/adc/ad4130.c +++ b/drivers/iio/adc/ad4130.c @@ -1817,6 +1817,11 @@ static const struct clk_ops ad4130_int_clk_ops = { .unprepare = ad4130_int_clk_unprepare, }; +static void ad4130_clk_del_provider(void *of_node) +{ + of_clk_del_provider(of_node); +} + static int ad4130_setup_int_clk(struct ad4130_state *st) { struct device *dev = &st->spi->dev; @@ -1824,6 +1829,7 @@ static int ad4130_setup_int_clk(struct ad4130_state *st) struct clk_init_data init; const char *clk_name; struct clk *clk; + int ret; if (st->int_pin_sel == AD4130_INT_PIN_CLK || st->mclk_sel != AD4130_MCLK_76_8KHZ) @@ -1843,7 +1849,11 @@ static int ad4130_setup_int_clk(struct ad4130_state *st) if (IS_ERR(clk)) return PTR_ERR(clk); - return of_clk_add_provider(of_node, of_clk_src_simple_get, clk); + ret = of_clk_add_provider(of_node, of_clk_src_simple_get, clk); + if (ret) + return ret; + + return devm_add_action_or_reset(dev, ad4130_clk_del_provider, of_node); } static int ad4130_setup(struct iio_dev *indio_dev) diff --git a/drivers/iio/adc/ad7192.c b/drivers/iio/adc/ad7192.c index 55a6ab591016..99bb604b78c8 100644 --- a/drivers/iio/adc/ad7192.c +++ b/drivers/iio/adc/ad7192.c @@ -897,10 +897,6 @@ static const struct iio_info ad7195_info = { __AD719x_CHANNEL(_si, _channel1, -1, _address, NULL, IIO_VOLTAGE, \ BIT(IIO_CHAN_INFO_SCALE), ad7192_calibsys_ext_info) -#define AD719x_SHORTED_CHANNEL(_si, _channel1, _address) \ - __AD719x_CHANNEL(_si, _channel1, -1, _address, "shorted", IIO_VOLTAGE, \ - BIT(IIO_CHAN_INFO_SCALE), ad7192_calibsys_ext_info) - #define AD719x_TEMP_CHANNEL(_si, _address) \ __AD719x_CHANNEL(_si, 0, -1, _address, NULL, IIO_TEMP, 0, NULL) @@ -908,7 +904,7 @@ static const struct iio_chan_spec ad7192_channels[] = { AD719x_DIFF_CHANNEL(0, 1, 2, AD7192_CH_AIN1P_AIN2M), AD719x_DIFF_CHANNEL(1, 3, 4, AD7192_CH_AIN3P_AIN4M), AD719x_TEMP_CHANNEL(2, AD7192_CH_TEMP), - AD719x_SHORTED_CHANNEL(3, 2, AD7192_CH_AIN2P_AIN2M), + AD719x_DIFF_CHANNEL(3, 2, 2, AD7192_CH_AIN2P_AIN2M), AD719x_CHANNEL(4, 1, AD7192_CH_AIN1), AD719x_CHANNEL(5, 2, AD7192_CH_AIN2), AD719x_CHANNEL(6, 3, AD7192_CH_AIN3), @@ -922,7 +918,7 @@ static const struct iio_chan_spec ad7193_channels[] = { AD719x_DIFF_CHANNEL(2, 5, 6, AD7193_CH_AIN5P_AIN6M), AD719x_DIFF_CHANNEL(3, 7, 8, AD7193_CH_AIN7P_AIN8M), AD719x_TEMP_CHANNEL(4, AD7193_CH_TEMP), - AD719x_SHORTED_CHANNEL(5, 2, AD7193_CH_AIN2P_AIN2M), + AD719x_DIFF_CHANNEL(5, 2, 2, AD7193_CH_AIN2P_AIN2M), AD719x_CHANNEL(6, 1, AD7193_CH_AIN1), AD719x_CHANNEL(7, 2, AD7193_CH_AIN2), AD719x_CHANNEL(8, 3, AD7193_CH_AIN3), diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c index d8570f620785..7e2192870743 100644 --- a/drivers/iio/adc/ad_sigma_delta.c +++ b/drivers/iio/adc/ad_sigma_delta.c @@ -584,6 +584,10 @@ static int devm_ad_sd_probe_trigger(struct device *dev, struct iio_dev *indio_de init_completion(&sigma_delta->completion); sigma_delta->irq_dis = true; + + /* the IRQ core clears IRQ_DISABLE_UNLAZY flag when freeing an IRQ */ + irq_set_status_flags(sigma_delta->spi->irq, IRQ_DISABLE_UNLAZY); + ret = devm_request_irq(dev, sigma_delta->spi->irq, ad_sd_data_rdy_trig_poll, sigma_delta->info->irq_flags | IRQF_NO_AUTOEN, diff --git a/drivers/iio/adc/imx93_adc.c b/drivers/iio/adc/imx93_adc.c index a775d2e40567..dce9ec91e4a7 100644 --- a/drivers/iio/adc/imx93_adc.c +++ b/drivers/iio/adc/imx93_adc.c @@ -236,8 +236,7 @@ static int imx93_adc_read_raw(struct iio_dev *indio_dev, { struct imx93_adc *adc = iio_priv(indio_dev); struct device *dev = adc->dev; - long ret; - u32 vref_uv; + int ret; switch (mask) { case IIO_CHAN_INFO_RAW: @@ -253,10 +252,10 @@ static int imx93_adc_read_raw(struct iio_dev *indio_dev, return IIO_VAL_INT; case IIO_CHAN_INFO_SCALE: - ret = vref_uv = regulator_get_voltage(adc->vref); + ret = regulator_get_voltage(adc->vref); if (ret < 0) return ret; - *val = vref_uv / 1000; + *val = ret / 1000; *val2 = 12; return IIO_VAL_FRACTIONAL_LOG2; diff --git a/drivers/iio/adc/mt6370-adc.c b/drivers/iio/adc/mt6370-adc.c index bc62e5a9d50d..0bc112135bca 100644 --- a/drivers/iio/adc/mt6370-adc.c +++ b/drivers/iio/adc/mt6370-adc.c @@ -19,6 +19,7 @@ #include <dt-bindings/iio/adc/mediatek,mt6370_adc.h> +#define MT6370_REG_DEV_INFO 0x100 #define MT6370_REG_CHG_CTRL3 0x113 #define MT6370_REG_CHG_CTRL7 0x117 #define MT6370_REG_CHG_ADC 0x121 @@ -27,6 +28,7 @@ #define MT6370_ADC_START_MASK BIT(0) #define MT6370_ADC_IN_SEL_MASK GENMASK(7, 4) #define MT6370_AICR_ICHG_MASK GENMASK(7, 2) +#define MT6370_VENID_MASK GENMASK(7, 4) #define MT6370_AICR_100_mA 0x0 #define MT6370_AICR_150_mA 0x1 @@ -47,6 +49,10 @@ #define ADC_CONV_TIME_MS 35 #define ADC_CONV_POLLING_TIME_US 1000 +#define MT6370_VID_RT5081 0x8 +#define MT6370_VID_RT5081A 0xA +#define MT6370_VID_MT6370 0xE + struct mt6370_adc_data { struct device *dev; struct regmap *regmap; @@ -55,6 +61,7 @@ struct mt6370_adc_data { * from being read at the same time. */ struct mutex adc_lock; + unsigned int vid; }; static int mt6370_adc_read_channel(struct mt6370_adc_data *priv, int chan, @@ -98,6 +105,30 @@ adc_unlock: return ret; } +static int mt6370_adc_get_ibus_scale(struct mt6370_adc_data *priv) +{ + switch (priv->vid) { + case MT6370_VID_RT5081: + case MT6370_VID_RT5081A: + case MT6370_VID_MT6370: + return 3350; + default: + return 3875; + } +} + +static int mt6370_adc_get_ibat_scale(struct mt6370_adc_data *priv) +{ + switch (priv->vid) { + case MT6370_VID_RT5081: + case MT6370_VID_RT5081A: + case MT6370_VID_MT6370: + return 2680; + default: + return 3870; + } +} + static int mt6370_adc_read_scale(struct mt6370_adc_data *priv, int chan, int *val1, int *val2) { @@ -123,7 +154,7 @@ static int mt6370_adc_read_scale(struct mt6370_adc_data *priv, case MT6370_AICR_250_mA: case MT6370_AICR_300_mA: case MT6370_AICR_350_mA: - *val1 = 3350; + *val1 = mt6370_adc_get_ibus_scale(priv); break; default: *val1 = 5000; @@ -150,7 +181,7 @@ static int mt6370_adc_read_scale(struct mt6370_adc_data *priv, case MT6370_ICHG_600_mA: case MT6370_ICHG_700_mA: case MT6370_ICHG_800_mA: - *val1 = 2680; + *val1 = mt6370_adc_get_ibat_scale(priv); break; default: *val1 = 5000; @@ -251,6 +282,20 @@ static const struct iio_chan_spec mt6370_adc_channels[] = { MT6370_ADC_CHAN(TEMP_JC, IIO_TEMP, 12, BIT(IIO_CHAN_INFO_OFFSET)), }; +static int mt6370_get_vendor_info(struct mt6370_adc_data *priv) +{ + unsigned int dev_info; + int ret; + + ret = regmap_read(priv->regmap, MT6370_REG_DEV_INFO, &dev_info); + if (ret) + return ret; + + priv->vid = FIELD_GET(MT6370_VENID_MASK, dev_info); + + return 0; +} + static int mt6370_adc_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -272,6 +317,10 @@ static int mt6370_adc_probe(struct platform_device *pdev) priv->regmap = regmap; mutex_init(&priv->adc_lock); + ret = mt6370_get_vendor_info(priv); + if (ret) + return dev_err_probe(dev, ret, "Failed to get vid\n"); + ret = regmap_write(priv->regmap, MT6370_REG_CHG_ADC, 0); if (ret) return dev_err_probe(dev, ret, "Failed to reset ADC\n"); diff --git a/drivers/iio/adc/mxs-lradc-adc.c b/drivers/iio/adc/mxs-lradc-adc.c index bca79a93cbe4..a50f39143d3e 100644 --- a/drivers/iio/adc/mxs-lradc-adc.c +++ b/drivers/iio/adc/mxs-lradc-adc.c @@ -757,13 +757,13 @@ static int mxs_lradc_adc_probe(struct platform_device *pdev) ret = mxs_lradc_adc_trigger_init(iio); if (ret) - goto err_trig; + return ret; ret = iio_triggered_buffer_setup(iio, &iio_pollfunc_store_time, &mxs_lradc_adc_trigger_handler, &mxs_lradc_adc_buffer_ops); if (ret) - return ret; + goto err_trig; adc->vref_mv = mxs_lradc_adc_vref_mv[lradc->soc]; @@ -801,9 +801,9 @@ static int mxs_lradc_adc_probe(struct platform_device *pdev) err_dev: mxs_lradc_adc_hw_stop(adc); - mxs_lradc_adc_trigger_remove(iio); -err_trig: iio_triggered_buffer_cleanup(iio); +err_trig: + mxs_lradc_adc_trigger_remove(iio); return ret; } @@ -814,8 +814,8 @@ static int mxs_lradc_adc_remove(struct platform_device *pdev) iio_device_unregister(iio); mxs_lradc_adc_hw_stop(adc); - mxs_lradc_adc_trigger_remove(iio); iio_triggered_buffer_cleanup(iio); + mxs_lradc_adc_trigger_remove(iio); return 0; } diff --git a/drivers/iio/adc/palmas_gpadc.c b/drivers/iio/adc/palmas_gpadc.c index c1c439215aeb..7dfc9c927a23 100644 --- a/drivers/iio/adc/palmas_gpadc.c +++ b/drivers/iio/adc/palmas_gpadc.c @@ -547,7 +547,7 @@ static int palmas_gpadc_read_raw(struct iio_dev *indio_dev, int adc_chan = chan->channel; int ret = 0; - if (adc_chan > PALMAS_ADC_CH_MAX) + if (adc_chan >= PALMAS_ADC_CH_MAX) return -EINVAL; mutex_lock(&adc->lock); @@ -595,7 +595,7 @@ static int palmas_gpadc_read_event_config(struct iio_dev *indio_dev, int adc_chan = chan->channel; int ret = 0; - if (adc_chan > PALMAS_ADC_CH_MAX || type != IIO_EV_TYPE_THRESH) + if (adc_chan >= PALMAS_ADC_CH_MAX || type != IIO_EV_TYPE_THRESH) return -EINVAL; mutex_lock(&adc->lock); @@ -684,7 +684,7 @@ static int palmas_gpadc_write_event_config(struct iio_dev *indio_dev, int adc_chan = chan->channel; int ret; - if (adc_chan > PALMAS_ADC_CH_MAX || type != IIO_EV_TYPE_THRESH) + if (adc_chan >= PALMAS_ADC_CH_MAX || type != IIO_EV_TYPE_THRESH) return -EINVAL; mutex_lock(&adc->lock); @@ -710,7 +710,7 @@ static int palmas_gpadc_read_event_value(struct iio_dev *indio_dev, int adc_chan = chan->channel; int ret; - if (adc_chan > PALMAS_ADC_CH_MAX || type != IIO_EV_TYPE_THRESH) + if (adc_chan >= PALMAS_ADC_CH_MAX || type != IIO_EV_TYPE_THRESH) return -EINVAL; mutex_lock(&adc->lock); @@ -744,7 +744,7 @@ static int palmas_gpadc_write_event_value(struct iio_dev *indio_dev, int old; int ret; - if (adc_chan > PALMAS_ADC_CH_MAX || type != IIO_EV_TYPE_THRESH) + if (adc_chan >= PALMAS_ADC_CH_MAX || type != IIO_EV_TYPE_THRESH) return -EINVAL; mutex_lock(&adc->lock); diff --git a/drivers/iio/adc/stm32-adc.c b/drivers/iio/adc/stm32-adc.c index 1aadb2ad2cab..bd7e2408bf28 100644 --- a/drivers/iio/adc/stm32-adc.c +++ b/drivers/iio/adc/stm32-adc.c @@ -2006,16 +2006,15 @@ static int stm32_adc_get_legacy_chan_count(struct iio_dev *indio_dev, struct stm * to get the *real* number of channels. */ ret = device_property_count_u32(dev, "st,adc-diff-channels"); - if (ret < 0) - return ret; - - ret /= (int)(sizeof(struct stm32_adc_diff_channel) / sizeof(u32)); - if (ret > adc_info->max_channels) { - dev_err(&indio_dev->dev, "Bad st,adc-diff-channels?\n"); - return -EINVAL; - } else if (ret > 0) { - adc->num_diff = ret; - num_channels += ret; + if (ret > 0) { + ret /= (int)(sizeof(struct stm32_adc_diff_channel) / sizeof(u32)); + if (ret > adc_info->max_channels) { + dev_err(&indio_dev->dev, "Bad st,adc-diff-channels?\n"); + return -EINVAL; + } else if (ret > 0) { + adc->num_diff = ret; + num_channels += ret; + } } /* Optional sample time is provided either for each, or all channels */ @@ -2037,6 +2036,7 @@ static int stm32_adc_legacy_chan_init(struct iio_dev *indio_dev, struct stm32_adc_diff_channel diff[STM32_ADC_CH_MAX]; struct device *dev = &indio_dev->dev; u32 num_diff = adc->num_diff; + int num_se = nchans - num_diff; int size = num_diff * sizeof(*diff) / sizeof(u32); int scan_index = 0, ret, i, c; u32 smp = 0, smps[STM32_ADC_CH_MAX], chans[STM32_ADC_CH_MAX]; @@ -2063,29 +2063,32 @@ static int stm32_adc_legacy_chan_init(struct iio_dev *indio_dev, scan_index++; } } - - ret = device_property_read_u32_array(dev, "st,adc-channels", chans, - nchans); - if (ret) - return ret; - - for (c = 0; c < nchans; c++) { - if (chans[c] >= adc_info->max_channels) { - dev_err(&indio_dev->dev, "Invalid channel %d\n", - chans[c]); - return -EINVAL; + if (num_se > 0) { + ret = device_property_read_u32_array(dev, "st,adc-channels", chans, num_se); + if (ret) { + dev_err(&indio_dev->dev, "Failed to get st,adc-channels %d\n", ret); + return ret; } - /* Channel can't be configured both as single-ended & diff */ - for (i = 0; i < num_diff; i++) { - if (chans[c] == diff[i].vinp) { - dev_err(&indio_dev->dev, "channel %d misconfigured\n", chans[c]); + for (c = 0; c < num_se; c++) { + if (chans[c] >= adc_info->max_channels) { + dev_err(&indio_dev->dev, "Invalid channel %d\n", + chans[c]); return -EINVAL; } + + /* Channel can't be configured both as single-ended & diff */ + for (i = 0; i < num_diff; i++) { + if (chans[c] == diff[i].vinp) { + dev_err(&indio_dev->dev, "channel %d misconfigured\n", + chans[c]); + return -EINVAL; + } + } + stm32_adc_chan_init_one(indio_dev, &channels[scan_index], + chans[c], 0, scan_index, false); + scan_index++; } - stm32_adc_chan_init_one(indio_dev, &channels[scan_index], - chans[c], 0, scan_index, false); - scan_index++; } if (adc->nsmps > 0) { @@ -2306,7 +2309,7 @@ static int stm32_adc_chan_fw_init(struct iio_dev *indio_dev, bool timestamping) if (legacy) ret = stm32_adc_legacy_chan_init(indio_dev, adc, channels, - num_channels); + timestamping ? num_channels - 1 : num_channels); else ret = stm32_adc_generic_chan_init(indio_dev, adc, channels); if (ret < 0) diff --git a/drivers/iio/addac/ad74413r.c b/drivers/iio/addac/ad74413r.c index 07e9f6ae16a8..e3366cf5eb31 100644 --- a/drivers/iio/addac/ad74413r.c +++ b/drivers/iio/addac/ad74413r.c @@ -1007,7 +1007,7 @@ static int ad74413r_read_raw(struct iio_dev *indio_dev, ret = ad74413r_get_single_adc_result(indio_dev, chan->channel, val); - if (ret) + if (ret < 0) return ret; ad74413r_adc_to_resistance_result(*val, val); diff --git a/drivers/iio/dac/Makefile b/drivers/iio/dac/Makefile index 6c74fea21736..addd97a78838 100644 --- a/drivers/iio/dac/Makefile +++ b/drivers/iio/dac/Makefile @@ -17,7 +17,7 @@ obj-$(CONFIG_AD5592R_BASE) += ad5592r-base.o obj-$(CONFIG_AD5592R) += ad5592r.o obj-$(CONFIG_AD5593R) += ad5593r.o obj-$(CONFIG_AD5755) += ad5755.o -obj-$(CONFIG_AD5755) += ad5758.o +obj-$(CONFIG_AD5758) += ad5758.o obj-$(CONFIG_AD5761) += ad5761.o obj-$(CONFIG_AD5764) += ad5764.o obj-$(CONFIG_AD5766) += ad5766.o diff --git a/drivers/iio/dac/mcp4725.c b/drivers/iio/dac/mcp4725.c index 46bf758760f8..3f5661a3718f 100644 --- a/drivers/iio/dac/mcp4725.c +++ b/drivers/iio/dac/mcp4725.c @@ -47,12 +47,18 @@ static int mcp4725_suspend(struct device *dev) struct mcp4725_data *data = iio_priv(i2c_get_clientdata( to_i2c_client(dev))); u8 outbuf[2]; + int ret; outbuf[0] = (data->powerdown_mode + 1) << 4; outbuf[1] = 0; data->powerdown = true; - return i2c_master_send(data->client, outbuf, 2); + ret = i2c_master_send(data->client, outbuf, 2); + if (ret < 0) + return ret; + else if (ret != 2) + return -EIO; + return 0; } static int mcp4725_resume(struct device *dev) @@ -60,13 +66,19 @@ static int mcp4725_resume(struct device *dev) struct mcp4725_data *data = iio_priv(i2c_get_clientdata( to_i2c_client(dev))); u8 outbuf[2]; + int ret; /* restore previous DAC value */ outbuf[0] = (data->dac_value >> 8) & 0xf; outbuf[1] = data->dac_value & 0xff; data->powerdown = false; - return i2c_master_send(data->client, outbuf, 2); + ret = i2c_master_send(data->client, outbuf, 2); + if (ret < 0) + return ret; + else if (ret != 2) + return -EIO; + return 0; } static DEFINE_SIMPLE_DEV_PM_OPS(mcp4725_pm_ops, mcp4725_suspend, mcp4725_resume); diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c index 99576b2c171f..32d7f8364230 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c @@ -275,9 +275,14 @@ static int inv_icm42600_buffer_preenable(struct iio_dev *indio_dev) { struct inv_icm42600_state *st = iio_device_get_drvdata(indio_dev); struct device *dev = regmap_get_device(st->map); + struct inv_icm42600_timestamp *ts = iio_priv(indio_dev); pm_runtime_get_sync(dev); + mutex_lock(&st->lock); + inv_icm42600_timestamp_reset(ts); + mutex_unlock(&st->lock); + return 0; } @@ -375,7 +380,6 @@ static int inv_icm42600_buffer_postdisable(struct iio_dev *indio_dev) struct device *dev = regmap_get_device(st->map); unsigned int sensor; unsigned int *watermark; - struct inv_icm42600_timestamp *ts; struct inv_icm42600_sensor_conf conf = INV_ICM42600_SENSOR_CONF_INIT; unsigned int sleep_temp = 0; unsigned int sleep_sensor = 0; @@ -385,11 +389,9 @@ static int inv_icm42600_buffer_postdisable(struct iio_dev *indio_dev) if (indio_dev == st->indio_gyro) { sensor = INV_ICM42600_SENSOR_GYRO; watermark = &st->fifo.watermark.gyro; - ts = iio_priv(st->indio_gyro); } else if (indio_dev == st->indio_accel) { sensor = INV_ICM42600_SENSOR_ACCEL; watermark = &st->fifo.watermark.accel; - ts = iio_priv(st->indio_accel); } else { return -EINVAL; } @@ -417,8 +419,6 @@ static int inv_icm42600_buffer_postdisable(struct iio_dev *indio_dev) if (!st->fifo.on) ret = inv_icm42600_set_temp_conf(st, false, &sleep_temp); - inv_icm42600_timestamp_reset(ts); - out_unlock: mutex_unlock(&st->lock); diff --git a/drivers/iio/industrialio-gts-helper.c b/drivers/iio/industrialio-gts-helper.c index 8bb68975b259..7653261d2dc2 100644 --- a/drivers/iio/industrialio-gts-helper.c +++ b/drivers/iio/industrialio-gts-helper.c @@ -337,6 +337,17 @@ free_gains: return ret; } +static void iio_gts_us_to_int_micro(int *time_us, int *int_micro_times, + int num_times) +{ + int i; + + for (i = 0; i < num_times; i++) { + int_micro_times[i * 2] = time_us[i] / 1000000; + int_micro_times[i * 2 + 1] = time_us[i] % 1000000; + } +} + /** * iio_gts_build_avail_time_table - build table of available integration times * @gts: Gain time scale descriptor @@ -351,7 +362,7 @@ free_gains: */ static int iio_gts_build_avail_time_table(struct iio_gts *gts) { - int *times, i, j, idx = 0; + int *times, i, j, idx = 0, *int_micro_times; if (!gts->num_itime) return 0; @@ -378,13 +389,24 @@ static int iio_gts_build_avail_time_table(struct iio_gts *gts) } } } - gts->avail_time_tables = times; - /* - * This is just to survive a unlikely corner-case where times in the - * given time table were not unique. Else we could just trust the - * gts->num_itime. - */ - gts->num_avail_time_tables = idx; + + /* create a list of times formatted as list of IIO_VAL_INT_PLUS_MICRO */ + int_micro_times = kcalloc(idx, sizeof(int) * 2, GFP_KERNEL); + if (int_micro_times) { + /* + * This is just to survive a unlikely corner-case where times in + * the given time table were not unique. Else we could just + * trust the gts->num_itime. + */ + gts->num_avail_time_tables = idx; + iio_gts_us_to_int_micro(times, int_micro_times, idx); + } + + gts->avail_time_tables = int_micro_times; + kfree(times); + + if (!int_micro_times) + return -ENOMEM; return 0; } @@ -683,8 +705,8 @@ int iio_gts_avail_times(struct iio_gts *gts, const int **vals, int *type, return -EINVAL; *vals = gts->avail_time_tables; - *type = IIO_VAL_INT; - *length = gts->num_avail_time_tables; + *type = IIO_VAL_INT_PLUS_MICRO; + *length = gts->num_avail_time_tables * 2; return IIO_AVAIL_LIST; } diff --git a/drivers/iio/light/rohm-bu27034.c b/drivers/iio/light/rohm-bu27034.c index e486dcf35eba..f85194fda6b0 100644 --- a/drivers/iio/light/rohm-bu27034.c +++ b/drivers/iio/light/rohm-bu27034.c @@ -231,6 +231,9 @@ struct bu27034_result { static const struct regmap_range bu27034_volatile_ranges[] = { { + .range_min = BU27034_REG_SYSTEM_CONTROL, + .range_max = BU27034_REG_SYSTEM_CONTROL, + }, { .range_min = BU27034_REG_MODE_CONTROL4, .range_max = BU27034_REG_MODE_CONTROL4, }, { @@ -1167,11 +1170,12 @@ static int bu27034_read_raw(struct iio_dev *idev, switch (mask) { case IIO_CHAN_INFO_INT_TIME: - *val = bu27034_get_int_time(data); - if (*val < 0) - return *val; + *val = 0; + *val2 = bu27034_get_int_time(data); + if (*val2 < 0) + return *val2; - return IIO_VAL_INT; + return IIO_VAL_INT_PLUS_MICRO; case IIO_CHAN_INFO_SCALE: return bu27034_get_scale(data, chan->channel, val, val2); @@ -1229,7 +1233,10 @@ static int bu27034_write_raw(struct iio_dev *idev, ret = bu27034_set_scale(data, chan->channel, val, val2); break; case IIO_CHAN_INFO_INT_TIME: - ret = bu27034_try_set_int_time(data, val); + if (!val) + ret = bu27034_try_set_int_time(data, val2); + else + ret = -EINVAL; break; default: ret = -EINVAL; @@ -1268,12 +1275,19 @@ static int bu27034_chip_init(struct bu27034_data *data) int ret, sel; /* Reset */ - ret = regmap_update_bits(data->regmap, BU27034_REG_SYSTEM_CONTROL, + ret = regmap_write_bits(data->regmap, BU27034_REG_SYSTEM_CONTROL, BU27034_MASK_SW_RESET, BU27034_MASK_SW_RESET); if (ret) return dev_err_probe(data->dev, ret, "Sensor reset failed\n"); msleep(1); + + ret = regmap_reinit_cache(data->regmap, &bu27034_regmap); + if (ret) { + dev_err(data->dev, "Failed to reinit reg cache\n"); + return ret; + } + /* * Read integration time here to ensure it is in regmap cache. We do * this to speed-up the int-time acquisition in the start of the buffer diff --git a/drivers/iio/light/vcnl4035.c b/drivers/iio/light/vcnl4035.c index 14e29330e972..94f5d611e98c 100644 --- a/drivers/iio/light/vcnl4035.c +++ b/drivers/iio/light/vcnl4035.c @@ -8,6 +8,7 @@ * TODO: Proximity */ #include <linux/bitops.h> +#include <linux/bitfield.h> #include <linux/i2c.h> #include <linux/module.h> #include <linux/pm_runtime.h> @@ -42,6 +43,7 @@ #define VCNL4035_ALS_PERS_MASK GENMASK(3, 2) #define VCNL4035_INT_ALS_IF_H_MASK BIT(12) #define VCNL4035_INT_ALS_IF_L_MASK BIT(13) +#define VCNL4035_DEV_ID_MASK GENMASK(7, 0) /* Default values */ #define VCNL4035_MODE_ALS_ENABLE BIT(0) @@ -413,6 +415,7 @@ static int vcnl4035_init(struct vcnl4035_data *data) return ret; } + id = FIELD_GET(VCNL4035_DEV_ID_MASK, id); if (id != VCNL4035_DEV_ID_VAL) { dev_err(&data->client->dev, "Wrong id, got %x, expected %x\n", id, VCNL4035_DEV_ID_VAL); diff --git a/drivers/iio/magnetometer/tmag5273.c b/drivers/iio/magnetometer/tmag5273.c index 28bb7efe8df8..e155a75b3cd2 100644 --- a/drivers/iio/magnetometer/tmag5273.c +++ b/drivers/iio/magnetometer/tmag5273.c @@ -296,12 +296,13 @@ static int tmag5273_read_raw(struct iio_dev *indio_dev, return ret; ret = tmag5273_get_measure(data, &t, &x, &y, &z, &angle, &magnitude); - if (ret) - return ret; pm_runtime_mark_last_busy(data->dev); pm_runtime_put_autosuspend(data->dev); + if (ret) + return ret; + switch (chan->address) { case TEMPERATURE: *val = t; diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index e86afecfbe46..b1c36412025f 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -3341,9 +3341,7 @@ static int bnxt_re_process_raw_qp_pkt_rx(struct bnxt_re_qp *gsi_qp, udwr.remote_qkey = gsi_sqp->qplib_qp.qkey; /* post data received in the send queue */ - rc = bnxt_re_post_send_shadow_qp(rdev, gsi_sqp, swr); - - return 0; + return bnxt_re_post_send_shadow_qp(rdev, gsi_sqp, swr); } static void bnxt_re_process_res_rawqp1_wc(struct ib_wc *wc, diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index b9e2f89337e8..e34eccd178d0 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -1336,6 +1336,10 @@ static void bnxt_re_setup_cc(struct bnxt_re_dev *rdev, bool enable) { struct bnxt_qplib_cc_param cc_param = {}; + /* Do not enable congestion control on VFs */ + if (rdev->is_virtfn) + return; + /* Currently enabling only for GenP5 adapters */ if (!bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx)) return; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index f139d4cd1712..8974f6235cfa 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -2056,6 +2056,12 @@ int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq) u32 pg_sz_lvl; int rc; + if (!cq->dpi) { + dev_err(&rcfw->pdev->dev, + "FP: CREATE_CQ failed due to NULL DPI\n"); + return -EINVAL; + } + hwq_attr.res = res; hwq_attr.depth = cq->max_wqe; hwq_attr.stride = sizeof(struct cq_base); @@ -2069,11 +2075,6 @@ int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq) CMDQ_BASE_OPCODE_CREATE_CQ, sizeof(req)); - if (!cq->dpi) { - dev_err(&rcfw->pdev->dev, - "FP: CREATE_CQ failed due to NULL DPI\n"); - return -EINVAL; - } req.dpi = cpu_to_le32(cq->dpi->dpi); req.cq_handle = cpu_to_le64(cq->cq_handle); req.cq_size = cpu_to_le32(cq->hwq.max_elements); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c index 126d4f26f75a..81b0c5e879f9 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c @@ -215,17 +215,9 @@ int bnxt_qplib_alloc_init_hwq(struct bnxt_qplib_hwq *hwq, return -EINVAL; hwq_attr->sginfo->npages = npages; } else { - unsigned long sginfo_num_pages = ib_umem_num_dma_blocks( - hwq_attr->sginfo->umem, hwq_attr->sginfo->pgsize); - + npages = ib_umem_num_dma_blocks(hwq_attr->sginfo->umem, + hwq_attr->sginfo->pgsize); hwq->is_user = true; - npages = sginfo_num_pages; - npages = (npages * PAGE_SIZE) / - BIT_ULL(hwq_attr->sginfo->pgshft); - if ((sginfo_num_pages * PAGE_SIZE) % - BIT_ULL(hwq_attr->sginfo->pgshft)) - if (!npages) - npages++; } if (npages == MAX_PBL_LVL_0_PGS && !hwq_attr->sginfo->nopte) { diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c index 1714a1e23113..b967a17a44be 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c @@ -617,16 +617,15 @@ int bnxt_qplib_reg_mr(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mr, /* Free the hwq if it already exist, must be a rereg */ if (mr->hwq.max_elements) bnxt_qplib_free_hwq(res, &mr->hwq); - /* Use system PAGE_SIZE */ hwq_attr.res = res; hwq_attr.depth = pages; - hwq_attr.stride = buf_pg_size; + hwq_attr.stride = sizeof(dma_addr_t); hwq_attr.type = HWQ_TYPE_MR; hwq_attr.sginfo = &sginfo; hwq_attr.sginfo->umem = umem; hwq_attr.sginfo->npages = pages; - hwq_attr.sginfo->pgsize = PAGE_SIZE; - hwq_attr.sginfo->pgshft = PAGE_SHIFT; + hwq_attr.sginfo->pgsize = buf_pg_size; + hwq_attr.sginfo->pgshft = ilog2(buf_pg_size); rc = bnxt_qplib_alloc_init_hwq(&mr->hwq, &hwq_attr); if (rc) { dev_err(&res->pdev->dev, diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c index 8eca6c14d0cf..2a195c4b0f17 100644 --- a/drivers/infiniband/hw/efa/efa_verbs.c +++ b/drivers/infiniband/hw/efa/efa_verbs.c @@ -1403,7 +1403,7 @@ static int pbl_continuous_initialize(struct efa_dev *dev, */ static int pbl_indirect_initialize(struct efa_dev *dev, struct pbl_context *pbl) { - u32 size_in_pages = DIV_ROUND_UP(pbl->pbl_buf_size_in_bytes, PAGE_SIZE); + u32 size_in_pages = DIV_ROUND_UP(pbl->pbl_buf_size_in_bytes, EFA_CHUNK_PAYLOAD_SIZE); struct scatterlist *sgl; int sg_dma_cnt, err; diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 84f1167de1d9..d4c6b9bc0a4e 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -4583,11 +4583,9 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp, mtu = ib_mtu_enum_to_int(ib_mtu); if (WARN_ON(mtu <= 0)) return -EINVAL; -#define MAX_LP_MSG_LEN 16384 - /* MTU * (2 ^ LP_PKTN_INI) shouldn't be bigger than 16KB */ - lp_pktn_ini = ilog2(MAX_LP_MSG_LEN / mtu); - if (WARN_ON(lp_pktn_ini >= 0xF)) - return -EINVAL; +#define MIN_LP_MSG_LEN 1024 + /* mtu * (2 ^ lp_pktn_ini) should be in the range of 1024 to mtu */ + lp_pktn_ini = ilog2(max(mtu, MIN_LP_MSG_LEN) / mtu); if (attr_mask & IB_QP_PATH_MTU) { hr_reg_write(context, QPC_MTU, ib_mtu); @@ -5012,7 +5010,6 @@ static int hns_roce_v2_set_abs_fields(struct ib_qp *ibqp, static bool check_qp_timeout_cfg_range(struct hns_roce_dev *hr_dev, u8 *timeout) { #define QP_ACK_TIMEOUT_MAX_HIP08 20 -#define QP_ACK_TIMEOUT_OFFSET 10 #define QP_ACK_TIMEOUT_MAX 31 if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08) { @@ -5021,7 +5018,7 @@ static bool check_qp_timeout_cfg_range(struct hns_roce_dev *hr_dev, u8 *timeout) "local ACK timeout shall be 0 to 20.\n"); return false; } - *timeout += QP_ACK_TIMEOUT_OFFSET; + *timeout += HNS_ROCE_V2_QP_ACK_TIMEOUT_OFS_HIP08; } else if (hr_dev->pci_dev->revision > PCI_REVISION_ID_HIP08) { if (*timeout > QP_ACK_TIMEOUT_MAX) { ibdev_warn(&hr_dev->ib_dev, @@ -5307,6 +5304,18 @@ out: return ret; } +static u8 get_qp_timeout_attr(struct hns_roce_dev *hr_dev, + struct hns_roce_v2_qp_context *context) +{ + u8 timeout; + + timeout = (u8)hr_reg_read(context, QPC_AT); + if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08) + timeout -= HNS_ROCE_V2_QP_ACK_TIMEOUT_OFS_HIP08; + + return timeout; +} + static int hns_roce_v2_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr) @@ -5384,7 +5393,7 @@ static int hns_roce_v2_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, qp_attr->max_dest_rd_atomic = 1 << hr_reg_read(&context, QPC_RR_MAX); qp_attr->min_rnr_timer = (u8)hr_reg_read(&context, QPC_MIN_RNR_TIME); - qp_attr->timeout = (u8)hr_reg_read(&context, QPC_AT); + qp_attr->timeout = get_qp_timeout_attr(hr_dev, &context); qp_attr->retry_cnt = hr_reg_read(&context, QPC_RETRY_NUM_INIT); qp_attr->rnr_retry = hr_reg_read(&context, QPC_RNR_NUM_INIT); diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index 1b44d2434ab4..7033eae2407c 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -44,6 +44,8 @@ #define HNS_ROCE_V2_MAX_XRCD_NUM 0x1000000 #define HNS_ROCE_V2_RSV_XRCD_NUM 0 +#define HNS_ROCE_V2_QP_ACK_TIMEOUT_OFS_HIP08 10 + #define HNS_ROCE_V3_SCCC_SZ 64 #define HNS_ROCE_V3_GMV_ENTRY_SZ 32 diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c index 37a5cf62f88b..14376490ac22 100644 --- a/drivers/infiniband/hw/hns/hns_roce_mr.c +++ b/drivers/infiniband/hw/hns/hns_roce_mr.c @@ -33,6 +33,7 @@ #include <linux/vmalloc.h> #include <rdma/ib_umem.h> +#include <linux/math.h> #include "hns_roce_device.h" #include "hns_roce_cmd.h" #include "hns_roce_hem.h" @@ -909,6 +910,44 @@ static int mtr_init_buf_cfg(struct hns_roce_dev *hr_dev, return page_cnt; } +static u64 cal_pages_per_l1ba(unsigned int ba_per_bt, unsigned int hopnum) +{ + return int_pow(ba_per_bt, hopnum - 1); +} + +static unsigned int cal_best_bt_pg_sz(struct hns_roce_dev *hr_dev, + struct hns_roce_mtr *mtr, + unsigned int pg_shift) +{ + unsigned long cap = hr_dev->caps.page_size_cap; + struct hns_roce_buf_region *re; + unsigned int pgs_per_l1ba; + unsigned int ba_per_bt; + unsigned int ba_num; + int i; + + for_each_set_bit_from(pg_shift, &cap, sizeof(cap) * BITS_PER_BYTE) { + if (!(BIT(pg_shift) & cap)) + continue; + + ba_per_bt = BIT(pg_shift) / BA_BYTE_LEN; + ba_num = 0; + for (i = 0; i < mtr->hem_cfg.region_count; i++) { + re = &mtr->hem_cfg.region[i]; + if (re->hopnum == 0) + continue; + + pgs_per_l1ba = cal_pages_per_l1ba(ba_per_bt, re->hopnum); + ba_num += DIV_ROUND_UP(re->count, pgs_per_l1ba); + } + + if (ba_num <= ba_per_bt) + return pg_shift; + } + + return 0; +} + static int mtr_alloc_mtt(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr, unsigned int ba_page_shift) { @@ -917,6 +956,10 @@ static int mtr_alloc_mtt(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr, hns_roce_hem_list_init(&mtr->hem_list); if (!cfg->is_direct) { + ba_page_shift = cal_best_bt_pg_sz(hr_dev, mtr, ba_page_shift); + if (!ba_page_shift) + return -ERANGE; + ret = hns_roce_hem_list_request(hr_dev, &mtr->hem_list, cfg->region, cfg->region_count, ba_page_shift); diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index ab5cdf782785..eaa12c124598 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -522,11 +522,6 @@ static int irdma_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) if (!iwqp->user_mode) cancel_delayed_work_sync(&iwqp->dwork_flush); - irdma_qp_rem_ref(&iwqp->ibqp); - wait_for_completion(&iwqp->free_qp); - irdma_free_lsmm_rsrc(iwqp); - irdma_cqp_qp_destroy_cmd(&iwdev->rf->sc_dev, &iwqp->sc_qp); - if (!iwqp->user_mode) { if (iwqp->iwscq) { irdma_clean_cqes(iwqp, iwqp->iwscq); @@ -534,6 +529,12 @@ static int irdma_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) irdma_clean_cqes(iwqp, iwqp->iwrcq); } } + + irdma_qp_rem_ref(&iwqp->ibqp); + wait_for_completion(&iwqp->free_qp); + irdma_free_lsmm_rsrc(iwqp); + irdma_cqp_qp_destroy_cmd(&iwdev->rf->sc_dev, &iwqp->sc_qp); + irdma_remove_push_mmap_entries(iwqp); irdma_free_qp_rsrc(iwqp); @@ -3291,6 +3292,7 @@ static int irdma_post_send(struct ib_qp *ibqp, break; case IB_WR_LOCAL_INV: info.op_type = IRDMA_OP_TYPE_INV_STAG; + info.local_fence = info.read_fence; info.op.inv_local_stag.target_stag = ib_wr->ex.invalidate_rkey; err = irdma_uk_stag_local_invalidate(ukqp, &info, true); break; diff --git a/drivers/infiniband/hw/mlx5/ib_rep.c b/drivers/infiniband/hw/mlx5/ib_rep.c index ddcfc116b19a..c7a4ee896121 100644 --- a/drivers/infiniband/hw/mlx5/ib_rep.c +++ b/drivers/infiniband/hw/mlx5/ib_rep.c @@ -30,45 +30,65 @@ mlx5_ib_set_vport_rep(struct mlx5_core_dev *dev, static void mlx5_ib_register_peer_vport_reps(struct mlx5_core_dev *mdev); +static void mlx5_ib_num_ports_update(struct mlx5_core_dev *dev, u32 *num_ports) +{ + struct mlx5_core_dev *peer_dev; + int i; + + mlx5_lag_for_each_peer_mdev(dev, peer_dev, i) { + u32 peer_num_ports = mlx5_eswitch_get_total_vports(peer_dev); + + if (mlx5_lag_is_mpesw(peer_dev)) + *num_ports += peer_num_ports; + else + /* Only 1 ib port is the representor for all uplinks */ + *num_ports += peer_num_ports - 1; + } +} + static int mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) { u32 num_ports = mlx5_eswitch_get_total_vports(dev); + struct mlx5_core_dev *lag_master = dev; const struct mlx5_ib_profile *profile; struct mlx5_core_dev *peer_dev; struct mlx5_ib_dev *ibdev; - int second_uplink = false; - u32 peer_num_ports; + int new_uplink = false; int vport_index; int ret; + int i; vport_index = rep->vport_index; if (mlx5_lag_is_shared_fdb(dev)) { - peer_dev = mlx5_lag_get_peer_mdev(dev); - peer_num_ports = mlx5_eswitch_get_total_vports(peer_dev); if (mlx5_lag_is_master(dev)) { - if (mlx5_lag_is_mpesw(dev)) - num_ports += peer_num_ports; - else - num_ports += peer_num_ports - 1; - + mlx5_ib_num_ports_update(dev, &num_ports); } else { if (rep->vport == MLX5_VPORT_UPLINK) { if (!mlx5_lag_is_mpesw(dev)) return 0; - second_uplink = true; + new_uplink = true; } + mlx5_lag_for_each_peer_mdev(dev, peer_dev, i) { + u32 peer_n_ports = mlx5_eswitch_get_total_vports(peer_dev); + + if (mlx5_lag_is_master(peer_dev)) + lag_master = peer_dev; + else if (!mlx5_lag_is_mpesw(dev)) + /* Only 1 ib port is the representor for all uplinks */ + peer_n_ports--; - vport_index += peer_num_ports; - dev = peer_dev; + if (mlx5_get_dev_index(peer_dev) < mlx5_get_dev_index(dev)) + vport_index += peer_n_ports; + } } } - if (rep->vport == MLX5_VPORT_UPLINK && !second_uplink) + if (rep->vport == MLX5_VPORT_UPLINK && !new_uplink) profile = &raw_eth_profile; else - return mlx5_ib_set_vport_rep(dev, rep, vport_index); + return mlx5_ib_set_vport_rep(lag_master, rep, vport_index); ibdev = ib_alloc_device(mlx5_ib_dev, ib_dev); if (!ibdev) @@ -85,8 +105,8 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) vport_index = rep->vport_index; ibdev->port[vport_index].rep = rep; ibdev->port[vport_index].roce.netdev = - mlx5_ib_get_rep_netdev(dev->priv.eswitch, rep->vport); - ibdev->mdev = dev; + mlx5_ib_get_rep_netdev(lag_master->priv.eswitch, rep->vport); + ibdev->mdev = lag_master; ibdev->num_ports = num_ports; ret = __mlx5_ib_add(ibdev, profile); @@ -94,8 +114,8 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) goto fail_add; rep->rep_data[REP_IB].priv = ibdev; - if (mlx5_lag_is_shared_fdb(dev)) - mlx5_ib_register_peer_vport_reps(dev); + if (mlx5_lag_is_shared_fdb(lag_master)) + mlx5_ib_register_peer_vport_reps(lag_master); return 0; @@ -118,23 +138,27 @@ mlx5_ib_vport_rep_unload(struct mlx5_eswitch_rep *rep) struct mlx5_ib_dev *dev = mlx5_ib_rep_to_dev(rep); int vport_index = rep->vport_index; struct mlx5_ib_port *port; + int i; if (WARN_ON(!mdev)) return; + if (!dev) + return; + if (mlx5_lag_is_shared_fdb(mdev) && !mlx5_lag_is_master(mdev)) { - struct mlx5_core_dev *peer_mdev; - - if (rep->vport == MLX5_VPORT_UPLINK) + if (rep->vport == MLX5_VPORT_UPLINK && !mlx5_lag_is_mpesw(mdev)) return; - peer_mdev = mlx5_lag_get_peer_mdev(mdev); - vport_index += mlx5_eswitch_get_total_vports(peer_mdev); + for (i = 0; i < dev->num_ports; i++) { + if (dev->port[i].rep == rep) + break; + } + if (WARN_ON(i == dev->num_ports)) + return; + vport_index = i; } - if (!dev) - return; - port = &dev->port[vport_index]; write_lock(&port->roce.netdev_lock); port->roce.netdev = NULL; @@ -143,13 +167,18 @@ mlx5_ib_vport_rep_unload(struct mlx5_eswitch_rep *rep) port->rep = NULL; if (rep->vport == MLX5_VPORT_UPLINK) { - struct mlx5_core_dev *peer_mdev; - struct mlx5_eswitch *esw; + + if (mlx5_lag_is_shared_fdb(mdev) && !mlx5_lag_is_master(mdev)) + return; if (mlx5_lag_is_shared_fdb(mdev)) { - peer_mdev = mlx5_lag_get_peer_mdev(mdev); - esw = peer_mdev->priv.eswitch; - mlx5_eswitch_unregister_vport_reps(esw, REP_IB); + struct mlx5_core_dev *peer_mdev; + struct mlx5_eswitch *esw; + + mlx5_lag_for_each_peer_mdev(mdev, peer_mdev, i) { + esw = peer_mdev->priv.eswitch; + mlx5_eswitch_unregister_vport_reps(esw, REP_IB); + } } __mlx5_ib_remove(dev, dev->profile, MLX5_IB_STAGE_MAX); } @@ -163,14 +192,14 @@ static const struct mlx5_eswitch_rep_ops rep_ops = { static void mlx5_ib_register_peer_vport_reps(struct mlx5_core_dev *mdev) { - struct mlx5_core_dev *peer_mdev = mlx5_lag_get_peer_mdev(mdev); + struct mlx5_core_dev *peer_mdev; struct mlx5_eswitch *esw; + int i; - if (!peer_mdev) - return; - - esw = peer_mdev->priv.eswitch; - mlx5_eswitch_register_vport_reps(esw, &rep_ops, REP_IB); + mlx5_lag_for_each_peer_mdev(mdev, peer_mdev, i) { + esw = peer_mdev->priv.eswitch; + mlx5_eswitch_register_vport_reps(esw, &rep_ops, REP_IB); + } } struct net_device *mlx5_ib_get_rep_netdev(struct mlx5_eswitch *esw, diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c index db18ace74d2b..f46c5a5fd0ae 100644 --- a/drivers/infiniband/sw/rxe/rxe_comp.c +++ b/drivers/infiniband/sw/rxe/rxe_comp.c @@ -115,15 +115,16 @@ static enum ib_wc_opcode wr_to_wc_opcode(enum ib_wr_opcode opcode) void retransmit_timer(struct timer_list *t) { struct rxe_qp *qp = from_timer(qp, t, retrans_timer); + unsigned long flags; rxe_dbg_qp(qp, "retransmit timer fired\n"); - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp->valid) { qp->comp.timeout = 1; rxe_sched_task(&qp->comp.task); } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } void rxe_comp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb) @@ -481,11 +482,13 @@ static void do_complete(struct rxe_qp *qp, struct rxe_send_wqe *wqe) static void comp_check_sq_drain_done(struct rxe_qp *qp) { - spin_lock_bh(&qp->state_lock); + unsigned long flags; + + spin_lock_irqsave(&qp->state_lock, flags); if (unlikely(qp_state(qp) == IB_QPS_SQD)) { if (qp->attr.sq_draining && qp->comp.psn == qp->req.psn) { qp->attr.sq_draining = 0; - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (qp->ibqp.event_handler) { struct ib_event ev; @@ -499,7 +502,7 @@ static void comp_check_sq_drain_done(struct rxe_qp *qp) return; } } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } static inline enum comp_state complete_ack(struct rxe_qp *qp, @@ -625,13 +628,15 @@ static void free_pkt(struct rxe_pkt_info *pkt) */ static void reset_retry_timer(struct rxe_qp *qp) { + unsigned long flags; + if (qp_type(qp) == IB_QPT_RC && qp->qp_timeout_jiffies) { - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp_state(qp) >= IB_QPS_RTS && psn_compare(qp->req.psn, qp->comp.psn) > 0) mod_timer(&qp->retrans_timer, jiffies + qp->qp_timeout_jiffies); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } } @@ -643,18 +648,19 @@ int rxe_completer(struct rxe_qp *qp) struct rxe_pkt_info *pkt = NULL; enum comp_state state; int ret; + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (!qp->valid || qp_state(qp) == IB_QPS_ERR || qp_state(qp) == IB_QPS_RESET) { bool notify = qp->valid && (qp_state(qp) == IB_QPS_ERR); drain_resp_pkts(qp); flush_send_queue(qp, notify); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); goto exit; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (qp->comp.timeout) { qp->comp.timeout_retry = 1; diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index 2bc7361152ea..a38fab19bed1 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -412,15 +412,16 @@ int rxe_xmit_packet(struct rxe_qp *qp, struct rxe_pkt_info *pkt, int err; int is_request = pkt->mask & RXE_REQ_MASK; struct rxe_dev *rxe = to_rdev(qp->ibqp.device); + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if ((is_request && (qp_state(qp) < IB_QPS_RTS)) || (!is_request && (qp_state(qp) < IB_QPS_RTR))) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); rxe_dbg_qp(qp, "Packet dropped. QP is not in ready state\n"); goto drop; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); rxe_icrc_generate(skb, pkt); diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index c5451a4488ca..61a2eb77d999 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -300,6 +300,7 @@ int rxe_qp_from_init(struct rxe_dev *rxe, struct rxe_qp *qp, struct rxe_pd *pd, struct rxe_cq *rcq = to_rcq(init->recv_cq); struct rxe_cq *scq = to_rcq(init->send_cq); struct rxe_srq *srq = init->srq ? to_rsrq(init->srq) : NULL; + unsigned long flags; rxe_get(pd); rxe_get(rcq); @@ -325,10 +326,10 @@ int rxe_qp_from_init(struct rxe_dev *rxe, struct rxe_qp *qp, struct rxe_pd *pd, if (err) goto err2; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); qp->attr.qp_state = IB_QPS_RESET; qp->valid = 1; - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return 0; @@ -492,24 +493,28 @@ static void rxe_qp_reset(struct rxe_qp *qp) /* move the qp to the error state */ void rxe_qp_error(struct rxe_qp *qp) { - spin_lock_bh(&qp->state_lock); + unsigned long flags; + + spin_lock_irqsave(&qp->state_lock, flags); qp->attr.qp_state = IB_QPS_ERR; /* drain work and packet queues */ rxe_sched_task(&qp->resp.task); rxe_sched_task(&qp->comp.task); rxe_sched_task(&qp->req.task); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } static void rxe_qp_sqd(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask) { - spin_lock_bh(&qp->state_lock); + unsigned long flags; + + spin_lock_irqsave(&qp->state_lock, flags); qp->attr.sq_draining = 1; rxe_sched_task(&qp->comp.task); rxe_sched_task(&qp->req.task); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } /* caller should hold qp->state_lock */ @@ -555,14 +560,16 @@ int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask, qp->attr.cur_qp_state = attr->qp_state; if (mask & IB_QP_STATE) { - spin_lock_bh(&qp->state_lock); + unsigned long flags; + + spin_lock_irqsave(&qp->state_lock, flags); err = __qp_chk_state(qp, attr, mask); if (!err) { qp->attr.qp_state = attr->qp_state; rxe_dbg_qp(qp, "state -> %s\n", qps2str[attr->qp_state]); } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (err) return err; @@ -688,6 +695,8 @@ int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask, /* called by the query qp verb */ int rxe_qp_to_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask) { + unsigned long flags; + *attr = qp->attr; attr->rq_psn = qp->resp.psn; @@ -708,12 +717,13 @@ int rxe_qp_to_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask) /* Applications that get this state typically spin on it. * Yield the processor */ - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp->attr.sq_draining) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); cond_resched(); + } else { + spin_unlock_irqrestore(&qp->state_lock, flags); } - spin_unlock_bh(&qp->state_lock); return 0; } @@ -736,10 +746,11 @@ int rxe_qp_chk_destroy(struct rxe_qp *qp) static void rxe_qp_do_cleanup(struct work_struct *work) { struct rxe_qp *qp = container_of(work, typeof(*qp), cleanup_work.work); + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); qp->valid = 0; - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); qp->qp_timeout_jiffies = 0; if (qp_type(qp) == IB_QPT_RC) { diff --git a/drivers/infiniband/sw/rxe/rxe_recv.c b/drivers/infiniband/sw/rxe/rxe_recv.c index 2f953cc74256..5861e4244049 100644 --- a/drivers/infiniband/sw/rxe/rxe_recv.c +++ b/drivers/infiniband/sw/rxe/rxe_recv.c @@ -14,6 +14,7 @@ static int check_type_state(struct rxe_dev *rxe, struct rxe_pkt_info *pkt, struct rxe_qp *qp) { unsigned int pkt_type; + unsigned long flags; if (unlikely(!qp->valid)) return -EINVAL; @@ -38,19 +39,19 @@ static int check_type_state(struct rxe_dev *rxe, struct rxe_pkt_info *pkt, return -EINVAL; } - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (pkt->mask & RXE_REQ_MASK) { if (unlikely(qp_state(qp) < IB_QPS_RTR)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return -EINVAL; } } else { if (unlikely(qp_state(qp) < IB_QPS_RTS)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return -EINVAL; } } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return 0; } diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c index 65134a9aefe7..5fe7cbae3031 100644 --- a/drivers/infiniband/sw/rxe/rxe_req.c +++ b/drivers/infiniband/sw/rxe/rxe_req.c @@ -99,17 +99,18 @@ static void req_retry(struct rxe_qp *qp) void rnr_nak_timer(struct timer_list *t) { struct rxe_qp *qp = from_timer(qp, t, rnr_nak_timer); + unsigned long flags; rxe_dbg_qp(qp, "nak timer fired\n"); - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp->valid) { /* request a send queue retry */ qp->req.need_retry = 1; qp->req.wait_for_rnr_timer = 0; rxe_sched_task(&qp->req.task); } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } static void req_check_sq_drain_done(struct rxe_qp *qp) @@ -118,8 +119,9 @@ static void req_check_sq_drain_done(struct rxe_qp *qp) unsigned int index; unsigned int cons; struct rxe_send_wqe *wqe; + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp_state(qp) == IB_QPS_SQD) { q = qp->sq.queue; index = qp->req.wqe_index; @@ -140,7 +142,7 @@ static void req_check_sq_drain_done(struct rxe_qp *qp) break; qp->attr.sq_draining = 0; - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (qp->ibqp.event_handler) { struct ib_event ev; @@ -154,7 +156,7 @@ static void req_check_sq_drain_done(struct rxe_qp *qp) return; } while (0); } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } static struct rxe_send_wqe *__req_next_wqe(struct rxe_qp *qp) @@ -173,6 +175,7 @@ static struct rxe_send_wqe *__req_next_wqe(struct rxe_qp *qp) static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp) { struct rxe_send_wqe *wqe; + unsigned long flags; req_check_sq_drain_done(qp); @@ -180,13 +183,13 @@ static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp) if (wqe == NULL) return NULL; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (unlikely((qp_state(qp) == IB_QPS_SQD) && (wqe->state != wqe_state_processing))) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return NULL; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); wqe->mask = wr_opcode_mask(wqe->wr.opcode, qp); return wqe; @@ -676,16 +679,17 @@ int rxe_requester(struct rxe_qp *qp) struct rxe_queue *q = qp->sq.queue; struct rxe_ah *ah; struct rxe_av *av; + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (unlikely(!qp->valid)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); goto exit; } if (unlikely(qp_state(qp) == IB_QPS_ERR)) { wqe = __req_next_wqe(qp); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (wqe) goto err; else @@ -700,10 +704,10 @@ int rxe_requester(struct rxe_qp *qp) qp->req.wait_psn = 0; qp->req.need_retry = 0; qp->req.wait_for_rnr_timer = 0; - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); goto exit; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); /* we come here if the retransmit timer has fired * or if the rnr timer has fired. If the retransmit diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index 68f6cd188d8e..1da044f6b7d4 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -1047,6 +1047,7 @@ static enum resp_states do_complete(struct rxe_qp *qp, struct ib_uverbs_wc *uwc = &cqe.uibwc; struct rxe_recv_wqe *wqe = qp->resp.wqe; struct rxe_dev *rxe = to_rdev(qp->ibqp.device); + unsigned long flags; if (!wqe) goto finish; @@ -1137,12 +1138,12 @@ static enum resp_states do_complete(struct rxe_qp *qp, return RESPST_ERR_CQ_OVERFLOW; finish: - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (unlikely(qp_state(qp) == IB_QPS_ERR)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return RESPST_CHK_RESOURCE; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (unlikely(!pkt)) return RESPST_DONE; @@ -1468,18 +1469,19 @@ int rxe_responder(struct rxe_qp *qp) enum resp_states state; struct rxe_pkt_info *pkt = NULL; int ret; + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (!qp->valid || qp_state(qp) == IB_QPS_ERR || qp_state(qp) == IB_QPS_RESET) { bool notify = qp->valid && (qp_state(qp) == IB_QPS_ERR); drain_req_pkts(qp); flush_recv_queue(qp, notify); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); goto exit; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); qp->resp.aeth_syndrome = AETH_ACK_UNLIMITED; diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index dea605b7f683..4d8f6b8051ff 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -904,10 +904,10 @@ static int rxe_post_send_kernel(struct rxe_qp *qp, if (!err) rxe_sched_task(&qp->req.task); - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp_state(qp) == IB_QPS_ERR) rxe_sched_task(&qp->comp.task); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return err; } @@ -917,22 +917,23 @@ static int rxe_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr, { struct rxe_qp *qp = to_rqp(ibqp); int err; + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); /* caller has already called destroy_qp */ if (WARN_ON_ONCE(!qp->valid)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); rxe_err_qp(qp, "qp has been destroyed"); return -EINVAL; } if (unlikely(qp_state(qp) < IB_QPS_RTS)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); *bad_wr = wr; rxe_err_qp(qp, "qp not ready to send"); return -EINVAL; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (qp->is_user) { /* Utilize process context to do protocol processing */ @@ -1008,22 +1009,22 @@ static int rxe_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr, struct rxe_rq *rq = &qp->rq; unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); /* caller has already called destroy_qp */ if (WARN_ON_ONCE(!qp->valid)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); rxe_err_qp(qp, "qp has been destroyed"); return -EINVAL; } /* see C10-97.2.1 */ if (unlikely((qp_state(qp) < IB_QPS_INIT))) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); *bad_wr = wr; rxe_dbg_qp(qp, "qp not ready to post recv"); return -EINVAL; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (unlikely(qp->srq)) { *bad_wr = wr; @@ -1044,10 +1045,10 @@ static int rxe_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr, spin_unlock_irqrestore(&rq->producer_lock, flags); - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp_state(qp) == IB_QPS_ERR) rxe_sched_task(&qp->resp.task); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return err; } diff --git a/drivers/infiniband/sw/siw/siw_qp_tx.c b/drivers/infiniband/sw/siw/siw_qp_tx.c index 4b292e0504f1..ffb16beb6c30 100644 --- a/drivers/infiniband/sw/siw/siw_qp_tx.c +++ b/drivers/infiniband/sw/siw/siw_qp_tx.c @@ -312,7 +312,7 @@ static int siw_tx_ctrl(struct siw_iwarp_tx *c_tx, struct socket *s, } /* - * 0copy TCP transmit interface: Use do_tcp_sendpages. + * 0copy TCP transmit interface: Use MSG_SPLICE_PAGES. * * Using sendpage to push page by page appears to be less efficient * than using sendmsg, even if data are copied. @@ -323,20 +323,27 @@ static int siw_tx_ctrl(struct siw_iwarp_tx *c_tx, struct socket *s, static int siw_tcp_sendpages(struct socket *s, struct page **page, int offset, size_t size) { + struct bio_vec bvec; + struct msghdr msg = { + .msg_flags = (MSG_MORE | MSG_DONTWAIT | MSG_SENDPAGE_NOTLAST | + MSG_SPLICE_PAGES), + }; struct sock *sk = s->sk; - int i = 0, rv = 0, sent = 0, - flags = MSG_MORE | MSG_DONTWAIT | MSG_SENDPAGE_NOTLAST; + int i = 0, rv = 0, sent = 0; while (size) { size_t bytes = min_t(size_t, PAGE_SIZE - offset, size); if (size + offset <= PAGE_SIZE) - flags = MSG_MORE | MSG_DONTWAIT; + msg.msg_flags &= ~MSG_SENDPAGE_NOTLAST; tcp_rate_check_app_limited(sk); + bvec_set_page(&bvec, page[i], bytes, offset); + iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); + try_page_again: lock_sock(sk); - rv = do_tcp_sendpages(sk, page[i], offset, bytes, flags); + rv = tcp_sendmsg_locked(sk, &msg, size); release_sock(sk); if (rv > 0) { diff --git a/drivers/input/input.c b/drivers/input/input.c index 37e876d45eb9..641eb86f276e 100644 --- a/drivers/input/input.c +++ b/drivers/input/input.c @@ -703,7 +703,7 @@ void input_close_device(struct input_handle *handle) __input_release_device(handle); - if (!dev->inhibited && !--dev->users) { + if (!--dev->users && !dev->inhibited) { if (dev->poller) input_dev_poller_stop(dev->poller); if (dev->close) diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 28be88e0e96a..f33622fe946f 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -281,7 +281,6 @@ static const struct xpad_device { { 0x1430, 0xf801, "RedOctane Controller", 0, XTYPE_XBOX360 }, { 0x146b, 0x0601, "BigBen Interactive XBOX 360 Controller", 0, XTYPE_XBOX360 }, { 0x146b, 0x0604, "Bigben Interactive DAIJA Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 }, - { 0x1532, 0x0037, "Razer Sabertooth", 0, XTYPE_XBOX360 }, { 0x1532, 0x0a00, "Razer Atrox Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOXONE }, { 0x1532, 0x0a03, "Razer Wildcat", 0, XTYPE_XBOXONE }, { 0x15e4, 0x3f00, "Power A Mini Pro Elite", 0, XTYPE_XBOX360 }, diff --git a/drivers/input/misc/soc_button_array.c b/drivers/input/misc/soc_button_array.c index 09489380afda..e79f5497948b 100644 --- a/drivers/input/misc/soc_button_array.c +++ b/drivers/input/misc/soc_button_array.c @@ -109,6 +109,27 @@ static const struct dmi_system_id dmi_use_low_level_irq[] = { }; /* + * Some devices have a wrong entry which points to a GPIO which is + * required in another driver, so this driver must not claim it. + */ +static const struct dmi_system_id dmi_invalid_acpi_index[] = { + { + /* + * Lenovo Yoga Book X90F / X90L, the PNP0C40 home button entry + * points to a GPIO which is not a home button and which is + * required by the lenovo-yogabook driver. + */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Intel Corporation"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "CHERRYVIEW D1 PLATFORM"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "YETI-11"), + }, + .driver_data = (void *)1l, + }, + {} /* Terminating entry */ +}; + +/* * Get the Nth GPIO number from the ACPI object. */ static int soc_button_lookup_gpio(struct device *dev, int acpi_index, @@ -137,6 +158,8 @@ soc_button_device_create(struct platform_device *pdev, struct platform_device *pd; struct gpio_keys_button *gpio_keys; struct gpio_keys_platform_data *gpio_keys_pdata; + const struct dmi_system_id *dmi_id; + int invalid_acpi_index = -1; int error, gpio, irq; int n_buttons = 0; @@ -154,10 +177,17 @@ soc_button_device_create(struct platform_device *pdev, gpio_keys = (void *)(gpio_keys_pdata + 1); n_buttons = 0; + dmi_id = dmi_first_match(dmi_invalid_acpi_index); + if (dmi_id) + invalid_acpi_index = (long)dmi_id->driver_data; + for (info = button_info; info->name; info++) { if (info->autorepeat != autorepeat) continue; + if (info->acpi_index == invalid_acpi_index) + continue; + error = soc_button_lookup_gpio(&pdev->dev, info->acpi_index, &gpio, &irq); if (error || irq < 0) { /* diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c index ece97f8c6a3e..2118b2075f43 100644 --- a/drivers/input/mouse/elantech.c +++ b/drivers/input/mouse/elantech.c @@ -674,10 +674,11 @@ static void process_packet_head_v4(struct psmouse *psmouse) struct input_dev *dev = psmouse->dev; struct elantech_data *etd = psmouse->private; unsigned char *packet = psmouse->packet; - int id = ((packet[3] & 0xe0) >> 5) - 1; + int id; int pres, traces; - if (id < 0) + id = ((packet[3] & 0xe0) >> 5) - 1; + if (id < 0 || id >= ETP_MAX_FINGERS) return; etd->mt[id].x = ((packet[1] & 0x0f) << 8) | packet[2]; @@ -707,7 +708,7 @@ static void process_packet_motion_v4(struct psmouse *psmouse) int id, sid; id = ((packet[0] & 0xe0) >> 5) - 1; - if (id < 0) + if (id < 0 || id >= ETP_MAX_FINGERS) return; sid = ((packet[3] & 0xe0) >> 5) - 1; @@ -728,7 +729,7 @@ static void process_packet_motion_v4(struct psmouse *psmouse) input_report_abs(dev, ABS_MT_POSITION_X, etd->mt[id].x); input_report_abs(dev, ABS_MT_POSITION_Y, etd->mt[id].y); - if (sid >= 0) { + if (sid >= 0 && sid < ETP_MAX_FINGERS) { etd->mt[sid].x += delta_x2 * weight; etd->mt[sid].y -= delta_y2 * weight; input_mt_slot(dev, sid); diff --git a/drivers/input/touchscreen/cyttsp5.c b/drivers/input/touchscreen/cyttsp5.c index 30102cb80fac..3c9d07218f48 100644 --- a/drivers/input/touchscreen/cyttsp5.c +++ b/drivers/input/touchscreen/cyttsp5.c @@ -560,7 +560,7 @@ static int cyttsp5_hid_output_get_sysinfo(struct cyttsp5 *ts) static int cyttsp5_hid_output_bl_launch_app(struct cyttsp5 *ts) { int rc; - u8 cmd[HID_OUTPUT_BL_LAUNCH_APP]; + u8 cmd[HID_OUTPUT_BL_LAUNCH_APP_SIZE]; u16 crc; put_unaligned_le16(HID_OUTPUT_BL_LAUNCH_APP_SIZE, cmd); diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index db98c3f86e8c..4d800601e8ec 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -282,6 +282,7 @@ config EXYNOS_IOMMU_DEBUG config IPMMU_VMSA bool "Renesas VMSA-compatible IPMMU" depends on ARCH_RENESAS || COMPILE_TEST + depends on ARM || ARM64 || COMPILE_TEST depends on !GENERIC_ATOMIC64 # for IOMMU_IO_PGTABLE_LPAE select IOMMU_API select IOMMU_IO_PGTABLE_LPAE @@ -417,22 +418,6 @@ config S390_IOMMU help Support for the IOMMU API for s390 PCI devices. -config S390_CCW_IOMMU - bool "S390 CCW IOMMU Support" - depends on S390 && CCW || COMPILE_TEST - select IOMMU_API - help - Enables bits of IOMMU API required by VFIO. The iommu_ops - is not implemented as it is not necessary for VFIO. - -config S390_AP_IOMMU - bool "S390 AP IOMMU Support" - depends on S390 && ZCRYPT || COMPILE_TEST - select IOMMU_API - help - Enables bits of IOMMU API required by VFIO. The iommu_ops - is not implemented as it is not necessary for VFIO. - config MTK_IOMMU tristate "MediaTek IOMMU Support" depends on ARCH_MEDIATEK || COMPILE_TEST diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h index e98f20a9bdd8..9beeceb9d825 100644 --- a/drivers/iommu/amd/amd_iommu.h +++ b/drivers/iommu/amd/amd_iommu.h @@ -15,9 +15,7 @@ extern irqreturn_t amd_iommu_int_thread(int irq, void *data); extern irqreturn_t amd_iommu_int_handler(int irq, void *data); extern void amd_iommu_apply_erratum_63(struct amd_iommu *iommu, u16 devid); extern void amd_iommu_restart_event_logging(struct amd_iommu *iommu); -extern int amd_iommu_init_devices(void); -extern void amd_iommu_uninit_devices(void); -extern void amd_iommu_init_notifier(void); +extern void amd_iommu_restart_ga_log(struct amd_iommu *iommu); extern void amd_iommu_set_rlookup_table(struct amd_iommu *iommu, u16 devid); #ifdef CONFIG_AMD_IOMMU_DEBUGFS diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 329a406cc37d..c2d80a4e5fb0 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -759,6 +759,30 @@ void amd_iommu_restart_event_logging(struct amd_iommu *iommu) } /* + * This function restarts event logging in case the IOMMU experienced + * an GA log overflow. + */ +void amd_iommu_restart_ga_log(struct amd_iommu *iommu) +{ + u32 status; + + status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET); + if (status & MMIO_STATUS_GALOG_RUN_MASK) + return; + + pr_info_ratelimited("IOMMU GA Log restarting\n"); + + iommu_feature_disable(iommu, CONTROL_GALOG_EN); + iommu_feature_disable(iommu, CONTROL_GAINT_EN); + + writel(MMIO_STATUS_GALOG_OVERFLOW_MASK, + iommu->mmio_base + MMIO_STATUS_OFFSET); + + iommu_feature_enable(iommu, CONTROL_GAINT_EN); + iommu_feature_enable(iommu, CONTROL_GALOG_EN); +} + +/* * This function resets the command buffer if the IOMMU stopped fetching * commands from it. */ diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 4a314647d1f7..dc1ec6849775 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -845,6 +845,7 @@ amd_iommu_set_pci_msi_domain(struct device *dev, struct amd_iommu *iommu) { } (MMIO_STATUS_EVT_OVERFLOW_INT_MASK | \ MMIO_STATUS_EVT_INT_MASK | \ MMIO_STATUS_PPR_INT_MASK | \ + MMIO_STATUS_GALOG_OVERFLOW_MASK | \ MMIO_STATUS_GALOG_INT_MASK) irqreturn_t amd_iommu_int_thread(int irq, void *data) @@ -868,10 +869,16 @@ irqreturn_t amd_iommu_int_thread(int irq, void *data) } #ifdef CONFIG_IRQ_REMAP - if (status & MMIO_STATUS_GALOG_INT_MASK) { + if (status & (MMIO_STATUS_GALOG_INT_MASK | + MMIO_STATUS_GALOG_OVERFLOW_MASK)) { pr_devel("Processing IOMMU GA Log\n"); iommu_poll_ga_log(iommu); } + + if (status & MMIO_STATUS_GALOG_OVERFLOW_MASK) { + pr_info_ratelimited("IOMMU GA Log overflow\n"); + amd_iommu_restart_ga_log(iommu); + } #endif if (status & MMIO_STATUS_EVT_OVERFLOW_INT_MASK) { @@ -2067,7 +2074,7 @@ static struct protection_domain *protection_domain_alloc(unsigned int type) { struct io_pgtable_ops *pgtbl_ops; struct protection_domain *domain; - int pgtable = amd_iommu_pgtable; + int pgtable; int mode = DEFAULT_PGTABLE_LEVEL; int ret; @@ -2084,6 +2091,10 @@ static struct protection_domain *protection_domain_alloc(unsigned int type) mode = PAGE_MODE_NONE; } else if (type == IOMMU_DOMAIN_UNMANAGED) { pgtable = AMD_IOMMU_V1; + } else if (type == IOMMU_DOMAIN_DMA || type == IOMMU_DOMAIN_DMA_FQ) { + pgtable = amd_iommu_pgtable; + } else { + return NULL; } switch (pgtable) { @@ -2118,6 +2129,15 @@ out_err: return NULL; } +static inline u64 dma_max_address(void) +{ + if (amd_iommu_pgtable == AMD_IOMMU_V1) + return ~0ULL; + + /* V2 with 4/5 level page table */ + return ((1ULL << PM_LEVEL_SHIFT(amd_iommu_gpt_level)) - 1); +} + static struct iommu_domain *amd_iommu_domain_alloc(unsigned type) { struct protection_domain *domain; @@ -2134,7 +2154,7 @@ static struct iommu_domain *amd_iommu_domain_alloc(unsigned type) return NULL; domain->domain.geometry.aperture_start = 0; - domain->domain.geometry.aperture_end = ~0ULL; + domain->domain.geometry.aperture_end = dma_max_address(); domain->domain.geometry.force_aperture = true; return &domain->domain; @@ -2387,7 +2407,7 @@ static void amd_iommu_iotlb_sync(struct iommu_domain *domain, unsigned long flags; spin_lock_irqsave(&dom->lock, flags); - domain_flush_pages(dom, gather->start, gather->end - gather->start, 1); + domain_flush_pages(dom, gather->start, gather->end - gather->start + 1, 1); amd_iommu_domain_flush_complete(dom); spin_unlock_irqrestore(&dom->lock, flags); } @@ -3493,8 +3513,7 @@ int amd_iommu_activate_guest_mode(void *data) struct irte_ga *entry = (struct irte_ga *) ir_data->entry; u64 valid; - if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) || - !entry || entry->lo.fields_vapic.guest_mode) + if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) || !entry) return 0; valid = entry->lo.fields_vapic.valid; diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c index ae09c627bc84..c71afda79d64 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c @@ -517,6 +517,7 @@ static const struct of_device_id __maybe_unused qcom_smmu_impl_of_match[] = { { .compatible = "qcom,qcm2290-smmu-500", .data = &qcom_smmu_500_impl0_data }, { .compatible = "qcom,qdu1000-smmu-500", .data = &qcom_smmu_500_impl0_data }, { .compatible = "qcom,sc7180-smmu-500", .data = &qcom_smmu_500_impl0_data }, + { .compatible = "qcom,sc7180-smmu-v2", .data = &qcom_smmu_v2_data }, { .compatible = "qcom,sc7280-smmu-500", .data = &qcom_smmu_500_impl0_data }, { .compatible = "qcom,sc8180x-smmu-500", .data = &qcom_smmu_500_impl0_data }, { .compatible = "qcom,sc8280xp-smmu-500", .data = &qcom_smmu_500_impl0_data }, @@ -561,5 +562,14 @@ struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu) if (match) return qcom_smmu_create(smmu, match->data); + /* + * If you hit this WARN_ON() you are missing an entry in the + * qcom_smmu_impl_of_match[] table, and GPU per-process page- + * tables will be broken. + */ + WARN(of_device_is_compatible(np, "qcom,adreno-smmu"), + "Missing qcom_smmu_impl_of_match entry for: %s", + dev_name(smmu->dev)); + return smmu; } diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index aecc7d154f28..e93906d6e112 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -781,7 +781,8 @@ static void mtk_iommu_flush_iotlb_all(struct iommu_domain *domain) { struct mtk_iommu_domain *dom = to_mtk_domain(domain); - mtk_iommu_tlb_flush_all(dom->bank->parent_data); + if (dom->bank) + mtk_iommu_tlb_flush_all(dom->bank->parent_data); } static void mtk_iommu_iotlb_sync(struct iommu_domain *domain, diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c index ea5a3088bb7e..4054030c3237 100644 --- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -1335,20 +1335,22 @@ static int rk_iommu_probe(struct platform_device *pdev) for (i = 0; i < iommu->num_irq; i++) { int irq = platform_get_irq(pdev, i); - if (irq < 0) - return irq; + if (irq < 0) { + err = irq; + goto err_pm_disable; + } err = devm_request_irq(iommu->dev, irq, rk_iommu_irq, IRQF_SHARED, dev_name(dev), iommu); - if (err) { - pm_runtime_disable(dev); - goto err_remove_sysfs; - } + if (err) + goto err_pm_disable; } dma_set_mask_and_coherent(dev, rk_ops->dma_bit_mask); return 0; +err_pm_disable: + pm_runtime_disable(dev); err_remove_sysfs: iommu_device_sysfs_remove(&iommu->iommu); err_put_group: diff --git a/drivers/irqchip/irq-gic-common.c b/drivers/irqchip/irq-gic-common.c index a610821c8ff2..afd6a1841715 100644 --- a/drivers/irqchip/irq-gic-common.c +++ b/drivers/irqchip/irq-gic-common.c @@ -16,7 +16,13 @@ void gic_enable_of_quirks(const struct device_node *np, const struct gic_quirk *quirks, void *data) { for (; quirks->desc; quirks++) { - if (!of_device_is_compatible(np, quirks->compatible)) + if (!quirks->compatible && !quirks->property) + continue; + if (quirks->compatible && + !of_device_is_compatible(np, quirks->compatible)) + continue; + if (quirks->property && + !of_property_read_bool(np, quirks->property)) continue; if (quirks->init(data)) pr_info("GIC: enabling workaround for %s\n", @@ -28,7 +34,7 @@ void gic_enable_quirks(u32 iidr, const struct gic_quirk *quirks, void *data) { for (; quirks->desc; quirks++) { - if (quirks->compatible) + if (quirks->compatible || quirks->property) continue; if (quirks->iidr != (quirks->mask & iidr)) continue; diff --git a/drivers/irqchip/irq-gic-common.h b/drivers/irqchip/irq-gic-common.h index 27e3d4ed4f32..3db4592cda1c 100644 --- a/drivers/irqchip/irq-gic-common.h +++ b/drivers/irqchip/irq-gic-common.h @@ -13,6 +13,7 @@ struct gic_quirk { const char *desc; const char *compatible; + const char *property; bool (*init)(void *data); u32 iidr; u32 mask; diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 6fcee221f201..a605aa79435a 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -39,6 +39,7 @@ #define FLAGS_WORKAROUND_GICR_WAKER_MSM8996 (1ULL << 0) #define FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539 (1ULL << 1) +#define FLAGS_WORKAROUND_MTK_GICR_SAVE (1ULL << 2) #define GIC_IRQ_TYPE_PARTITION (GIC_IRQ_TYPE_LPI + 1) @@ -1720,6 +1721,15 @@ static bool gic_enable_quirk_msm8996(void *data) return true; } +static bool gic_enable_quirk_mtk_gicr(void *data) +{ + struct gic_chip_data *d = data; + + d->flags |= FLAGS_WORKAROUND_MTK_GICR_SAVE; + + return true; +} + static bool gic_enable_quirk_cavium_38539(void *data) { struct gic_chip_data *d = data; @@ -1793,6 +1803,11 @@ static const struct gic_quirk gic_quirks[] = { .init = gic_enable_quirk_msm8996, }, { + .desc = "GICv3: Mediatek Chromebook GICR save problem", + .property = "mediatek,broken-save-restore-fw", + .init = gic_enable_quirk_mtk_gicr, + }, + { .desc = "GICv3: HIP06 erratum 161010803", .iidr = 0x0204043b, .mask = 0xffffffff, @@ -1834,6 +1849,11 @@ static void gic_enable_nmi_support(void) if (!gic_prio_masking_enabled()) return; + if (gic_data.flags & FLAGS_WORKAROUND_MTK_GICR_SAVE) { + pr_warn("Skipping NMI enable due to firmware issues\n"); + return; + } + ppi_nmi_refs = kcalloc(gic_data.ppi_nr, sizeof(*ppi_nmi_refs), GFP_KERNEL); if (!ppi_nmi_refs) return; diff --git a/drivers/irqchip/irq-mbigen.c b/drivers/irqchip/irq-mbigen.c index eada5e0e3eb9..5101a3fb11df 100644 --- a/drivers/irqchip/irq-mbigen.c +++ b/drivers/irqchip/irq-mbigen.c @@ -240,26 +240,27 @@ static int mbigen_of_create_domain(struct platform_device *pdev, struct irq_domain *domain; struct device_node *np; u32 num_pins; + int ret = 0; + + parent = bus_get_dev_root(&platform_bus_type); + if (!parent) + return -ENODEV; for_each_child_of_node(pdev->dev.of_node, np) { if (!of_property_read_bool(np, "interrupt-controller")) continue; - parent = bus_get_dev_root(&platform_bus_type); - if (parent) { - child = of_platform_device_create(np, NULL, parent); - put_device(parent); - if (!child) { - of_node_put(np); - return -ENOMEM; - } + child = of_platform_device_create(np, NULL, parent); + if (!child) { + ret = -ENOMEM; + break; } if (of_property_read_u32(child->dev.of_node, "num-pins", &num_pins) < 0) { dev_err(&pdev->dev, "No num-pins property\n"); - of_node_put(np); - return -EINVAL; + ret = -EINVAL; + break; } domain = platform_msi_create_device_domain(&child->dev, num_pins, @@ -267,12 +268,16 @@ static int mbigen_of_create_domain(struct platform_device *pdev, &mbigen_domain_ops, mgn_chip); if (!domain) { - of_node_put(np); - return -ENOMEM; + ret = -ENOMEM; + break; } } - return 0; + put_device(parent); + if (ret) + of_node_put(np); + + return ret; } #ifdef CONFIG_ACPI diff --git a/drivers/irqchip/irq-meson-gpio.c b/drivers/irqchip/irq-meson-gpio.c index 2aaa9aad3e87..7da18ef95211 100644 --- a/drivers/irqchip/irq-meson-gpio.c +++ b/drivers/irqchip/irq-meson-gpio.c @@ -150,7 +150,7 @@ static const struct meson_gpio_irq_params s4_params = { INIT_MESON_S4_COMMON_DATA(82) }; -static const struct of_device_id meson_irq_gpio_matches[] = { +static const struct of_device_id meson_irq_gpio_matches[] __maybe_unused = { { .compatible = "amlogic,meson8-gpio-intc", .data = &meson8_params }, { .compatible = "amlogic,meson8b-gpio-intc", .data = &meson8b_params }, { .compatible = "amlogic,meson-gxbb-gpio-intc", .data = &gxbb_params }, diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index 046c355e120b..6d5ecc10a870 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -50,7 +50,7 @@ void __iomem *mips_gic_base; static DEFINE_PER_CPU_READ_MOSTLY(unsigned long[GIC_MAX_LONGS], pcpu_masks); -static DEFINE_SPINLOCK(gic_lock); +static DEFINE_RAW_SPINLOCK(gic_lock); static struct irq_domain *gic_irq_domain; static int gic_shared_intrs; static unsigned int gic_cpu_pin; @@ -210,7 +210,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type) irq = GIC_HWIRQ_TO_SHARED(d->hwirq); - spin_lock_irqsave(&gic_lock, flags); + raw_spin_lock_irqsave(&gic_lock, flags); switch (type & IRQ_TYPE_SENSE_MASK) { case IRQ_TYPE_EDGE_FALLING: pol = GIC_POL_FALLING_EDGE; @@ -250,7 +250,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type) else irq_set_chip_handler_name_locked(d, &gic_level_irq_controller, handle_level_irq, NULL); - spin_unlock_irqrestore(&gic_lock, flags); + raw_spin_unlock_irqrestore(&gic_lock, flags); return 0; } @@ -268,7 +268,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *cpumask, return -EINVAL; /* Assumption : cpumask refers to a single CPU */ - spin_lock_irqsave(&gic_lock, flags); + raw_spin_lock_irqsave(&gic_lock, flags); /* Re-route this IRQ */ write_gic_map_vp(irq, BIT(mips_cm_vp_id(cpu))); @@ -279,7 +279,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *cpumask, set_bit(irq, per_cpu_ptr(pcpu_masks, cpu)); irq_data_update_effective_affinity(d, cpumask_of(cpu)); - spin_unlock_irqrestore(&gic_lock, flags); + raw_spin_unlock_irqrestore(&gic_lock, flags); return IRQ_SET_MASK_OK; } @@ -357,12 +357,12 @@ static void gic_mask_local_irq_all_vpes(struct irq_data *d) cd = irq_data_get_irq_chip_data(d); cd->mask = false; - spin_lock_irqsave(&gic_lock, flags); + raw_spin_lock_irqsave(&gic_lock, flags); for_each_online_cpu(cpu) { write_gic_vl_other(mips_cm_vp_id(cpu)); write_gic_vo_rmask(BIT(intr)); } - spin_unlock_irqrestore(&gic_lock, flags); + raw_spin_unlock_irqrestore(&gic_lock, flags); } static void gic_unmask_local_irq_all_vpes(struct irq_data *d) @@ -375,12 +375,12 @@ static void gic_unmask_local_irq_all_vpes(struct irq_data *d) cd = irq_data_get_irq_chip_data(d); cd->mask = true; - spin_lock_irqsave(&gic_lock, flags); + raw_spin_lock_irqsave(&gic_lock, flags); for_each_online_cpu(cpu) { write_gic_vl_other(mips_cm_vp_id(cpu)); write_gic_vo_smask(BIT(intr)); } - spin_unlock_irqrestore(&gic_lock, flags); + raw_spin_unlock_irqrestore(&gic_lock, flags); } static void gic_all_vpes_irq_cpu_online(void) @@ -393,19 +393,21 @@ static void gic_all_vpes_irq_cpu_online(void) unsigned long flags; int i; - spin_lock_irqsave(&gic_lock, flags); + raw_spin_lock_irqsave(&gic_lock, flags); for (i = 0; i < ARRAY_SIZE(local_intrs); i++) { unsigned int intr = local_intrs[i]; struct gic_all_vpes_chip_data *cd; + if (!gic_local_irq_is_routable(intr)) + continue; cd = &gic_all_vpes_chip_data[intr]; write_gic_vl_map(mips_gic_vx_map_reg(intr), cd->map); if (cd->mask) write_gic_vl_smask(BIT(intr)); } - spin_unlock_irqrestore(&gic_lock, flags); + raw_spin_unlock_irqrestore(&gic_lock, flags); } static struct irq_chip gic_all_vpes_local_irq_controller = { @@ -435,11 +437,11 @@ static int gic_shared_irq_domain_map(struct irq_domain *d, unsigned int virq, data = irq_get_irq_data(virq); - spin_lock_irqsave(&gic_lock, flags); + raw_spin_lock_irqsave(&gic_lock, flags); write_gic_map_pin(intr, GIC_MAP_PIN_MAP_TO_PIN | gic_cpu_pin); write_gic_map_vp(intr, BIT(mips_cm_vp_id(cpu))); irq_data_update_effective_affinity(data, cpumask_of(cpu)); - spin_unlock_irqrestore(&gic_lock, flags); + raw_spin_unlock_irqrestore(&gic_lock, flags); return 0; } @@ -531,12 +533,12 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq, if (!gic_local_irq_is_routable(intr)) return -EPERM; - spin_lock_irqsave(&gic_lock, flags); + raw_spin_lock_irqsave(&gic_lock, flags); for_each_online_cpu(cpu) { write_gic_vl_other(mips_cm_vp_id(cpu)); write_gic_vo_map(mips_gic_vx_map_reg(intr), map); } - spin_unlock_irqrestore(&gic_lock, flags); + raw_spin_unlock_irqrestore(&gic_lock, flags); return 0; } diff --git a/drivers/leds/rgb/leds-qcom-lpg.c b/drivers/leds/rgb/leds-qcom-lpg.c index 55a037234df1..1c849814a491 100644 --- a/drivers/leds/rgb/leds-qcom-lpg.c +++ b/drivers/leds/rgb/leds-qcom-lpg.c @@ -312,14 +312,14 @@ static int lpg_calc_freq(struct lpg_channel *chan, uint64_t period) max_res = LPG_RESOLUTION_9BIT; } - min_period = (u64)NSEC_PER_SEC * - div64_u64((1 << pwm_resolution_arr[0]), clk_rate_arr[clk_len - 1]); + min_period = div64_u64((u64)NSEC_PER_SEC * (1 << pwm_resolution_arr[0]), + clk_rate_arr[clk_len - 1]); if (period <= min_period) return -EINVAL; /* Limit period to largest possible value, to avoid overflows */ - max_period = (u64)NSEC_PER_SEC * max_res * LPG_MAX_PREDIV * - div64_u64((1 << LPG_MAX_M), 1024); + max_period = div64_u64((u64)NSEC_PER_SEC * max_res * LPG_MAX_PREDIV * (1 << LPG_MAX_M), + 1024); if (period > max_period) period = max_period; diff --git a/drivers/leds/trigger/ledtrig-netdev.c b/drivers/leds/trigger/ledtrig-netdev.c index d5e774d83021..b0a6f2749552 100644 --- a/drivers/leds/trigger/ledtrig-netdev.c +++ b/drivers/leds/trigger/ledtrig-netdev.c @@ -20,10 +20,12 @@ #include <linux/list.h> #include <linux/module.h> #include <linux/netdevice.h> -#include <linux/spinlock.h> +#include <linux/mutex.h> #include <linux/timer.h> #include "../leds.h" +#define NETDEV_LED_DEFAULT_INTERVAL 50 + /* * Configurable sysfs attributes: * @@ -37,7 +39,7 @@ */ struct led_netdev_data { - spinlock_t lock; + struct mutex lock; struct delayed_work work; struct notifier_block notifier; @@ -50,16 +52,8 @@ struct led_netdev_data { unsigned int last_activity; unsigned long mode; -#define NETDEV_LED_LINK 0 -#define NETDEV_LED_TX 1 -#define NETDEV_LED_RX 2 -#define NETDEV_LED_MODE_LINKUP 3 -}; - -enum netdev_led_attr { - NETDEV_ATTR_LINK, - NETDEV_ATTR_TX, - NETDEV_ATTR_RX + bool carrier_link_up; + bool hw_control; }; static void set_baseline_state(struct led_netdev_data *trigger_data) @@ -67,16 +61,23 @@ static void set_baseline_state(struct led_netdev_data *trigger_data) int current_brightness; struct led_classdev *led_cdev = trigger_data->led_cdev; + /* Already validated, hw control is possible with the requested mode */ + if (trigger_data->hw_control) { + led_cdev->hw_control_set(led_cdev, trigger_data->mode); + + return; + } + current_brightness = led_cdev->brightness; if (current_brightness) led_cdev->blink_brightness = current_brightness; if (!led_cdev->blink_brightness) led_cdev->blink_brightness = led_cdev->max_brightness; - if (!test_bit(NETDEV_LED_MODE_LINKUP, &trigger_data->mode)) + if (!trigger_data->carrier_link_up) { led_set_brightness(led_cdev, LED_OFF); - else { - if (test_bit(NETDEV_LED_LINK, &trigger_data->mode)) + } else { + if (test_bit(TRIGGER_NETDEV_LINK, &trigger_data->mode)) led_set_brightness(led_cdev, led_cdev->blink_brightness); else @@ -85,44 +86,107 @@ static void set_baseline_state(struct led_netdev_data *trigger_data) /* If we are looking for RX/TX start periodically * checking stats */ - if (test_bit(NETDEV_LED_TX, &trigger_data->mode) || - test_bit(NETDEV_LED_RX, &trigger_data->mode)) + if (test_bit(TRIGGER_NETDEV_TX, &trigger_data->mode) || + test_bit(TRIGGER_NETDEV_RX, &trigger_data->mode)) schedule_delayed_work(&trigger_data->work, 0); } } +static bool supports_hw_control(struct led_classdev *led_cdev) +{ + if (!led_cdev->hw_control_get || !led_cdev->hw_control_set || + !led_cdev->hw_control_is_supported) + return false; + + return !strcmp(led_cdev->hw_control_trigger, led_cdev->trigger->name); +} + +/* + * Validate the configured netdev is the same as the one associated with + * the LED driver in hw control. + */ +static bool validate_net_dev(struct led_classdev *led_cdev, + struct net_device *net_dev) +{ + struct device *dev = led_cdev->hw_control_get_device(led_cdev); + struct net_device *ndev; + + if (!dev) + return false; + + ndev = to_net_dev(dev); + + return ndev == net_dev; +} + +static bool can_hw_control(struct led_netdev_data *trigger_data) +{ + unsigned long default_interval = msecs_to_jiffies(NETDEV_LED_DEFAULT_INTERVAL); + unsigned int interval = atomic_read(&trigger_data->interval); + struct led_classdev *led_cdev = trigger_data->led_cdev; + int ret; + + if (!supports_hw_control(led_cdev)) + return false; + + /* + * Interval must be set to the default + * value. Any different value is rejected if in hw + * control. + */ + if (interval != default_interval) + return false; + + /* + * net_dev must be set with hw control, otherwise no + * blinking can be happening and there is nothing to + * offloaded. Additionally, for hw control to be + * valid, the configured netdev must be the same as + * netdev associated to the LED. + */ + if (!validate_net_dev(led_cdev, trigger_data->net_dev)) + return false; + + /* Check if the requested mode is supported */ + ret = led_cdev->hw_control_is_supported(led_cdev, trigger_data->mode); + /* Fall back to software blinking if not supported */ + if (ret == -EOPNOTSUPP) + return false; + if (ret) { + dev_warn(led_cdev->dev, + "Current mode check failed with error %d\n", ret); + return false; + } + + return true; +} + static ssize_t device_name_show(struct device *dev, struct device_attribute *attr, char *buf) { struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev); ssize_t len; - spin_lock_bh(&trigger_data->lock); + mutex_lock(&trigger_data->lock); len = sprintf(buf, "%s\n", trigger_data->device_name); - spin_unlock_bh(&trigger_data->lock); + mutex_unlock(&trigger_data->lock); return len; } -static ssize_t device_name_store(struct device *dev, - struct device_attribute *attr, const char *buf, - size_t size) +static int set_device_name(struct led_netdev_data *trigger_data, + const char *name, size_t size) { - struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev); - - if (size >= IFNAMSIZ) - return -EINVAL; - cancel_delayed_work_sync(&trigger_data->work); - spin_lock_bh(&trigger_data->lock); + mutex_lock(&trigger_data->lock); if (trigger_data->net_dev) { dev_put(trigger_data->net_dev); trigger_data->net_dev = NULL; } - memcpy(trigger_data->device_name, buf, size); + memcpy(trigger_data->device_name, name, size); trigger_data->device_name[size] = 0; if (size > 0 && trigger_data->device_name[size - 1] == '\n') trigger_data->device_name[size - 1] = 0; @@ -131,36 +195,48 @@ static ssize_t device_name_store(struct device *dev, trigger_data->net_dev = dev_get_by_name(&init_net, trigger_data->device_name); - clear_bit(NETDEV_LED_MODE_LINKUP, &trigger_data->mode); + trigger_data->carrier_link_up = false; if (trigger_data->net_dev != NULL) - if (netif_carrier_ok(trigger_data->net_dev)) - set_bit(NETDEV_LED_MODE_LINKUP, &trigger_data->mode); + trigger_data->carrier_link_up = netif_carrier_ok(trigger_data->net_dev); trigger_data->last_activity = 0; set_baseline_state(trigger_data); - spin_unlock_bh(&trigger_data->lock); + mutex_unlock(&trigger_data->lock); + return 0; +} + +static ssize_t device_name_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t size) +{ + struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev); + int ret; + + if (size >= IFNAMSIZ) + return -EINVAL; + + ret = set_device_name(trigger_data, buf, size); + + if (ret < 0) + return ret; return size; } static DEVICE_ATTR_RW(device_name); static ssize_t netdev_led_attr_show(struct device *dev, char *buf, - enum netdev_led_attr attr) + enum led_trigger_netdev_modes attr) { struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev); int bit; switch (attr) { - case NETDEV_ATTR_LINK: - bit = NETDEV_LED_LINK; - break; - case NETDEV_ATTR_TX: - bit = NETDEV_LED_TX; - break; - case NETDEV_ATTR_RX: - bit = NETDEV_LED_RX; + case TRIGGER_NETDEV_LINK: + case TRIGGER_NETDEV_TX: + case TRIGGER_NETDEV_RX: + bit = attr; break; default: return -EINVAL; @@ -170,7 +246,7 @@ static ssize_t netdev_led_attr_show(struct device *dev, char *buf, } static ssize_t netdev_led_attr_store(struct device *dev, const char *buf, - size_t size, enum netdev_led_attr attr) + size_t size, enum led_trigger_netdev_modes attr) { struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev); unsigned long state; @@ -182,14 +258,10 @@ static ssize_t netdev_led_attr_store(struct device *dev, const char *buf, return ret; switch (attr) { - case NETDEV_ATTR_LINK: - bit = NETDEV_LED_LINK; - break; - case NETDEV_ATTR_TX: - bit = NETDEV_LED_TX; - break; - case NETDEV_ATTR_RX: - bit = NETDEV_LED_RX; + case TRIGGER_NETDEV_LINK: + case TRIGGER_NETDEV_TX: + case TRIGGER_NETDEV_RX: + bit = attr; break; default: return -EINVAL; @@ -202,52 +274,29 @@ static ssize_t netdev_led_attr_store(struct device *dev, const char *buf, else clear_bit(bit, &trigger_data->mode); + trigger_data->hw_control = can_hw_control(trigger_data); + set_baseline_state(trigger_data); return size; } -static ssize_t link_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - return netdev_led_attr_show(dev, buf, NETDEV_ATTR_LINK); -} - -static ssize_t link_store(struct device *dev, - struct device_attribute *attr, const char *buf, size_t size) -{ - return netdev_led_attr_store(dev, buf, size, NETDEV_ATTR_LINK); -} - -static DEVICE_ATTR_RW(link); - -static ssize_t tx_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - return netdev_led_attr_show(dev, buf, NETDEV_ATTR_TX); -} - -static ssize_t tx_store(struct device *dev, - struct device_attribute *attr, const char *buf, size_t size) -{ - return netdev_led_attr_store(dev, buf, size, NETDEV_ATTR_TX); -} - -static DEVICE_ATTR_RW(tx); - -static ssize_t rx_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - return netdev_led_attr_show(dev, buf, NETDEV_ATTR_RX); -} - -static ssize_t rx_store(struct device *dev, - struct device_attribute *attr, const char *buf, size_t size) -{ - return netdev_led_attr_store(dev, buf, size, NETDEV_ATTR_RX); -} - -static DEVICE_ATTR_RW(rx); +#define DEFINE_NETDEV_TRIGGER(trigger_name, trigger) \ + static ssize_t trigger_name##_show(struct device *dev, \ + struct device_attribute *attr, char *buf) \ + { \ + return netdev_led_attr_show(dev, buf, trigger); \ + } \ + static ssize_t trigger_name##_store(struct device *dev, \ + struct device_attribute *attr, const char *buf, size_t size) \ + { \ + return netdev_led_attr_store(dev, buf, size, trigger); \ + } \ + static DEVICE_ATTR_RW(trigger_name) + +DEFINE_NETDEV_TRIGGER(link, TRIGGER_NETDEV_LINK); +DEFINE_NETDEV_TRIGGER(tx, TRIGGER_NETDEV_TX); +DEFINE_NETDEV_TRIGGER(rx, TRIGGER_NETDEV_RX); static ssize_t interval_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -266,6 +315,9 @@ static ssize_t interval_store(struct device *dev, unsigned long value; int ret; + if (trigger_data->hw_control) + return -EINVAL; + ret = kstrtoul(buf, 0, &value); if (ret) return ret; @@ -313,11 +365,13 @@ static int netdev_trig_notify(struct notifier_block *nb, cancel_delayed_work_sync(&trigger_data->work); - spin_lock_bh(&trigger_data->lock); + mutex_lock(&trigger_data->lock); - clear_bit(NETDEV_LED_MODE_LINKUP, &trigger_data->mode); + trigger_data->carrier_link_up = false; switch (evt) { case NETDEV_CHANGENAME: + trigger_data->carrier_link_up = netif_carrier_ok(dev); + fallthrough; case NETDEV_REGISTER: if (trigger_data->net_dev) dev_put(trigger_data->net_dev); @@ -330,14 +384,13 @@ static int netdev_trig_notify(struct notifier_block *nb, break; case NETDEV_UP: case NETDEV_CHANGE: - if (netif_carrier_ok(dev)) - set_bit(NETDEV_LED_MODE_LINKUP, &trigger_data->mode); + trigger_data->carrier_link_up = netif_carrier_ok(dev); break; } set_baseline_state(trigger_data); - spin_unlock_bh(&trigger_data->lock); + mutex_unlock(&trigger_data->lock); return NOTIFY_DONE; } @@ -360,21 +413,21 @@ static void netdev_trig_work(struct work_struct *work) } /* If we are not looking for RX/TX then return */ - if (!test_bit(NETDEV_LED_TX, &trigger_data->mode) && - !test_bit(NETDEV_LED_RX, &trigger_data->mode)) + if (!test_bit(TRIGGER_NETDEV_TX, &trigger_data->mode) && + !test_bit(TRIGGER_NETDEV_RX, &trigger_data->mode)) return; dev_stats = dev_get_stats(trigger_data->net_dev, &temp); new_activity = - (test_bit(NETDEV_LED_TX, &trigger_data->mode) ? + (test_bit(TRIGGER_NETDEV_TX, &trigger_data->mode) ? dev_stats->tx_packets : 0) + - (test_bit(NETDEV_LED_RX, &trigger_data->mode) ? + (test_bit(TRIGGER_NETDEV_RX, &trigger_data->mode) ? dev_stats->rx_packets : 0); if (trigger_data->last_activity != new_activity) { led_stop_software_blink(trigger_data->led_cdev); - invert = test_bit(NETDEV_LED_LINK, &trigger_data->mode); + invert = test_bit(TRIGGER_NETDEV_LINK, &trigger_data->mode); interval = jiffies_to_msecs( atomic_read(&trigger_data->interval)); /* base state is ON (link present) */ @@ -392,13 +445,15 @@ static void netdev_trig_work(struct work_struct *work) static int netdev_trig_activate(struct led_classdev *led_cdev) { struct led_netdev_data *trigger_data; + unsigned long mode; + struct device *dev; int rc; trigger_data = kzalloc(sizeof(struct led_netdev_data), GFP_KERNEL); if (!trigger_data) return -ENOMEM; - spin_lock_init(&trigger_data->lock); + mutex_init(&trigger_data->lock); trigger_data->notifier.notifier_call = netdev_trig_notify; trigger_data->notifier.priority = 10; @@ -410,9 +465,24 @@ static int netdev_trig_activate(struct led_classdev *led_cdev) trigger_data->device_name[0] = 0; trigger_data->mode = 0; - atomic_set(&trigger_data->interval, msecs_to_jiffies(50)); + atomic_set(&trigger_data->interval, msecs_to_jiffies(NETDEV_LED_DEFAULT_INTERVAL)); trigger_data->last_activity = 0; + /* Check if hw control is active by default on the LED. + * Init already enabled mode in hw control. + */ + if (supports_hw_control(led_cdev) && + !led_cdev->hw_control_get(led_cdev, &mode)) { + dev = led_cdev->hw_control_get_device(led_cdev); + if (dev) { + const char *name = dev_name(dev); + + set_device_name(trigger_data, name, strlen(name)); + trigger_data->hw_control = true; + trigger_data->mode = mode; + } + } + led_set_trigger_data(led_cdev, trigger_data); rc = register_netdevice_notifier(&trigger_data->notifier); diff --git a/drivers/mailbox/mailbox-test.c b/drivers/mailbox/mailbox-test.c index c4a705c30331..fc6a12a51b40 100644 --- a/drivers/mailbox/mailbox-test.c +++ b/drivers/mailbox/mailbox-test.c @@ -98,6 +98,7 @@ static ssize_t mbox_test_message_write(struct file *filp, size_t count, loff_t *ppos) { struct mbox_test_device *tdev = filp->private_data; + char *message; void *data; int ret; @@ -113,12 +114,13 @@ static ssize_t mbox_test_message_write(struct file *filp, return -EINVAL; } - mutex_lock(&tdev->mutex); - - tdev->message = kzalloc(MBOX_MAX_MSG_LEN, GFP_KERNEL); - if (!tdev->message) + message = kzalloc(MBOX_MAX_MSG_LEN, GFP_KERNEL); + if (!message) return -ENOMEM; + mutex_lock(&tdev->mutex); + + tdev->message = message; ret = copy_from_user(tdev->message, userbuf, count); if (ret) { ret = -EFAULT; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 4739ed891e75..9ea285fbc4a6 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5516,7 +5516,7 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio) sector = raid5_compute_sector(conf, raid_bio->bi_iter.bi_sector, 0, &dd_idx, NULL); - end_sector = bio_end_sector(raid_bio); + end_sector = sector + bio_sectors(raid_bio); rcu_read_lock(); if (r5c_big_stripe_cached(conf, sector)) diff --git a/drivers/media/cec/core/cec-adap.c b/drivers/media/cec/core/cec-adap.c index 769ea6b2e1d0..241b1621b197 100644 --- a/drivers/media/cec/core/cec-adap.c +++ b/drivers/media/cec/core/cec-adap.c @@ -1091,7 +1091,8 @@ void cec_received_msg_ts(struct cec_adapter *adap, mutex_lock(&adap->lock); dprintk(2, "%s: %*ph\n", __func__, msg->len, msg->msg); - adap->last_initiator = 0xff; + if (!adap->transmit_in_progress) + adap->last_initiator = 0xff; /* Check if this message was for us (directed or broadcast). */ if (!cec_msg_is_broadcast(msg)) { @@ -1585,7 +1586,7 @@ static void cec_claim_log_addrs(struct cec_adapter *adap, bool block) * * This function is called with adap->lock held. */ -static int cec_adap_enable(struct cec_adapter *adap) +int cec_adap_enable(struct cec_adapter *adap) { bool enable; int ret = 0; @@ -1595,6 +1596,9 @@ static int cec_adap_enable(struct cec_adapter *adap) if (adap->needs_hpd) enable = enable && adap->phys_addr != CEC_PHYS_ADDR_INVALID; + if (adap->devnode.unregistered) + enable = false; + if (enable == adap->is_enabled) return 0; diff --git a/drivers/media/cec/core/cec-core.c b/drivers/media/cec/core/cec-core.c index af358e901b5f..7e153c5cad04 100644 --- a/drivers/media/cec/core/cec-core.c +++ b/drivers/media/cec/core/cec-core.c @@ -191,6 +191,8 @@ static void cec_devnode_unregister(struct cec_adapter *adap) mutex_lock(&adap->lock); __cec_s_phys_addr(adap, CEC_PHYS_ADDR_INVALID, false); __cec_s_log_addrs(adap, NULL, false); + // Disable the adapter (since adap->devnode.unregistered is true) + cec_adap_enable(adap); mutex_unlock(&adap->lock); cdev_device_del(&devnode->cdev, &devnode->dev); diff --git a/drivers/media/cec/core/cec-priv.h b/drivers/media/cec/core/cec-priv.h index b78df931aa74..ed1f8c67626b 100644 --- a/drivers/media/cec/core/cec-priv.h +++ b/drivers/media/cec/core/cec-priv.h @@ -47,6 +47,7 @@ int cec_monitor_pin_cnt_inc(struct cec_adapter *adap); void cec_monitor_pin_cnt_dec(struct cec_adapter *adap); int cec_adap_status(struct seq_file *file, void *priv); int cec_thread_func(void *_adap); +int cec_adap_enable(struct cec_adapter *adap); void __cec_s_phys_addr(struct cec_adapter *adap, u16 phys_addr, bool block); int __cec_s_log_addrs(struct cec_adapter *adap, struct cec_log_addrs *log_addrs, bool block); diff --git a/drivers/media/dvb-core/dvb_ca_en50221.c b/drivers/media/dvb-core/dvb_ca_en50221.c index c2d2792227f8..baf64540dc00 100644 --- a/drivers/media/dvb-core/dvb_ca_en50221.c +++ b/drivers/media/dvb-core/dvb_ca_en50221.c @@ -151,6 +151,12 @@ struct dvb_ca_private { /* mutex serializing ioctls */ struct mutex ioctl_mutex; + + /* A mutex used when a device is disconnected */ + struct mutex remove_mutex; + + /* Whether the device is disconnected */ + int exit; }; static void dvb_ca_private_free(struct dvb_ca_private *ca) @@ -187,7 +193,7 @@ static void dvb_ca_en50221_thread_wakeup(struct dvb_ca_private *ca); static int dvb_ca_en50221_read_data(struct dvb_ca_private *ca, int slot, u8 *ebuf, int ecount); static int dvb_ca_en50221_write_data(struct dvb_ca_private *ca, int slot, - u8 *ebuf, int ecount); + u8 *ebuf, int ecount, int size_write_flag); /** * findstr - Safely find needle in haystack. @@ -370,7 +376,7 @@ static int dvb_ca_en50221_link_init(struct dvb_ca_private *ca, int slot) ret = dvb_ca_en50221_wait_if_status(ca, slot, STATUSREG_FR, HZ / 10); if (ret) return ret; - ret = dvb_ca_en50221_write_data(ca, slot, buf, 2); + ret = dvb_ca_en50221_write_data(ca, slot, buf, 2, CMDREG_SW); if (ret != 2) return -EIO; ret = ca->pub->write_cam_control(ca->pub, slot, CTRLIF_COMMAND, IRQEN); @@ -778,11 +784,13 @@ exit: * @buf: The data in this buffer is treated as a complete link-level packet to * be written. * @bytes_write: Size of ebuf. + * @size_write_flag: A flag on Command Register which says whether the link size + * information will be writen or not. * * return: Number of bytes written, or < 0 on error. */ static int dvb_ca_en50221_write_data(struct dvb_ca_private *ca, int slot, - u8 *buf, int bytes_write) + u8 *buf, int bytes_write, int size_write_flag) { struct dvb_ca_slot *sl = &ca->slot_info[slot]; int status; @@ -817,7 +825,7 @@ static int dvb_ca_en50221_write_data(struct dvb_ca_private *ca, int slot, /* OK, set HC bit */ status = ca->pub->write_cam_control(ca->pub, slot, CTRLIF_COMMAND, - IRQEN | CMDREG_HC); + IRQEN | CMDREG_HC | size_write_flag); if (status) goto exit; @@ -1508,7 +1516,7 @@ static ssize_t dvb_ca_en50221_io_write(struct file *file, mutex_lock(&sl->slot_lock); status = dvb_ca_en50221_write_data(ca, slot, fragbuf, - fraglen + 2); + fraglen + 2, 0); mutex_unlock(&sl->slot_lock); if (status == (fraglen + 2)) { written = 1; @@ -1709,12 +1717,22 @@ static int dvb_ca_en50221_io_open(struct inode *inode, struct file *file) dprintk("%s\n", __func__); - if (!try_module_get(ca->pub->owner)) + mutex_lock(&ca->remove_mutex); + + if (ca->exit) { + mutex_unlock(&ca->remove_mutex); + return -ENODEV; + } + + if (!try_module_get(ca->pub->owner)) { + mutex_unlock(&ca->remove_mutex); return -EIO; + } err = dvb_generic_open(inode, file); if (err < 0) { module_put(ca->pub->owner); + mutex_unlock(&ca->remove_mutex); return err; } @@ -1739,6 +1757,7 @@ static int dvb_ca_en50221_io_open(struct inode *inode, struct file *file) dvb_ca_private_get(ca); + mutex_unlock(&ca->remove_mutex); return 0; } @@ -1758,6 +1777,8 @@ static int dvb_ca_en50221_io_release(struct inode *inode, struct file *file) dprintk("%s\n", __func__); + mutex_lock(&ca->remove_mutex); + /* mark the CA device as closed */ ca->open = 0; dvb_ca_en50221_thread_update_delay(ca); @@ -1768,6 +1789,13 @@ static int dvb_ca_en50221_io_release(struct inode *inode, struct file *file) dvb_ca_private_put(ca); + if (dvbdev->users == 1 && ca->exit == 1) { + mutex_unlock(&ca->remove_mutex); + wake_up(&dvbdev->wait_queue); + } else { + mutex_unlock(&ca->remove_mutex); + } + return err; } @@ -1891,6 +1919,7 @@ int dvb_ca_en50221_init(struct dvb_adapter *dvb_adapter, } mutex_init(&ca->ioctl_mutex); + mutex_init(&ca->remove_mutex); if (signal_pending(current)) { ret = -EINTR; @@ -1933,6 +1962,14 @@ void dvb_ca_en50221_release(struct dvb_ca_en50221 *pubca) dprintk("%s\n", __func__); + mutex_lock(&ca->remove_mutex); + ca->exit = 1; + mutex_unlock(&ca->remove_mutex); + + if (ca->dvbdev->users < 1) + wait_event(ca->dvbdev->wait_queue, + ca->dvbdev->users == 1); + /* shutdown the thread if there was one */ kthread_stop(ca->thread); diff --git a/drivers/media/dvb-core/dvb_demux.c b/drivers/media/dvb-core/dvb_demux.c index 398c86279b5b..7c4d86bfdd6c 100644 --- a/drivers/media/dvb-core/dvb_demux.c +++ b/drivers/media/dvb-core/dvb_demux.c @@ -115,12 +115,12 @@ static inline int dvb_dmx_swfilter_payload(struct dvb_demux_feed *feed, cc = buf[3] & 0x0f; ccok = ((feed->cc + 1) & 0x0f) == cc; - feed->cc = cc; if (!ccok) { set_buf_flags(feed, DMX_BUFFER_FLAG_DISCONTINUITY_DETECTED); dprintk_sect_loss("missed packet: %d instead of %d!\n", cc, (feed->cc + 1) & 0x0f); } + feed->cc = cc; if (buf[1] & 0x40) // PUSI ? feed->peslen = 0xfffa; @@ -300,7 +300,6 @@ static int dvb_dmx_swfilter_section_packet(struct dvb_demux_feed *feed, cc = buf[3] & 0x0f; ccok = ((feed->cc + 1) & 0x0f) == cc; - feed->cc = cc; if (buf[3] & 0x20) { /* adaption field present, check for discontinuity_indicator */ @@ -336,6 +335,7 @@ static int dvb_dmx_swfilter_section_packet(struct dvb_demux_feed *feed, feed->pusi_seen = false; dvb_dmx_swfilter_section_new(feed); } + feed->cc = cc; if (buf[1] & 0x40) { /* PUSI=1 (is set), section boundary is here */ diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c index cc0a789f09ae..bc6950a5740f 100644 --- a/drivers/media/dvb-core/dvb_frontend.c +++ b/drivers/media/dvb-core/dvb_frontend.c @@ -293,14 +293,22 @@ static int dvb_frontend_get_event(struct dvb_frontend *fe, } if (events->eventw == events->eventr) { - int ret; + struct wait_queue_entry wait; + int ret = 0; if (flags & O_NONBLOCK) return -EWOULDBLOCK; - ret = wait_event_interruptible(events->wait_queue, - dvb_frontend_test_event(fepriv, events)); - + init_waitqueue_entry(&wait, current); + add_wait_queue(&events->wait_queue, &wait); + while (!dvb_frontend_test_event(fepriv, events)) { + wait_woken(&wait, TASK_INTERRUPTIBLE, 0); + if (signal_pending(current)) { + ret = -ERESTARTSYS; + break; + } + } + remove_wait_queue(&events->wait_queue, &wait); if (ret < 0) return ret; } @@ -809,15 +817,26 @@ static void dvb_frontend_stop(struct dvb_frontend *fe) dev_dbg(fe->dvb->device, "%s:\n", __func__); + mutex_lock(&fe->remove_mutex); + if (fe->exit != DVB_FE_DEVICE_REMOVED) fe->exit = DVB_FE_NORMAL_EXIT; mb(); - if (!fepriv->thread) + if (!fepriv->thread) { + mutex_unlock(&fe->remove_mutex); return; + } kthread_stop(fepriv->thread); + mutex_unlock(&fe->remove_mutex); + + if (fepriv->dvbdev->users < -1) { + wait_event(fepriv->dvbdev->wait_queue, + fepriv->dvbdev->users == -1); + } + sema_init(&fepriv->sem, 1); fepriv->state = FESTATE_IDLE; @@ -2761,9 +2780,13 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) struct dvb_adapter *adapter = fe->dvb; int ret; + mutex_lock(&fe->remove_mutex); + dev_dbg(fe->dvb->device, "%s:\n", __func__); - if (fe->exit == DVB_FE_DEVICE_REMOVED) - return -ENODEV; + if (fe->exit == DVB_FE_DEVICE_REMOVED) { + ret = -ENODEV; + goto err_remove_mutex; + } if (adapter->mfe_shared == 2) { mutex_lock(&adapter->mfe_lock); @@ -2771,7 +2794,8 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) if (adapter->mfe_dvbdev && !adapter->mfe_dvbdev->writers) { mutex_unlock(&adapter->mfe_lock); - return -EBUSY; + ret = -EBUSY; + goto err_remove_mutex; } adapter->mfe_dvbdev = dvbdev; } @@ -2794,8 +2818,10 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) while (mferetry-- && (mfedev->users != -1 || mfepriv->thread)) { if (msleep_interruptible(500)) { - if (signal_pending(current)) - return -EINTR; + if (signal_pending(current)) { + ret = -EINTR; + goto err_remove_mutex; + } } } @@ -2807,7 +2833,8 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) if (mfedev->users != -1 || mfepriv->thread) { mutex_unlock(&adapter->mfe_lock); - return -EBUSY; + ret = -EBUSY; + goto err_remove_mutex; } adapter->mfe_dvbdev = dvbdev; } @@ -2866,6 +2893,8 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) if (adapter->mfe_shared) mutex_unlock(&adapter->mfe_lock); + + mutex_unlock(&fe->remove_mutex); return ret; err3: @@ -2887,6 +2916,9 @@ err1: err0: if (adapter->mfe_shared) mutex_unlock(&adapter->mfe_lock); + +err_remove_mutex: + mutex_unlock(&fe->remove_mutex); return ret; } @@ -2897,6 +2929,8 @@ static int dvb_frontend_release(struct inode *inode, struct file *file) struct dvb_frontend_private *fepriv = fe->frontend_priv; int ret; + mutex_lock(&fe->remove_mutex); + dev_dbg(fe->dvb->device, "%s:\n", __func__); if ((file->f_flags & O_ACCMODE) != O_RDONLY) { @@ -2918,10 +2952,18 @@ static int dvb_frontend_release(struct inode *inode, struct file *file) } mutex_unlock(&fe->dvb->mdev_lock); #endif - if (fe->exit != DVB_FE_NO_EXIT) - wake_up(&dvbdev->wait_queue); if (fe->ops.ts_bus_ctrl) fe->ops.ts_bus_ctrl(fe, 0); + + if (fe->exit != DVB_FE_NO_EXIT) { + mutex_unlock(&fe->remove_mutex); + wake_up(&dvbdev->wait_queue); + } else { + mutex_unlock(&fe->remove_mutex); + } + + } else { + mutex_unlock(&fe->remove_mutex); } dvb_frontend_put(fe); @@ -3022,6 +3064,7 @@ int dvb_register_frontend(struct dvb_adapter *dvb, fepriv = fe->frontend_priv; kref_init(&fe->refcount); + mutex_init(&fe->remove_mutex); /* * After initialization, there need to be two references: one diff --git a/drivers/media/dvb-core/dvb_net.c b/drivers/media/dvb-core/dvb_net.c index 8a2febf33ce2..8bb8dd34c223 100644 --- a/drivers/media/dvb-core/dvb_net.c +++ b/drivers/media/dvb-core/dvb_net.c @@ -1564,15 +1564,43 @@ static long dvb_net_ioctl(struct file *file, return dvb_usercopy(file, cmd, arg, dvb_net_do_ioctl); } +static int locked_dvb_net_open(struct inode *inode, struct file *file) +{ + struct dvb_device *dvbdev = file->private_data; + struct dvb_net *dvbnet = dvbdev->priv; + int ret; + + if (mutex_lock_interruptible(&dvbnet->remove_mutex)) + return -ERESTARTSYS; + + if (dvbnet->exit) { + mutex_unlock(&dvbnet->remove_mutex); + return -ENODEV; + } + + ret = dvb_generic_open(inode, file); + + mutex_unlock(&dvbnet->remove_mutex); + + return ret; +} + static int dvb_net_close(struct inode *inode, struct file *file) { struct dvb_device *dvbdev = file->private_data; struct dvb_net *dvbnet = dvbdev->priv; + mutex_lock(&dvbnet->remove_mutex); + dvb_generic_release(inode, file); - if(dvbdev->users == 1 && dvbnet->exit == 1) + if (dvbdev->users == 1 && dvbnet->exit == 1) { + mutex_unlock(&dvbnet->remove_mutex); wake_up(&dvbdev->wait_queue); + } else { + mutex_unlock(&dvbnet->remove_mutex); + } + return 0; } @@ -1580,7 +1608,7 @@ static int dvb_net_close(struct inode *inode, struct file *file) static const struct file_operations dvb_net_fops = { .owner = THIS_MODULE, .unlocked_ioctl = dvb_net_ioctl, - .open = dvb_generic_open, + .open = locked_dvb_net_open, .release = dvb_net_close, .llseek = noop_llseek, }; @@ -1599,10 +1627,13 @@ void dvb_net_release (struct dvb_net *dvbnet) { int i; + mutex_lock(&dvbnet->remove_mutex); dvbnet->exit = 1; + mutex_unlock(&dvbnet->remove_mutex); + if (dvbnet->dvbdev->users < 1) wait_event(dvbnet->dvbdev->wait_queue, - dvbnet->dvbdev->users==1); + dvbnet->dvbdev->users == 1); dvb_unregister_device(dvbnet->dvbdev); @@ -1621,6 +1652,7 @@ int dvb_net_init (struct dvb_adapter *adap, struct dvb_net *dvbnet, int i; mutex_init(&dvbnet->ioctl_mutex); + mutex_init(&dvbnet->remove_mutex); dvbnet->demux = dmx; for (i=0; i<DVB_NET_DEVICES_MAX; i++) diff --git a/drivers/media/dvb-core/dvbdev.c b/drivers/media/dvb-core/dvbdev.c index e9b3ce09e534..a4b05e366ccc 100644 --- a/drivers/media/dvb-core/dvbdev.c +++ b/drivers/media/dvb-core/dvbdev.c @@ -27,6 +27,7 @@ #include <media/tuner.h> static DEFINE_MUTEX(dvbdev_mutex); +static LIST_HEAD(dvbdevfops_list); static int dvbdev_debug; module_param(dvbdev_debug, int, 0644); @@ -453,14 +454,15 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, enum dvb_device_type type, int demux_sink_pads) { struct dvb_device *dvbdev; - struct file_operations *dvbdevfops; + struct file_operations *dvbdevfops = NULL; + struct dvbdevfops_node *node = NULL, *new_node = NULL; struct device *clsdev; int minor; int id, ret; mutex_lock(&dvbdev_register_lock); - if ((id = dvbdev_get_free_id (adap, type)) < 0){ + if ((id = dvbdev_get_free_id (adap, type)) < 0) { mutex_unlock(&dvbdev_register_lock); *pdvbdev = NULL; pr_err("%s: couldn't find free device id\n", __func__); @@ -468,18 +470,45 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, } *pdvbdev = dvbdev = kzalloc(sizeof(*dvbdev), GFP_KERNEL); - if (!dvbdev){ mutex_unlock(&dvbdev_register_lock); return -ENOMEM; } - dvbdevfops = kmemdup(template->fops, sizeof(*dvbdevfops), GFP_KERNEL); + /* + * When a device of the same type is probe()d more than once, + * the first allocated fops are used. This prevents memory leaks + * that can occur when the same device is probe()d repeatedly. + */ + list_for_each_entry(node, &dvbdevfops_list, list_head) { + if (node->fops->owner == adap->module && + node->type == type && + node->template == template) { + dvbdevfops = node->fops; + break; + } + } - if (!dvbdevfops){ - kfree (dvbdev); - mutex_unlock(&dvbdev_register_lock); - return -ENOMEM; + if (dvbdevfops == NULL) { + dvbdevfops = kmemdup(template->fops, sizeof(*dvbdevfops), GFP_KERNEL); + if (!dvbdevfops) { + kfree(dvbdev); + mutex_unlock(&dvbdev_register_lock); + return -ENOMEM; + } + + new_node = kzalloc(sizeof(struct dvbdevfops_node), GFP_KERNEL); + if (!new_node) { + kfree(dvbdevfops); + kfree(dvbdev); + mutex_unlock(&dvbdev_register_lock); + return -ENOMEM; + } + + new_node->fops = dvbdevfops; + new_node->type = type; + new_node->template = template; + list_add_tail (&new_node->list_head, &dvbdevfops_list); } memcpy(dvbdev, template, sizeof(struct dvb_device)); @@ -490,20 +519,20 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, dvbdev->priv = priv; dvbdev->fops = dvbdevfops; init_waitqueue_head (&dvbdev->wait_queue); - dvbdevfops->owner = adap->module; - list_add_tail (&dvbdev->list_head, &adap->device_list); - down_write(&minor_rwsem); #ifdef CONFIG_DVB_DYNAMIC_MINORS for (minor = 0; minor < MAX_DVB_MINORS; minor++) if (dvb_minors[minor] == NULL) break; - if (minor == MAX_DVB_MINORS) { + if (new_node) { + list_del (&new_node->list_head); + kfree(dvbdevfops); + kfree(new_node); + } list_del (&dvbdev->list_head); - kfree(dvbdevfops); kfree(dvbdev); up_write(&minor_rwsem); mutex_unlock(&dvbdev_register_lock); @@ -512,41 +541,47 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, #else minor = nums2minor(adap->num, type, id); #endif - dvbdev->minor = minor; dvb_minors[minor] = dvb_device_get(dvbdev); up_write(&minor_rwsem); - ret = dvb_register_media_device(dvbdev, type, minor, demux_sink_pads); if (ret) { pr_err("%s: dvb_register_media_device failed to create the mediagraph\n", __func__); - + if (new_node) { + list_del (&new_node->list_head); + kfree(dvbdevfops); + kfree(new_node); + } dvb_media_device_free(dvbdev); list_del (&dvbdev->list_head); - kfree(dvbdevfops); kfree(dvbdev); mutex_unlock(&dvbdev_register_lock); return ret; } - mutex_unlock(&dvbdev_register_lock); - clsdev = device_create(dvb_class, adap->device, MKDEV(DVB_MAJOR, minor), dvbdev, "dvb%d.%s%d", adap->num, dnames[type], id); if (IS_ERR(clsdev)) { pr_err("%s: failed to create device dvb%d.%s%d (%ld)\n", __func__, adap->num, dnames[type], id, PTR_ERR(clsdev)); + if (new_node) { + list_del (&new_node->list_head); + kfree(dvbdevfops); + kfree(new_node); + } dvb_media_device_free(dvbdev); list_del (&dvbdev->list_head); - kfree(dvbdevfops); kfree(dvbdev); + mutex_unlock(&dvbdev_register_lock); return PTR_ERR(clsdev); } + dprintk("DVB: register adapter%d/%s%d @ minor: %i (0x%02x)\n", adap->num, dnames[type], id, minor, minor); + mutex_unlock(&dvbdev_register_lock); return 0; } EXPORT_SYMBOL(dvb_register_device); @@ -575,7 +610,6 @@ static void dvb_free_device(struct kref *ref) { struct dvb_device *dvbdev = container_of(ref, struct dvb_device, ref); - kfree (dvbdev->fops); kfree (dvbdev); } @@ -1081,9 +1115,17 @@ error: static void __exit exit_dvbdev(void) { + struct dvbdevfops_node *node, *next; + class_destroy(dvb_class); cdev_del(&dvb_device_cdev); unregister_chrdev_region(MKDEV(DVB_MAJOR, 0), MAX_DVB_MINORS); + + list_for_each_entry_safe(node, next, &dvbdevfops_list, list_head) { + list_del (&node->list_head); + kfree(node->fops); + kfree(node); + } } subsys_initcall(init_dvbdev); diff --git a/drivers/media/dvb-frontends/mn88443x.c b/drivers/media/dvb-frontends/mn88443x.c index 1f1753f2ab1a..0782f8377eb2 100644 --- a/drivers/media/dvb-frontends/mn88443x.c +++ b/drivers/media/dvb-frontends/mn88443x.c @@ -798,7 +798,7 @@ MODULE_DEVICE_TABLE(i2c, mn88443x_i2c_id); static struct i2c_driver mn88443x_driver = { .driver = { .name = "mn88443x", - .of_match_table = of_match_ptr(mn88443x_of_match), + .of_match_table = mn88443x_of_match, }, .probe_new = mn88443x_probe, .remove = mn88443x_remove, diff --git a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c index 8287851b5ffd..d85bfbb77a25 100644 --- a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c +++ b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c @@ -697,7 +697,7 @@ static void netup_unidvb_dma_fini(struct netup_unidvb_dev *ndev, int num) netup_unidvb_dma_enable(dma, 0); msleep(50); cancel_work_sync(&dma->work); - del_timer(&dma->timeout); + del_timer_sync(&dma->timeout); } static int netup_unidvb_dma_setup(struct netup_unidvb_dev *ndev) @@ -887,12 +887,7 @@ static int netup_unidvb_initdev(struct pci_dev *pci_dev, ndev->lmmio0, (u32)pci_resource_len(pci_dev, 0), ndev->lmmio1, (u32)pci_resource_len(pci_dev, 1), pci_dev->irq); - if (request_irq(pci_dev->irq, netup_unidvb_isr, IRQF_SHARED, - "netup_unidvb", pci_dev) < 0) { - dev_err(&pci_dev->dev, - "%s(): can't get IRQ %d\n", __func__, pci_dev->irq); - goto irq_request_err; - } + ndev->dma_size = 2 * 188 * NETUP_DMA_BLOCKS_COUNT * NETUP_DMA_PACKETS_COUNT; ndev->dma_virt = dma_alloc_coherent(&pci_dev->dev, @@ -933,6 +928,14 @@ static int netup_unidvb_initdev(struct pci_dev *pci_dev, dev_err(&pci_dev->dev, "netup_unidvb: DMA setup failed\n"); goto dma_setup_err; } + + if (request_irq(pci_dev->irq, netup_unidvb_isr, IRQF_SHARED, + "netup_unidvb", pci_dev) < 0) { + dev_err(&pci_dev->dev, + "%s(): can't get IRQ %d\n", __func__, pci_dev->irq); + goto dma_setup_err; + } + dev_info(&pci_dev->dev, "netup_unidvb: device has been initialized\n"); return 0; @@ -951,8 +954,6 @@ spi_setup_err: dma_free_coherent(&pci_dev->dev, ndev->dma_size, ndev->dma_virt, ndev->dma_phys); dma_alloc_err: - free_irq(pci_dev->irq, pci_dev); -irq_request_err: iounmap(ndev->lmmio1); pci_bar1_error: iounmap(ndev->lmmio0); diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_stateful.c b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_stateful.c index 29991551cf61..0fbd030026c7 100644 --- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_stateful.c +++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_stateful.c @@ -584,6 +584,9 @@ static void mtk_init_vdec_params(struct mtk_vcodec_ctx *ctx) if (!(ctx->dev->dec_capability & VCODEC_CAPABILITY_4K_DISABLED)) { for (i = 0; i < num_supported_formats; i++) { + if (mtk_video_formats[i].type != MTK_FMT_DEC) + continue; + mtk_video_formats[i].frmsize.max_width = VCODEC_DEC_4K_CODED_WIDTH; mtk_video_formats[i].frmsize.max_height = diff --git a/drivers/media/platform/qcom/camss/camss-video.c b/drivers/media/platform/qcom/camss/camss-video.c index 898f32177b12..8640db306026 100644 --- a/drivers/media/platform/qcom/camss/camss-video.c +++ b/drivers/media/platform/qcom/camss/camss-video.c @@ -353,7 +353,6 @@ static int video_get_subdev_format(struct camss_video *video, if (subdev == NULL) return -EPIPE; - memset(&fmt, 0, sizeof(fmt)); fmt.pad = pad; ret = v4l2_subdev_call(subdev, pad, get_fmt, NULL, &fmt); diff --git a/drivers/media/platform/verisilicon/hantro_v4l2.c b/drivers/media/platform/verisilicon/hantro_v4l2.c index 835518534e3b..61cfaaf4e927 100644 --- a/drivers/media/platform/verisilicon/hantro_v4l2.c +++ b/drivers/media/platform/verisilicon/hantro_v4l2.c @@ -397,10 +397,12 @@ hantro_reset_raw_fmt(struct hantro_ctx *ctx, int bit_depth) if (!raw_vpu_fmt) return -EINVAL; - if (ctx->is_encoder) + if (ctx->is_encoder) { encoded_fmt = &ctx->dst_fmt; - else + ctx->vpu_src_fmt = raw_vpu_fmt; + } else { encoded_fmt = &ctx->src_fmt; + } hantro_reset_fmt(&raw_fmt, raw_vpu_fmt); raw_fmt.width = encoded_fmt->width; diff --git a/drivers/media/usb/dvb-usb-v2/ce6230.c b/drivers/media/usb/dvb-usb-v2/ce6230.c index 44540de1a206..d3b5cb4a24da 100644 --- a/drivers/media/usb/dvb-usb-v2/ce6230.c +++ b/drivers/media/usb/dvb-usb-v2/ce6230.c @@ -101,6 +101,10 @@ static int ce6230_i2c_master_xfer(struct i2c_adapter *adap, if (num > i + 1 && (msg[i+1].flags & I2C_M_RD)) { if (msg[i].addr == ce6230_zl10353_config.demod_address) { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } req.cmd = DEMOD_READ; req.value = msg[i].addr >> 1; req.index = msg[i].buf[0]; @@ -117,6 +121,10 @@ static int ce6230_i2c_master_xfer(struct i2c_adapter *adap, } else { if (msg[i].addr == ce6230_zl10353_config.demod_address) { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } req.cmd = DEMOD_WRITE; req.value = msg[i].addr >> 1; req.index = msg[i].buf[0]; diff --git a/drivers/media/usb/dvb-usb-v2/ec168.c b/drivers/media/usb/dvb-usb-v2/ec168.c index 7ed0ab9e429b..0e4773fc025c 100644 --- a/drivers/media/usb/dvb-usb-v2/ec168.c +++ b/drivers/media/usb/dvb-usb-v2/ec168.c @@ -115,6 +115,10 @@ static int ec168_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], while (i < num) { if (num > i + 1 && (msg[i+1].flags & I2C_M_RD)) { if (msg[i].addr == ec168_ec100_config.demod_address) { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } req.cmd = READ_DEMOD; req.value = 0; req.index = 0xff00 + msg[i].buf[0]; /* reg */ @@ -131,6 +135,10 @@ static int ec168_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], } } else { if (msg[i].addr == ec168_ec100_config.demod_address) { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } req.cmd = WRITE_DEMOD; req.value = msg[i].buf[1]; /* val */ req.index = 0xff00 + msg[i].buf[0]; /* reg */ @@ -139,6 +147,10 @@ static int ec168_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], ret = ec168_ctrl_msg(d, &req); i += 1; } else { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } req.cmd = WRITE_I2C; req.value = msg[i].buf[0]; /* val */ req.index = 0x0100 + msg[i].addr; /* I2C addr */ diff --git a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c index 795a012d4020..f7884bb56fcc 100644 --- a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c +++ b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c @@ -176,6 +176,10 @@ static int rtl28xxu_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], ret = -EOPNOTSUPP; goto err_mutex_unlock; } else if (msg[0].addr == 0x10) { + if (msg[0].len < 1 || msg[1].len < 1) { + ret = -EOPNOTSUPP; + goto err_mutex_unlock; + } /* method 1 - integrated demod */ if (msg[0].buf[0] == 0x00) { /* return demod page from driver cache */ @@ -189,6 +193,10 @@ static int rtl28xxu_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], ret = rtl28xxu_ctrl_msg(d, &req); } } else if (msg[0].len < 2) { + if (msg[0].len < 1) { + ret = -EOPNOTSUPP; + goto err_mutex_unlock; + } /* method 2 - old I2C */ req.value = (msg[0].buf[0] << 8) | (msg[0].addr << 1); req.index = CMD_I2C_RD; @@ -217,8 +225,16 @@ static int rtl28xxu_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], ret = -EOPNOTSUPP; goto err_mutex_unlock; } else if (msg[0].addr == 0x10) { + if (msg[0].len < 1) { + ret = -EOPNOTSUPP; + goto err_mutex_unlock; + } /* method 1 - integrated demod */ if (msg[0].buf[0] == 0x00) { + if (msg[0].len < 2) { + ret = -EOPNOTSUPP; + goto err_mutex_unlock; + } /* save demod page for later demod access */ dev->page = msg[0].buf[1]; ret = 0; @@ -231,6 +247,10 @@ static int rtl28xxu_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], ret = rtl28xxu_ctrl_msg(d, &req); } } else if ((msg[0].len < 23) && (!dev->new_i2c_write)) { + if (msg[0].len < 1) { + ret = -EOPNOTSUPP; + goto err_mutex_unlock; + } /* method 2 - old I2C */ req.value = (msg[0].buf[0] << 8) | (msg[0].addr << 1); req.index = CMD_I2C_WR; diff --git a/drivers/media/usb/dvb-usb/az6027.c b/drivers/media/usb/dvb-usb/az6027.c index 7d78ee09be5e..a31c6f82f4e9 100644 --- a/drivers/media/usb/dvb-usb/az6027.c +++ b/drivers/media/usb/dvb-usb/az6027.c @@ -988,6 +988,10 @@ static int az6027_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], int n /* write/read request */ if (i + 1 < num && (msg[i + 1].flags & I2C_M_RD)) { req = 0xB9; + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } index = (((msg[i].buf[0] << 8) & 0xff00) | (msg[i].buf[1] & 0x00ff)); value = msg[i].addr + (msg[i].len << 8); length = msg[i + 1].len + 6; @@ -1001,6 +1005,10 @@ static int az6027_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], int n /* demod 16bit addr */ req = 0xBD; + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } index = (((msg[i].buf[0] << 8) & 0xff00) | (msg[i].buf[1] & 0x00ff)); value = msg[i].addr + (2 << 8); length = msg[i].len - 2; @@ -1026,6 +1034,10 @@ static int az6027_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], int n } else { req = 0xBD; + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } index = msg[i].buf[0] & 0x00FF; value = msg[i].addr + (1 << 8); length = msg[i].len - 1; diff --git a/drivers/media/usb/dvb-usb/digitv.c b/drivers/media/usb/dvb-usb/digitv.c index 2756815a780b..32134be16914 100644 --- a/drivers/media/usb/dvb-usb/digitv.c +++ b/drivers/media/usb/dvb-usb/digitv.c @@ -63,6 +63,10 @@ static int digitv_i2c_xfer(struct i2c_adapter *adap,struct i2c_msg msg[],int num warn("more than 2 i2c messages at a time is not handled yet. TODO."); for (i = 0; i < num; i++) { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } /* write/read request */ if (i+1 < num && (msg[i+1].flags & I2C_M_RD)) { if (digitv_ctrl_msg(d, USB_READ_COFDM, msg[i].buf[0], NULL, 0, diff --git a/drivers/media/usb/dvb-usb/dw2102.c b/drivers/media/usb/dvb-usb/dw2102.c index 0ca764282c76..8747960e6146 100644 --- a/drivers/media/usb/dvb-usb/dw2102.c +++ b/drivers/media/usb/dvb-usb/dw2102.c @@ -946,7 +946,7 @@ static int su3000_read_mac_address(struct dvb_usb_device *d, u8 mac[6]) for (i = 0; i < 6; i++) { obuf[1] = 0xf0 + i; if (i2c_transfer(&d->i2c_adap, msg, 2) != 2) - break; + return -1; else mac[i] = ibuf[0]; } diff --git a/drivers/media/usb/pvrusb2/Kconfig b/drivers/media/usb/pvrusb2/Kconfig index 9501b10b31aa..0df10270dbdf 100644 --- a/drivers/media/usb/pvrusb2/Kconfig +++ b/drivers/media/usb/pvrusb2/Kconfig @@ -37,6 +37,7 @@ config VIDEO_PVRUSB2_DVB bool "pvrusb2 ATSC/DVB support" default y depends on VIDEO_PVRUSB2 && DVB_CORE + depends on VIDEO_PVRUSB2=m || DVB_CORE=y select DVB_LGDT330X if MEDIA_SUBDRV_AUTOSELECT select DVB_S5H1409 if MEDIA_SUBDRV_AUTOSELECT select DVB_S5H1411 if MEDIA_SUBDRV_AUTOSELECT diff --git a/drivers/media/usb/ttusb-dec/ttusb_dec.c b/drivers/media/usb/ttusb-dec/ttusb_dec.c index 38822cedd93a..c4474d4c44e2 100644 --- a/drivers/media/usb/ttusb-dec/ttusb_dec.c +++ b/drivers/media/usb/ttusb-dec/ttusb_dec.c @@ -1544,8 +1544,7 @@ static void ttusb_dec_exit_dvb(struct ttusb_dec *dec) dvb_dmx_release(&dec->demux); if (dec->fe) { dvb_unregister_frontend(dec->fe); - if (dec->fe->ops.release) - dec->fe->ops.release(dec->fe); + dvb_frontend_detach(dec->fe); } dvb_unregister_adapter(&dec->adapter); } diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c index 7aefa76a42b3..d631ce4f9f7b 100644 --- a/drivers/media/usb/uvc/uvc_driver.c +++ b/drivers/media/usb/uvc/uvc_driver.c @@ -251,14 +251,17 @@ static int uvc_parse_format(struct uvc_device *dev, /* Find the format descriptor from its GUID. */ fmtdesc = uvc_format_by_guid(&buffer[5]); - if (fmtdesc != NULL) { - format->fcc = fmtdesc->fcc; - } else { + if (!fmtdesc) { + /* + * Unknown video formats are not fatal errors, the + * caller will skip this descriptor. + */ dev_info(&streaming->intf->dev, "Unknown video format %pUl\n", &buffer[5]); - format->fcc = 0; + return 0; } + format->fcc = fmtdesc->fcc; format->bpp = buffer[21]; /* @@ -675,7 +678,7 @@ static int uvc_parse_streaming(struct uvc_device *dev, interval = (u32 *)&frame[nframes]; streaming->format = format; - streaming->nformats = nformats; + streaming->nformats = 0; /* Parse the format descriptors. */ while (buflen > 2 && buffer[1] == USB_DT_CS_INTERFACE) { @@ -689,7 +692,10 @@ static int uvc_parse_streaming(struct uvc_device *dev, &interval, buffer, buflen); if (ret < 0) goto error; + if (!ret) + break; + streaming->nformats++; frame += format->nframes; format++; diff --git a/drivers/media/v4l2-core/v4l2-mc.c b/drivers/media/v4l2-core/v4l2-mc.c index bf0c18100664..22fe08fce0a9 100644 --- a/drivers/media/v4l2-core/v4l2-mc.c +++ b/drivers/media/v4l2-core/v4l2-mc.c @@ -314,8 +314,7 @@ int v4l2_create_fwnode_links_to_pad(struct v4l2_subdev *src_sd, { struct fwnode_handle *endpoint; - if (!(sink->flags & MEDIA_PAD_FL_SINK) || - !is_media_entity_v4l2_subdev(sink->entity)) + if (!(sink->flags & MEDIA_PAD_FL_SINK)) return -EINVAL; fwnode_graph_for_each_endpoint(dev_fwnode(src_sd->dev), endpoint) { diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index f48466960f1b..30d4d0476248 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -316,12 +316,14 @@ static void fastrpc_free_map(struct kref *ref) if (map->table) { if (map->attr & FASTRPC_ATTR_SECUREMAP) { struct qcom_scm_vmperm perm; + int vmid = map->fl->cctx->vmperms[0].vmid; + u64 src_perms = BIT(QCOM_SCM_VMID_HLOS) | BIT(vmid); int err = 0; perm.vmid = QCOM_SCM_VMID_HLOS; perm.perm = QCOM_SCM_PERM_RWX; err = qcom_scm_assign_mem(map->phys, map->size, - &map->fl->cctx->perms, &perm, 1); + &src_perms, &perm, 1); if (err) { dev_err(map->fl->sctx->dev, "Failed to assign memory phys 0x%llx size 0x%llx err %d", map->phys, map->size, err); @@ -787,8 +789,12 @@ static int fastrpc_map_create(struct fastrpc_user *fl, int fd, goto map_err; } - map->phys = sg_dma_address(map->table->sgl); - map->phys += ((u64)fl->sctx->sid << 32); + if (attr & FASTRPC_ATTR_SECUREMAP) { + map->phys = sg_phys(map->table->sgl); + } else { + map->phys = sg_dma_address(map->table->sgl); + map->phys += ((u64)fl->sctx->sid << 32); + } map->size = len; map->va = sg_virt(map->table->sgl); map->len = len; @@ -798,9 +804,15 @@ static int fastrpc_map_create(struct fastrpc_user *fl, int fd, * If subsystem VMIDs are defined in DTSI, then do * hyp_assign from HLOS to those VM(s) */ + u64 src_perms = BIT(QCOM_SCM_VMID_HLOS); + struct qcom_scm_vmperm dst_perms[2] = {0}; + + dst_perms[0].vmid = QCOM_SCM_VMID_HLOS; + dst_perms[0].perm = QCOM_SCM_PERM_RW; + dst_perms[1].vmid = fl->cctx->vmperms[0].vmid; + dst_perms[1].perm = QCOM_SCM_PERM_RWX; map->attr = attr; - err = qcom_scm_assign_mem(map->phys, (u64)map->size, &fl->cctx->perms, - fl->cctx->vmperms, fl->cctx->vmcount); + err = qcom_scm_assign_mem(map->phys, (u64)map->size, &src_perms, dst_perms, 2); if (err) { dev_err(sess->dev, "Failed to assign memory with phys 0x%llx size 0x%llx err %d", map->phys, map->size, err); @@ -1892,7 +1904,7 @@ static int fastrpc_req_mmap(struct fastrpc_user *fl, char __user *argp) req.vaddrout = rsp_msg.vaddr; /* Add memory to static PD pool, protection thru hypervisor */ - if (req.flags != ADSP_MMAP_REMOTE_HEAP_ADDR && fl->cctx->vmcount) { + if (req.flags == ADSP_MMAP_REMOTE_HEAP_ADDR && fl->cctx->vmcount) { struct qcom_scm_vmperm perm; perm.vmid = QCOM_SCM_VMID_HLOS; @@ -2337,8 +2349,10 @@ static void fastrpc_notify_users(struct fastrpc_user *user) struct fastrpc_invoke_ctx *ctx; spin_lock(&user->lock); - list_for_each_entry(ctx, &user->pending, node) + list_for_each_entry(ctx, &user->pending, node) { + ctx->retval = -EPIPE; complete(&ctx->work); + } spin_unlock(&user->lock); } @@ -2349,7 +2363,9 @@ static void fastrpc_rpmsg_remove(struct rpmsg_device *rpdev) struct fastrpc_user *user; unsigned long flags; + /* No invocations past this point */ spin_lock_irqsave(&cctx->lock, flags); + cctx->rpdev = NULL; list_for_each_entry(user, &cctx->users, user) fastrpc_notify_users(user); spin_unlock_irqrestore(&cctx->lock, flags); @@ -2368,7 +2384,6 @@ static void fastrpc_rpmsg_remove(struct rpmsg_device *rpdev) of_platform_depopulate(&rpdev->dev); - cctx->rpdev = NULL; fastrpc_channel_ctx_put(cctx); } diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 00c33edb9fb9..d920c4178389 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -264,6 +264,7 @@ static ssize_t power_ro_lock_store(struct device *dev, goto out_put; } req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_BOOT_WP; + req_to_mmc_queue_req(req)->drv_op_result = -EIO; blk_execute_rq(req, false); ret = req_to_mmc_queue_req(req)->drv_op_result; blk_mq_free_request(req); @@ -651,6 +652,7 @@ static int mmc_blk_ioctl_cmd(struct mmc_blk_data *md, idatas[0] = idata; req_to_mmc_queue_req(req)->drv_op = rpmb ? MMC_DRV_OP_IOCTL_RPMB : MMC_DRV_OP_IOCTL; + req_to_mmc_queue_req(req)->drv_op_result = -EIO; req_to_mmc_queue_req(req)->drv_op_data = idatas; req_to_mmc_queue_req(req)->ioc_count = 1; blk_execute_rq(req, false); @@ -722,6 +724,7 @@ static int mmc_blk_ioctl_multi_cmd(struct mmc_blk_data *md, } req_to_mmc_queue_req(req)->drv_op = rpmb ? MMC_DRV_OP_IOCTL_RPMB : MMC_DRV_OP_IOCTL; + req_to_mmc_queue_req(req)->drv_op_result = -EIO; req_to_mmc_queue_req(req)->drv_op_data = idata; req_to_mmc_queue_req(req)->ioc_count = n; blk_execute_rq(req, false); @@ -2806,6 +2809,7 @@ static int mmc_dbg_card_status_get(void *data, u64 *val) if (IS_ERR(req)) return PTR_ERR(req); req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_GET_CARD_STATUS; + req_to_mmc_queue_req(req)->drv_op_result = -EIO; blk_execute_rq(req, false); ret = req_to_mmc_queue_req(req)->drv_op_result; if (ret >= 0) { @@ -2844,6 +2848,7 @@ static int mmc_ext_csd_open(struct inode *inode, struct file *filp) goto out_free; } req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_GET_EXT_CSD; + req_to_mmc_queue_req(req)->drv_op_result = -EIO; req_to_mmc_queue_req(req)->drv_op_data = &ext_csd; blk_execute_rq(req, false); err = req_to_mmc_queue_req(req)->drv_op_result; diff --git a/drivers/mmc/core/pwrseq_sd8787.c b/drivers/mmc/core/pwrseq_sd8787.c index 2e120ad83020..0c5f5e371e1f 100644 --- a/drivers/mmc/core/pwrseq_sd8787.c +++ b/drivers/mmc/core/pwrseq_sd8787.c @@ -28,7 +28,6 @@ struct mmc_pwrseq_sd8787 { struct mmc_pwrseq pwrseq; struct gpio_desc *reset_gpio; struct gpio_desc *pwrdn_gpio; - u32 reset_pwrdwn_delay_ms; }; #define to_pwrseq_sd8787(p) container_of(p, struct mmc_pwrseq_sd8787, pwrseq) @@ -39,7 +38,7 @@ static void mmc_pwrseq_sd8787_pre_power_on(struct mmc_host *host) gpiod_set_value_cansleep(pwrseq->reset_gpio, 1); - msleep(pwrseq->reset_pwrdwn_delay_ms); + msleep(300); gpiod_set_value_cansleep(pwrseq->pwrdn_gpio, 1); } @@ -51,17 +50,37 @@ static void mmc_pwrseq_sd8787_power_off(struct mmc_host *host) gpiod_set_value_cansleep(pwrseq->reset_gpio, 0); } +static void mmc_pwrseq_wilc1000_pre_power_on(struct mmc_host *host) +{ + struct mmc_pwrseq_sd8787 *pwrseq = to_pwrseq_sd8787(host->pwrseq); + + /* The pwrdn_gpio is really CHIP_EN, reset_gpio is RESETN */ + gpiod_set_value_cansleep(pwrseq->pwrdn_gpio, 1); + msleep(5); + gpiod_set_value_cansleep(pwrseq->reset_gpio, 1); +} + +static void mmc_pwrseq_wilc1000_power_off(struct mmc_host *host) +{ + struct mmc_pwrseq_sd8787 *pwrseq = to_pwrseq_sd8787(host->pwrseq); + + gpiod_set_value_cansleep(pwrseq->reset_gpio, 0); + gpiod_set_value_cansleep(pwrseq->pwrdn_gpio, 0); +} + static const struct mmc_pwrseq_ops mmc_pwrseq_sd8787_ops = { .pre_power_on = mmc_pwrseq_sd8787_pre_power_on, .power_off = mmc_pwrseq_sd8787_power_off, }; -static const u32 sd8787_delay_ms = 300; -static const u32 wilc1000_delay_ms = 5; +static const struct mmc_pwrseq_ops mmc_pwrseq_wilc1000_ops = { + .pre_power_on = mmc_pwrseq_wilc1000_pre_power_on, + .power_off = mmc_pwrseq_wilc1000_power_off, +}; static const struct of_device_id mmc_pwrseq_sd8787_of_match[] = { - { .compatible = "mmc-pwrseq-sd8787", .data = &sd8787_delay_ms }, - { .compatible = "mmc-pwrseq-wilc1000", .data = &wilc1000_delay_ms }, + { .compatible = "mmc-pwrseq-sd8787", .data = &mmc_pwrseq_sd8787_ops }, + { .compatible = "mmc-pwrseq-wilc1000", .data = &mmc_pwrseq_wilc1000_ops }, {/* sentinel */}, }; MODULE_DEVICE_TABLE(of, mmc_pwrseq_sd8787_of_match); @@ -77,7 +96,6 @@ static int mmc_pwrseq_sd8787_probe(struct platform_device *pdev) return -ENOMEM; match = of_match_node(mmc_pwrseq_sd8787_of_match, pdev->dev.of_node); - pwrseq->reset_pwrdwn_delay_ms = *(u32 *)match->data; pwrseq->pwrdn_gpio = devm_gpiod_get(dev, "powerdown", GPIOD_OUT_LOW); if (IS_ERR(pwrseq->pwrdn_gpio)) @@ -88,7 +106,7 @@ static int mmc_pwrseq_sd8787_probe(struct platform_device *pdev) return PTR_ERR(pwrseq->reset_gpio); pwrseq->pwrseq.dev = dev; - pwrseq->pwrseq.ops = &mmc_pwrseq_sd8787_ops; + pwrseq->pwrseq.ops = match->data; pwrseq->pwrseq.owner = THIS_MODULE; platform_set_drvdata(pdev, pwrseq); diff --git a/drivers/mmc/host/sdhci-cadence.c b/drivers/mmc/host/sdhci-cadence.c index b24aa27da50c..d2f625054689 100644 --- a/drivers/mmc/host/sdhci-cadence.c +++ b/drivers/mmc/host/sdhci-cadence.c @@ -540,9 +540,11 @@ static int sdhci_cdns_probe(struct platform_device *pdev) if (host->mmc->caps & MMC_CAP_HW_RESET) { priv->rst_hw = devm_reset_control_get_optional_exclusive(dev, NULL); - if (IS_ERR(priv->rst_hw)) - return dev_err_probe(mmc_dev(host->mmc), PTR_ERR(priv->rst_hw), - "reset controller error\n"); + if (IS_ERR(priv->rst_hw)) { + ret = dev_err_probe(mmc_dev(host->mmc), PTR_ERR(priv->rst_hw), + "reset controller error\n"); + goto free; + } if (priv->rst_hw) host->mmc_host_ops.card_hw_reset = sdhci_cdns_mmc_hw_reset; } diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index d7c0c0b9e26c..eebf94604a7f 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -1634,6 +1634,10 @@ sdhci_esdhc_imx_probe_dt(struct platform_device *pdev, if (ret) return ret; + /* HS400/HS400ES require 8 bit bus */ + if (!(host->mmc->caps & MMC_CAP_8_BIT_DATA)) + host->mmc->caps2 &= ~(MMC_CAP2_HS400 | MMC_CAP2_HS400_ES); + if (mmc_gpio_get_cd(host->mmc) >= 0) host->quirks &= ~SDHCI_QUIRK_BROKEN_CARD_DETECTION; @@ -1724,10 +1728,6 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev) host->mmc_host_ops.init_card = usdhc_init_card; } - err = sdhci_esdhc_imx_probe_dt(pdev, host, imx_data); - if (err) - goto disable_ahb_clk; - if (imx_data->socdata->flags & ESDHC_FLAG_MAN_TUNING) sdhci_esdhc_ops.platform_execute_tuning = esdhc_executing_tuning; @@ -1735,15 +1735,13 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev) if (imx_data->socdata->flags & ESDHC_FLAG_ERR004536) host->quirks |= SDHCI_QUIRK_BROKEN_ADMA; - if (host->mmc->caps & MMC_CAP_8_BIT_DATA && - imx_data->socdata->flags & ESDHC_FLAG_HS400) + if (imx_data->socdata->flags & ESDHC_FLAG_HS400) host->mmc->caps2 |= MMC_CAP2_HS400; if (imx_data->socdata->flags & ESDHC_FLAG_BROKEN_AUTO_CMD23) host->quirks2 |= SDHCI_QUIRK2_ACMD23_BROKEN; - if (host->mmc->caps & MMC_CAP_8_BIT_DATA && - imx_data->socdata->flags & ESDHC_FLAG_HS400_ES) { + if (imx_data->socdata->flags & ESDHC_FLAG_HS400_ES) { host->mmc->caps2 |= MMC_CAP2_HS400_ES; host->mmc_host_ops.hs400_enhanced_strobe = esdhc_hs400_enhanced_strobe; @@ -1765,6 +1763,10 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev) goto disable_ahb_clk; } + err = sdhci_esdhc_imx_probe_dt(pdev, host, imx_data); + if (err) + goto disable_ahb_clk; + sdhci_esdhc_imx_hwinit(host); err = sdhci_add_host(host); diff --git a/drivers/mmc/host/vub300.c b/drivers/mmc/host/vub300.c index e4c4bfac3763..9ec593d52f0f 100644 --- a/drivers/mmc/host/vub300.c +++ b/drivers/mmc/host/vub300.c @@ -1713,6 +1713,9 @@ static void construct_request_response(struct vub300_mmc_host *vub300, int bytes = 3 & less_cmd; int words = less_cmd >> 2; u8 *r = vub300->resp.response.command_response; + + if (!resp_len) + return; if (bytes == 3) { cmd->resp[words] = (r[1 + (words << 2)] << 24) | (r[2 + (words << 2)] << 16) diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c index 01f1c6792df9..8dc4f5c493fc 100644 --- a/drivers/mtd/mtdchar.c +++ b/drivers/mtd/mtdchar.c @@ -590,8 +590,8 @@ static void adjust_oob_length(struct mtd_info *mtd, uint64_t start, (end_page - start_page + 1) * oob_per_page); } -static int mtdchar_write_ioctl(struct mtd_info *mtd, - struct mtd_write_req __user *argp) +static noinline_for_stack int +mtdchar_write_ioctl(struct mtd_info *mtd, struct mtd_write_req __user *argp) { struct mtd_info *master = mtd_get_master(mtd); struct mtd_write_req req; @@ -688,8 +688,8 @@ static int mtdchar_write_ioctl(struct mtd_info *mtd, return ret; } -static int mtdchar_read_ioctl(struct mtd_info *mtd, - struct mtd_read_req __user *argp) +static noinline_for_stack int +mtdchar_read_ioctl(struct mtd_info *mtd, struct mtd_read_req __user *argp) { struct mtd_info *master = mtd_get_master(mtd); struct mtd_read_req req; diff --git a/drivers/mtd/nand/raw/ingenic/ingenic_ecc.h b/drivers/mtd/nand/raw/ingenic/ingenic_ecc.h index 2cda439b5e11..017868f59f22 100644 --- a/drivers/mtd/nand/raw/ingenic/ingenic_ecc.h +++ b/drivers/mtd/nand/raw/ingenic/ingenic_ecc.h @@ -36,25 +36,25 @@ int ingenic_ecc_correct(struct ingenic_ecc *ecc, void ingenic_ecc_release(struct ingenic_ecc *ecc); struct ingenic_ecc *of_ingenic_ecc_get(struct device_node *np); #else /* CONFIG_MTD_NAND_INGENIC_ECC */ -int ingenic_ecc_calculate(struct ingenic_ecc *ecc, +static inline int ingenic_ecc_calculate(struct ingenic_ecc *ecc, struct ingenic_ecc_params *params, const u8 *buf, u8 *ecc_code) { return -ENODEV; } -int ingenic_ecc_correct(struct ingenic_ecc *ecc, +static inline int ingenic_ecc_correct(struct ingenic_ecc *ecc, struct ingenic_ecc_params *params, u8 *buf, u8 *ecc_code) { return -ENODEV; } -void ingenic_ecc_release(struct ingenic_ecc *ecc) +static inline void ingenic_ecc_release(struct ingenic_ecc *ecc) { } -struct ingenic_ecc *of_ingenic_ecc_get(struct device_node *np) +static inline struct ingenic_ecc *of_ingenic_ecc_get(struct device_node *np) { return ERR_PTR(-ENODEV); } diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c index afb424579f0b..30c15e4e1cc0 100644 --- a/drivers/mtd/nand/raw/marvell_nand.c +++ b/drivers/mtd/nand/raw/marvell_nand.c @@ -2457,6 +2457,12 @@ static int marvell_nfc_setup_interface(struct nand_chip *chip, int chipnr, NDTR1_WAIT_MODE; } + /* + * Reset nfc->selected_chip so the next command will cause the timing + * registers to be updated in marvell_nfc_select_target(). + */ + nfc->selected_chip = NULL; + return 0; } @@ -2894,10 +2900,6 @@ static int marvell_nfc_init(struct marvell_nfc *nfc) regmap_update_bits(sysctrl_base, GENCONF_CLK_GATING_CTRL, GENCONF_CLK_GATING_CTRL_ND_GATE, GENCONF_CLK_GATING_CTRL_ND_GATE); - - regmap_update_bits(sysctrl_base, GENCONF_ND_CLK_CTRL, - GENCONF_ND_CLK_CTRL_EN, - GENCONF_ND_CLK_CTRL_EN); } /* Configure the DMA if appropriate */ diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c index 0bb0ad14a2fc..5f29fac8669a 100644 --- a/drivers/mtd/spi-nor/core.c +++ b/drivers/mtd/spi-nor/core.c @@ -2018,6 +2018,7 @@ static const struct spi_nor_manufacturer *manufacturers[] = { static const struct flash_info spi_nor_generic_flash = { .name = "spi-nor-generic", + .n_banks = 1, /* * JESD216 rev A doesn't specify the page size, therefore we need a * sane default. @@ -2921,7 +2922,8 @@ static void spi_nor_late_init_params(struct spi_nor *nor) if (nor->flags & SNOR_F_HAS_LOCK && !nor->params->locking_ops) spi_nor_init_default_locking_ops(nor); - nor->params->bank_size = div64_u64(nor->params->size, nor->info->n_banks); + if (nor->info->n_banks > 1) + params->bank_size = div64_u64(params->size, nor->info->n_banks); } /** @@ -2987,6 +2989,7 @@ static void spi_nor_init_default_params(struct spi_nor *nor) /* Set SPI NOR sizes. */ params->writesize = 1; params->size = (u64)info->sector_size * info->n_sectors; + params->bank_size = params->size; params->page_size = info->page_size; if (!(info->flags & SPI_NOR_NO_FR)) { diff --git a/drivers/mtd/spi-nor/spansion.c b/drivers/mtd/spi-nor/spansion.c index 15f9a80c10b9..36876aa849ed 100644 --- a/drivers/mtd/spi-nor/spansion.c +++ b/drivers/mtd/spi-nor/spansion.c @@ -361,7 +361,7 @@ static int cypress_nor_determine_addr_mode_by_sr1(struct spi_nor *nor, */ static int cypress_nor_set_addr_mode_nbytes(struct spi_nor *nor) { - struct spi_mem_op op; + struct spi_mem_op op = {}; u8 addr_mode; int ret; @@ -492,7 +492,7 @@ s25fs256t_post_bfpt_fixup(struct spi_nor *nor, const struct sfdp_parameter_header *bfpt_header, const struct sfdp_bfpt *bfpt) { - struct spi_mem_op op; + struct spi_mem_op op = {}; int ret; ret = cypress_nor_set_addr_mode_nbytes(nor); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index ebf61c19dcef..007cec23a92f 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1,8 +1,9 @@ +// SPDX-License-Identifier: GPL-1.0+ /* * originally based on the dummy device. * * Copyright 1999, Thomas Davis, tadavis@lbl.gov. - * Licensed under the GPL. Based on dummy.c, and eql.c devices. + * Based on dummy.c, and eql.c devices. * * bonding.c: an Ethernet Bonding driver * @@ -3949,7 +3950,11 @@ static int bond_slave_netdev_event(unsigned long event, unblock_netpoll_tx(); break; case NETDEV_FEAT_CHANGE: - bond_compute_features(bond); + if (!bond->notifier_ctx) { + bond->notifier_ctx = true; + bond_compute_features(bond); + bond->notifier_ctx = false; + } break; case NETDEV_RESEND_IGMP: /* Propagate to master device */ @@ -6344,6 +6349,8 @@ static int bond_init(struct net_device *bond_dev) if (!bond->wq) return -ENOMEM; + bond->notifier_ctx = false; + spin_lock_init(&bond->stats_lock); netdev_lockdep_set_classes(bond_dev); diff --git a/drivers/net/bonding/bonding_priv.h b/drivers/net/bonding/bonding_priv.h index 48cdf3a49a7d..fef6288c6944 100644 --- a/drivers/net/bonding/bonding_priv.h +++ b/drivers/net/bonding/bonding_priv.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-1.0+ */ /* * Bond several ethernet interfaces into a Cisco, running 'Etherchannel'. * @@ -7,9 +8,6 @@ * BUT, I'm the one who modified it for ethernet, so: * (c) Copyright 1999, Thomas Davis, tadavis@lbl.gov * - * This software may be used and distributed according to the terms - * of the GNU Public License, incorporated herein by reference. - * */ #ifndef _BONDING_PRIV_H diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig index 3ceccafd701b..b190007c01be 100644 --- a/drivers/net/can/Kconfig +++ b/drivers/net/can/Kconfig @@ -95,7 +95,7 @@ config CAN_AT91 config CAN_BXCAN tristate "STM32 Basic Extended CAN (bxCAN) devices" - depends on OF || ARCH_STM32 || COMPILE_TEST + depends on ARCH_STM32 || COMPILE_TEST depends on HAS_IOMEM select CAN_RX_OFFLOAD help diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c index 199cb200f2bd..4621266851ed 100644 --- a/drivers/net/can/at91_can.c +++ b/drivers/net/can/at91_can.c @@ -1346,7 +1346,7 @@ static int at91_can_probe(struct platform_device *pdev) return err; } -static int at91_can_remove(struct platform_device *pdev) +static void at91_can_remove(struct platform_device *pdev) { struct net_device *dev = platform_get_drvdata(pdev); struct at91_priv *priv = netdev_priv(dev); @@ -1362,8 +1362,6 @@ static int at91_can_remove(struct platform_device *pdev) clk_put(priv->clk); free_candev(dev); - - return 0; } static const struct platform_device_id at91_can_id_table[] = { @@ -1381,7 +1379,7 @@ MODULE_DEVICE_TABLE(platform, at91_can_id_table); static struct platform_driver at91_can_driver = { .probe = at91_can_probe, - .remove = at91_can_remove, + .remove_new = at91_can_remove, .driver = { .name = KBUILD_MODNAME, .of_match_table = of_match_ptr(at91_can_dt_ids), diff --git a/drivers/net/can/bxcan.c b/drivers/net/can/bxcan.c index e26ccd41e3cb..39de7164bc4e 100644 --- a/drivers/net/can/bxcan.c +++ b/drivers/net/can/bxcan.c @@ -118,7 +118,7 @@ #define BXCAN_FiR1_REG(b) (0x40 + (b) * 8) #define BXCAN_FiR2_REG(b) (0x44 + (b) * 8) -#define BXCAN_FILTER_ID(primary) (primary ? 0 : 14) +#define BXCAN_FILTER_ID(cfg) ((cfg) == BXCAN_CFG_DUAL_SECONDARY ? 14 : 0) /* Filter primary register (FMR) bits */ #define BXCAN_FMR_CANSB_MASK GENMASK(13, 8) @@ -135,6 +135,12 @@ enum bxcan_lec_code { BXCAN_LEC_UNUSED }; +enum bxcan_cfg { + BXCAN_CFG_SINGLE = 0, + BXCAN_CFG_DUAL_PRIMARY, + BXCAN_CFG_DUAL_SECONDARY +}; + /* Structure of the message buffer */ struct bxcan_mb { u32 id; /* can identifier */ @@ -167,7 +173,7 @@ struct bxcan_priv { struct regmap *gcan; int tx_irq; int sce_irq; - bool primary; + enum bxcan_cfg cfg; struct clk *clk; spinlock_t rmw_lock; /* lock for read-modify-write operations */ unsigned int tx_head; @@ -202,17 +208,17 @@ static inline void bxcan_rmw(struct bxcan_priv *priv, void __iomem *addr, spin_unlock_irqrestore(&priv->rmw_lock, flags); } -static void bxcan_disable_filters(struct bxcan_priv *priv, bool primary) +static void bxcan_disable_filters(struct bxcan_priv *priv, enum bxcan_cfg cfg) { - unsigned int fid = BXCAN_FILTER_ID(primary); + unsigned int fid = BXCAN_FILTER_ID(cfg); u32 fmask = BIT(fid); regmap_update_bits(priv->gcan, BXCAN_FA1R_REG, fmask, 0); } -static void bxcan_enable_filters(struct bxcan_priv *priv, bool primary) +static void bxcan_enable_filters(struct bxcan_priv *priv, enum bxcan_cfg cfg) { - unsigned int fid = BXCAN_FILTER_ID(primary); + unsigned int fid = BXCAN_FILTER_ID(cfg); u32 fmask = BIT(fid); /* Filter settings: @@ -680,7 +686,7 @@ static int bxcan_chip_start(struct net_device *ndev) BXCAN_BTR_BRP_MASK | BXCAN_BTR_TS1_MASK | BXCAN_BTR_TS2_MASK | BXCAN_BTR_SJW_MASK, set); - bxcan_enable_filters(priv, priv->primary); + bxcan_enable_filters(priv, priv->cfg); /* Clear all internal status */ priv->tx_head = 0; @@ -806,7 +812,7 @@ static void bxcan_chip_stop(struct net_device *ndev) BXCAN_IER_EPVIE | BXCAN_IER_EWGIE | BXCAN_IER_FOVIE1 | BXCAN_IER_FFIE1 | BXCAN_IER_FMPIE1 | BXCAN_IER_FOVIE0 | BXCAN_IER_FFIE0 | BXCAN_IER_FMPIE0 | BXCAN_IER_TMEIE, 0); - bxcan_disable_filters(priv, priv->primary); + bxcan_disable_filters(priv, priv->cfg); bxcan_enter_sleep_mode(priv); priv->can.state = CAN_STATE_STOPPED; } @@ -931,7 +937,7 @@ static int bxcan_probe(struct platform_device *pdev) struct clk *clk = NULL; void __iomem *regs; struct regmap *gcan; - bool primary; + enum bxcan_cfg cfg; int err, rx_irq, tx_irq, sce_irq; regs = devm_platform_ioremap_resource(pdev, 0); @@ -946,7 +952,13 @@ static int bxcan_probe(struct platform_device *pdev) return PTR_ERR(gcan); } - primary = of_property_read_bool(np, "st,can-primary"); + if (of_property_read_bool(np, "st,can-primary")) + cfg = BXCAN_CFG_DUAL_PRIMARY; + else if (of_property_read_bool(np, "st,can-secondary")) + cfg = BXCAN_CFG_DUAL_SECONDARY; + else + cfg = BXCAN_CFG_SINGLE; + clk = devm_clk_get(dev, NULL); if (IS_ERR(clk)) { dev_err(dev, "failed to get clock\n"); @@ -954,22 +966,16 @@ static int bxcan_probe(struct platform_device *pdev) } rx_irq = platform_get_irq_byname(pdev, "rx0"); - if (rx_irq < 0) { - dev_err(dev, "failed to get rx0 irq\n"); + if (rx_irq < 0) return rx_irq; - } tx_irq = platform_get_irq_byname(pdev, "tx"); - if (tx_irq < 0) { - dev_err(dev, "failed to get tx irq\n"); + if (tx_irq < 0) return tx_irq; - } sce_irq = platform_get_irq_byname(pdev, "sce"); - if (sce_irq < 0) { - dev_err(dev, "failed to get sce irq\n"); + if (sce_irq < 0) return sce_irq; - } ndev = alloc_candev(sizeof(struct bxcan_priv), BXCAN_TX_MB_NUM); if (!ndev) { @@ -992,7 +998,7 @@ static int bxcan_probe(struct platform_device *pdev) priv->clk = clk; priv->tx_irq = tx_irq; priv->sce_irq = sce_irq; - priv->primary = primary; + priv->cfg = cfg; priv->can.clock.freq = clk_get_rate(clk); spin_lock_init(&priv->rmw_lock); priv->tx_head = 0; @@ -1027,7 +1033,7 @@ out_free_candev: return err; } -static int bxcan_remove(struct platform_device *pdev) +static void bxcan_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); struct bxcan_priv *priv = netdev_priv(ndev); @@ -1036,7 +1042,6 @@ static int bxcan_remove(struct platform_device *pdev) clk_disable_unprepare(priv->clk); can_rx_offload_del(&priv->offload); free_candev(ndev); - return 0; } static int __maybe_unused bxcan_suspend(struct device *dev) @@ -1088,7 +1093,7 @@ static struct platform_driver bxcan_driver = { .of_match_table = bxcan_of_match, }, .probe = bxcan_probe, - .remove = bxcan_remove, + .remove_new = bxcan_remove, }; module_platform_driver(bxcan_driver); diff --git a/drivers/net/can/c_can/c_can_platform.c b/drivers/net/can/c_can/c_can_platform.c index 03ccb7cfacaf..925930b6c4ca 100644 --- a/drivers/net/can/c_can/c_can_platform.c +++ b/drivers/net/can/c_can/c_can_platform.c @@ -410,7 +410,7 @@ exit: return ret; } -static int c_can_plat_remove(struct platform_device *pdev) +static void c_can_plat_remove(struct platform_device *pdev) { struct net_device *dev = platform_get_drvdata(pdev); struct c_can_priv *priv = netdev_priv(dev); @@ -418,8 +418,6 @@ static int c_can_plat_remove(struct platform_device *pdev) unregister_c_can_dev(dev); pm_runtime_disable(priv->device); free_c_can_dev(dev); - - return 0; } #ifdef CONFIG_PM @@ -487,7 +485,7 @@ static struct platform_driver c_can_plat_driver = { .of_match_table = c_can_of_table, }, .probe = c_can_plat_probe, - .remove = c_can_plat_remove, + .remove_new = c_can_plat_remove, .suspend = c_can_suspend, .resume = c_can_resume, .id_table = c_can_id_table, diff --git a/drivers/net/can/cc770/cc770_isa.c b/drivers/net/can/cc770/cc770_isa.c index 8f6dccd5a587..22009440a983 100644 --- a/drivers/net/can/cc770/cc770_isa.c +++ b/drivers/net/can/cc770/cc770_isa.c @@ -285,7 +285,7 @@ exit: return err; } -static int cc770_isa_remove(struct platform_device *pdev) +static void cc770_isa_remove(struct platform_device *pdev) { struct net_device *dev = platform_get_drvdata(pdev); struct cc770_priv *priv = netdev_priv(dev); @@ -303,13 +303,11 @@ static int cc770_isa_remove(struct platform_device *pdev) release_region(port[idx], CC770_IOSIZE); } free_cc770dev(dev); - - return 0; } static struct platform_driver cc770_isa_driver = { .probe = cc770_isa_probe, - .remove = cc770_isa_remove, + .remove_new = cc770_isa_remove, .driver = { .name = KBUILD_MODNAME, }, diff --git a/drivers/net/can/cc770/cc770_platform.c b/drivers/net/can/cc770/cc770_platform.c index 8dcc32e4e30e..13bcfba05f18 100644 --- a/drivers/net/can/cc770/cc770_platform.c +++ b/drivers/net/can/cc770/cc770_platform.c @@ -230,7 +230,7 @@ exit_release_mem: return err; } -static int cc770_platform_remove(struct platform_device *pdev) +static void cc770_platform_remove(struct platform_device *pdev) { struct net_device *dev = platform_get_drvdata(pdev); struct cc770_priv *priv = netdev_priv(dev); @@ -242,8 +242,6 @@ static int cc770_platform_remove(struct platform_device *pdev) mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); release_mem_region(mem->start, resource_size(mem)); - - return 0; } static const struct of_device_id cc770_platform_table[] = { @@ -259,7 +257,7 @@ static struct platform_driver cc770_platform_driver = { .of_match_table = cc770_platform_table, }, .probe = cc770_platform_probe, - .remove = cc770_platform_remove, + .remove_new = cc770_platform_remove, }; module_platform_driver(cc770_platform_driver); diff --git a/drivers/net/can/ctucanfd/ctucanfd_platform.c b/drivers/net/can/ctucanfd/ctucanfd_platform.c index a17561d97192..55bb10b157b4 100644 --- a/drivers/net/can/ctucanfd/ctucanfd_platform.c +++ b/drivers/net/can/ctucanfd/ctucanfd_platform.c @@ -86,7 +86,7 @@ err: * This function frees all the resources allocated to the device. * Return: 0 always */ -static int ctucan_platform_remove(struct platform_device *pdev) +static void ctucan_platform_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); struct ctucan_priv *priv = netdev_priv(ndev); @@ -97,8 +97,6 @@ static int ctucan_platform_remove(struct platform_device *pdev) pm_runtime_disable(&pdev->dev); netif_napi_del(&priv->napi); free_candev(ndev); - - return 0; } static SIMPLE_DEV_PM_OPS(ctucan_platform_pm_ops, ctucan_suspend, ctucan_resume); @@ -113,7 +111,7 @@ MODULE_DEVICE_TABLE(of, ctucan_of_match); static struct platform_driver ctucanfd_driver = { .probe = ctucan_platform_probe, - .remove = ctucan_platform_remove, + .remove_new = ctucan_platform_remove, .driver = { .name = DRV_NAME, .pm = &ctucan_platform_pm_ops, diff --git a/drivers/net/can/dev/skb.c b/drivers/net/can/dev/skb.c index 241ec636e91f..f6d05b3ef59a 100644 --- a/drivers/net/can/dev/skb.c +++ b/drivers/net/can/dev/skb.c @@ -54,7 +54,8 @@ int can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, /* check flag whether this packet has to be looped back */ if (!(dev->flags & IFF_ECHO) || (skb->protocol != htons(ETH_P_CAN) && - skb->protocol != htons(ETH_P_CANFD))) { + skb->protocol != htons(ETH_P_CANFD) && + skb->protocol != htons(ETH_P_CANXL))) { kfree_skb(skb); return 0; } diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c index 6d638c93977b..ff0fc18baf13 100644 --- a/drivers/net/can/flexcan/flexcan-core.c +++ b/drivers/net/can/flexcan/flexcan-core.c @@ -2218,7 +2218,7 @@ static int flexcan_probe(struct platform_device *pdev) return err; } -static int flexcan_remove(struct platform_device *pdev) +static void flexcan_remove(struct platform_device *pdev) { struct net_device *dev = platform_get_drvdata(pdev); @@ -2227,8 +2227,6 @@ static int flexcan_remove(struct platform_device *pdev) unregister_flexcandev(dev); pm_runtime_disable(&pdev->dev); free_candev(dev); - - return 0; } static int __maybe_unused flexcan_suspend(struct device *device) @@ -2379,7 +2377,7 @@ static struct platform_driver flexcan_driver = { .of_match_table = flexcan_of_match, }, .probe = flexcan_probe, - .remove = flexcan_remove, + .remove_new = flexcan_remove, .id_table = flexcan_id_table, }; diff --git a/drivers/net/can/grcan.c b/drivers/net/can/grcan.c index 4bedcc3eea0d..3174efdae271 100644 --- a/drivers/net/can/grcan.c +++ b/drivers/net/can/grcan.c @@ -1696,7 +1696,7 @@ exit_error: return err; } -static int grcan_remove(struct platform_device *ofdev) +static void grcan_remove(struct platform_device *ofdev) { struct net_device *dev = platform_get_drvdata(ofdev); struct grcan_priv *priv = netdev_priv(dev); @@ -1706,8 +1706,6 @@ static int grcan_remove(struct platform_device *ofdev) irq_dispose_mapping(dev->irq); netif_napi_del(&priv->napi); free_candev(dev); - - return 0; } static const struct of_device_id grcan_match[] = { @@ -1726,7 +1724,7 @@ static struct platform_driver grcan_driver = { .of_match_table = grcan_match, }, .probe = grcan_probe, - .remove = grcan_remove, + .remove_new = grcan_remove, }; module_platform_driver(grcan_driver); diff --git a/drivers/net/can/ifi_canfd/ifi_canfd.c b/drivers/net/can/ifi_canfd/ifi_canfd.c index 07eaf724a572..1d6642c94f2f 100644 --- a/drivers/net/can/ifi_canfd/ifi_canfd.c +++ b/drivers/net/can/ifi_canfd/ifi_canfd.c @@ -1013,15 +1013,13 @@ err_reg: return ret; } -static int ifi_canfd_plat_remove(struct platform_device *pdev) +static void ifi_canfd_plat_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); unregister_candev(ndev); platform_set_drvdata(pdev, NULL); free_candev(ndev); - - return 0; } static const struct of_device_id ifi_canfd_of_table[] = { @@ -1036,7 +1034,7 @@ static struct platform_driver ifi_canfd_plat_driver = { .of_match_table = ifi_canfd_of_table, }, .probe = ifi_canfd_plat_probe, - .remove = ifi_canfd_plat_remove, + .remove_new = ifi_canfd_plat_remove, }; module_platform_driver(ifi_canfd_plat_driver); diff --git a/drivers/net/can/janz-ican3.c b/drivers/net/can/janz-ican3.c index 0732a5092141..d048ea565b89 100644 --- a/drivers/net/can/janz-ican3.c +++ b/drivers/net/can/janz-ican3.c @@ -2023,7 +2023,7 @@ out_return: return ret; } -static int ican3_remove(struct platform_device *pdev) +static void ican3_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); struct ican3_dev *mod = netdev_priv(ndev); @@ -2042,8 +2042,6 @@ static int ican3_remove(struct platform_device *pdev) iounmap(mod->dpm); free_candev(ndev); - - return 0; } static struct platform_driver ican3_driver = { @@ -2051,7 +2049,7 @@ static struct platform_driver ican3_driver = { .name = DRV_NAME, }, .probe = ican3_probe, - .remove = ican3_remove, + .remove_new = ican3_remove, }; module_platform_driver(ican3_driver); diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 53e8a914c88b..be189edb256c 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -71,10 +71,12 @@ MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices"); #define KVASER_PCIEFD_SYSID_BUILD_REG (KVASER_PCIEFD_SYSID_BASE + 0x14) /* Shared receive buffer registers */ #define KVASER_PCIEFD_SRB_BASE 0x1f200 +#define KVASER_PCIEFD_SRB_FIFO_LAST_REG (KVASER_PCIEFD_SRB_BASE + 0x1f4) #define KVASER_PCIEFD_SRB_CMD_REG (KVASER_PCIEFD_SRB_BASE + 0x200) #define KVASER_PCIEFD_SRB_IEN_REG (KVASER_PCIEFD_SRB_BASE + 0x204) #define KVASER_PCIEFD_SRB_IRQ_REG (KVASER_PCIEFD_SRB_BASE + 0x20c) #define KVASER_PCIEFD_SRB_STAT_REG (KVASER_PCIEFD_SRB_BASE + 0x210) +#define KVASER_PCIEFD_SRB_RX_NR_PACKETS_REG (KVASER_PCIEFD_SRB_BASE + 0x214) #define KVASER_PCIEFD_SRB_CTRL_REG (KVASER_PCIEFD_SRB_BASE + 0x218) /* EPCS flash controller registers */ #define KVASER_PCIEFD_SPI_BASE 0x1fc00 @@ -111,6 +113,9 @@ MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices"); /* DMA support */ #define KVASER_PCIEFD_SRB_STAT_DMA BIT(24) +/* SRB current packet level */ +#define KVASER_PCIEFD_SRB_RX_NR_PACKETS_MASK 0xff + /* DMA Enable */ #define KVASER_PCIEFD_SRB_CTRL_DMA_ENABLE BIT(0) @@ -526,7 +531,7 @@ static int kvaser_pciefd_set_tx_irq(struct kvaser_pciefd_can *can) KVASER_PCIEFD_KCAN_IRQ_TOF | KVASER_PCIEFD_KCAN_IRQ_ABD | KVASER_PCIEFD_KCAN_IRQ_TAE | KVASER_PCIEFD_KCAN_IRQ_TAL | KVASER_PCIEFD_KCAN_IRQ_FDIC | KVASER_PCIEFD_KCAN_IRQ_BPP | - KVASER_PCIEFD_KCAN_IRQ_TAR | KVASER_PCIEFD_KCAN_IRQ_TFD; + KVASER_PCIEFD_KCAN_IRQ_TAR; iowrite32(msk, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); @@ -554,6 +559,8 @@ static void kvaser_pciefd_setup_controller(struct kvaser_pciefd_can *can) if (can->can.ctrlmode & CAN_CTRLMODE_LISTENONLY) mode |= KVASER_PCIEFD_KCAN_MODE_LOM; + else + mode &= ~KVASER_PCIEFD_KCAN_MODE_LOM; mode |= KVASER_PCIEFD_KCAN_MODE_EEN; mode |= KVASER_PCIEFD_KCAN_MODE_EPEN; @@ -572,7 +579,7 @@ static void kvaser_pciefd_start_controller_flush(struct kvaser_pciefd_can *can) spin_lock_irqsave(&can->lock, irq); iowrite32(-1, can->reg_base + KVASER_PCIEFD_KCAN_IRQ_REG); - iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD | KVASER_PCIEFD_KCAN_IRQ_TFD, + iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); status = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_STAT_REG); @@ -615,7 +622,7 @@ static int kvaser_pciefd_bus_on(struct kvaser_pciefd_can *can) iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); iowrite32(-1, can->reg_base + KVASER_PCIEFD_KCAN_IRQ_REG); - iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD | KVASER_PCIEFD_KCAN_IRQ_TFD, + iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); mode = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_MODE_REG); @@ -719,6 +726,7 @@ static int kvaser_pciefd_stop(struct net_device *netdev) iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); del_timer(&can->bec_poll_timer); } + can->can.state = CAN_STATE_STOPPED; close_candev(netdev); return ret; @@ -1007,8 +1015,7 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie) SET_NETDEV_DEV(netdev, &pcie->pci->dev); iowrite32(-1, can->reg_base + KVASER_PCIEFD_KCAN_IRQ_REG); - iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD | - KVASER_PCIEFD_KCAN_IRQ_TFD, + iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); pcie->can[i] = can; @@ -1058,6 +1065,7 @@ static int kvaser_pciefd_setup_dma(struct kvaser_pciefd *pcie) { int i; u32 srb_status; + u32 srb_packet_count; dma_addr_t dma_addr[KVASER_PCIEFD_DMA_COUNT]; /* Disable the DMA */ @@ -1085,6 +1093,15 @@ static int kvaser_pciefd_setup_dma(struct kvaser_pciefd *pcie) KVASER_PCIEFD_SRB_CMD_RDB1, pcie->reg_base + KVASER_PCIEFD_SRB_CMD_REG); + /* Empty Rx FIFO */ + srb_packet_count = ioread32(pcie->reg_base + KVASER_PCIEFD_SRB_RX_NR_PACKETS_REG) & + KVASER_PCIEFD_SRB_RX_NR_PACKETS_MASK; + while (srb_packet_count) { + /* Drop current packet in FIFO */ + ioread32(pcie->reg_base + KVASER_PCIEFD_SRB_FIFO_LAST_REG); + srb_packet_count--; + } + srb_status = ioread32(pcie->reg_base + KVASER_PCIEFD_SRB_STAT_REG); if (!(srb_status & KVASER_PCIEFD_SRB_STAT_DI)) { dev_err(&pcie->pci->dev, "DMA not idle before enabling\n"); @@ -1425,9 +1442,6 @@ static int kvaser_pciefd_handle_status_packet(struct kvaser_pciefd *pcie, cmd = KVASER_PCIEFD_KCAN_CMD_AT; cmd |= ++can->cmd_seq << KVASER_PCIEFD_KCAN_CMD_SEQ_SHIFT; iowrite32(cmd, can->reg_base + KVASER_PCIEFD_KCAN_CMD_REG); - - iowrite32(KVASER_PCIEFD_KCAN_IRQ_TFD, - can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); } else if (p->header[0] & KVASER_PCIEFD_SPACK_IDET && p->header[0] & KVASER_PCIEFD_SPACK_IRM && cmdseq == (p->header[1] & KVASER_PCIEFD_PACKET_SEQ_MSK) && @@ -1714,15 +1728,6 @@ static int kvaser_pciefd_transmit_irq(struct kvaser_pciefd_can *can) if (irq & KVASER_PCIEFD_KCAN_IRQ_TOF) netdev_err(can->can.dev, "Tx FIFO overflow\n"); - if (irq & KVASER_PCIEFD_KCAN_IRQ_TFD) { - u8 count = ioread32(can->reg_base + - KVASER_PCIEFD_KCAN_TX_NPACKETS_REG) & 0xff; - - if (count == 0) - iowrite32(KVASER_PCIEFD_KCAN_CTRL_EFLUSH, - can->reg_base + KVASER_PCIEFD_KCAN_CTRL_REG); - } - if (irq & KVASER_PCIEFD_KCAN_IRQ_BPP) netdev_err(can->can.dev, "Fail to change bittiming, when not in reset mode\n"); @@ -1824,6 +1829,11 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev, if (err) goto err_teardown_can_ctrls; + err = request_irq(pcie->pci->irq, kvaser_pciefd_irq_handler, + IRQF_SHARED, KVASER_PCIEFD_DRV_NAME, pcie); + if (err) + goto err_teardown_can_ctrls; + iowrite32(KVASER_PCIEFD_SRB_IRQ_DPD0 | KVASER_PCIEFD_SRB_IRQ_DPD1, pcie->reg_base + KVASER_PCIEFD_SRB_IRQ_REG); @@ -1844,11 +1854,6 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev, iowrite32(KVASER_PCIEFD_SRB_CMD_RDB1, pcie->reg_base + KVASER_PCIEFD_SRB_CMD_REG); - err = request_irq(pcie->pci->irq, kvaser_pciefd_irq_handler, - IRQF_SHARED, KVASER_PCIEFD_DRV_NAME, pcie); - if (err) - goto err_teardown_can_ctrls; - err = kvaser_pciefd_reg_candev(pcie); if (err) goto err_free_irq; @@ -1856,6 +1861,8 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev, return 0; err_free_irq: + /* Disable PCI interrupts */ + iowrite32(0, pcie->reg_base + KVASER_PCIEFD_IEN_REG); free_irq(pcie->pci->irq, pcie); err_teardown_can_ctrls: diff --git a/drivers/net/can/m_can/m_can_platform.c b/drivers/net/can/m_can/m_can_platform.c index 9c1dcf838006..94dc82644113 100644 --- a/drivers/net/can/m_can/m_can_platform.c +++ b/drivers/net/can/m_can/m_can_platform.c @@ -164,7 +164,7 @@ static __maybe_unused int m_can_resume(struct device *dev) return m_can_class_resume(dev); } -static int m_can_plat_remove(struct platform_device *pdev) +static void m_can_plat_remove(struct platform_device *pdev) { struct m_can_plat_priv *priv = platform_get_drvdata(pdev); struct m_can_classdev *mcan_class = &priv->cdev; @@ -172,8 +172,6 @@ static int m_can_plat_remove(struct platform_device *pdev) m_can_class_unregister(mcan_class); m_can_class_free_dev(mcan_class->net); - - return 0; } static int __maybe_unused m_can_runtime_suspend(struct device *dev) @@ -223,7 +221,7 @@ static struct platform_driver m_can_plat_driver = { .pm = &m_can_pmops, }, .probe = m_can_plat_probe, - .remove = m_can_plat_remove, + .remove_new = m_can_plat_remove, }; module_platform_driver(m_can_plat_driver); diff --git a/drivers/net/can/mscan/mpc5xxx_can.c b/drivers/net/can/mscan/mpc5xxx_can.c index b0ed798ae70f..4837df6efa92 100644 --- a/drivers/net/can/mscan/mpc5xxx_can.c +++ b/drivers/net/can/mscan/mpc5xxx_can.c @@ -349,7 +349,7 @@ exit_unmap_mem: return err; } -static int mpc5xxx_can_remove(struct platform_device *ofdev) +static void mpc5xxx_can_remove(struct platform_device *ofdev) { const struct of_device_id *match; const struct mpc5xxx_can_data *data; @@ -365,8 +365,6 @@ static int mpc5xxx_can_remove(struct platform_device *ofdev) iounmap(priv->reg_base); irq_dispose_mapping(dev->irq); free_candev(dev); - - return 0; } #ifdef CONFIG_PM @@ -437,7 +435,7 @@ static struct platform_driver mpc5xxx_can_driver = { .of_match_table = mpc5xxx_can_table, }, .probe = mpc5xxx_can_probe, - .remove = mpc5xxx_can_remove, + .remove_new = mpc5xxx_can_remove, #ifdef CONFIG_PM .suspend = mpc5xxx_can_suspend, .resume = mpc5xxx_can_resume, diff --git a/drivers/net/can/rcar/rcar_can.c b/drivers/net/can/rcar/rcar_can.c index cc43c9c5e38c..f5aa5dbacaf2 100644 --- a/drivers/net/can/rcar/rcar_can.c +++ b/drivers/net/can/rcar/rcar_can.c @@ -824,7 +824,7 @@ fail: return err; } -static int rcar_can_remove(struct platform_device *pdev) +static void rcar_can_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); struct rcar_can_priv *priv = netdev_priv(ndev); @@ -832,7 +832,6 @@ static int rcar_can_remove(struct platform_device *pdev) unregister_candev(ndev); netif_napi_del(&priv->napi); free_candev(ndev); - return 0; } static int __maybe_unused rcar_can_suspend(struct device *dev) @@ -908,7 +907,7 @@ static struct platform_driver rcar_can_driver = { .pm = &rcar_can_pm_ops, }, .probe = rcar_can_probe, - .remove = rcar_can_remove, + .remove_new = rcar_can_remove, }; module_platform_driver(rcar_can_driver); diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c index 963c42f43755..e4d748913439 100644 --- a/drivers/net/can/rcar/rcar_canfd.c +++ b/drivers/net/can/rcar/rcar_canfd.c @@ -2078,7 +2078,7 @@ fail_dev: return err; } -static int rcar_canfd_remove(struct platform_device *pdev) +static void rcar_canfd_remove(struct platform_device *pdev) { struct rcar_canfd_global *gpriv = platform_get_drvdata(pdev); u32 ch; @@ -2096,8 +2096,6 @@ static int rcar_canfd_remove(struct platform_device *pdev) clk_disable_unprepare(gpriv->clkp); reset_control_assert(gpriv->rstc1); reset_control_assert(gpriv->rstc2); - - return 0; } static int __maybe_unused rcar_canfd_suspend(struct device *dev) @@ -2130,7 +2128,7 @@ static struct platform_driver rcar_canfd_driver = { .pm = &rcar_canfd_pm_ops, }, .probe = rcar_canfd_probe, - .remove = rcar_canfd_remove, + .remove_new = rcar_canfd_remove, }; module_platform_driver(rcar_canfd_driver); diff --git a/drivers/net/can/sja1000/sja1000_isa.c b/drivers/net/can/sja1000/sja1000_isa.c index db3e767d5320..fca5a9a1d857 100644 --- a/drivers/net/can/sja1000/sja1000_isa.c +++ b/drivers/net/can/sja1000/sja1000_isa.c @@ -223,7 +223,7 @@ exit: return err; } -static int sja1000_isa_remove(struct platform_device *pdev) +static void sja1000_isa_remove(struct platform_device *pdev) { struct net_device *dev = platform_get_drvdata(pdev); struct sja1000_priv *priv = netdev_priv(dev); @@ -241,13 +241,11 @@ static int sja1000_isa_remove(struct platform_device *pdev) release_region(port[idx], SJA1000_IOSIZE); } free_sja1000dev(dev); - - return 0; } static struct platform_driver sja1000_isa_driver = { .probe = sja1000_isa_probe, - .remove = sja1000_isa_remove, + .remove_new = sja1000_isa_remove, .driver = { .name = DRV_NAME, }, diff --git a/drivers/net/can/sja1000/sja1000_platform.c b/drivers/net/can/sja1000/sja1000_platform.c index 6779d5357069..b4889b5746e5 100644 --- a/drivers/net/can/sja1000/sja1000_platform.c +++ b/drivers/net/can/sja1000/sja1000_platform.c @@ -317,19 +317,17 @@ static int sp_probe(struct platform_device *pdev) return err; } -static int sp_remove(struct platform_device *pdev) +static void sp_remove(struct platform_device *pdev) { struct net_device *dev = platform_get_drvdata(pdev); unregister_sja1000dev(dev); free_sja1000dev(dev); - - return 0; } static struct platform_driver sp_driver = { .probe = sp_probe, - .remove = sp_remove, + .remove_new = sp_remove, .driver = { .name = DRV_NAME, .of_match_table = sp_of_table, diff --git a/drivers/net/can/softing/softing_main.c b/drivers/net/can/softing/softing_main.c index c72f505d29fe..bd25137062c5 100644 --- a/drivers/net/can/softing/softing_main.c +++ b/drivers/net/can/softing/softing_main.c @@ -729,7 +729,7 @@ static const struct attribute_group softing_pdev_group = { /* * platform driver */ -static int softing_pdev_remove(struct platform_device *pdev) +static void softing_pdev_remove(struct platform_device *pdev) { struct softing *card = platform_get_drvdata(pdev); int j; @@ -747,7 +747,6 @@ static int softing_pdev_remove(struct platform_device *pdev) iounmap(card->dpram); kfree(card); - return 0; } static int softing_pdev_probe(struct platform_device *pdev) @@ -855,7 +854,7 @@ static struct platform_driver softing_driver = { .name = KBUILD_MODNAME, }, .probe = softing_pdev_probe, - .remove = softing_pdev_remove, + .remove_new = softing_pdev_remove, }; module_platform_driver(softing_driver); diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c index 2b78f9197681..0827830bbf28 100644 --- a/drivers/net/can/sun4i_can.c +++ b/drivers/net/can/sun4i_can.c @@ -791,14 +791,12 @@ static const struct of_device_id sun4ican_of_match[] = { MODULE_DEVICE_TABLE(of, sun4ican_of_match); -static int sun4ican_remove(struct platform_device *pdev) +static void sun4ican_remove(struct platform_device *pdev) { struct net_device *dev = platform_get_drvdata(pdev); unregister_netdev(dev); free_candev(dev); - - return 0; } static int sun4ican_probe(struct platform_device *pdev) @@ -901,7 +899,7 @@ static struct platform_driver sun4i_can_driver = { .of_match_table = sun4ican_of_match, }, .probe = sun4ican_probe, - .remove = sun4ican_remove, + .remove_new = sun4ican_remove, }; module_platform_driver(sun4i_can_driver); diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c index 27700f72eac2..9bab0b4cc449 100644 --- a/drivers/net/can/ti_hecc.c +++ b/drivers/net/can/ti_hecc.c @@ -963,7 +963,7 @@ probe_exit_candev: return err; } -static int ti_hecc_remove(struct platform_device *pdev) +static void ti_hecc_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); struct ti_hecc_priv *priv = netdev_priv(ndev); @@ -973,8 +973,6 @@ static int ti_hecc_remove(struct platform_device *pdev) clk_put(priv->clk); can_rx_offload_del(&priv->offload); free_candev(ndev); - - return 0; } #ifdef CONFIG_PM @@ -1028,7 +1026,7 @@ static struct platform_driver ti_hecc_driver = { .of_match_table = ti_hecc_dt_ids, }, .probe = ti_hecc_probe, - .remove = ti_hecc_remove, + .remove_new = ti_hecc_remove, .suspend = ti_hecc_suspend, .resume = ti_hecc_resume, }; diff --git a/drivers/net/can/usb/Kconfig b/drivers/net/can/usb/Kconfig index 445504ababce..58fcd2b34820 100644 --- a/drivers/net/can/usb/Kconfig +++ b/drivers/net/can/usb/Kconfig @@ -38,6 +38,18 @@ config CAN_ETAS_ES58X To compile this driver as a module, choose M here: the module will be called etas_es58x. +config CAN_F81604 + tristate "Fintek F81604 USB to 2CAN interface" + help + This driver supports the Fintek F81604 USB to 2CAN interface. + The device can support CAN2.0A/B protocol and also support + 2 output pins to control external terminator (optional). + + To compile this driver as a module, choose M here: the module will + be called f81604. + + (see also https://www.fintek.com.tw). + config CAN_GS_USB tristate "Geschwister Schneider UG and candleLight compatible interfaces" help diff --git a/drivers/net/can/usb/Makefile b/drivers/net/can/usb/Makefile index 1ea16be5743b..8b11088e9a59 100644 --- a/drivers/net/can/usb/Makefile +++ b/drivers/net/can/usb/Makefile @@ -7,6 +7,7 @@ obj-$(CONFIG_CAN_8DEV_USB) += usb_8dev.o obj-$(CONFIG_CAN_EMS_USB) += ems_usb.o obj-$(CONFIG_CAN_ESD_USB) += esd_usb.o obj-$(CONFIG_CAN_ETAS_ES58X) += etas_es58x/ +obj-$(CONFIG_CAN_F81604) += f81604.o obj-$(CONFIG_CAN_GS_USB) += gs_usb.o obj-$(CONFIG_CAN_KVASER_USB) += kvaser_usb/ obj-$(CONFIG_CAN_MCBA_USB) += mcba_usb.o diff --git a/drivers/net/can/usb/f81604.c b/drivers/net/can/usb/f81604.c new file mode 100644 index 000000000000..ec8cef7fd2d5 --- /dev/null +++ b/drivers/net/can/usb/f81604.c @@ -0,0 +1,1201 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Fintek F81604 USB-to-2CAN controller driver. + * + * Copyright (C) 2023 Ji-Ze Hong (Peter Hong) <peter_hong@fintek.com.tw> + */ +#include <linux/bitfield.h> +#include <linux/netdevice.h> +#include <linux/units.h> +#include <linux/usb.h> + +#include <linux/can.h> +#include <linux/can/dev.h> +#include <linux/can/error.h> +#include <linux/can/platform/sja1000.h> + +#include <asm-generic/unaligned.h> + +/* vendor and product id */ +#define F81604_VENDOR_ID 0x2c42 +#define F81604_PRODUCT_ID 0x1709 +#define F81604_CAN_CLOCK (12 * MEGA) +#define F81604_MAX_DEV 2 +#define F81604_SET_DEVICE_RETRY 10 + +#define F81604_USB_TIMEOUT 2000 +#define F81604_SET_GET_REGISTER 0xA0 +#define F81604_PORT_OFFSET 0x1000 +#define F81604_MAX_RX_URBS 4 + +#define F81604_CMD_DATA 0x00 + +#define F81604_DLC_LEN_MASK GENMASK(3, 0) +#define F81604_DLC_EFF_BIT BIT(7) +#define F81604_DLC_RTR_BIT BIT(6) + +#define F81604_SFF_SHIFT 5 +#define F81604_EFF_SHIFT 3 + +#define F81604_BRP_MASK GENMASK(5, 0) +#define F81604_SJW_MASK GENMASK(7, 6) + +#define F81604_SEG1_MASK GENMASK(3, 0) +#define F81604_SEG2_MASK GENMASK(6, 4) + +#define F81604_CLEAR_ALC 0 +#define F81604_CLEAR_ECC 1 +#define F81604_CLEAR_OVERRUN 2 + +/* device setting */ +#define F81604_CTRL_MODE_REG 0x80 +#define F81604_TX_ONESHOT (0x03 << 3) +#define F81604_TX_NORMAL (0x01 << 3) +#define F81604_RX_AUTO_RELEASE_BUF BIT(1) +#define F81604_INT_WHEN_CHANGE BIT(0) + +#define F81604_TERMINATOR_REG 0x105 +#define F81604_CAN0_TERM BIT(2) +#define F81604_CAN1_TERM BIT(3) + +#define F81604_TERMINATION_DISABLED CAN_TERMINATION_DISABLED +#define F81604_TERMINATION_ENABLED 120 + +/* SJA1000 registers - manual section 6.4 (Pelican Mode) */ +#define F81604_SJA1000_MOD 0x00 +#define F81604_SJA1000_CMR 0x01 +#define F81604_SJA1000_IR 0x03 +#define F81604_SJA1000_IER 0x04 +#define F81604_SJA1000_ALC 0x0B +#define F81604_SJA1000_ECC 0x0C +#define F81604_SJA1000_RXERR 0x0E +#define F81604_SJA1000_TXERR 0x0F +#define F81604_SJA1000_ACCC0 0x10 +#define F81604_SJA1000_ACCM0 0x14 +#define F81604_MAX_FILTER_CNT 4 + +/* Common registers - manual section 6.5 */ +#define F81604_SJA1000_BTR0 0x06 +#define F81604_SJA1000_BTR1 0x07 +#define F81604_SJA1000_BTR1_SAMPLE_TRIPLE BIT(7) +#define F81604_SJA1000_OCR 0x08 +#define F81604_SJA1000_CDR 0x1F + +/* mode register */ +#define F81604_SJA1000_MOD_RM 0x01 +#define F81604_SJA1000_MOD_LOM 0x02 +#define F81604_SJA1000_MOD_STM 0x04 + +/* commands */ +#define F81604_SJA1000_CMD_CDO 0x08 + +/* interrupt sources */ +#define F81604_SJA1000_IRQ_BEI 0x80 +#define F81604_SJA1000_IRQ_ALI 0x40 +#define F81604_SJA1000_IRQ_EPI 0x20 +#define F81604_SJA1000_IRQ_DOI 0x08 +#define F81604_SJA1000_IRQ_EI 0x04 +#define F81604_SJA1000_IRQ_TI 0x02 +#define F81604_SJA1000_IRQ_RI 0x01 +#define F81604_SJA1000_IRQ_ALL 0xFF +#define F81604_SJA1000_IRQ_OFF 0x00 + +/* status register content */ +#define F81604_SJA1000_SR_BS 0x80 +#define F81604_SJA1000_SR_ES 0x40 +#define F81604_SJA1000_SR_TCS 0x08 + +/* ECC register */ +#define F81604_SJA1000_ECC_SEG 0x1F +#define F81604_SJA1000_ECC_DIR 0x20 +#define F81604_SJA1000_ECC_BIT 0x00 +#define F81604_SJA1000_ECC_FORM 0x40 +#define F81604_SJA1000_ECC_STUFF 0x80 +#define F81604_SJA1000_ECC_MASK 0xc0 + +/* ALC register */ +#define F81604_SJA1000_ALC_MASK 0x1f + +/* table of devices that work with this driver */ +static const struct usb_device_id f81604_table[] = { + { USB_DEVICE(F81604_VENDOR_ID, F81604_PRODUCT_ID) }, + {} /* Terminating entry */ +}; + +MODULE_DEVICE_TABLE(usb, f81604_table); + +static const struct ethtool_ops f81604_ethtool_ops = { + .get_ts_info = ethtool_op_get_ts_info, +}; + +static const u16 f81604_termination[] = { F81604_TERMINATION_DISABLED, + F81604_TERMINATION_ENABLED }; + +struct f81604_priv { + struct net_device *netdev[F81604_MAX_DEV]; +}; + +struct f81604_port_priv { + struct can_priv can; + struct net_device *netdev; + struct sk_buff *echo_skb; + + unsigned long clear_flags; + struct work_struct clear_reg_work; + + struct usb_device *dev; + struct usb_interface *intf; + + struct usb_anchor urbs_anchor; +}; + +/* Interrupt endpoint data format: + * Byte 0: Status register. + * Byte 1: Interrupt register. + * Byte 2: Interrupt enable register. + * Byte 3: Arbitration lost capture(ALC) register. + * Byte 4: Error code capture(ECC) register. + * Byte 5: Error warning limit register. + * Byte 6: RX error counter register. + * Byte 7: TX error counter register. + * Byte 8: Reserved. + */ +struct f81604_int_data { + u8 sr; + u8 isrc; + u8 ier; + u8 alc; + u8 ecc; + u8 ewlr; + u8 rxerr; + u8 txerr; + u8 val; +} __packed __aligned(4); + +struct f81604_sff { + __be16 id; + u8 data[CAN_MAX_DLEN]; +} __packed __aligned(2); + +struct f81604_eff { + __be32 id; + u8 data[CAN_MAX_DLEN]; +} __packed __aligned(2); + +struct f81604_can_frame { + u8 cmd; + + /* According for F81604 DLC define: + * bit 3~0: data length (0~8) + * bit6: is RTR flag. + * bit7: is EFF frame. + */ + u8 dlc; + + union { + struct f81604_sff sff; + struct f81604_eff eff; + }; +} __packed __aligned(2); + +static const u8 bulk_in_addr[F81604_MAX_DEV] = { 2, 4 }; +static const u8 bulk_out_addr[F81604_MAX_DEV] = { 1, 3 }; +static const u8 int_in_addr[F81604_MAX_DEV] = { 1, 3 }; + +static int f81604_write(struct usb_device *dev, u16 reg, u8 data) +{ + int ret; + + ret = usb_control_msg_send(dev, 0, F81604_SET_GET_REGISTER, + USB_TYPE_VENDOR | USB_DIR_OUT, 0, reg, + &data, sizeof(data), F81604_USB_TIMEOUT, + GFP_KERNEL); + if (ret) + dev_err(&dev->dev, "%s: reg: %x data: %x failed: %pe\n", + __func__, reg, data, ERR_PTR(ret)); + + return ret; +} + +static int f81604_read(struct usb_device *dev, u16 reg, u8 *data) +{ + int ret; + + ret = usb_control_msg_recv(dev, 0, F81604_SET_GET_REGISTER, + USB_TYPE_VENDOR | USB_DIR_IN, 0, reg, data, + sizeof(*data), F81604_USB_TIMEOUT, + GFP_KERNEL); + + if (ret < 0) + dev_err(&dev->dev, "%s: reg: %x failed: %pe\n", __func__, reg, + ERR_PTR(ret)); + + return ret; +} + +static int f81604_update_bits(struct usb_device *dev, u16 reg, u8 mask, + u8 data) +{ + int ret; + u8 tmp; + + ret = f81604_read(dev, reg, &tmp); + if (ret) + return ret; + + tmp &= ~mask; + tmp |= (mask & data); + + return f81604_write(dev, reg, tmp); +} + +static int f81604_sja1000_write(struct f81604_port_priv *priv, u16 reg, + u8 data) +{ + int port = priv->netdev->dev_port; + int real_reg; + + real_reg = reg + F81604_PORT_OFFSET * port + F81604_PORT_OFFSET; + return f81604_write(priv->dev, real_reg, data); +} + +static int f81604_sja1000_read(struct f81604_port_priv *priv, u16 reg, + u8 *data) +{ + int port = priv->netdev->dev_port; + int real_reg; + + real_reg = reg + F81604_PORT_OFFSET * port + F81604_PORT_OFFSET; + return f81604_read(priv->dev, real_reg, data); +} + +static int f81604_set_reset_mode(struct f81604_port_priv *priv) +{ + int ret, i; + u8 tmp; + + /* disable interrupts */ + ret = f81604_sja1000_write(priv, F81604_SJA1000_IER, + F81604_SJA1000_IRQ_OFF); + if (ret) + return ret; + + for (i = 0; i < F81604_SET_DEVICE_RETRY; i++) { + ret = f81604_sja1000_read(priv, F81604_SJA1000_MOD, &tmp); + if (ret) + return ret; + + /* check reset bit */ + if (tmp & F81604_SJA1000_MOD_RM) { + priv->can.state = CAN_STATE_STOPPED; + return 0; + } + + /* reset chip */ + ret = f81604_sja1000_write(priv, F81604_SJA1000_MOD, + F81604_SJA1000_MOD_RM); + if (ret) + return ret; + } + + return -EPERM; +} + +static int f81604_set_normal_mode(struct f81604_port_priv *priv) +{ + u8 tmp, ier = 0; + u8 mod_reg = 0; + int ret, i; + + for (i = 0; i < F81604_SET_DEVICE_RETRY; i++) { + ret = f81604_sja1000_read(priv, F81604_SJA1000_MOD, &tmp); + if (ret) + return ret; + + /* check reset bit */ + if ((tmp & F81604_SJA1000_MOD_RM) == 0) { + priv->can.state = CAN_STATE_ERROR_ACTIVE; + /* enable interrupts, RI handled by bulk-in */ + ier = F81604_SJA1000_IRQ_ALL & ~F81604_SJA1000_IRQ_RI; + if (!(priv->can.ctrlmode & + CAN_CTRLMODE_BERR_REPORTING)) + ier &= ~F81604_SJA1000_IRQ_BEI; + + return f81604_sja1000_write(priv, F81604_SJA1000_IER, + ier); + } + + /* set chip to normal mode */ + if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY) + mod_reg |= F81604_SJA1000_MOD_LOM; + if (priv->can.ctrlmode & CAN_CTRLMODE_PRESUME_ACK) + mod_reg |= F81604_SJA1000_MOD_STM; + + ret = f81604_sja1000_write(priv, F81604_SJA1000_MOD, mod_reg); + if (ret) + return ret; + } + + return -EPERM; +} + +static int f81604_chipset_init(struct f81604_port_priv *priv) +{ + int i, ret; + + /* set clock divider and output control register */ + ret = f81604_sja1000_write(priv, F81604_SJA1000_CDR, + CDR_CBP | CDR_PELICAN); + if (ret) + return ret; + + /* set acceptance filter (accept all) */ + for (i = 0; i < F81604_MAX_FILTER_CNT; ++i) { + ret = f81604_sja1000_write(priv, F81604_SJA1000_ACCC0 + i, 0); + if (ret) + return ret; + } + + for (i = 0; i < F81604_MAX_FILTER_CNT; ++i) { + ret = f81604_sja1000_write(priv, F81604_SJA1000_ACCM0 + i, + 0xFF); + if (ret) + return ret; + } + + return f81604_sja1000_write(priv, F81604_SJA1000_OCR, + OCR_TX0_PUSHPULL | OCR_TX1_PUSHPULL | + OCR_MODE_NORMAL); +} + +static void f81604_process_rx_packet(struct net_device *netdev, + struct f81604_can_frame *frame) +{ + struct net_device_stats *stats = &netdev->stats; + struct can_frame *cf; + struct sk_buff *skb; + + if (frame->cmd != F81604_CMD_DATA) + return; + + skb = alloc_can_skb(netdev, &cf); + if (!skb) { + stats->rx_dropped++; + return; + } + + cf->len = can_cc_dlc2len(frame->dlc & F81604_DLC_LEN_MASK); + + if (frame->dlc & F81604_DLC_EFF_BIT) { + cf->can_id = get_unaligned_be32(&frame->eff.id) >> + F81604_EFF_SHIFT; + cf->can_id |= CAN_EFF_FLAG; + + if (!(frame->dlc & F81604_DLC_RTR_BIT)) + memcpy(cf->data, frame->eff.data, cf->len); + } else { + cf->can_id = get_unaligned_be16(&frame->sff.id) >> + F81604_SFF_SHIFT; + + if (!(frame->dlc & F81604_DLC_RTR_BIT)) + memcpy(cf->data, frame->sff.data, cf->len); + } + + if (frame->dlc & F81604_DLC_RTR_BIT) + cf->can_id |= CAN_RTR_FLAG; + else + stats->rx_bytes += cf->len; + + stats->rx_packets++; + netif_rx(skb); +} + +static void f81604_read_bulk_callback(struct urb *urb) +{ + struct f81604_can_frame *frame = urb->transfer_buffer; + struct net_device *netdev = urb->context; + int ret; + + if (!netif_device_present(netdev)) + return; + + if (urb->status) + netdev_info(netdev, "%s: URB aborted %pe\n", __func__, + ERR_PTR(urb->status)); + + switch (urb->status) { + case 0: /* success */ + break; + + case -ENOENT: + case -EPIPE: + case -EPROTO: + case -ESHUTDOWN: + return; + + default: + goto resubmit_urb; + } + + if (urb->actual_length != sizeof(*frame)) { + netdev_warn(netdev, "URB length %u not equal to %zu\n", + urb->actual_length, sizeof(*frame)); + goto resubmit_urb; + } + + f81604_process_rx_packet(netdev, frame); + +resubmit_urb: + ret = usb_submit_urb(urb, GFP_ATOMIC); + if (ret == -ENODEV) + netif_device_detach(netdev); + else if (ret) + netdev_err(netdev, + "%s: failed to resubmit read bulk urb: %pe\n", + __func__, ERR_PTR(ret)); +} + +static void f81604_handle_tx(struct f81604_port_priv *priv, + struct f81604_int_data *data) +{ + struct net_device *netdev = priv->netdev; + struct net_device_stats *stats = &netdev->stats; + + /* transmission buffer released */ + if (priv->can.ctrlmode & CAN_CTRLMODE_ONE_SHOT && + !(data->sr & F81604_SJA1000_SR_TCS)) { + stats->tx_errors++; + can_free_echo_skb(netdev, 0, NULL); + } else { + /* transmission complete */ + stats->tx_bytes += can_get_echo_skb(netdev, 0, NULL); + stats->tx_packets++; + } + + netif_wake_queue(netdev); +} + +static void f81604_handle_can_bus_errors(struct f81604_port_priv *priv, + struct f81604_int_data *data) +{ + enum can_state can_state = priv->can.state; + struct net_device *netdev = priv->netdev; + struct net_device_stats *stats = &netdev->stats; + struct can_frame *cf; + struct sk_buff *skb; + + /* Note: ALC/ECC will not auto clear by read here, must be cleared by + * read register (via clear_reg_work). + */ + + skb = alloc_can_err_skb(netdev, &cf); + if (skb) { + cf->can_id |= CAN_ERR_CNT; + cf->data[6] = data->txerr; + cf->data[7] = data->rxerr; + } + + if (data->isrc & F81604_SJA1000_IRQ_DOI) { + /* data overrun interrupt */ + netdev_dbg(netdev, "data overrun interrupt\n"); + + if (skb) { + cf->can_id |= CAN_ERR_CRTL; + cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW; + } + + stats->rx_over_errors++; + stats->rx_errors++; + + set_bit(F81604_CLEAR_OVERRUN, &priv->clear_flags); + } + + if (data->isrc & F81604_SJA1000_IRQ_EI) { + /* error warning interrupt */ + netdev_dbg(netdev, "error warning interrupt\n"); + + if (data->sr & F81604_SJA1000_SR_BS) + can_state = CAN_STATE_BUS_OFF; + else if (data->sr & F81604_SJA1000_SR_ES) + can_state = CAN_STATE_ERROR_WARNING; + else + can_state = CAN_STATE_ERROR_ACTIVE; + } + + if (data->isrc & F81604_SJA1000_IRQ_BEI) { + /* bus error interrupt */ + netdev_dbg(netdev, "bus error interrupt\n"); + + priv->can.can_stats.bus_error++; + stats->rx_errors++; + + if (skb) { + cf->can_id |= CAN_ERR_PROT | CAN_ERR_BUSERROR; + + /* set error type */ + switch (data->ecc & F81604_SJA1000_ECC_MASK) { + case F81604_SJA1000_ECC_BIT: + cf->data[2] |= CAN_ERR_PROT_BIT; + break; + case F81604_SJA1000_ECC_FORM: + cf->data[2] |= CAN_ERR_PROT_FORM; + break; + case F81604_SJA1000_ECC_STUFF: + cf->data[2] |= CAN_ERR_PROT_STUFF; + break; + default: + break; + } + + /* set error location */ + cf->data[3] = data->ecc & F81604_SJA1000_ECC_SEG; + + /* Error occurred during transmission? */ + if ((data->ecc & F81604_SJA1000_ECC_DIR) == 0) + cf->data[2] |= CAN_ERR_PROT_TX; + } + + set_bit(F81604_CLEAR_ECC, &priv->clear_flags); + } + + if (data->isrc & F81604_SJA1000_IRQ_EPI) { + if (can_state == CAN_STATE_ERROR_PASSIVE) + can_state = CAN_STATE_ERROR_WARNING; + else + can_state = CAN_STATE_ERROR_PASSIVE; + + /* error passive interrupt */ + netdev_dbg(netdev, "error passive interrupt: %d\n", can_state); + } + + if (data->isrc & F81604_SJA1000_IRQ_ALI) { + /* arbitration lost interrupt */ + netdev_dbg(netdev, "arbitration lost interrupt\n"); + + priv->can.can_stats.arbitration_lost++; + + if (skb) { + cf->can_id |= CAN_ERR_LOSTARB; + cf->data[0] = data->alc & F81604_SJA1000_ALC_MASK; + } + + set_bit(F81604_CLEAR_ALC, &priv->clear_flags); + } + + if (can_state != priv->can.state) { + enum can_state tx_state, rx_state; + + tx_state = data->txerr >= data->rxerr ? can_state : 0; + rx_state = data->txerr <= data->rxerr ? can_state : 0; + + can_change_state(netdev, cf, tx_state, rx_state); + + if (can_state == CAN_STATE_BUS_OFF) + can_bus_off(netdev); + } + + if (priv->clear_flags) + schedule_work(&priv->clear_reg_work); + + if (skb) + netif_rx(skb); +} + +static void f81604_read_int_callback(struct urb *urb) +{ + struct f81604_int_data *data = urb->transfer_buffer; + struct net_device *netdev = urb->context; + struct f81604_port_priv *priv; + int ret; + + priv = netdev_priv(netdev); + + if (!netif_device_present(netdev)) + return; + + if (urb->status) + netdev_info(netdev, "%s: Int URB aborted: %pe\n", __func__, + ERR_PTR(urb->status)); + + switch (urb->status) { + case 0: /* success */ + break; + + case -ENOENT: + case -EPIPE: + case -EPROTO: + case -ESHUTDOWN: + return; + + default: + goto resubmit_urb; + } + + /* handle Errors */ + if (data->isrc & (F81604_SJA1000_IRQ_DOI | F81604_SJA1000_IRQ_EI | + F81604_SJA1000_IRQ_BEI | F81604_SJA1000_IRQ_EPI | + F81604_SJA1000_IRQ_ALI)) + f81604_handle_can_bus_errors(priv, data); + + /* handle TX */ + if (priv->can.state != CAN_STATE_BUS_OFF && + (data->isrc & F81604_SJA1000_IRQ_TI)) + f81604_handle_tx(priv, data); + +resubmit_urb: + ret = usb_submit_urb(urb, GFP_ATOMIC); + if (ret == -ENODEV) + netif_device_detach(netdev); + else if (ret) + netdev_err(netdev, "%s: failed to resubmit int urb: %pe\n", + __func__, ERR_PTR(ret)); +} + +static void f81604_unregister_urbs(struct f81604_port_priv *priv) +{ + usb_kill_anchored_urbs(&priv->urbs_anchor); +} + +static int f81604_register_urbs(struct f81604_port_priv *priv) +{ + struct net_device *netdev = priv->netdev; + struct f81604_int_data *int_data; + int id = netdev->dev_port; + struct urb *int_urb; + int rx_urb_cnt; + int ret; + + for (rx_urb_cnt = 0; rx_urb_cnt < F81604_MAX_RX_URBS; ++rx_urb_cnt) { + struct f81604_can_frame *frame; + struct urb *rx_urb; + + rx_urb = usb_alloc_urb(0, GFP_KERNEL); + if (!rx_urb) { + ret = -ENOMEM; + break; + } + + frame = kmalloc(sizeof(*frame), GFP_KERNEL); + if (!frame) { + usb_free_urb(rx_urb); + ret = -ENOMEM; + break; + } + + usb_fill_bulk_urb(rx_urb, priv->dev, + usb_rcvbulkpipe(priv->dev, bulk_in_addr[id]), + frame, sizeof(*frame), + f81604_read_bulk_callback, netdev); + + rx_urb->transfer_flags |= URB_FREE_BUFFER; + usb_anchor_urb(rx_urb, &priv->urbs_anchor); + + ret = usb_submit_urb(rx_urb, GFP_KERNEL); + if (ret) { + usb_unanchor_urb(rx_urb); + usb_free_urb(rx_urb); + break; + } + + /* Drop reference, USB core will take care of freeing it */ + usb_free_urb(rx_urb); + } + + if (rx_urb_cnt == 0) { + netdev_warn(netdev, "%s: submit rx urb failed: %pe\n", + __func__, ERR_PTR(ret)); + + goto error; + } + + int_urb = usb_alloc_urb(0, GFP_KERNEL); + if (!int_urb) { + ret = -ENOMEM; + goto error; + } + + int_data = kmalloc(sizeof(*int_data), GFP_KERNEL); + if (!int_data) { + usb_free_urb(int_urb); + ret = -ENOMEM; + goto error; + } + + usb_fill_int_urb(int_urb, priv->dev, + usb_rcvintpipe(priv->dev, int_in_addr[id]), int_data, + sizeof(*int_data), f81604_read_int_callback, netdev, + 1); + + int_urb->transfer_flags |= URB_FREE_BUFFER; + usb_anchor_urb(int_urb, &priv->urbs_anchor); + + ret = usb_submit_urb(int_urb, GFP_KERNEL); + if (ret) { + usb_unanchor_urb(int_urb); + usb_free_urb(int_urb); + + netdev_warn(netdev, "%s: submit int urb failed: %pe\n", + __func__, ERR_PTR(ret)); + goto error; + } + + /* Drop reference, USB core will take care of freeing it */ + usb_free_urb(int_urb); + + return 0; + +error: + f81604_unregister_urbs(priv); + return ret; +} + +static int f81604_start(struct net_device *netdev) +{ + struct f81604_port_priv *priv = netdev_priv(netdev); + int ret; + u8 mode; + u8 tmp; + + mode = F81604_RX_AUTO_RELEASE_BUF | F81604_INT_WHEN_CHANGE; + + /* Set TR/AT mode */ + if (priv->can.ctrlmode & CAN_CTRLMODE_ONE_SHOT) + mode |= F81604_TX_ONESHOT; + else + mode |= F81604_TX_NORMAL; + + ret = f81604_sja1000_write(priv, F81604_CTRL_MODE_REG, mode); + if (ret) + return ret; + + /* set reset mode */ + ret = f81604_set_reset_mode(priv); + if (ret) + return ret; + + ret = f81604_chipset_init(priv); + if (ret) + return ret; + + /* Clear error counters and error code capture */ + ret = f81604_sja1000_write(priv, F81604_SJA1000_TXERR, 0); + if (ret) + return ret; + + ret = f81604_sja1000_write(priv, F81604_SJA1000_RXERR, 0); + if (ret) + return ret; + + /* Read clear for ECC/ALC/IR register */ + ret = f81604_sja1000_read(priv, F81604_SJA1000_ECC, &tmp); + if (ret) + return ret; + + ret = f81604_sja1000_read(priv, F81604_SJA1000_ALC, &tmp); + if (ret) + return ret; + + ret = f81604_sja1000_read(priv, F81604_SJA1000_IR, &tmp); + if (ret) + return ret; + + ret = f81604_register_urbs(priv); + if (ret) + return ret; + + ret = f81604_set_normal_mode(priv); + if (ret) { + f81604_unregister_urbs(priv); + return ret; + } + + return 0; +} + +static int f81604_set_bittiming(struct net_device *dev) +{ + struct f81604_port_priv *priv = netdev_priv(dev); + struct can_bittiming *bt = &priv->can.bittiming; + u8 btr0, btr1; + int ret; + + btr0 = FIELD_PREP(F81604_BRP_MASK, bt->brp - 1) | + FIELD_PREP(F81604_SJW_MASK, bt->sjw - 1); + + btr1 = FIELD_PREP(F81604_SEG1_MASK, + bt->prop_seg + bt->phase_seg1 - 1) | + FIELD_PREP(F81604_SEG2_MASK, bt->phase_seg2 - 1); + + if (priv->can.ctrlmode & CAN_CTRLMODE_3_SAMPLES) + btr1 |= F81604_SJA1000_BTR1_SAMPLE_TRIPLE; + + ret = f81604_sja1000_write(priv, F81604_SJA1000_BTR0, btr0); + if (ret) { + netdev_warn(dev, "%s: Set BTR0 failed: %pe\n", __func__, + ERR_PTR(ret)); + return ret; + } + + ret = f81604_sja1000_write(priv, F81604_SJA1000_BTR1, btr1); + if (ret) { + netdev_warn(dev, "%s: Set BTR1 failed: %pe\n", __func__, + ERR_PTR(ret)); + return ret; + } + + return 0; +} + +static int f81604_set_mode(struct net_device *netdev, enum can_mode mode) +{ + int ret; + + switch (mode) { + case CAN_MODE_START: + ret = f81604_start(netdev); + if (!ret && netif_queue_stopped(netdev)) + netif_wake_queue(netdev); + break; + + default: + ret = -EOPNOTSUPP; + } + + return ret; +} + +static void f81604_write_bulk_callback(struct urb *urb) +{ + struct net_device *netdev = urb->context; + + if (!netif_device_present(netdev)) + return; + + if (urb->status) + netdev_info(netdev, "%s: Tx URB error: %pe\n", __func__, + ERR_PTR(urb->status)); +} + +static void f81604_clear_reg_work(struct work_struct *work) +{ + struct f81604_port_priv *priv; + u8 tmp; + + priv = container_of(work, struct f81604_port_priv, clear_reg_work); + + /* dummy read for clear Arbitration lost capture(ALC) register. */ + if (test_and_clear_bit(F81604_CLEAR_ALC, &priv->clear_flags)) + f81604_sja1000_read(priv, F81604_SJA1000_ALC, &tmp); + + /* dummy read for clear Error code capture(ECC) register. */ + if (test_and_clear_bit(F81604_CLEAR_ECC, &priv->clear_flags)) + f81604_sja1000_read(priv, F81604_SJA1000_ECC, &tmp); + + /* dummy write for clear data overrun flag. */ + if (test_and_clear_bit(F81604_CLEAR_OVERRUN, &priv->clear_flags)) + f81604_sja1000_write(priv, F81604_SJA1000_CMR, + F81604_SJA1000_CMD_CDO); +} + +static netdev_tx_t f81604_start_xmit(struct sk_buff *skb, + struct net_device *netdev) +{ + struct can_frame *cf = (struct can_frame *)skb->data; + struct f81604_port_priv *priv = netdev_priv(netdev); + struct net_device_stats *stats = &netdev->stats; + struct f81604_can_frame *frame; + struct urb *write_urb; + int ret; + + if (can_dev_dropped_skb(netdev, skb)) + return NETDEV_TX_OK; + + netif_stop_queue(netdev); + + write_urb = usb_alloc_urb(0, GFP_ATOMIC); + if (!write_urb) + goto nomem_urb; + + frame = kzalloc(sizeof(*frame), GFP_ATOMIC); + if (!frame) + goto nomem_buf; + + usb_fill_bulk_urb(write_urb, priv->dev, + usb_sndbulkpipe(priv->dev, + bulk_out_addr[netdev->dev_port]), + frame, sizeof(*frame), f81604_write_bulk_callback, + priv->netdev); + + write_urb->transfer_flags |= URB_FREE_BUFFER; + + frame->cmd = F81604_CMD_DATA; + frame->dlc = cf->len; + + if (cf->can_id & CAN_RTR_FLAG) + frame->dlc |= F81604_DLC_RTR_BIT; + + if (cf->can_id & CAN_EFF_FLAG) { + u32 id = (cf->can_id & CAN_EFF_MASK) << F81604_EFF_SHIFT; + + put_unaligned_be32(id, &frame->eff.id); + + frame->dlc |= F81604_DLC_EFF_BIT; + + if (!(cf->can_id & CAN_RTR_FLAG)) + memcpy(&frame->eff.data, cf->data, cf->len); + } else { + u32 id = (cf->can_id & CAN_SFF_MASK) << F81604_SFF_SHIFT; + + put_unaligned_be16(id, &frame->sff.id); + + if (!(cf->can_id & CAN_RTR_FLAG)) + memcpy(&frame->sff.data, cf->data, cf->len); + } + + can_put_echo_skb(skb, netdev, 0, 0); + + ret = usb_submit_urb(write_urb, GFP_ATOMIC); + if (ret) { + netdev_err(netdev, "%s: failed to resubmit tx bulk urb: %pe\n", + __func__, ERR_PTR(ret)); + + can_free_echo_skb(netdev, 0, NULL); + stats->tx_dropped++; + stats->tx_errors++; + + if (ret == -ENODEV) + netif_device_detach(netdev); + else + netif_wake_queue(netdev); + } + + /* let usb core take care of this urb */ + usb_free_urb(write_urb); + + return NETDEV_TX_OK; + +nomem_buf: + usb_free_urb(write_urb); + +nomem_urb: + dev_kfree_skb(skb); + stats->tx_dropped++; + stats->tx_errors++; + netif_wake_queue(netdev); + + return NETDEV_TX_OK; +} + +static int f81604_get_berr_counter(const struct net_device *netdev, + struct can_berr_counter *bec) +{ + struct f81604_port_priv *priv = netdev_priv(netdev); + u8 txerr, rxerr; + int ret; + + ret = f81604_sja1000_read(priv, F81604_SJA1000_TXERR, &txerr); + if (ret) + return ret; + + ret = f81604_sja1000_read(priv, F81604_SJA1000_RXERR, &rxerr); + if (ret) + return ret; + + bec->txerr = txerr; + bec->rxerr = rxerr; + + return 0; +} + +/* Open USB device */ +static int f81604_open(struct net_device *netdev) +{ + int ret; + + ret = open_candev(netdev); + if (ret) + return ret; + + ret = f81604_start(netdev); + if (ret) { + if (ret == -ENODEV) + netif_device_detach(netdev); + + close_candev(netdev); + return ret; + } + + netif_start_queue(netdev); + return 0; +} + +/* Close USB device */ +static int f81604_close(struct net_device *netdev) +{ + struct f81604_port_priv *priv = netdev_priv(netdev); + + f81604_set_reset_mode(priv); + + netif_stop_queue(netdev); + cancel_work_sync(&priv->clear_reg_work); + close_candev(netdev); + + f81604_unregister_urbs(priv); + + return 0; +} + +static const struct net_device_ops f81604_netdev_ops = { + .ndo_open = f81604_open, + .ndo_stop = f81604_close, + .ndo_start_xmit = f81604_start_xmit, + .ndo_change_mtu = can_change_mtu, +}; + +static const struct can_bittiming_const f81604_bittiming_const = { + .name = KBUILD_MODNAME, + .tseg1_min = 1, + .tseg1_max = 16, + .tseg2_min = 1, + .tseg2_max = 8, + .sjw_max = 4, + .brp_min = 1, + .brp_max = 64, + .brp_inc = 1, +}; + +/* Called by the usb core when driver is unloaded or device is removed */ +static void f81604_disconnect(struct usb_interface *intf) +{ + struct f81604_priv *priv = usb_get_intfdata(intf); + int i; + + for (i = 0; i < ARRAY_SIZE(priv->netdev); ++i) { + if (!priv->netdev[i]) + continue; + + unregister_netdev(priv->netdev[i]); + free_candev(priv->netdev[i]); + } +} + +static int __f81604_set_termination(struct usb_device *dev, int idx, u16 term) +{ + u8 mask, data = 0; + + if (idx == 0) + mask = F81604_CAN0_TERM; + else + mask = F81604_CAN1_TERM; + + if (term) + data = mask; + + return f81604_update_bits(dev, F81604_TERMINATOR_REG, mask, data); +} + +static int f81604_set_termination(struct net_device *netdev, u16 term) +{ + struct f81604_port_priv *port_priv = netdev_priv(netdev); + + ASSERT_RTNL(); + + return __f81604_set_termination(port_priv->dev, netdev->dev_port, + term); +} + +static int f81604_probe(struct usb_interface *intf, + const struct usb_device_id *id) +{ + struct usb_device *dev = interface_to_usbdev(intf); + struct net_device *netdev; + struct f81604_priv *priv; + int i, ret; + + priv = devm_kzalloc(&intf->dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + usb_set_intfdata(intf, priv); + + for (i = 0; i < ARRAY_SIZE(priv->netdev); ++i) { + ret = __f81604_set_termination(dev, i, 0); + if (ret) { + dev_err(&intf->dev, + "Setting termination of CH#%d failed: %pe\n", + i, ERR_PTR(ret)); + return ret; + } + } + + for (i = 0; i < ARRAY_SIZE(priv->netdev); ++i) { + struct f81604_port_priv *port_priv; + + netdev = alloc_candev(sizeof(*port_priv), 1); + if (!netdev) { + dev_err(&intf->dev, "Couldn't alloc candev: %d\n", i); + ret = -ENOMEM; + + goto failure_cleanup; + } + + port_priv = netdev_priv(netdev); + + INIT_WORK(&port_priv->clear_reg_work, f81604_clear_reg_work); + init_usb_anchor(&port_priv->urbs_anchor); + + port_priv->intf = intf; + port_priv->dev = dev; + port_priv->netdev = netdev; + port_priv->can.clock.freq = F81604_CAN_CLOCK; + + port_priv->can.termination_const = f81604_termination; + port_priv->can.termination_const_cnt = + ARRAY_SIZE(f81604_termination); + port_priv->can.bittiming_const = &f81604_bittiming_const; + port_priv->can.do_set_bittiming = f81604_set_bittiming; + port_priv->can.do_set_mode = f81604_set_mode; + port_priv->can.do_set_termination = f81604_set_termination; + port_priv->can.do_get_berr_counter = f81604_get_berr_counter; + port_priv->can.ctrlmode_supported = + CAN_CTRLMODE_LISTENONLY | CAN_CTRLMODE_3_SAMPLES | + CAN_CTRLMODE_ONE_SHOT | CAN_CTRLMODE_BERR_REPORTING | + CAN_CTRLMODE_PRESUME_ACK; + + netdev->ethtool_ops = &f81604_ethtool_ops; + netdev->netdev_ops = &f81604_netdev_ops; + netdev->flags |= IFF_ECHO; + netdev->dev_port = i; + + SET_NETDEV_DEV(netdev, &intf->dev); + + ret = register_candev(netdev); + if (ret) { + netdev_err(netdev, "register CAN device failed: %pe\n", + ERR_PTR(ret)); + free_candev(netdev); + + goto failure_cleanup; + } + + priv->netdev[i] = netdev; + } + + return 0; + +failure_cleanup: + f81604_disconnect(intf); + return ret; +} + +static struct usb_driver f81604_driver = { + .name = KBUILD_MODNAME, + .probe = f81604_probe, + .disconnect = f81604_disconnect, + .id_table = f81604_table, +}; + +module_usb_driver(f81604_driver); + +MODULE_AUTHOR("Ji-Ze Hong (Peter Hong) <peter_hong@fintek.com.tw>"); +MODULE_DESCRIPTION("Fintek F81604 USB to 2xCANBUS"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c index 43c812ea1de0..797c69a0314d 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -1898,20 +1898,18 @@ err: * This function frees all the resources allocated to the device. * Return: 0 always */ -static int xcan_remove(struct platform_device *pdev) +static void xcan_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); unregister_candev(ndev); pm_runtime_disable(&pdev->dev); free_candev(ndev); - - return 0; } static struct platform_driver xcan_driver = { .probe = xcan_probe, - .remove = xcan_remove, + .remove_new = xcan_remove, .driver = { .name = DRIVER_NAME, .pm = &xcan_dev_pm_ops, diff --git a/drivers/net/dsa/hirschmann/hellcreek.c b/drivers/net/dsa/hirschmann/hellcreek.c index 595a548bb0a8..af50001ccdd4 100644 --- a/drivers/net/dsa/hirschmann/hellcreek.c +++ b/drivers/net/dsa/hirschmann/hellcreek.c @@ -1885,13 +1885,17 @@ static int hellcreek_port_setup_tc(struct dsa_switch *ds, int port, case TC_SETUP_QDISC_TAPRIO: { struct tc_taprio_qopt_offload *taprio = type_data; - if (!hellcreek_validate_schedule(hellcreek, taprio)) - return -EOPNOTSUPP; + switch (taprio->cmd) { + case TAPRIO_CMD_REPLACE: + if (!hellcreek_validate_schedule(hellcreek, taprio)) + return -EOPNOTSUPP; - if (taprio->enable) return hellcreek_port_set_schedule(ds, port, taprio); - - return hellcreek_port_del_schedule(ds, port); + case TAPRIO_CMD_DESTROY: + return hellcreek_port_del_schedule(ds, port); + default: + return -EOPNOTSUPP; + } } default: return -EOPNOTSUPP; diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c index cbe831875347..ff76444057d2 100644 --- a/drivers/net/dsa/lan9303-core.c +++ b/drivers/net/dsa/lan9303-core.c @@ -1188,8 +1188,6 @@ static int lan9303_port_fdb_add(struct dsa_switch *ds, int port, struct lan9303 *chip = ds->priv; dev_dbg(chip->dev, "%s(%d, %pM, %d)\n", __func__, port, addr, vid); - if (vid) - return -EOPNOTSUPP; return lan9303_alr_add_port(chip, addr, port, false); } @@ -1201,8 +1199,6 @@ static int lan9303_port_fdb_del(struct dsa_switch *ds, int port, struct lan9303 *chip = ds->priv; dev_dbg(chip->dev, "%s(%d, %pM, %d)\n", __func__, port, addr, vid); - if (vid) - return -EOPNOTSUPP; lan9303_alr_del_port(chip, addr, port); return 0; @@ -1462,7 +1458,6 @@ int lan9303_remove(struct lan9303 *chip) /* assert reset to the whole device to prevent it from doing anything */ gpiod_set_value_cansleep(chip->reset_gpio, 1); - gpiod_unexport(chip->reset_gpio); return 0; } diff --git a/drivers/net/dsa/lan9303_i2c.c b/drivers/net/dsa/lan9303_i2c.c index e8844820c3a9..bbbec322bc4f 100644 --- a/drivers/net/dsa/lan9303_i2c.c +++ b/drivers/net/dsa/lan9303_i2c.c @@ -105,7 +105,7 @@ static struct i2c_driver lan9303_i2c_driver = { .name = "LAN9303_I2C", .of_match_table = lan9303_i2c_of_match, }, - .probe_new = lan9303_i2c_probe, + .probe = lan9303_i2c_probe, .remove = lan9303_i2c_remove, .shutdown = lan9303_i2c_shutdown, .id_table = lan9303_i2c_id, diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index f56fca1b1a22..84d502589f8e 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -28,13 +28,13 @@ static void ksz_cfg(struct ksz_device *dev, u32 addr, u8 bits, bool set) { - regmap_update_bits(dev->regmap[0], addr, bits, set ? bits : 0); + regmap_update_bits(ksz_regmap_8(dev), addr, bits, set ? bits : 0); } static void ksz_port_cfg(struct ksz_device *dev, int port, int offset, u8 bits, bool set) { - regmap_update_bits(dev->regmap[0], PORT_CTRL_ADDR(port, offset), + regmap_update_bits(ksz_regmap_8(dev), PORT_CTRL_ADDR(port, offset), bits, set ? bits : 0); } @@ -941,7 +941,6 @@ void ksz8_flush_dyn_mac_table(struct ksz_device *dev, int port) { u8 learn[DSA_MAX_PORTS]; int first, index, cnt; - struct ksz_port *p; const u16 *regs; regs = dev->info->regs; @@ -955,9 +954,6 @@ void ksz8_flush_dyn_mac_table(struct ksz_device *dev, int port) cnt = dev->info->port_cnt; } for (index = first; index < cnt; index++) { - p = &dev->ports[index]; - if (!p->on) - continue; ksz_pread8(dev, index, regs[P_STP_CTRL], &learn[index]); if (!(learn[index] & PORT_LEARN_DISABLE)) ksz_pwrite8(dev, index, regs[P_STP_CTRL], @@ -965,9 +961,6 @@ void ksz8_flush_dyn_mac_table(struct ksz_device *dev, int port) } ksz_cfg(dev, S_FLUSH_TABLE_CTRL, SW_FLUSH_DYN_MAC_TABLE, true); for (index = first; index < cnt; index++) { - p = &dev->ports[index]; - if (!p->on) - continue; if (!(learn[index] & PORT_LEARN_DISABLE)) ksz_pwrite8(dev, index, regs[P_STP_CTRL], learn[index]); } @@ -1338,25 +1331,14 @@ void ksz8_config_cpu_port(struct dsa_switch *ds) ksz_cfg(dev, regs[S_TAIL_TAG_CTRL], masks[SW_TAIL_TAG_ENABLE], true); - p = &dev->ports[dev->cpu_port]; - p->on = 1; - ksz8_port_setup(dev, dev->cpu_port, true); for (i = 0; i < dev->phy_port_cnt; i++) { - p = &dev->ports[i]; - ksz_port_stp_state_set(ds, i, BR_STATE_DISABLED); - - /* Last port may be disabled. */ - if (i == dev->phy_port_cnt) - break; - p->on = 1; } for (i = 0; i < dev->phy_port_cnt; i++) { p = &dev->ports[i]; - if (!p->on) - continue; + if (!ksz_is_ksz88x3(dev)) { ksz_pread8(dev, i, regs[P_REMOTE_STATUS], &remote); if (remote & KSZ8_PORT_FIBER_MODE) @@ -1425,14 +1407,14 @@ int ksz8_setup(struct dsa_switch *ds) ksz_cfg(dev, S_LINK_AGING_CTRL, SW_LINK_AUTO_AGING, true); /* Enable aggressive back off algorithm in half duplex mode. */ - regmap_update_bits(dev->regmap[0], REG_SW_CTRL_1, + regmap_update_bits(ksz_regmap_8(dev), REG_SW_CTRL_1, SW_AGGR_BACKOFF, SW_AGGR_BACKOFF); /* * Make sure unicast VLAN boundary is set as default and * enable no excessive collision drop. */ - regmap_update_bits(dev->regmap[0], REG_SW_CTRL_2, + regmap_update_bits(ksz_regmap_8(dev), REG_SW_CTRL_2, UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP, UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP); diff --git a/drivers/net/dsa/microchip/ksz8863_smi.c b/drivers/net/dsa/microchip/ksz8863_smi.c index 3698112138b7..fd6e2e69a42a 100644 --- a/drivers/net/dsa/microchip/ksz8863_smi.c +++ b/drivers/net/dsa/microchip/ksz8863_smi.c @@ -104,6 +104,7 @@ static const struct regmap_config ksz8863_regmap_config[] = { .cache_type = REGCACHE_NONE, .lock = ksz_regmap_lock, .unlock = ksz_regmap_unlock, + .max_register = U8_MAX, }, { .name = "#16", @@ -113,6 +114,7 @@ static const struct regmap_config ksz8863_regmap_config[] = { .cache_type = REGCACHE_NONE, .lock = ksz_regmap_lock, .unlock = ksz_regmap_unlock, + .max_register = U8_MAX, }, { .name = "#32", @@ -122,11 +124,14 @@ static const struct regmap_config ksz8863_regmap_config[] = { .cache_type = REGCACHE_NONE, .lock = ksz_regmap_lock, .unlock = ksz_regmap_unlock, + .max_register = U8_MAX, } }; static int ksz8863_smi_probe(struct mdio_device *mdiodev) { + struct device *ddev = &mdiodev->dev; + const struct ksz_chip_data *chip; struct regmap_config rc; struct ksz_device *dev; int ret; @@ -136,9 +141,15 @@ static int ksz8863_smi_probe(struct mdio_device *mdiodev) if (!dev) return -ENOMEM; - for (i = 0; i < ARRAY_SIZE(ksz8863_regmap_config); i++) { + chip = device_get_match_data(ddev); + if (!chip) + return -EINVAL; + + for (i = 0; i < __KSZ_NUM_REGMAPS; i++) { rc = ksz8863_regmap_config[i]; rc.lock_arg = &dev->regmap_mutex; + rc.wr_table = chip->wr_table; + rc.rd_table = chip->rd_table; dev->regmap[i] = devm_regmap_init(&mdiodev->dev, ®map_smi[i], dev, &rc); diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index bf13d47c26cf..fc5157a10af5 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -21,25 +21,25 @@ static void ksz_cfg(struct ksz_device *dev, u32 addr, u8 bits, bool set) { - regmap_update_bits(dev->regmap[0], addr, bits, set ? bits : 0); + regmap_update_bits(ksz_regmap_8(dev), addr, bits, set ? bits : 0); } static void ksz_port_cfg(struct ksz_device *dev, int port, int offset, u8 bits, bool set) { - regmap_update_bits(dev->regmap[0], PORT_CTRL_ADDR(port, offset), + regmap_update_bits(ksz_regmap_8(dev), PORT_CTRL_ADDR(port, offset), bits, set ? bits : 0); } static void ksz9477_cfg32(struct ksz_device *dev, u32 addr, u32 bits, bool set) { - regmap_update_bits(dev->regmap[2], addr, bits, set ? bits : 0); + regmap_update_bits(ksz_regmap_32(dev), addr, bits, set ? bits : 0); } static void ksz9477_port_cfg32(struct ksz_device *dev, int port, int offset, u32 bits, bool set) { - regmap_update_bits(dev->regmap[2], PORT_CTRL_ADDR(port, offset), + regmap_update_bits(ksz_regmap_32(dev), PORT_CTRL_ADDR(port, offset), bits, set ? bits : 0); } @@ -52,7 +52,7 @@ int ksz9477_change_mtu(struct ksz_device *dev, int port, int mtu) frame_size = mtu + VLAN_ETH_HLEN + ETH_FCS_LEN; - return regmap_update_bits(dev->regmap[1], REG_SW_MTU__2, + return regmap_update_bits(ksz_regmap_16(dev), REG_SW_MTU__2, REG_SW_MTU_MASK, frame_size); } @@ -60,7 +60,7 @@ static int ksz9477_wait_vlan_ctrl_ready(struct ksz_device *dev) { unsigned int val; - return regmap_read_poll_timeout(dev->regmap[0], REG_SW_VLAN_CTRL, + return regmap_read_poll_timeout(ksz_regmap_8(dev), REG_SW_VLAN_CTRL, val, !(val & VLAN_START), 10, 1000); } @@ -147,7 +147,7 @@ static int ksz9477_wait_alu_ready(struct ksz_device *dev) { unsigned int val; - return regmap_read_poll_timeout(dev->regmap[2], REG_SW_ALU_CTRL__4, + return regmap_read_poll_timeout(ksz_regmap_32(dev), REG_SW_ALU_CTRL__4, val, !(val & ALU_START), 10, 1000); } @@ -155,7 +155,7 @@ static int ksz9477_wait_alu_sta_ready(struct ksz_device *dev) { unsigned int val; - return regmap_read_poll_timeout(dev->regmap[2], + return regmap_read_poll_timeout(ksz_regmap_32(dev), REG_SW_ALU_STAT_CTRL__4, val, !(val & ALU_STAT_START), 10, 1000); @@ -170,7 +170,7 @@ int ksz9477_reset_switch(struct ksz_device *dev) ksz_cfg(dev, REG_SW_OPERATION, SW_RESET, true); /* turn off SPI DO Edge select */ - regmap_update_bits(dev->regmap[0], REG_SW_GLOBAL_SERIAL_CTRL_0, + regmap_update_bits(ksz_regmap_8(dev), REG_SW_GLOBAL_SERIAL_CTRL_0, SPI_AUTO_EDGE_DETECTION, 0); /* default configuration */ @@ -213,7 +213,7 @@ void ksz9477_r_mib_cnt(struct ksz_device *dev, int port, u16 addr, u64 *cnt) data |= (addr << MIB_COUNTER_INDEX_S); ksz_pwrite32(dev, port, REG_PORT_MIB_CTRL_STAT__4, data); - ret = regmap_read_poll_timeout(dev->regmap[2], + ret = regmap_read_poll_timeout(ksz_regmap_32(dev), PORT_CTRL_ADDR(port, REG_PORT_MIB_CTRL_STAT__4), val, !(val & MIB_COUNTER_READ), 10, 1000); /* failed to read MIB. get out of loop */ @@ -346,7 +346,7 @@ void ksz9477_flush_dyn_mac_table(struct ksz_device *dev, int port) const u16 *regs = dev->info->regs; u8 data; - regmap_update_bits(dev->regmap[0], REG_SW_LUE_CTRL_2, + regmap_update_bits(ksz_regmap_8(dev), REG_SW_LUE_CTRL_2, SW_FLUSH_OPTION_M << SW_FLUSH_OPTION_S, SW_FLUSH_OPTION_DYN_MAC << SW_FLUSH_OPTION_S); @@ -889,62 +889,6 @@ static phy_interface_t ksz9477_get_interface(struct ksz_device *dev, int port) return interface; } -static void ksz9477_port_mmd_write(struct ksz_device *dev, int port, - u8 dev_addr, u16 reg_addr, u16 val) -{ - ksz_pwrite16(dev, port, REG_PORT_PHY_MMD_SETUP, - MMD_SETUP(PORT_MMD_OP_INDEX, dev_addr)); - ksz_pwrite16(dev, port, REG_PORT_PHY_MMD_INDEX_DATA, reg_addr); - ksz_pwrite16(dev, port, REG_PORT_PHY_MMD_SETUP, - MMD_SETUP(PORT_MMD_OP_DATA_NO_INCR, dev_addr)); - ksz_pwrite16(dev, port, REG_PORT_PHY_MMD_INDEX_DATA, val); -} - -static void ksz9477_phy_errata_setup(struct ksz_device *dev, int port) -{ - /* Apply PHY settings to address errata listed in - * KSZ9477, KSZ9897, KSZ9896, KSZ9567, KSZ8565 - * Silicon Errata and Data Sheet Clarification documents: - * - * Register settings are needed to improve PHY receive performance - */ - ksz9477_port_mmd_write(dev, port, 0x01, 0x6f, 0xdd0b); - ksz9477_port_mmd_write(dev, port, 0x01, 0x8f, 0x6032); - ksz9477_port_mmd_write(dev, port, 0x01, 0x9d, 0x248c); - ksz9477_port_mmd_write(dev, port, 0x01, 0x75, 0x0060); - ksz9477_port_mmd_write(dev, port, 0x01, 0xd3, 0x7777); - ksz9477_port_mmd_write(dev, port, 0x1c, 0x06, 0x3008); - ksz9477_port_mmd_write(dev, port, 0x1c, 0x08, 0x2001); - - /* Transmit waveform amplitude can be improved - * (1000BASE-T, 100BASE-TX, 10BASE-Te) - */ - ksz9477_port_mmd_write(dev, port, 0x1c, 0x04, 0x00d0); - - /* Energy Efficient Ethernet (EEE) feature select must - * be manually disabled (except on KSZ8565 which is 100Mbit) - */ - if (dev->info->gbit_capable[port]) - ksz9477_port_mmd_write(dev, port, 0x07, 0x3c, 0x0000); - - /* Register settings are required to meet data sheet - * supply current specifications - */ - ksz9477_port_mmd_write(dev, port, 0x1c, 0x13, 0x6eff); - ksz9477_port_mmd_write(dev, port, 0x1c, 0x14, 0xe6ff); - ksz9477_port_mmd_write(dev, port, 0x1c, 0x15, 0x6eff); - ksz9477_port_mmd_write(dev, port, 0x1c, 0x16, 0xe6ff); - ksz9477_port_mmd_write(dev, port, 0x1c, 0x17, 0x00ff); - ksz9477_port_mmd_write(dev, port, 0x1c, 0x18, 0x43ff); - ksz9477_port_mmd_write(dev, port, 0x1c, 0x19, 0xc3ff); - ksz9477_port_mmd_write(dev, port, 0x1c, 0x1a, 0x6fff); - ksz9477_port_mmd_write(dev, port, 0x1c, 0x1b, 0x07ff); - ksz9477_port_mmd_write(dev, port, 0x1c, 0x1c, 0x0fff); - ksz9477_port_mmd_write(dev, port, 0x1c, 0x1d, 0xe7ff); - ksz9477_port_mmd_write(dev, port, 0x1c, 0x1e, 0xefff); - ksz9477_port_mmd_write(dev, port, 0x1c, 0x20, 0xeeee); -} - void ksz9477_get_caps(struct ksz_device *dev, int port, struct phylink_config *config) { @@ -1029,20 +973,10 @@ void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port) /* enable 802.1p priority */ ksz_port_cfg(dev, port, P_PRIO_CTRL, PORT_802_1P_PRIO_ENABLE, true); - if (dev->info->internal_phy[port]) { - /* do not force flow control */ - ksz_port_cfg(dev, port, REG_PORT_CTRL_0, - PORT_FORCE_TX_FLOW_CTRL | PORT_FORCE_RX_FLOW_CTRL, - false); - - if (dev->info->phy_errata_9477) - ksz9477_phy_errata_setup(dev, port); - } else { - /* force flow control */ - ksz_port_cfg(dev, port, REG_PORT_CTRL_0, - PORT_FORCE_TX_FLOW_CTRL | PORT_FORCE_RX_FLOW_CTRL, - true); - } + /* force flow control for non-PHY ports only */ + ksz_port_cfg(dev, port, REG_PORT_CTRL_0, + PORT_FORCE_TX_FLOW_CTRL | PORT_FORCE_RX_FLOW_CTRL, + !dev->info->internal_phy[port]); if (cpu_port) member = dsa_user_ports(ds); @@ -1165,7 +1099,7 @@ int ksz9477_setup(struct dsa_switch *ds) ksz_cfg(dev, REG_SW_MAC_CTRL_1, SW_JUMBO_PACKET, true); /* Now we can configure default MTU value */ - ret = regmap_update_bits(dev->regmap[1], REG_SW_MTU__2, REG_SW_MTU_MASK, + ret = regmap_update_bits(ksz_regmap_16(dev), REG_SW_MTU__2, REG_SW_MTU_MASK, VLAN_ETH_FRAME_LEN + ETH_FCS_LEN); if (ret) return ret; diff --git a/drivers/net/dsa/microchip/ksz9477_i2c.c b/drivers/net/dsa/microchip/ksz9477_i2c.c index 97a317263a2f..2710afad4f3a 100644 --- a/drivers/net/dsa/microchip/ksz9477_i2c.c +++ b/drivers/net/dsa/microchip/ksz9477_i2c.c @@ -24,7 +24,7 @@ static int ksz9477_i2c_probe(struct i2c_client *i2c) if (!dev) return -ENOMEM; - for (i = 0; i < ARRAY_SIZE(ksz9477_regmap_config); i++) { + for (i = 0; i < __KSZ_NUM_REGMAPS; i++) { rc = ksz9477_regmap_config[i]; rc.lock_arg = &dev->regmap_mutex; dev->regmap[i] = devm_regmap_init_i2c(i2c, &rc); @@ -119,7 +119,7 @@ static struct i2c_driver ksz9477_i2c_driver = { .name = "ksz9477-switch", .of_match_table = ksz9477_dt_ids, }, - .probe_new = ksz9477_i2c_probe, + .probe = ksz9477_i2c_probe, .remove = ksz9477_i2c_remove, .shutdown = ksz9477_i2c_shutdown, .id_table = ksz9477_i2c_id, diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index a4428be5f483..813b91a816bb 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -1075,6 +1075,45 @@ static const struct regmap_access_table ksz9896_register_set = { .n_yes_ranges = ARRAY_SIZE(ksz9896_valid_regs), }; +static const struct regmap_range ksz8873_valid_regs[] = { + regmap_reg_range(0x00, 0x01), + /* global control register */ + regmap_reg_range(0x02, 0x0f), + + /* port registers */ + regmap_reg_range(0x10, 0x1d), + regmap_reg_range(0x1e, 0x1f), + regmap_reg_range(0x20, 0x2d), + regmap_reg_range(0x2e, 0x2f), + regmap_reg_range(0x30, 0x39), + regmap_reg_range(0x3f, 0x3f), + + /* advanced control registers */ + regmap_reg_range(0x60, 0x6f), + regmap_reg_range(0x70, 0x75), + regmap_reg_range(0x76, 0x78), + regmap_reg_range(0x79, 0x7a), + regmap_reg_range(0x7b, 0x83), + regmap_reg_range(0x8e, 0x99), + regmap_reg_range(0x9a, 0xa5), + regmap_reg_range(0xa6, 0xa6), + regmap_reg_range(0xa7, 0xaa), + regmap_reg_range(0xab, 0xae), + regmap_reg_range(0xaf, 0xba), + regmap_reg_range(0xbb, 0xbc), + regmap_reg_range(0xbd, 0xbd), + regmap_reg_range(0xc0, 0xc0), + regmap_reg_range(0xc2, 0xc2), + regmap_reg_range(0xc3, 0xc3), + regmap_reg_range(0xc4, 0xc4), + regmap_reg_range(0xc6, 0xc6), +}; + +static const struct regmap_access_table ksz8873_register_set = { + .yes_ranges = ksz8873_valid_regs, + .n_yes_ranges = ARRAY_SIZE(ksz8873_valid_regs), +}; + const struct ksz_chip_data ksz_switch_chips[] = { [KSZ8563] = { .chip_id = KSZ8563_CHIP_ID, @@ -1214,6 +1253,8 @@ const struct ksz_chip_data ksz_switch_chips[] = { .supports_mii = {false, false, true}, .supports_rmii = {false, false, true}, .internal_phy = {true, true, false}, + .wr_table = &ksz8873_register_set, + .rd_table = &ksz8873_register_set, }, [KSZ9477] = { @@ -1229,7 +1270,6 @@ const struct ksz_chip_data ksz_switch_chips[] = { .tc_cbs_supported = true, .tc_ets_supported = true, .ops = &ksz9477_dev_ops, - .phy_errata_9477 = true, .mib_names = ksz9477_mib_names, .mib_cnt = ARRAY_SIZE(ksz9477_mib_names), .reg_mib_cnt = MIB_COUNTER_NUM, @@ -1262,7 +1302,6 @@ const struct ksz_chip_data ksz_switch_chips[] = { .port_nirqs = 2, .num_tx_queues = 4, .ops = &ksz9477_dev_ops, - .phy_errata_9477 = true, .mib_names = ksz9477_mib_names, .mib_cnt = ARRAY_SIZE(ksz9477_mib_names), .reg_mib_cnt = MIB_COUNTER_NUM, @@ -1295,7 +1334,6 @@ const struct ksz_chip_data ksz_switch_chips[] = { .port_nirqs = 2, .num_tx_queues = 4, .ops = &ksz9477_dev_ops, - .phy_errata_9477 = true, .mib_names = ksz9477_mib_names, .mib_cnt = ARRAY_SIZE(ksz9477_mib_names), .reg_mib_cnt = MIB_COUNTER_NUM, @@ -1382,7 +1420,6 @@ const struct ksz_chip_data ksz_switch_chips[] = { .tc_cbs_supported = true, .tc_ets_supported = true, .ops = &ksz9477_dev_ops, - .phy_errata_9477 = true, .mib_names = ksz9477_mib_names, .mib_cnt = ARRAY_SIZE(ksz9477_mib_names), .reg_mib_cnt = MIB_COUNTER_NUM, @@ -2095,7 +2132,7 @@ static int ksz_setup(struct dsa_switch *ds) } /* set broadcast storm protection 10% rate */ - regmap_update_bits(dev->regmap[1], regs[S_BROADCAST_CTRL], + regmap_update_bits(ksz_regmap_16(dev), regs[S_BROADCAST_CTRL], BROADCAST_STORM_RATE, (BROADCAST_STORM_VALUE * BROADCAST_STORM_PROT_RATE) / 100); @@ -2106,7 +2143,7 @@ static int ksz_setup(struct dsa_switch *ds) ds->num_tx_queues = dev->info->num_tx_queues; - regmap_update_bits(dev->regmap[0], regs[S_MULTICAST_CTRL], + regmap_update_bits(ksz_regmap_8(dev), regs[S_MULTICAST_CTRL], MULTICAST_STORM_DISABLE, MULTICAST_STORM_DISABLE); ksz_init_mib_timer(dev); @@ -2156,7 +2193,7 @@ static int ksz_setup(struct dsa_switch *ds) } /* start switch */ - regmap_update_bits(dev->regmap[0], regs[S_START_CTRL], + regmap_update_bits(ksz_regmap_8(dev), regs[S_START_CTRL], SW_START, SW_START); return 0; diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index 8abecaf6089e..a66b56857ec6 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -22,6 +22,13 @@ struct ksz_device; struct ksz_port; +enum ksz_regmap_width { + KSZ_REGMAP_8, + KSZ_REGMAP_16, + KSZ_REGMAP_32, + __KSZ_NUM_REGMAPS, +}; + struct vlan_table { u32 table[3]; }; @@ -53,7 +60,6 @@ struct ksz_chip_data { bool tc_cbs_supported; bool tc_ets_supported; const struct ksz_dev_ops *ops; - bool phy_errata_9477; bool ksz87xx_eee_link_erratum; const struct ksz_mib_names *mib_names; int mib_cnt; @@ -101,7 +107,6 @@ struct ksz_port { int stp_state; struct phy_device phydev; - u32 on:1; /* port is not disabled by hardware */ u32 fiber:1; /* port is fiber */ u32 force:1; u32 read:1; /* read MIB counters in background */ @@ -137,7 +142,7 @@ struct ksz_device { const struct ksz_dev_ops *dev_ops; struct device *dev; - struct regmap *regmap[3]; + struct regmap *regmap[__KSZ_NUM_REGMAPS]; void *priv; int irq; @@ -377,11 +382,25 @@ phy_interface_t ksz_get_xmii(struct ksz_device *dev, int port, bool gbit); extern const struct ksz_chip_data ksz_switch_chips[]; /* Common register access functions */ +static inline struct regmap *ksz_regmap_8(struct ksz_device *dev) +{ + return dev->regmap[KSZ_REGMAP_8]; +} + +static inline struct regmap *ksz_regmap_16(struct ksz_device *dev) +{ + return dev->regmap[KSZ_REGMAP_16]; +} + +static inline struct regmap *ksz_regmap_32(struct ksz_device *dev) +{ + return dev->regmap[KSZ_REGMAP_32]; +} static inline int ksz_read8(struct ksz_device *dev, u32 reg, u8 *val) { unsigned int value; - int ret = regmap_read(dev->regmap[0], reg, &value); + int ret = regmap_read(ksz_regmap_8(dev), reg, &value); if (ret) dev_err(dev->dev, "can't read 8bit reg: 0x%x %pe\n", reg, @@ -394,7 +413,7 @@ static inline int ksz_read8(struct ksz_device *dev, u32 reg, u8 *val) static inline int ksz_read16(struct ksz_device *dev, u32 reg, u16 *val) { unsigned int value; - int ret = regmap_read(dev->regmap[1], reg, &value); + int ret = regmap_read(ksz_regmap_16(dev), reg, &value); if (ret) dev_err(dev->dev, "can't read 16bit reg: 0x%x %pe\n", reg, @@ -407,7 +426,7 @@ static inline int ksz_read16(struct ksz_device *dev, u32 reg, u16 *val) static inline int ksz_read32(struct ksz_device *dev, u32 reg, u32 *val) { unsigned int value; - int ret = regmap_read(dev->regmap[2], reg, &value); + int ret = regmap_read(ksz_regmap_32(dev), reg, &value); if (ret) dev_err(dev->dev, "can't read 32bit reg: 0x%x %pe\n", reg, @@ -422,7 +441,7 @@ static inline int ksz_read64(struct ksz_device *dev, u32 reg, u64 *val) u32 value[2]; int ret; - ret = regmap_bulk_read(dev->regmap[2], reg, value, 2); + ret = regmap_bulk_read(ksz_regmap_32(dev), reg, value, 2); if (ret) dev_err(dev->dev, "can't read 64bit reg: 0x%x %pe\n", reg, ERR_PTR(ret)); @@ -436,7 +455,7 @@ static inline int ksz_write8(struct ksz_device *dev, u32 reg, u8 value) { int ret; - ret = regmap_write(dev->regmap[0], reg, value); + ret = regmap_write(ksz_regmap_8(dev), reg, value); if (ret) dev_err(dev->dev, "can't write 8bit reg: 0x%x %pe\n", reg, ERR_PTR(ret)); @@ -448,7 +467,7 @@ static inline int ksz_write16(struct ksz_device *dev, u32 reg, u16 value) { int ret; - ret = regmap_write(dev->regmap[1], reg, value); + ret = regmap_write(ksz_regmap_16(dev), reg, value); if (ret) dev_err(dev->dev, "can't write 16bit reg: 0x%x %pe\n", reg, ERR_PTR(ret)); @@ -460,7 +479,7 @@ static inline int ksz_write32(struct ksz_device *dev, u32 reg, u32 value) { int ret; - ret = regmap_write(dev->regmap[2], reg, value); + ret = regmap_write(ksz_regmap_32(dev), reg, value); if (ret) dev_err(dev->dev, "can't write 32bit reg: 0x%x %pe\n", reg, ERR_PTR(ret)); @@ -473,7 +492,7 @@ static inline int ksz_rmw16(struct ksz_device *dev, u32 reg, u16 mask, { int ret; - ret = regmap_update_bits(dev->regmap[1], reg, mask, value); + ret = regmap_update_bits(ksz_regmap_16(dev), reg, mask, value); if (ret) dev_err(dev->dev, "can't rmw 16bit reg 0x%x: %pe\n", reg, ERR_PTR(ret)); @@ -486,7 +505,7 @@ static inline int ksz_rmw32(struct ksz_device *dev, u32 reg, u32 mask, { int ret; - ret = regmap_update_bits(dev->regmap[2], reg, mask, value); + ret = regmap_update_bits(ksz_regmap_32(dev), reg, mask, value); if (ret) dev_err(dev->dev, "can't rmw 32bit reg 0x%x: %pe\n", reg, ERR_PTR(ret)); @@ -503,12 +522,19 @@ static inline int ksz_write64(struct ksz_device *dev, u32 reg, u64 value) val[0] = swab32(value & 0xffffffffULL); val[1] = swab32(value >> 32ULL); - return regmap_bulk_write(dev->regmap[2], reg, val, 2); + return regmap_bulk_write(ksz_regmap_32(dev), reg, val, 2); } static inline int ksz_rmw8(struct ksz_device *dev, int offset, u8 mask, u8 val) { - return regmap_update_bits(dev->regmap[0], offset, mask, val); + int ret; + + ret = regmap_update_bits(ksz_regmap_8(dev), offset, mask, val); + if (ret) + dev_err(dev->dev, "can't rmw 8bit reg 0x%x: %pe\n", offset, + ERR_PTR(ret)); + + return ret; } static inline int ksz_pread8(struct ksz_device *dev, int port, int offset, @@ -549,12 +575,20 @@ static inline int ksz_pwrite32(struct ksz_device *dev, int port, int offset, data); } -static inline void ksz_prmw8(struct ksz_device *dev, int port, int offset, - u8 mask, u8 val) +static inline int ksz_prmw8(struct ksz_device *dev, int port, int offset, + u8 mask, u8 val) { - regmap_update_bits(dev->regmap[0], - dev->dev_ops->get_port_addr(port, offset), - mask, val); + int ret; + + ret = regmap_update_bits(ksz_regmap_8(dev), + dev->dev_ops->get_port_addr(port, offset), + mask, val); + if (ret) + dev_err(dev->dev, "can't rmw 8bit reg 0x%x: %pe\n", + dev->dev_ops->get_port_addr(port, offset), + ERR_PTR(ret)); + + return ret; } static inline void ksz_regmap_lock(void *__mtx) @@ -709,9 +743,9 @@ static inline int is_lan937x(struct ksz_device *dev) #define KSZ_REGMAP_TABLE(ksz, swp, regbits, regpad, regalign) \ static const struct regmap_config ksz##_regmap_config[] = { \ - KSZ_REGMAP_ENTRY(8, swp, (regbits), (regpad), (regalign)), \ - KSZ_REGMAP_ENTRY(16, swp, (regbits), (regpad), (regalign)), \ - KSZ_REGMAP_ENTRY(32, swp, (regbits), (regpad), (regalign)), \ + [KSZ_REGMAP_8] = KSZ_REGMAP_ENTRY(8, swp, (regbits), (regpad), (regalign)), \ + [KSZ_REGMAP_16] = KSZ_REGMAP_ENTRY(16, swp, (regbits), (regpad), (regalign)), \ + [KSZ_REGMAP_32] = KSZ_REGMAP_ENTRY(32, swp, (regbits), (regpad), (regalign)), \ } #endif diff --git a/drivers/net/dsa/microchip/ksz_spi.c b/drivers/net/dsa/microchip/ksz_spi.c index 96c52e8fb51b..279338451621 100644 --- a/drivers/net/dsa/microchip/ksz_spi.c +++ b/drivers/net/dsa/microchip/ksz_spi.c @@ -63,7 +63,7 @@ static int ksz_spi_probe(struct spi_device *spi) else regmap_config = ksz9477_regmap_config; - for (i = 0; i < ARRAY_SIZE(ksz8795_regmap_config); i++) { + for (i = 0; i < __KSZ_NUM_REGMAPS; i++) { rc = regmap_config[i]; rc.lock_arg = &dev->regmap_mutex; rc.wr_table = chip->wr_table; diff --git a/drivers/net/dsa/microchip/lan937x_main.c b/drivers/net/dsa/microchip/lan937x_main.c index 399a3905e6ca..b479a628b1ae 100644 --- a/drivers/net/dsa/microchip/lan937x_main.c +++ b/drivers/net/dsa/microchip/lan937x_main.c @@ -20,13 +20,13 @@ static int lan937x_cfg(struct ksz_device *dev, u32 addr, u8 bits, bool set) { - return regmap_update_bits(dev->regmap[0], addr, bits, set ? bits : 0); + return regmap_update_bits(ksz_regmap_8(dev), addr, bits, set ? bits : 0); } static int lan937x_port_cfg(struct ksz_device *dev, int port, int offset, u8 bits, bool set) { - return regmap_update_bits(dev->regmap[0], PORT_CTRL_ADDR(port, offset), + return regmap_update_bits(ksz_regmap_8(dev), PORT_CTRL_ADDR(port, offset), bits, set ? bits : 0); } @@ -86,7 +86,7 @@ static int lan937x_internal_phy_write(struct ksz_device *dev, int addr, int reg, if (ret < 0) return ret; - ret = regmap_read_poll_timeout(dev->regmap[1], REG_VPHY_IND_CTRL__2, + ret = regmap_read_poll_timeout(ksz_regmap_16(dev), REG_VPHY_IND_CTRL__2, value, !(value & VPHY_IND_BUSY), 10, 1000); if (ret < 0) { @@ -116,7 +116,7 @@ static int lan937x_internal_phy_read(struct ksz_device *dev, int addr, int reg, if (ret < 0) return ret; - ret = regmap_read_poll_timeout(dev->regmap[1], REG_VPHY_IND_CTRL__2, + ret = regmap_read_poll_timeout(ksz_regmap_16(dev), REG_VPHY_IND_CTRL__2, value, !(value & VPHY_IND_BUSY), 10, 1000); if (ret < 0) { diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 64a2f2f83735..8b51756bd805 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -463,11 +463,11 @@ restore_link: return err; } -static int mv88e6xxx_phy_is_internal(struct dsa_switch *ds, int port) +static int mv88e6xxx_phy_is_internal(struct mv88e6xxx_chip *chip, int port) { - struct mv88e6xxx_chip *chip = ds->priv; - - return port < chip->info->num_internal_phys; + return port >= chip->info->internal_phys_offset && + port < chip->info->num_internal_phys + + chip->info->internal_phys_offset; } static int mv88e6xxx_port_ppu_updates(struct mv88e6xxx_chip *chip, int port) @@ -479,7 +479,7 @@ static int mv88e6xxx_port_ppu_updates(struct mv88e6xxx_chip *chip, int port) * report whether the port is internal. */ if (chip->info->family == MV88E6XXX_FAMILY_6250) - return port < chip->info->num_internal_phys; + return mv88e6xxx_phy_is_internal(chip, port); err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_STS, ®); if (err) { @@ -584,7 +584,7 @@ static void mv88e6095_phylink_get_caps(struct mv88e6xxx_chip *chip, int port, config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100; - if (mv88e6xxx_phy_is_internal(chip->ds, port)) { + if (mv88e6xxx_phy_is_internal(chip, port)) { __set_bit(PHY_INTERFACE_MODE_MII, config->supported_interfaces); } else { if (cmode < ARRAY_SIZE(mv88e6185_phy_interface_modes) && @@ -790,6 +790,8 @@ static void mv88e6393x_phylink_get_caps(struct mv88e6xxx_chip *chip, int port, unsigned long *supported = config->supported_interfaces; bool is_6191x = chip->info->prod_num == MV88E6XXX_PORT_SWITCH_ID_PROD_6191X; + bool is_6361 = + chip->info->prod_num == MV88E6XXX_PORT_SWITCH_ID_PROD_6361; mv88e6xxx_translate_cmode(chip->ports[port].cmode, supported); @@ -804,13 +806,16 @@ static void mv88e6393x_phylink_get_caps(struct mv88e6xxx_chip *chip, int port, /* 6191X supports >1G modes only on port 10 */ if (!is_6191x || port == 10) { __set_bit(PHY_INTERFACE_MODE_2500BASEX, supported); - __set_bit(PHY_INTERFACE_MODE_5GBASER, supported); - __set_bit(PHY_INTERFACE_MODE_10GBASER, supported); - /* FIXME: USXGMII is not supported yet */ - /* __set_bit(PHY_INTERFACE_MODE_USXGMII, supported); */ - - config->mac_capabilities |= MAC_2500FD | MAC_5000FD | - MAC_10000FD; + config->mac_capabilities |= MAC_2500FD; + + /* 6361 only supports up to 2500BaseX */ + if (!is_6361) { + __set_bit(PHY_INTERFACE_MODE_5GBASER, supported); + __set_bit(PHY_INTERFACE_MODE_10GBASER, supported); + __set_bit(PHY_INTERFACE_MODE_USXGMII, supported); + config->mac_capabilities |= MAC_5000FD | + MAC_10000FD; + } } } @@ -832,7 +837,7 @@ static void mv88e6xxx_get_caps(struct dsa_switch *ds, int port, chip->info->ops->phylink_get_caps(chip, port, config); mv88e6xxx_reg_unlock(chip); - if (mv88e6xxx_phy_is_internal(ds, port)) { + if (mv88e6xxx_phy_is_internal(chip, port)) { __set_bit(PHY_INTERFACE_MODE_INTERNAL, config->supported_interfaces); /* Internal ports with no phy-mode need GMII for PHYLIB */ @@ -841,29 +846,38 @@ static void mv88e6xxx_get_caps(struct dsa_switch *ds, int port, } } +static int mv88e6xxx_mac_prepare(struct dsa_switch *ds, int port, + unsigned int mode, phy_interface_t interface) +{ + struct mv88e6xxx_chip *chip = ds->priv; + int err = 0; + + /* In inband mode, the link may come up at any time while the link + * is not forced down. Force the link down while we reconfigure the + * interface mode. + */ + if (mode == MLO_AN_INBAND && + chip->ports[port].interface != interface && + chip->info->ops->port_set_link) { + mv88e6xxx_reg_lock(chip); + err = chip->info->ops->port_set_link(chip, port, + LINK_FORCED_DOWN); + mv88e6xxx_reg_unlock(chip); + } + + return err; +} + static void mv88e6xxx_mac_config(struct dsa_switch *ds, int port, unsigned int mode, const struct phylink_link_state *state) { struct mv88e6xxx_chip *chip = ds->priv; - struct mv88e6xxx_port *p; int err = 0; - p = &chip->ports[port]; - mv88e6xxx_reg_lock(chip); - if (mode != MLO_AN_PHY || !mv88e6xxx_phy_is_internal(ds, port)) { - /* In inband mode, the link may come up at any time while the - * link is not forced down. Force the link down while we - * reconfigure the interface mode. - */ - if (mode == MLO_AN_INBAND && - p->interface != state->interface && - chip->info->ops->port_set_link) - chip->info->ops->port_set_link(chip, port, - LINK_FORCED_DOWN); - + if (mode != MLO_AN_PHY || !mv88e6xxx_phy_is_internal(chip, port)) { err = mv88e6xxx_port_config_interface(chip, port, state->interface); if (err && err != -EOPNOTSUPP) @@ -880,24 +894,38 @@ static void mv88e6xxx_mac_config(struct dsa_switch *ds, int port, err = 0; } +err_unlock: + mv88e6xxx_reg_unlock(chip); + + if (err && err != -EOPNOTSUPP) + dev_err(ds->dev, "p%d: failed to configure MAC/PCS\n", port); +} + +static int mv88e6xxx_mac_finish(struct dsa_switch *ds, int port, + unsigned int mode, phy_interface_t interface) +{ + struct mv88e6xxx_chip *chip = ds->priv; + int err = 0; + /* Undo the forced down state above after completing configuration * irrespective of its state on entry, which allows the link to come * up in the in-band case where there is no separate SERDES. Also * ensure that the link can come up if the PPU is in use and we are * in PHY mode (we treat the PPU as an effective in-band mechanism.) */ + mv88e6xxx_reg_lock(chip); + if (chip->info->ops->port_set_link && - ((mode == MLO_AN_INBAND && p->interface != state->interface) || + ((mode == MLO_AN_INBAND && + chip->ports[port].interface != interface) || (mode == MLO_AN_PHY && mv88e6xxx_port_ppu_updates(chip, port)))) - chip->info->ops->port_set_link(chip, port, LINK_UNFORCED); - - p->interface = state->interface; + err = chip->info->ops->port_set_link(chip, port, LINK_UNFORCED); -err_unlock: mv88e6xxx_reg_unlock(chip); - if (err && err != -EOPNOTSUPP) - dev_err(ds->dev, "p%d: failed to configure MAC/PCS\n", port); + chip->ports[port].interface = interface; + + return err; } static void mv88e6xxx_mac_link_down(struct dsa_switch *ds, int port, @@ -3311,7 +3339,7 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) caps = pl_config.mac_capabilities; if (chip->info->ops->port_max_speed_mode) - mode = chip->info->ops->port_max_speed_mode(port); + mode = chip->info->ops->port_max_speed_mode(chip, port); else mode = PHY_INTERFACE_MODE_NA; @@ -5043,6 +5071,7 @@ static const struct mv88e6xxx_ops mv88e6250_ops = { .avb_ops = &mv88e6352_avb_ops, .ptp_ops = &mv88e6250_ptp_ops, .phylink_get_caps = mv88e6250_phylink_get_caps, + .set_max_frame_size = mv88e6185_g1_set_max_frame_size, }; static const struct mv88e6xxx_ops mv88e6290_ops = { @@ -5642,6 +5671,46 @@ static const struct mv88e6xxx_ops mv88e6393x_ops = { }; static const struct mv88e6xxx_info mv88e6xxx_table[] = { + [MV88E6020] = { + .prod_num = MV88E6XXX_PORT_SWITCH_ID_PROD_6020, + .family = MV88E6XXX_FAMILY_6250, + .name = "Marvell 88E6020", + .num_databases = 64, + .num_ports = 4, + .num_internal_phys = 2, + .max_vid = 4095, + .port_base_addr = 0x8, + .phy_base_addr = 0x0, + .global1_addr = 0xf, + .global2_addr = 0x7, + .age_time_coeff = 15000, + .g1_irqs = 9, + .g2_irqs = 5, + .atu_move_port_mask = 0xf, + .dual_chip = true, + .ops = &mv88e6250_ops, + }, + + [MV88E6071] = { + .prod_num = MV88E6XXX_PORT_SWITCH_ID_PROD_6071, + .family = MV88E6XXX_FAMILY_6250, + .name = "Marvell 88E6071", + .num_databases = 64, + .num_ports = 7, + .num_internal_phys = 5, + .max_vid = 4095, + .port_base_addr = 0x08, + .phy_base_addr = 0x00, + .global1_addr = 0x0f, + .global2_addr = 0x07, + .age_time_coeff = 15000, + .g1_irqs = 9, + .g2_irqs = 5, + .atu_move_port_mask = 0xf, + .dual_chip = true, + .ops = &mv88e6250_ops, + }, + [MV88E6085] = { .prod_num = MV88E6XXX_PORT_SWITCH_ID_PROD_6085, .family = MV88E6XXX_FAMILY_6097, @@ -6024,7 +6093,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6191X", .num_databases = 4096, .num_ports = 11, /* 10 + Z80 */ - .num_internal_phys = 9, + .num_internal_phys = 8, + .internal_phys_offset = 1, .max_vid = 8191, .max_sid = 63, .port_base_addr = 0x0, @@ -6047,7 +6117,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6193X", .num_databases = 4096, .num_ports = 11, /* 10 + Z80 */ - .num_internal_phys = 9, + .num_internal_phys = 8, + .internal_phys_offset = 1, .max_vid = 8191, .max_sid = 63, .port_base_addr = 0x0, @@ -6309,6 +6380,32 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .ptp_support = true, .ops = &mv88e6352_ops, }, + [MV88E6361] = { + .prod_num = MV88E6XXX_PORT_SWITCH_ID_PROD_6361, + .family = MV88E6XXX_FAMILY_6393, + .name = "Marvell 88E6361", + .num_databases = 4096, + .num_macs = 16384, + .num_ports = 11, + /* Ports 1, 2 and 8 are not routed */ + .invalid_port_mask = BIT(1) | BIT(2) | BIT(8), + .num_internal_phys = 5, + .internal_phys_offset = 3, + .max_vid = 4095, + .max_sid = 63, + .port_base_addr = 0x0, + .phy_base_addr = 0x0, + .global1_addr = 0x1b, + .global2_addr = 0x1c, + .age_time_coeff = 3750, + .g1_irqs = 10, + .g2_irqs = 14, + .atu_move_port_mask = 0x1f, + .pvt = true, + .multi_chip = true, + .ptp_support = true, + .ops = &mv88e6393x_ops, + }, [MV88E6390] = { .prod_num = MV88E6XXX_PORT_SWITCH_ID_PROD_6390, .family = MV88E6XXX_FAMILY_6390, @@ -6366,7 +6463,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .name = "Marvell 88E6393X", .num_databases = 4096, .num_ports = 11, /* 10 + Z80 */ - .num_internal_phys = 9, + .num_internal_phys = 8, + .internal_phys_offset = 1, .max_vid = 8191, .max_sid = 63, .port_base_addr = 0x0, @@ -7002,7 +7100,9 @@ static const struct dsa_switch_ops mv88e6xxx_switch_ops = { .port_teardown = mv88e6xxx_port_teardown, .phylink_get_caps = mv88e6xxx_get_caps, .phylink_mac_link_state = mv88e6xxx_serdes_pcs_get_state, + .phylink_mac_prepare = mv88e6xxx_mac_prepare, .phylink_mac_config = mv88e6xxx_mac_config, + .phylink_mac_finish = mv88e6xxx_mac_finish, .phylink_mac_an_restart = mv88e6xxx_serdes_pcs_an_restart, .phylink_mac_link_down = mv88e6xxx_mac_link_down, .phylink_mac_link_up = mv88e6xxx_mac_link_up, @@ -7170,7 +7270,7 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev) goto out; } if (chip->reset) - usleep_range(1000, 2000); + usleep_range(10000, 20000); /* Detect if the device is configured in single chip addressing mode, * otherwise continue with address specific smi init/detection. diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h index da6e1339f809..0ad34b2d8913 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.h +++ b/drivers/net/dsa/mv88e6xxx/chip.h @@ -54,6 +54,8 @@ enum mv88e6xxx_frame_mode { /* List of supported models */ enum mv88e6xxx_model { + MV88E6020, + MV88E6071, MV88E6085, MV88E6095, MV88E6097, @@ -82,6 +84,7 @@ enum mv88e6xxx_model { MV88E6350, MV88E6351, MV88E6352, + MV88E6361, MV88E6390, MV88E6390X, MV88E6393X, @@ -94,13 +97,13 @@ enum mv88e6xxx_family { MV88E6XXX_FAMILY_6097, /* 6046 6085 6096 6097 */ MV88E6XXX_FAMILY_6165, /* 6123 6161 6165 */ MV88E6XXX_FAMILY_6185, /* 6108 6121 6122 6131 6152 6155 6182 6185 */ - MV88E6XXX_FAMILY_6250, /* 6220 6250 */ + MV88E6XXX_FAMILY_6250, /* 6220 6250 6020 6071 */ MV88E6XXX_FAMILY_6320, /* 6320 6321 */ MV88E6XXX_FAMILY_6341, /* 6141 6341 */ MV88E6XXX_FAMILY_6351, /* 6171 6175 6350 6351 */ MV88E6XXX_FAMILY_6352, /* 6172 6176 6240 6352 */ MV88E6XXX_FAMILY_6390, /* 6190 6190X 6191 6290 6390 6390X */ - MV88E6XXX_FAMILY_6393, /* 6191X 6193X 6393X */ + MV88E6XXX_FAMILY_6393, /* 6191X 6193X 6361 6393X */ }; /** @@ -167,6 +170,11 @@ struct mv88e6xxx_info { /* Supports PTP */ bool ptp_support; + + /* Internal PHY start index. 0 means that internal PHYs range starts at + * port 0, 1 means internal PHYs range starts at port 1, etc + */ + unsigned int internal_phys_offset; }; struct mv88e6xxx_atu_entry { @@ -513,7 +521,8 @@ struct mv88e6xxx_ops { int speed, int duplex); /* What interface mode should be used for maximum speed? */ - phy_interface_t (*port_max_speed_mode)(int port); + phy_interface_t (*port_max_speed_mode)(struct mv88e6xxx_chip *chip, + int port); int (*port_tag_remap)(struct mv88e6xxx_chip *chip, int port); diff --git a/drivers/net/dsa/mv88e6xxx/global2.c b/drivers/net/dsa/mv88e6xxx/global2.c index 615896893076..937a01f2ba75 100644 --- a/drivers/net/dsa/mv88e6xxx/global2.c +++ b/drivers/net/dsa/mv88e6xxx/global2.c @@ -1196,9 +1196,12 @@ out: int mv88e6xxx_g2_irq_mdio_setup(struct mv88e6xxx_chip *chip, struct mii_bus *bus) { + int phy_start = chip->info->internal_phys_offset; + int phy_end = chip->info->internal_phys_offset + + chip->info->num_internal_phys; int phy, irq; - for (phy = 0; phy < chip->info->num_internal_phys; phy++) { + for (phy = phy_start; phy < phy_end; phy++) { irq = irq_find_mapping(chip->g2_irq.domain, phy); if (irq < 0) return irq; diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c index f79cf716c541..dd66ec902d4c 100644 --- a/drivers/net/dsa/mv88e6xxx/port.c +++ b/drivers/net/dsa/mv88e6xxx/port.c @@ -342,7 +342,8 @@ int mv88e6341_port_set_speed_duplex(struct mv88e6xxx_chip *chip, int port, duplex); } -phy_interface_t mv88e6341_port_max_speed_mode(int port) +phy_interface_t mv88e6341_port_max_speed_mode(struct mv88e6xxx_chip *chip, + int port) { if (port == 5) return PHY_INTERFACE_MODE_2500BASEX; @@ -381,7 +382,8 @@ int mv88e6390_port_set_speed_duplex(struct mv88e6xxx_chip *chip, int port, duplex); } -phy_interface_t mv88e6390_port_max_speed_mode(int port) +phy_interface_t mv88e6390_port_max_speed_mode(struct mv88e6xxx_chip *chip, + int port) { if (port == 9 || port == 10) return PHY_INTERFACE_MODE_2500BASEX; @@ -403,7 +405,8 @@ int mv88e6390x_port_set_speed_duplex(struct mv88e6xxx_chip *chip, int port, duplex); } -phy_interface_t mv88e6390x_port_max_speed_mode(int port) +phy_interface_t mv88e6390x_port_max_speed_mode(struct mv88e6xxx_chip *chip, + int port) { if (port == 9 || port == 10) return PHY_INTERFACE_MODE_XAUI; @@ -421,6 +424,10 @@ int mv88e6393x_port_set_speed_duplex(struct mv88e6xxx_chip *chip, int port, u16 reg, ctrl; int err; + if (chip->info->prod_num == MV88E6XXX_PORT_SWITCH_ID_PROD_6361 && + speed > 2500) + return -EOPNOTSUPP; + if (speed == 200 && port != 0) return -EOPNOTSUPP; @@ -500,12 +507,17 @@ int mv88e6393x_port_set_speed_duplex(struct mv88e6xxx_chip *chip, int port, return 0; } -phy_interface_t mv88e6393x_port_max_speed_mode(int port) +phy_interface_t mv88e6393x_port_max_speed_mode(struct mv88e6xxx_chip *chip, + int port) { - if (port == 0 || port == 9 || port == 10) - return PHY_INTERFACE_MODE_10GBASER; - return PHY_INTERFACE_MODE_NA; + if (port != 0 && port != 9 && port != 10) + return PHY_INTERFACE_MODE_NA; + + if (chip->info->prod_num == MV88E6XXX_PORT_SWITCH_ID_PROD_6361) + return PHY_INTERFACE_MODE_2500BASEX; + + return PHY_INTERFACE_MODE_10GBASER; } static int mv88e6xxx_port_set_cmode(struct mv88e6xxx_chip *chip, int port, @@ -554,6 +566,9 @@ static int mv88e6xxx_port_set_cmode(struct mv88e6xxx_chip *chip, int port, case PHY_INTERFACE_MODE_10GBASER: cmode = MV88E6393X_PORT_STS_CMODE_10GBASER; break; + case PHY_INTERFACE_MODE_USXGMII: + cmode = MV88E6393X_PORT_STS_CMODE_USXGMII; + break; default: cmode = 0; } diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h index aec9d4fd20e3..86deeb347cbc 100644 --- a/drivers/net/dsa/mv88e6xxx/port.h +++ b/drivers/net/dsa/mv88e6xxx/port.h @@ -111,6 +111,8 @@ /* Offset 0x03: Switch Identifier Register */ #define MV88E6XXX_PORT_SWITCH_ID 0x03 #define MV88E6XXX_PORT_SWITCH_ID_PROD_MASK 0xfff0 +#define MV88E6XXX_PORT_SWITCH_ID_PROD_6020 0x0200 +#define MV88E6XXX_PORT_SWITCH_ID_PROD_6071 0x0710 #define MV88E6XXX_PORT_SWITCH_ID_PROD_6085 0x04a0 #define MV88E6XXX_PORT_SWITCH_ID_PROD_6095 0x0950 #define MV88E6XXX_PORT_SWITCH_ID_PROD_6097 0x0990 @@ -133,6 +135,7 @@ #define MV88E6XXX_PORT_SWITCH_ID_PROD_6220 0x2200 #define MV88E6XXX_PORT_SWITCH_ID_PROD_6240 0x2400 #define MV88E6XXX_PORT_SWITCH_ID_PROD_6250 0x2500 +#define MV88E6XXX_PORT_SWITCH_ID_PROD_6361 0x2610 #define MV88E6XXX_PORT_SWITCH_ID_PROD_6290 0x2900 #define MV88E6XXX_PORT_SWITCH_ID_PROD_6321 0x3100 #define MV88E6XXX_PORT_SWITCH_ID_PROD_6141 0x3400 @@ -276,7 +279,7 @@ /* Offset 0x10: Extended Port Control Command */ #define MV88E6393X_PORT_EPC_CMD 0x10 #define MV88E6393X_PORT_EPC_CMD_BUSY 0x8000 -#define MV88E6393X_PORT_EPC_CMD_WRITE 0x0300 +#define MV88E6393X_PORT_EPC_CMD_WRITE 0x3000 #define MV88E6393X_PORT_EPC_INDEX_PORT_ETYPE 0x02 /* Offset 0x11: Extended Port Control Data */ @@ -359,10 +362,14 @@ int mv88e6390x_port_set_speed_duplex(struct mv88e6xxx_chip *chip, int port, int mv88e6393x_port_set_speed_duplex(struct mv88e6xxx_chip *chip, int port, int speed, int duplex); -phy_interface_t mv88e6341_port_max_speed_mode(int port); -phy_interface_t mv88e6390_port_max_speed_mode(int port); -phy_interface_t mv88e6390x_port_max_speed_mode(int port); -phy_interface_t mv88e6393x_port_max_speed_mode(int port); +phy_interface_t mv88e6341_port_max_speed_mode(struct mv88e6xxx_chip *chip, + int port); +phy_interface_t mv88e6390_port_max_speed_mode(struct mv88e6xxx_chip *chip, + int port); +phy_interface_t mv88e6390x_port_max_speed_mode(struct mv88e6xxx_chip *chip, + int port); +phy_interface_t mv88e6393x_port_max_speed_mode(struct mv88e6xxx_chip *chip, + int port); int mv88e6xxx_port_set_state(struct mv88e6xxx_chip *chip, int port, u8 state); diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c index 72faec8f44dc..80167d53212f 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.c +++ b/drivers/net/dsa/mv88e6xxx/serdes.c @@ -683,7 +683,8 @@ int mv88e6393x_serdes_get_lane(struct mv88e6xxx_chip *chip, int port) cmode == MV88E6XXX_PORT_STS_CMODE_SGMII || cmode == MV88E6XXX_PORT_STS_CMODE_2500BASEX || cmode == MV88E6393X_PORT_STS_CMODE_5GBASER || - cmode == MV88E6393X_PORT_STS_CMODE_10GBASER) + cmode == MV88E6393X_PORT_STS_CMODE_10GBASER || + cmode == MV88E6393X_PORT_STS_CMODE_USXGMII) lane = port; return lane; @@ -984,7 +985,42 @@ static int mv88e6393x_serdes_pcs_get_state_10g(struct mv88e6xxx_chip *chip, state->speed = SPEED_10000; state->duplex = DUPLEX_FULL; } + return 0; +} + +/* USXGMII registers for Marvell switch 88e639x are undocumented and this function is based + * on some educated guesses. It appears that there are no status bits related to + * autonegotiation complete or flow control. + */ +static int mv88e639x_serdes_pcs_get_state_usxgmii(struct mv88e6xxx_chip *chip, + int port, int lane, + struct phylink_link_state *state) +{ + u16 status, lp_status; + int err; + err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS, + MV88E6390_USXGMII_PHY_STATUS, &status); + if (err) { + dev_err(chip->dev, "can't read Serdes USXGMII PHY status: %d\n", err); + return err; + } + dev_dbg(chip->dev, "USXGMII PHY status: 0x%x\n", status); + + state->link = !!(status & MDIO_USXGMII_LINK); + state->an_complete = state->link; + + if (state->link) { + err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS, + MV88E6390_USXGMII_LP_STATUS, &lp_status); + if (err) { + dev_err(chip->dev, "can't read Serdes USXGMII LP status: %d\n", err); + return err; + } + dev_dbg(chip->dev, "USXGMII LP status: 0x%x\n", lp_status); + /* lp_status appears to include the "link" bit as per USXGMII spec. */ + phylink_decode_usxgmii_word(state, lp_status); + } return 0; } @@ -1020,6 +1056,9 @@ int mv88e6393x_serdes_pcs_get_state(struct mv88e6xxx_chip *chip, int port, case PHY_INTERFACE_MODE_10GBASER: return mv88e6393x_serdes_pcs_get_state_10g(chip, port, lane, state); + case PHY_INTERFACE_MODE_USXGMII: + return mv88e639x_serdes_pcs_get_state_usxgmii(chip, port, lane, + state); default: return -EOPNOTSUPP; @@ -1173,6 +1212,7 @@ int mv88e6393x_serdes_irq_enable(struct mv88e6xxx_chip *chip, int port, return mv88e6390_serdes_irq_enable_sgmii(chip, lane, enable); case MV88E6393X_PORT_STS_CMODE_5GBASER: case MV88E6393X_PORT_STS_CMODE_10GBASER: + case MV88E6393X_PORT_STS_CMODE_USXGMII: return mv88e6393x_serdes_irq_enable_10g(chip, lane, enable); } @@ -1213,6 +1253,7 @@ irqreturn_t mv88e6393x_serdes_irq_status(struct mv88e6xxx_chip *chip, int port, break; case MV88E6393X_PORT_STS_CMODE_5GBASER: case MV88E6393X_PORT_STS_CMODE_10GBASER: + case MV88E6393X_PORT_STS_CMODE_USXGMII: err = mv88e6393x_serdes_irq_status_10g(chip, lane, &status); if (err) return err; @@ -1477,7 +1518,8 @@ static int mv88e6393x_serdes_erratum_5_2(struct mv88e6xxx_chip *chip, int lane, * to SERDES operating in 10G mode. These registers only apply to 10G * operation and have no effect on other speeds. */ - if (cmode != MV88E6393X_PORT_STS_CMODE_10GBASER) + if (cmode != MV88E6393X_PORT_STS_CMODE_10GBASER && + cmode != MV88E6393X_PORT_STS_CMODE_USXGMII) return 0; for (i = 0; i < ARRAY_SIZE(fixes); ++i) { @@ -1582,6 +1624,7 @@ int mv88e6393x_serdes_power(struct mv88e6xxx_chip *chip, int port, int lane, break; case MV88E6393X_PORT_STS_CMODE_5GBASER: case MV88E6393X_PORT_STS_CMODE_10GBASER: + case MV88E6393X_PORT_STS_CMODE_USXGMII: err = mv88e6390_serdes_power_10g(chip, lane, on); break; default: diff --git a/drivers/net/dsa/mv88e6xxx/serdes.h b/drivers/net/dsa/mv88e6xxx/serdes.h index 29bb4e91e2f6..e245687ddb1d 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.h +++ b/drivers/net/dsa/mv88e6xxx/serdes.h @@ -48,6 +48,10 @@ #define MV88E6393X_10G_INT_LINK_CHANGE BIT(2) #define MV88E6393X_10G_INT_STATUS 0x9001 +/* USXGMII */ +#define MV88E6390_USXGMII_LP_STATUS 0xf0a2 +#define MV88E6390_USXGMII_PHY_STATUS 0xf0a6 + /* 1000BASE-X and SGMII */ #define MV88E6390_SGMII_BMCR (0x2000 + MII_BMCR) #define MV88E6390_SGMII_BMSR (0x2000 + MII_BMSR) diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index cfb3faeaa5bf..903532ea9fa4 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -1021,7 +1021,6 @@ static int vsc9959_mdio_bus_alloc(struct ocelot *ocelot) for (port = 0; port < felix->info->num_ports; port++) { struct ocelot_port *ocelot_port = ocelot->ports[port]; struct phylink_pcs *phylink_pcs; - struct mdio_device *mdio_device; if (dsa_is_unused_port(felix->ds, port)) continue; @@ -1029,16 +1028,10 @@ static int vsc9959_mdio_bus_alloc(struct ocelot *ocelot) if (ocelot_port->phy_mode == PHY_INTERFACE_MODE_INTERNAL) continue; - mdio_device = mdio_device_create(felix->imdio, port); - if (IS_ERR(mdio_device)) + phylink_pcs = lynx_pcs_create_mdiodev(felix->imdio, port); + if (IS_ERR(phylink_pcs)) continue; - phylink_pcs = lynx_pcs_create(mdio_device); - if (!phylink_pcs) { - mdio_device_free(mdio_device); - continue; - } - felix->pcs[port] = phylink_pcs; dev_info(dev, "Found PCS at internal MDIO address %d\n", port); @@ -1054,14 +1047,9 @@ static void vsc9959_mdio_bus_free(struct ocelot *ocelot) for (port = 0; port < ocelot->num_phys_ports; port++) { struct phylink_pcs *phylink_pcs = felix->pcs[port]; - struct mdio_device *mdio_device; - if (!phylink_pcs) - continue; - - mdio_device = lynx_get_mdio_device(phylink_pcs); - mdio_device_free(mdio_device); - lynx_pcs_destroy(phylink_pcs); + if (phylink_pcs) + lynx_pcs_destroy(phylink_pcs); } mdiobus_unregister(felix->imdio); mdiobus_free(felix->imdio); @@ -1423,7 +1411,7 @@ static int vsc9959_qos_port_tas_set(struct ocelot *ocelot, int port, mutex_lock(&ocelot->tas_lock); - if (!taprio->enable) { + if (taprio->cmd == TAPRIO_CMD_DESTROY) { ocelot_port_mqprio(ocelot, port, &taprio->mqprio); ocelot_rmw_rix(ocelot, 0, QSYS_TAG_CONFIG_ENABLE, QSYS_TAG_CONFIG, port); @@ -1435,6 +1423,9 @@ static int vsc9959_qos_port_tas_set(struct ocelot *ocelot, int port, mutex_unlock(&ocelot->tas_lock); return 0; + } else if (taprio->cmd != TAPRIO_CMD_REPLACE) { + ret = -EOPNOTSUPP; + goto err_unlock; } ret = ocelot_port_mqprio(ocelot, port, &taprio->mqprio); diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c index 96d4972a62f0..15003b2af264 100644 --- a/drivers/net/dsa/ocelot/seville_vsc9953.c +++ b/drivers/net/dsa/ocelot/seville_vsc9953.c @@ -912,7 +912,6 @@ static int vsc9953_mdio_bus_alloc(struct ocelot *ocelot) for (port = 0; port < felix->info->num_ports; port++) { struct ocelot_port *ocelot_port = ocelot->ports[port]; struct phylink_pcs *phylink_pcs; - struct mdio_device *mdio_device; int addr = port + 4; if (dsa_is_unused_port(felix->ds, port)) @@ -921,16 +920,10 @@ static int vsc9953_mdio_bus_alloc(struct ocelot *ocelot) if (ocelot_port->phy_mode == PHY_INTERFACE_MODE_INTERNAL) continue; - mdio_device = mdio_device_create(felix->imdio, addr); - if (IS_ERR(mdio_device)) + phylink_pcs = lynx_pcs_create_mdiodev(felix->imdio, addr); + if (IS_ERR(phylink_pcs)) continue; - phylink_pcs = lynx_pcs_create(mdio_device); - if (!phylink_pcs) { - mdio_device_free(mdio_device); - continue; - } - felix->pcs[port] = phylink_pcs; dev_info(dev, "Found PCS at internal MDIO address %d\n", addr); @@ -946,14 +939,9 @@ static void vsc9953_mdio_bus_free(struct ocelot *ocelot) for (port = 0; port < ocelot->num_phys_ports; port++) { struct phylink_pcs *phylink_pcs = felix->pcs[port]; - struct mdio_device *mdio_device; - - if (!phylink_pcs) - continue; - mdio_device = lynx_get_mdio_device(phylink_pcs); - mdio_device_free(mdio_device); - lynx_pcs_destroy(phylink_pcs); + if (phylink_pcs) + lynx_pcs_destroy(phylink_pcs); } /* mdiobus_unregister and mdiobus_free handled by devres */ diff --git a/drivers/net/dsa/qca/Kconfig b/drivers/net/dsa/qca/Kconfig index 4347b42c50fd..de9da469908b 100644 --- a/drivers/net/dsa/qca/Kconfig +++ b/drivers/net/dsa/qca/Kconfig @@ -20,6 +20,7 @@ config NET_DSA_QCA8K_LEDS_SUPPORT bool "Qualcomm Atheros QCA8K Ethernet switch family LEDs support" depends on NET_DSA_QCA8K depends on LEDS_CLASS=y || LEDS_CLASS=NET_DSA_QCA8K + depends on LEDS_TRIGGERS help This enabled support for LEDs present on the Qualcomm Atheros QCA8K Ethernet switch chips. diff --git a/drivers/net/dsa/qca/ar9331.c b/drivers/net/dsa/qca/ar9331.c index e7b98b864fa1..b2bf78ac485e 100644 --- a/drivers/net/dsa/qca/ar9331.c +++ b/drivers/net/dsa/qca/ar9331.c @@ -391,7 +391,7 @@ static int ar9331_sw_mbus_init(struct ar9331_sw_priv *priv) static int ar9331_sw_setup_port(struct dsa_switch *ds, int port) { - struct ar9331_sw_priv *priv = (struct ar9331_sw_priv *)ds->priv; + struct ar9331_sw_priv *priv = ds->priv; struct regmap *regmap = priv->regmap; u32 port_mask, port_ctrl, val; int ret; @@ -439,7 +439,7 @@ error: static int ar9331_sw_setup(struct dsa_switch *ds) { - struct ar9331_sw_priv *priv = (struct ar9331_sw_priv *)ds->priv; + struct ar9331_sw_priv *priv = ds->priv; struct regmap *regmap = priv->regmap; int ret, i; @@ -484,7 +484,7 @@ error: static void ar9331_sw_port_disable(struct dsa_switch *ds, int port) { - struct ar9331_sw_priv *priv = (struct ar9331_sw_priv *)ds->priv; + struct ar9331_sw_priv *priv = ds->priv; struct regmap *regmap = priv->regmap; int ret; @@ -527,7 +527,7 @@ static void ar9331_sw_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, const struct phylink_link_state *state) { - struct ar9331_sw_priv *priv = (struct ar9331_sw_priv *)ds->priv; + struct ar9331_sw_priv *priv = ds->priv; struct regmap *regmap = priv->regmap; int ret; @@ -542,7 +542,7 @@ static void ar9331_sw_phylink_mac_link_down(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface) { - struct ar9331_sw_priv *priv = (struct ar9331_sw_priv *)ds->priv; + struct ar9331_sw_priv *priv = ds->priv; struct ar9331_sw_port *p = &priv->port[port]; struct regmap *regmap = priv->regmap; int ret; @@ -562,7 +562,7 @@ static void ar9331_sw_phylink_mac_link_up(struct dsa_switch *ds, int port, int speed, int duplex, bool tx_pause, bool rx_pause) { - struct ar9331_sw_priv *priv = (struct ar9331_sw_priv *)ds->priv; + struct ar9331_sw_priv *priv = ds->priv; struct ar9331_sw_port *p = &priv->port[port]; struct regmap *regmap = priv->regmap; u32 val; @@ -665,7 +665,7 @@ static void ar9331_do_stats_poll(struct work_struct *work) static void ar9331_get_stats64(struct dsa_switch *ds, int port, struct rtnl_link_stats64 *s) { - struct ar9331_sw_priv *priv = (struct ar9331_sw_priv *)ds->priv; + struct ar9331_sw_priv *priv = ds->priv; struct ar9331_sw_port *p = &priv->port[port]; spin_lock(&p->stats_lock); @@ -676,7 +676,7 @@ static void ar9331_get_stats64(struct dsa_switch *ds, int port, static void ar9331_get_pause_stats(struct dsa_switch *ds, int port, struct ethtool_pause_stats *pause_stats) { - struct ar9331_sw_priv *priv = (struct ar9331_sw_priv *)ds->priv; + struct ar9331_sw_priv *priv = ds->priv; struct ar9331_sw_port *p = &priv->port[port]; spin_lock(&p->stats_lock); diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c index 6d5ac7588a69..dee7b6579916 100644 --- a/drivers/net/dsa/qca/qca8k-8xxx.c +++ b/drivers/net/dsa/qca/qca8k-8xxx.c @@ -1756,7 +1756,7 @@ static int qca8k_connect_tag_protocol(struct dsa_switch *ds, static int qca8k_setup(struct dsa_switch *ds) { - struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv; + struct qca8k_priv *priv = ds->priv; int cpu_port, ret, i; u32 mask; diff --git a/drivers/net/dsa/qca/qca8k-common.c b/drivers/net/dsa/qca/qca8k-common.c index 96773e432558..8c2dc0e48ff4 100644 --- a/drivers/net/dsa/qca/qca8k-common.c +++ b/drivers/net/dsa/qca/qca8k-common.c @@ -760,7 +760,7 @@ int qca8k_port_fdb_add(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db) { - struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv; + struct qca8k_priv *priv = ds->priv; u16 port_mask = BIT(port); return qca8k_port_fdb_insert(priv, addr, port_mask, vid); @@ -770,7 +770,7 @@ int qca8k_port_fdb_del(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db) { - struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv; + struct qca8k_priv *priv = ds->priv; u16 port_mask = BIT(port); if (!vid) @@ -782,7 +782,7 @@ int qca8k_port_fdb_del(struct dsa_switch *ds, int port, int qca8k_port_fdb_dump(struct dsa_switch *ds, int port, dsa_fdb_dump_cb_t *cb, void *data) { - struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv; + struct qca8k_priv *priv = ds->priv; struct qca8k_fdb _fdb = { 0 }; int cnt = QCA8K_NUM_FDB_RECORDS; bool is_static; diff --git a/drivers/net/dsa/qca/qca8k-leds.c b/drivers/net/dsa/qca/qca8k-leds.c index b883692b7d86..6f02029b454b 100644 --- a/drivers/net/dsa/qca/qca8k-leds.c +++ b/drivers/net/dsa/qca/qca8k-leds.c @@ -5,6 +5,18 @@ #include "qca8k.h" #include "qca8k_leds.h" +static u32 qca8k_phy_to_port(int phy) +{ + /* Internal PHY 0 has port at index 1. + * Internal PHY 1 has port at index 2. + * Internal PHY 2 has port at index 3. + * Internal PHY 3 has port at index 4. + * Internal PHY 4 has port at index 5. + */ + + return phy + 1; +} + static int qca8k_get_enable_led_reg(int port_num, int led_num, struct qca8k_led_pattern_en *reg_info) { @@ -32,6 +44,43 @@ qca8k_get_enable_led_reg(int port_num, int led_num, struct qca8k_led_pattern_en } static int +qca8k_get_control_led_reg(int port_num, int led_num, struct qca8k_led_pattern_en *reg_info) +{ + reg_info->reg = QCA8K_LED_CTRL_REG(led_num); + + /* 6 total control rule: + * 3 control rules for phy0-3 that applies to all their leds + * 3 control rules for phy4 + */ + if (port_num == 4) + reg_info->shift = QCA8K_LED_PHY4_CONTROL_RULE_SHIFT; + else + reg_info->shift = QCA8K_LED_PHY0123_CONTROL_RULE_SHIFT; + + return 0; +} + +static int +qca8k_parse_netdev(unsigned long rules, u32 *offload_trigger) +{ + /* Parsing specific to netdev trigger */ + if (test_bit(TRIGGER_NETDEV_TX, &rules)) + *offload_trigger |= QCA8K_LED_TX_BLINK_MASK; + if (test_bit(TRIGGER_NETDEV_RX, &rules)) + *offload_trigger |= QCA8K_LED_RX_BLINK_MASK; + + if (rules && !*offload_trigger) + return -EOPNOTSUPP; + + /* Enable some default rule by default to the requested mode: + * - Blink at 4Hz by default + */ + *offload_trigger |= QCA8K_LED_BLINK_4HZ; + + return 0; +} + +static int qca8k_led_brightness_set(struct qca8k_led *led, enum led_brightness brightness) { @@ -165,6 +214,133 @@ qca8k_cled_blink_set(struct led_classdev *ldev, } static int +qca8k_cled_trigger_offload(struct led_classdev *ldev, bool enable) +{ + struct qca8k_led *led = container_of(ldev, struct qca8k_led, cdev); + + struct qca8k_led_pattern_en reg_info; + struct qca8k_priv *priv = led->priv; + u32 mask, val = QCA8K_LED_ALWAYS_OFF; + + qca8k_get_enable_led_reg(led->port_num, led->led_num, ®_info); + + if (enable) + val = QCA8K_LED_RULE_CONTROLLED; + + if (led->port_num == 0 || led->port_num == 4) { + mask = QCA8K_LED_PATTERN_EN_MASK; + val <<= QCA8K_LED_PATTERN_EN_SHIFT; + } else { + mask = QCA8K_LED_PHY123_PATTERN_EN_MASK; + } + + return regmap_update_bits(priv->regmap, reg_info.reg, mask << reg_info.shift, + val << reg_info.shift); +} + +static bool +qca8k_cled_hw_control_status(struct led_classdev *ldev) +{ + struct qca8k_led *led = container_of(ldev, struct qca8k_led, cdev); + + struct qca8k_led_pattern_en reg_info; + struct qca8k_priv *priv = led->priv; + u32 val; + + qca8k_get_enable_led_reg(led->port_num, led->led_num, ®_info); + + regmap_read(priv->regmap, reg_info.reg, &val); + + val >>= reg_info.shift; + + if (led->port_num == 0 || led->port_num == 4) { + val &= QCA8K_LED_PATTERN_EN_MASK; + val >>= QCA8K_LED_PATTERN_EN_SHIFT; + } else { + val &= QCA8K_LED_PHY123_PATTERN_EN_MASK; + } + + return val == QCA8K_LED_RULE_CONTROLLED; +} + +static int +qca8k_cled_hw_control_is_supported(struct led_classdev *ldev, unsigned long rules) +{ + u32 offload_trigger = 0; + + return qca8k_parse_netdev(rules, &offload_trigger); +} + +static int +qca8k_cled_hw_control_set(struct led_classdev *ldev, unsigned long rules) +{ + struct qca8k_led *led = container_of(ldev, struct qca8k_led, cdev); + struct qca8k_led_pattern_en reg_info; + struct qca8k_priv *priv = led->priv; + u32 offload_trigger = 0; + int ret; + + ret = qca8k_parse_netdev(rules, &offload_trigger); + if (ret) + return ret; + + ret = qca8k_cled_trigger_offload(ldev, true); + if (ret) + return ret; + + qca8k_get_control_led_reg(led->port_num, led->led_num, ®_info); + + return regmap_update_bits(priv->regmap, reg_info.reg, + QCA8K_LED_RULE_MASK << reg_info.shift, + offload_trigger << reg_info.shift); +} + +static int +qca8k_cled_hw_control_get(struct led_classdev *ldev, unsigned long *rules) +{ + struct qca8k_led *led = container_of(ldev, struct qca8k_led, cdev); + struct qca8k_led_pattern_en reg_info; + struct qca8k_priv *priv = led->priv; + u32 val; + int ret; + + /* With hw control not active return err */ + if (!qca8k_cled_hw_control_status(ldev)) + return -EINVAL; + + qca8k_get_control_led_reg(led->port_num, led->led_num, ®_info); + + ret = regmap_read(priv->regmap, reg_info.reg, &val); + if (ret) + return ret; + + val >>= reg_info.shift; + val &= QCA8K_LED_RULE_MASK; + + /* Parsing specific to netdev trigger */ + if (val & QCA8K_LED_TX_BLINK_MASK) + set_bit(TRIGGER_NETDEV_TX, rules); + if (val & QCA8K_LED_RX_BLINK_MASK) + set_bit(TRIGGER_NETDEV_RX, rules); + + return 0; +} + +static struct device *qca8k_cled_hw_control_get_device(struct led_classdev *ldev) +{ + struct qca8k_led *led = container_of(ldev, struct qca8k_led, cdev); + struct qca8k_priv *priv = led->priv; + struct dsa_port *dp; + + dp = dsa_to_port(priv->ds, qca8k_phy_to_port(led->port_num)); + if (!dp) + return NULL; + if (dp->slave) + return &dp->slave->dev; + return NULL; +} + +static int qca8k_parse_port_leds(struct qca8k_priv *priv, struct fwnode_handle *port, int port_num) { struct fwnode_handle *led = NULL, *leds = NULL; @@ -224,6 +400,11 @@ qca8k_parse_port_leds(struct qca8k_priv *priv, struct fwnode_handle *port, int p port_led->cdev.max_brightness = 1; port_led->cdev.brightness_set_blocking = qca8k_cled_brightness_set_blocking; port_led->cdev.blink_set = qca8k_cled_blink_set; + port_led->cdev.hw_control_is_supported = qca8k_cled_hw_control_is_supported; + port_led->cdev.hw_control_set = qca8k_cled_hw_control_set; + port_led->cdev.hw_control_get = qca8k_cled_hw_control_get; + port_led->cdev.hw_control_get_device = qca8k_cled_hw_control_get_device; + port_led->cdev.hw_control_trigger = "netdev"; init_data.default_label = ":port"; init_data.fwnode = led; init_data.devname_mandatory = true; diff --git a/drivers/net/dsa/rzn1_a5psw.c b/drivers/net/dsa/rzn1_a5psw.c index 919027cf2012..c37d2e537230 100644 --- a/drivers/net/dsa/rzn1_a5psw.c +++ b/drivers/net/dsa/rzn1_a5psw.c @@ -120,6 +120,22 @@ static void a5psw_port_mgmtfwd_set(struct a5psw *a5psw, int port, bool enable) a5psw_port_pattern_set(a5psw, port, A5PSW_PATTERN_MGMTFWD, enable); } +static void a5psw_port_tx_enable(struct a5psw *a5psw, int port, bool enable) +{ + u32 mask = A5PSW_PORT_ENA_TX(port); + u32 reg = enable ? mask : 0; + + /* Even though the port TX is disabled through TXENA bit in the + * PORT_ENA register, it can still send BPDUs. This depends on the tag + * configuration added when sending packets from the CPU port to the + * switch port. Indeed, when using forced forwarding without filtering, + * even disabled ports will be able to send packets that are tagged. + * This allows to implement STP support when ports are in a state where + * forwarding traffic should be stopped but BPDUs should still be sent. + */ + a5psw_reg_rmw(a5psw, A5PSW_PORT_ENA, mask, reg); +} + static void a5psw_port_enable_set(struct a5psw *a5psw, int port, bool enable) { u32 port_ena = 0; @@ -292,6 +308,22 @@ static int a5psw_set_ageing_time(struct dsa_switch *ds, unsigned int msecs) return 0; } +static void a5psw_port_learning_set(struct a5psw *a5psw, int port, bool learn) +{ + u32 mask = A5PSW_INPUT_LEARN_DIS(port); + u32 reg = !learn ? mask : 0; + + a5psw_reg_rmw(a5psw, A5PSW_INPUT_LEARN, mask, reg); +} + +static void a5psw_port_rx_block_set(struct a5psw *a5psw, int port, bool block) +{ + u32 mask = A5PSW_INPUT_LEARN_BLOCK(port); + u32 reg = block ? mask : 0; + + a5psw_reg_rmw(a5psw, A5PSW_INPUT_LEARN, mask, reg); +} + static void a5psw_flooding_set_resolution(struct a5psw *a5psw, int port, bool set) { @@ -308,6 +340,14 @@ static void a5psw_flooding_set_resolution(struct a5psw *a5psw, int port, a5psw_reg_writel(a5psw, offsets[i], a5psw->bridged_ports); } +static void a5psw_port_set_standalone(struct a5psw *a5psw, int port, + bool standalone) +{ + a5psw_port_learning_set(a5psw, port, !standalone); + a5psw_flooding_set_resolution(a5psw, port, !standalone); + a5psw_port_mgmtfwd_set(a5psw, port, standalone); +} + static int a5psw_port_bridge_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge, bool *tx_fwd_offload, @@ -323,8 +363,7 @@ static int a5psw_port_bridge_join(struct dsa_switch *ds, int port, } a5psw->br_dev = bridge.dev; - a5psw_flooding_set_resolution(a5psw, port, true); - a5psw_port_mgmtfwd_set(a5psw, port, false); + a5psw_port_set_standalone(a5psw, port, false); return 0; } @@ -334,8 +373,7 @@ static void a5psw_port_bridge_leave(struct dsa_switch *ds, int port, { struct a5psw *a5psw = ds->priv; - a5psw_flooding_set_resolution(a5psw, port, false); - a5psw_port_mgmtfwd_set(a5psw, port, true); + a5psw_port_set_standalone(a5psw, port, true); /* No more ports bridged */ if (a5psw->bridged_ports == BIT(A5PSW_CPU_PORT)) @@ -344,28 +382,35 @@ static void a5psw_port_bridge_leave(struct dsa_switch *ds, int port, static void a5psw_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) { - u32 mask = A5PSW_INPUT_LEARN_DIS(port) | A5PSW_INPUT_LEARN_BLOCK(port); + bool learning_enabled, rx_enabled, tx_enabled; struct a5psw *a5psw = ds->priv; - u32 reg = 0; switch (state) { case BR_STATE_DISABLED: case BR_STATE_BLOCKING: - reg |= A5PSW_INPUT_LEARN_DIS(port); - reg |= A5PSW_INPUT_LEARN_BLOCK(port); - break; case BR_STATE_LISTENING: - reg |= A5PSW_INPUT_LEARN_DIS(port); + rx_enabled = false; + tx_enabled = false; + learning_enabled = false; break; case BR_STATE_LEARNING: - reg |= A5PSW_INPUT_LEARN_BLOCK(port); + rx_enabled = false; + tx_enabled = false; + learning_enabled = true; break; case BR_STATE_FORWARDING: - default: + rx_enabled = true; + tx_enabled = true; + learning_enabled = true; break; + default: + dev_err(ds->dev, "invalid STP state: %d\n", state); + return; } - a5psw_reg_rmw(a5psw, A5PSW_INPUT_LEARN, mask, reg); + a5psw_port_learning_set(a5psw, port, learning_enabled); + a5psw_port_rx_block_set(a5psw, port, !rx_enabled); + a5psw_port_tx_enable(a5psw, port, tx_enabled); } static void a5psw_port_fast_age(struct dsa_switch *ds, int port) @@ -673,7 +718,7 @@ static int a5psw_setup(struct dsa_switch *ds) } /* Configure management port */ - reg = A5PSW_CPU_PORT | A5PSW_MGMT_CFG_DISCARD; + reg = A5PSW_CPU_PORT | A5PSW_MGMT_CFG_ENABLE; a5psw_reg_writel(a5psw, A5PSW_MGMT_CFG, reg); /* Set pattern 0 to forward all frame to mgmt port */ @@ -722,13 +767,15 @@ static int a5psw_setup(struct dsa_switch *ds) if (dsa_port_is_unused(dp)) continue; - /* Enable egress flooding for CPU port */ - if (dsa_port_is_cpu(dp)) + /* Enable egress flooding and learning for CPU port */ + if (dsa_port_is_cpu(dp)) { a5psw_flooding_set_resolution(a5psw, port, true); + a5psw_port_learning_set(a5psw, port, true); + } - /* Enable management forward only for user ports */ + /* Enable standalone mode for user ports */ if (dsa_port_is_user(dp)) - a5psw_port_mgmtfwd_set(a5psw, port, true); + a5psw_port_set_standalone(a5psw, port, true); } return 0; diff --git a/drivers/net/dsa/rzn1_a5psw.h b/drivers/net/dsa/rzn1_a5psw.h index c67abd49c013..b869192eef3f 100644 --- a/drivers/net/dsa/rzn1_a5psw.h +++ b/drivers/net/dsa/rzn1_a5psw.h @@ -19,6 +19,7 @@ #define A5PSW_PORT_OFFSET(port) (0x400 * (port)) #define A5PSW_PORT_ENA 0x8 +#define A5PSW_PORT_ENA_TX(port) BIT(port) #define A5PSW_PORT_ENA_RX_SHIFT 16 #define A5PSW_PORT_ENA_TX_RX(port) (BIT((port) + A5PSW_PORT_ENA_RX_SHIFT) | \ BIT(port)) @@ -36,7 +37,7 @@ #define A5PSW_INPUT_LEARN_BLOCK(p) BIT(p) #define A5PSW_MGMT_CFG 0x20 -#define A5PSW_MGMT_CFG_DISCARD BIT(7) +#define A5PSW_MGMT_CFG_ENABLE BIT(6) #define A5PSW_MODE_CFG 0x24 #define A5PSW_MODE_STATS_RESET BIT(31) diff --git a/drivers/net/dsa/sja1105/sja1105_mdio.c b/drivers/net/dsa/sja1105/sja1105_mdio.c index 01f1cb719042..833e55e4b961 100644 --- a/drivers/net/dsa/sja1105/sja1105_mdio.c +++ b/drivers/net/dsa/sja1105/sja1105_mdio.c @@ -400,7 +400,6 @@ static int sja1105_mdiobus_pcs_register(struct sja1105_private *priv) } for (port = 0; port < ds->num_ports; port++) { - struct mdio_device *mdiodev; struct dw_xpcs *xpcs; if (dsa_is_unused_port(ds, port)) @@ -410,13 +409,7 @@ static int sja1105_mdiobus_pcs_register(struct sja1105_private *priv) priv->phy_mode[port] != PHY_INTERFACE_MODE_2500BASEX) continue; - mdiodev = mdio_device_create(bus, port); - if (IS_ERR(mdiodev)) { - rc = PTR_ERR(mdiodev); - goto out_pcs_free; - } - - xpcs = xpcs_create(mdiodev, priv->phy_mode[port]); + xpcs = xpcs_create_mdiodev(bus, port, priv->phy_mode[port]); if (IS_ERR(xpcs)) { rc = PTR_ERR(xpcs); goto out_pcs_free; @@ -434,7 +427,6 @@ out_pcs_free: if (!priv->xpcs[port]) continue; - mdio_device_free(priv->xpcs[port]->mdiodev); xpcs_destroy(priv->xpcs[port]); priv->xpcs[port] = NULL; } @@ -457,7 +449,6 @@ static void sja1105_mdiobus_pcs_unregister(struct sja1105_private *priv) if (!priv->xpcs[port]) continue; - mdio_device_free(priv->xpcs[port]->mdiodev); xpcs_destroy(priv->xpcs[port]); priv->xpcs[port] = NULL; } diff --git a/drivers/net/dsa/sja1105/sja1105_tas.c b/drivers/net/dsa/sja1105/sja1105_tas.c index e6153848a950..d7818710bc02 100644 --- a/drivers/net/dsa/sja1105/sja1105_tas.c +++ b/drivers/net/dsa/sja1105/sja1105_tas.c @@ -516,10 +516,11 @@ int sja1105_setup_tc_taprio(struct dsa_switch *ds, int port, /* Can't change an already configured port (must delete qdisc first). * Can't delete the qdisc from an unconfigured port. */ - if (!!tas_data->offload[port] == admin->enable) + if ((!!tas_data->offload[port] && admin->cmd == TAPRIO_CMD_REPLACE) || + (!tas_data->offload[port] && admin->cmd == TAPRIO_CMD_DESTROY)) return -EINVAL; - if (!admin->enable) { + if (admin->cmd == TAPRIO_CMD_DESTROY) { taprio_offload_free(tas_data->offload[port]); tas_data->offload[port] = NULL; @@ -528,6 +529,8 @@ int sja1105_setup_tc_taprio(struct dsa_switch *ds, int port, return rc; return sja1105_static_config_reload(priv, SJA1105_SCHEDULING); + } else if (admin->cmd != TAPRIO_CMD_REPLACE) { + return -EOPNOTSUPP; } /* The cycle time extension is the amount of time the last cycle from diff --git a/drivers/net/dsa/xrs700x/xrs700x_i2c.c b/drivers/net/dsa/xrs700x/xrs700x_i2c.c index 14ff6887a225..c1179d7311f7 100644 --- a/drivers/net/dsa/xrs700x/xrs700x_i2c.c +++ b/drivers/net/dsa/xrs700x/xrs700x_i2c.c @@ -147,7 +147,7 @@ static struct i2c_driver xrs700x_i2c_driver = { .name = "xrs700x-i2c", .of_match_table = of_match_ptr(xrs700x_i2c_dt_ids), }, - .probe_new = xrs700x_i2c_probe, + .probe = xrs700x_i2c_probe, .remove = xrs700x_i2c_remove, .shutdown = xrs700x_i2c_shutdown, .id_table = xrs700x_i2c_id, diff --git a/drivers/net/ethernet/3com/3c515.c b/drivers/net/ethernet/3com/3c515.c index d2f4358cc550..ba3e7aa1a28f 100644 --- a/drivers/net/ethernet/3com/3c515.c +++ b/drivers/net/ethernet/3com/3c515.c @@ -66,8 +66,10 @@ static int max_interrupt_work = 20; #include <linux/timer.h> #include <linux/ethtool.h> #include <linux/bitops.h> - #include <linux/uaccess.h> + +#include <net/Space.h> + #include <asm/io.h> #include <asm/dma.h> diff --git a/drivers/net/ethernet/3com/3c589_cs.c b/drivers/net/ethernet/3com/3c589_cs.c index 82f94b1635bf..5267e9dcd87e 100644 --- a/drivers/net/ethernet/3com/3c589_cs.c +++ b/drivers/net/ethernet/3com/3c589_cs.c @@ -195,6 +195,7 @@ static int tc589_probe(struct pcmcia_device *link) { struct el3_private *lp; struct net_device *dev; + int ret; dev_dbg(&link->dev, "3c589_attach()\n"); @@ -218,7 +219,15 @@ static int tc589_probe(struct pcmcia_device *link) dev->ethtool_ops = &netdev_ethtool_ops; - return tc589_config(link); + ret = tc589_config(link); + if (ret) + goto err_free_netdev; + + return 0; + +err_free_netdev: + free_netdev(dev); + return ret; } static void tc589_detach(struct pcmcia_device *link) diff --git a/drivers/net/ethernet/8390/8390.h b/drivers/net/ethernet/8390/8390.h index e52264465998..f784a6e2ab0e 100644 --- a/drivers/net/ethernet/8390/8390.h +++ b/drivers/net/ethernet/8390/8390.h @@ -1,3 +1,5 @@ +/* SPDX-License-Identifier: GPL-1.0+ */ + /* Generic NS8390 register definitions. */ /* This file is part of Donald Becker's 8390 drivers, and is distributed diff --git a/drivers/net/ethernet/8390/apne.c b/drivers/net/ethernet/8390/apne.c index 991ad953aa79..a09f383dd249 100644 --- a/drivers/net/ethernet/8390/apne.c +++ b/drivers/net/ethernet/8390/apne.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Amiga Linux/68k 8390 based PCMCIA Ethernet Driver for the Amiga 1200 * @@ -19,12 +20,6 @@ * * ---------------------------------------------------------------------------- * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file COPYING in the main directory of the Linux - * distribution for more details. - * - * ---------------------------------------------------------------------------- - * */ diff --git a/drivers/net/ethernet/8390/axnet_cs.c b/drivers/net/ethernet/8390/axnet_cs.c index 78f985885547..fea489af72fb 100644 --- a/drivers/net/ethernet/8390/axnet_cs.c +++ b/drivers/net/ethernet/8390/axnet_cs.c @@ -1,3 +1,5 @@ +// SPDX-License-Identifier: GPL-1.0+ + /*====================================================================== A PCMCIA ethernet driver for Asix AX88190-based cards @@ -17,9 +19,7 @@ Written 1992,1993 by Donald Becker. Copyright 1993 United States Government as represented by the - Director, National Security Agency. This software may be used and - distributed according to the terms of the GNU General Public License, - incorporated herein by reference. + Director, National Security Agency. Donald Becker may be reached at becker@scyld.com ======================================================================*/ diff --git a/drivers/net/ethernet/8390/hydra.c b/drivers/net/ethernet/8390/hydra.c index 1df7601af86a..24f49a8ff903 100644 --- a/drivers/net/ethernet/8390/hydra.c +++ b/drivers/net/ethernet/8390/hydra.c @@ -1,10 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-only + /* New Hydra driver using generic 8390 core */ /* Based on old hydra driver by Topi Kanerva (topi@susanna.oulu.fi) */ -/* This file is subject to the terms and conditions of the GNU General */ -/* Public License. See the file COPYING in the main directory of the */ -/* Linux distribution for more details. */ - /* Peter De Schrijver (p2@mind.be) */ /* Oldenburg 2000 */ diff --git a/drivers/net/ethernet/8390/lib8390.c b/drivers/net/ethernet/8390/lib8390.c index e84021282edf..84aeb8054304 100644 --- a/drivers/net/ethernet/8390/lib8390.c +++ b/drivers/net/ethernet/8390/lib8390.c @@ -1,3 +1,5 @@ +// SPDX-License-Identifier: GPL-1.0+ + /* 8390.c: A general NS8390 ethernet driver core for linux. */ /* Written 1992-94 by Donald Becker. @@ -5,9 +7,6 @@ Copyright 1993 United States Government as represented by the Director, National Security Agency. - This software may be used and distributed according to the terms - of the GNU General Public License, incorporated herein by reference. - The author may be reached as becker@scyld.com, or C/O Scyld Computing Corporation 410 Severn Ave., Suite 210 diff --git a/drivers/net/ethernet/8390/mac8390.c b/drivers/net/ethernet/8390/mac8390.c index 7fb819b9b89a..4a0a095a1a8a 100644 --- a/drivers/net/ethernet/8390/mac8390.c +++ b/drivers/net/ethernet/8390/mac8390.c @@ -1,11 +1,9 @@ +// SPDX-License-Identifier: GPL-1.0+ /* mac8390.c: New driver for 8390-based Nubus (or Nubus-alike) Ethernet cards on Linux */ /* Based on the former daynaport.c driver, by Alan Cox. Some code taken from or inspired by skeleton.c by Donald Becker, acenic.c by - Jes Sorensen, and ne2k-pci.c by Donald Becker and Paul Gortmaker. - - This software may be used and distributed according to the terms of - the GNU Public License, incorporated herein by reference. */ + Jes Sorensen, and ne2k-pci.c by Donald Becker and Paul Gortmaker. */ /* 2000-02-28: support added for Dayna and Kinetics cards by A.G.deWijn@phys.uu.nl */ diff --git a/drivers/net/ethernet/8390/mcf8390.c b/drivers/net/ethernet/8390/mcf8390.c index 8a7918d33419..217838b28220 100644 --- a/drivers/net/ethernet/8390/mcf8390.c +++ b/drivers/net/ethernet/8390/mcf8390.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Support for ColdFire CPU based boards using a NS8390 Ethernet device. * @@ -5,9 +6,6 @@ * * (C) Copyright 2012, Greg Ungerer <gerg@uclinux.org> * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file COPYING in the main directory of the Linux - * distribution for more details. */ #include <linux/module.h> diff --git a/drivers/net/ethernet/8390/ne.c b/drivers/net/ethernet/8390/ne.c index 0a9118b8be0c..7d89ec1cf273 100644 --- a/drivers/net/ethernet/8390/ne.c +++ b/drivers/net/ethernet/8390/ne.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-1.0+ /* ne.c: A general non-shared-memory NS8390 ethernet driver for linux. */ /* Written 1992-94 by Donald Becker. @@ -5,9 +6,6 @@ Copyright 1993 United States Government as represented by the Director, National Security Agency. - This software may be used and distributed according to the terms - of the GNU General Public License, incorporated herein by reference. - The author may be reached as becker@scyld.com, or C/O Scyld Computing Corporation, 410 Severn Ave., Suite 210, Annapolis MD 21403 @@ -52,6 +50,7 @@ static const char version2[] = #include <linux/etherdevice.h> #include <linux/jiffies.h> #include <linux/platform_device.h> +#include <net/Space.h> #include <asm/io.h> diff --git a/drivers/net/ethernet/8390/ne2k-pci.c b/drivers/net/ethernet/8390/ne2k-pci.c index 6a0a2039600a..2c6bd36d2f31 100644 --- a/drivers/net/ethernet/8390/ne2k-pci.c +++ b/drivers/net/ethernet/8390/ne2k-pci.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-1.0+ /* A Linux device driver for PCI NE2000 clones. * * Authors and other copyright holders: diff --git a/drivers/net/ethernet/8390/pcnet_cs.c b/drivers/net/ethernet/8390/pcnet_cs.c index 0f07fe03da98..9bd5e991f1e5 100644 --- a/drivers/net/ethernet/8390/pcnet_cs.c +++ b/drivers/net/ethernet/8390/pcnet_cs.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-1.0+ /*====================================================================== A PCMCIA ethernet driver for NS8390-based cards @@ -17,9 +18,7 @@ Written 1992,1993 by Donald Becker. Copyright 1993 United States Government as represented by the - Director, National Security Agency. This software may be used and - distributed according to the terms of the GNU General Public License, - incorporated herein by reference. + Director, National Security Agency. Donald Becker may be reached at becker@scyld.com Based also on Keith Moore's changes to Don Becker's code, for IBM diff --git a/drivers/net/ethernet/8390/smc-ultra.c b/drivers/net/ethernet/8390/smc-ultra.c index 6e62c37c9400..22ca804b2e95 100644 --- a/drivers/net/ethernet/8390/smc-ultra.c +++ b/drivers/net/ethernet/8390/smc-ultra.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-1.0+ /* smc-ultra.c: A SMC Ultra ethernet driver for linux. */ /* This is a driver for the SMC Ultra and SMC EtherEZ ISA ethercards. @@ -7,9 +8,6 @@ Copyright 1993 United States Government as represented by the Director, National Security Agency. - This software may be used and distributed according to the terms - of the GNU General Public License, incorporated herein by reference. - The author may be reached as becker@scyld.com, or C/O Scyld Computing Corporation 410 Severn Ave., Suite 210 @@ -66,6 +64,7 @@ static const char version[] = #include <linux/isapnp.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> +#include <net/Space.h> #include <asm/io.h> #include <asm/irq.h> diff --git a/drivers/net/ethernet/8390/stnic.c b/drivers/net/ethernet/8390/stnic.c index bd89ca8a92df..265976e3b64a 100644 --- a/drivers/net/ethernet/8390/stnic.c +++ b/drivers/net/ethernet/8390/stnic.c @@ -1,9 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-only /* stnic.c : A SH7750 specific part of driver for NS DP83902A ST-NIC. * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * * Copyright (C) 1999 kaz Kojima */ diff --git a/drivers/net/ethernet/8390/wd.c b/drivers/net/ethernet/8390/wd.c index 5b00c452bede..ffd639477dfc 100644 --- a/drivers/net/ethernet/8390/wd.c +++ b/drivers/net/ethernet/8390/wd.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-1.0+ /* wd.c: A WD80x3 ethernet driver for linux. */ /* Written 1993-94 by Donald Becker. @@ -5,9 +6,6 @@ Copyright 1993 United States Government as represented by the Director, National Security Agency. - This software may be used and distributed according to the terms - of the GNU General Public License, incorporated herein by reference. - The author may be reached as becker@scyld.com, or C/O Scyld Computing Corporation 410 Severn Ave., Suite 210 @@ -37,6 +35,7 @@ static const char version[] = #include <linux/delay.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> +#include <net/Space.h> #include <asm/io.h> diff --git a/drivers/net/ethernet/8390/zorro8390.c b/drivers/net/ethernet/8390/zorro8390.c index e8b4fe813a08..d70390e9d03d 100644 --- a/drivers/net/ethernet/8390/zorro8390.c +++ b/drivers/net/ethernet/8390/zorro8390.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Amiga Linux/m68k and Linux/PPC Zorro NS8390 Ethernet Driver * @@ -9,12 +10,6 @@ * * --------------------------------------------------------------------------- * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file COPYING in the main directory of the Linux - * distribution for more details. - * - * --------------------------------------------------------------------------- - * * The Ariadne II and X-Surf are Zorro-II boards containing Realtek RTL8019AS * Ethernet Controllers. */ diff --git a/drivers/net/ethernet/altera/Kconfig b/drivers/net/ethernet/altera/Kconfig index dd7fd41ccde5..17985319088c 100644 --- a/drivers/net/ethernet/altera/Kconfig +++ b/drivers/net/ethernet/altera/Kconfig @@ -4,7 +4,9 @@ config ALTERA_TSE depends on HAS_DMA select PHYLIB select PHYLINK - select PCS_ALTERA_TSE + select PCS_LYNX + select MDIO_REGMAP + select REGMAP_MMIO help This driver supports the Altera Triple-Speed (TSE) Ethernet MAC. diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index 66e3af73ec41..2e15800e5310 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -27,14 +27,16 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/mii.h> +#include <linux/mdio/mdio-regmap.h> #include <linux/netdevice.h> #include <linux/of_device.h> #include <linux/of_mdio.h> #include <linux/of_net.h> #include <linux/of_platform.h> -#include <linux/pcs-altera-tse.h> +#include <linux/pcs-lynx.h> #include <linux/phy.h> #include <linux/platform_device.h> +#include <linux/regmap.h> #include <linux/skbuff.h> #include <asm/cacheflush.h> @@ -1036,10 +1038,6 @@ static struct net_device_ops altera_tse_netdev_ops = { .ndo_validate_addr = eth_validate_addr, }; -static void alt_tse_mac_an_restart(struct phylink_config *config) -{ -} - static void alt_tse_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) { @@ -1096,7 +1094,6 @@ static struct phylink_pcs *alt_tse_select_pcs(struct phylink_config *config, } static const struct phylink_mac_ops alt_tse_phylink_ops = { - .mac_an_restart = alt_tse_mac_an_restart, .mac_config = alt_tse_mac_config, .mac_link_down = alt_tse_mac_link_down, .mac_link_up = alt_tse_mac_link_up, @@ -1137,13 +1134,16 @@ static int request_and_map(struct platform_device *pdev, const char *name, static int altera_tse_probe(struct platform_device *pdev) { const struct of_device_id *of_id = NULL; + struct regmap_config pcs_regmap_cfg; struct altera_tse_private *priv; + struct mdio_regmap_config mrc; struct resource *control_port; + struct regmap *pcs_regmap; struct resource *dma_res; struct resource *pcs_res; + struct mii_bus *pcs_bus; struct net_device *ndev; void __iomem *descmap; - int pcs_reg_width = 2; int ret = -ENODEV; ndev = alloc_etherdev(sizeof(struct altera_tse_private)); @@ -1255,18 +1255,41 @@ static int altera_tse_probe(struct platform_device *pdev) if (ret) goto err_free_netdev; + memset(&pcs_regmap_cfg, 0, sizeof(pcs_regmap_cfg)); + memset(&mrc, 0, sizeof(mrc)); /* SGMII PCS address space. The location can vary depending on how the * IP is integrated. We can have a resource dedicated to it at a specific * address space, but if it's not the case, we fallback to the mdiophy0 * from the MAC's address space */ - ret = request_and_map(pdev, "pcs", &pcs_res, - &priv->pcs_base); + ret = request_and_map(pdev, "pcs", &pcs_res, &priv->pcs_base); if (ret) { + /* If we can't find a dedicated resource for the PCS, fallback + * to the internal PCS, that has a different address stride + */ priv->pcs_base = priv->mac_dev + tse_csroffs(mdio_phy0); - pcs_reg_width = 4; + pcs_regmap_cfg.reg_bits = 32; + /* Values are MDIO-like values, on 16 bits */ + pcs_regmap_cfg.val_bits = 16; + pcs_regmap_cfg.reg_shift = REGMAP_UPSHIFT(2); + } else { + pcs_regmap_cfg.reg_bits = 16; + pcs_regmap_cfg.val_bits = 16; + pcs_regmap_cfg.reg_shift = REGMAP_UPSHIFT(1); } + /* Create a regmap for the PCS so that it can be used by the PCS driver */ + pcs_regmap = devm_regmap_init_mmio(&pdev->dev, priv->pcs_base, + &pcs_regmap_cfg); + if (IS_ERR(pcs_regmap)) { + ret = PTR_ERR(pcs_regmap); + goto err_free_netdev; + } + mrc.regmap = pcs_regmap; + mrc.parent = &pdev->dev; + mrc.valid_addr = 0x0; + mrc.autoscan = false; + /* Rx IRQ */ priv->rx_irq = platform_get_irq_byname(pdev, "rx_irq"); if (priv->rx_irq == -ENXIO) { @@ -1389,7 +1412,18 @@ static int altera_tse_probe(struct platform_device *pdev) (unsigned long) control_port->start, priv->rx_irq, priv->tx_irq); - priv->pcs = alt_tse_pcs_create(ndev, priv->pcs_base, pcs_reg_width); + snprintf(mrc.name, MII_BUS_ID_SIZE, "%s-pcs-mii", ndev->name); + pcs_bus = devm_mdio_regmap_register(&pdev->dev, &mrc); + if (IS_ERR(pcs_bus)) { + ret = PTR_ERR(pcs_bus); + goto err_init_pcs; + } + + priv->pcs = lynx_pcs_create_mdiodev(pcs_bus, 0); + if (IS_ERR(priv->pcs)) { + ret = PTR_ERR(priv->pcs); + goto err_init_pcs; + } priv->phylink_config.dev = &ndev->dev; priv->phylink_config.type = PHYLINK_NETDEV; @@ -1412,12 +1446,13 @@ static int altera_tse_probe(struct platform_device *pdev) if (IS_ERR(priv->phylink)) { dev_err(&pdev->dev, "failed to create phylink\n"); ret = PTR_ERR(priv->phylink); - goto err_init_phy; + goto err_init_phylink; } return 0; - -err_init_phy: +err_init_phylink: + lynx_pcs_destroy(priv->pcs); +err_init_pcs: unregister_netdev(ndev); err_register_netdev: netif_napi_del(&priv->napi); @@ -1438,6 +1473,8 @@ static int altera_tse_remove(struct platform_device *pdev) altera_tse_mdio_destroy(ndev); unregister_netdev(ndev); phylink_destroy(priv->phylink); + lynx_pcs_destroy(priv->pcs); + free_netdev(ndev); return 0; diff --git a/drivers/net/ethernet/amd/lance.c b/drivers/net/ethernet/amd/lance.c index 8971665a4b2a..6cf38180cc01 100644 --- a/drivers/net/ethernet/amd/lance.c +++ b/drivers/net/ethernet/amd/lance.c @@ -59,6 +59,7 @@ static const char version[] = "lance.c:v1.16 2006/11/09 dplatt@3do.com, becker@c #include <linux/skbuff.h> #include <linux/mm.h> #include <linux/bitops.h> +#include <net/Space.h> #include <asm/io.h> #include <asm/dma.h> diff --git a/drivers/net/ethernet/amd/pds_core/dev.c b/drivers/net/ethernet/amd/pds_core/dev.c index f7c597ea5daf..debe5216fe29 100644 --- a/drivers/net/ethernet/amd/pds_core/dev.c +++ b/drivers/net/ethernet/amd/pds_core/dev.c @@ -68,9 +68,15 @@ bool pdsc_is_fw_running(struct pdsc *pdsc) bool pdsc_is_fw_good(struct pdsc *pdsc) { - u8 gen = pdsc->fw_status & PDS_CORE_FW_STS_F_GENERATION; + bool fw_running = pdsc_is_fw_running(pdsc); + u8 gen; - return pdsc_is_fw_running(pdsc) && gen == pdsc->fw_generation; + /* Make sure to update the cached fw_status by calling + * pdsc_is_fw_running() before getting the generation + */ + gen = pdsc->fw_status & PDS_CORE_FW_STS_F_GENERATION; + + return fw_running && gen == pdsc->fw_generation; } static u8 pdsc_devcmd_status(struct pdsc *pdsc) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c index 33a9574e9e04..32d2c6fac652 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c @@ -1329,7 +1329,7 @@ static enum xgbe_mode xgbe_phy_status_aneg(struct xgbe_prv_data *pdata) return pdata->phy_if.phy_impl.an_outcome(pdata); } -static void xgbe_phy_status_result(struct xgbe_prv_data *pdata) +static bool xgbe_phy_status_result(struct xgbe_prv_data *pdata) { struct ethtool_link_ksettings *lks = &pdata->phy.lks; enum xgbe_mode mode; @@ -1367,8 +1367,13 @@ static void xgbe_phy_status_result(struct xgbe_prv_data *pdata) pdata->phy.duplex = DUPLEX_FULL; - if (xgbe_set_mode(pdata, mode) && pdata->an_again) + if (!xgbe_set_mode(pdata, mode)) + return false; + + if (pdata->an_again) xgbe_phy_reconfig_aneg(pdata); + + return true; } static void xgbe_phy_status(struct xgbe_prv_data *pdata) @@ -1398,7 +1403,8 @@ static void xgbe_phy_status(struct xgbe_prv_data *pdata) return; } - xgbe_phy_status_result(pdata); + if (xgbe_phy_status_result(pdata)) + return; if (test_bit(XGBE_LINK_INIT, &pdata->dev_state)) clear_bit(XGBE_LINK_INIT, &pdata->dev_state); diff --git a/drivers/net/ethernet/arc/emac.h b/drivers/net/ethernet/arc/emac.h index d820ae03a966..0e244f0e25fd 100644 --- a/drivers/net/ethernet/arc/emac.h +++ b/drivers/net/ethernet/arc/emac.h @@ -220,6 +220,6 @@ static inline void arc_reg_clr(struct arc_emac_priv *priv, int reg, int mask) int arc_mdio_probe(struct arc_emac_priv *priv); int arc_mdio_remove(struct arc_emac_priv *priv); int arc_emac_probe(struct net_device *ndev, int interface); -int arc_emac_remove(struct net_device *ndev); +void arc_emac_remove(struct net_device *ndev); #endif /* ARC_EMAC_H */ diff --git a/drivers/net/ethernet/arc/emac_arc.c b/drivers/net/ethernet/arc/emac_arc.c index 800620b8f10d..ce3147e886a1 100644 --- a/drivers/net/ethernet/arc/emac_arc.c +++ b/drivers/net/ethernet/arc/emac_arc.c @@ -61,11 +61,11 @@ out_netdev: static int emac_arc_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); - int err; - err = arc_emac_remove(ndev); + arc_emac_remove(ndev); free_netdev(ndev); - return err; + + return 0; } static const struct of_device_id emac_arc_dt_ids[] = { diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c index ba0646b3b122..2b427d8a1831 100644 --- a/drivers/net/ethernet/arc/emac_main.c +++ b/drivers/net/ethernet/arc/emac_main.c @@ -1008,7 +1008,7 @@ out_put_node: } EXPORT_SYMBOL_GPL(arc_emac_probe); -int arc_emac_remove(struct net_device *ndev) +void arc_emac_remove(struct net_device *ndev) { struct arc_emac_priv *priv = netdev_priv(ndev); @@ -1019,8 +1019,6 @@ int arc_emac_remove(struct net_device *ndev) if (!IS_ERR(priv->clk)) clk_disable_unprepare(priv->clk); - - return 0; } EXPORT_SYMBOL_GPL(arc_emac_remove); diff --git a/drivers/net/ethernet/arc/emac_rockchip.c b/drivers/net/ethernet/arc/emac_rockchip.c index 1c9ca3bcb871..509101112279 100644 --- a/drivers/net/ethernet/arc/emac_rockchip.c +++ b/drivers/net/ethernet/arc/emac_rockchip.c @@ -248,9 +248,8 @@ static int emac_rockchip_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); struct rockchip_priv_data *priv = netdev_priv(ndev); - int err; - err = arc_emac_remove(ndev); + arc_emac_remove(ndev); clk_disable_unprepare(priv->refclk); @@ -261,7 +260,7 @@ static int emac_rockchip_remove(struct platform_device *pdev) clk_disable_unprepare(priv->macclk); free_netdev(ndev); - return err; + return 0; } static struct platform_driver emac_rockchip_driver = { diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 38d0cdaf22a5..bf1611cce974 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -2531,9 +2531,9 @@ static int bcm_sysport_probe(struct platform_device *pdev) priv->irq0 = platform_get_irq(pdev, 0); if (!priv->is_lite) { priv->irq1 = platform_get_irq(pdev, 1); - priv->wol_irq = platform_get_irq(pdev, 2); + priv->wol_irq = platform_get_irq_optional(pdev, 2); } else { - priv->wol_irq = platform_get_irq(pdev, 1); + priv->wol_irq = platform_get_irq_optional(pdev, 1); } if (priv->irq0 <= 0 || (priv->irq1 <= 0 && !priv->is_lite)) { ret = -EINVAL; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index f42e51bd3e42..e5b54e6025be 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -692,7 +692,7 @@ next_tx_int: __netif_txq_completed_wake(txq, nr_pkts, tx_bytes, bnxt_tx_avail(bp, txr), bp->tx_wake_thresh, - READ_ONCE(txr->dev_state) != BNXT_DEV_STATE_CLOSING); + READ_ONCE(txr->dev_state) == BNXT_DEV_STATE_CLOSING); } static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping, @@ -2361,6 +2361,9 @@ static int bnxt_async_event_process(struct bnxt *bp, struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; u64 ns; + if (!ptp) + goto async_event_process_exit; + spin_lock_bh(&ptp->ptp_lock); bnxt_ptp_update_current_time(bp); ns = (((u64)BNXT_EVENT_PHC_RTC_UPDATE(data1) << @@ -4759,6 +4762,9 @@ int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap, int bmap_size, if (event_id == ASYNC_EVENT_CMPL_EVENT_ID_ERROR_RECOVERY && !(bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY)) continue; + if (event_id == ASYNC_EVENT_CMPL_EVENT_ID_PHC_UPDATE && + !bp->ptp_cfg) + continue; __set_bit(bnxt_async_events_arr[i], async_events_bmap); } if (bmap && bmap_size) { @@ -5346,6 +5352,7 @@ static void bnxt_hwrm_update_rss_hash_cfg(struct bnxt *bp) if (hwrm_req_init(bp, req, HWRM_VNIC_RSS_QCFG)) return; + req->vnic_id = cpu_to_le16(vnic->fw_vnic_id); /* all contexts configured to same hash_type, zero always exists */ req->rss_ctx_idx = cpu_to_le16(vnic->fw_rss_cos_lb_ctx[0]); resp = hwrm_req_hold(bp, req); @@ -8808,6 +8815,9 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init) goto err_out; } + if (BNXT_VF(bp)) + bnxt_hwrm_func_qcfg(bp); + rc = bnxt_setup_vnic(bp, 0); if (rc) goto err_out; @@ -11594,6 +11604,7 @@ static void bnxt_tx_timeout(struct net_device *dev, unsigned int txqueue) static void bnxt_fw_health_check(struct bnxt *bp) { struct bnxt_fw_health *fw_health = bp->fw_health; + struct pci_dev *pdev = bp->pdev; u32 val; if (!fw_health->enabled || test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) @@ -11607,7 +11618,7 @@ static void bnxt_fw_health_check(struct bnxt *bp) } val = bnxt_fw_health_readl(bp, BNXT_FW_HEARTBEAT_REG); - if (val == fw_health->last_fw_heartbeat) { + if (val == fw_health->last_fw_heartbeat && pci_device_is_present(pdev)) { fw_health->arrests++; goto fw_reset; } @@ -11615,7 +11626,7 @@ static void bnxt_fw_health_check(struct bnxt *bp) fw_health->last_fw_heartbeat = val; val = bnxt_fw_health_readl(bp, BNXT_FW_RESET_CNT_REG); - if (val != fw_health->last_fw_reset_cnt) { + if (val != fw_health->last_fw_reset_cnt && pci_device_is_present(pdev)) { fw_health->discoveries++; goto fw_reset; } @@ -13021,26 +13032,37 @@ static void bnxt_cfg_ntp_filters(struct bnxt *bp) #endif /* CONFIG_RFS_ACCEL */ -static int bnxt_udp_tunnel_sync(struct net_device *netdev, unsigned int table) +static int bnxt_udp_tunnel_set_port(struct net_device *netdev, unsigned int table, + unsigned int entry, struct udp_tunnel_info *ti) { struct bnxt *bp = netdev_priv(netdev); - struct udp_tunnel_info ti; unsigned int cmd; - udp_tunnel_nic_get_port(netdev, table, 0, &ti); - if (ti.type == UDP_TUNNEL_TYPE_VXLAN) + if (ti->type == UDP_TUNNEL_TYPE_VXLAN) cmd = TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN; else cmd = TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE; - if (ti.port) - return bnxt_hwrm_tunnel_dst_port_alloc(bp, ti.port, cmd); + return bnxt_hwrm_tunnel_dst_port_alloc(bp, ti->port, cmd); +} + +static int bnxt_udp_tunnel_unset_port(struct net_device *netdev, unsigned int table, + unsigned int entry, struct udp_tunnel_info *ti) +{ + struct bnxt *bp = netdev_priv(netdev); + unsigned int cmd; + + if (ti->type == UDP_TUNNEL_TYPE_VXLAN) + cmd = TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN; + else + cmd = TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE; return bnxt_hwrm_tunnel_dst_port_free(bp, cmd); } static const struct udp_tunnel_nic_info bnxt_udp_tunnels = { - .sync_table = bnxt_udp_tunnel_sync, + .set_port = bnxt_udp_tunnel_set_port, + .unset_port = bnxt_udp_tunnel_unset_port, .flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP | UDP_TUNNEL_NIC_INFO_OPEN_ONLY, .tables = { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 2dd8ee4a6f75..8fd5071d8b09 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -3831,7 +3831,7 @@ static int bnxt_reset(struct net_device *dev, u32 *flags) } } - if (req & BNXT_FW_RESET_AP) { + if (!BNXT_CHIP_P4_PLUS(bp) && (req & BNXT_FW_RESET_AP)) { /* This feature is not supported in older firmware versions */ if (bp->hwrm_spec_code >= 0x10803) { if (!bnxt_firmware_reset_ap(dev)) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index e46689128e32..f3886710e778 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -952,6 +952,7 @@ int bnxt_ptp_init(struct bnxt *bp, bool phc_cfg) bnxt_ptp_timecounter_init(bp, true); bnxt_ptp_adjfine_rtc(bp, 0); } + bnxt_hwrm_func_drv_rgtr(bp, NULL, 0, true); ptp->ptp_info = bnxt_ptp_caps; if ((bp->fw_cap & BNXT_FW_CAP_PTP_PPS)) { diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index f28ffc31df22..2b5761ad2f92 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1272,7 +1272,8 @@ static void bcmgenet_get_ethtool_stats(struct net_device *dev, } } -static void bcmgenet_eee_enable_set(struct net_device *dev, bool enable) +void bcmgenet_eee_enable_set(struct net_device *dev, bool enable, + bool tx_lpi_enabled) { struct bcmgenet_priv *priv = netdev_priv(dev); u32 off = priv->hw_params->tbuf_offset + TBUF_ENERGY_CTRL; @@ -1292,7 +1293,7 @@ static void bcmgenet_eee_enable_set(struct net_device *dev, bool enable) /* Enable EEE and switch to a 27Mhz clock automatically */ reg = bcmgenet_readl(priv->base + off); - if (enable) + if (tx_lpi_enabled) reg |= TBUF_EEE_EN | TBUF_PM_EN; else reg &= ~(TBUF_EEE_EN | TBUF_PM_EN); @@ -1313,6 +1314,7 @@ static void bcmgenet_eee_enable_set(struct net_device *dev, bool enable) priv->eee.eee_enabled = enable; priv->eee.eee_active = enable; + priv->eee.tx_lpi_enabled = tx_lpi_enabled; } static int bcmgenet_get_eee(struct net_device *dev, struct ethtool_eee *e) @@ -1328,6 +1330,7 @@ static int bcmgenet_get_eee(struct net_device *dev, struct ethtool_eee *e) e->eee_enabled = p->eee_enabled; e->eee_active = p->eee_active; + e->tx_lpi_enabled = p->tx_lpi_enabled; e->tx_lpi_timer = bcmgenet_umac_readl(priv, UMAC_EEE_LPI_TIMER); return phy_ethtool_get_eee(dev->phydev, e); @@ -1337,7 +1340,6 @@ static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_eee *e) { struct bcmgenet_priv *priv = netdev_priv(dev); struct ethtool_eee *p = &priv->eee; - int ret = 0; if (GENET_IS_V1(priv)) return -EOPNOTSUPP; @@ -1348,16 +1350,11 @@ static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_eee *e) p->eee_enabled = e->eee_enabled; if (!p->eee_enabled) { - bcmgenet_eee_enable_set(dev, false); + bcmgenet_eee_enable_set(dev, false, false); } else { - ret = phy_init_eee(dev->phydev, false); - if (ret) { - netif_err(priv, hw, dev, "EEE initialization failed\n"); - return ret; - } - + p->eee_active = phy_init_eee(dev->phydev, false) >= 0; bcmgenet_umac_writel(priv, e->tx_lpi_timer, UMAC_EEE_LPI_TIMER); - bcmgenet_eee_enable_set(dev, true); + bcmgenet_eee_enable_set(dev, p->eee_active, e->tx_lpi_enabled); } return phy_ethtool_set_eee(dev->phydev, e); @@ -3450,7 +3447,7 @@ err_clk_disable: return ret; } -static void bcmgenet_netif_stop(struct net_device *dev) +static void bcmgenet_netif_stop(struct net_device *dev, bool stop_phy) { struct bcmgenet_priv *priv = netdev_priv(dev); @@ -3465,6 +3462,8 @@ static void bcmgenet_netif_stop(struct net_device *dev) /* Disable MAC transmit. TX DMA disabled must be done before this */ umac_enable_set(priv, CMD_TX_EN, false); + if (stop_phy) + phy_stop(dev->phydev); bcmgenet_disable_rx_napi(priv); bcmgenet_intr_disable(priv); @@ -3485,7 +3484,7 @@ static int bcmgenet_close(struct net_device *dev) netif_dbg(priv, ifdown, dev, "bcmgenet_close\n"); - bcmgenet_netif_stop(dev); + bcmgenet_netif_stop(dev, false); /* Really kill the PHY state machine and disconnect from it */ phy_disconnect(dev->phydev); @@ -4277,9 +4276,6 @@ static int bcmgenet_resume(struct device *d) if (!device_may_wakeup(d)) phy_resume(dev->phydev); - if (priv->eee.eee_enabled) - bcmgenet_eee_enable_set(dev, true); - bcmgenet_netif_start(dev); netif_device_attach(dev); @@ -4303,7 +4299,7 @@ static int bcmgenet_suspend(struct device *d) netif_device_detach(dev); - bcmgenet_netif_stop(dev); + bcmgenet_netif_stop(dev, true); if (!device_may_wakeup(d)) phy_suspend(dev->phydev); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h index 946f6e283c4e..1985c0ec4da2 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -703,4 +703,7 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv, void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv, enum bcmgenet_power_mode mode); +void bcmgenet_eee_enable_set(struct net_device *dev, bool enable, + bool tx_lpi_enabled); + #endif /* __BCMGENET_H__ */ diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index be042905ada2..c15ed0acdb77 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -87,6 +87,11 @@ static void bcmgenet_mac_config(struct net_device *dev) reg |= CMD_TX_EN | CMD_RX_EN; } bcmgenet_umac_writel(priv, reg, UMAC_CMD); + + priv->eee.eee_active = phy_init_eee(phydev, 0) >= 0; + bcmgenet_eee_enable_set(dev, + priv->eee.eee_enabled && priv->eee.eee_active, + priv->eee.tx_lpi_enabled); } /* setup netdev link state when PHY link status change and diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig index 1c76c95b0b27..ca742cc146d7 100644 --- a/drivers/net/ethernet/cavium/Kconfig +++ b/drivers/net/ethernet/cavium/Kconfig @@ -62,6 +62,9 @@ config CAVIUM_PTP Precision Time Protocol or other purposes. Timestamps can be used in BGX, TNS, GTI, and NIC blocks. +config LIQUIDIO_CORE + tristate + config LIQUIDIO tristate "Cavium LiquidIO support" depends on 64BIT && PCI @@ -69,6 +72,7 @@ config LIQUIDIO depends on PTP_1588_CLOCK_OPTIONAL select FW_LOADER select LIBCRC32C + select LIQUIDIO_CORE select NET_DEVLINK help This driver supports Cavium LiquidIO Intelligent Server Adapters @@ -92,6 +96,7 @@ config LIQUIDIO_VF tristate "Cavium LiquidIO VF support" depends on 64BIT && PCI_MSI depends on PTP_1588_CLOCK_OPTIONAL + select LIQUIDIO_CORE help This driver supports Cavium LiquidIO Intelligent Server Adapter based on CN23XX chips. diff --git a/drivers/net/ethernet/cavium/liquidio/Makefile b/drivers/net/ethernet/cavium/liquidio/Makefile index bc9937502043..4ee80af88e79 100644 --- a/drivers/net/ethernet/cavium/liquidio/Makefile +++ b/drivers/net/ethernet/cavium/liquidio/Makefile @@ -3,7 +3,9 @@ # Cavium Liquidio ethernet device driver # -common-objs := lio_ethtool.o \ +obj-$(CONFIG_LIQUIDIO_CORE) += liquidio-core.o +liquidio-core-y := \ + lio_ethtool.o \ lio_core.o \ request_manager.o \ response_manager.o \ @@ -18,7 +20,7 @@ common-objs := lio_ethtool.o \ octeon_nic.o obj-$(CONFIG_LIQUIDIO) += liquidio.o -liquidio-y := lio_main.o octeon_console.o lio_vf_rep.o $(common-objs) +liquidio-y := lio_main.o octeon_console.o lio_vf_rep.o obj-$(CONFIG_LIQUIDIO_VF) += liquidio_vf.o -liquidio_vf-y := lio_vf_main.o $(common-objs) +liquidio_vf-y := lio_vf_main.o diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c index 9ed3d1ab2ca5..068ed52b66c9 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c +++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c @@ -719,12 +719,10 @@ static int cn23xx_setup_pf_mbox(struct octeon_device *oct) for (i = 0; i < oct->sriov_info.max_vfs; i++) { q_no = i * oct->sriov_info.rings_per_vf; - mbox = vmalloc(sizeof(*mbox)); + mbox = vzalloc(sizeof(*mbox)); if (!mbox) goto free_mbox; - memset(mbox, 0, sizeof(struct octeon_mbox)); - spin_lock_init(&mbox->lock); mbox->oct_dev = oct; @@ -1377,6 +1375,7 @@ int setup_cn23xx_octeon_pf_device(struct octeon_device *oct) return 0; } +EXPORT_SYMBOL_GPL(setup_cn23xx_octeon_pf_device); int validate_cn23xx_pf_config_info(struct octeon_device *oct, struct octeon_config *conf23xx) @@ -1435,6 +1434,7 @@ int cn23xx_fw_loaded(struct octeon_device *oct) val = octeon_read_csr64(oct, CN23XX_SLI_SCRATCH2); return (val >> SCR2_BIT_FW_LOADED) & 1ULL; } +EXPORT_SYMBOL_GPL(cn23xx_fw_loaded); void cn23xx_tell_vf_its_macaddr_changed(struct octeon_device *oct, int vfidx, u8 *mac) @@ -1456,6 +1456,7 @@ void cn23xx_tell_vf_its_macaddr_changed(struct octeon_device *oct, int vfidx, octeon_mbox_write(oct, &mbox_cmd); } } +EXPORT_SYMBOL_GPL(cn23xx_tell_vf_its_macaddr_changed); static void cn23xx_get_vf_stats_callback(struct octeon_device *oct, @@ -1510,3 +1511,4 @@ int cn23xx_get_vf_stats(struct octeon_device *oct, int vfidx, return 0; } +EXPORT_SYMBOL_GPL(cn23xx_get_vf_stats); diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c index fda49404968c..dd5d80fee24f 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c +++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c @@ -279,12 +279,10 @@ static int cn23xx_setup_vf_mbox(struct octeon_device *oct) { struct octeon_mbox *mbox = NULL; - mbox = vmalloc(sizeof(*mbox)); + mbox = vzalloc(sizeof(*mbox)); if (!mbox) return 1; - memset(mbox, 0, sizeof(struct octeon_mbox)); - spin_lock_init(&mbox->lock); mbox->oct_dev = oct; @@ -386,6 +384,7 @@ void cn23xx_vf_ask_pf_to_do_flr(struct octeon_device *oct) octeon_mbox_write(oct, &mbox_cmd); } +EXPORT_SYMBOL_GPL(cn23xx_vf_ask_pf_to_do_flr); static void octeon_pfvf_hs_callback(struct octeon_device *oct, struct octeon_mbox_cmd *cmd, @@ -468,6 +467,7 @@ int cn23xx_octeon_pfvf_handshake(struct octeon_device *oct) return 0; } +EXPORT_SYMBOL_GPL(cn23xx_octeon_pfvf_handshake); static void cn23xx_handle_vf_mbox_intr(struct octeon_ioq_vector *ioq_vector) { @@ -680,3 +680,4 @@ int cn23xx_setup_octeon_vf_device(struct octeon_device *oct) return 0; } +EXPORT_SYMBOL_GPL(cn23xx_setup_octeon_vf_device); diff --git a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c index 39643be8c30a..93fccfec288d 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c +++ b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c @@ -697,6 +697,7 @@ int lio_setup_cn66xx_octeon_device(struct octeon_device *oct) return 0; } +EXPORT_SYMBOL_GPL(lio_setup_cn66xx_octeon_device); int lio_validate_cn6xxx_config_info(struct octeon_device *oct, struct octeon_config *conf6xxx) diff --git a/drivers/net/ethernet/cavium/liquidio/cn68xx_device.c b/drivers/net/ethernet/cavium/liquidio/cn68xx_device.c index 30254e4cf70f..b5103def3761 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn68xx_device.c +++ b/drivers/net/ethernet/cavium/liquidio/cn68xx_device.c @@ -181,3 +181,4 @@ int lio_setup_cn68xx_octeon_device(struct octeon_device *oct) return 0; } +EXPORT_SYMBOL_GPL(lio_setup_cn68xx_octeon_device); diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c index 882b2be06ea0..9cc6303c82ff 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_core.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c @@ -26,6 +26,9 @@ #include "octeon_main.h" #include "octeon_network.h" +MODULE_AUTHOR("Cavium Networks, <support@cavium.com>"); +MODULE_LICENSE("GPL"); + /* OOM task polling interval */ #define LIO_OOM_POLL_INTERVAL_MS 250 @@ -71,6 +74,7 @@ void lio_delete_glists(struct lio *lio) kfree(lio->glist); lio->glist = NULL; } +EXPORT_SYMBOL_GPL(lio_delete_glists); /** * lio_setup_glists - Setup gather lists @@ -154,6 +158,7 @@ int lio_setup_glists(struct octeon_device *oct, struct lio *lio, int num_iqs) return 0; } +EXPORT_SYMBOL_GPL(lio_setup_glists); int liquidio_set_feature(struct net_device *netdev, int cmd, u16 param1) { @@ -180,6 +185,7 @@ int liquidio_set_feature(struct net_device *netdev, int cmd, u16 param1) } return ret; } +EXPORT_SYMBOL_GPL(liquidio_set_feature); void octeon_report_tx_completion_to_bql(void *txq, unsigned int pkts_compl, unsigned int bytes_compl) @@ -395,6 +401,7 @@ void liquidio_link_ctrl_cmd_completion(void *nctrl_ptr) nctrl->ncmd.s.cmd); } } +EXPORT_SYMBOL_GPL(liquidio_link_ctrl_cmd_completion); void octeon_pf_changed_vf_macaddr(struct octeon_device *oct, u8 *mac) { @@ -478,6 +485,7 @@ int setup_rx_oom_poll_fn(struct net_device *netdev) return 0; } +EXPORT_SYMBOL_GPL(setup_rx_oom_poll_fn); void cleanup_rx_oom_poll_fn(struct net_device *netdev) { @@ -495,6 +503,7 @@ void cleanup_rx_oom_poll_fn(struct net_device *netdev) } } } +EXPORT_SYMBOL_GPL(cleanup_rx_oom_poll_fn); /* Runs in interrupt context. */ static void lio_update_txq_status(struct octeon_device *oct, int iq_num) @@ -899,6 +908,7 @@ int liquidio_setup_io_queues(struct octeon_device *octeon_dev, int ifidx, return 0; } +EXPORT_SYMBOL_GPL(liquidio_setup_io_queues); static int liquidio_schedule_msix_droq_pkt_handler(struct octeon_droq *droq, u64 ret) @@ -1194,6 +1204,7 @@ int octeon_setup_interrupt(struct octeon_device *oct, u32 num_ioqs) } return 0; } +EXPORT_SYMBOL_GPL(octeon_setup_interrupt); /** * liquidio_change_mtu - Net device change_mtu @@ -1256,6 +1267,7 @@ int liquidio_change_mtu(struct net_device *netdev, int new_mtu) WRITE_ONCE(sc->caller_is_done, true); return 0; } +EXPORT_SYMBOL_GPL(liquidio_change_mtu); int lio_wait_for_clean_oq(struct octeon_device *oct) { @@ -1279,6 +1291,7 @@ int lio_wait_for_clean_oq(struct octeon_device *oct) return pending_pkts; } +EXPORT_SYMBOL_GPL(lio_wait_for_clean_oq); static void octnet_nic_stats_callback(struct octeon_device *oct_dev, @@ -1509,6 +1522,7 @@ lio_fetch_stats_exit: return; } +EXPORT_SYMBOL_GPL(lio_fetch_stats); int liquidio_set_speed(struct lio *lio, int speed) { @@ -1659,6 +1673,7 @@ int liquidio_get_speed(struct lio *lio) return retval; } +EXPORT_SYMBOL_GPL(liquidio_get_speed); int liquidio_set_fec(struct lio *lio, int on_off) { @@ -1812,3 +1827,4 @@ int liquidio_get_fec(struct lio *lio) return retval; } +EXPORT_SYMBOL_GPL(liquidio_get_fec); diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c index 2c10ae3f7fc1..9d56181a301f 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c @@ -3180,3 +3180,4 @@ void liquidio_set_ethtool_ops(struct net_device *netdev) else netdev->ethtool_ops = &lio_ethtool_ops; } +EXPORT_SYMBOL_GPL(liquidio_set_ethtool_ops); diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c index e159194d0aef..364f4f912dc2 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_device.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c @@ -564,6 +564,7 @@ void octeon_init_device_list(int conf_type) for (i = 0; i < MAX_OCTEON_DEVICES; i++) oct_set_config_info(i, conf_type); } +EXPORT_SYMBOL_GPL(octeon_init_device_list); static void *__retrieve_octeon_config_info(struct octeon_device *oct, u16 card_type) @@ -633,6 +634,7 @@ char *lio_get_state_string(atomic_t *state_ptr) return oct_dev_state_str[OCT_DEV_STATE_INVALID]; return oct_dev_state_str[istate]; } +EXPORT_SYMBOL_GPL(lio_get_state_string); static char *get_oct_app_string(u32 app_mode) { @@ -661,6 +663,7 @@ void octeon_free_device_mem(struct octeon_device *oct) octeon_device[i] = NULL; octeon_device_count--; } +EXPORT_SYMBOL_GPL(octeon_free_device_mem); static struct octeon_device *octeon_allocate_device_mem(u32 pci_id, u32 priv_size) @@ -747,6 +750,7 @@ struct octeon_device *octeon_allocate_device(u32 pci_id, return oct; } +EXPORT_SYMBOL_GPL(octeon_allocate_device); /** Register a device's bus location at initialization time. * @param octeon_dev - pointer to the octeon device structure. @@ -804,6 +808,7 @@ int octeon_register_device(struct octeon_device *oct, return refcount; } +EXPORT_SYMBOL_GPL(octeon_register_device); /** Deregister a device at de-initialization time. * @param octeon_dev - pointer to the octeon device structure. @@ -821,6 +826,7 @@ int octeon_deregister_device(struct octeon_device *oct) return refcount; } +EXPORT_SYMBOL_GPL(octeon_deregister_device); int octeon_allocate_ioq_vector(struct octeon_device *oct, u32 num_ioqs) @@ -853,12 +859,14 @@ octeon_allocate_ioq_vector(struct octeon_device *oct, u32 num_ioqs) return 0; } +EXPORT_SYMBOL_GPL(octeon_allocate_ioq_vector); void octeon_free_ioq_vector(struct octeon_device *oct) { vfree(oct->ioq_vector); } +EXPORT_SYMBOL_GPL(octeon_free_ioq_vector); /* this function is only for setting up the first queue */ int octeon_setup_instr_queues(struct octeon_device *oct) @@ -904,6 +912,7 @@ int octeon_setup_instr_queues(struct octeon_device *oct) oct->num_iqs++; return 0; } +EXPORT_SYMBOL_GPL(octeon_setup_instr_queues); int octeon_setup_output_queues(struct octeon_device *oct) { @@ -940,6 +949,7 @@ int octeon_setup_output_queues(struct octeon_device *oct) return 0; } +EXPORT_SYMBOL_GPL(octeon_setup_output_queues); int octeon_set_io_queues_off(struct octeon_device *oct) { @@ -989,6 +999,7 @@ int octeon_set_io_queues_off(struct octeon_device *oct) } return 0; } +EXPORT_SYMBOL_GPL(octeon_set_io_queues_off); void octeon_set_droq_pkt_op(struct octeon_device *oct, u32 q_no, @@ -1027,6 +1038,7 @@ int octeon_init_dispatch_list(struct octeon_device *oct) return 0; } +EXPORT_SYMBOL_GPL(octeon_init_dispatch_list); void octeon_delete_dispatch_list(struct octeon_device *oct) { @@ -1058,6 +1070,7 @@ void octeon_delete_dispatch_list(struct octeon_device *oct) kfree(temp); } } +EXPORT_SYMBOL_GPL(octeon_delete_dispatch_list); octeon_dispatch_fn_t octeon_get_dispatch(struct octeon_device *octeon_dev, u16 opcode, @@ -1180,6 +1193,7 @@ octeon_register_dispatch_fn(struct octeon_device *oct, return 0; } +EXPORT_SYMBOL_GPL(octeon_register_dispatch_fn); int octeon_core_drv_init(struct octeon_recv_info *recv_info, void *buf) { @@ -1262,6 +1276,7 @@ core_drv_init_err: octeon_free_recv_info(recv_info); return 0; } +EXPORT_SYMBOL_GPL(octeon_core_drv_init); int octeon_get_tx_qsize(struct octeon_device *oct, u32 q_no) @@ -1272,6 +1287,7 @@ int octeon_get_tx_qsize(struct octeon_device *oct, u32 q_no) return -1; } +EXPORT_SYMBOL_GPL(octeon_get_tx_qsize); int octeon_get_rx_qsize(struct octeon_device *oct, u32 q_no) { @@ -1280,6 +1296,7 @@ int octeon_get_rx_qsize(struct octeon_device *oct, u32 q_no) return oct->droq[q_no]->max_count; return -1; } +EXPORT_SYMBOL_GPL(octeon_get_rx_qsize); /* Retruns the host firmware handshake OCTEON specific configuration */ struct octeon_config *octeon_get_conf(struct octeon_device *oct) @@ -1302,6 +1319,7 @@ struct octeon_config *octeon_get_conf(struct octeon_device *oct) } return default_oct_conf; } +EXPORT_SYMBOL_GPL(octeon_get_conf); /* scratch register address is same in all the OCT-II and CN70XX models */ #define CNXX_SLI_SCRATCH1 0x3C0 @@ -1318,6 +1336,7 @@ struct octeon_device *lio_get_device(u32 octeon_id) else return octeon_device[octeon_id]; } +EXPORT_SYMBOL_GPL(lio_get_device); u64 lio_pci_readq(struct octeon_device *oct, u64 addr) { @@ -1349,6 +1368,7 @@ u64 lio_pci_readq(struct octeon_device *oct, u64 addr) return val64; } +EXPORT_SYMBOL_GPL(lio_pci_readq); void lio_pci_writeq(struct octeon_device *oct, u64 val, @@ -1369,6 +1389,7 @@ void lio_pci_writeq(struct octeon_device *oct, spin_unlock_irqrestore(&oct->pci_win_lock, flags); } +EXPORT_SYMBOL_GPL(lio_pci_writeq); int octeon_mem_access_ok(struct octeon_device *oct) { @@ -1388,6 +1409,7 @@ int octeon_mem_access_ok(struct octeon_device *oct) return access_okay ? 0 : 1; } +EXPORT_SYMBOL_GPL(octeon_mem_access_ok); int octeon_wait_for_ddr_init(struct octeon_device *oct, u32 *timeout) { @@ -1408,6 +1430,7 @@ int octeon_wait_for_ddr_init(struct octeon_device *oct, u32 *timeout) return ret; } +EXPORT_SYMBOL_GPL(octeon_wait_for_ddr_init); /* Get the octeon id assigned to the octeon device passed as argument. * This function is exported to other modules. @@ -1462,3 +1485,4 @@ void lio_enable_irq(struct octeon_droq *droq, struct octeon_instr_queue *iq) } } } +EXPORT_SYMBOL_GPL(lio_enable_irq); diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c index d4080bddcb6b..0d6ee30affb9 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c @@ -107,6 +107,7 @@ u32 octeon_droq_check_hw_for_pkts(struct octeon_droq *droq) return last_count; } +EXPORT_SYMBOL_GPL(octeon_droq_check_hw_for_pkts); static void octeon_droq_compute_max_packet_bufs(struct octeon_droq *droq) { @@ -216,6 +217,7 @@ int octeon_delete_droq(struct octeon_device *oct, u32 q_no) return 0; } +EXPORT_SYMBOL_GPL(octeon_delete_droq); int octeon_init_droq(struct octeon_device *oct, u32 q_no, @@ -773,6 +775,7 @@ octeon_droq_process_packets(struct octeon_device *oct, return 0; } +EXPORT_SYMBOL_GPL(octeon_droq_process_packets); /* * Utility function to poll for packets. check_hw_for_packets must be @@ -921,6 +924,7 @@ int octeon_unregister_droq_ops(struct octeon_device *oct, u32 q_no) return 0; } +EXPORT_SYMBOL_GPL(octeon_unregister_droq_ops); int octeon_create_droq(struct octeon_device *oct, u32 q_no, u32 num_descs, diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_mem_ops.c b/drivers/net/ethernet/cavium/liquidio/octeon_mem_ops.c index 7ccab36143c1..d70132437af3 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_mem_ops.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_mem_ops.c @@ -164,6 +164,7 @@ octeon_pci_read_core_mem(struct octeon_device *oct, { __octeon_pci_rw_core_mem(oct, coreaddr, buf, len, 1); } +EXPORT_SYMBOL_GPL(octeon_pci_read_core_mem); void octeon_pci_write_core_mem(struct octeon_device *oct, @@ -173,6 +174,7 @@ octeon_pci_write_core_mem(struct octeon_device *oct, { __octeon_pci_rw_core_mem(oct, coreaddr, (u8 *)buf, len, 0); } +EXPORT_SYMBOL_GPL(octeon_pci_write_core_mem); u64 octeon_read_device_mem64(struct octeon_device *oct, u64 coreaddr) { @@ -182,6 +184,7 @@ u64 octeon_read_device_mem64(struct octeon_device *oct, u64 coreaddr) return be64_to_cpu(ret); } +EXPORT_SYMBOL_GPL(octeon_read_device_mem64); u32 octeon_read_device_mem32(struct octeon_device *oct, u64 coreaddr) { @@ -191,6 +194,7 @@ u32 octeon_read_device_mem32(struct octeon_device *oct, u64 coreaddr) return be32_to_cpu(ret); } +EXPORT_SYMBOL_GPL(octeon_read_device_mem32); void octeon_write_device_mem32(struct octeon_device *oct, u64 coreaddr, u32 val) @@ -199,3 +203,4 @@ void octeon_write_device_mem32(struct octeon_device *oct, u64 coreaddr, __octeon_pci_rw_core_mem(oct, coreaddr, (u8 *)&t, 4, 0); } +EXPORT_SYMBOL_GPL(octeon_write_device_mem32); diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_nic.c b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c index 1a706f81bbb0..dee56ea740e7 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_nic.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c @@ -79,6 +79,7 @@ octeon_alloc_soft_command_resp(struct octeon_device *oct, return sc; } +EXPORT_SYMBOL_GPL(octeon_alloc_soft_command_resp); int octnet_send_nic_data_pkt(struct octeon_device *oct, struct octnic_data_pkt *ndata, @@ -90,6 +91,7 @@ int octnet_send_nic_data_pkt(struct octeon_device *oct, ndata->buf, ndata->datasize, ndata->reqtype); } +EXPORT_SYMBOL_GPL(octnet_send_nic_data_pkt); static inline struct octeon_soft_command *octnic_alloc_ctrl_pkt_sc(struct octeon_device *oct, @@ -196,3 +198,4 @@ octnet_send_nic_ctrl_pkt(struct octeon_device *oct, return retval; } +EXPORT_SYMBOL_GPL(octnet_send_nic_ctrl_pkt); diff --git a/drivers/net/ethernet/cavium/liquidio/request_manager.c b/drivers/net/ethernet/cavium/liquidio/request_manager.c index 32f854c0cd79..de8a6ce86ad7 100644 --- a/drivers/net/ethernet/cavium/liquidio/request_manager.c +++ b/drivers/net/ethernet/cavium/liquidio/request_manager.c @@ -185,6 +185,7 @@ int octeon_delete_instr_queue(struct octeon_device *oct, u32 iq_no) } return 1; } +EXPORT_SYMBOL_GPL(octeon_delete_instr_queue); /* Return 0 on success, 1 on failure */ int octeon_setup_iq(struct octeon_device *oct, @@ -258,6 +259,7 @@ int lio_wait_for_instr_fetch(struct octeon_device *oct) return instr_cnt; } +EXPORT_SYMBOL_GPL(lio_wait_for_instr_fetch); static inline void ring_doorbell(struct octeon_device *oct, struct octeon_instr_queue *iq) @@ -282,6 +284,7 @@ octeon_ring_doorbell_locked(struct octeon_device *oct, u32 iq_no) ring_doorbell(oct, iq); spin_unlock(&iq->post_lock); } +EXPORT_SYMBOL_GPL(octeon_ring_doorbell_locked); static inline void __copy_cmd_into_iq(struct octeon_instr_queue *iq, u8 *cmd) @@ -345,6 +348,7 @@ octeon_register_reqtype_free_fn(struct octeon_device *oct, int reqtype, return 0; } +EXPORT_SYMBOL_GPL(octeon_register_reqtype_free_fn); static inline void __add_to_request_list(struct octeon_instr_queue *iq, @@ -430,6 +434,7 @@ lio_process_iq_request_list(struct octeon_device *oct, return inst_count; } +EXPORT_SYMBOL_GPL(lio_process_iq_request_list); /* Can only be called from process context */ int @@ -566,6 +571,7 @@ octeon_send_command(struct octeon_device *oct, u32 iq_no, return st.status; } +EXPORT_SYMBOL_GPL(octeon_send_command); void octeon_prepare_soft_command(struct octeon_device *oct, @@ -673,6 +679,7 @@ octeon_prepare_soft_command(struct octeon_device *oct, } } } +EXPORT_SYMBOL_GPL(octeon_prepare_soft_command); int octeon_send_soft_command(struct octeon_device *oct, struct octeon_soft_command *sc) @@ -726,6 +733,7 @@ int octeon_send_soft_command(struct octeon_device *oct, return (octeon_send_command(oct, sc->iq_no, 1, &sc->cmd, sc, len, REQTYPE_SOFT_COMMAND)); } +EXPORT_SYMBOL_GPL(octeon_send_soft_command); int octeon_setup_sc_buffer_pool(struct octeon_device *oct) { @@ -755,6 +763,7 @@ int octeon_setup_sc_buffer_pool(struct octeon_device *oct) return 0; } +EXPORT_SYMBOL_GPL(octeon_setup_sc_buffer_pool); int octeon_free_sc_done_list(struct octeon_device *oct) { @@ -794,6 +803,7 @@ int octeon_free_sc_done_list(struct octeon_device *oct) return 0; } +EXPORT_SYMBOL_GPL(octeon_free_sc_done_list); int octeon_free_sc_zombie_list(struct octeon_device *oct) { @@ -818,6 +828,7 @@ int octeon_free_sc_zombie_list(struct octeon_device *oct) return 0; } +EXPORT_SYMBOL_GPL(octeon_free_sc_zombie_list); int octeon_free_sc_buffer_pool(struct octeon_device *oct) { @@ -842,6 +853,7 @@ int octeon_free_sc_buffer_pool(struct octeon_device *oct) return 0; } +EXPORT_SYMBOL_GPL(octeon_free_sc_buffer_pool); struct octeon_soft_command *octeon_alloc_soft_command(struct octeon_device *oct, u32 datasize, @@ -913,6 +925,7 @@ struct octeon_soft_command *octeon_alloc_soft_command(struct octeon_device *oct, return sc; } +EXPORT_SYMBOL_GPL(octeon_alloc_soft_command); void octeon_free_soft_command(struct octeon_device *oct, struct octeon_soft_command *sc) @@ -925,3 +938,4 @@ void octeon_free_soft_command(struct octeon_device *oct, spin_unlock_bh(&oct->sc_buf_pool.lock); } +EXPORT_SYMBOL_GPL(octeon_free_soft_command); diff --git a/drivers/net/ethernet/cavium/liquidio/response_manager.c b/drivers/net/ethernet/cavium/liquidio/response_manager.c index ac7747ccf56a..861050966e18 100644 --- a/drivers/net/ethernet/cavium/liquidio/response_manager.c +++ b/drivers/net/ethernet/cavium/liquidio/response_manager.c @@ -52,12 +52,14 @@ int octeon_setup_response_list(struct octeon_device *oct) return ret; } +EXPORT_SYMBOL_GPL(octeon_setup_response_list); void octeon_delete_response_list(struct octeon_device *oct) { cancel_delayed_work_sync(&oct->dma_comp_wq.wk.work); destroy_workqueue(oct->dma_comp_wq.wq); } +EXPORT_SYMBOL_GPL(octeon_delete_response_list); int lio_process_ordered_list(struct octeon_device *octeon_dev, u32 force_quit) @@ -219,6 +221,7 @@ int lio_process_ordered_list(struct octeon_device *octeon_dev, return 0; } +EXPORT_SYMBOL_GPL(lio_process_ordered_list); static void oct_poll_req_completion(struct work_struct *work) { diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h index 41714203ace8..da4818d2c856 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h @@ -568,6 +568,7 @@ void chtls_destroy_sock(struct sock *sk); int chtls_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int chtls_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len); +void chtls_splice_eof(struct socket *sock); int chtls_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); int send_tx_flowc_wr(struct sock *sk, int compl, diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c index ae6b17b96bf1..e08ac960c967 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c @@ -1092,7 +1092,17 @@ new_buf: if (copy > size) copy = size; - if (skb_tailroom(skb) > 0) { + if (msg->msg_flags & MSG_SPLICE_PAGES) { + err = skb_splice_from_iter(skb, &msg->msg_iter, copy, + sk->sk_allocation); + if (err < 0) { + if (err == -EMSGSIZE) + goto new_buf; + goto do_fault; + } + copy = err; + sk_wmem_queued_add(sk, copy); + } else if (skb_tailroom(skb) > 0) { copy = min(copy, skb_tailroom(skb)); if (is_tls_tx(csk)) copy = min_t(int, copy, csk->tlshws.txleft); @@ -1227,113 +1237,27 @@ out_err: goto done; } -int chtls_sendpage(struct sock *sk, struct page *page, - int offset, size_t size, int flags) +void chtls_splice_eof(struct socket *sock) { - struct chtls_sock *csk; - struct chtls_dev *cdev; - int mss, err, copied; - struct tcp_sock *tp; - long timeo; + struct sock *sk = sock->sk; - tp = tcp_sk(sk); - copied = 0; - csk = rcu_dereference_sk_user_data(sk); - cdev = csk->cdev; lock_sock(sk); - timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); - - err = sk_stream_wait_connect(sk, &timeo); - if (!sk_in_state(sk, TCPF_ESTABLISHED | TCPF_CLOSE_WAIT) && - err != 0) - goto out_err; - - mss = csk->mss; - csk_set_flag(csk, CSK_TX_MORE_DATA); - - while (size > 0) { - struct sk_buff *skb = skb_peek_tail(&csk->txq); - int copy, i; - - if (!skb || (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NO_APPEND) || - (copy = mss - skb->len) <= 0) { -new_buf: - if (!csk_mem_free(cdev, sk)) - goto wait_for_sndbuf; - - if (is_tls_tx(csk)) { - skb = get_record_skb(sk, - select_size(sk, size, - flags, - TX_TLSHDR_LEN), - true); - } else { - skb = get_tx_skb(sk, 0); - } - if (!skb) - goto wait_for_memory; - copy = mss; - } - if (copy > size) - copy = size; - - i = skb_shinfo(skb)->nr_frags; - if (skb_can_coalesce(skb, i, page, offset)) { - skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); - } else if (i < MAX_SKB_FRAGS) { - get_page(page); - skb_fill_page_desc(skb, i, page, offset, copy); - } else { - tx_skb_finalize(skb); - push_frames_if_head(sk); - goto new_buf; - } - - skb->len += copy; - if (skb->len == mss) - tx_skb_finalize(skb); - skb->data_len += copy; - skb->truesize += copy; - sk->sk_wmem_queued += copy; - tp->write_seq += copy; - copied += copy; - offset += copy; - size -= copy; - - if (corked(tp, flags) && - (sk_stream_wspace(sk) < sk_stream_min_wspace(sk))) - ULP_SKB_CB(skb)->flags |= ULPCB_FLAG_NO_APPEND; - - if (!size) - break; - - if (unlikely(ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NO_APPEND)) - push_frames_if_head(sk); - continue; -wait_for_sndbuf: - set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); -wait_for_memory: - err = csk_wait_memory(cdev, sk, &timeo); - if (err) - goto do_error; - } -out: - csk_reset_flag(csk, CSK_TX_MORE_DATA); - if (copied) - chtls_tcp_push(sk, flags); -done: + chtls_tcp_push(sk, 0); release_sock(sk); - return copied; +} -do_error: - if (copied) - goto out; +int chtls_sendpage(struct sock *sk, struct page *page, + int offset, size_t size, int flags) +{ + struct msghdr msg = { .msg_flags = flags | MSG_SPLICE_PAGES, }; + struct bio_vec bvec; -out_err: - if (csk_conn_inline(csk)) - csk_reset_flag(csk, CSK_TX_MORE_DATA); - copied = sk_stream_error(sk, flags, err); - goto done; + if (flags & MSG_SENDPAGE_NOTLAST) + msg.msg_flags |= MSG_MORE; + + bvec_set_page(&bvec, page, size, offset); + iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); + return chtls_sendmsg(sk, &msg, size); } static void chtls_select_window(struct sock *sk) diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c index 1e55b12fee51..6b6787eafd2f 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c @@ -606,6 +606,7 @@ static void __init chtls_init_ulp_ops(void) chtls_cpl_prot.destroy = chtls_destroy_sock; chtls_cpl_prot.shutdown = chtls_shutdown; chtls_cpl_prot.sendmsg = chtls_sendmsg; + chtls_cpl_prot.splice_eof = chtls_splice_eof; chtls_cpl_prot.sendpage = chtls_sendpage; chtls_cpl_prot.recvmsg = chtls_recvmsg; chtls_cpl_prot.setsockopt = chtls_setsockopt; diff --git a/drivers/net/ethernet/cirrus/cs89x0.c b/drivers/net/ethernet/cirrus/cs89x0.c index 06a0c00af99c..276c32c3926a 100644 --- a/drivers/net/ethernet/cirrus/cs89x0.c +++ b/drivers/net/ethernet/cirrus/cs89x0.c @@ -72,6 +72,8 @@ #include <linux/gfp.h> #include <linux/io.h> +#include <net/Space.h> + #include <asm/irq.h> #include <linux/atomic.h> #if ALLOW_DMA diff --git a/drivers/net/ethernet/engleder/tsnep_selftests.c b/drivers/net/ethernet/engleder/tsnep_selftests.c index 1581d6b22232..8a9145f93147 100644 --- a/drivers/net/ethernet/engleder/tsnep_selftests.c +++ b/drivers/net/ethernet/engleder/tsnep_selftests.c @@ -329,7 +329,7 @@ static bool disable_taprio(struct tsnep_adapter *adapter) int retval; memset(&qopt, 0, sizeof(qopt)); - qopt.enable = 0; + qopt.cmd = TAPRIO_CMD_DESTROY; retval = tsnep_tc_setup(adapter->netdev, TC_SETUP_QDISC_TAPRIO, &qopt); if (retval) return false; @@ -360,7 +360,7 @@ static bool tsnep_test_taprio(struct tsnep_adapter *adapter) for (i = 0; i < 255; i++) qopt->entries[i].command = TC_TAPRIO_CMD_SET_GATES; - qopt->enable = 1; + qopt->cmd = TAPRIO_CMD_REPLACE; qopt->base_time = ktime_set(0, 0); qopt->cycle_time = 1500000; qopt->cycle_time_extension = 0; @@ -382,7 +382,7 @@ static bool tsnep_test_taprio(struct tsnep_adapter *adapter) if (!run_taprio(adapter, qopt, 100)) goto failed; - qopt->enable = 1; + qopt->cmd = TAPRIO_CMD_REPLACE; qopt->base_time = ktime_set(0, 0); qopt->cycle_time = 411854; qopt->cycle_time_extension = 0; @@ -406,7 +406,7 @@ static bool tsnep_test_taprio(struct tsnep_adapter *adapter) if (!run_taprio(adapter, qopt, 100)) goto failed; - qopt->enable = 1; + qopt->cmd = TAPRIO_CMD_REPLACE; qopt->base_time = ktime_set(0, 0); delay_base_time(adapter, qopt, 12); qopt->cycle_time = 125000; @@ -457,7 +457,7 @@ static bool tsnep_test_taprio_change(struct tsnep_adapter *adapter) for (i = 0; i < 255; i++) qopt->entries[i].command = TC_TAPRIO_CMD_SET_GATES; - qopt->enable = 1; + qopt->cmd = TAPRIO_CMD_REPLACE; qopt->base_time = ktime_set(0, 0); qopt->cycle_time = 100000; qopt->cycle_time_extension = 0; @@ -610,7 +610,7 @@ static bool tsnep_test_taprio_extension(struct tsnep_adapter *adapter) for (i = 0; i < 255; i++) qopt->entries[i].command = TC_TAPRIO_CMD_SET_GATES; - qopt->enable = 1; + qopt->cmd = TAPRIO_CMD_REPLACE; qopt->base_time = ktime_set(0, 0); qopt->cycle_time = 100000; qopt->cycle_time_extension = 50000; diff --git a/drivers/net/ethernet/engleder/tsnep_tc.c b/drivers/net/ethernet/engleder/tsnep_tc.c index d083e6684f12..745b191a5540 100644 --- a/drivers/net/ethernet/engleder/tsnep_tc.c +++ b/drivers/net/ethernet/engleder/tsnep_tc.c @@ -325,7 +325,7 @@ static int tsnep_taprio(struct tsnep_adapter *adapter, if (!adapter->gate_control) return -EOPNOTSUPP; - if (!qopt->enable) { + if (qopt->cmd == TAPRIO_CMD_DESTROY) { /* disable gate control if active */ mutex_lock(&adapter->gate_control_lock); @@ -337,6 +337,8 @@ static int tsnep_taprio(struct tsnep_adapter *adapter, mutex_unlock(&adapter->gate_control_lock); return 0; + } else if (qopt->cmd != TAPRIO_CMD_REPLACE) { + return -EOPNOTSUPP; } retval = tsnep_validate_gcl(qopt); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c index b1871e6c4006..d860d9fe73af 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c @@ -247,8 +247,8 @@ static int dpaa2_pcs_create(struct dpaa2_mac *mac, struct fwnode_handle *dpmac_node, int id) { - struct mdio_device *mdiodev; struct fwnode_handle *node; + struct phylink_pcs *pcs; node = fwnode_find_reference(dpmac_node, "pcs-handle", 0); if (IS_ERR(node)) { @@ -257,26 +257,27 @@ static int dpaa2_pcs_create(struct dpaa2_mac *mac, return 0; } - if (!fwnode_device_is_available(node)) { - netdev_err(mac->net_dev, "pcs-handle node not available\n"); - fwnode_handle_put(node); - return -ENODEV; - } - - mdiodev = fwnode_mdio_find_device(node); + pcs = lynx_pcs_create_fwnode(node); fwnode_handle_put(node); - if (!mdiodev) { + + if (pcs == ERR_PTR(-EPROBE_DEFER)) { netdev_dbg(mac->net_dev, "missing PCS device\n"); return -EPROBE_DEFER; } - mac->pcs = lynx_pcs_create(mdiodev); - if (!mac->pcs) { - netdev_err(mac->net_dev, "lynx_pcs_create() failed\n"); - put_device(&mdiodev->dev); - return -ENOMEM; + if (pcs == ERR_PTR(-ENODEV)) { + netdev_err(mac->net_dev, "pcs-handle node not available\n"); + return PTR_ERR(pcs); + } + + if (IS_ERR(pcs)) { + netdev_err(mac->net_dev, + "lynx_pcs_create_fwnode() failed: %pe\n", pcs); + return PTR_ERR(pcs); } + mac->pcs = pcs; + return 0; } @@ -285,11 +286,7 @@ static void dpaa2_pcs_destroy(struct dpaa2_mac *mac) struct phylink_pcs *phylink_pcs = mac->pcs; if (phylink_pcs) { - struct mdio_device *mdio = lynx_get_mdio_device(phylink_pcs); - struct device *dev = &mdio->dev; - lynx_pcs_destroy(phylink_pcs); - put_device(dev); mac->pcs = NULL; } } diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 63854294ac33..164b73df9f6b 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -1229,7 +1229,13 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring, if (!skb) break; - rx_byte_cnt += skb->len; + /* When set, the outer VLAN header is extracted and reported + * in the receive buffer descriptor. So rx_byte_cnt should + * add the length of the extracted VLAN header. + */ + if (bd_status & ENETC_RXBD_FLAG_VLAN) + rx_byte_cnt += VLAN_HLEN; + rx_byte_cnt += skb->len + ETH_HLEN; rx_frm_cnt++; napi_gro_receive(napi, skb); @@ -1564,6 +1570,14 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring, enetc_build_xdp_buff(rx_ring, bd_status, &rxbd, &i, &cleaned_cnt, &xdp_buff); + /* When set, the outer VLAN header is extracted and reported + * in the receive buffer descriptor. So rx_byte_cnt should + * add the length of the extracted VLAN header. + */ + if (bd_status & ENETC_RXBD_FLAG_VLAN) + rx_byte_cnt += VLAN_HLEN; + rx_byte_cnt += xdp_get_buff_len(&xdp_buff); + xdp_act = bpf_prog_run_xdp(prog, &xdp_buff); switch (xdp_act) { @@ -2624,7 +2638,7 @@ static void enetc_debug_tx_ring_prios(struct enetc_ndev_priv *priv) priv->tx_ring[i]->prio); } -static void enetc_reset_tc_mqprio(struct net_device *ndev) +void enetc_reset_tc_mqprio(struct net_device *ndev) { struct enetc_ndev_priv *priv = netdev_priv(ndev); struct enetc_hw *hw = &priv->si->hw; @@ -2649,6 +2663,7 @@ static void enetc_reset_tc_mqprio(struct net_device *ndev) enetc_change_preemptible_tcs(priv, 0); } +EXPORT_SYMBOL_GPL(enetc_reset_tc_mqprio); int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data) { diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h index c97a8e3d7a7f..8577cf7699a0 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.h +++ b/drivers/net/ethernet/freescale/enetc/enetc.h @@ -429,6 +429,7 @@ struct net_device_stats *enetc_get_stats(struct net_device *ndev); void enetc_set_features(struct net_device *ndev, netdev_features_t features); int enetc_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd); int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data); +void enetc_reset_tc_mqprio(struct net_device *ndev); int enetc_setup_bpf(struct net_device *ndev, struct netdev_bpf *bpf); int enetc_xdp_xmit(struct net_device *ndev, int num_frames, struct xdp_frame **frames, u32 flags); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index 7cd22d370caa..1416262d4296 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -863,7 +863,6 @@ static int enetc_imdio_create(struct enetc_pf *pf) struct device *dev = &pf->si->pdev->dev; struct enetc_mdio_priv *mdio_priv; struct phylink_pcs *phylink_pcs; - struct mdio_device *mdio_device; struct mii_bus *bus; int err; @@ -889,17 +888,9 @@ static int enetc_imdio_create(struct enetc_pf *pf) goto free_mdio_bus; } - mdio_device = mdio_device_create(bus, 0); - if (IS_ERR(mdio_device)) { - err = PTR_ERR(mdio_device); - dev_err(dev, "cannot create mdio device (%d)\n", err); - goto unregister_mdiobus; - } - - phylink_pcs = lynx_pcs_create(mdio_device); - if (!phylink_pcs) { - mdio_device_free(mdio_device); - err = -ENOMEM; + phylink_pcs = lynx_pcs_create_mdiodev(bus, 0); + if (IS_ERR(phylink_pcs)) { + err = PTR_ERR(phylink_pcs); dev_err(dev, "cannot create lynx pcs (%d)\n", err); goto unregister_mdiobus; } @@ -918,13 +909,8 @@ free_mdio_bus: static void enetc_imdio_remove(struct enetc_pf *pf) { - struct mdio_device *mdio_device; - - if (pf->pcs) { - mdio_device = lynx_get_mdio_device(pf->pcs); - mdio_device_free(mdio_device); + if (pf->pcs) lynx_pcs_destroy(pf->pcs); - } if (pf->imdio) { mdiobus_unregister(pf->imdio); mdiobus_free(pf->imdio); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c index 83c27bbbc6ed..71157eba1fbe 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c @@ -43,10 +43,9 @@ void enetc_sched_speed_set(struct enetc_ndev_priv *priv, int speed) enetc_port_wr(hw, ENETC_PMR, (tmp & ~ENETC_PMR_PSPEED_MASK) | pspeed); } -static int enetc_setup_taprio(struct net_device *ndev, +static int enetc_setup_taprio(struct enetc_ndev_priv *priv, struct tc_taprio_qopt_offload *admin_conf) { - struct enetc_ndev_priv *priv = netdev_priv(ndev); struct enetc_hw *hw = &priv->si->hw; struct enetc_cbd cbd = {.cmd = 0}; struct tgs_gcl_conf *gcl_config; @@ -60,19 +59,13 @@ static int enetc_setup_taprio(struct net_device *ndev, int err; int i; + /* TSD and Qbv are mutually exclusive in hardware */ + for (i = 0; i < priv->num_tx_rings; i++) + if (priv->tx_ring[i]->tsd_enable) + return -EBUSY; + if (admin_conf->num_entries > enetc_get_max_gcl_len(hw)) return -EINVAL; - gcl_len = admin_conf->num_entries; - - tge = enetc_rd(hw, ENETC_PTGCR); - if (!admin_conf->enable) { - enetc_wr(hw, ENETC_PTGCR, tge & ~ENETC_PTGCR_TGE); - enetc_reset_ptcmsdur(hw); - - priv->active_offloads &= ~ENETC_F_QBV; - - return 0; - } if (admin_conf->cycle_time > U32_MAX || admin_conf->cycle_time_extension > U32_MAX) @@ -82,6 +75,7 @@ static int enetc_setup_taprio(struct net_device *ndev, * control BD descriptor. */ gcl_config = &cbd.gcl_conf; + gcl_len = admin_conf->num_entries; data_size = struct_size(gcl_data, entry, gcl_len); tmp = enetc_cbd_alloc_data_mem(priv->si, &cbd, data_size, @@ -115,6 +109,7 @@ static int enetc_setup_taprio(struct net_device *ndev, cbd.cls = BDCR_CMD_PORT_GCL; cbd.status_flags = 0; + tge = enetc_rd(hw, ENETC_PTGCR); enetc_wr(hw, ENETC_PTGCR, tge | ENETC_PTGCR_TGE); err = enetc_send_cmd(priv->si, &cbd); @@ -132,25 +127,92 @@ static int enetc_setup_taprio(struct net_device *ndev, return 0; } -int enetc_setup_tc_taprio(struct net_device *ndev, void *type_data) +static void enetc_reset_taprio(struct enetc_ndev_priv *priv) +{ + struct enetc_hw *hw = &priv->si->hw; + u32 val; + + val = enetc_rd(hw, ENETC_PTGCR); + enetc_wr(hw, ENETC_PTGCR, val & ~ENETC_PTGCR_TGE); + enetc_reset_ptcmsdur(hw); + + priv->active_offloads &= ~ENETC_F_QBV; +} + +static void enetc_taprio_destroy(struct net_device *ndev) { - struct tc_taprio_qopt_offload *taprio = type_data; struct enetc_ndev_priv *priv = netdev_priv(ndev); - int err, i; - /* TSD and Qbv are mutually exclusive in hardware */ + enetc_reset_taprio(priv); + enetc_reset_tc_mqprio(ndev); +} + +static void enetc_taprio_stats(struct net_device *ndev, + struct tc_taprio_qopt_stats *stats) +{ + struct enetc_ndev_priv *priv = netdev_priv(ndev); + u64 window_drops = 0; + int i; + for (i = 0; i < priv->num_tx_rings; i++) - if (priv->tx_ring[i]->tsd_enable) - return -EBUSY; + window_drops += priv->tx_ring[i]->stats.win_drop; + + stats->window_drops = window_drops; +} + +static void enetc_taprio_tc_stats(struct net_device *ndev, + struct tc_taprio_qopt_tc_stats *tc_stats) +{ + struct tc_taprio_qopt_stats *stats = &tc_stats->stats; + struct enetc_ndev_priv *priv = netdev_priv(ndev); + int tc = tc_stats->tc; + u64 window_drops = 0; + int i; + + for (i = 0; i < priv->num_tx_rings; i++) + if (priv->tx_ring[i]->prio == tc) + window_drops += priv->tx_ring[i]->stats.win_drop; + + stats->window_drops = window_drops; +} + +static int enetc_taprio_replace(struct net_device *ndev, + struct tc_taprio_qopt_offload *offload) +{ + struct enetc_ndev_priv *priv = netdev_priv(ndev); + int err; - err = enetc_setup_tc_mqprio(ndev, &taprio->mqprio); + err = enetc_setup_tc_mqprio(ndev, &offload->mqprio); if (err) return err; - err = enetc_setup_taprio(ndev, taprio); - if (err) { - taprio->mqprio.qopt.num_tc = 0; - enetc_setup_tc_mqprio(ndev, &taprio->mqprio); + err = enetc_setup_taprio(priv, offload); + if (err) + enetc_reset_tc_mqprio(ndev); + + return err; +} + +int enetc_setup_tc_taprio(struct net_device *ndev, void *type_data) +{ + struct tc_taprio_qopt_offload *offload = type_data; + int err = 0; + + switch (offload->cmd) { + case TAPRIO_CMD_REPLACE: + err = enetc_taprio_replace(ndev, offload); + break; + case TAPRIO_CMD_DESTROY: + enetc_taprio_destroy(ndev); + break; + case TAPRIO_CMD_STATS: + enetc_taprio_stats(ndev, &offload->stats); + break; + case TAPRIO_CMD_TC_STATS: + enetc_taprio_tc_stats(ndev, &offload->tc_stats); + break; + default: + err = -EOPNOTSUPP; } return err; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index cd215ab20ff9..4d37a811ae15 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1011,24 +1011,6 @@ static void fec_enet_enable_ring(struct net_device *ndev) } } -static void fec_enet_reset_skb(struct net_device *ndev) -{ - struct fec_enet_private *fep = netdev_priv(ndev); - struct fec_enet_priv_tx_q *txq; - int i, j; - - for (i = 0; i < fep->num_tx_queues; i++) { - txq = fep->tx_queue[i]; - - for (j = 0; j < txq->bd.ring_size; j++) { - if (txq->tx_skbuff[j]) { - dev_kfree_skb_any(txq->tx_skbuff[j]); - txq->tx_skbuff[j] = NULL; - } - } - } -} - /* * This function is called to start or restart the FEC during a link * change, transmit timeout, or to reconfigure the FEC. The network @@ -1071,9 +1053,6 @@ fec_restart(struct net_device *ndev) fec_enet_enable_ring(ndev); - /* Reset tx SKB buffers. */ - fec_enet_reset_skb(ndev); - /* Enable MII mode */ if (fep->full_duplex == DUPLEX_FULL) { /* FD enable */ @@ -3791,20 +3770,18 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep, struct xdp_frame *frame) { unsigned int index, status, estatus; - struct bufdesc *bdp, *last_bdp; + struct bufdesc *bdp; dma_addr_t dma_addr; int entries_free; entries_free = fec_enet_get_free_txdesc_num(txq); if (entries_free < MAX_SKB_FRAGS + 1) { netdev_err(fep->netdev, "NOT enough BD for SG!\n"); - xdp_return_frame(frame); return -EBUSY; } /* Fill in a Tx ring entry */ bdp = txq->bd.cur; - last_bdp = bdp; status = fec16_to_cpu(bdp->cbd_sc); status &= ~BD_ENET_TX_STATS; @@ -3832,9 +3809,13 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep, ebdp->cbd_esc = cpu_to_fec32(estatus); } - index = fec_enet_get_bd_index(last_bdp, &txq->bd); txq->tx_skbuff[index] = NULL; + /* Make sure the updates to rest of the descriptor are performed before + * transferring ownership. + */ + dma_wmb(); + /* Send it on its way. Tell FEC it's ready, interrupt when done, * it's the last BD of the frame, and to put the CRC on the end. */ @@ -3842,10 +3823,16 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep, bdp->cbd_sc = cpu_to_fec16(status); /* If this was the last BD in the ring, start at the beginning again. */ - bdp = fec_enet_get_nextdesc(last_bdp, &txq->bd); + bdp = fec_enet_get_nextdesc(bdp, &txq->bd); + + /* Make sure the update to bdp are performed before txq->bd.cur. */ + dma_wmb(); txq->bd.cur = bdp; + /* Trigger transmission start */ + writel(0, txq->bd.reg_desc_active); + return 0; } @@ -3874,12 +3861,6 @@ static int fec_enet_xdp_xmit(struct net_device *dev, sent_frames++; } - /* Make sure the update to bdp and tx_skbuff are performed. */ - wmb(); - - /* Trigger transmission start */ - writel(0, txq->bd.reg_desc_active); - __netif_tx_unlock(nq); return sent_frames; @@ -4031,6 +4012,11 @@ static int fec_enet_init(struct net_device *ndev) ndev->hw_features = ndev->features; + if (!(fep->quirks & FEC_QUIRK_SWAP_FRAME)) + ndev->xdp_features = NETDEV_XDP_ACT_BASIC | + NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT; + fec_restart(ndev); if (fep->quirks & FEC_QUIRK_MIB_CLEAR) @@ -4478,9 +4464,11 @@ fec_drv_remove(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; int ret; - ret = pm_runtime_resume_and_get(&pdev->dev); + ret = pm_runtime_get_sync(&pdev->dev); if (ret < 0) - return ret; + dev_err(&pdev->dev, + "Failed to resume device in remove callback (%pe)\n", + ERR_PTR(ret)); cancel_work_sync(&fep->tx_timeout_work); fec_ptp_stop(pdev); @@ -4493,8 +4481,13 @@ fec_drv_remove(struct platform_device *pdev) of_phy_deregister_fixed_link(np); of_node_put(fep->phy_node); - clk_disable_unprepare(fep->clk_ahb); - clk_disable_unprepare(fep->clk_ipg); + /* After pm_runtime_get_sync() failed, the clks are still off, so skip + * disabling them again. + */ + if (ret >= 0) { + clk_disable_unprepare(fep->clk_ahb); + clk_disable_unprepare(fep->clk_ipg); + } pm_runtime_put_noidle(&pdev->dev); pm_runtime_disable(&pdev->dev); diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c index 625c79d5636f..3b75cc543be9 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.c +++ b/drivers/net/ethernet/freescale/fman/fman_memac.c @@ -976,14 +976,10 @@ static int memac_init(struct fman_mac *memac) static void pcs_put(struct phylink_pcs *pcs) { - struct mdio_device *mdiodev; - if (IS_ERR_OR_NULL(pcs)) return; - mdiodev = lynx_get_mdio_device(pcs); lynx_pcs_destroy(pcs); - mdio_device_free(mdiodev); } static int memac_free(struct fman_mac *memac) @@ -1043,20 +1039,14 @@ static struct phylink_pcs *memac_pcs_create(struct device_node *mac_node, int index) { struct device_node *node; - struct mdio_device *mdiodev = NULL; struct phylink_pcs *pcs; node = of_parse_phandle(mac_node, "pcsphy-handle", index); - if (node && of_device_is_available(node)) - mdiodev = of_mdio_find_device(node); - of_node_put(node); + if (!node) + return ERR_PTR(-ENODEV); - if (!mdiodev) - return ERR_PTR(-EPROBE_DEFER); - - pcs = lynx_pcs_create(mdiodev); - if (!pcs) - mdio_device_free(mdiodev); + pcs = lynx_pcs_create_fwnode(of_fwnode_handle(node)); + of_node_put(node); return pcs; } diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index caa00c72aeeb..8fb70db63b8b 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -31,6 +31,7 @@ // Minimum amount of time between queue kicks in msec (10 seconds) #define MIN_TX_TIMEOUT_GAP (1000 * 10) +#define DQO_TX_MAX 0x3FFFF const char gve_version_str[] = GVE_VERSION; static const char gve_version_prefix[] = GVE_VERSION_PREFIX; @@ -2047,6 +2048,10 @@ static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device) goto err; } + /* Big TCP is only supported on DQ*/ + if (!gve_is_gqi(priv)) + netif_set_tso_max_size(priv->dev, DQO_TX_MAX); + priv->num_registered_pages = 0; priv->rx_copybreak = GVE_DEFAULT_RX_COPYBREAK; /* gvnic has one Notification Block per MSI-x vector, except for the diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c index b76143bfd594..3c09e66ba1ab 100644 --- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c @@ -8,6 +8,7 @@ #include "gve_adminq.h" #include "gve_utils.h" #include "gve_dqo.h" +#include <net/ip.h> #include <linux/tcp.h> #include <linux/slab.h> #include <linux/skbuff.h> @@ -646,6 +647,9 @@ static int gve_try_tx_skb(struct gve_priv *priv, struct gve_tx_ring *tx, goto drop; } + if (unlikely(ipv6_hopopt_jumbo_remove(skb))) + goto drop; + num_buffer_descs = gve_num_buffer_descs_needed(skb); } else { num_buffer_descs = gve_num_buffer_descs_needed(skb); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c index cbbab5b2b402..b85c412683dd 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c @@ -331,9 +331,25 @@ static int hclge_comm_cmd_csq_done(struct hclge_comm_hw *hw) return head == hw->cmq.csq.next_to_use; } -static void hclge_comm_wait_for_resp(struct hclge_comm_hw *hw, +static u32 hclge_get_cmdq_tx_timeout(u16 opcode, u32 tx_timeout) +{ + static const struct hclge_cmdq_tx_timeout_map cmdq_tx_timeout_map[] = { + {HCLGE_OPC_CFG_RST_TRIGGER, HCLGE_COMM_CMDQ_TX_TIMEOUT_500MS}, + }; + u32 i; + + for (i = 0; i < ARRAY_SIZE(cmdq_tx_timeout_map); i++) + if (cmdq_tx_timeout_map[i].opcode == opcode) + return cmdq_tx_timeout_map[i].tx_timeout; + + return tx_timeout; +} + +static void hclge_comm_wait_for_resp(struct hclge_comm_hw *hw, u16 opcode, bool *is_completed) { + u32 cmdq_tx_timeout = hclge_get_cmdq_tx_timeout(opcode, + hw->cmq.tx_timeout); u32 timeout = 0; do { @@ -343,7 +359,7 @@ static void hclge_comm_wait_for_resp(struct hclge_comm_hw *hw, } udelay(1); timeout++; - } while (timeout < hw->cmq.tx_timeout); + } while (timeout < cmdq_tx_timeout); } static int hclge_comm_cmd_convert_err_code(u16 desc_ret) @@ -407,7 +423,8 @@ static int hclge_comm_cmd_check_result(struct hclge_comm_hw *hw, * if multi descriptors to be sent, use the first one to check */ if (HCLGE_COMM_SEND_SYNC(le16_to_cpu(desc->flag))) - hclge_comm_wait_for_resp(hw, &is_completed); + hclge_comm_wait_for_resp(hw, le16_to_cpu(desc->opcode), + &is_completed); if (!is_completed) ret = -EBADE; @@ -529,7 +546,7 @@ int hclge_comm_cmd_queue_init(struct pci_dev *pdev, struct hclge_comm_hw *hw) cmdq->crq.desc_num = HCLGE_COMM_NIC_CMQ_DESC_NUM; /* Setup Tx write back timeout */ - cmdq->tx_timeout = HCLGE_COMM_CMDQ_TX_TIMEOUT; + cmdq->tx_timeout = HCLGE_COMM_CMDQ_TX_TIMEOUT_DEFAULT; /* Setup queue rings */ ret = hclge_comm_alloc_cmd_queue(hw, HCLGE_COMM_TYPE_CSQ); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h index de72ecbfd5ad..18f1b4bf362d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h @@ -54,7 +54,8 @@ #define HCLGE_COMM_NIC_SW_RST_RDY BIT(HCLGE_COMM_NIC_SW_RST_RDY_B) #define HCLGE_COMM_NIC_CMQ_DESC_NUM_S 3 #define HCLGE_COMM_NIC_CMQ_DESC_NUM 1024 -#define HCLGE_COMM_CMDQ_TX_TIMEOUT 30000 +#define HCLGE_COMM_CMDQ_TX_TIMEOUT_DEFAULT 30000 +#define HCLGE_COMM_CMDQ_TX_TIMEOUT_500MS 500000 enum hclge_opcode_type { /* Generic commands */ @@ -360,6 +361,11 @@ struct hclge_comm_caps_bit_map { u16 local_bit; }; +struct hclge_cmdq_tx_timeout_map { + u32 opcode; + u32 tx_timeout; +}; + struct hclge_comm_firmware_compat_cmd { __le32 compat; u8 rsv[20]; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 4c3e90a1c4d0..d385ffc21876 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -130,7 +130,7 @@ static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = { .name = "tx_bd_queue", .cmd = HNAE3_DBG_CMD_TX_BD, .dentry = HNS3_DBG_DENTRY_TX_BD, - .buf_len = HNS3_DBG_READ_LEN_4MB, + .buf_len = HNS3_DBG_READ_LEN_5MB, .init = hns3_dbg_bd_file_init, }, { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h index 97578eabb7d8..4a5ef8a90a10 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h @@ -10,6 +10,7 @@ #define HNS3_DBG_READ_LEN_128KB 0x20000 #define HNS3_DBG_READ_LEN_1MB 0x100000 #define HNS3_DBG_READ_LEN_4MB 0x400000 +#define HNS3_DBG_READ_LEN_5MB 0x500000 #define HNS3_DBG_WRITE_LEN 1024 #define HNS3_DBG_DATA_STR_LEN 32 diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 4fb5406c1951..2689b108f7df 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -8053,12 +8053,15 @@ static void hclge_ae_stop(struct hnae3_handle *handle) /* If it is not PF reset or FLR, the firmware will disable the MAC, * so it only need to stop phy here. */ - if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) && - hdev->reset_type != HNAE3_FUNC_RESET && - hdev->reset_type != HNAE3_FLR_RESET) { - hclge_mac_stop_phy(hdev); - hclge_update_link_status(hdev); - return; + if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) { + hclge_pfc_pause_en_cfg(hdev, HCLGE_PFC_TX_RX_DISABLE, + HCLGE_PFC_DISABLE); + if (hdev->reset_type != HNAE3_FUNC_RESET && + hdev->reset_type != HNAE3_FLR_RESET) { + hclge_mac_stop_phy(hdev); + hclge_update_link_status(hdev); + return; + } } hclge_reset_tqp(handle); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 4a33f65190e2..922c0da3660c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -171,8 +171,8 @@ int hclge_mac_pause_en_cfg(struct hclge_dev *hdev, bool tx, bool rx) return hclge_cmd_send(&hdev->hw, &desc, 1); } -static int hclge_pfc_pause_en_cfg(struct hclge_dev *hdev, u8 tx_rx_bitmap, - u8 pfc_bitmap) +int hclge_pfc_pause_en_cfg(struct hclge_dev *hdev, u8 tx_rx_bitmap, + u8 pfc_bitmap) { struct hclge_desc desc; struct hclge_pfc_en_cmd *pfc = (struct hclge_pfc_en_cmd *)desc.data; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h index 68f28a98e380..dd6f1fd486cf 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h @@ -164,6 +164,9 @@ struct hclge_bp_to_qs_map_cmd { u32 rsvd1; }; +#define HCLGE_PFC_DISABLE 0 +#define HCLGE_PFC_TX_RX_DISABLE 0 + struct hclge_pfc_en_cmd { u8 tx_rx_en_bitmap; u8 pri_en_bitmap; @@ -235,6 +238,8 @@ void hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc); void hclge_tm_pfc_info_update(struct hclge_dev *hdev); int hclge_tm_dwrr_cfg(struct hclge_dev *hdev); int hclge_tm_init_hw(struct hclge_dev *hdev, bool init); +int hclge_pfc_pause_en_cfg(struct hclge_dev *hdev, u8 tx_rx_bitmap, + u8 pfc_bitmap); int hclge_mac_pause_en_cfg(struct hclge_dev *hdev, bool tx, bool rx); int hclge_pause_addr_cfg(struct hclge_dev *hdev, const u8 *mac_addr); void hclge_pfc_rx_stats_get(struct hclge_dev *hdev, u64 *stats); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index f24046250341..dd08989a4c7c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1436,7 +1436,10 @@ static int hclgevf_reset_wait(struct hclgevf_dev *hdev) * might happen in case reset assertion was made by PF. Yes, this also * means we might end up waiting bit more even for VF reset. */ - msleep(5000); + if (hdev->reset_type == HNAE3_VF_FULL_RESET) + msleep(5000); + else + msleep(500); return 0; } diff --git a/drivers/net/ethernet/i825xx/82596.c b/drivers/net/ethernet/i825xx/82596.c index 3ee89ae496d0..773d7aa29ef5 100644 --- a/drivers/net/ethernet/i825xx/82596.c +++ b/drivers/net/ethernet/i825xx/82596.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-1.0+ /* 82596.c: A generic 82596 ethernet driver for linux. */ /* Based on Apricot.c @@ -31,9 +32,7 @@ Driver skeleton Written 1993 by Donald Becker. Copyright 1993 United States Government as represented by the Director, - National Security Agency. This software may only be used and distributed - according to the terms of the GNU General Public License as modified by SRC, - incorporated herein by reference. + National Security Agency. The author may be reached as becker@scyld.com, or C/O Scyld Computing Corporation, 410 Severn Ave., Suite 210, Annapolis MD 21403 diff --git a/drivers/net/ethernet/i825xx/lasi_82596.c b/drivers/net/ethernet/i825xx/lasi_82596.c index 0af70094aba3..3e53e0c243ba 100644 --- a/drivers/net/ethernet/i825xx/lasi_82596.c +++ b/drivers/net/ethernet/i825xx/lasi_82596.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-1.0+ /* lasi_82596.c -- driver for the intel 82596 ethernet controller, as munged into HPPA boxen . @@ -59,9 +60,7 @@ Driver skeleton Written 1993 by Donald Becker. Copyright 1993 United States Government as represented by the Director, - National Security Agency. This software may only be used and distributed - according to the terms of the GNU General Public License as modified by SRC, - incorporated herein by reference. + National Security Agency. The author may be reached as becker@scyld.com, or C/O Scyld Computing Corporation, 410 Severn Ave., Suite 210, Annapolis MD 21403 diff --git a/drivers/net/ethernet/i825xx/lib82596.c b/drivers/net/ethernet/i825xx/lib82596.c index ca2fb303fcc6..67d248a7a6f4 100644 --- a/drivers/net/ethernet/i825xx/lib82596.c +++ b/drivers/net/ethernet/i825xx/lib82596.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-1.0+ /* lasi_82596.c -- driver for the intel 82596 ethernet controller, as munged into HPPA boxen . @@ -59,9 +60,7 @@ Driver skeleton Written 1993 by Donald Becker. Copyright 1993 United States Government as represented by the Director, - National Security Agency. This software may only be used and distributed - according to the terms of the GNU General Public License as modified by SRC, - incorporated herein by reference. + National Security Agency. The author may be reached as becker@scyld.com, or C/O Scyld Computing Corporation, 410 Severn Ave., Suite 210, Annapolis MD 21403 diff --git a/drivers/net/ethernet/i825xx/sun3_82586.c b/drivers/net/ethernet/i825xx/sun3_82586.c index 3909c6a0af89..5e27470c6b1e 100644 --- a/drivers/net/ethernet/i825xx/sun3_82586.c +++ b/drivers/net/ethernet/i825xx/sun3_82586.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Sun3 i82586 Ethernet driver * diff --git a/drivers/net/ethernet/i825xx/sun3_82586.h b/drivers/net/ethernet/i825xx/sun3_82586.h index d82eca563266..d8e249d704a7 100644 --- a/drivers/net/ethernet/i825xx/sun3_82586.h +++ b/drivers/net/ethernet/i825xx/sun3_82586.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Intel i82586 Ethernet definitions * diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index bd7ef59b1f2e..771a3c909c45 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -4198,7 +4198,7 @@ void e1000e_reset(struct e1000_adapter *adapter) /** * e1000e_trigger_lsc - trigger an LSC interrupt - * @adapter: + * @adapter: board private structure * * Fire a link status change interrupt to start the watchdog. **/ diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 9afbbdac3590..7c0578b5457b 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -2238,11 +2238,6 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, iavf_process_config(adapter); adapter->flags |= IAVF_FLAG_SETUP_NETDEV_FEATURES; - /* Request VLAN offload settings */ - if (VLAN_V2_ALLOWED(adapter)) - iavf_set_vlan_offload_features(adapter, 0, - netdev->features); - iavf_set_queue_vlan_tag_loc(adapter); was_mac_changed = !ether_addr_equal(netdev->dev_addr, diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile index 5d89392f969b..817977e3039d 100644 --- a/drivers/net/ethernet/intel/ice/Makefile +++ b/drivers/net/ethernet/intel/ice/Makefile @@ -18,6 +18,7 @@ ice-y := ice_main.o \ ice_txrx_lib.o \ ice_txrx.o \ ice_fltr.o \ + ice_irq.o \ ice_pf_vsi_vlan_ops.o \ ice_vsi_vlan_ops.o \ ice_vsi_vlan_lib.o \ diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index aa32111afd6e..b4bca1d964a9 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -32,6 +32,7 @@ #include <linux/pkt_sched.h> #include <linux/if_bridge.h> #include <linux/ctype.h> +#include <linux/linkmode.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/auxiliary_bus.h> @@ -74,6 +75,7 @@ #include "ice_lag.h" #include "ice_vsi_vlan_ops.h" #include "ice_gnss.h" +#include "ice_irq.h" #define ICE_BAR0 0 #define ICE_REQ_DESC_MULTIPLE 32 @@ -103,11 +105,6 @@ #define ICE_Q_WAIT_RETRY_LIMIT 10 #define ICE_Q_WAIT_MAX_RETRY (5 * ICE_Q_WAIT_RETRY_LIMIT) #define ICE_MAX_LG_RSS_QS 256 -#define ICE_RES_VALID_BIT 0x8000 -#define ICE_RES_MISC_VEC_ID (ICE_RES_VALID_BIT - 1) -#define ICE_RES_RDMA_VEC_ID (ICE_RES_MISC_VEC_ID - 1) -/* All VF control VSIs share the same IRQ, so assign a unique ID for them */ -#define ICE_RES_VF_CTRL_VEC_ID (ICE_RES_RDMA_VEC_ID - 1) #define ICE_INVAL_Q_INDEX 0xffff #define ICE_MAX_RXQS_PER_TC 256 /* Used when setting VSI context per TC Rx queues */ @@ -245,12 +242,6 @@ struct ice_tc_cfg { struct ice_tc_info tc_info[ICE_MAX_TRAFFIC_CLASS]; }; -struct ice_res_tracker { - u16 num_entries; - u16 end; - u16 list[]; -}; - struct ice_qs_cfg { struct mutex *qs_mutex; /* will be assigned to &pf->avail_q_mutex */ unsigned long *pf_map; @@ -348,7 +339,9 @@ struct ice_vsi { u32 rx_buf_failed; u32 rx_page_failed; u16 num_q_vectors; - u16 base_vector; /* IRQ base for OS reserved vectors */ + /* tell if only dynamic irq allocation is allowed */ + bool irq_dyn_alloc; + enum ice_vsi_type type; u16 vsi_num; /* HW (absolute) index of this VSI */ u16 idx; /* software index in pf->vsi[] */ @@ -479,6 +472,7 @@ struct ice_q_vector { char name[ICE_INT_NAME_STR_LEN]; u16 total_events; /* net_dim(): number of interrupts processed */ + struct msi_map irq; } ____cacheline_internodealigned_in_smp; enum ice_pf_flags { @@ -539,7 +533,7 @@ struct ice_pf { /* OS reserved IRQ details */ struct msix_entry *msix_entries; - struct ice_res_tracker *irq_tracker; + struct ice_irq_tracker irq_tracker; /* First MSIX vector used by SR-IOV VFs. Calculated by subtracting the * number of MSIX vectors needed for all SR-IOV VFs from the number of * MSIX vectors allowed on this PF. @@ -583,8 +577,7 @@ struct ice_pf { u32 hw_csum_rx_error; u32 oicr_err_reg; - u16 oicr_idx; /* Other interrupt cause MSIX vector index */ - u16 num_avail_sw_msix; /* remaining MSIX SW vectors left unclaimed */ + struct msi_map oicr_irq; /* Other interrupt cause MSIX vector */ u16 max_pf_txqs; /* Total Tx queues PF wide */ u16 max_pf_rxqs; /* Total Rx queues PF wide */ u16 num_lan_msix; /* Total MSIX vectors for base driver */ @@ -670,7 +663,7 @@ ice_irq_dynamic_ena(struct ice_hw *hw, struct ice_vsi *vsi, struct ice_q_vector *q_vector) { u32 vector = (vsi && q_vector) ? q_vector->reg_idx : - ((struct ice_pf *)hw->back)->oicr_idx; + ((struct ice_pf *)hw->back)->oicr_irq.index; int itr = ICE_ITR_NONE; u32 val; @@ -821,25 +814,6 @@ static inline bool ice_is_switchdev_running(struct ice_pf *pf) return pf->switchdev.is_running; } -/** - * ice_set_sriov_cap - enable SRIOV in PF flags - * @pf: PF struct - */ -static inline void ice_set_sriov_cap(struct ice_pf *pf) -{ - if (pf->hw.func_caps.common_cap.sr_iov_1_1) - set_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags); -} - -/** - * ice_clear_sriov_cap - disable SRIOV in PF flags - * @pf: PF struct - */ -static inline void ice_clear_sriov_cap(struct ice_pf *pf) -{ - clear_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags); -} - #define ICE_FD_STAT_CTR_BLOCK_COUNT 256 #define ICE_FD_STAT_PF_IDX(base_idx) \ ((base_idx) * ICE_FD_STAT_CTR_BLOCK_COUNT) diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 838d9b274d68..63d3e1dcbba5 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -1087,7 +1087,7 @@ struct ice_aqc_get_phy_caps { #define ICE_PHY_TYPE_HIGH_100G_CAUI2 BIT_ULL(2) #define ICE_PHY_TYPE_HIGH_100G_AUI2_AOC_ACC BIT_ULL(3) #define ICE_PHY_TYPE_HIGH_100G_AUI2 BIT_ULL(4) -#define ICE_PHY_TYPE_HIGH_MAX_INDEX 5 +#define ICE_PHY_TYPE_HIGH_MAX_INDEX 4 struct ice_aqc_get_phy_caps_data { __le64 phy_type_low; /* Use values from ICE_PHY_TYPE_LOW_* */ diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c index fba178e07600..cca0e753f38f 100644 --- a/drivers/net/ethernet/intel/ice/ice_arfs.c +++ b/drivers/net/ethernet/intel/ice/ice_arfs.c @@ -596,7 +596,7 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi) { struct net_device *netdev; struct ice_pf *pf; - int base_idx, i; + int i; if (!vsi || vsi->type != ICE_VSI_PF) return 0; @@ -613,10 +613,9 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi) if (unlikely(!netdev->rx_cpu_rmap)) return -EINVAL; - base_idx = vsi->base_vector; ice_for_each_q_vector(vsi, i) if (irq_cpu_rmap_add(netdev->rx_cpu_rmap, - pf->msix_entries[base_idx + i].vector)) { + vsi->q_vectors[i]->irq.virq)) { ice_free_cpu_rx_rmap(vsi); return -EINVAL; } diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 1911d644dfa8..4a12316f7b46 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -103,10 +103,10 @@ static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, u16 v_idx) { struct ice_pf *pf = vsi->back; struct ice_q_vector *q_vector; + int err; /* allocate q_vector */ - q_vector = devm_kzalloc(ice_pf_to_dev(pf), sizeof(*q_vector), - GFP_KERNEL); + q_vector = kzalloc(sizeof(*q_vector), GFP_KERNEL); if (!q_vector) return -ENOMEM; @@ -118,9 +118,34 @@ static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, u16 v_idx) q_vector->rx.itr_mode = ITR_DYNAMIC; q_vector->tx.type = ICE_TX_CONTAINER; q_vector->rx.type = ICE_RX_CONTAINER; + q_vector->irq.index = -ENOENT; - if (vsi->type == ICE_VSI_VF) + if (vsi->type == ICE_VSI_VF) { + q_vector->reg_idx = ice_calc_vf_reg_idx(vsi->vf, q_vector); goto out; + } else if (vsi->type == ICE_VSI_CTRL && vsi->vf) { + struct ice_vsi *ctrl_vsi = ice_get_vf_ctrl_vsi(pf, vsi); + + if (ctrl_vsi) { + if (unlikely(!ctrl_vsi->q_vectors)) { + err = -ENOENT; + goto err_free_q_vector; + } + + q_vector->irq = ctrl_vsi->q_vectors[0]->irq; + goto skip_alloc; + } + } + + q_vector->irq = ice_alloc_irq(pf, vsi->irq_dyn_alloc); + if (q_vector->irq.index < 0) { + err = -ENOMEM; + goto err_free_q_vector; + } + +skip_alloc: + q_vector->reg_idx = q_vector->irq.index; + /* only set affinity_mask if the CPU is online */ if (cpu_online(v_idx)) cpumask_set_cpu(v_idx, &q_vector->affinity_mask); @@ -137,6 +162,11 @@ out: vsi->q_vectors[v_idx] = q_vector; return 0; + +err_free_q_vector: + kfree(q_vector); + + return err; } /** @@ -168,7 +198,19 @@ static void ice_free_q_vector(struct ice_vsi *vsi, int v_idx) if (vsi->netdev) netif_napi_del(&q_vector->napi); - devm_kfree(dev, q_vector); + /* release MSIX interrupt if q_vector had interrupt allocated */ + if (q_vector->irq.index < 0) + goto free_q_vector; + + /* only free last VF ctrl vsi interrupt */ + if (vsi->type == ICE_VSI_CTRL && vsi->vf && + ice_get_vf_ctrl_vsi(pf, vsi)) + goto free_q_vector; + + ice_free_irq(pf, q_vector->irq); + +free_q_vector: + kfree(q_vector); vsi->q_vectors[v_idx] = NULL; } diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 0157f6e98d3e..eb2dc0983776 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -5160,7 +5160,7 @@ ice_aq_read_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr, */ int ice_aq_write_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr, - u16 bus_addr, __le16 addr, u8 params, u8 *data, + u16 bus_addr, __le16 addr, u8 params, const u8 *data, struct ice_sq_cd *cd) { struct ice_aq_desc desc = { 0 }; diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 8ba5f935a092..81961a7d6598 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -229,7 +229,7 @@ ice_aq_read_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr, struct ice_sq_cd *cd); int ice_aq_write_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr, - u16 bus_addr, __le16 addr, u8 params, u8 *data, + u16 bus_addr, __le16 addr, u8 params, const u8 *data, struct ice_sq_cd *cd); bool ice_fw_supports_report_dflt_cfg(struct ice_hw *hw); #endif /* _ICE_COMMON_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index c6d4926f0fcf..850db8e0e6b0 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -932,10 +932,9 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring, if ((first->tx_flags & ICE_TX_FLAGS_HW_VLAN || first->tx_flags & ICE_TX_FLAGS_HW_OUTER_SINGLE_VLAN) || skb->priority != TC_PRIO_CONTROL) { - first->tx_flags &= ~ICE_TX_FLAGS_VLAN_PR_M; + first->vid &= ~VLAN_PRIO_MASK; /* Mask the lower 3 bits to set the 802.1p priority */ - first->tx_flags |= (skb->priority & 0x7) << - ICE_TX_FLAGS_VLAN_PR_S; + first->vid |= (skb->priority << VLAN_PRIO_SHIFT) & VLAN_PRIO_MASK; /* if this is not already set it means a VLAN 0 + priority needs * to be offloaded */ diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c index bc44cc220818..80dc5445b50d 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.c +++ b/drivers/net/ethernet/intel/ice/ice_devlink.c @@ -1256,8 +1256,6 @@ static const struct devlink_ops ice_devlink_ops = { BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE), .reload_down = ice_devlink_reload_down, .reload_up = ice_devlink_reload_up, - .port_split = ice_devlink_port_split, - .port_unsplit = ice_devlink_port_unsplit, .eswitch_mode_get = ice_eswitch_mode_get, .eswitch_mode_set = ice_eswitch_mode_set, .info_get = ice_devlink_info_get, @@ -1512,6 +1510,11 @@ ice_devlink_set_port_split_options(struct ice_pf *pf, ice_active_port_option = active_idx; } +static const struct devlink_port_ops ice_devlink_port_ops = { + .port_split = ice_devlink_port_split, + .port_unsplit = ice_devlink_port_unsplit, +}; + /** * ice_devlink_create_pf_port - Create a devlink port for this PF * @pf: the PF to create a devlink port for @@ -1551,7 +1554,8 @@ int ice_devlink_create_pf_port(struct ice_pf *pf) devlink_port_attrs_set(devlink_port, &attrs); devlink = priv_to_devlink(pf); - err = devlink_port_register(devlink, devlink_port, vsi->idx); + err = devlink_port_register_with_ops(devlink, devlink_port, vsi->idx, + &ice_devlink_port_ops); if (err) { dev_err(dev, "Failed to create devlink port for PF %d, error %d\n", pf->hw.pf_id, err); diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index f6dd3f8fd936..ad0a007b7398 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -10,16 +10,15 @@ #include "ice_tc_lib.h" /** - * ice_eswitch_add_vf_mac_rule - add adv rule with VF's MAC + * ice_eswitch_add_vf_sp_rule - add adv rule with VF's VSI index * @pf: pointer to PF struct * @vf: pointer to VF struct - * @mac: VF's MAC address * * This function adds advanced rule that forwards packets with - * VF's MAC address (src MAC) to the corresponding switchdev ctrl VSI queue. + * VF's VSI index to the corresponding switchdev ctrl VSI queue. */ -int -ice_eswitch_add_vf_mac_rule(struct ice_pf *pf, struct ice_vf *vf, const u8 *mac) +static int +ice_eswitch_add_vf_sp_rule(struct ice_pf *pf, struct ice_vf *vf) { struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi; struct ice_adv_rule_info rule_info = { 0 }; @@ -32,76 +31,41 @@ ice_eswitch_add_vf_mac_rule(struct ice_pf *pf, struct ice_vf *vf, const u8 *mac) if (!list) return -ENOMEM; - list[0].type = ICE_MAC_OFOS; - ether_addr_copy(list[0].h_u.eth_hdr.src_addr, mac); - eth_broadcast_addr(list[0].m_u.eth_hdr.src_addr); + ice_rule_add_src_vsi_metadata(list); - rule_info.sw_act.flag |= ICE_FLTR_TX; + rule_info.sw_act.flag = ICE_FLTR_TX; rule_info.sw_act.vsi_handle = ctrl_vsi->idx; rule_info.sw_act.fltr_act = ICE_FWD_TO_Q; - rule_info.rx = false; rule_info.sw_act.fwd_id.q_id = hw->func_caps.common_cap.rxq_first_id + ctrl_vsi->rxq_map[vf->vf_id]; rule_info.flags_info.act |= ICE_SINGLE_ACT_LB_ENABLE; rule_info.flags_info.act_valid = true; rule_info.tun_type = ICE_SW_TUN_AND_NON_TUN; + rule_info.src_vsi = vf->lan_vsi_idx; err = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, - vf->repr->mac_rule); + &vf->repr->sp_rule); if (err) - dev_err(ice_pf_to_dev(pf), "Unable to add VF mac rule in switchdev mode for VF %d", + dev_err(ice_pf_to_dev(pf), "Unable to add VF slow-path rule in switchdev mode for VF %d", vf->vf_id); - else - vf->repr->rule_added = true; kfree(list); return err; } /** - * ice_eswitch_replay_vf_mac_rule - replay adv rule with VF's MAC - * @vf: pointer to vF struct - * - * This function replays VF's MAC rule after reset. - */ -void ice_eswitch_replay_vf_mac_rule(struct ice_vf *vf) -{ - int err; - - if (!ice_is_switchdev_running(vf->pf)) - return; - - if (is_valid_ether_addr(vf->hw_lan_addr)) { - err = ice_eswitch_add_vf_mac_rule(vf->pf, vf, - vf->hw_lan_addr); - if (err) { - dev_err(ice_pf_to_dev(vf->pf), "Failed to add MAC %pM for VF %d\n, error %d\n", - vf->hw_lan_addr, vf->vf_id, err); - return; - } - vf->num_mac++; - - ether_addr_copy(vf->dev_lan_addr, vf->hw_lan_addr); - } -} - -/** - * ice_eswitch_del_vf_mac_rule - delete adv rule with VF's MAC + * ice_eswitch_del_vf_sp_rule - delete adv rule with VF's VSI index * @vf: pointer to the VF struct * - * Delete the advanced rule that was used to forward packets with the VF's MAC - * address (src MAC) to the corresponding switchdev ctrl VSI queue. + * Delete the advanced rule that was used to forward packets with the VF's VSI + * index to the corresponding switchdev ctrl VSI queue. */ -void ice_eswitch_del_vf_mac_rule(struct ice_vf *vf) +static void ice_eswitch_del_vf_sp_rule(struct ice_vf *vf) { - if (!ice_is_switchdev_running(vf->pf)) - return; - - if (!vf->repr->rule_added) + if (!vf->repr) return; - ice_rem_adv_rule_by_id(&vf->pf->hw, vf->repr->mac_rule); - vf->repr->rule_added = false; + ice_rem_adv_rule_by_id(&vf->pf->hw, &vf->repr->sp_rule); } /** @@ -237,6 +201,7 @@ ice_eswitch_release_reprs(struct ice_pf *pf, struct ice_vsi *ctrl_vsi) ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof); metadata_dst_free(vf->repr->dst); vf->repr->dst = NULL; + ice_eswitch_del_vf_sp_rule(vf); ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr, ICE_FWD_TO_VSI); @@ -264,25 +229,30 @@ static int ice_eswitch_setup_reprs(struct ice_pf *pf) vf->repr->dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX, GFP_KERNEL); if (!vf->repr->dst) { - ice_fltr_add_mac_and_broadcast(vsi, - vf->hw_lan_addr, + ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr, + ICE_FWD_TO_VSI); + goto err; + } + + if (ice_eswitch_add_vf_sp_rule(pf, vf)) { + ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr, ICE_FWD_TO_VSI); goto err; } if (ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof)) { - ice_fltr_add_mac_and_broadcast(vsi, - vf->hw_lan_addr, + ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr, ICE_FWD_TO_VSI); + ice_eswitch_del_vf_sp_rule(vf); metadata_dst_free(vf->repr->dst); vf->repr->dst = NULL; goto err; } if (ice_vsi_add_vlan_zero(vsi)) { - ice_fltr_add_mac_and_broadcast(vsi, - vf->hw_lan_addr, + ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr, ICE_FWD_TO_VSI); + ice_eswitch_del_vf_sp_rule(vf); metadata_dst_free(vf->repr->dst); vf->repr->dst = NULL; ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof); diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.h b/drivers/net/ethernet/intel/ice/ice_eswitch.h index 6a413331572b..b18bf83a2f5b 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.h +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.h @@ -20,11 +20,6 @@ bool ice_is_eswitch_mode_switchdev(struct ice_pf *pf); void ice_eswitch_update_repr(struct ice_vsi *vsi); void ice_eswitch_stop_all_tx_queues(struct ice_pf *pf); -int -ice_eswitch_add_vf_mac_rule(struct ice_pf *pf, struct ice_vf *vf, - const u8 *mac); -void ice_eswitch_replay_vf_mac_rule(struct ice_vf *vf); -void ice_eswitch_del_vf_mac_rule(struct ice_vf *vf); void ice_eswitch_set_target_vsi(struct sk_buff *skb, struct ice_tx_offload_params *off); @@ -34,15 +29,6 @@ ice_eswitch_port_start_xmit(struct sk_buff *skb, struct net_device *netdev); static inline void ice_eswitch_release(struct ice_pf *pf) { } static inline void ice_eswitch_stop_all_tx_queues(struct ice_pf *pf) { } -static inline void ice_eswitch_replay_vf_mac_rule(struct ice_vf *vf) { } -static inline void ice_eswitch_del_vf_mac_rule(struct ice_vf *vf) { } - -static inline int -ice_eswitch_add_vf_mac_rule(struct ice_pf *pf, struct ice_vf *vf, - const u8 *mac) -{ - return -EOPNOTSUPP; -} static inline void ice_eswitch_set_target_vsi(struct sk_buff *skb, diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index f86e814354a3..8d5cbbd0b3d5 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -4,6 +4,7 @@ /* ethtool support for ice */ #include "ice.h" +#include "ice_ethtool.h" #include "ice_flow.h" #include "ice_fltr.h" #include "ice_lib.h" @@ -956,7 +957,7 @@ static u64 ice_intr_test(struct net_device *netdev) netdev_info(netdev, "interrupt test\n"); - wr32(&pf->hw, GLINT_DYN_CTL(pf->oicr_idx), + wr32(&pf->hw, GLINT_DYN_CTL(pf->oicr_irq.index), GLINT_DYN_CTL_SW_ITR_INDX_M | GLINT_DYN_CTL_INTENA_MSK_M | GLINT_DYN_CTL_SWINT_TRIG_M); @@ -1658,15 +1659,26 @@ ice_mask_min_supported_speeds(struct ice_hw *hw, *phy_types_low &= ~ICE_PHY_TYPE_LOW_MASK_MIN_1G; } -#define ice_ethtool_advertise_link_mode(aq_link_speed, ethtool_link_mode) \ - do { \ - if (req_speeds & (aq_link_speed) || \ - (!req_speeds && \ - (advert_phy_type_lo & phy_type_mask_lo || \ - advert_phy_type_hi & phy_type_mask_hi))) \ - ethtool_link_ksettings_add_link_mode(ks, advertising,\ - ethtool_link_mode); \ - } while (0) +/** + * ice_linkmode_set_bit - set link mode bit + * @phy_to_ethtool: PHY type to ethtool link mode struct to set + * @ks: ethtool link ksettings struct to fill out + * @req_speeds: speed requested by user + * @advert_phy_type: advertised PHY type + * @phy_type: PHY type + */ +static void +ice_linkmode_set_bit(const struct ice_phy_type_to_ethtool *phy_to_ethtool, + struct ethtool_link_ksettings *ks, u32 req_speeds, + u64 advert_phy_type, u32 phy_type) +{ + linkmode_set_bit(phy_to_ethtool->link_mode, ks->link_modes.supported); + + if (req_speeds & phy_to_ethtool->aq_link_speed || + (!req_speeds && advert_phy_type & BIT(phy_type))) + linkmode_set_bit(phy_to_ethtool->link_mode, + ks->link_modes.advertising); +} /** * ice_phy_type_to_ethtool - convert the phy_types to ethtool link modes @@ -1682,11 +1694,10 @@ ice_phy_type_to_ethtool(struct net_device *netdev, struct ice_pf *pf = vsi->back; u64 advert_phy_type_lo = 0; u64 advert_phy_type_hi = 0; - u64 phy_type_mask_lo = 0; - u64 phy_type_mask_hi = 0; u64 phy_types_high = 0; u64 phy_types_low = 0; - u16 req_speeds; + u32 req_speeds; + u32 i; req_speeds = vsi->port_info->phy.link_info.req_speeds; @@ -1743,272 +1754,22 @@ ice_phy_type_to_ethtool(struct net_device *netdev, advert_phy_type_hi = vsi->port_info->phy.phy_type_high; } - ethtool_link_ksettings_zero_link_mode(ks, supported); - ethtool_link_ksettings_zero_link_mode(ks, advertising); - - phy_type_mask_lo = ICE_PHY_TYPE_LOW_100BASE_TX | - ICE_PHY_TYPE_LOW_100M_SGMII; - if (phy_types_low & phy_type_mask_lo) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 100baseT_Full); - - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_100MB, - 100baseT_Full); - } - - phy_type_mask_lo = ICE_PHY_TYPE_LOW_1000BASE_T | - ICE_PHY_TYPE_LOW_1G_SGMII; - if (phy_types_low & phy_type_mask_lo) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 1000baseT_Full); - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_1000MB, - 1000baseT_Full); - } - - phy_type_mask_lo = ICE_PHY_TYPE_LOW_1000BASE_KX; - if (phy_types_low & phy_type_mask_lo) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 1000baseKX_Full); - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_1000MB, - 1000baseKX_Full); - } - - phy_type_mask_lo = ICE_PHY_TYPE_LOW_1000BASE_SX | - ICE_PHY_TYPE_LOW_1000BASE_LX; - if (phy_types_low & phy_type_mask_lo) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 1000baseX_Full); - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_1000MB, - 1000baseX_Full); - } - - phy_type_mask_lo = ICE_PHY_TYPE_LOW_2500BASE_T; - if (phy_types_low & phy_type_mask_lo) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 2500baseT_Full); - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_2500MB, - 2500baseT_Full); - } - - phy_type_mask_lo = ICE_PHY_TYPE_LOW_2500BASE_X | - ICE_PHY_TYPE_LOW_2500BASE_KX; - if (phy_types_low & phy_type_mask_lo) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 2500baseX_Full); - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_2500MB, - 2500baseX_Full); - } - - phy_type_mask_lo = ICE_PHY_TYPE_LOW_5GBASE_T | - ICE_PHY_TYPE_LOW_5GBASE_KR; - if (phy_types_low & phy_type_mask_lo) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 5000baseT_Full); - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_5GB, - 5000baseT_Full); - } - - phy_type_mask_lo = ICE_PHY_TYPE_LOW_10GBASE_T | - ICE_PHY_TYPE_LOW_10G_SFI_DA | - ICE_PHY_TYPE_LOW_10G_SFI_AOC_ACC | - ICE_PHY_TYPE_LOW_10G_SFI_C2C; - if (phy_types_low & phy_type_mask_lo) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 10000baseT_Full); - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_10GB, - 10000baseT_Full); - } - - phy_type_mask_lo = ICE_PHY_TYPE_LOW_10GBASE_KR_CR1; - if (phy_types_low & phy_type_mask_lo) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 10000baseKR_Full); - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_10GB, - 10000baseKR_Full); - } - - phy_type_mask_lo = ICE_PHY_TYPE_LOW_10GBASE_SR; - if (phy_types_low & phy_type_mask_lo) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 10000baseSR_Full); - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_10GB, - 10000baseSR_Full); - } - - phy_type_mask_lo = ICE_PHY_TYPE_LOW_10GBASE_LR; - if (phy_types_low & phy_type_mask_lo) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 10000baseLR_Full); - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_10GB, - 10000baseLR_Full); - } - - phy_type_mask_lo = ICE_PHY_TYPE_LOW_25GBASE_T | - ICE_PHY_TYPE_LOW_25GBASE_CR | - ICE_PHY_TYPE_LOW_25GBASE_CR_S | - ICE_PHY_TYPE_LOW_25GBASE_CR1 | - ICE_PHY_TYPE_LOW_25G_AUI_AOC_ACC | - ICE_PHY_TYPE_LOW_25G_AUI_C2C; - if (phy_types_low & phy_type_mask_lo) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 25000baseCR_Full); - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_25GB, - 25000baseCR_Full); - } - - phy_type_mask_lo = ICE_PHY_TYPE_LOW_25GBASE_SR | - ICE_PHY_TYPE_LOW_25GBASE_LR; - if (phy_types_low & phy_type_mask_lo) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 25000baseSR_Full); - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_25GB, - 25000baseSR_Full); - } - - phy_type_mask_lo = ICE_PHY_TYPE_LOW_25GBASE_KR | - ICE_PHY_TYPE_LOW_25GBASE_KR_S | - ICE_PHY_TYPE_LOW_25GBASE_KR1; - if (phy_types_low & phy_type_mask_lo) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 25000baseKR_Full); - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_25GB, - 25000baseKR_Full); - } - - phy_type_mask_lo = ICE_PHY_TYPE_LOW_40GBASE_KR4; - if (phy_types_low & phy_type_mask_lo) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 40000baseKR4_Full); - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_40GB, - 40000baseKR4_Full); - } - - phy_type_mask_lo = ICE_PHY_TYPE_LOW_40GBASE_CR4 | - ICE_PHY_TYPE_LOW_40G_XLAUI_AOC_ACC | - ICE_PHY_TYPE_LOW_40G_XLAUI; - if (phy_types_low & phy_type_mask_lo) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 40000baseCR4_Full); - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_40GB, - 40000baseCR4_Full); - } - - phy_type_mask_lo = ICE_PHY_TYPE_LOW_40GBASE_SR4; - if (phy_types_low & phy_type_mask_lo) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 40000baseSR4_Full); - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_40GB, - 40000baseSR4_Full); - } - - phy_type_mask_lo = ICE_PHY_TYPE_LOW_40GBASE_LR4; - if (phy_types_low & phy_type_mask_lo) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 40000baseLR4_Full); - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_40GB, - 40000baseLR4_Full); - } - - phy_type_mask_lo = ICE_PHY_TYPE_LOW_50GBASE_CR2 | - ICE_PHY_TYPE_LOW_50G_LAUI2_AOC_ACC | - ICE_PHY_TYPE_LOW_50G_LAUI2 | - ICE_PHY_TYPE_LOW_50G_AUI2_AOC_ACC | - ICE_PHY_TYPE_LOW_50G_AUI2 | - ICE_PHY_TYPE_LOW_50GBASE_CP | - ICE_PHY_TYPE_LOW_50GBASE_SR | - ICE_PHY_TYPE_LOW_50G_AUI1_AOC_ACC | - ICE_PHY_TYPE_LOW_50G_AUI1; - if (phy_types_low & phy_type_mask_lo) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 50000baseCR2_Full); - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_50GB, - 50000baseCR2_Full); - } - - phy_type_mask_lo = ICE_PHY_TYPE_LOW_50GBASE_KR2 | - ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4; - if (phy_types_low & phy_type_mask_lo) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 50000baseKR2_Full); - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_50GB, - 50000baseKR2_Full); - } - - phy_type_mask_lo = ICE_PHY_TYPE_LOW_50GBASE_SR2 | - ICE_PHY_TYPE_LOW_50GBASE_LR2 | - ICE_PHY_TYPE_LOW_50GBASE_FR | - ICE_PHY_TYPE_LOW_50GBASE_LR; - if (phy_types_low & phy_type_mask_lo) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 50000baseSR2_Full); - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_50GB, - 50000baseSR2_Full); - } - - phy_type_mask_lo = ICE_PHY_TYPE_LOW_100GBASE_CR4 | - ICE_PHY_TYPE_LOW_100G_CAUI4_AOC_ACC | - ICE_PHY_TYPE_LOW_100G_CAUI4 | - ICE_PHY_TYPE_LOW_100G_AUI4_AOC_ACC | - ICE_PHY_TYPE_LOW_100G_AUI4 | - ICE_PHY_TYPE_LOW_100GBASE_CR_PAM4; - phy_type_mask_hi = ICE_PHY_TYPE_HIGH_100G_CAUI2_AOC_ACC | - ICE_PHY_TYPE_HIGH_100G_CAUI2 | - ICE_PHY_TYPE_HIGH_100G_AUI2_AOC_ACC | - ICE_PHY_TYPE_HIGH_100G_AUI2; - if (phy_types_low & phy_type_mask_lo || - phy_types_high & phy_type_mask_hi) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 100000baseCR4_Full); - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_100GB, - 100000baseCR4_Full); - } - - if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CP2) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 100000baseCR2_Full); - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_100GB, - 100000baseCR2_Full); - } - - if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_SR4) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 100000baseSR4_Full); - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_100GB, - 100000baseSR4_Full); - } - - if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_SR2) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 100000baseSR2_Full); - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_100GB, - 100000baseSR2_Full); - } - - phy_type_mask_lo = ICE_PHY_TYPE_LOW_100GBASE_LR4 | - ICE_PHY_TYPE_LOW_100GBASE_DR; - if (phy_types_low & phy_type_mask_lo) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 100000baseLR4_ER4_Full); - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_100GB, - 100000baseLR4_ER4_Full); - } + linkmode_zero(ks->link_modes.supported); + linkmode_zero(ks->link_modes.advertising); - phy_type_mask_lo = ICE_PHY_TYPE_LOW_100GBASE_KR4 | - ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4; - if (phy_types_low & phy_type_mask_lo) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 100000baseKR4_Full); - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_100GB, - 100000baseKR4_Full); + for (i = 0; i < BITS_PER_TYPE(u64); i++) { + if (phy_types_low & BIT_ULL(i)) + ice_linkmode_set_bit(&phy_type_low_lkup[i], ks, + req_speeds, advert_phy_type_lo, + i); } - if (phy_types_high & ICE_PHY_TYPE_HIGH_100GBASE_KR2_PAM4) { - ethtool_link_ksettings_add_link_mode(ks, supported, - 100000baseKR2_Full); - ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_100GB, - 100000baseKR2_Full); + for (i = 0; i < BITS_PER_TYPE(u64); i++) { + if (phy_types_high & BIT_ULL(i)) + ice_linkmode_set_bit(&phy_type_high_lkup[i], ks, + req_speeds, advert_phy_type_hi, + i); } - } #define TEST_SET_BITS_TIMEOUT 50 diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.h b/drivers/net/ethernet/intel/ice/ice_ethtool.h new file mode 100644 index 000000000000..b403ee79cd5e --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.h @@ -0,0 +1,105 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2023 Intel Corporation */ + +#ifndef _ICE_ETHTOOL_H_ +#define _ICE_ETHTOOL_H_ + +struct ice_phy_type_to_ethtool { + u64 aq_link_speed; + u8 link_mode; +}; + +/* Macro to make PHY type to Ethtool link mode table entry. + * The index is the PHY type. + */ +#define ICE_PHY_TYPE(LINK_SPEED, ETHTOOL_LINK_MODE) {\ + .aq_link_speed = ICE_AQ_LINK_SPEED_##LINK_SPEED, \ + .link_mode = ETHTOOL_LINK_MODE_##ETHTOOL_LINK_MODE##_BIT, \ +} + +/* Lookup table mapping PHY type low to link speed and Ethtool link modes. + * Array index corresponds to HW PHY type bit, see + * ice_adminq_cmd.h:ICE_PHY_TYPE_LOW_*. + */ +static const struct ice_phy_type_to_ethtool +phy_type_low_lkup[] = { + [0] = ICE_PHY_TYPE(100MB, 100baseT_Full), + [1] = ICE_PHY_TYPE(100MB, 100baseT_Full), + [2] = ICE_PHY_TYPE(1000MB, 1000baseT_Full), + [3] = ICE_PHY_TYPE(1000MB, 1000baseX_Full), + [4] = ICE_PHY_TYPE(1000MB, 1000baseX_Full), + [5] = ICE_PHY_TYPE(1000MB, 1000baseKX_Full), + [6] = ICE_PHY_TYPE(1000MB, 1000baseT_Full), + [7] = ICE_PHY_TYPE(2500MB, 2500baseT_Full), + [8] = ICE_PHY_TYPE(2500MB, 2500baseX_Full), + [9] = ICE_PHY_TYPE(2500MB, 2500baseX_Full), + [10] = ICE_PHY_TYPE(5GB, 5000baseT_Full), + [11] = ICE_PHY_TYPE(5GB, 5000baseT_Full), + [12] = ICE_PHY_TYPE(10GB, 10000baseT_Full), + [13] = ICE_PHY_TYPE(10GB, 10000baseCR_Full), + [14] = ICE_PHY_TYPE(10GB, 10000baseSR_Full), + [15] = ICE_PHY_TYPE(10GB, 10000baseLR_Full), + [16] = ICE_PHY_TYPE(10GB, 10000baseKR_Full), + [17] = ICE_PHY_TYPE(10GB, 10000baseCR_Full), + [18] = ICE_PHY_TYPE(10GB, 10000baseKR_Full), + [19] = ICE_PHY_TYPE(25GB, 25000baseCR_Full), + [20] = ICE_PHY_TYPE(25GB, 25000baseCR_Full), + [21] = ICE_PHY_TYPE(25GB, 25000baseCR_Full), + [22] = ICE_PHY_TYPE(25GB, 25000baseCR_Full), + [23] = ICE_PHY_TYPE(25GB, 25000baseSR_Full), + [24] = ICE_PHY_TYPE(25GB, 25000baseSR_Full), + [25] = ICE_PHY_TYPE(25GB, 25000baseKR_Full), + [26] = ICE_PHY_TYPE(25GB, 25000baseKR_Full), + [27] = ICE_PHY_TYPE(25GB, 25000baseKR_Full), + [28] = ICE_PHY_TYPE(25GB, 25000baseSR_Full), + [29] = ICE_PHY_TYPE(25GB, 25000baseCR_Full), + [30] = ICE_PHY_TYPE(40GB, 40000baseCR4_Full), + [31] = ICE_PHY_TYPE(40GB, 40000baseSR4_Full), + [32] = ICE_PHY_TYPE(40GB, 40000baseLR4_Full), + [33] = ICE_PHY_TYPE(40GB, 40000baseKR4_Full), + [34] = ICE_PHY_TYPE(40GB, 40000baseSR4_Full), + [35] = ICE_PHY_TYPE(40GB, 40000baseCR4_Full), + [36] = ICE_PHY_TYPE(50GB, 50000baseCR2_Full), + [37] = ICE_PHY_TYPE(50GB, 50000baseSR2_Full), + [38] = ICE_PHY_TYPE(50GB, 50000baseSR2_Full), + [39] = ICE_PHY_TYPE(50GB, 50000baseKR2_Full), + [40] = ICE_PHY_TYPE(50GB, 50000baseSR2_Full), + [41] = ICE_PHY_TYPE(50GB, 50000baseCR2_Full), + [42] = ICE_PHY_TYPE(50GB, 50000baseSR2_Full), + [43] = ICE_PHY_TYPE(50GB, 50000baseCR2_Full), + [44] = ICE_PHY_TYPE(50GB, 50000baseCR_Full), + [45] = ICE_PHY_TYPE(50GB, 50000baseSR_Full), + [46] = ICE_PHY_TYPE(50GB, 50000baseLR_ER_FR_Full), + [47] = ICE_PHY_TYPE(50GB, 50000baseLR_ER_FR_Full), + [48] = ICE_PHY_TYPE(50GB, 50000baseKR_Full), + [49] = ICE_PHY_TYPE(50GB, 50000baseSR_Full), + [50] = ICE_PHY_TYPE(50GB, 50000baseCR_Full), + [51] = ICE_PHY_TYPE(100GB, 100000baseCR4_Full), + [52] = ICE_PHY_TYPE(100GB, 100000baseSR4_Full), + [53] = ICE_PHY_TYPE(100GB, 100000baseLR4_ER4_Full), + [54] = ICE_PHY_TYPE(100GB, 100000baseKR4_Full), + [55] = ICE_PHY_TYPE(100GB, 100000baseCR4_Full), + [56] = ICE_PHY_TYPE(100GB, 100000baseCR4_Full), + [57] = ICE_PHY_TYPE(100GB, 100000baseSR4_Full), + [58] = ICE_PHY_TYPE(100GB, 100000baseCR4_Full), + [59] = ICE_PHY_TYPE(100GB, 100000baseCR4_Full), + [60] = ICE_PHY_TYPE(100GB, 100000baseKR4_Full), + [61] = ICE_PHY_TYPE(100GB, 100000baseCR2_Full), + [62] = ICE_PHY_TYPE(100GB, 100000baseSR2_Full), + [63] = ICE_PHY_TYPE(100GB, 100000baseLR4_ER4_Full), +}; + +/* Lookup table mapping PHY type high to link speed and Ethtool link modes. + * Array index corresponds to HW PHY type bit, see + * ice_adminq_cmd.h:ICE_PHY_TYPE_HIGH_* + */ +static const struct ice_phy_type_to_ethtool +phy_type_high_lkup[] = { + [0] = ICE_PHY_TYPE(100GB, 100000baseKR2_Full), + [1] = ICE_PHY_TYPE(100GB, 100000baseSR2_Full), + [2] = ICE_PHY_TYPE(100GB, 100000baseCR2_Full), + [3] = ICE_PHY_TYPE(100GB, 100000baseSR2_Full), + [4] = ICE_PHY_TYPE(100GB, 100000baseCR2_Full), +}; + +#endif /* !_ICE_ETHTOOL_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.c b/drivers/net/ethernet/intel/ice/ice_gnss.c index 2ea8a2b11bcd..bd0ed155e11b 100644 --- a/drivers/net/ethernet/intel/ice/ice_gnss.c +++ b/drivers/net/ethernet/intel/ice/ice_gnss.c @@ -16,8 +16,8 @@ * * number of bytes written - success * * negative - error code */ -static unsigned int -ice_gnss_do_write(struct ice_pf *pf, unsigned char *buf, unsigned int size) +static int +ice_gnss_do_write(struct ice_pf *pf, const unsigned char *buf, unsigned int size) { struct ice_aqc_link_topo_addr link_topo; struct ice_hw *hw = &pf->hw; @@ -72,39 +72,7 @@ err_out: dev_err(ice_pf_to_dev(pf), "GNSS failed to write, offset=%u, size=%u, err=%d\n", offset, size, err); - return offset; -} - -/** - * ice_gnss_write_pending - Write all pending data to internal GNSS - * @work: GNSS write work structure - */ -static void ice_gnss_write_pending(struct kthread_work *work) -{ - struct gnss_serial *gnss = container_of(work, struct gnss_serial, - write_work); - struct ice_pf *pf = gnss->back; - - if (!pf) - return; - - if (!test_bit(ICE_FLAG_GNSS, pf->flags)) - return; - - if (!list_empty(&gnss->queue)) { - struct gnss_write_buf *write_buf = NULL; - unsigned int bytes; - - write_buf = list_first_entry(&gnss->queue, - struct gnss_write_buf, queue); - - bytes = ice_gnss_do_write(pf, write_buf->buf, write_buf->size); - dev_dbg(ice_pf_to_dev(pf), "%u bytes written to GNSS\n", bytes); - - list_del(&write_buf->queue); - kfree(write_buf->buf); - kfree(write_buf); - } + return err; } /** @@ -220,8 +188,6 @@ static struct gnss_serial *ice_gnss_struct_init(struct ice_pf *pf) pf->gnss_serial = gnss; kthread_init_delayed_work(&gnss->read_work, ice_gnss_read); - INIT_LIST_HEAD(&gnss->queue); - kthread_init_work(&gnss->write_work, ice_gnss_write_pending); kworker = kthread_create_worker(0, "ice-gnss-%s", dev_name(dev)); if (IS_ERR(kworker)) { kfree(gnss); @@ -281,7 +247,6 @@ static void ice_gnss_close(struct gnss_device *gdev) if (!gnss) return; - kthread_cancel_work_sync(&gnss->write_work); kthread_cancel_delayed_work_sync(&gnss->read_work); } @@ -300,10 +265,7 @@ ice_gnss_write(struct gnss_device *gdev, const unsigned char *buf, size_t count) { struct ice_pf *pf = gnss_get_drvdata(gdev); - struct gnss_write_buf *write_buf; struct gnss_serial *gnss; - unsigned char *cmd_buf; - int err = count; /* We cannot write a single byte using our I2C implementation. */ if (count <= 1 || count > ICE_GNSS_TTY_WRITE_BUF) @@ -319,24 +281,7 @@ ice_gnss_write(struct gnss_device *gdev, const unsigned char *buf, if (!gnss) return -ENODEV; - cmd_buf = kcalloc(count, sizeof(*buf), GFP_KERNEL); - if (!cmd_buf) - return -ENOMEM; - - memcpy(cmd_buf, buf, count); - write_buf = kzalloc(sizeof(*write_buf), GFP_KERNEL); - if (!write_buf) { - kfree(cmd_buf); - return -ENOMEM; - } - - write_buf->buf = cmd_buf; - write_buf->size = count; - INIT_LIST_HEAD(&write_buf->queue); - list_add_tail(&write_buf->queue, &gnss->queue); - kthread_queue_work(gnss->kworker, &gnss->write_work); - - return err; + return ice_gnss_do_write(pf, buf, count); } static const struct gnss_operations ice_gnss_ops = { @@ -432,7 +377,6 @@ void ice_gnss_exit(struct ice_pf *pf) if (pf->gnss_serial) { struct gnss_serial *gnss = pf->gnss_serial; - kthread_cancel_work_sync(&gnss->write_work); kthread_cancel_delayed_work_sync(&gnss->read_work); kthread_destroy_worker(gnss->kworker); gnss->kworker = NULL; diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.h b/drivers/net/ethernet/intel/ice/ice_gnss.h index b8bb8b63d081..75e567ad7059 100644 --- a/drivers/net/ethernet/intel/ice/ice_gnss.h +++ b/drivers/net/ethernet/intel/ice/ice_gnss.h @@ -22,26 +22,16 @@ */ #define ICE_GNSS_UBX_WRITE_BYTES (ICE_MAX_I2C_WRITE_BYTES + 1) -struct gnss_write_buf { - struct list_head queue; - unsigned int size; - unsigned char *buf; -}; - /** * struct gnss_serial - data used to initialize GNSS TTY port * @back: back pointer to PF * @kworker: kwork thread for handling periodic work * @read_work: read_work function for handling GNSS reads - * @write_work: write_work function for handling GNSS writes - * @queue: write buffers queue */ struct gnss_serial { struct ice_pf *back; struct kthread_worker *kworker; struct kthread_delayed_work read_work; - struct kthread_work write_work; - struct list_head queue; }; #if IS_ENABLED(CONFIG_GNSS) diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c index e6bc2285071e..145b27f2a4ce 100644 --- a/drivers/net/ethernet/intel/ice/ice_idc.c +++ b/drivers/net/ethernet/intel/ice/ice_idc.c @@ -229,20 +229,34 @@ void ice_get_qos_params(struct ice_pf *pf, struct iidc_qos_params *qos) EXPORT_SYMBOL_GPL(ice_get_qos_params); /** - * ice_reserve_rdma_qvector - Reserve vector resources for RDMA driver + * ice_alloc_rdma_qvectors - Allocate vector resources for RDMA driver * @pf: board private structure to initialize */ -static int ice_reserve_rdma_qvector(struct ice_pf *pf) +static int ice_alloc_rdma_qvectors(struct ice_pf *pf) { if (ice_is_rdma_ena(pf)) { - int index; - - index = ice_get_res(pf, pf->irq_tracker, pf->num_rdma_msix, - ICE_RES_RDMA_VEC_ID); - if (index < 0) - return index; - pf->num_avail_sw_msix -= pf->num_rdma_msix; - pf->rdma_base_vector = (u16)index; + int i; + + pf->msix_entries = kcalloc(pf->num_rdma_msix, + sizeof(*pf->msix_entries), + GFP_KERNEL); + if (!pf->msix_entries) + return -ENOMEM; + + /* RDMA is the only user of pf->msix_entries array */ + pf->rdma_base_vector = 0; + + for (i = 0; i < pf->num_rdma_msix; i++) { + struct msix_entry *entry = &pf->msix_entries[i]; + struct msi_map map; + + map = ice_alloc_irq(pf, false); + if (map.index < 0) + break; + + entry->entry = map.index; + entry->vector = map.virq; + } } return 0; } @@ -253,9 +267,21 @@ static int ice_reserve_rdma_qvector(struct ice_pf *pf) */ static void ice_free_rdma_qvector(struct ice_pf *pf) { - pf->num_avail_sw_msix -= pf->num_rdma_msix; - ice_free_res(pf->irq_tracker, pf->rdma_base_vector, - ICE_RES_RDMA_VEC_ID); + int i; + + if (!pf->msix_entries) + return; + + for (i = 0; i < pf->num_rdma_msix; i++) { + struct msi_map map; + + map.index = pf->msix_entries[i].entry; + map.virq = pf->msix_entries[i].vector; + ice_free_irq(pf, map); + } + + kfree(pf->msix_entries); + pf->msix_entries = NULL; } /** @@ -357,7 +383,7 @@ int ice_init_rdma(struct ice_pf *pf) } /* Reserve vector resources */ - ret = ice_reserve_rdma_qvector(pf); + ret = ice_alloc_rdma_qvectors(pf); if (ret < 0) { dev_err(dev, "failed to reserve vectors for RDMA\n"); goto err_reserve_rdma_qvector; diff --git a/drivers/net/ethernet/intel/ice/ice_irq.c b/drivers/net/ethernet/intel/ice/ice_irq.c new file mode 100644 index 000000000000..ad82ff7d1995 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_irq.c @@ -0,0 +1,378 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023, Intel Corporation. */ + +#include "ice.h" +#include "ice_lib.h" +#include "ice_irq.h" + +/** + * ice_init_irq_tracker - initialize interrupt tracker + * @pf: board private structure + * @max_vectors: maximum number of vectors that tracker can hold + * @num_static: number of preallocated interrupts + */ +static void +ice_init_irq_tracker(struct ice_pf *pf, unsigned int max_vectors, + unsigned int num_static) +{ + pf->irq_tracker.num_entries = max_vectors; + pf->irq_tracker.num_static = num_static; + xa_init_flags(&pf->irq_tracker.entries, XA_FLAGS_ALLOC); +} + +/** + * ice_deinit_irq_tracker - free xarray tracker + * @pf: board private structure + */ +static void ice_deinit_irq_tracker(struct ice_pf *pf) +{ + xa_destroy(&pf->irq_tracker.entries); +} + +/** + * ice_free_irq_res - free a block of resources + * @pf: board private structure + * @index: starting index previously returned by ice_get_res + */ +static void ice_free_irq_res(struct ice_pf *pf, u16 index) +{ + struct ice_irq_entry *entry; + + entry = xa_erase(&pf->irq_tracker.entries, index); + kfree(entry); +} + +/** + * ice_get_irq_res - get an interrupt resource + * @pf: board private structure + * @dyn_only: force entry to be dynamically allocated + * + * Allocate new irq entry in the free slot of the tracker. Since xarray + * is used, always allocate new entry at the lowest possible index. Set + * proper allocation limit for maximum tracker entries. + * + * Returns allocated irq entry or NULL on failure. + */ +static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf, bool dyn_only) +{ + struct xa_limit limit = { .max = pf->irq_tracker.num_entries, + .min = 0 }; + unsigned int num_static = pf->irq_tracker.num_static; + struct ice_irq_entry *entry; + unsigned int index; + int ret; + + entry = kzalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + return NULL; + + /* skip preallocated entries if the caller says so */ + if (dyn_only) + limit.min = num_static; + + ret = xa_alloc(&pf->irq_tracker.entries, &index, entry, limit, + GFP_KERNEL); + + if (ret) { + kfree(entry); + entry = NULL; + } else { + entry->index = index; + entry->dynamic = index >= num_static; + } + + return entry; +} + +/** + * ice_reduce_msix_usage - Reduce usage of MSI-X vectors + * @pf: board private structure + * @v_remain: number of remaining MSI-X vectors to be distributed + * + * Reduce the usage of MSI-X vectors when entire request cannot be fulfilled. + * pf->num_lan_msix and pf->num_rdma_msix values are set based on number of + * remaining vectors. + */ +static void ice_reduce_msix_usage(struct ice_pf *pf, int v_remain) +{ + int v_rdma; + + if (!ice_is_rdma_ena(pf)) { + pf->num_lan_msix = v_remain; + return; + } + + /* RDMA needs at least 1 interrupt in addition to AEQ MSIX */ + v_rdma = ICE_RDMA_NUM_AEQ_MSIX + 1; + + if (v_remain < ICE_MIN_LAN_TXRX_MSIX + ICE_MIN_RDMA_MSIX) { + dev_warn(ice_pf_to_dev(pf), "Not enough MSI-X vectors to support RDMA.\n"); + clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); + + pf->num_rdma_msix = 0; + pf->num_lan_msix = ICE_MIN_LAN_TXRX_MSIX; + } else if ((v_remain < ICE_MIN_LAN_TXRX_MSIX + v_rdma) || + (v_remain - v_rdma < v_rdma)) { + /* Support minimum RDMA and give remaining vectors to LAN MSIX + */ + pf->num_rdma_msix = ICE_MIN_RDMA_MSIX; + pf->num_lan_msix = v_remain - ICE_MIN_RDMA_MSIX; + } else { + /* Split remaining MSIX with RDMA after accounting for AEQ MSIX + */ + pf->num_rdma_msix = (v_remain - ICE_RDMA_NUM_AEQ_MSIX) / 2 + + ICE_RDMA_NUM_AEQ_MSIX; + pf->num_lan_msix = v_remain - pf->num_rdma_msix; + } +} + +/** + * ice_ena_msix_range - Request a range of MSIX vectors from the OS + * @pf: board private structure + * + * Compute the number of MSIX vectors wanted and request from the OS. Adjust + * device usage if there are not enough vectors. Return the number of vectors + * reserved or negative on failure. + */ +static int ice_ena_msix_range(struct ice_pf *pf) +{ + int num_cpus, hw_num_msix, v_other, v_wanted, v_actual; + struct device *dev = ice_pf_to_dev(pf); + int err; + + hw_num_msix = pf->hw.func_caps.common_cap.num_msix_vectors; + num_cpus = num_online_cpus(); + + /* LAN miscellaneous handler */ + v_other = ICE_MIN_LAN_OICR_MSIX; + + /* Flow Director */ + if (test_bit(ICE_FLAG_FD_ENA, pf->flags)) + v_other += ICE_FDIR_MSIX; + + /* switchdev */ + v_other += ICE_ESWITCH_MSIX; + + v_wanted = v_other; + + /* LAN traffic */ + pf->num_lan_msix = num_cpus; + v_wanted += pf->num_lan_msix; + + /* RDMA auxiliary driver */ + if (ice_is_rdma_ena(pf)) { + pf->num_rdma_msix = num_cpus + ICE_RDMA_NUM_AEQ_MSIX; + v_wanted += pf->num_rdma_msix; + } + + if (v_wanted > hw_num_msix) { + int v_remain; + + dev_warn(dev, "not enough device MSI-X vectors. wanted = %d, available = %d\n", + v_wanted, hw_num_msix); + + if (hw_num_msix < ICE_MIN_MSIX) { + err = -ERANGE; + goto exit_err; + } + + v_remain = hw_num_msix - v_other; + if (v_remain < ICE_MIN_LAN_TXRX_MSIX) { + v_other = ICE_MIN_MSIX - ICE_MIN_LAN_TXRX_MSIX; + v_remain = ICE_MIN_LAN_TXRX_MSIX; + } + + ice_reduce_msix_usage(pf, v_remain); + v_wanted = pf->num_lan_msix + pf->num_rdma_msix + v_other; + + dev_notice(dev, "Reducing request to %d MSI-X vectors for LAN traffic.\n", + pf->num_lan_msix); + if (ice_is_rdma_ena(pf)) + dev_notice(dev, "Reducing request to %d MSI-X vectors for RDMA.\n", + pf->num_rdma_msix); + } + + /* actually reserve the vectors */ + v_actual = pci_alloc_irq_vectors(pf->pdev, ICE_MIN_MSIX, v_wanted, + PCI_IRQ_MSIX); + if (v_actual < 0) { + dev_err(dev, "unable to reserve MSI-X vectors\n"); + err = v_actual; + goto exit_err; + } + + if (v_actual < v_wanted) { + dev_warn(dev, "not enough OS MSI-X vectors. requested = %d, obtained = %d\n", + v_wanted, v_actual); + + if (v_actual < ICE_MIN_MSIX) { + /* error if we can't get minimum vectors */ + pci_free_irq_vectors(pf->pdev); + err = -ERANGE; + goto exit_err; + } else { + int v_remain = v_actual - v_other; + + if (v_remain < ICE_MIN_LAN_TXRX_MSIX) + v_remain = ICE_MIN_LAN_TXRX_MSIX; + + ice_reduce_msix_usage(pf, v_remain); + + dev_notice(dev, "Enabled %d MSI-X vectors for LAN traffic.\n", + pf->num_lan_msix); + + if (ice_is_rdma_ena(pf)) + dev_notice(dev, "Enabled %d MSI-X vectors for RDMA.\n", + pf->num_rdma_msix); + } + } + + return v_actual; + +exit_err: + pf->num_rdma_msix = 0; + pf->num_lan_msix = 0; + return err; +} + +/** + * ice_clear_interrupt_scheme - Undo things done by ice_init_interrupt_scheme + * @pf: board private structure + */ +void ice_clear_interrupt_scheme(struct ice_pf *pf) +{ + pci_free_irq_vectors(pf->pdev); + ice_deinit_irq_tracker(pf); +} + +/** + * ice_init_interrupt_scheme - Determine proper interrupt scheme + * @pf: board private structure to initialize + */ +int ice_init_interrupt_scheme(struct ice_pf *pf) +{ + int total_vectors = pf->hw.func_caps.common_cap.num_msix_vectors; + int vectors, max_vectors; + + vectors = ice_ena_msix_range(pf); + + if (vectors < 0) + return -ENOMEM; + + if (pci_msix_can_alloc_dyn(pf->pdev)) + max_vectors = total_vectors; + else + max_vectors = vectors; + + ice_init_irq_tracker(pf, max_vectors, vectors); + + return 0; +} + +/** + * ice_alloc_irq - Allocate new interrupt vector + * @pf: board private structure + * @dyn_only: force dynamic allocation of the interrupt + * + * Allocate new interrupt vector for a given owner id. + * return struct msi_map with interrupt details and track + * allocated interrupt appropriately. + * + * This function reserves new irq entry from the irq_tracker. + * if according to the tracker information all interrupts that + * were allocated with ice_pci_alloc_irq_vectors are already used + * and dynamically allocated interrupts are supported then new + * interrupt will be allocated with pci_msix_alloc_irq_at. + * + * Some callers may only support dynamically allocated interrupts. + * This is indicated with dyn_only flag. + * + * On failure, return map with negative .index. The caller + * is expected to check returned map index. + * + */ +struct msi_map ice_alloc_irq(struct ice_pf *pf, bool dyn_only) +{ + int sriov_base_vector = pf->sriov_base_vector; + struct msi_map map = { .index = -ENOENT }; + struct device *dev = ice_pf_to_dev(pf); + struct ice_irq_entry *entry; + + entry = ice_get_irq_res(pf, dyn_only); + if (!entry) + return map; + + /* fail if we're about to violate SRIOV vectors space */ + if (sriov_base_vector && entry->index >= sriov_base_vector) + goto exit_free_res; + + if (pci_msix_can_alloc_dyn(pf->pdev) && entry->dynamic) { + map = pci_msix_alloc_irq_at(pf->pdev, entry->index, NULL); + if (map.index < 0) + goto exit_free_res; + dev_dbg(dev, "allocated new irq at index %d\n", map.index); + } else { + map.index = entry->index; + map.virq = pci_irq_vector(pf->pdev, map.index); + } + + return map; + +exit_free_res: + dev_err(dev, "Could not allocate irq at idx %d\n", entry->index); + ice_free_irq_res(pf, entry->index); + return map; +} + +/** + * ice_free_irq - Free interrupt vector + * @pf: board private structure + * @map: map with interrupt details + * + * Remove allocated interrupt from the interrupt tracker. If interrupt was + * allocated dynamically, free respective interrupt vector. + */ +void ice_free_irq(struct ice_pf *pf, struct msi_map map) +{ + struct ice_irq_entry *entry; + + entry = xa_load(&pf->irq_tracker.entries, map.index); + + if (!entry) { + dev_err(ice_pf_to_dev(pf), "Failed to get MSIX interrupt entry at index %d", + map.index); + return; + } + + dev_dbg(ice_pf_to_dev(pf), "Free irq at index %d\n", map.index); + + if (entry->dynamic) + pci_msix_free_irq(pf->pdev, map); + + ice_free_irq_res(pf, map.index); +} + +/** + * ice_get_max_used_msix_vector - Get the max used interrupt vector + * @pf: board private structure + * + * Return index of maximum used interrupt vectors with respect to the + * beginning of the MSIX table. Take into account that some interrupts + * may have been dynamically allocated after MSIX was initially enabled. + */ +int ice_get_max_used_msix_vector(struct ice_pf *pf) +{ + unsigned long start, index, max_idx; + void *entry; + + /* Treat all preallocated interrupts as used */ + start = pf->irq_tracker.num_static; + max_idx = start - 1; + + xa_for_each_start(&pf->irq_tracker.entries, index, entry, start) { + if (index > max_idx) + max_idx = index; + } + + return max_idx; +} diff --git a/drivers/net/ethernet/intel/ice/ice_irq.h b/drivers/net/ethernet/intel/ice/ice_irq.h new file mode 100644 index 000000000000..f35efc08575e --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_irq.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2023, Intel Corporation. */ + +#ifndef _ICE_IRQ_H_ +#define _ICE_IRQ_H_ + +struct ice_irq_entry { + unsigned int index; + bool dynamic; /* allocation type flag */ +}; + +struct ice_irq_tracker { + struct xarray entries; + u16 num_entries; /* total vectors available */ + u16 num_static; /* preallocated entries */ +}; + +int ice_init_interrupt_scheme(struct ice_pf *pf); +void ice_clear_interrupt_scheme(struct ice_pf *pf); + +struct msi_map ice_alloc_irq(struct ice_pf *pf, bool dyn_only); +void ice_free_irq(struct ice_pf *pf, struct msi_map map); +int ice_get_max_used_msix_vector(struct ice_pf *pf); + +#endif diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c index ee5b36941ba3..5a7753bda324 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.c +++ b/drivers/net/ethernet/intel/ice/ice_lag.c @@ -7,15 +7,6 @@ #include "ice_lag.h" /** - * ice_lag_nop_handler - no-op Rx handler to disable LAG - * @pskb: pointer to skb pointer - */ -rx_handler_result_t ice_lag_nop_handler(struct sk_buff __always_unused **pskb) -{ - return RX_HANDLER_PASS; -} - -/** * ice_lag_set_primary - set PF LAG state as Primary * @lag: LAG info struct */ @@ -158,7 +149,6 @@ ice_lag_link(struct ice_lag *lag, struct netdev_notifier_changeupper_info *info) lag->upper_netdev = upper; } - ice_clear_sriov_cap(pf); ice_clear_rdma_cap(pf); lag->bonded = true; @@ -205,7 +195,6 @@ ice_lag_unlink(struct ice_lag *lag, } lag->peer_netdev = NULL; - ice_set_sriov_cap(pf); ice_set_rdma_cap(pf); lag->bonded = false; lag->role = ICE_LAG_NONE; @@ -229,7 +218,6 @@ static void ice_lag_unregister(struct ice_lag *lag, struct net_device *netdev) if (lag->upper_netdev) { dev_put(lag->upper_netdev); lag->upper_netdev = NULL; - ice_set_sriov_cap(pf); ice_set_rdma_cap(pf); } /* perform some cleanup in case we come back */ diff --git a/drivers/net/ethernet/intel/ice/ice_lag.h b/drivers/net/ethernet/intel/ice/ice_lag.h index 51b5cf467ce2..2c373676c42f 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.h +++ b/drivers/net/ethernet/intel/ice/ice_lag.h @@ -25,63 +25,9 @@ struct ice_lag { struct notifier_block notif_block; u8 bonded:1; /* currently bonded */ u8 primary:1; /* this is primary */ - u8 handler:1; /* did we register a rx_netdev_handler */ - /* each thing blocking bonding will increment this value by one. - * If this value is zero, then bonding is allowed. - */ - u16 dis_lag; u8 role; }; int ice_init_lag(struct ice_pf *pf); void ice_deinit_lag(struct ice_pf *pf); -rx_handler_result_t ice_lag_nop_handler(struct sk_buff **pskb); - -/** - * ice_disable_lag - increment LAG disable count - * @lag: LAG struct - */ -static inline void ice_disable_lag(struct ice_lag *lag) -{ - /* If LAG this PF is not already disabled, disable it */ - rtnl_lock(); - if (!netdev_is_rx_handler_busy(lag->netdev)) { - if (!netdev_rx_handler_register(lag->netdev, - ice_lag_nop_handler, - NULL)) - lag->handler = true; - } - rtnl_unlock(); - lag->dis_lag++; -} - -/** - * ice_enable_lag - decrement disable count for a PF - * @lag: LAG struct - * - * Decrement the disable counter for a port, and if that count reaches - * zero, then remove the no-op Rx handler from that netdev - */ -static inline void ice_enable_lag(struct ice_lag *lag) -{ - if (lag->dis_lag) - lag->dis_lag--; - if (!lag->dis_lag && lag->handler) { - rtnl_lock(); - netdev_rx_handler_unregister(lag->netdev); - rtnl_unlock(); - lag->handler = false; - } -} - -/** - * ice_is_lag_dis - is LAG disabled - * @lag: LAG struct - * - * Return true if bonding is disabled - */ -static inline bool ice_is_lag_dis(struct ice_lag *lag) -{ - return !!(lag->dis_lag); -} #endif /* _ICE_LAG_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 450317dfcca7..5ddb95d1073a 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -1371,190 +1371,6 @@ out: } /** - * ice_free_res - free a block of resources - * @res: pointer to the resource - * @index: starting index previously returned by ice_get_res - * @id: identifier to track owner - * - * Returns number of resources freed - */ -int ice_free_res(struct ice_res_tracker *res, u16 index, u16 id) -{ - int count = 0; - int i; - - if (!res || index >= res->end) - return -EINVAL; - - id |= ICE_RES_VALID_BIT; - for (i = index; i < res->end && res->list[i] == id; i++) { - res->list[i] = 0; - count++; - } - - return count; -} - -/** - * ice_search_res - Search the tracker for a block of resources - * @res: pointer to the resource - * @needed: size of the block needed - * @id: identifier to track owner - * - * Returns the base item index of the block, or -ENOMEM for error - */ -static int ice_search_res(struct ice_res_tracker *res, u16 needed, u16 id) -{ - u16 start = 0, end = 0; - - if (needed > res->end) - return -ENOMEM; - - id |= ICE_RES_VALID_BIT; - - do { - /* skip already allocated entries */ - if (res->list[end++] & ICE_RES_VALID_BIT) { - start = end; - if ((start + needed) > res->end) - break; - } - - if (end == (start + needed)) { - int i = start; - - /* there was enough, so assign it to the requestor */ - while (i != end) - res->list[i++] = id; - - return start; - } - } while (end < res->end); - - return -ENOMEM; -} - -/** - * ice_get_free_res_count - Get free count from a resource tracker - * @res: Resource tracker instance - */ -static u16 ice_get_free_res_count(struct ice_res_tracker *res) -{ - u16 i, count = 0; - - for (i = 0; i < res->end; i++) - if (!(res->list[i] & ICE_RES_VALID_BIT)) - count++; - - return count; -} - -/** - * ice_get_res - get a block of resources - * @pf: board private structure - * @res: pointer to the resource - * @needed: size of the block needed - * @id: identifier to track owner - * - * Returns the base item index of the block, or negative for error - */ -int -ice_get_res(struct ice_pf *pf, struct ice_res_tracker *res, u16 needed, u16 id) -{ - if (!res || !pf) - return -EINVAL; - - if (!needed || needed > res->num_entries || id >= ICE_RES_VALID_BIT) { - dev_err(ice_pf_to_dev(pf), "param err: needed=%d, num_entries = %d id=0x%04x\n", - needed, res->num_entries, id); - return -EINVAL; - } - - return ice_search_res(res, needed, id); -} - -/** - * ice_get_vf_ctrl_res - Get VF control VSI resource - * @pf: pointer to the PF structure - * @vsi: the VSI to allocate a resource for - * - * Look up whether another VF has already allocated the control VSI resource. - * If so, re-use this resource so that we share it among all VFs. - * - * Otherwise, allocate the resource and return it. - */ -static int ice_get_vf_ctrl_res(struct ice_pf *pf, struct ice_vsi *vsi) -{ - struct ice_vf *vf; - unsigned int bkt; - int base; - - rcu_read_lock(); - ice_for_each_vf_rcu(pf, bkt, vf) { - if (vf != vsi->vf && vf->ctrl_vsi_idx != ICE_NO_VSI) { - base = pf->vsi[vf->ctrl_vsi_idx]->base_vector; - rcu_read_unlock(); - return base; - } - } - rcu_read_unlock(); - - return ice_get_res(pf, pf->irq_tracker, vsi->num_q_vectors, - ICE_RES_VF_CTRL_VEC_ID); -} - -/** - * ice_vsi_setup_vector_base - Set up the base vector for the given VSI - * @vsi: ptr to the VSI - * - * This should only be called after ice_vsi_alloc_def() which allocates the - * corresponding SW VSI structure and initializes num_queue_pairs for the - * newly allocated VSI. - * - * Returns 0 on success or negative on failure - */ -static int ice_vsi_setup_vector_base(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - struct device *dev; - u16 num_q_vectors; - int base; - - dev = ice_pf_to_dev(pf); - /* SRIOV doesn't grab irq_tracker entries for each VSI */ - if (vsi->type == ICE_VSI_VF) - return 0; - if (vsi->type == ICE_VSI_CHNL) - return 0; - - if (vsi->base_vector) { - dev_dbg(dev, "VSI %d has non-zero base vector %d\n", - vsi->vsi_num, vsi->base_vector); - return -EEXIST; - } - - num_q_vectors = vsi->num_q_vectors; - /* reserve slots from OS requested IRQs */ - if (vsi->type == ICE_VSI_CTRL && vsi->vf) { - base = ice_get_vf_ctrl_res(pf, vsi); - } else { - base = ice_get_res(pf, pf->irq_tracker, num_q_vectors, - vsi->idx); - } - - if (base < 0) { - dev_err(dev, "%d MSI-X interrupts available. %s %d failed to get %d MSI-X vectors\n", - ice_get_free_res_count(pf->irq_tracker), - ice_vsi_type_str(vsi->type), vsi->idx, num_q_vectors); - return -ENOENT; - } - vsi->base_vector = (u16)base; - pf->num_avail_sw_msix -= num_q_vectors; - - return 0; -} - -/** * ice_vsi_clear_rings - Deallocates the Tx and Rx rings for VSI * @vsi: the VSI having rings deallocated */ @@ -2410,50 +2226,6 @@ static void ice_vsi_set_tc_cfg(struct ice_vsi *vsi) } /** - * ice_vsi_set_q_vectors_reg_idx - set the HW register index for all q_vectors - * @vsi: VSI to set the q_vectors register index on - */ -static int -ice_vsi_set_q_vectors_reg_idx(struct ice_vsi *vsi) -{ - u16 i; - - if (!vsi || !vsi->q_vectors) - return -EINVAL; - - ice_for_each_q_vector(vsi, i) { - struct ice_q_vector *q_vector = vsi->q_vectors[i]; - - if (!q_vector) { - dev_err(ice_pf_to_dev(vsi->back), "Failed to set reg_idx on q_vector %d VSI %d\n", - i, vsi->vsi_num); - goto clear_reg_idx; - } - - if (vsi->type == ICE_VSI_VF) { - struct ice_vf *vf = vsi->vf; - - q_vector->reg_idx = ice_calc_vf_reg_idx(vf, q_vector); - } else { - q_vector->reg_idx = - q_vector->v_idx + vsi->base_vector; - } - } - - return 0; - -clear_reg_idx: - ice_for_each_q_vector(vsi, i) { - struct ice_q_vector *q_vector = vsi->q_vectors[i]; - - if (q_vector) - q_vector->reg_idx = 0; - } - - return -EINVAL; -} - -/** * ice_cfg_sw_lldp - Config switch rules for LLDP packet handling * @vsi: the VSI being configured * @tx: bool to determine Tx or Rx rule @@ -2611,37 +2383,6 @@ static void ice_set_agg_vsi(struct ice_vsi *vsi) vsi->agg_node->num_vsis); } -/** - * ice_free_vf_ctrl_res - Free the VF control VSI resource - * @pf: pointer to PF structure - * @vsi: the VSI to free resources for - * - * Check if the VF control VSI resource is still in use. If no VF is using it - * any more, release the VSI resource. Otherwise, leave it to be cleaned up - * once no other VF uses it. - */ -static void ice_free_vf_ctrl_res(struct ice_pf *pf, struct ice_vsi *vsi) -{ - struct ice_vf *vf; - unsigned int bkt; - - rcu_read_lock(); - ice_for_each_vf_rcu(pf, bkt, vf) { - if (vf != vsi->vf && vf->ctrl_vsi_idx != ICE_NO_VSI) { - rcu_read_unlock(); - return; - } - } - rcu_read_unlock(); - - /* No other VFs left that have control VSI. It is now safe to reclaim - * SW interrupts back to the common pool. - */ - ice_free_res(pf->irq_tracker, vsi->base_vector, - ICE_RES_VF_CTRL_VEC_ID); - pf->num_avail_sw_msix += vsi->num_q_vectors; -} - static int ice_vsi_cfg_tc_lan(struct ice_pf *pf, struct ice_vsi *vsi) { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; @@ -2728,14 +2469,6 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) if (ret) goto unroll_vsi_init; - ret = ice_vsi_setup_vector_base(vsi); - if (ret) - goto unroll_alloc_q_vector; - - ret = ice_vsi_set_q_vectors_reg_idx(vsi); - if (ret) - goto unroll_vector_base; - ret = ice_vsi_alloc_rings(vsi); if (ret) goto unroll_vector_base; @@ -2745,6 +2478,8 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) goto unroll_vector_base; ice_vsi_map_rings_to_vectors(vsi); + vsi->stat_offsets_loaded = false; + if (ice_is_xdp_ena_vsi(vsi)) { ret = ice_vsi_determine_xdp_res(vsi); if (ret) @@ -2786,13 +2521,12 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) if (ret) goto unroll_alloc_q_vector; - ret = ice_vsi_set_q_vectors_reg_idx(vsi); - if (ret) - goto unroll_vector_base; - ret = ice_vsi_alloc_ring_stats(vsi); if (ret) goto unroll_vector_base; + + vsi->stat_offsets_loaded = false; + /* Do not exit if configuring RSS had an issue, at least * receive traffic on first queue. Hence no need to capture * return value @@ -2822,8 +2556,6 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) unroll_vector_base: /* reclaim SW interrupts back to the common pool */ - ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx); - pf->num_avail_sw_msix += vsi->num_q_vectors; unroll_alloc_q_vector: ice_vsi_free_q_vectors(vsi); unroll_vsi_init: @@ -2915,14 +2647,6 @@ void ice_vsi_decfg(struct ice_vsi *vsi) * many interrupts each VF needs. SR-IOV MSIX resources are also * cleared in the same manner. */ - if (vsi->type == ICE_VSI_CTRL && vsi->vf) { - ice_free_vf_ctrl_res(pf, vsi); - } else if (vsi->type != ICE_VSI_VF) { - /* reclaim SW interrupts back to the common pool */ - ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx); - pf->num_avail_sw_msix += vsi->num_q_vectors; - vsi->base_vector = 0; - } if (vsi->type == ICE_VSI_VF && vsi->agg_node && vsi->agg_node->valid) @@ -2988,8 +2712,6 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params) return vsi; err_vsi_cfg: - if (params->type == ICE_VSI_VF) - ice_enable_lag(pf->lag); ice_vsi_free(vsi); return NULL; @@ -3039,7 +2761,6 @@ static void ice_vsi_release_msix(struct ice_vsi *vsi) void ice_vsi_free_irq(struct ice_vsi *vsi) { struct ice_pf *pf = vsi->back; - int base = vsi->base_vector; int i; if (!vsi->q_vectors || !vsi->irqs_ready) @@ -3053,10 +2774,9 @@ void ice_vsi_free_irq(struct ice_vsi *vsi) ice_free_cpu_rx_rmap(vsi); ice_for_each_q_vector(vsi, i) { - u16 vector = i + base; int irq_num; - irq_num = pf->msix_entries[vector].vector; + irq_num = vsi->q_vectors[i]->irq.virq; /* free only the irqs that were actually requested */ if (!vsi->q_vectors[i] || @@ -3188,7 +2908,6 @@ void ice_dis_vsi(struct ice_vsi *vsi, bool locked) */ void ice_vsi_dis_irq(struct ice_vsi *vsi) { - int base = vsi->base_vector; struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; u32 val; @@ -3235,7 +2954,7 @@ void ice_vsi_dis_irq(struct ice_vsi *vsi) return; ice_for_each_q_vector(vsi, i) - synchronize_irq(pf->msix_entries[i + base].vector); + synchronize_irq(vsi->q_vectors[i]->irq.virq); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index 75221478f2dc..e985766e6bb5 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -104,11 +104,6 @@ int ice_ena_vsi(struct ice_vsi *vsi, bool locked); void ice_vsi_decfg(struct ice_vsi *vsi); void ice_dis_vsi(struct ice_vsi *vsi, bool locked); -int ice_free_res(struct ice_res_tracker *res, u16 index, u16 id); - -int -ice_get_res(struct ice_pf *pf, struct ice_res_tracker *res, u16 needed, u16 id); - int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags); int ice_vsi_cfg(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index a1f7c8edc22f..62e91512aeab 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2490,7 +2490,6 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) { int q_vectors = vsi->num_q_vectors; struct ice_pf *pf = vsi->back; - int base = vsi->base_vector; struct device *dev; int rx_int_idx = 0; int tx_int_idx = 0; @@ -2501,7 +2500,7 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) for (vector = 0; vector < q_vectors; vector++) { struct ice_q_vector *q_vector = vsi->q_vectors[vector]; - irq_num = pf->msix_entries[base + vector].vector; + irq_num = q_vector->irq.virq; if (q_vector->tx.tx_ring && q_vector->rx.rx_ring) { snprintf(q_vector->name, sizeof(q_vector->name) - 1, @@ -2555,9 +2554,8 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) return 0; free_q_irqs: - while (vector) { - vector--; - irq_num = pf->msix_entries[base + vector].vector; + while (vector--) { + irq_num = vsi->q_vectors[vector]->irq.virq; if (!IS_ENABLED(CONFIG_RFS_ACCEL)) irq_set_affinity_notifier(irq_num, NULL); irq_set_affinity_hint(irq_num, NULL); @@ -3047,7 +3045,7 @@ static void ice_ena_misc_vector(struct ice_pf *pf) wr32(hw, PFINT_OICR_ENA, val); /* SW_ITR_IDX = 0, but don't change INTENA */ - wr32(hw, GLINT_DYN_CTL(pf->oicr_idx), + wr32(hw, GLINT_DYN_CTL(pf->oicr_irq.index), GLINT_DYN_CTL_SW_ITR_INDX_M | GLINT_DYN_CTL_INTENA_MSK_M); } @@ -3234,6 +3232,7 @@ static void ice_dis_ctrlq_interrupts(struct ice_hw *hw) */ static void ice_free_irq_msix_misc(struct ice_pf *pf) { + int misc_irq_num = pf->oicr_irq.virq; struct ice_hw *hw = &pf->hw; ice_dis_ctrlq_interrupts(hw); @@ -3242,14 +3241,10 @@ static void ice_free_irq_msix_misc(struct ice_pf *pf) wr32(hw, PFINT_OICR_ENA, 0); ice_flush(hw); - if (pf->msix_entries) { - synchronize_irq(pf->msix_entries[pf->oicr_idx].vector); - devm_free_irq(ice_pf_to_dev(pf), - pf->msix_entries[pf->oicr_idx].vector, pf); - } + synchronize_irq(misc_irq_num); + devm_free_irq(ice_pf_to_dev(pf), misc_irq_num, pf); - pf->num_avail_sw_msix += 1; - ice_free_res(pf->irq_tracker, pf->oicr_idx, ICE_RES_MISC_VEC_ID); + ice_free_irq(pf, pf->oicr_irq); } /** @@ -3295,7 +3290,8 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf) { struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; - int oicr_idx, err = 0; + struct msi_map oicr_irq; + int err = 0; if (!pf->int_name[0]) snprintf(pf->int_name, sizeof(pf->int_name) - 1, "%s-%s:misc", @@ -3309,30 +3305,26 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf) goto skip_req_irq; /* reserve one vector in irq_tracker for misc interrupts */ - oicr_idx = ice_get_res(pf, pf->irq_tracker, 1, ICE_RES_MISC_VEC_ID); - if (oicr_idx < 0) - return oicr_idx; - - pf->num_avail_sw_msix -= 1; - pf->oicr_idx = (u16)oicr_idx; - - err = devm_request_threaded_irq(dev, - pf->msix_entries[pf->oicr_idx].vector, - ice_misc_intr, ice_misc_intr_thread_fn, - 0, pf->int_name, pf); + oicr_irq = ice_alloc_irq(pf, false); + if (oicr_irq.index < 0) + return oicr_irq.index; + + pf->oicr_irq = oicr_irq; + err = devm_request_threaded_irq(dev, pf->oicr_irq.virq, ice_misc_intr, + ice_misc_intr_thread_fn, 0, + pf->int_name, pf); if (err) { dev_err(dev, "devm_request_threaded_irq for %s failed: %d\n", pf->int_name, err); - ice_free_res(pf->irq_tracker, 1, ICE_RES_MISC_VEC_ID); - pf->num_avail_sw_msix += 1; + ice_free_irq(pf, pf->oicr_irq); return err; } skip_req_irq: ice_ena_misc_vector(pf); - ice_ena_ctrlq_interrupts(hw, pf->oicr_idx); - wr32(hw, GLINT_ITR(ICE_RX_ITR, pf->oicr_idx), + ice_ena_ctrlq_interrupts(hw, pf->oicr_irq.index); + wr32(hw, GLINT_ITR(ICE_RX_ITR, pf->oicr_irq.index), ITR_REG_ALIGN(ICE_ITR_8K) >> ICE_ITR_GRAN_S); ice_flush(hw); @@ -3901,224 +3893,6 @@ static int ice_init_pf(struct ice_pf *pf) } /** - * ice_reduce_msix_usage - Reduce usage of MSI-X vectors - * @pf: board private structure - * @v_remain: number of remaining MSI-X vectors to be distributed - * - * Reduce the usage of MSI-X vectors when entire request cannot be fulfilled. - * pf->num_lan_msix and pf->num_rdma_msix values are set based on number of - * remaining vectors. - */ -static void ice_reduce_msix_usage(struct ice_pf *pf, int v_remain) -{ - int v_rdma; - - if (!ice_is_rdma_ena(pf)) { - pf->num_lan_msix = v_remain; - return; - } - - /* RDMA needs at least 1 interrupt in addition to AEQ MSIX */ - v_rdma = ICE_RDMA_NUM_AEQ_MSIX + 1; - - if (v_remain < ICE_MIN_LAN_TXRX_MSIX + ICE_MIN_RDMA_MSIX) { - dev_warn(ice_pf_to_dev(pf), "Not enough MSI-X vectors to support RDMA.\n"); - clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); - - pf->num_rdma_msix = 0; - pf->num_lan_msix = ICE_MIN_LAN_TXRX_MSIX; - } else if ((v_remain < ICE_MIN_LAN_TXRX_MSIX + v_rdma) || - (v_remain - v_rdma < v_rdma)) { - /* Support minimum RDMA and give remaining vectors to LAN MSIX */ - pf->num_rdma_msix = ICE_MIN_RDMA_MSIX; - pf->num_lan_msix = v_remain - ICE_MIN_RDMA_MSIX; - } else { - /* Split remaining MSIX with RDMA after accounting for AEQ MSIX - */ - pf->num_rdma_msix = (v_remain - ICE_RDMA_NUM_AEQ_MSIX) / 2 + - ICE_RDMA_NUM_AEQ_MSIX; - pf->num_lan_msix = v_remain - pf->num_rdma_msix; - } -} - -/** - * ice_ena_msix_range - Request a range of MSIX vectors from the OS - * @pf: board private structure - * - * Compute the number of MSIX vectors wanted and request from the OS. Adjust - * device usage if there are not enough vectors. Return the number of vectors - * reserved or negative on failure. - */ -static int ice_ena_msix_range(struct ice_pf *pf) -{ - int num_cpus, hw_num_msix, v_other, v_wanted, v_actual; - struct device *dev = ice_pf_to_dev(pf); - int err, i; - - hw_num_msix = pf->hw.func_caps.common_cap.num_msix_vectors; - num_cpus = num_online_cpus(); - - /* LAN miscellaneous handler */ - v_other = ICE_MIN_LAN_OICR_MSIX; - - /* Flow Director */ - if (test_bit(ICE_FLAG_FD_ENA, pf->flags)) - v_other += ICE_FDIR_MSIX; - - /* switchdev */ - v_other += ICE_ESWITCH_MSIX; - - v_wanted = v_other; - - /* LAN traffic */ - pf->num_lan_msix = num_cpus; - v_wanted += pf->num_lan_msix; - - /* RDMA auxiliary driver */ - if (ice_is_rdma_ena(pf)) { - pf->num_rdma_msix = num_cpus + ICE_RDMA_NUM_AEQ_MSIX; - v_wanted += pf->num_rdma_msix; - } - - if (v_wanted > hw_num_msix) { - int v_remain; - - dev_warn(dev, "not enough device MSI-X vectors. wanted = %d, available = %d\n", - v_wanted, hw_num_msix); - - if (hw_num_msix < ICE_MIN_MSIX) { - err = -ERANGE; - goto exit_err; - } - - v_remain = hw_num_msix - v_other; - if (v_remain < ICE_MIN_LAN_TXRX_MSIX) { - v_other = ICE_MIN_MSIX - ICE_MIN_LAN_TXRX_MSIX; - v_remain = ICE_MIN_LAN_TXRX_MSIX; - } - - ice_reduce_msix_usage(pf, v_remain); - v_wanted = pf->num_lan_msix + pf->num_rdma_msix + v_other; - - dev_notice(dev, "Reducing request to %d MSI-X vectors for LAN traffic.\n", - pf->num_lan_msix); - if (ice_is_rdma_ena(pf)) - dev_notice(dev, "Reducing request to %d MSI-X vectors for RDMA.\n", - pf->num_rdma_msix); - } - - pf->msix_entries = devm_kcalloc(dev, v_wanted, - sizeof(*pf->msix_entries), GFP_KERNEL); - if (!pf->msix_entries) { - err = -ENOMEM; - goto exit_err; - } - - for (i = 0; i < v_wanted; i++) - pf->msix_entries[i].entry = i; - - /* actually reserve the vectors */ - v_actual = pci_enable_msix_range(pf->pdev, pf->msix_entries, - ICE_MIN_MSIX, v_wanted); - if (v_actual < 0) { - dev_err(dev, "unable to reserve MSI-X vectors\n"); - err = v_actual; - goto msix_err; - } - - if (v_actual < v_wanted) { - dev_warn(dev, "not enough OS MSI-X vectors. requested = %d, obtained = %d\n", - v_wanted, v_actual); - - if (v_actual < ICE_MIN_MSIX) { - /* error if we can't get minimum vectors */ - pci_disable_msix(pf->pdev); - err = -ERANGE; - goto msix_err; - } else { - int v_remain = v_actual - v_other; - - if (v_remain < ICE_MIN_LAN_TXRX_MSIX) - v_remain = ICE_MIN_LAN_TXRX_MSIX; - - ice_reduce_msix_usage(pf, v_remain); - - dev_notice(dev, "Enabled %d MSI-X vectors for LAN traffic.\n", - pf->num_lan_msix); - - if (ice_is_rdma_ena(pf)) - dev_notice(dev, "Enabled %d MSI-X vectors for RDMA.\n", - pf->num_rdma_msix); - } - } - - return v_actual; - -msix_err: - devm_kfree(dev, pf->msix_entries); - -exit_err: - pf->num_rdma_msix = 0; - pf->num_lan_msix = 0; - return err; -} - -/** - * ice_dis_msix - Disable MSI-X interrupt setup in OS - * @pf: board private structure - */ -static void ice_dis_msix(struct ice_pf *pf) -{ - pci_disable_msix(pf->pdev); - devm_kfree(ice_pf_to_dev(pf), pf->msix_entries); - pf->msix_entries = NULL; -} - -/** - * ice_clear_interrupt_scheme - Undo things done by ice_init_interrupt_scheme - * @pf: board private structure - */ -static void ice_clear_interrupt_scheme(struct ice_pf *pf) -{ - ice_dis_msix(pf); - - if (pf->irq_tracker) { - devm_kfree(ice_pf_to_dev(pf), pf->irq_tracker); - pf->irq_tracker = NULL; - } -} - -/** - * ice_init_interrupt_scheme - Determine proper interrupt scheme - * @pf: board private structure to initialize - */ -static int ice_init_interrupt_scheme(struct ice_pf *pf) -{ - int vectors; - - vectors = ice_ena_msix_range(pf); - - if (vectors < 0) - return vectors; - - /* set up vector assignment tracking */ - pf->irq_tracker = devm_kzalloc(ice_pf_to_dev(pf), - struct_size(pf->irq_tracker, list, vectors), - GFP_KERNEL); - if (!pf->irq_tracker) { - ice_dis_msix(pf); - return -ENOMEM; - } - - /* populate SW interrupts pool with number of OS granted IRQs. */ - pf->num_avail_sw_msix = (u16)vectors; - pf->irq_tracker->num_entries = (u16)vectors; - pf->irq_tracker->end = pf->irq_tracker->num_entries; - - return 0; -} - -/** * ice_is_wol_supported - check if WoL is supported * @hw: pointer to hardware info * diff --git a/drivers/net/ethernet/intel/ice/ice_protocol_type.h b/drivers/net/ethernet/intel/ice/ice_protocol_type.h index 02a4e1cf624e..6a9364761165 100644 --- a/drivers/net/ethernet/intel/ice/ice_protocol_type.h +++ b/drivers/net/ethernet/intel/ice/ice_protocol_type.h @@ -47,6 +47,7 @@ enum ice_protocol_type { ICE_L2TPV3, ICE_VLAN_EX, ICE_VLAN_IN, + ICE_HW_METADATA, ICE_VXLAN_GPE, ICE_SCTP_IL, ICE_PROTOCOL_LAST @@ -115,17 +116,7 @@ enum ice_prot_id { #define ICE_L2TPV3_HW 104 #define ICE_UDP_OF_HW 52 /* UDP Tunnels */ -#define ICE_META_DATA_ID_HW 255 /* this is used for tunnel and VLAN type */ -#define ICE_MDID_SIZE 2 - -#define ICE_TUN_FLAG_MDID 21 -#define ICE_TUN_FLAG_MDID_OFF (ICE_MDID_SIZE * ICE_TUN_FLAG_MDID) -#define ICE_TUN_FLAG_MASK 0xFF - -#define ICE_VLAN_FLAG_MDID 20 -#define ICE_VLAN_FLAG_MDID_OFF (ICE_MDID_SIZE * ICE_VLAN_FLAG_MDID) -#define ICE_PKT_FLAGS_0_TO_15_VLAN_FLAGS_MASK 0xD000 #define ICE_TUN_FLAG_FV_IND 2 @@ -230,6 +221,191 @@ struct ice_nvgre_hdr { __be32 tni_flow; }; +/* Metadata information + * + * Not all MDIDs can be used by switch block. It depends on package version. + * + * MDID 16 (Rx offset) + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | A | B | Reserved | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * + * A = Source port where the transaction came from (3b). + * + * B = Destination TC of the packet. The TC is relative to a port (5b). + * + * MDID 17 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | PTYPE | Reserved | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * + * PTYPE = Encodes the packet type (10b). + * + * MDID 18 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Packet length | R | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * + * Packet length = Length of the packet in bytes + * (packet always carriers CRC) (14b). + * R = Reserved (2b). + * + * MDID 19 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Source VSI | Reserved | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * + * Source VSI = Source VSI of packet loopbacked in switch (for egress) (10b). + */ +#define ICE_MDID_SOURCE_VSI_MASK GENMASK(9, 0) + +/* + * MDID 20 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * |A|B|C|D|E|F|R|R|G|H|I|J|K|L|M|N| + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * + * A = DSI - set for DSI RX pkts. + * B = ipsec_decrypted - invalid on NIC. + * C = marker - this is a marker packet. + * D = from_network - for TX sets to 0 + * for RX: + * * 1 - packet is from external link + * * 0 - packet source is from internal + * E = source_interface_is_rx - reflect the physical interface from where the + * packet was received: + * * 1 - Rx + * * 0 - Tx + * F = from_mng - The bit signals that the packet's origin is the management. + * G = ucast - Outer L2 MAC address is unicast. + * H = mcast - Outer L2 MAC address is multicast. + * I = bcast - Outer L2 MAC address is broadcast. + * J = second_outer_mac_present - 2 outer MAC headers are present in the packet. + * K = STAG or BVLAN - Outer L2 header has STAG (ethernet type 0x88a8) or + * BVLAN (ethernet type 0x88a8). + * L = ITAG - Outer L2 header has ITAG *ethernet type 0x88e7) + * M = EVLAN (0x8100) - Outer L2 header has EVLAN (ethernet type 0x8100) + * N = EVLAN (0x9100) - Outer L2 header has EVLAN (ethernet type 0x9100) + */ +#define ICE_PKT_VLAN_STAG BIT(12) +#define ICE_PKT_VLAN_ITAG BIT(13) +#define ICE_PKT_VLAN_EVLAN (BIT(14) | BIT(15)) +#define ICE_PKT_VLAN_MASK (ICE_PKT_VLAN_STAG | ICE_PKT_VLAN_ITAG | \ + ICE_PKT_VLAN_EVLAN) +/* MDID 21 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * |A|B|C|D|E|F|G|H|I|J|R|R|K|L|M|N| + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * + * A = VLAN (0x8100) - Outer L2 header has VLAN (ethernet type 0x8100) + * B = NSHoE - Outer L2 header has NSH (ethernet type 0x894f) + * C = MPLS (0x8847) - There is at least 1 MPLS tag in the outer header + * (ethernet type 0x8847) + * D = MPLS (0x8848) - There is at least 1 MPLS tag in the outer header + * (ethernet type 0x8848) + * E = multi MPLS - There is more than a single MPLS tag in the outer header + * F = inner MPLS - There is inner MPLS tag in the packet + * G = tunneled MAC - Set if the packet includes a tunneled MAC + * H = tunneled VLAN - Same as VLAN, but for a tunneled header + * I = pkt_is_frag - Packet is fragmented (ipv4 or ipv6) + * J = ipv6_ext - The packet has routing or destination ipv6 extension in inner + * or outer ipv6 headers + * K = RoCE - UDP packet detected as RoCEv2 + * L = UDP_XSUM_0 - Set to 1 if L4 checksum is 0 in a UDP packet + * M = ESP - This is a ESP packet + * N = NAT_ESP - This is a ESP packet encapsulated in UDP NAT + */ +#define ICE_PKT_TUNNEL_MAC BIT(6) +#define ICE_PKT_TUNNEL_VLAN BIT(7) +#define ICE_PKT_TUNNEL_MASK (ICE_PKT_TUNNEL_MAC | ICE_PKT_TUNNEL_VLAN) + +/* MDID 22 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * |A|B|C|D|E|F| G |H|I|J| K |L|M| + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * + * A = fin - fin flag in tcp header + * B = sync - sync flag in tcp header + * C = rst - rst flag in tcp header + * D = psh - psh flag in tcp header + * E = ack - ack flag in tcp header + * F = urg - urg flag in tcp header + * G = tunnel type (3b) - Flags used to decode tunnel type: + * * b000 - not a VXLAN/Geneve/GRE tunnel + * * b001 - VXLAN-GPE + * * b010 - VXLAN (non-GPE) + * * b011 - Geneve + * * b100 - GRE (no key, no xsum) + * * b101 - GREK (key, no xsum) + * * b110 - GREC (no key, xsum) + * * b111 - GREKC (key, xsum) + * H = UDP_GRE - Packet is UDP (VXLAN or VLAN_GPE or Geneve or MPLSoUDP or GRE) + * tunnel + * I = OAM - VXLAN/Geneve/tunneled NSH packet with the OAM bit set + * J = tunneled NSH - Packet has NSHoGRE or NSHoUDP + * K = switch (2b) - Direction on switch + * * b00 - normal + * * b01 - TX force only LAN + * * b10 - TX disable LAN + * * b11 - direct to VSI + * L = swpe - Represents SWPE bit in TX command + * M = sw_cmd - Switch command + * + * MDID 23 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * |A|B|C|D| R |E|F|R| + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * + * A = MAC error - Produced by MAC according to L2 error conditions + * B = PPRS no offload - FIFO overflow in PPRS or any problematic condition in + * PPRS ANA + * C = abort - Set when malicious packet is detected + * D = partial analysis - ANA's analysing got cut in the middle + * (header > 504B etc.) + * E = FLM - Flow director hit indication + * F = FDLONG - Flow direector long bucket indication + * + */ +#define ICE_MDID_SIZE 2 +#define ICE_META_DATA_ID_HW 255 + +enum ice_hw_metadata_id { + ICE_SOURCE_PORT_MDID = 16, + ICE_PTYPE_MDID = 17, + ICE_PACKET_LENGTH_MDID = 18, + ICE_SOURCE_VSI_MDID = 19, + ICE_PKT_VLAN_MDID = 20, + ICE_PKT_TUNNEL_MDID = 21, + ICE_PKT_TCP_MDID = 22, + ICE_PKT_ERROR_MDID = 23, +}; + +enum ice_hw_metadata_offset { + ICE_SOURCE_PORT_MDID_OFFSET = ICE_MDID_SIZE * ICE_SOURCE_PORT_MDID, + ICE_PTYPE_MDID_OFFSET = ICE_MDID_SIZE * ICE_PTYPE_MDID, + ICE_PACKET_LENGTH_MDID_OFFSET = ICE_MDID_SIZE * ICE_PACKET_LENGTH_MDID, + ICE_SOURCE_VSI_MDID_OFFSET = ICE_MDID_SIZE * ICE_SOURCE_VSI_MDID, + ICE_PKT_VLAN_MDID_OFFSET = ICE_MDID_SIZE * ICE_PKT_VLAN_MDID, + ICE_PKT_TUNNEL_MDID_OFFSET = ICE_MDID_SIZE * ICE_PKT_TUNNEL_MDID, + ICE_PKT_TCP_MDID_OFFSET = ICE_MDID_SIZE * ICE_PKT_TCP_MDID, + ICE_PKT_ERROR_MDID_OFFSET = ICE_MDID_SIZE * ICE_PKT_ERROR_MDID, +}; + +enum ice_pkt_flags { + ICE_PKT_FLAGS_VLAN = 0, + ICE_PKT_FLAGS_TUNNEL = 1, + ICE_PKT_FLAGS_TCP = 2, + ICE_PKT_FLAGS_ERROR = 3, +}; + +struct ice_hw_metadata { + __be16 source_port; + __be16 ptype; + __be16 packet_length; + __be16 source_vsi; + __be16 flags[4]; +}; + union ice_prot_hdr { struct ice_ether_hdr eth_hdr; struct ice_ethtype_hdr ethertype; @@ -243,6 +419,7 @@ union ice_prot_hdr { struct ice_udp_gtp_hdr gtp_hdr; struct ice_pppoe_hdr pppoe_hdr; struct ice_l2tpv3_sess_hdr l2tpv3_sess_hdr; + struct ice_hw_metadata metadata; }; /* This is mapping table entry that maps every word within a given protocol diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index ac6f06f9a2ed..d4b6c997141d 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -911,7 +911,7 @@ ice_ptp_release_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx) spin_unlock(&tx->lock); /* wait for potentially outstanding interrupt to complete */ - synchronize_irq(pf->msix_entries[pf->oicr_idx].vector); + synchronize_irq(pf->oicr_irq.virq); ice_ptp_flush_tx_tracker(pf, tx); diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c index fd1f8b0ad0ab..e30e12321abd 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.c +++ b/drivers/net/ethernet/intel/ice/ice_repr.c @@ -298,14 +298,6 @@ static int ice_repr_add(struct ice_vf *vf) if (!repr) return -ENOMEM; -#ifdef CONFIG_ICE_SWITCHDEV - repr->mac_rule = kzalloc(sizeof(*repr->mac_rule), GFP_KERNEL); - if (!repr->mac_rule) { - err = -ENOMEM; - goto err_alloc_rule; - } -#endif - repr->netdev = alloc_etherdev(sizeof(struct ice_netdev_priv)); if (!repr->netdev) { err = -ENOMEM; @@ -351,11 +343,6 @@ err_alloc_q_vector: free_netdev(repr->netdev); repr->netdev = NULL; err_alloc: -#ifdef CONFIG_ICE_SWITCHDEV - kfree(repr->mac_rule); - repr->mac_rule = NULL; -err_alloc_rule: -#endif kfree(repr); vf->repr = NULL; return err; @@ -376,10 +363,6 @@ static void ice_repr_rem(struct ice_vf *vf) ice_devlink_destroy_vf_port(vf); free_netdev(vf->repr->netdev); vf->repr->netdev = NULL; -#ifdef CONFIG_ICE_SWITCHDEV - kfree(vf->repr->mac_rule); - vf->repr->mac_rule = NULL; -#endif kfree(vf->repr); vf->repr = NULL; diff --git a/drivers/net/ethernet/intel/ice/ice_repr.h b/drivers/net/ethernet/intel/ice/ice_repr.h index 378a45bfa256..9c2a6f496b3b 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.h +++ b/drivers/net/ethernet/intel/ice/ice_repr.h @@ -13,9 +13,8 @@ struct ice_repr { struct net_device *netdev; struct metadata_dst *dst; #ifdef CONFIG_ICE_SWITCHDEV - /* info about slow path MAC rule */ - struct ice_rule_query_data *mac_rule; - u8 rule_added; + /* info about slow path rule */ + struct ice_rule_query_data sp_rule; #endif }; diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index f1dca59bd844..2ea6d24977a6 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -135,18 +135,9 @@ static void ice_dis_vf_mappings(struct ice_vf *vf) */ static int ice_sriov_free_msix_res(struct ice_pf *pf) { - struct ice_res_tracker *res; - if (!pf) return -EINVAL; - res = pf->irq_tracker; - if (!res) - return -EINVAL; - - /* give back irq_tracker resources used */ - WARN_ON(pf->sriov_base_vector < res->num_entries); - pf->sriov_base_vector = 0; return 0; @@ -410,29 +401,6 @@ int ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector) } /** - * ice_get_max_valid_res_idx - Get the max valid resource index - * @res: pointer to the resource to find the max valid index for - * - * Start from the end of the ice_res_tracker and return right when we find the - * first res->list entry with the ICE_RES_VALID_BIT set. This function is only - * valid for SR-IOV because it is the only consumer that manipulates the - * res->end and this is always called when res->end is set to res->num_entries. - */ -static int ice_get_max_valid_res_idx(struct ice_res_tracker *res) -{ - int i; - - if (!res) - return -EINVAL; - - for (i = res->num_entries - 1; i >= 0; i--) - if (res->list[i] & ICE_RES_VALID_BIT) - return i; - - return 0; -} - -/** * ice_sriov_set_msix_res - Set any used MSIX resources * @pf: pointer to PF structure * @num_msix_needed: number of MSIX vectors needed for all SR-IOV VFs @@ -450,7 +418,7 @@ static int ice_get_max_valid_res_idx(struct ice_res_tracker *res) static int ice_sriov_set_msix_res(struct ice_pf *pf, u16 num_msix_needed) { u16 total_vectors = pf->hw.func_caps.common_cap.num_msix_vectors; - int vectors_used = pf->irq_tracker->num_entries; + int vectors_used = ice_get_max_used_msix_vector(pf); int sriov_base_vector; sriov_base_vector = total_vectors - num_msix_needed; @@ -490,7 +458,7 @@ static int ice_sriov_set_msix_res(struct ice_pf *pf, u16 num_msix_needed) */ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs) { - int max_valid_res_idx = ice_get_max_valid_res_idx(pf->irq_tracker); + int vectors_used = ice_get_max_used_msix_vector(pf); u16 num_msix_per_vf, num_txq, num_rxq, avail_qs; int msix_avail_per_vf, msix_avail_for_sriov; struct device *dev = ice_pf_to_dev(pf); @@ -501,12 +469,9 @@ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs) if (!num_vfs) return -EINVAL; - if (max_valid_res_idx < 0) - return -ENOSPC; - /* determine MSI-X resources per VF */ msix_avail_for_sriov = pf->hw.func_caps.common_cap.num_msix_vectors - - pf->irq_tracker->num_entries; + vectors_used; msix_avail_per_vf = msix_avail_for_sriov / num_vfs; if (msix_avail_per_vf >= ICE_NUM_VF_MSIX_MED) { num_msix_per_vf = ICE_NUM_VF_MSIX_MED; @@ -871,7 +836,7 @@ static int ice_ena_vfs(struct ice_pf *pf, u16 num_vfs) int ret; /* Disable global interrupt 0 so we don't try to handle the VFLR. */ - wr32(hw, GLINT_DYN_CTL(pf->oicr_idx), + wr32(hw, GLINT_DYN_CTL(pf->oicr_irq.index), ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S); set_bit(ICE_OICR_INTR_DIS, pf->state); ice_flush(hw); @@ -1014,8 +979,6 @@ int ice_sriov_configure(struct pci_dev *pdev, int num_vfs) if (!num_vfs) { if (!pci_vfs_assigned(pdev)) { ice_free_vfs(pf); - if (pf->lag) - ice_enable_lag(pf->lag); return 0; } @@ -1027,8 +990,6 @@ int ice_sriov_configure(struct pci_dev *pdev, int num_vfs) if (err) return err; - if (pf->lag) - ice_disable_lag(pf->lag); return num_vfs; } @@ -1171,7 +1132,7 @@ int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena) if (!vf) return -EINVAL; - ret = ice_check_vf_ready_for_cfg(vf); + ret = ice_check_vf_ready_for_reset(vf); if (ret) goto out_put_vf; @@ -1286,7 +1247,7 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) goto out_put_vf; } - ret = ice_check_vf_ready_for_cfg(vf); + ret = ice_check_vf_ready_for_reset(vf); if (ret) goto out_put_vf; @@ -1340,7 +1301,7 @@ int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted) return -EOPNOTSUPP; } - ret = ice_check_vf_ready_for_cfg(vf); + ret = ice_check_vf_ready_for_reset(vf); if (ret) goto out_put_vf; @@ -1653,7 +1614,7 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, if (!vf) return -EINVAL; - ret = ice_check_vf_ready_for_cfg(vf); + ret = ice_check_vf_ready_for_reset(vf); if (ret) goto out_put_vf; diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 46b36851af46..2ea9e1ae5517 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -4540,6 +4540,11 @@ ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, return status; } +#define ICE_PROTOCOL_ENTRY(id, ...) { \ + .prot_type = id, \ + .offs = {__VA_ARGS__}, \ +} + /* This is mapping table entry that maps every word within a given protocol * structure to the real byte offset as per the specification of that * protocol header. @@ -4550,29 +4555,38 @@ ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, * structure is added to that union. */ static const struct ice_prot_ext_tbl_entry ice_prot_ext[ICE_PROTOCOL_LAST] = { - { ICE_MAC_OFOS, { 0, 2, 4, 6, 8, 10, 12 } }, - { ICE_MAC_IL, { 0, 2, 4, 6, 8, 10, 12 } }, - { ICE_ETYPE_OL, { 0 } }, - { ICE_ETYPE_IL, { 0 } }, - { ICE_VLAN_OFOS, { 2, 0 } }, - { ICE_IPV4_OFOS, { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18 } }, - { ICE_IPV4_IL, { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18 } }, - { ICE_IPV6_OFOS, { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, - 26, 28, 30, 32, 34, 36, 38 } }, - { ICE_IPV6_IL, { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, - 26, 28, 30, 32, 34, 36, 38 } }, - { ICE_TCP_IL, { 0, 2 } }, - { ICE_UDP_OF, { 0, 2 } }, - { ICE_UDP_ILOS, { 0, 2 } }, - { ICE_VXLAN, { 8, 10, 12, 14 } }, - { ICE_GENEVE, { 8, 10, 12, 14 } }, - { ICE_NVGRE, { 0, 2, 4, 6 } }, - { ICE_GTP, { 8, 10, 12, 14, 16, 18, 20, 22 } }, - { ICE_GTP_NO_PAY, { 8, 10, 12, 14 } }, - { ICE_PPPOE, { 0, 2, 4, 6 } }, - { ICE_L2TPV3, { 0, 2, 4, 6, 8, 10 } }, - { ICE_VLAN_EX, { 2, 0 } }, - { ICE_VLAN_IN, { 2, 0 } }, + ICE_PROTOCOL_ENTRY(ICE_MAC_OFOS, 0, 2, 4, 6, 8, 10, 12), + ICE_PROTOCOL_ENTRY(ICE_MAC_IL, 0, 2, 4, 6, 8, 10, 12), + ICE_PROTOCOL_ENTRY(ICE_ETYPE_OL, 0), + ICE_PROTOCOL_ENTRY(ICE_ETYPE_IL, 0), + ICE_PROTOCOL_ENTRY(ICE_VLAN_OFOS, 2, 0), + ICE_PROTOCOL_ENTRY(ICE_IPV4_OFOS, 0, 2, 4, 6, 8, 10, 12, 14, 16, 18), + ICE_PROTOCOL_ENTRY(ICE_IPV4_IL, 0, 2, 4, 6, 8, 10, 12, 14, 16, 18), + ICE_PROTOCOL_ENTRY(ICE_IPV6_OFOS, 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, + 20, 22, 24, 26, 28, 30, 32, 34, 36, 38), + ICE_PROTOCOL_ENTRY(ICE_IPV6_IL, 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, + 22, 24, 26, 28, 30, 32, 34, 36, 38), + ICE_PROTOCOL_ENTRY(ICE_TCP_IL, 0, 2), + ICE_PROTOCOL_ENTRY(ICE_UDP_OF, 0, 2), + ICE_PROTOCOL_ENTRY(ICE_UDP_ILOS, 0, 2), + ICE_PROTOCOL_ENTRY(ICE_VXLAN, 8, 10, 12, 14), + ICE_PROTOCOL_ENTRY(ICE_GENEVE, 8, 10, 12, 14), + ICE_PROTOCOL_ENTRY(ICE_NVGRE, 0, 2, 4, 6), + ICE_PROTOCOL_ENTRY(ICE_GTP, 8, 10, 12, 14, 16, 18, 20, 22), + ICE_PROTOCOL_ENTRY(ICE_GTP_NO_PAY, 8, 10, 12, 14), + ICE_PROTOCOL_ENTRY(ICE_PPPOE, 0, 2, 4, 6), + ICE_PROTOCOL_ENTRY(ICE_L2TPV3, 0, 2, 4, 6, 8, 10), + ICE_PROTOCOL_ENTRY(ICE_VLAN_EX, 2, 0), + ICE_PROTOCOL_ENTRY(ICE_VLAN_IN, 2, 0), + ICE_PROTOCOL_ENTRY(ICE_HW_METADATA, + ICE_SOURCE_PORT_MDID_OFFSET, + ICE_PTYPE_MDID_OFFSET, + ICE_PACKET_LENGTH_MDID_OFFSET, + ICE_SOURCE_VSI_MDID_OFFSET, + ICE_PKT_VLAN_MDID_OFFSET, + ICE_PKT_TUNNEL_MDID_OFFSET, + ICE_PKT_TCP_MDID_OFFSET, + ICE_PKT_ERROR_MDID_OFFSET), }; static struct ice_protocol_entry ice_prot_id_tbl[ICE_PROTOCOL_LAST] = { @@ -4597,6 +4611,7 @@ static struct ice_protocol_entry ice_prot_id_tbl[ICE_PROTOCOL_LAST] = { { ICE_L2TPV3, ICE_L2TPV3_HW }, { ICE_VLAN_EX, ICE_VLAN_OF_HW }, { ICE_VLAN_IN, ICE_VLAN_OL_HW }, + { ICE_HW_METADATA, ICE_META_DATA_ID_HW }, }; /** @@ -5255,71 +5270,6 @@ ice_create_recipe_group(struct ice_hw *hw, struct ice_sw_recipe *rm, return status; } -/** - * ice_tun_type_match_word - determine if tun type needs a match mask - * @tun_type: tunnel type - * @mask: mask to be used for the tunnel - */ -static bool ice_tun_type_match_word(enum ice_sw_tunnel_type tun_type, u16 *mask) -{ - switch (tun_type) { - case ICE_SW_TUN_GENEVE: - case ICE_SW_TUN_VXLAN: - case ICE_SW_TUN_NVGRE: - case ICE_SW_TUN_GTPU: - case ICE_SW_TUN_GTPC: - *mask = ICE_TUN_FLAG_MASK; - return true; - - default: - *mask = 0; - return false; - } -} - -/** - * ice_add_special_words - Add words that are not protocols, such as metadata - * @rinfo: other information regarding the rule e.g. priority and action info - * @lkup_exts: lookup word structure - * @dvm_ena: is double VLAN mode enabled - */ -static int -ice_add_special_words(struct ice_adv_rule_info *rinfo, - struct ice_prot_lkup_ext *lkup_exts, bool dvm_ena) -{ - u16 mask; - - /* If this is a tunneled packet, then add recipe index to match the - * tunnel bit in the packet metadata flags. - */ - if (ice_tun_type_match_word(rinfo->tun_type, &mask)) { - if (lkup_exts->n_val_words < ICE_MAX_CHAIN_WORDS) { - u8 word = lkup_exts->n_val_words++; - - lkup_exts->fv_words[word].prot_id = ICE_META_DATA_ID_HW; - lkup_exts->fv_words[word].off = ICE_TUN_FLAG_MDID_OFF; - lkup_exts->field_mask[word] = mask; - } else { - return -ENOSPC; - } - } - - if (rinfo->vlan_type != 0 && dvm_ena) { - if (lkup_exts->n_val_words < ICE_MAX_CHAIN_WORDS) { - u8 word = lkup_exts->n_val_words++; - - lkup_exts->fv_words[word].prot_id = ICE_META_DATA_ID_HW; - lkup_exts->fv_words[word].off = ICE_VLAN_FLAG_MDID_OFF; - lkup_exts->field_mask[word] = - ICE_PKT_FLAGS_0_TO_15_VLAN_FLAGS_MASK; - } else { - return -ENOSPC; - } - } - - return 0; -} - /* ice_get_compat_fv_bitmap - Get compatible field vector bitmap for rule * @hw: pointer to hardware structure * @rinfo: other information regarding the rule e.g. priority and action info @@ -5433,13 +5383,6 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, if (status) goto err_unroll; - /* Create any special protocol/offset pairs, such as looking at tunnel - * bits by extracting metadata - */ - status = ice_add_special_words(rinfo, lkup_exts, ice_is_dvm_ena(hw)); - if (status) - goto err_unroll; - /* Group match words into recipes using preferred recipe grouping * criteria. */ @@ -5725,6 +5668,10 @@ ice_fill_adv_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, * was already checked when search for the dummy packet */ type = lkups[i].type; + /* metadata isn't present in the packet */ + if (type == ICE_HW_METADATA) + continue; + for (j = 0; offsets[j].type != ICE_PROTOCOL_LAST; j++) { if (type == offsets[j].type) { offset = offsets[j].offset; @@ -5860,16 +5807,21 @@ ice_fill_adv_packet_tun(struct ice_hw *hw, enum ice_sw_tunnel_type tun_type, /** * ice_fill_adv_packet_vlan - fill dummy packet with VLAN tag type + * @hw: pointer to hw structure * @vlan_type: VLAN tag type * @pkt: dummy packet to fill in * @offsets: offset info for the dummy packet */ static int -ice_fill_adv_packet_vlan(u16 vlan_type, u8 *pkt, +ice_fill_adv_packet_vlan(struct ice_hw *hw, u16 vlan_type, u8 *pkt, const struct ice_dummy_pkt_offsets *offsets) { u16 i; + /* Check if there is something to do */ + if (!vlan_type || !ice_is_dvm_ena(hw)) + return 0; + /* Find VLAN header and insert VLAN TPID */ for (i = 0; offsets[i].type != ICE_PROTOCOL_LAST; i++) { if (offsets[i].type == ICE_VLAN_OFOS || @@ -5888,6 +5840,15 @@ ice_fill_adv_packet_vlan(u16 vlan_type, u8 *pkt, return -EIO; } +static bool ice_rules_equal(const struct ice_adv_rule_info *first, + const struct ice_adv_rule_info *second) +{ + return first->sw_act.flag == second->sw_act.flag && + first->tun_type == second->tun_type && + first->vlan_type == second->vlan_type && + first->src_vsi == second->src_vsi; +} + /** * ice_find_adv_rule_entry - Search a rule entry * @hw: pointer to the hardware structure @@ -5921,9 +5882,7 @@ ice_find_adv_rule_entry(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, lkups_matched = false; break; } - if (rinfo->sw_act.flag == list_itr->rule_info.sw_act.flag && - rinfo->tun_type == list_itr->rule_info.tun_type && - rinfo->vlan_type == list_itr->rule_info.vlan_type && + if (ice_rules_equal(rinfo, &list_itr->rule_info) && lkups_matched) return list_itr; } @@ -6039,6 +5998,26 @@ ice_adv_add_update_vsi_list(struct ice_hw *hw, return status; } +void ice_rule_add_tunnel_metadata(struct ice_adv_lkup_elem *lkup) +{ + lkup->type = ICE_HW_METADATA; + lkup->m_u.metadata.flags[ICE_PKT_FLAGS_TUNNEL] = + cpu_to_be16(ICE_PKT_TUNNEL_MASK); +} + +void ice_rule_add_vlan_metadata(struct ice_adv_lkup_elem *lkup) +{ + lkup->type = ICE_HW_METADATA; + lkup->m_u.metadata.flags[ICE_PKT_FLAGS_VLAN] = + cpu_to_be16(ICE_PKT_VLAN_MASK); +} + +void ice_rule_add_src_vsi_metadata(struct ice_adv_lkup_elem *lkup) +{ + lkup->type = ICE_HW_METADATA; + lkup->m_u.metadata.source_vsi = cpu_to_be16(ICE_MDID_SOURCE_VSI_MASK); +} + /** * ice_add_adv_rule - helper function to create an advanced switch rule * @hw: pointer to the hardware structure @@ -6120,7 +6099,10 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, if (rinfo->sw_act.fltr_act == ICE_FWD_TO_VSI) rinfo->sw_act.fwd_id.hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); - if (rinfo->sw_act.flag & ICE_FLTR_TX) + + if (rinfo->src_vsi) + rinfo->sw_act.src = ice_get_hw_vsi_num(hw, rinfo->src_vsi); + else rinfo->sw_act.src = ice_get_hw_vsi_num(hw, vsi_handle); status = ice_add_adv_recipe(hw, lkups, lkups_cnt, rinfo, &rid); @@ -6189,19 +6171,20 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, goto err_ice_add_adv_rule; } - /* set the rule LOOKUP type based on caller specified 'Rx' - * instead of hardcoding it to be either LOOKUP_TX/RX + /* If there is no matching criteria for direction there + * is only one difference between Rx and Tx: + * - get switch id base on VSI number from source field (Tx) + * - get switch id base on port number (Rx) * - * for 'Rx' set the source to be the port number - * for 'Tx' set the source to be the source HW VSI number (determined - * by caller) + * If matching on direction metadata is chose rule direction is + * extracted from type value set here. */ - if (rinfo->rx) { - s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX); - s_rule->src = cpu_to_le16(hw->port_info->lport); - } else { + if (rinfo->sw_act.flag & ICE_FLTR_TX) { s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_TX); s_rule->src = cpu_to_le16(rinfo->sw_act.src); + } else { + s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX); + s_rule->src = cpu_to_le16(hw->port_info->lport); } s_rule->recipe_id = cpu_to_le16(rid); @@ -6211,22 +6194,16 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, if (status) goto err_ice_add_adv_rule; - if (rinfo->tun_type != ICE_NON_TUN && - rinfo->tun_type != ICE_SW_TUN_AND_NON_TUN) { - status = ice_fill_adv_packet_tun(hw, rinfo->tun_type, - s_rule->hdr_data, - profile->offsets); - if (status) - goto err_ice_add_adv_rule; - } + status = ice_fill_adv_packet_tun(hw, rinfo->tun_type, s_rule->hdr_data, + profile->offsets); + if (status) + goto err_ice_add_adv_rule; - if (rinfo->vlan_type != 0 && ice_is_dvm_ena(hw)) { - status = ice_fill_adv_packet_vlan(rinfo->vlan_type, - s_rule->hdr_data, - profile->offsets); - if (status) - goto err_ice_add_adv_rule; - } + status = ice_fill_adv_packet_vlan(hw, rinfo->vlan_type, + s_rule->hdr_data, + profile->offsets); + if (status) + goto err_ice_add_adv_rule; status = ice_aq_sw_rules(hw, (struct ice_aqc_sw_rules *)s_rule, rule_buf_sz, 1, ice_aqc_opc_add_sw_rules, @@ -6469,13 +6446,6 @@ ice_rem_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, return -EIO; } - /* Create any special protocol/offset pairs, such as looking at tunnel - * bits by extracting metadata - */ - status = ice_add_special_words(rinfo, &lkup_exts, ice_is_dvm_ena(hw)); - if (status) - return status; - rid = ice_find_recp(hw, &lkup_exts, rinfo->tun_type); /* If did not find a recipe that match the existing criteria */ if (rid == ICE_MAX_NUM_RECIPES) diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h index 68d8e8a6a189..c84b56fe84a5 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.h +++ b/drivers/net/ethernet/intel/ice/ice_switch.h @@ -10,7 +10,6 @@ #define ICE_DFLT_VSI_INVAL 0xff #define ICE_FLTR_RX BIT(0) #define ICE_FLTR_TX BIT(1) -#define ICE_FLTR_TX_RX (ICE_FLTR_RX | ICE_FLTR_TX) #define ICE_VSI_INVAL_ID 0xffff #define ICE_INVAL_Q_HANDLE 0xFFFF @@ -187,12 +186,13 @@ struct ice_adv_rule_flags_info { }; struct ice_adv_rule_info { + /* Store metadata values in rule info */ enum ice_sw_tunnel_type tun_type; - struct ice_sw_act_ctrl sw_act; - u32 priority; - u8 rx; /* true means LOOKUP_RX otherwise LOOKUP_TX */ - u16 fltr_rule_id; u16 vlan_type; + u16 fltr_rule_id; + u32 priority; + u16 src_vsi; + struct ice_sw_act_ctrl sw_act; struct ice_adv_rule_flags_info flags_info; }; @@ -342,6 +342,9 @@ ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, u16 counter_id); /* Switch/bridge related commands */ +void ice_rule_add_tunnel_metadata(struct ice_adv_lkup_elem *lkup); +void ice_rule_add_vlan_metadata(struct ice_adv_lkup_elem *lkup); +void ice_rule_add_src_vsi_metadata(struct ice_adv_lkup_elem *lkup); int ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, struct ice_adv_rule_info *rinfo, diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index d1a31f236d26..b54052ef6050 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -54,6 +54,10 @@ ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers, if (flags & (ICE_TC_FLWR_FIELD_VLAN | ICE_TC_FLWR_FIELD_VLAN_PRIO)) lkups_cnt++; + /* is VLAN TPID specified */ + if (flags & ICE_TC_FLWR_FIELD_VLAN_TPID) + lkups_cnt++; + /* is CVLAN specified? */ if (flags & (ICE_TC_FLWR_FIELD_CVLAN | ICE_TC_FLWR_FIELD_CVLAN_PRIO)) lkups_cnt++; @@ -80,6 +84,10 @@ ice_tc_count_lkups(u32 flags, struct ice_tc_flower_lyr_2_4_hdrs *headers, ICE_TC_FLWR_FIELD_SRC_L4_PORT)) lkups_cnt++; + /* matching for tunneled packets in metadata */ + if (fltr->tunnel_type != TNL_LAST) + lkups_cnt++; + return lkups_cnt; } @@ -320,6 +328,10 @@ ice_tc_fill_tunnel_outer(u32 flags, struct ice_tc_flower_fltr *fltr, i++; } + /* always fill matching on tunneled packets in metadata */ + ice_rule_add_tunnel_metadata(&list[i]); + i++; + return i; } @@ -390,10 +402,6 @@ ice_tc_fill_rules(struct ice_hw *hw, u32 flags, /* copy VLAN info */ if (flags & (ICE_TC_FLWR_FIELD_VLAN | ICE_TC_FLWR_FIELD_VLAN_PRIO)) { - vlan_tpid = be16_to_cpu(headers->vlan_hdr.vlan_tpid); - rule_info->vlan_type = - ice_check_supported_vlan_tpid(vlan_tpid); - if (flags & ICE_TC_FLWR_FIELD_CVLAN) list[i].type = ICE_VLAN_EX; else @@ -418,6 +426,15 @@ ice_tc_fill_rules(struct ice_hw *hw, u32 flags, i++; } + if (flags & ICE_TC_FLWR_FIELD_VLAN_TPID) { + vlan_tpid = be16_to_cpu(headers->vlan_hdr.vlan_tpid); + rule_info->vlan_type = + ice_check_supported_vlan_tpid(vlan_tpid); + + ice_rule_add_vlan_metadata(&list[i]); + i++; + } + if (flags & (ICE_TC_FLWR_FIELD_CVLAN | ICE_TC_FLWR_FIELD_CVLAN_PRIO)) { list[i].type = ICE_VLAN_IN; @@ -698,12 +715,10 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) if (fltr->direction == ICE_ESWITCH_FLTR_INGRESS) { rule_info.sw_act.flag |= ICE_FLTR_RX; rule_info.sw_act.src = hw->pf_id; - rule_info.rx = true; rule_info.flags_info.act = ICE_SINGLE_ACT_LB_ENABLE; } else { rule_info.sw_act.flag |= ICE_FLTR_TX; rule_info.sw_act.src = vsi->idx; - rule_info.rx = false; rule_info.flags_info.act = ICE_SINGLE_ACT_LAN_ENABLE; } @@ -910,7 +925,6 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi, rule_info.sw_act.vsi_handle = dest_vsi->idx; rule_info.priority = ICE_SWITCH_FLTR_PRIO_VSI; rule_info.sw_act.src = hw->pf_id; - rule_info.rx = true; dev_dbg(dev, "add switch rule for TC:%u vsi_idx:%u, lkups_cnt:%u\n", tc_fltr->action.fwd.tc.tc_class, rule_info.sw_act.vsi_handle, lkups_cnt); @@ -921,7 +935,6 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi, rule_info.sw_act.vsi_handle = dest_vsi->idx; rule_info.priority = ICE_SWITCH_FLTR_PRIO_QUEUE; rule_info.sw_act.src = hw->pf_id; - rule_info.rx = true; dev_dbg(dev, "add switch rule action to forward to queue:%u (HW queue %u), lkups_cnt:%u\n", tc_fltr->action.fwd.q.queue, tc_fltr->action.fwd.q.hw_queue, lkups_cnt); @@ -929,7 +942,6 @@ ice_add_tc_flower_adv_fltr(struct ice_vsi *vsi, case ICE_DROP_PACKET: rule_info.sw_act.flag |= ICE_FLTR_RX; rule_info.sw_act.src = hw->pf_id; - rule_info.rx = true; rule_info.priority = ICE_SWITCH_FLTR_PRIO_VSI; break; default: @@ -1460,8 +1472,10 @@ ice_parse_cls_flower(struct net_device *filter_dev, struct ice_vsi *vsi, VLAN_PRIO_MASK); } - if (match.mask->vlan_tpid) + if (match.mask->vlan_tpid) { headers->vlan_hdr.vlan_tpid = match.key->vlan_tpid; + fltr->flags |= ICE_TC_FLWR_FIELD_VLAN_TPID; + } } if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CVLAN)) { diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.h b/drivers/net/ethernet/intel/ice/ice_tc_lib.h index 8d5e22ac7023..8bbc1a62bdb1 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.h @@ -33,6 +33,7 @@ #define ICE_TC_FLWR_FIELD_L2TPV3_SESSID BIT(26) #define ICE_TC_FLWR_FIELD_VLAN_PRIO BIT(27) #define ICE_TC_FLWR_FIELD_CVLAN_PRIO BIT(28) +#define ICE_TC_FLWR_FIELD_VLAN_TPID BIT(29) #define ICE_TC_FLOWER_MASK_32 0xFFFFFFFF diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 4fcf2d07eb85..52d0a126eb61 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -1152,11 +1152,11 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) unsigned int total_rx_bytes = 0, total_rx_pkts = 0; unsigned int offset = rx_ring->rx_offset; struct xdp_buff *xdp = &rx_ring->xdp; + u32 cached_ntc = rx_ring->first_desc; struct ice_tx_ring *xdp_ring = NULL; struct bpf_prog *xdp_prog = NULL; u32 ntc = rx_ring->next_to_clean; u32 cnt = rx_ring->count; - u32 cached_ntc = ntc; u32 xdp_xmit = 0; u32 cached_ntu; bool failure; @@ -1664,8 +1664,7 @@ ice_tx_map(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first, if (first->tx_flags & ICE_TX_FLAGS_HW_VLAN) { td_cmd |= (u64)ICE_TX_DESC_CMD_IL2TAG1; - td_tag = (first->tx_flags & ICE_TX_FLAGS_VLAN_M) >> - ICE_TX_FLAGS_VLAN_S; + td_tag = first->vid; } dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE); @@ -1998,7 +1997,7 @@ ice_tx_prepare_vlan_flags(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first) * VLAN offloads exclusively so we only care about the VLAN ID here */ if (skb_vlan_tag_present(skb)) { - first->tx_flags |= skb_vlan_tag_get(skb) << ICE_TX_FLAGS_VLAN_S; + first->vid = skb_vlan_tag_get(skb); if (tx_ring->flags & ICE_TX_FLAGS_RING_VLAN_L2TAG2) first->tx_flags |= ICE_TX_FLAGS_HW_OUTER_SINGLE_VLAN; else @@ -2388,8 +2387,7 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring) offload.cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX | (ICE_TX_CTX_DESC_IL2TAG2 << ICE_TXD_CTX_QW1_CMD_S)); - offload.cd_l2tag2 = (first->tx_flags & ICE_TX_FLAGS_VLAN_M) >> - ICE_TX_FLAGS_VLAN_S; + offload.cd_l2tag2 = first->vid; } /* set up TSO offload */ diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index fff0efe28373..166413fc33f4 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -127,10 +127,6 @@ static inline int ice_skb_pad(void) #define ICE_TX_FLAGS_IPV6 BIT(6) #define ICE_TX_FLAGS_TUNNEL BIT(7) #define ICE_TX_FLAGS_HW_OUTER_SINGLE_VLAN BIT(8) -#define ICE_TX_FLAGS_VLAN_M 0xffff0000 -#define ICE_TX_FLAGS_VLAN_PR_M 0xe0000000 -#define ICE_TX_FLAGS_VLAN_PR_S 29 -#define ICE_TX_FLAGS_VLAN_S 16 #define ICE_XDP_PASS 0 #define ICE_XDP_CONSUMED BIT(0) @@ -182,8 +178,9 @@ struct ice_tx_buf { unsigned int gso_segs; unsigned int nr_frags; /* used for mbuf XDP */ }; - u32 type:16; /* &ice_tx_buf_type */ - u32 tx_flags:16; + u32 tx_flags:12; + u32 type:4; /* &ice_tx_buf_type */ + u32 vid:16; DEFINE_DMA_UNMAP_LEN(len); DEFINE_DMA_UNMAP_ADDR(dma); }; diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index 89fd6982df09..b26ce4425f45 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -186,6 +186,25 @@ int ice_check_vf_ready_for_cfg(struct ice_vf *vf) } /** + * ice_check_vf_ready_for_reset - check if VF is ready to be reset + * @vf: VF to check if it's ready to be reset + * + * The purpose of this function is to ensure that the VF is not in reset, + * disabled, and is both initialized and active, thus enabling us to safely + * initialize another reset. + */ +int ice_check_vf_ready_for_reset(struct ice_vf *vf) +{ + int ret; + + ret = ice_check_vf_ready_for_cfg(vf); + if (!ret && !test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) + ret = -EAGAIN; + + return ret; +} + +/** * ice_trigger_vf_reset - Reset a VF on HW * @vf: pointer to the VF structure * @is_vflr: true if VFLR was issued, false if not @@ -670,8 +689,6 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) */ ice_vf_clear_all_promisc_modes(vf, vsi); - ice_eswitch_del_vf_mac_rule(vf); - ice_vf_fdir_exit(vf); ice_vf_fdir_init(vf); /* clean VF control VSI when resetting VF since it should be setup @@ -697,7 +714,6 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) } ice_eswitch_update_repr(vsi); - ice_eswitch_replay_vf_mac_rule(vf); /* if the VF has been reset allow it to come up again */ ice_mbx_clear_malvf(&vf->mbx_info); @@ -1310,3 +1326,35 @@ void ice_vf_set_initialized(struct ice_vf *vf) set_bit(ICE_VF_STATE_INIT, vf->vf_states); memset(&vf->vlan_v2_caps, 0, sizeof(vf->vlan_v2_caps)); } + +/** + * ice_get_vf_ctrl_vsi - Get first VF control VSI pointer + * @pf: the PF private structure + * @vsi: pointer to the VSI + * + * Return first found VF control VSI other than the vsi + * passed by parameter. This function is used to determine + * whether new resources have to be allocated for control VSI + * or they can be shared with existing one. + * + * Return found VF control VSI pointer other itself. Return + * NULL Otherwise. + * + */ +struct ice_vsi *ice_get_vf_ctrl_vsi(struct ice_pf *pf, struct ice_vsi *vsi) +{ + struct ice_vsi *ctrl_vsi = NULL; + struct ice_vf *vf; + unsigned int bkt; + + rcu_read_lock(); + ice_for_each_vf_rcu(pf, bkt, vf) { + if (vf != vsi->vf && vf->ctrl_vsi_idx != ICE_NO_VSI) { + ctrl_vsi = pf->vsi[vf->ctrl_vsi_idx]; + break; + } + } + + rcu_read_unlock(); + return ctrl_vsi; +} diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h index e3cda6fb71ab..67172fdd9bc2 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h @@ -215,6 +215,7 @@ u16 ice_get_num_vfs(struct ice_pf *pf); struct ice_vsi *ice_get_vf_vsi(struct ice_vf *vf); bool ice_is_vf_disabled(struct ice_vf *vf); int ice_check_vf_ready_for_cfg(struct ice_vf *vf); +int ice_check_vf_ready_for_reset(struct ice_vf *vf); void ice_set_vf_state_dis(struct ice_vf *vf); bool ice_is_any_vf_in_unicast_promisc(struct ice_pf *pf); void @@ -226,6 +227,7 @@ int ice_vf_clear_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m); int ice_reset_vf(struct ice_vf *vf, u32 flags); void ice_reset_all_vfs(struct ice_pf *pf); +struct ice_vsi *ice_get_vf_ctrl_vsi(struct ice_pf *pf, struct ice_vsi *vsi); #else /* CONFIG_PCI_IOV */ static inline struct ice_vf *ice_get_vf_by_id(struct ice_pf *pf, u16 vf_id) { @@ -290,6 +292,12 @@ static inline int ice_reset_vf(struct ice_vf *vf, u32 flags) static inline void ice_reset_all_vfs(struct ice_pf *pf) { } + +static inline struct ice_vsi * +ice_get_vf_ctrl_vsi(struct ice_pf *pf, struct ice_vsi *vsi) +{ + return NULL; +} #endif /* !CONFIG_PCI_IOV */ #endif /* _ICE_VF_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index 97243c616d5d..efbc2968a7bf 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -3730,7 +3730,6 @@ static int ice_vc_repr_add_mac(struct ice_vf *vf, u8 *msg) for (i = 0; i < al->num_elements; i++) { u8 *mac_addr = al->list[i].addr; - int result; if (!is_unicast_ether_addr(mac_addr) || ether_addr_equal(mac_addr, vf->hw_lan_addr)) @@ -3742,13 +3741,6 @@ static int ice_vc_repr_add_mac(struct ice_vf *vf, u8 *msg) goto handle_mac_exit; } - result = ice_eswitch_add_vf_mac_rule(pf, vf, mac_addr); - if (result) { - dev_err(ice_pf_to_dev(pf), "Failed to add MAC %pM for VF %d\n, error %d\n", - mac_addr, vf->vf_id, result); - goto handle_mac_exit; - } - ice_vfhw_mac_add(vf, &al->list[i]); vf->num_mac++; break; @@ -3955,6 +3947,7 @@ error_handler: ice_vc_notify_vf_link_state(vf); break; case VIRTCHNL_OP_RESET_VF: + clear_bit(ICE_VF_STATE_ACTIVE, vf->vf_states); ops->reset_vf(vf); break; case VIRTCHNL_OP_ADD_ETH_ADDR: diff --git a/drivers/net/ethernet/intel/ice/ice_vlan_mode.c b/drivers/net/ethernet/intel/ice/ice_vlan_mode.c index bcda2e004807..1279c1ffe31c 100644 --- a/drivers/net/ethernet/intel/ice/ice_vlan_mode.c +++ b/drivers/net/ethernet/intel/ice/ice_vlan_mode.c @@ -219,7 +219,7 @@ static struct ice_update_recipe_lkup_idx_params ice_dvm_dflt_recipes[] = { .rid = ICE_SW_LKUP_VLAN, .fv_idx = ICE_PKT_FLAGS_0_TO_15_FV_IDX, .ignore_valid = false, - .mask = ICE_PKT_FLAGS_0_TO_15_VLAN_FLAGS_MASK, + .mask = ICE_PKT_VLAN_MASK, .mask_valid = true, .lkup_idx = ICE_SW_LKUP_VLAN_PKT_FLAGS_LKUP_IDX, }, diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index d1e489da7363..a7fe2b4ce655 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -90,7 +90,6 @@ ice_qvec_dis_irq(struct ice_vsi *vsi, struct ice_rx_ring *rx_ring, { struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; - int base = vsi->base_vector; u16 reg; u32 val; @@ -103,11 +102,9 @@ ice_qvec_dis_irq(struct ice_vsi *vsi, struct ice_rx_ring *rx_ring, wr32(hw, QINT_RQCTL(reg), val); if (q_vector) { - u16 v_idx = q_vector->v_idx; - wr32(hw, GLINT_DYN_CTL(q_vector->reg_idx), 0); ice_flush(hw); - synchronize_irq(pf->msix_entries[v_idx + base].vector); + synchronize_irq(q_vector->irq.virq); } } diff --git a/drivers/net/ethernet/intel/igb/e1000_mac.c b/drivers/net/ethernet/intel/igb/e1000_mac.c index 205d577bdbba..caf91c6f52b4 100644 --- a/drivers/net/ethernet/intel/igb/e1000_mac.c +++ b/drivers/net/ethernet/intel/igb/e1000_mac.c @@ -426,7 +426,7 @@ void igb_mta_set(struct e1000_hw *hw, u32 hash_value) static u32 igb_hash_mc_addr(struct e1000_hw *hw, u8 *mc_addr) { u32 hash_value, hash_mask; - u8 bit_shift = 0; + u8 bit_shift = 1; /* Register count multiplied by bits per register */ hash_mask = (hw->mac.mta_reg_count * 32) - 1; @@ -434,7 +434,7 @@ static u32 igb_hash_mc_addr(struct e1000_hw *hw, u8 *mc_addr) /* For a mc_filter_type of 0, bit_shift is the number of left-shifts * where 0xFF would still fall within the hash mask. */ - while (hash_mask >> bit_shift != 0xFF) + while (hash_mask >> bit_shift != 0xFF && bit_shift < 4) bit_shift++; /* The portion of the address that is used for the hash table diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 58872a4c2540..c5cdb880774d 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -183,11 +183,13 @@ static int igb_resume(struct device *); static int igb_runtime_suspend(struct device *dev); static int igb_runtime_resume(struct device *dev); static int igb_runtime_idle(struct device *dev); +#ifdef CONFIG_PM static const struct dev_pm_ops igb_pm_ops = { SET_SYSTEM_SLEEP_PM_OPS(igb_suspend, igb_resume) SET_RUNTIME_PM_OPS(igb_runtime_suspend, igb_runtime_resume, igb_runtime_idle) }; +#endif static void igb_shutdown(struct pci_dev *); static int igb_pci_sriov_configure(struct pci_dev *dev, int num_vfs); #ifdef CONFIG_IGB_DCA diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 34aebf00a512..18d4af934d8c 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -13,6 +13,7 @@ #include <linux/ptp_clock_kernel.h> #include <linux/timecounter.h> #include <linux/net_tstamp.h> +#include <linux/bitfield.h> #include "igc_hw.h" @@ -311,6 +312,33 @@ extern char igc_driver_name[]; #define IGC_MRQC_RSS_FIELD_IPV4_UDP 0x00400000 #define IGC_MRQC_RSS_FIELD_IPV6_UDP 0x00800000 +/* RX-desc Write-Back format RSS Type's */ +enum igc_rss_type_num { + IGC_RSS_TYPE_NO_HASH = 0, + IGC_RSS_TYPE_HASH_TCP_IPV4 = 1, + IGC_RSS_TYPE_HASH_IPV4 = 2, + IGC_RSS_TYPE_HASH_TCP_IPV6 = 3, + IGC_RSS_TYPE_HASH_IPV6_EX = 4, + IGC_RSS_TYPE_HASH_IPV6 = 5, + IGC_RSS_TYPE_HASH_TCP_IPV6_EX = 6, + IGC_RSS_TYPE_HASH_UDP_IPV4 = 7, + IGC_RSS_TYPE_HASH_UDP_IPV6 = 8, + IGC_RSS_TYPE_HASH_UDP_IPV6_EX = 9, + IGC_RSS_TYPE_MAX = 10, +}; +#define IGC_RSS_TYPE_MAX_TABLE 16 +#define IGC_RSS_TYPE_MASK GENMASK(3,0) /* 4-bits (3:0) = mask 0x0F */ + +/* igc_rss_type - Rx descriptor RSS type field */ +static inline u32 igc_rss_type(const union igc_adv_rx_desc *rx_desc) +{ + /* RSS Type 4-bits (3:0) number: 0-9 (above 9 is reserved) + * Accessing the same bits via u16 (wb.lower.lo_dword.hs_rss.pkt_info) + * is slightly slower than via u32 (wb.lower.lo_dword.data) + */ + return le32_get_bits(rx_desc->wb.lower.lo_dword.data, IGC_RSS_TYPE_MASK); +} + /* Interrupt defines */ #define IGC_START_ITR 648 /* ~6000 ints/sec */ #define IGC_4K_ITR 980 @@ -471,6 +499,13 @@ struct igc_rx_buffer { }; }; +/* context wrapper around xdp_buff to provide access to descriptor metadata */ +struct igc_xdp_buff { + struct xdp_buff xdp; + union igc_adv_rx_desc *rx_desc; + ktime_t rx_ts; /* data indication bit IGC_RXDADV_STAT_TSIP */ +}; + struct igc_q_vector { struct igc_adapter *adapter; /* backlink */ void __iomem *itr_register; diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 1c4676882082..88145c30c919 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -1690,14 +1690,36 @@ static void igc_rx_checksum(struct igc_ring *ring, le32_to_cpu(rx_desc->wb.upper.status_error)); } +/* Mapping HW RSS Type to enum pkt_hash_types */ +static const enum pkt_hash_types igc_rss_type_table[IGC_RSS_TYPE_MAX_TABLE] = { + [IGC_RSS_TYPE_NO_HASH] = PKT_HASH_TYPE_L2, + [IGC_RSS_TYPE_HASH_TCP_IPV4] = PKT_HASH_TYPE_L4, + [IGC_RSS_TYPE_HASH_IPV4] = PKT_HASH_TYPE_L3, + [IGC_RSS_TYPE_HASH_TCP_IPV6] = PKT_HASH_TYPE_L4, + [IGC_RSS_TYPE_HASH_IPV6_EX] = PKT_HASH_TYPE_L3, + [IGC_RSS_TYPE_HASH_IPV6] = PKT_HASH_TYPE_L3, + [IGC_RSS_TYPE_HASH_TCP_IPV6_EX] = PKT_HASH_TYPE_L4, + [IGC_RSS_TYPE_HASH_UDP_IPV4] = PKT_HASH_TYPE_L4, + [IGC_RSS_TYPE_HASH_UDP_IPV6] = PKT_HASH_TYPE_L4, + [IGC_RSS_TYPE_HASH_UDP_IPV6_EX] = PKT_HASH_TYPE_L4, + [10] = PKT_HASH_TYPE_NONE, /* RSS Type above 9 "Reserved" by HW */ + [11] = PKT_HASH_TYPE_NONE, /* keep array sized for SW bit-mask */ + [12] = PKT_HASH_TYPE_NONE, /* to handle future HW revisons */ + [13] = PKT_HASH_TYPE_NONE, + [14] = PKT_HASH_TYPE_NONE, + [15] = PKT_HASH_TYPE_NONE, +}; + static inline void igc_rx_hash(struct igc_ring *ring, union igc_adv_rx_desc *rx_desc, struct sk_buff *skb) { - if (ring->netdev->features & NETIF_F_RXHASH) - skb_set_hash(skb, - le32_to_cpu(rx_desc->wb.lower.hi_dword.rss), - PKT_HASH_TYPE_L3); + if (ring->netdev->features & NETIF_F_RXHASH) { + u32 rss_hash = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss); + u32 rss_type = igc_rss_type(rx_desc); + + skb_set_hash(skb, rss_hash, igc_rss_type_table[rss_type]); + } } static void igc_rx_vlan(struct igc_ring *rx_ring, @@ -2214,6 +2236,8 @@ static bool igc_alloc_rx_buffers_zc(struct igc_ring *ring, u16 count) if (!count) return ok; + XSK_CHECK_PRIV_TYPE(struct igc_xdp_buff); + desc = IGC_RX_DESC(ring, i); bi = &ring->rx_buffer_info[i]; i -= ring->count; @@ -2387,6 +2411,8 @@ static int igc_xdp_xmit_back(struct igc_adapter *adapter, struct xdp_buff *xdp) nq = txring_txq(ring); __netif_tx_lock(nq, cpu); + /* Avoid transmit queue timeout since we share it with the slow path */ + txq_trans_cond_update(nq); res = igc_xdp_init_tx_descriptor(ring, xdpf); __netif_tx_unlock(nq); return res; @@ -2498,8 +2524,8 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) union igc_adv_rx_desc *rx_desc; struct igc_rx_buffer *rx_buffer; unsigned int size, truesize; + struct igc_xdp_buff ctx; ktime_t timestamp = 0; - struct xdp_buff xdp; int pkt_offset = 0; void *pktbuf; @@ -2528,18 +2554,20 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) if (igc_test_staterr(rx_desc, IGC_RXDADV_STAT_TSIP)) { timestamp = igc_ptp_rx_pktstamp(q_vector->adapter, pktbuf); + ctx.rx_ts = timestamp; pkt_offset = IGC_TS_HDR_LEN; size -= IGC_TS_HDR_LEN; } if (!skb) { - xdp_init_buff(&xdp, truesize, &rx_ring->xdp_rxq); - xdp_prepare_buff(&xdp, pktbuf - igc_rx_offset(rx_ring), + xdp_init_buff(&ctx.xdp, truesize, &rx_ring->xdp_rxq); + xdp_prepare_buff(&ctx.xdp, pktbuf - igc_rx_offset(rx_ring), igc_rx_offset(rx_ring) + pkt_offset, size, true); - xdp_buff_clear_frags_flag(&xdp); + xdp_buff_clear_frags_flag(&ctx.xdp); + ctx.rx_desc = rx_desc; - skb = igc_xdp_run_prog(adapter, &xdp); + skb = igc_xdp_run_prog(adapter, &ctx.xdp); } if (IS_ERR(skb)) { @@ -2561,9 +2589,9 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) } else if (skb) igc_add_rx_frag(rx_ring, rx_buffer, skb, size); else if (ring_uses_build_skb(rx_ring)) - skb = igc_build_skb(rx_ring, rx_buffer, &xdp); + skb = igc_build_skb(rx_ring, rx_buffer, &ctx.xdp); else - skb = igc_construct_skb(rx_ring, rx_buffer, &xdp, + skb = igc_construct_skb(rx_ring, rx_buffer, &ctx.xdp, timestamp); /* exit if we failed to retrieve a buffer */ @@ -2664,6 +2692,15 @@ static void igc_dispatch_skb_zc(struct igc_q_vector *q_vector, napi_gro_receive(&q_vector->napi, skb); } +static struct igc_xdp_buff *xsk_buff_to_igc_ctx(struct xdp_buff *xdp) +{ + /* xdp_buff pointer used by ZC code path is alloc as xdp_buff_xsk. The + * igc_xdp_buff shares its layout with xdp_buff_xsk and private + * igc_xdp_buff fields fall into xdp_buff_xsk->cb + */ + return (struct igc_xdp_buff *)xdp; +} + static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget) { struct igc_adapter *adapter = q_vector->adapter; @@ -2682,6 +2719,7 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget) while (likely(total_packets < budget)) { union igc_adv_rx_desc *desc; struct igc_rx_buffer *bi; + struct igc_xdp_buff *ctx; ktime_t timestamp = 0; unsigned int size; int res; @@ -2699,9 +2737,13 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget) bi = &ring->rx_buffer_info[ntc]; + ctx = xsk_buff_to_igc_ctx(bi->xdp); + ctx->rx_desc = desc; + if (igc_test_staterr(desc, IGC_RXDADV_STAT_TSIP)) { timestamp = igc_ptp_rx_pktstamp(q_vector->adapter, bi->xdp->data); + ctx->rx_ts = timestamp; bi->xdp->data += IGC_TS_HDR_LEN; @@ -2789,6 +2831,9 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring) __netif_tx_lock(nq, cpu); + /* Avoid transmit queue timeout since we share it with the slow path */ + txq_trans_cond_update(nq); + budget = igc_desc_unused(ring); while (xsk_tx_peek_desc(pool, &xdp_desc) && budget--) { @@ -6068,9 +6113,18 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, size_t n; int i; - adapter->qbv_enable = qopt->enable; + switch (qopt->cmd) { + case TAPRIO_CMD_REPLACE: + adapter->qbv_enable = true; + break; + case TAPRIO_CMD_DESTROY: + adapter->qbv_enable = false; + break; + default: + return -EOPNOTSUPP; + } - if (!qopt->enable) + if (!adapter->qbv_enable) return igc_tsn_clear_schedule(adapter); if (qopt->base_time < 0) @@ -6314,6 +6368,9 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, __netif_tx_lock(nq, cpu); + /* Avoid transmit queue timeout since we share it with the slow path */ + txq_trans_cond_update(nq); + drops = 0; for (i = 0; i < num_frames; i++) { int err; @@ -6454,6 +6511,58 @@ u32 igc_rd32(struct igc_hw *hw, u32 reg) return value; } +/* Mapping HW RSS Type to enum xdp_rss_hash_type */ +static enum xdp_rss_hash_type igc_xdp_rss_type[IGC_RSS_TYPE_MAX_TABLE] = { + [IGC_RSS_TYPE_NO_HASH] = XDP_RSS_TYPE_L2, + [IGC_RSS_TYPE_HASH_TCP_IPV4] = XDP_RSS_TYPE_L4_IPV4_TCP, + [IGC_RSS_TYPE_HASH_IPV4] = XDP_RSS_TYPE_L3_IPV4, + [IGC_RSS_TYPE_HASH_TCP_IPV6] = XDP_RSS_TYPE_L4_IPV6_TCP, + [IGC_RSS_TYPE_HASH_IPV6_EX] = XDP_RSS_TYPE_L3_IPV6_EX, + [IGC_RSS_TYPE_HASH_IPV6] = XDP_RSS_TYPE_L3_IPV6, + [IGC_RSS_TYPE_HASH_TCP_IPV6_EX] = XDP_RSS_TYPE_L4_IPV6_TCP_EX, + [IGC_RSS_TYPE_HASH_UDP_IPV4] = XDP_RSS_TYPE_L4_IPV4_UDP, + [IGC_RSS_TYPE_HASH_UDP_IPV6] = XDP_RSS_TYPE_L4_IPV6_UDP, + [IGC_RSS_TYPE_HASH_UDP_IPV6_EX] = XDP_RSS_TYPE_L4_IPV6_UDP_EX, + [10] = XDP_RSS_TYPE_NONE, /* RSS Type above 9 "Reserved" by HW */ + [11] = XDP_RSS_TYPE_NONE, /* keep array sized for SW bit-mask */ + [12] = XDP_RSS_TYPE_NONE, /* to handle future HW revisons */ + [13] = XDP_RSS_TYPE_NONE, + [14] = XDP_RSS_TYPE_NONE, + [15] = XDP_RSS_TYPE_NONE, +}; + +static int igc_xdp_rx_hash(const struct xdp_md *_ctx, u32 *hash, + enum xdp_rss_hash_type *rss_type) +{ + const struct igc_xdp_buff *ctx = (void *)_ctx; + + if (!(ctx->xdp.rxq->dev->features & NETIF_F_RXHASH)) + return -ENODATA; + + *hash = le32_to_cpu(ctx->rx_desc->wb.lower.hi_dword.rss); + *rss_type = igc_xdp_rss_type[igc_rss_type(ctx->rx_desc)]; + + return 0; +} + +static int igc_xdp_rx_timestamp(const struct xdp_md *_ctx, u64 *timestamp) +{ + const struct igc_xdp_buff *ctx = (void *)_ctx; + + if (igc_test_staterr(ctx->rx_desc, IGC_RXDADV_STAT_TSIP)) { + *timestamp = ctx->rx_ts; + + return 0; + } + + return -ENODATA; +} + +static const struct xdp_metadata_ops igc_xdp_metadata_ops = { + .xmo_rx_hash = igc_xdp_rx_hash, + .xmo_rx_timestamp = igc_xdp_rx_timestamp, +}; + /** * igc_probe - Device Initialization Routine * @pdev: PCI device information struct @@ -6527,6 +6636,7 @@ static int igc_probe(struct pci_dev *pdev, hw->hw_addr = adapter->io_addr; netdev->netdev_ops = &igc_netdev_ops; + netdev->xdp_metadata_ops = &igc_xdp_metadata_ops; igc_ethtool_set_ops(netdev); netdev->watchdog_timeo = 5 * HZ; @@ -6554,6 +6664,7 @@ static int igc_probe(struct pci_dev *pdev, netdev->features |= NETIF_F_TSO; netdev->features |= NETIF_F_TSO6; netdev->features |= NETIF_F_TSO_ECN; + netdev->features |= NETIF_F_RXHASH; netdev->features |= NETIF_F_RXCSUM; netdev->features |= NETIF_F_HW_CSUM; netdev->features |= NETIF_F_SCTP_CRC; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 5d83c887a3fc..1726297f2e0d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1256,7 +1256,7 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, if (!__netif_txq_completed_wake(txq, total_packets, total_bytes, ixgbe_desc_unused(tx_ring), TX_WAKE_THRESHOLD, - netif_carrier_ok(tx_ring->netdev) && + !netif_carrier_ok(tx_ring->netdev) || test_bit(__IXGBE_DOWN, &adapter->state))) ++tx_ring->tx_stats.restart_queue; diff --git a/drivers/net/ethernet/marvell/octeontx2/Kconfig b/drivers/net/ethernet/marvell/octeontx2/Kconfig index 993ac180a5db..a32d85d6f599 100644 --- a/drivers/net/ethernet/marvell/octeontx2/Kconfig +++ b/drivers/net/ethernet/marvell/octeontx2/Kconfig @@ -32,6 +32,7 @@ config OCTEONTX2_PF tristate "Marvell OcteonTX2 NIC Physical Function driver" select OCTEONTX2_MBOX select NET_DEVLINK + select PAGE_POOL depends on (64BIT && COMPILE_TEST) || ARM64 select DIMLIB depends on PCI diff --git a/drivers/net/ethernet/marvell/octeontx2/af/common.h b/drivers/net/ethernet/marvell/octeontx2/af/common.h index 8931864ee110..f5bf719a6ccf 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/common.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/common.h @@ -142,7 +142,7 @@ enum nix_scheduler { #define TXSCH_RR_QTM_MAX ((1 << 24) - 1) #define TXSCH_TL1_DFLT_RR_QTM TXSCH_RR_QTM_MAX -#define TXSCH_TL1_DFLT_RR_PRIO (0x1ull) +#define TXSCH_TL1_DFLT_RR_PRIO (0x7ull) #define CN10K_MAX_DWRR_WEIGHT 16384 /* Weight is 14bit on CN10K */ /* Min/Max packet sizes, excluding FCS */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index 9533b1d92960..3b26893efdf8 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -1222,6 +1222,11 @@ static int rvu_dbg_npa_ctx_display(struct seq_file *m, void *unused, int ctype) for (aura = id; aura < max_id; aura++) { aq_req.aura_id = aura; + + /* Skip if queue is uninitialized */ + if (ctype == NPA_AQ_CTYPE_POOL && !test_bit(aura, pfvf->pool_bmap)) + continue; + seq_printf(m, "======%s : %d=======\n", (ctype == NPA_AQ_CTYPE_AURA) ? "AURA" : "POOL", aq_req.aura_id); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 4ad707e758b9..79ed7af0b0a4 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -1691,6 +1691,42 @@ exit: return true; } +static void nix_reset_tx_schedule(struct rvu *rvu, int blkaddr, + int lvl, int schq) +{ + u64 tlx_parent = 0, tlx_schedule = 0; + + switch (lvl) { + case NIX_TXSCH_LVL_TL2: + tlx_parent = NIX_AF_TL2X_PARENT(schq); + tlx_schedule = NIX_AF_TL2X_SCHEDULE(schq); + break; + case NIX_TXSCH_LVL_TL3: + tlx_parent = NIX_AF_TL3X_PARENT(schq); + tlx_schedule = NIX_AF_TL3X_SCHEDULE(schq); + break; + case NIX_TXSCH_LVL_TL4: + tlx_parent = NIX_AF_TL4X_PARENT(schq); + tlx_schedule = NIX_AF_TL4X_SCHEDULE(schq); + break; + case NIX_TXSCH_LVL_MDQ: + /* no need to reset SMQ_CFG as HW clears this CSR + * on SMQ flush + */ + tlx_parent = NIX_AF_MDQX_PARENT(schq); + tlx_schedule = NIX_AF_MDQX_SCHEDULE(schq); + break; + default: + return; + } + + if (tlx_parent) + rvu_write64(rvu, blkaddr, tlx_parent, 0x0); + + if (tlx_schedule) + rvu_write64(rvu, blkaddr, tlx_schedule, 0x0); +} + /* Disable shaping of pkts by a scheduler queue * at a given scheduler level. */ @@ -2039,6 +2075,7 @@ int rvu_mbox_handler_nix_txsch_alloc(struct rvu *rvu, pfvf_map[schq] = TXSCH_MAP(pcifunc, 0); nix_reset_tx_linkcfg(rvu, blkaddr, lvl, schq); nix_reset_tx_shaping(rvu, blkaddr, nixlf, lvl, schq); + nix_reset_tx_schedule(rvu, blkaddr, lvl, schq); } for (idx = 0; idx < req->schq[lvl]; idx++) { @@ -2048,6 +2085,7 @@ int rvu_mbox_handler_nix_txsch_alloc(struct rvu *rvu, pfvf_map[schq] = TXSCH_MAP(pcifunc, 0); nix_reset_tx_linkcfg(rvu, blkaddr, lvl, schq); nix_reset_tx_shaping(rvu, blkaddr, nixlf, lvl, schq); + nix_reset_tx_schedule(rvu, blkaddr, lvl, schq); } } @@ -2143,6 +2181,7 @@ static int nix_txschq_free(struct rvu *rvu, u16 pcifunc) continue; nix_reset_tx_linkcfg(rvu, blkaddr, lvl, schq); nix_clear_tx_xoff(rvu, blkaddr, lvl, schq); + nix_reset_tx_shaping(rvu, blkaddr, nixlf, lvl, schq); } } nix_clear_tx_xoff(rvu, blkaddr, NIX_TXSCH_LVL_TL1, @@ -2181,6 +2220,7 @@ static int nix_txschq_free(struct rvu *rvu, u16 pcifunc) for (schq = 0; schq < txsch->schq.max; schq++) { if (TXSCH_MAP_FUNC(txsch->pfvf_map[schq]) != pcifunc) continue; + nix_reset_tx_schedule(rvu, blkaddr, lvl, schq); rvu_free_rsrc(&txsch->schq, schq); txsch->pfvf_map[schq] = TXSCH_MAP(0, NIX_TXSCHQ_FREE); } @@ -2240,6 +2280,9 @@ static int nix_txschq_free_one(struct rvu *rvu, */ nix_clear_tx_xoff(rvu, blkaddr, lvl, schq); + nix_reset_tx_linkcfg(rvu, blkaddr, lvl, schq); + nix_reset_tx_shaping(rvu, blkaddr, nixlf, lvl, schq); + /* Flush if it is a SMQ. Onus of disabling * TL2/3 queue links before SMQ flush is on user */ @@ -2249,6 +2292,8 @@ static int nix_txschq_free_one(struct rvu *rvu, goto err; } + nix_reset_tx_schedule(rvu, blkaddr, lvl, schq); + /* Free the resource */ rvu_free_rsrc(&txsch->schq, schq); txsch->pfvf_map[schq] = TXSCH_MAP(0, NIX_TXSCHQ_FREE); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile index 73fdb8798614..5664f768cb0c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile +++ b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile @@ -8,7 +8,7 @@ obj-$(CONFIG_OCTEONTX2_VF) += rvu_nicvf.o otx2_ptp.o rvu_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o \ otx2_flows.o otx2_tc.o cn10k.o otx2_dmac_flt.o \ - otx2_devlink.o + otx2_devlink.o qos_sq.o qos.o rvu_nicvf-y := otx2_vf.o otx2_devlink.o rvu_nicpf-$(CONFIG_DCB) += otx2_dcbnl.o diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c index 8eaa50d0f668..6e2fb24be8c1 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c @@ -239,7 +239,7 @@ static int cn10k_mcs_write_rx_secy(struct otx2_nic *pfvf, cipher = MCS_GCM_AES_128; dev_warn(pfvf->dev, "Unsupported key length\n"); break; - }; + } policy |= FIELD_PREP(MCS_RX_SECY_PLCY_CIP, cipher); policy |= FIELD_PREP(MCS_RX_SECY_PLCY_VAL, secy->validate_frames); @@ -426,13 +426,16 @@ static int cn10k_mcs_write_tx_secy(struct otx2_nic *pfvf, struct mcs_secy_plcy_write_req *req; struct mbox *mbox = &pfvf->mbox; struct macsec_tx_sc *sw_tx_sc; - /* Insert SecTag after 12 bytes (DA+SA)*/ - u8 tag_offset = 12; u8 sectag_tci = 0; + u8 tag_offset; u64 policy; u8 cipher; int ret; + /* Insert SecTag after 12 bytes (DA+SA) or 16 bytes + * if VLAN tag needs to be sent in clear text. + */ + tag_offset = txsc->vlan_dev ? 16 : 12; sw_tx_sc = &secy->tx_sc; mutex_lock(&mbox->lock); @@ -473,7 +476,7 @@ static int cn10k_mcs_write_tx_secy(struct otx2_nic *pfvf, cipher = MCS_GCM_AES_128; dev_warn(pfvf->dev, "Unsupported key length\n"); break; - }; + } policy |= FIELD_PREP(MCS_TX_SECY_PLCY_CIP, cipher); @@ -1163,6 +1166,7 @@ static int cn10k_mdo_add_secy(struct macsec_context *ctx) txsc->encoding_sa = secy->tx_sc.encoding_sa; txsc->last_validate_frames = secy->validate_frames; txsc->last_replay_protect = secy->replay_protect; + txsc->vlan_dev = is_vlan_dev(ctx->netdev); list_add(&txsc->entry, &cfg->txsc_list); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 8a41ad8ca04f..a79cb680bb23 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -89,6 +89,11 @@ int otx2_update_sq_stats(struct otx2_nic *pfvf, int qidx) if (!pfvf->qset.sq) return 0; + if (qidx >= pfvf->hw.non_qos_queues) { + if (!test_bit(qidx - pfvf->hw.non_qos_queues, pfvf->qos.qos_sq_bmap)) + return 0; + } + otx2_nix_sq_op_stats(&sq->stats, pfvf, qidx); return 1; } @@ -513,11 +518,32 @@ void otx2_config_irq_coalescing(struct otx2_nic *pfvf, int qidx) (pfvf->hw.cq_ecount_wait - 1)); } -int __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool, - dma_addr_t *dma) +static int otx2_alloc_pool_buf(struct otx2_nic *pfvf, struct otx2_pool *pool, + dma_addr_t *dma) +{ + unsigned int offset = 0; + struct page *page; + size_t sz; + + sz = SKB_DATA_ALIGN(pool->rbsize); + sz = ALIGN(sz, OTX2_ALIGN); + + page = page_pool_alloc_frag(pool->page_pool, &offset, sz, GFP_ATOMIC); + if (unlikely(!page)) + return -ENOMEM; + + *dma = page_pool_get_dma_addr(page) + offset; + return 0; +} + +static int __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool, + dma_addr_t *dma) { u8 *buf; + if (pool->page_pool) + return otx2_alloc_pool_buf(pfvf, pool, dma); + buf = napi_alloc_frag_align(pool->rbsize, OTX2_ALIGN); if (unlikely(!buf)) return -ENOMEM; @@ -532,8 +558,8 @@ int __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool, return 0; } -static int otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool, - dma_addr_t *dma) +int otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool, + dma_addr_t *dma) { int ret; @@ -716,7 +742,8 @@ EXPORT_SYMBOL(otx2_smq_flush); int otx2_txsch_alloc(struct otx2_nic *pfvf) { struct nix_txsch_alloc_req *req; - int lvl; + struct nix_txsch_alloc_rsp *rsp; + int lvl, schq, rc; /* Get memory to put this msg */ req = otx2_mbox_alloc_msg_nix_txsch_alloc(&pfvf->mbox); @@ -726,43 +753,83 @@ int otx2_txsch_alloc(struct otx2_nic *pfvf) /* Request one schq per level */ for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) req->schq[lvl] = 1; + rc = otx2_sync_mbox_msg(&pfvf->mbox); + if (rc) + return rc; - return otx2_sync_mbox_msg(&pfvf->mbox); + rsp = (struct nix_txsch_alloc_rsp *) + otx2_mbox_get_rsp(&pfvf->mbox.mbox, 0, &req->hdr); + if (IS_ERR(rsp)) + return PTR_ERR(rsp); + + /* Setup transmit scheduler list */ + for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) + for (schq = 0; schq < rsp->schq[lvl]; schq++) + pfvf->hw.txschq_list[lvl][schq] = + rsp->schq_list[lvl][schq]; + + pfvf->hw.txschq_link_cfg_lvl = rsp->link_cfg_lvl; + + return 0; } -int otx2_txschq_stop(struct otx2_nic *pfvf) +void otx2_txschq_free_one(struct otx2_nic *pfvf, u16 lvl, u16 schq) { struct nix_txsch_free_req *free_req; - int lvl, schq, err; + int err; mutex_lock(&pfvf->mbox.lock); - /* Free the transmit schedulers */ + free_req = otx2_mbox_alloc_msg_nix_txsch_free(&pfvf->mbox); if (!free_req) { mutex_unlock(&pfvf->mbox.lock); - return -ENOMEM; + netdev_err(pfvf->netdev, + "Failed alloc txschq free req\n"); + return; } - free_req->flags = TXSCHQ_FREE_ALL; + free_req->schq_lvl = lvl; + free_req->schq = schq; + err = otx2_sync_mbox_msg(&pfvf->mbox); + if (err) { + netdev_err(pfvf->netdev, + "Failed stop txschq %d at level %d\n", schq, lvl); + } + mutex_unlock(&pfvf->mbox.lock); +} + +void otx2_txschq_stop(struct otx2_nic *pfvf) +{ + int lvl, schq; + + /* free non QOS TLx nodes */ + for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) + otx2_txschq_free_one(pfvf, lvl, + pfvf->hw.txschq_list[lvl][0]); /* Clear the txschq list */ for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) { for (schq = 0; schq < MAX_TXSCHQ_PER_FUNC; schq++) pfvf->hw.txschq_list[lvl][schq] = 0; } - return err; + } void otx2_sqb_flush(struct otx2_nic *pfvf) { int qidx, sqe_tail, sqe_head; + struct otx2_snd_queue *sq; u64 incr, *ptr, val; int timeout = 1000; ptr = (u64 *)otx2_get_regaddr(pfvf, NIX_LF_SQ_OP_STATUS); - for (qidx = 0; qidx < pfvf->hw.tot_tx_queues; qidx++) { + for (qidx = 0; qidx < otx2_get_total_tx_queues(pfvf); qidx++) { + sq = &pfvf->qset.sq[qidx]; + if (!sq->sqb_ptrs) + continue; + incr = (u64)qidx << 32; while (timeout) { val = otx2_atomic64_add(incr, ptr); @@ -862,7 +929,7 @@ int otx2_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura) return otx2_sync_mbox_msg(&pfvf->mbox); } -static int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura) +int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura) { struct otx2_qset *qset = &pfvf->qset; struct otx2_snd_queue *sq; @@ -935,9 +1002,17 @@ static int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx) cq->cint_idx = qidx - pfvf->hw.rx_queues; cq->cqe_cnt = qset->sqe_cnt; } else { - cq->cq_type = CQ_XDP; - cq->cint_idx = qidx - non_xdp_queues; - cq->cqe_cnt = qset->sqe_cnt; + if (pfvf->hw.xdp_queues && + qidx < non_xdp_queues + pfvf->hw.xdp_queues) { + cq->cq_type = CQ_XDP; + cq->cint_idx = qidx - non_xdp_queues; + cq->cqe_cnt = qset->sqe_cnt; + } else { + cq->cq_type = CQ_QOS; + cq->cint_idx = qidx - non_xdp_queues - + pfvf->hw.xdp_queues; + cq->cqe_cnt = qset->sqe_cnt; + } } cq->cqe_size = pfvf->qset.xqe_size; @@ -1048,7 +1123,7 @@ int otx2_config_nix_queues(struct otx2_nic *pfvf) } /* Initialize TX queues */ - for (qidx = 0; qidx < pfvf->hw.tot_tx_queues; qidx++) { + for (qidx = 0; qidx < pfvf->hw.non_qos_queues; qidx++) { u16 sqb_aura = otx2_get_pool_idx(pfvf, AURA_NIX_SQ, qidx); err = otx2_sq_init(pfvf, qidx, sqb_aura); @@ -1095,7 +1170,7 @@ int otx2_config_nix(struct otx2_nic *pfvf) /* Set RQ/SQ/CQ counts */ nixlf->rq_cnt = pfvf->hw.rx_queues; - nixlf->sq_cnt = pfvf->hw.tot_tx_queues; + nixlf->sq_cnt = otx2_get_total_tx_queues(pfvf); nixlf->cq_cnt = pfvf->qset.cq_cnt; nixlf->rss_sz = MAX_RSS_INDIR_TBL_SIZE; nixlf->rss_grps = MAX_RSS_GROUPS; @@ -1133,7 +1208,7 @@ void otx2_sq_free_sqbs(struct otx2_nic *pfvf) int sqb, qidx; u64 iova, pa; - for (qidx = 0; qidx < hw->tot_tx_queues; qidx++) { + for (qidx = 0; qidx < otx2_get_total_tx_queues(pfvf); qidx++) { sq = &qset->sq[qidx]; if (!sq->sqb_ptrs) continue; @@ -1151,10 +1226,31 @@ void otx2_sq_free_sqbs(struct otx2_nic *pfvf) } } +void otx2_free_bufs(struct otx2_nic *pfvf, struct otx2_pool *pool, + u64 iova, int size) +{ + struct page *page; + u64 pa; + + pa = otx2_iova_to_phys(pfvf->iommu_domain, iova); + page = virt_to_head_page(phys_to_virt(pa)); + + if (pool->page_pool) { + page_pool_put_full_page(pool->page_pool, page, true); + } else { + dma_unmap_page_attrs(pfvf->dev, iova, size, + DMA_FROM_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC); + + put_page(page); + } +} + void otx2_free_aura_ptr(struct otx2_nic *pfvf, int type) { int pool_id, pool_start = 0, pool_end = 0, size = 0; - u64 iova, pa; + struct otx2_pool *pool; + u64 iova; if (type == AURA_NIX_SQ) { pool_start = otx2_get_pool_idx(pfvf, type, 0); @@ -1170,15 +1266,13 @@ void otx2_free_aura_ptr(struct otx2_nic *pfvf, int type) /* Free SQB and RQB pointers from the aura pool */ for (pool_id = pool_start; pool_id < pool_end; pool_id++) { iova = otx2_aura_allocptr(pfvf, pool_id); + pool = &pfvf->qset.pool[pool_id]; while (iova) { if (type == AURA_NIX_RQ) iova -= OTX2_HEAD_ROOM; - pa = otx2_iova_to_phys(pfvf->iommu_domain, iova); - dma_unmap_page_attrs(pfvf->dev, iova, size, - DMA_FROM_DEVICE, - DMA_ATTR_SKIP_CPU_SYNC); - put_page(virt_to_page(phys_to_virt(pa))); + otx2_free_bufs(pfvf, pool, iova, size); + iova = otx2_aura_allocptr(pfvf, pool_id); } } @@ -1196,13 +1290,15 @@ void otx2_aura_pool_free(struct otx2_nic *pfvf) pool = &pfvf->qset.pool[pool_id]; qmem_free(pfvf->dev, pool->stack); qmem_free(pfvf->dev, pool->fc_addr); + page_pool_destroy(pool->page_pool); + pool->page_pool = NULL; } devm_kfree(pfvf->dev, pfvf->qset.pool); pfvf->qset.pool = NULL; } -static int otx2_aura_init(struct otx2_nic *pfvf, int aura_id, - int pool_id, int numptrs) +int otx2_aura_init(struct otx2_nic *pfvf, int aura_id, + int pool_id, int numptrs) { struct npa_aq_enq_req *aq; struct otx2_pool *pool; @@ -1278,9 +1374,10 @@ static int otx2_aura_init(struct otx2_nic *pfvf, int aura_id, return 0; } -static int otx2_pool_init(struct otx2_nic *pfvf, u16 pool_id, - int stack_pages, int numptrs, int buf_size) +int otx2_pool_init(struct otx2_nic *pfvf, u16 pool_id, + int stack_pages, int numptrs, int buf_size, int type) { + struct page_pool_params pp_params = { 0 }; struct npa_aq_enq_req *aq; struct otx2_pool *pool; int err; @@ -1324,6 +1421,22 @@ static int otx2_pool_init(struct otx2_nic *pfvf, u16 pool_id, aq->ctype = NPA_AQ_CTYPE_POOL; aq->op = NPA_AQ_INSTOP_INIT; + if (type != AURA_NIX_RQ) { + pool->page_pool = NULL; + return 0; + } + + pp_params.flags = PP_FLAG_PAGE_FRAG | PP_FLAG_DMA_MAP; + pp_params.pool_size = numptrs; + pp_params.nid = NUMA_NO_NODE; + pp_params.dev = pfvf->dev; + pp_params.dma_dir = DMA_FROM_DEVICE; + pool->page_pool = page_pool_create(&pp_params); + if (IS_ERR(pool->page_pool)) { + netdev_err(pfvf->netdev, "Creation of page pool failed\n"); + return PTR_ERR(pool->page_pool); + } + return 0; } @@ -1349,7 +1462,7 @@ int otx2_sq_aura_pool_init(struct otx2_nic *pfvf) stack_pages = (num_sqbs + hw->stack_pg_ptrs - 1) / hw->stack_pg_ptrs; - for (qidx = 0; qidx < hw->tot_tx_queues; qidx++) { + for (qidx = 0; qidx < hw->non_qos_queues; qidx++) { pool_id = otx2_get_pool_idx(pfvf, AURA_NIX_SQ, qidx); /* Initialize aura context */ err = otx2_aura_init(pfvf, pool_id, pool_id, num_sqbs); @@ -1358,7 +1471,7 @@ int otx2_sq_aura_pool_init(struct otx2_nic *pfvf) /* Initialize pool context */ err = otx2_pool_init(pfvf, pool_id, stack_pages, - num_sqbs, hw->sqb_size); + num_sqbs, hw->sqb_size, AURA_NIX_SQ); if (err) goto fail; } @@ -1369,7 +1482,7 @@ int otx2_sq_aura_pool_init(struct otx2_nic *pfvf) goto fail; /* Allocate pointers and free them to aura/pool */ - for (qidx = 0; qidx < hw->tot_tx_queues; qidx++) { + for (qidx = 0; qidx < hw->non_qos_queues; qidx++) { pool_id = otx2_get_pool_idx(pfvf, AURA_NIX_SQ, qidx); pool = &pfvf->qset.pool[pool_id]; @@ -1421,7 +1534,7 @@ int otx2_rq_aura_pool_init(struct otx2_nic *pfvf) } for (pool_id = 0; pool_id < hw->rqpool_cnt; pool_id++) { err = otx2_pool_init(pfvf, pool_id, stack_pages, - num_ptrs, pfvf->rbsize); + num_ptrs, pfvf->rbsize, AURA_NIX_RQ); if (err) goto fail; } @@ -1605,7 +1718,6 @@ int otx2_nix_config_bp(struct otx2_nic *pfvf, bool enable) req->bpid_per_chan = 0; #endif - return otx2_sync_mbox_msg(&pfvf->mbox); } EXPORT_SYMBOL(otx2_nix_config_bp); @@ -1629,21 +1741,6 @@ void mbox_handler_cgx_fec_stats(struct otx2_nic *pfvf, pfvf->hw.cgx_fec_uncorr_blks += rsp->fec_uncorr_blks; } -void mbox_handler_nix_txsch_alloc(struct otx2_nic *pf, - struct nix_txsch_alloc_rsp *rsp) -{ - int lvl, schq; - - /* Setup transmit scheduler list */ - for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) - for (schq = 0; schq < rsp->schq[lvl]; schq++) - pf->hw.txschq_list[lvl][schq] = - rsp->schq_list[lvl][schq]; - - pf->hw.txschq_link_cfg_lvl = rsp->link_cfg_lvl; -} -EXPORT_SYMBOL(mbox_handler_nix_txsch_alloc); - void mbox_handler_npa_lf_alloc(struct otx2_nic *pfvf, struct npa_lf_alloc_rsp *rsp) { diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index d17274aab374..a9ed15d1793a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -28,6 +28,7 @@ #include "otx2_txrx.h" #include "otx2_devlink.h" #include <rvu_trace.h> +#include "qos.h" /* IPv4 flag more fragment bit */ #define IPV4_FLAG_MORE 0x20 @@ -184,13 +185,29 @@ struct mbox { int up_num_msgs; /* mbox_up number of messages */ }; +/* Egress rate limiting definitions */ +#define MAX_BURST_EXPONENT 0x0FULL +#define MAX_BURST_MANTISSA 0xFFULL +#define MAX_BURST_SIZE 130816ULL +#define MAX_RATE_DIVIDER_EXPONENT 12ULL +#define MAX_RATE_EXPONENT 0x0FULL +#define MAX_RATE_MANTISSA 0xFFULL + +/* Bitfields in NIX_TLX_PIR register */ +#define TLX_RATE_MANTISSA GENMASK_ULL(8, 1) +#define TLX_RATE_EXPONENT GENMASK_ULL(12, 9) +#define TLX_RATE_DIVIDER_EXPONENT GENMASK_ULL(16, 13) +#define TLX_BURST_MANTISSA GENMASK_ULL(36, 29) +#define TLX_BURST_EXPONENT GENMASK_ULL(40, 37) + struct otx2_hw { struct pci_dev *pdev; struct otx2_rss_info rss_info; u16 rx_queues; u16 tx_queues; u16 xdp_queues; - u16 tot_tx_queues; + u16 tc_tx_queues; + u16 non_qos_queues; /* tx queues plus xdp queues */ u16 max_queues; u16 pool_cnt; u16 rqpool_cnt; @@ -251,6 +268,7 @@ struct otx2_hw { #define CN10K_RPM 3 #define CN10K_PTP_ONESTEP 4 #define CN10K_HW_MACSEC 5 +#define QOS_CIR_PIR_SUPPORT 6 unsigned long cap_flag; #define LMT_LINE_SIZE 128 @@ -401,6 +419,7 @@ struct cn10k_mcs_txsc { u8 encoding_sa; u8 salt[CN10K_MCS_SA_PER_SC][MACSEC_SALT_LEN]; ssci_t ssci[CN10K_MCS_SA_PER_SC]; + bool vlan_dev; /* macsec running on VLAN ? */ }; struct cn10k_mcs_rxsc { @@ -506,6 +525,8 @@ struct otx2_nic { u16 pfc_schq_list[NIX_TXSCH_LVL_CNT][MAX_TXSCHQ_PER_FUNC]; bool pfc_alloc_status[NIX_PF_PFC_PRIO_MAX]; #endif + /* qos */ + struct otx2_qos qos; /* napi event count. It is needed for adaptive irq coalescing. */ u32 napi_events; @@ -587,6 +608,7 @@ static inline void otx2_setup_dev_hw_settings(struct otx2_nic *pfvf) __set_bit(CN10K_LMTST, &hw->cap_flag); __set_bit(CN10K_RPM, &hw->cap_flag); __set_bit(CN10K_PTP_ONESTEP, &hw->cap_flag); + __set_bit(QOS_CIR_PIR_SUPPORT, &hw->cap_flag); } if (is_dev_cn10kb(pfvf->pdev)) @@ -750,8 +772,7 @@ static inline void cn10k_aura_freeptr(void *dev, int aura, u64 buf) /* Alloc pointer from pool/aura */ static inline u64 otx2_aura_allocptr(struct otx2_nic *pfvf, int aura) { - u64 *ptr = (u64 *)otx2_get_regaddr(pfvf, - NPA_LF_AURA_OP_ALLOCX(0)); + u64 *ptr = (__force u64 *)otx2_get_regaddr(pfvf, NPA_LF_AURA_OP_ALLOCX(0)); u64 incr = (u64)aura | BIT_ULL(63); return otx2_atomic64_add(incr, ptr); @@ -893,12 +914,34 @@ static inline void otx2_dma_unmap_page(struct otx2_nic *pfvf, static inline u16 otx2_get_smq_idx(struct otx2_nic *pfvf, u16 qidx) { + u16 smq; #ifdef CONFIG_DCB if (qidx < NIX_PF_PFC_PRIO_MAX && pfvf->pfc_alloc_status[qidx]) return pfvf->pfc_schq_list[NIX_TXSCH_LVL_SMQ][qidx]; #endif + /* check if qidx falls under QOS queues */ + if (qidx >= pfvf->hw.non_qos_queues) + smq = pfvf->qos.qid_to_sqmap[qidx - pfvf->hw.non_qos_queues]; + else + smq = pfvf->hw.txschq_list[NIX_TXSCH_LVL_SMQ][0]; + + return smq; +} + +static inline u16 otx2_get_total_tx_queues(struct otx2_nic *pfvf) +{ + return pfvf->hw.non_qos_queues + pfvf->hw.tc_tx_queues; +} + +static inline u64 otx2_convert_rate(u64 rate) +{ + u64 converted_rate; + + /* Convert bytes per second to Mbps */ + converted_rate = rate * 8; + converted_rate = max_t(u64, converted_rate / 1000000, 1); - return pfvf->hw.txschq_list[NIX_TXSCH_LVL_SMQ][0]; + return converted_rate; } /* MSI-X APIs */ @@ -925,19 +968,25 @@ int otx2_config_nix(struct otx2_nic *pfvf); int otx2_config_nix_queues(struct otx2_nic *pfvf); int otx2_txschq_config(struct otx2_nic *pfvf, int lvl, int prio, bool pfc_en); int otx2_txsch_alloc(struct otx2_nic *pfvf); -int otx2_txschq_stop(struct otx2_nic *pfvf); +void otx2_txschq_stop(struct otx2_nic *pfvf); +void otx2_txschq_free_one(struct otx2_nic *pfvf, u16 lvl, u16 schq); void otx2_sqb_flush(struct otx2_nic *pfvf); -int __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool, - dma_addr_t *dma); +int otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool, + dma_addr_t *dma); int otx2_rxtx_enable(struct otx2_nic *pfvf, bool enable); void otx2_ctx_disable(struct mbox *mbox, int type, bool npa); int otx2_nix_config_bp(struct otx2_nic *pfvf, bool enable); -void otx2_cleanup_rx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq); +void otx2_cleanup_rx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq, int qidx); void otx2_cleanup_tx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq); +int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura); int otx2_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura); int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura); int otx2_alloc_buffer(struct otx2_nic *pfvf, struct otx2_cq_queue *cq, dma_addr_t *dma); +int otx2_pool_init(struct otx2_nic *pfvf, u16 pool_id, + int stack_pages, int numptrs, int buf_size, int type); +int otx2_aura_init(struct otx2_nic *pfvf, int aura_id, + int pool_id, int numptrs); /* RSS configuration APIs*/ int otx2_rss_init(struct otx2_nic *pfvf); @@ -1005,6 +1054,8 @@ u16 otx2_get_max_mtu(struct otx2_nic *pfvf); int otx2_handle_ntuple_tc_features(struct net_device *netdev, netdev_features_t features); int otx2_smq_flush(struct otx2_nic *pfvf, int smq); +void otx2_free_bufs(struct otx2_nic *pfvf, struct otx2_pool *pool, + u64 iova, int size); /* tc support */ int otx2_init_tc(struct otx2_nic *nic); @@ -1045,4 +1096,24 @@ static inline void cn10k_handle_mcs_event(struct otx2_nic *pfvf, {} #endif /* CONFIG_MACSEC */ +/* qos support */ +static inline void otx2_qos_init(struct otx2_nic *pfvf, int qos_txqs) +{ + struct otx2_hw *hw = &pfvf->hw; + + hw->tc_tx_queues = qos_txqs; + INIT_LIST_HEAD(&pfvf->qos.qos_tree); + mutex_init(&pfvf->qos.qos_lock); +} + +static inline void otx2_shutdown_qos(struct otx2_nic *pfvf) +{ + mutex_destroy(&pfvf->qos.qos_lock); +} + +u16 otx2_select_queue(struct net_device *netdev, struct sk_buff *skb, + struct net_device *sb_dev); +int otx2_get_txq_by_classid(struct otx2_nic *pfvf, u16 classid); +void otx2_qos_config_txschq(struct otx2_nic *pfvf); +void otx2_clean_qos_queues(struct otx2_nic *pfvf); #endif /* OTX2_COMMON_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c index 0f8d1a69139f..c47d91da32dc 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c @@ -92,10 +92,16 @@ static void otx2_get_qset_strings(struct otx2_nic *pfvf, u8 **data, int qset) *data += ETH_GSTRING_LEN; } } - for (qidx = 0; qidx < pfvf->hw.tx_queues; qidx++) { + + for (qidx = 0; qidx < otx2_get_total_tx_queues(pfvf); qidx++) { for (stats = 0; stats < otx2_n_queue_stats; stats++) { - sprintf(*data, "txq%d: %s", qidx + start_qidx, - otx2_queue_stats[stats].name); + if (qidx >= pfvf->hw.non_qos_queues) + sprintf(*data, "txq_qos%d: %s", + qidx + start_qidx - pfvf->hw.non_qos_queues, + otx2_queue_stats[stats].name); + else + sprintf(*data, "txq%d: %s", qidx + start_qidx, + otx2_queue_stats[stats].name); *data += ETH_GSTRING_LEN; } } @@ -159,7 +165,7 @@ static void otx2_get_qset_stats(struct otx2_nic *pfvf, [otx2_queue_stats[stat].index]; } - for (qidx = 0; qidx < pfvf->hw.tx_queues; qidx++) { + for (qidx = 0; qidx < otx2_get_total_tx_queues(pfvf); qidx++) { if (!otx2_update_sq_stats(pfvf, qidx)) { for (stat = 0; stat < otx2_n_queue_stats; stat++) *((*data)++) = 0; @@ -254,7 +260,7 @@ static int otx2_get_sset_count(struct net_device *netdev, int sset) return -EINVAL; qstats_count = otx2_n_queue_stats * - (pfvf->hw.rx_queues + pfvf->hw.tx_queues); + (pfvf->hw.rx_queues + otx2_get_total_tx_queues(pfvf)); if (!test_bit(CN10K_RPM, &pfvf->hw.cap_flag)) mac_stats = CGX_RX_STATS_COUNT + CGX_TX_STATS_COUNT; otx2_update_lmac_fec_stats(pfvf); @@ -282,7 +288,7 @@ static int otx2_set_channels(struct net_device *dev, { struct otx2_nic *pfvf = netdev_priv(dev); bool if_up = netif_running(dev); - int err = 0; + int err, qos_txqs; if (!channel->rx_count || !channel->tx_count) return -EINVAL; @@ -296,14 +302,19 @@ static int otx2_set_channels(struct net_device *dev, if (if_up) dev->netdev_ops->ndo_stop(dev); - err = otx2_set_real_num_queues(dev, channel->tx_count, + qos_txqs = bitmap_weight(pfvf->qos.qos_sq_bmap, + OTX2_QOS_MAX_LEAF_NODES); + + err = otx2_set_real_num_queues(dev, channel->tx_count + qos_txqs, channel->rx_count); if (err) return err; pfvf->hw.rx_queues = channel->rx_count; pfvf->hw.tx_queues = channel->tx_count; - pfvf->qset.cq_cnt = pfvf->hw.tx_queues + pfvf->hw.rx_queues; + if (pfvf->xdp_prog) + pfvf->hw.xdp_queues = channel->rx_count; + pfvf->hw.non_qos_queues = pfvf->hw.tx_queues + pfvf->hw.xdp_queues; if (if_up) err = dev->netdev_ops->ndo_open(dev); @@ -1405,7 +1416,7 @@ static int otx2vf_get_sset_count(struct net_device *netdev, int sset) return -EINVAL; qstats_count = otx2_n_queue_stats * - (vf->hw.rx_queues + vf->hw.tx_queues); + (vf->hw.rx_queues + otx2_get_total_tx_queues(vf)); return otx2_n_dev_stats + otx2_n_drv_stats + qstats_count + 1; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 18284ad75157..db3fcab1c8cd 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -23,6 +23,7 @@ #include "otx2_struct.h" #include "otx2_ptp.h" #include "cn10k.h" +#include "qos.h" #include <rvu_trace.h> #define DRV_NAME "rvu_nicpf" @@ -791,10 +792,6 @@ static void otx2_process_pfaf_mbox_msg(struct otx2_nic *pf, case MBOX_MSG_NIX_LF_ALLOC: mbox_handler_nix_lf_alloc(pf, (struct nix_lf_alloc_rsp *)msg); break; - case MBOX_MSG_NIX_TXSCH_ALLOC: - mbox_handler_nix_txsch_alloc(pf, - (struct nix_txsch_alloc_rsp *)msg); - break; case MBOX_MSG_NIX_BP_ENABLE: mbox_handler_nix_bp_enable(pf, (struct nix_bp_cfg_rsp *)msg); break; @@ -1228,6 +1225,7 @@ static char *nix_snd_status_e_str[NIX_SND_STATUS_MAX] = { static irqreturn_t otx2_q_intr_handler(int irq, void *data) { struct otx2_nic *pf = data; + struct otx2_snd_queue *sq; u64 val, *ptr; u64 qidx = 0; @@ -1257,10 +1255,14 @@ static irqreturn_t otx2_q_intr_handler(int irq, void *data) } /* SQ */ - for (qidx = 0; qidx < pf->hw.tot_tx_queues; qidx++) { + for (qidx = 0; qidx < otx2_get_total_tx_queues(pf); qidx++) { u64 sq_op_err_dbg, mnq_err_dbg, snd_err_dbg; u8 sq_op_err_code, mnq_err_code, snd_err_code; + sq = &pf->qset.sq[qidx]; + if (!sq->sqb_ptrs) + continue; + /* Below debug registers captures first errors corresponding to * those registers. We don't have to check against SQ qid as * these are fatal errors. @@ -1383,8 +1385,11 @@ static void otx2_free_sq_res(struct otx2_nic *pf) otx2_ctx_disable(&pf->mbox, NIX_AQ_CTYPE_SQ, false); /* Free SQB pointers */ otx2_sq_free_sqbs(pf); - for (qidx = 0; qidx < pf->hw.tot_tx_queues; qidx++) { + for (qidx = 0; qidx < otx2_get_total_tx_queues(pf); qidx++) { sq = &qset->sq[qidx]; + /* Skip freeing Qos queues if they are not initialized */ + if (!sq->sqe) + continue; qmem_free(pf->dev, sq->sqe); qmem_free(pf->dev, sq->tso_hdrs); kfree(sq->sg); @@ -1433,7 +1438,7 @@ static int otx2_init_hw_resources(struct otx2_nic *pf) * so, aura count = pool count. */ hw->rqpool_cnt = hw->rx_queues; - hw->sqpool_cnt = hw->tot_tx_queues; + hw->sqpool_cnt = otx2_get_total_tx_queues(pf); hw->pool_cnt = hw->rqpool_cnt + hw->sqpool_cnt; /* Maximum hardware supported transmit length */ @@ -1516,8 +1521,7 @@ err_free_nix_queues: otx2_free_cq_res(pf); otx2_ctx_disable(mbox, NIX_AQ_CTYPE_RQ, false); err_free_txsch: - if (otx2_txschq_stop(pf)) - dev_err(pf->dev, "%s failed to stop TX schedulers\n", __func__); + otx2_txschq_stop(pf); err_free_sq_ptrs: otx2_sq_free_sqbs(pf); err_free_rq_ptrs: @@ -1551,22 +1555,24 @@ static void otx2_free_hw_resources(struct otx2_nic *pf) struct nix_lf_free_req *free_req; struct mbox *mbox = &pf->mbox; struct otx2_cq_queue *cq; + struct otx2_pool *pool; struct msg_req *req; - int qidx, err; + int pool_id; + int qidx; /* Ensure all SQE are processed */ otx2_sqb_flush(pf); /* Stop transmission */ - err = otx2_txschq_stop(pf); - if (err) - dev_err(pf->dev, "RVUPF: Failed to stop/free TX schedulers\n"); + otx2_txschq_stop(pf); #ifdef CONFIG_DCB if (pf->pfc_en) otx2_pfc_txschq_stop(pf); #endif + otx2_clean_qos_queues(pf); + mutex_lock(&mbox->lock); /* Disable backpressure */ if (!(pf->pcifunc & RVU_PFVF_FUNC_MASK)) @@ -1580,7 +1586,7 @@ static void otx2_free_hw_resources(struct otx2_nic *pf) for (qidx = 0; qidx < qset->cq_cnt; qidx++) { cq = &qset->cq[qidx]; if (cq->cq_type == CQ_RX) - otx2_cleanup_rx_cqes(pf, cq); + otx2_cleanup_rx_cqes(pf, cq, qidx); else otx2_cleanup_tx_cqes(pf, cq); } @@ -1590,6 +1596,13 @@ static void otx2_free_hw_resources(struct otx2_nic *pf) /* Free RQ buffer pointers*/ otx2_free_aura_ptr(pf, AURA_NIX_RQ); + for (qidx = 0; qidx < pf->hw.rx_queues; qidx++) { + pool_id = otx2_get_pool_idx(pf, AURA_NIX_RQ, qidx); + pool = &pf->qset.pool[pool_id]; + page_pool_destroy(pool->page_pool); + pool->page_pool = NULL; + } + otx2_free_cq_res(pf); /* Free all ingress bandwidth profiles allocated */ @@ -1688,11 +1701,14 @@ int otx2_open(struct net_device *netdev) netif_carrier_off(netdev); - pf->qset.cq_cnt = pf->hw.rx_queues + pf->hw.tot_tx_queues; /* RQ and SQs are mapped to different CQs, * so find out max CQ IRQs (i.e CINTs) needed. */ - pf->hw.cint_cnt = max(pf->hw.rx_queues, pf->hw.tx_queues); + pf->hw.cint_cnt = max3(pf->hw.rx_queues, pf->hw.tx_queues, + pf->hw.tc_tx_queues); + + pf->qset.cq_cnt = pf->hw.rx_queues + otx2_get_total_tx_queues(pf); + qset->napi = kcalloc(pf->hw.cint_cnt, sizeof(*cq_poll), GFP_KERNEL); if (!qset->napi) return -ENOMEM; @@ -1708,7 +1724,7 @@ int otx2_open(struct net_device *netdev) if (!qset->cq) goto err_free_mem; - qset->sq = kcalloc(pf->hw.tot_tx_queues, + qset->sq = kcalloc(otx2_get_total_tx_queues(pf), sizeof(struct otx2_snd_queue), GFP_KERNEL); if (!qset->sq) goto err_free_mem; @@ -1743,6 +1759,11 @@ int otx2_open(struct net_device *netdev) else cq_poll->cq_ids[CQ_XDP] = CINT_INVALID_CQ; + cq_poll->cq_ids[CQ_QOS] = (qidx < pf->hw.tc_tx_queues) ? + (qidx + pf->hw.rx_queues + + pf->hw.non_qos_queues) : + CINT_INVALID_CQ; + cq_poll->dev = (void *)pf; cq_poll->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_CQE; INIT_WORK(&cq_poll->dim.work, otx2_dim_work); @@ -1826,6 +1847,9 @@ int otx2_open(struct net_device *netdev) /* 'intf_down' may be checked on any cpu */ smp_wmb(); + /* Enable QoS configuration before starting tx queues */ + otx2_qos_config_txschq(pf); + /* we have already received link status notification */ if (pf->linfo.link_up && !(pf->pcifunc & RVU_PFVF_FUNC_MASK)) otx2_handle_link_event(pf); @@ -1947,6 +1971,12 @@ static netdev_tx_t otx2_xmit(struct sk_buff *skb, struct net_device *netdev) int qidx = skb_get_queue_mapping(skb); struct otx2_snd_queue *sq; struct netdev_queue *txq; + int sq_idx; + + /* XDP SQs are not mapped with TXQs + * advance qid to derive correct sq mapped with QOS + */ + sq_idx = (qidx >= pf->hw.tx_queues) ? (qidx + pf->hw.xdp_queues) : qidx; /* Check for minimum and maximum packet length */ if (skb->len <= ETH_HLEN || @@ -1955,7 +1985,7 @@ static netdev_tx_t otx2_xmit(struct sk_buff *skb, struct net_device *netdev) return NETDEV_TX_OK; } - sq = &pf->qset.sq[qidx]; + sq = &pf->qset.sq[sq_idx]; txq = netdev_get_tx_queue(netdev, qidx); if (!otx2_sq_append_skb(netdev, sq, skb, qidx)) { @@ -1973,14 +2003,48 @@ static netdev_tx_t otx2_xmit(struct sk_buff *skb, struct net_device *netdev) return NETDEV_TX_OK; } -static u16 otx2_select_queue(struct net_device *netdev, struct sk_buff *skb, - struct net_device *sb_dev) +static int otx2_qos_select_htb_queue(struct otx2_nic *pf, struct sk_buff *skb, + u16 htb_maj_id) +{ + u16 classid; + + if ((TC_H_MAJ(skb->priority) >> 16) == htb_maj_id) + classid = TC_H_MIN(skb->priority); + else + classid = READ_ONCE(pf->qos.defcls); + + if (!classid) + return 0; + + return otx2_get_txq_by_classid(pf, classid); +} + +u16 otx2_select_queue(struct net_device *netdev, struct sk_buff *skb, + struct net_device *sb_dev) { -#ifdef CONFIG_DCB struct otx2_nic *pf = netdev_priv(netdev); + bool qos_enabled; +#ifdef CONFIG_DCB u8 vlan_prio; #endif + int txq; + + qos_enabled = (netdev->real_num_tx_queues > pf->hw.tx_queues) ? true : false; + if (unlikely(qos_enabled)) { + /* This smp_load_acquire() pairs with smp_store_release() in + * otx2_qos_root_add() called from htb offload root creation + */ + u16 htb_maj_id = smp_load_acquire(&pf->qos.maj_id); + + if (unlikely(htb_maj_id)) { + txq = otx2_qos_select_htb_queue(pf, skb, htb_maj_id); + if (txq > 0) + return txq; + goto process_pfc; + } + } +process_pfc: #ifdef CONFIG_DCB if (!skb_vlan_tag_present(skb)) goto pick_tx; @@ -1994,8 +2058,13 @@ static u16 otx2_select_queue(struct net_device *netdev, struct sk_buff *skb, pick_tx: #endif - return netdev_pick_tx(netdev, skb, NULL); + txq = netdev_pick_tx(netdev, skb, NULL); + if (unlikely(qos_enabled)) + return txq % pf->hw.tx_queues; + + return txq; } +EXPORT_SYMBOL(otx2_select_queue); static netdev_features_t otx2_fix_features(struct net_device *dev, netdev_features_t features) @@ -2529,7 +2598,7 @@ static int otx2_xdp_setup(struct otx2_nic *pf, struct bpf_prog *prog) xdp_features_clear_redirect_target(dev); } - pf->hw.tot_tx_queues += pf->hw.xdp_queues; + pf->hw.non_qos_queues += pf->hw.xdp_queues; if (if_up) otx2_open(pf->netdev); @@ -2712,10 +2781,10 @@ static void otx2_sriov_vfcfg_cleanup(struct otx2_nic *pf) static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct device *dev = &pdev->dev; + int err, qcount, qos_txqs; struct net_device *netdev; struct otx2_nic *pf; struct otx2_hw *hw; - int err, qcount; int num_vec; err = pcim_enable_device(pdev); @@ -2740,8 +2809,9 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) /* Set number of queues */ qcount = min_t(int, num_online_cpus(), OTX2_MAX_CQ_CNT); + qos_txqs = min_t(int, qcount, OTX2_QOS_MAX_LEAF_NODES); - netdev = alloc_etherdev_mqs(sizeof(*pf), qcount, qcount); + netdev = alloc_etherdev_mqs(sizeof(*pf), qcount + qos_txqs, qcount); if (!netdev) { err = -ENOMEM; goto err_release_regions; @@ -2760,7 +2830,7 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) hw->pdev = pdev; hw->rx_queues = qcount; hw->tx_queues = qcount; - hw->tot_tx_queues = qcount; + hw->non_qos_queues = qcount; hw->max_queues = qcount; hw->rbuf_len = OTX2_DEFAULT_RBUF_LEN; /* Use CQE of 128 byte descriptor size by default */ @@ -2929,6 +2999,8 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto err_pf_sriov_init; #endif + otx2_qos_init(pf, qos_txqs); + return 0; err_pf_sriov_init: @@ -3104,6 +3176,7 @@ static void otx2_remove(struct pci_dev *pdev) otx2_ptp_destroy(pf); otx2_mcam_flow_del(pf); otx2_shutdown_tc(pf); + otx2_shutdown_qos(pf); otx2_detach_resources(&pf->mbox); if (pf->hw.lmt_info) free_percpu(pf->hw.lmt_info); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h index 1b967eaf948b..45a32e4b49d1 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h @@ -145,12 +145,25 @@ #define NIX_AF_TL1X_TOPOLOGY(a) (0xC80 | (a) << 16) #define NIX_AF_TL2X_PARENT(a) (0xE88 | (a) << 16) #define NIX_AF_TL2X_SCHEDULE(a) (0xE00 | (a) << 16) +#define NIX_AF_TL2X_TOPOLOGY(a) (0xE80 | (a) << 16) +#define NIX_AF_TL2X_CIR(a) (0xE20 | (a) << 16) +#define NIX_AF_TL2X_PIR(a) (0xE30 | (a) << 16) #define NIX_AF_TL3X_PARENT(a) (0x1088 | (a) << 16) #define NIX_AF_TL3X_SCHEDULE(a) (0x1000 | (a) << 16) +#define NIX_AF_TL3X_SHAPE(a) (0x1010 | (a) << 16) +#define NIX_AF_TL3X_CIR(a) (0x1020 | (a) << 16) +#define NIX_AF_TL3X_PIR(a) (0x1030 | (a) << 16) +#define NIX_AF_TL3X_TOPOLOGY(a) (0x1080 | (a) << 16) #define NIX_AF_TL4X_PARENT(a) (0x1288 | (a) << 16) #define NIX_AF_TL4X_SCHEDULE(a) (0x1200 | (a) << 16) +#define NIX_AF_TL4X_SHAPE(a) (0x1210 | (a) << 16) +#define NIX_AF_TL4X_CIR(a) (0x1220 | (a) << 16) #define NIX_AF_TL4X_PIR(a) (0x1230 | (a) << 16) +#define NIX_AF_TL4X_TOPOLOGY(a) (0x1280 | (a) << 16) #define NIX_AF_MDQX_SCHEDULE(a) (0x1400 | (a) << 16) +#define NIX_AF_MDQX_SHAPE(a) (0x1410 | (a) << 16) +#define NIX_AF_MDQX_CIR(a) (0x1420 | (a) << 16) +#define NIX_AF_MDQX_PIR(a) (0x1430 | (a) << 16) #define NIX_AF_MDQX_PARENT(a) (0x1480 | (a) << 16) #define NIX_AF_TL3_TL2X_LINKX_CFG(a, b) (0x1700 | (a) << 16 | (b) << 3) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c index 8392f63e433f..231c3f0efb60 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c @@ -19,25 +19,11 @@ #include "cn10k.h" #include "otx2_common.h" - -/* Egress rate limiting definitions */ -#define MAX_BURST_EXPONENT 0x0FULL -#define MAX_BURST_MANTISSA 0xFFULL -#define MAX_BURST_SIZE 130816ULL -#define MAX_RATE_DIVIDER_EXPONENT 12ULL -#define MAX_RATE_EXPONENT 0x0FULL -#define MAX_RATE_MANTISSA 0xFFULL +#include "qos.h" #define CN10K_MAX_BURST_MANTISSA 0x7FFFULL #define CN10K_MAX_BURST_SIZE 8453888ULL -/* Bitfields in NIX_TLX_PIR register */ -#define TLX_RATE_MANTISSA GENMASK_ULL(8, 1) -#define TLX_RATE_EXPONENT GENMASK_ULL(12, 9) -#define TLX_RATE_DIVIDER_EXPONENT GENMASK_ULL(16, 13) -#define TLX_BURST_MANTISSA GENMASK_ULL(36, 29) -#define TLX_BURST_EXPONENT GENMASK_ULL(40, 37) - #define CN10K_TLX_BURST_MANTISSA GENMASK_ULL(43, 29) #define CN10K_TLX_BURST_EXPONENT GENMASK_ULL(47, 44) @@ -147,8 +133,8 @@ static void otx2_get_egress_rate_cfg(u64 maxrate, u32 *exp, } } -static u64 otx2_get_txschq_rate_regval(struct otx2_nic *nic, - u64 maxrate, u32 burst) +u64 otx2_get_txschq_rate_regval(struct otx2_nic *nic, + u64 maxrate, u32 burst) { u32 burst_exp, burst_mantissa; u32 exp, mantissa, div_exp; @@ -264,7 +250,6 @@ static int otx2_tc_egress_matchall_install(struct otx2_nic *nic, struct netlink_ext_ack *extack = cls->common.extack; struct flow_action *actions = &cls->rule->action; struct flow_action_entry *entry; - u64 rate; int err; err = otx2_tc_validate_flow(nic, actions, extack); @@ -288,10 +273,8 @@ static int otx2_tc_egress_matchall_install(struct otx2_nic *nic, NL_SET_ERR_MSG_MOD(extack, "QoS offload not support packets per second"); return -EOPNOTSUPP; } - /* Convert bytes per second to Mbps */ - rate = entry->police.rate_bytes_ps * 8; - rate = max_t(u64, rate / 1000000, 1); - err = otx2_set_matchall_egress_rate(nic, entry->police.burst, rate); + err = otx2_set_matchall_egress_rate(nic, entry->police.burst, + otx2_convert_rate(entry->police.rate_bytes_ps)); if (err) return err; nic->flags |= OTX2_FLAG_TC_MATCHALL_EGRESS_ENABLED; @@ -1127,6 +1110,8 @@ int otx2_setup_tc(struct net_device *netdev, enum tc_setup_type type, switch (type) { case TC_SETUP_BLOCK: return otx2_setup_tc_block(netdev, type_data); + case TC_SETUP_QDISC_HTB: + return otx2_setup_tc_htb(netdev, type_data); default: return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c index 7045fedfd73a..e369baf11530 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c @@ -217,9 +217,6 @@ static bool otx2_skb_add_frag(struct otx2_nic *pfvf, struct sk_buff *skb, skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, va - page_address(page) + off, len - off, pfvf->rbsize); - - otx2_dma_unmap_page(pfvf, iova - OTX2_HEAD_ROOM, - pfvf->rbsize, DMA_FROM_DEVICE); return true; } @@ -382,6 +379,8 @@ static void otx2_rcv_pkt_handler(struct otx2_nic *pfvf, if (pfvf->netdev->features & NETIF_F_RXCSUM) skb->ip_summed = CHECKSUM_UNNECESSARY; + skb_mark_for_recycle(skb); + napi_gro_frags(napi); } @@ -464,12 +463,13 @@ process_cqe: break; } - if (cq->cq_type == CQ_XDP) { + qidx = cq->cq_idx - pfvf->hw.rx_queues; + + if (cq->cq_type == CQ_XDP) otx2_xdp_snd_pkt_handler(pfvf, sq, cqe); - } else { - otx2_snd_pkt_handler(pfvf, cq, sq, cqe, budget, - &tx_pkts, &tx_bytes); - } + else + otx2_snd_pkt_handler(pfvf, cq, &pfvf->qset.sq[qidx], + cqe, budget, &tx_pkts, &tx_bytes); cqe->hdr.cqe_type = NIX_XQE_TYPE_INVALID; processed_cqe++; @@ -486,7 +486,11 @@ process_cqe: if (likely(tx_pkts)) { struct netdev_queue *txq; - txq = netdev_get_tx_queue(pfvf->netdev, cq->cint_idx); + qidx = cq->cq_idx - pfvf->hw.rx_queues; + + if (qidx >= pfvf->hw.tx_queues) + qidx -= pfvf->hw.xdp_queues; + txq = netdev_get_tx_queue(pfvf->netdev, qidx); netdev_tx_completed_queue(txq, tx_pkts, tx_bytes); /* Check if queue was stopped earlier due to ring full */ smp_mb(); @@ -652,9 +656,7 @@ static void otx2_sqe_add_ext(struct otx2_nic *pfvf, struct otx2_snd_queue *sq, htons(ext->lso_sb - skb_network_offset(skb)); } else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) { ext->lso_format = pfvf->hw.lso_tsov6_idx; - - ipv6_hdr(skb)->payload_len = - htons(ext->lso_sb - skb_network_offset(skb)); + ipv6_hdr(skb)->payload_len = htons(tcp_hdrlen(skb)); } else if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) { __be16 l3_proto = vlan_get_protocol(skb); struct udphdr *udph = udp_hdr(skb); @@ -736,7 +738,8 @@ static void otx2_sqe_add_hdr(struct otx2_nic *pfvf, struct otx2_snd_queue *sq, sqe_hdr->aura = sq->aura_id; /* Post a CQE Tx after pkt transmission */ sqe_hdr->pnc = 1; - sqe_hdr->sq = qidx; + sqe_hdr->sq = (qidx >= pfvf->hw.tx_queues) ? + qidx + pfvf->hw.xdp_queues : qidx; } sqe_hdr->total = skb->len; /* Set SQE identifier which will be used later for freeing SKB */ @@ -1180,11 +1183,13 @@ bool otx2_sq_append_skb(struct net_device *netdev, struct otx2_snd_queue *sq, } EXPORT_SYMBOL(otx2_sq_append_skb); -void otx2_cleanup_rx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq) +void otx2_cleanup_rx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq, int qidx) { struct nix_cqe_rx_s *cqe; + struct otx2_pool *pool; int processed_cqe = 0; - u64 iova, pa; + u16 pool_id; + u64 iova; if (pfvf->xdp_prog) xdp_rxq_info_unreg(&cq->xdp_rxq); @@ -1192,6 +1197,9 @@ void otx2_cleanup_rx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq) if (otx2_nix_cq_op_status(pfvf, cq) || !cq->pend_cqe) return; + pool_id = otx2_get_pool_idx(pfvf, AURA_NIX_RQ, qidx); + pool = &pfvf->qset.pool[pool_id]; + while (cq->pend_cqe) { cqe = (struct nix_cqe_rx_s *)otx2_get_next_cqe(cq); processed_cqe++; @@ -1204,9 +1212,8 @@ void otx2_cleanup_rx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq) continue; } iova = cqe->sg.seg_addr - OTX2_HEAD_ROOM; - pa = otx2_iova_to_phys(pfvf->iommu_domain, iova); - otx2_dma_unmap_page(pfvf, iova, pfvf->rbsize, DMA_FROM_DEVICE); - put_page(virt_to_page(phys_to_virt(pa))); + + otx2_free_bufs(pfvf, pool, iova, pfvf->rbsize); } /* Free CQEs to HW */ @@ -1221,8 +1228,10 @@ void otx2_cleanup_tx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq) struct nix_cqe_tx_s *cqe; int processed_cqe = 0; struct sg_list *sg; + int qidx; - sq = &pfvf->qset.sq[cq->cint_idx]; + qidx = cq->cq_idx - pfvf->hw.rx_queues; + sq = &pfvf->qset.sq[qidx]; if (otx2_nix_cq_op_status(pfvf, cq) || !cq->pend_cqe) return; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h index 93cac2c2664c..b5d689eeff80 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h @@ -102,7 +102,8 @@ enum cq_type { CQ_RX, CQ_TX, CQ_XDP, - CQS_PER_CINT = 3, /* RQ + SQ + XDP */ + CQ_QOS, + CQS_PER_CINT = 4, /* RQ + SQ + XDP + QOS_SQ */ }; struct otx2_cq_poll { @@ -117,6 +118,7 @@ struct otx2_cq_poll { struct otx2_pool { struct qmem *stack; struct qmem *fc_addr; + struct page_pool *page_pool; u16 rbsize; }; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 53366dbfbf27..3734c799e416 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -70,10 +70,6 @@ static void otx2vf_process_vfaf_mbox_msg(struct otx2_nic *vf, case MBOX_MSG_NIX_LF_ALLOC: mbox_handler_nix_lf_alloc(vf, (struct nix_lf_alloc_rsp *)msg); break; - case MBOX_MSG_NIX_TXSCH_ALLOC: - mbox_handler_nix_txsch_alloc(vf, - (struct nix_txsch_alloc_rsp *)msg); - break; case MBOX_MSG_NIX_BP_ENABLE: mbox_handler_nix_bp_enable(vf, (struct nix_bp_cfg_rsp *)msg); break; @@ -479,6 +475,7 @@ static const struct net_device_ops otx2vf_netdev_ops = { .ndo_open = otx2vf_open, .ndo_stop = otx2vf_stop, .ndo_start_xmit = otx2vf_xmit, + .ndo_select_queue = otx2_select_queue, .ndo_set_rx_mode = otx2vf_set_rx_mode, .ndo_set_mac_address = otx2_set_mac_address, .ndo_change_mtu = otx2vf_change_mtu, @@ -524,10 +521,10 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) { int num_vec = pci_msix_vec_count(pdev); struct device *dev = &pdev->dev; + int err, qcount, qos_txqs; struct net_device *netdev; struct otx2_nic *vf; struct otx2_hw *hw; - int err, qcount; err = pcim_enable_device(pdev); if (err) { @@ -550,7 +547,8 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) pci_set_master(pdev); qcount = num_online_cpus(); - netdev = alloc_etherdev_mqs(sizeof(*vf), qcount, qcount); + qos_txqs = min_t(int, qcount, OTX2_QOS_MAX_LEAF_NODES); + netdev = alloc_etherdev_mqs(sizeof(*vf), qcount + qos_txqs, qcount); if (!netdev) { err = -ENOMEM; goto err_release_regions; @@ -570,7 +568,7 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) hw->rx_queues = qcount; hw->tx_queues = qcount; hw->max_queues = qcount; - hw->tot_tx_queues = qcount; + hw->non_qos_queues = qcount; hw->rbuf_len = OTX2_DEFAULT_RBUF_LEN; /* Use CQE of 128 byte descriptor size by default */ hw->xqe_size = 128; @@ -699,6 +697,7 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (err) goto err_shutdown_tc; #endif + otx2_qos_init(vf, qos_txqs); return 0; @@ -761,6 +760,7 @@ static void otx2vf_remove(struct pci_dev *pdev) otx2_ptp_destroy(vf); otx2_mcam_flow_del(vf); otx2_shutdown_tc(vf); + otx2_shutdown_qos(vf); otx2vf_disable_mbox_intr(vf); otx2_detach_resources(&vf->mbox); free_percpu(vf->hw.lmt_info); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c new file mode 100644 index 000000000000..d3a76c5ccda8 --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c @@ -0,0 +1,1363 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Marvell RVU Ethernet driver + * + * Copyright (C) 2023 Marvell. + * + */ +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/inetdevice.h> +#include <linux/bitfield.h> + +#include "otx2_common.h" +#include "cn10k.h" +#include "qos.h" + +#define OTX2_QOS_QID_INNER 0xFFFFU +#define OTX2_QOS_QID_NONE 0xFFFEU +#define OTX2_QOS_ROOT_CLASSID 0xFFFFFFFF +#define OTX2_QOS_CLASS_NONE 0 +#define OTX2_QOS_DEFAULT_PRIO 0xF +#define OTX2_QOS_INVALID_SQ 0xFFFF + +static void otx2_qos_update_tx_netdev_queues(struct otx2_nic *pfvf) +{ + struct otx2_hw *hw = &pfvf->hw; + int tx_queues, qos_txqs, err; + + qos_txqs = bitmap_weight(pfvf->qos.qos_sq_bmap, + OTX2_QOS_MAX_LEAF_NODES); + + tx_queues = hw->tx_queues + qos_txqs; + + err = netif_set_real_num_tx_queues(pfvf->netdev, tx_queues); + if (err) { + netdev_err(pfvf->netdev, + "Failed to set no of Tx queues: %d\n", tx_queues); + return; + } +} + +static void otx2_qos_get_regaddr(struct otx2_qos_node *node, + struct nix_txschq_config *cfg, + int index) +{ + if (node->level == NIX_TXSCH_LVL_SMQ) { + cfg->reg[index++] = NIX_AF_MDQX_PARENT(node->schq); + cfg->reg[index++] = NIX_AF_MDQX_SCHEDULE(node->schq); + cfg->reg[index++] = NIX_AF_MDQX_PIR(node->schq); + cfg->reg[index] = NIX_AF_MDQX_CIR(node->schq); + } else if (node->level == NIX_TXSCH_LVL_TL4) { + cfg->reg[index++] = NIX_AF_TL4X_PARENT(node->schq); + cfg->reg[index++] = NIX_AF_TL4X_SCHEDULE(node->schq); + cfg->reg[index++] = NIX_AF_TL4X_PIR(node->schq); + cfg->reg[index] = NIX_AF_TL4X_CIR(node->schq); + } else if (node->level == NIX_TXSCH_LVL_TL3) { + cfg->reg[index++] = NIX_AF_TL3X_PARENT(node->schq); + cfg->reg[index++] = NIX_AF_TL3X_SCHEDULE(node->schq); + cfg->reg[index++] = NIX_AF_TL3X_PIR(node->schq); + cfg->reg[index] = NIX_AF_TL3X_CIR(node->schq); + } else if (node->level == NIX_TXSCH_LVL_TL2) { + cfg->reg[index++] = NIX_AF_TL2X_PARENT(node->schq); + cfg->reg[index++] = NIX_AF_TL2X_SCHEDULE(node->schq); + cfg->reg[index++] = NIX_AF_TL2X_PIR(node->schq); + cfg->reg[index] = NIX_AF_TL2X_CIR(node->schq); + } +} + +static void otx2_config_sched_shaping(struct otx2_nic *pfvf, + struct otx2_qos_node *node, + struct nix_txschq_config *cfg, + int *num_regs) +{ + u64 maxrate; + + otx2_qos_get_regaddr(node, cfg, *num_regs); + + /* configure parent txschq */ + cfg->regval[*num_regs] = node->parent->schq << 16; + (*num_regs)++; + + /* configure prio/quantum */ + if (node->qid == OTX2_QOS_QID_NONE) { + cfg->regval[*num_regs] = node->prio << 24 | + mtu_to_dwrr_weight(pfvf, pfvf->tx_max_pktlen); + (*num_regs)++; + return; + } + + /* configure priority */ + cfg->regval[*num_regs] = (node->schq - node->parent->prio_anchor) << 24; + (*num_regs)++; + + /* configure PIR */ + maxrate = (node->rate > node->ceil) ? node->rate : node->ceil; + + cfg->regval[*num_regs] = + otx2_get_txschq_rate_regval(pfvf, maxrate, 65536); + (*num_regs)++; + + /* Don't configure CIR when both CIR+PIR not supported + * On 96xx, CIR + PIR + RED_ALGO=STALL causes deadlock + */ + if (!test_bit(QOS_CIR_PIR_SUPPORT, &pfvf->hw.cap_flag)) + return; + + cfg->regval[*num_regs] = + otx2_get_txschq_rate_regval(pfvf, node->rate, 65536); + (*num_regs)++; +} + +static void __otx2_qos_txschq_cfg(struct otx2_nic *pfvf, + struct otx2_qos_node *node, + struct nix_txschq_config *cfg) +{ + struct otx2_hw *hw = &pfvf->hw; + int num_regs = 0; + u8 level; + + level = node->level; + + /* program txschq registers */ + if (level == NIX_TXSCH_LVL_SMQ) { + cfg->reg[num_regs] = NIX_AF_SMQX_CFG(node->schq); + cfg->regval[num_regs] = ((u64)pfvf->tx_max_pktlen << 8) | + OTX2_MIN_MTU; + cfg->regval[num_regs] |= (0x20ULL << 51) | (0x80ULL << 39) | + (0x2ULL << 36); + num_regs++; + + otx2_config_sched_shaping(pfvf, node, cfg, &num_regs); + + } else if (level == NIX_TXSCH_LVL_TL4) { + otx2_config_sched_shaping(pfvf, node, cfg, &num_regs); + } else if (level == NIX_TXSCH_LVL_TL3) { + /* configure link cfg */ + if (level == pfvf->qos.link_cfg_lvl) { + cfg->reg[num_regs] = NIX_AF_TL3_TL2X_LINKX_CFG(node->schq, hw->tx_link); + cfg->regval[num_regs] = BIT_ULL(13) | BIT_ULL(12); + num_regs++; + } + + otx2_config_sched_shaping(pfvf, node, cfg, &num_regs); + } else if (level == NIX_TXSCH_LVL_TL2) { + /* configure link cfg */ + if (level == pfvf->qos.link_cfg_lvl) { + cfg->reg[num_regs] = NIX_AF_TL3_TL2X_LINKX_CFG(node->schq, hw->tx_link); + cfg->regval[num_regs] = BIT_ULL(13) | BIT_ULL(12); + num_regs++; + } + + /* check if node is root */ + if (node->qid == OTX2_QOS_QID_INNER && !node->parent) { + cfg->reg[num_regs] = NIX_AF_TL2X_SCHEDULE(node->schq); + cfg->regval[num_regs] = TXSCH_TL1_DFLT_RR_PRIO << 24 | + mtu_to_dwrr_weight(pfvf, + pfvf->tx_max_pktlen); + num_regs++; + goto txschq_cfg_out; + } + + otx2_config_sched_shaping(pfvf, node, cfg, &num_regs); + } + +txschq_cfg_out: + cfg->num_regs = num_regs; +} + +static int otx2_qos_txschq_set_parent_topology(struct otx2_nic *pfvf, + struct otx2_qos_node *parent) +{ + struct mbox *mbox = &pfvf->mbox; + struct nix_txschq_config *cfg; + int rc; + + if (parent->level == NIX_TXSCH_LVL_MDQ) + return 0; + + mutex_lock(&mbox->lock); + + cfg = otx2_mbox_alloc_msg_nix_txschq_cfg(&pfvf->mbox); + if (!cfg) { + mutex_unlock(&mbox->lock); + return -ENOMEM; + } + + cfg->lvl = parent->level; + + if (parent->level == NIX_TXSCH_LVL_TL4) + cfg->reg[0] = NIX_AF_TL4X_TOPOLOGY(parent->schq); + else if (parent->level == NIX_TXSCH_LVL_TL3) + cfg->reg[0] = NIX_AF_TL3X_TOPOLOGY(parent->schq); + else if (parent->level == NIX_TXSCH_LVL_TL2) + cfg->reg[0] = NIX_AF_TL2X_TOPOLOGY(parent->schq); + else if (parent->level == NIX_TXSCH_LVL_TL1) + cfg->reg[0] = NIX_AF_TL1X_TOPOLOGY(parent->schq); + + cfg->regval[0] = (u64)parent->prio_anchor << 32; + if (parent->level == NIX_TXSCH_LVL_TL1) + cfg->regval[0] |= (u64)TXSCH_TL1_DFLT_RR_PRIO << 1; + + cfg->num_regs++; + + rc = otx2_sync_mbox_msg(&pfvf->mbox); + + mutex_unlock(&mbox->lock); + + return rc; +} + +static void otx2_qos_free_hw_node_schq(struct otx2_nic *pfvf, + struct otx2_qos_node *parent) +{ + struct otx2_qos_node *node; + + list_for_each_entry_reverse(node, &parent->child_schq_list, list) + otx2_txschq_free_one(pfvf, node->level, node->schq); +} + +static void otx2_qos_free_hw_node(struct otx2_nic *pfvf, + struct otx2_qos_node *parent) +{ + struct otx2_qos_node *node, *tmp; + + list_for_each_entry_safe(node, tmp, &parent->child_list, list) { + otx2_qos_free_hw_node(pfvf, node); + otx2_qos_free_hw_node_schq(pfvf, node); + otx2_txschq_free_one(pfvf, node->level, node->schq); + } +} + +static void otx2_qos_free_hw_cfg(struct otx2_nic *pfvf, + struct otx2_qos_node *node) +{ + mutex_lock(&pfvf->qos.qos_lock); + + /* free child node hw mappings */ + otx2_qos_free_hw_node(pfvf, node); + otx2_qos_free_hw_node_schq(pfvf, node); + + /* free node hw mappings */ + otx2_txschq_free_one(pfvf, node->level, node->schq); + + mutex_unlock(&pfvf->qos.qos_lock); +} + +static void otx2_qos_sw_node_delete(struct otx2_nic *pfvf, + struct otx2_qos_node *node) +{ + hash_del_rcu(&node->hlist); + + if (node->qid != OTX2_QOS_QID_INNER && node->qid != OTX2_QOS_QID_NONE) { + __clear_bit(node->qid, pfvf->qos.qos_sq_bmap); + otx2_qos_update_tx_netdev_queues(pfvf); + } + + list_del(&node->list); + kfree(node); +} + +static void otx2_qos_free_sw_node_schq(struct otx2_nic *pfvf, + struct otx2_qos_node *parent) +{ + struct otx2_qos_node *node, *tmp; + + list_for_each_entry_safe(node, tmp, &parent->child_schq_list, list) { + list_del(&node->list); + kfree(node); + } +} + +static void __otx2_qos_free_sw_node(struct otx2_nic *pfvf, + struct otx2_qos_node *parent) +{ + struct otx2_qos_node *node, *tmp; + + list_for_each_entry_safe(node, tmp, &parent->child_list, list) { + __otx2_qos_free_sw_node(pfvf, node); + otx2_qos_free_sw_node_schq(pfvf, node); + otx2_qos_sw_node_delete(pfvf, node); + } +} + +static void otx2_qos_free_sw_node(struct otx2_nic *pfvf, + struct otx2_qos_node *node) +{ + mutex_lock(&pfvf->qos.qos_lock); + + __otx2_qos_free_sw_node(pfvf, node); + otx2_qos_free_sw_node_schq(pfvf, node); + otx2_qos_sw_node_delete(pfvf, node); + + mutex_unlock(&pfvf->qos.qos_lock); +} + +static void otx2_qos_destroy_node(struct otx2_nic *pfvf, + struct otx2_qos_node *node) +{ + otx2_qos_free_hw_cfg(pfvf, node); + otx2_qos_free_sw_node(pfvf, node); +} + +static void otx2_qos_fill_cfg_schq(struct otx2_qos_node *parent, + struct otx2_qos_cfg *cfg) +{ + struct otx2_qos_node *node; + + list_for_each_entry(node, &parent->child_schq_list, list) + cfg->schq[node->level]++; +} + +static void otx2_qos_fill_cfg_tl(struct otx2_qos_node *parent, + struct otx2_qos_cfg *cfg) +{ + struct otx2_qos_node *node; + + list_for_each_entry(node, &parent->child_list, list) { + otx2_qos_fill_cfg_tl(node, cfg); + cfg->schq_contig[node->level]++; + otx2_qos_fill_cfg_schq(node, cfg); + } +} + +static void otx2_qos_prepare_txschq_cfg(struct otx2_nic *pfvf, + struct otx2_qos_node *parent, + struct otx2_qos_cfg *cfg) +{ + mutex_lock(&pfvf->qos.qos_lock); + otx2_qos_fill_cfg_tl(parent, cfg); + mutex_unlock(&pfvf->qos.qos_lock); +} + +static void otx2_qos_read_txschq_cfg_schq(struct otx2_qos_node *parent, + struct otx2_qos_cfg *cfg) +{ + struct otx2_qos_node *node; + int cnt; + + list_for_each_entry(node, &parent->child_schq_list, list) { + cnt = cfg->dwrr_node_pos[node->level]; + cfg->schq_list[node->level][cnt] = node->schq; + cfg->schq[node->level]++; + cfg->dwrr_node_pos[node->level]++; + } +} + +static void otx2_qos_read_txschq_cfg_tl(struct otx2_qos_node *parent, + struct otx2_qos_cfg *cfg) +{ + struct otx2_qos_node *node; + int cnt; + + list_for_each_entry(node, &parent->child_list, list) { + otx2_qos_read_txschq_cfg_tl(node, cfg); + cnt = cfg->static_node_pos[node->level]; + cfg->schq_contig_list[node->level][cnt] = node->schq; + cfg->schq_contig[node->level]++; + cfg->static_node_pos[node->level]++; + otx2_qos_read_txschq_cfg_schq(node, cfg); + } +} + +static void otx2_qos_read_txschq_cfg(struct otx2_nic *pfvf, + struct otx2_qos_node *node, + struct otx2_qos_cfg *cfg) +{ + mutex_lock(&pfvf->qos.qos_lock); + otx2_qos_read_txschq_cfg_tl(node, cfg); + mutex_unlock(&pfvf->qos.qos_lock); +} + +static struct otx2_qos_node * +otx2_qos_alloc_root(struct otx2_nic *pfvf) +{ + struct otx2_qos_node *node; + + node = kzalloc(sizeof(*node), GFP_KERNEL); + if (!node) + return ERR_PTR(-ENOMEM); + + node->parent = NULL; + if (!is_otx2_vf(pfvf->pcifunc)) + node->level = NIX_TXSCH_LVL_TL1; + else + node->level = NIX_TXSCH_LVL_TL2; + + WRITE_ONCE(node->qid, OTX2_QOS_QID_INNER); + node->classid = OTX2_QOS_ROOT_CLASSID; + + hash_add_rcu(pfvf->qos.qos_hlist, &node->hlist, node->classid); + list_add_tail(&node->list, &pfvf->qos.qos_tree); + INIT_LIST_HEAD(&node->child_list); + INIT_LIST_HEAD(&node->child_schq_list); + + return node; +} + +static int otx2_qos_add_child_node(struct otx2_qos_node *parent, + struct otx2_qos_node *node) +{ + struct list_head *head = &parent->child_list; + struct otx2_qos_node *tmp_node; + struct list_head *tmp; + + for (tmp = head->next; tmp != head; tmp = tmp->next) { + tmp_node = list_entry(tmp, struct otx2_qos_node, list); + if (tmp_node->prio == node->prio) + return -EEXIST; + if (tmp_node->prio > node->prio) { + list_add_tail(&node->list, tmp); + return 0; + } + } + + list_add_tail(&node->list, head); + return 0; +} + +static int otx2_qos_alloc_txschq_node(struct otx2_nic *pfvf, + struct otx2_qos_node *node) +{ + struct otx2_qos_node *txschq_node, *parent, *tmp; + int lvl; + + parent = node; + for (lvl = node->level - 1; lvl >= NIX_TXSCH_LVL_MDQ; lvl--) { + txschq_node = kzalloc(sizeof(*txschq_node), GFP_KERNEL); + if (!txschq_node) + goto err_out; + + txschq_node->parent = parent; + txschq_node->level = lvl; + txschq_node->classid = OTX2_QOS_CLASS_NONE; + WRITE_ONCE(txschq_node->qid, OTX2_QOS_QID_NONE); + txschq_node->rate = 0; + txschq_node->ceil = 0; + txschq_node->prio = 0; + + mutex_lock(&pfvf->qos.qos_lock); + list_add_tail(&txschq_node->list, &node->child_schq_list); + mutex_unlock(&pfvf->qos.qos_lock); + + INIT_LIST_HEAD(&txschq_node->child_list); + INIT_LIST_HEAD(&txschq_node->child_schq_list); + parent = txschq_node; + } + + return 0; + +err_out: + list_for_each_entry_safe(txschq_node, tmp, &node->child_schq_list, + list) { + list_del(&txschq_node->list); + kfree(txschq_node); + } + return -ENOMEM; +} + +static struct otx2_qos_node * +otx2_qos_sw_create_leaf_node(struct otx2_nic *pfvf, + struct otx2_qos_node *parent, + u16 classid, u32 prio, u64 rate, u64 ceil, + u16 qid) +{ + struct otx2_qos_node *node; + int err; + + node = kzalloc(sizeof(*node), GFP_KERNEL); + if (!node) + return ERR_PTR(-ENOMEM); + + node->parent = parent; + node->level = parent->level - 1; + node->classid = classid; + WRITE_ONCE(node->qid, qid); + + node->rate = otx2_convert_rate(rate); + node->ceil = otx2_convert_rate(ceil); + node->prio = prio; + + __set_bit(qid, pfvf->qos.qos_sq_bmap); + + hash_add_rcu(pfvf->qos.qos_hlist, &node->hlist, classid); + + mutex_lock(&pfvf->qos.qos_lock); + err = otx2_qos_add_child_node(parent, node); + if (err) { + mutex_unlock(&pfvf->qos.qos_lock); + return ERR_PTR(err); + } + mutex_unlock(&pfvf->qos.qos_lock); + + INIT_LIST_HEAD(&node->child_list); + INIT_LIST_HEAD(&node->child_schq_list); + + err = otx2_qos_alloc_txschq_node(pfvf, node); + if (err) { + otx2_qos_sw_node_delete(pfvf, node); + return ERR_PTR(-ENOMEM); + } + + return node; +} + +static struct otx2_qos_node * +otx2_sw_node_find(struct otx2_nic *pfvf, u32 classid) +{ + struct otx2_qos_node *node = NULL; + + hash_for_each_possible(pfvf->qos.qos_hlist, node, hlist, classid) { + if (node->classid == classid) + break; + } + + return node; +} + +static struct otx2_qos_node * +otx2_sw_node_find_rcu(struct otx2_nic *pfvf, u32 classid) +{ + struct otx2_qos_node *node = NULL; + + hash_for_each_possible_rcu(pfvf->qos.qos_hlist, node, hlist, classid) { + if (node->classid == classid) + break; + } + + return node; +} + +int otx2_get_txq_by_classid(struct otx2_nic *pfvf, u16 classid) +{ + struct otx2_qos_node *node; + u16 qid; + int res; + + node = otx2_sw_node_find_rcu(pfvf, classid); + if (!node) { + res = -ENOENT; + goto out; + } + qid = READ_ONCE(node->qid); + if (qid == OTX2_QOS_QID_INNER) { + res = -EINVAL; + goto out; + } + res = pfvf->hw.tx_queues + qid; +out: + return res; +} + +static int +otx2_qos_txschq_config(struct otx2_nic *pfvf, struct otx2_qos_node *node) +{ + struct mbox *mbox = &pfvf->mbox; + struct nix_txschq_config *req; + int rc; + + mutex_lock(&mbox->lock); + + req = otx2_mbox_alloc_msg_nix_txschq_cfg(&pfvf->mbox); + if (!req) { + mutex_unlock(&mbox->lock); + return -ENOMEM; + } + + req->lvl = node->level; + __otx2_qos_txschq_cfg(pfvf, node, req); + + rc = otx2_sync_mbox_msg(&pfvf->mbox); + + mutex_unlock(&mbox->lock); + + return rc; +} + +static int otx2_qos_txschq_alloc(struct otx2_nic *pfvf, + struct otx2_qos_cfg *cfg) +{ + struct nix_txsch_alloc_req *req; + struct nix_txsch_alloc_rsp *rsp; + struct mbox *mbox = &pfvf->mbox; + int lvl, rc, schq; + + mutex_lock(&mbox->lock); + req = otx2_mbox_alloc_msg_nix_txsch_alloc(&pfvf->mbox); + if (!req) { + mutex_unlock(&mbox->lock); + return -ENOMEM; + } + + for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) { + req->schq[lvl] = cfg->schq[lvl]; + req->schq_contig[lvl] = cfg->schq_contig[lvl]; + } + + rc = otx2_sync_mbox_msg(&pfvf->mbox); + if (rc) { + mutex_unlock(&mbox->lock); + return rc; + } + + rsp = (struct nix_txsch_alloc_rsp *) + otx2_mbox_get_rsp(&pfvf->mbox.mbox, 0, &req->hdr); + + if (IS_ERR(rsp)) { + rc = PTR_ERR(rsp); + goto out; + } + + for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) { + for (schq = 0; schq < rsp->schq_contig[lvl]; schq++) { + cfg->schq_contig_list[lvl][schq] = + rsp->schq_contig_list[lvl][schq]; + } + } + + for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) { + for (schq = 0; schq < rsp->schq[lvl]; schq++) { + cfg->schq_list[lvl][schq] = + rsp->schq_list[lvl][schq]; + } + } + + pfvf->qos.link_cfg_lvl = rsp->link_cfg_lvl; + +out: + mutex_unlock(&mbox->lock); + return rc; +} + +static void otx2_qos_txschq_fill_cfg_schq(struct otx2_nic *pfvf, + struct otx2_qos_node *node, + struct otx2_qos_cfg *cfg) +{ + struct otx2_qos_node *tmp; + int cnt; + + list_for_each_entry(tmp, &node->child_schq_list, list) { + cnt = cfg->dwrr_node_pos[tmp->level]; + tmp->schq = cfg->schq_list[tmp->level][cnt]; + cfg->dwrr_node_pos[tmp->level]++; + } +} + +static void otx2_qos_txschq_fill_cfg_tl(struct otx2_nic *pfvf, + struct otx2_qos_node *node, + struct otx2_qos_cfg *cfg) +{ + struct otx2_qos_node *tmp; + int cnt; + + list_for_each_entry(tmp, &node->child_list, list) { + otx2_qos_txschq_fill_cfg_tl(pfvf, tmp, cfg); + cnt = cfg->static_node_pos[tmp->level]; + tmp->schq = cfg->schq_contig_list[tmp->level][cnt]; + if (cnt == 0) + node->prio_anchor = tmp->schq; + cfg->static_node_pos[tmp->level]++; + otx2_qos_txschq_fill_cfg_schq(pfvf, tmp, cfg); + } +} + +static void otx2_qos_txschq_fill_cfg(struct otx2_nic *pfvf, + struct otx2_qos_node *node, + struct otx2_qos_cfg *cfg) +{ + mutex_lock(&pfvf->qos.qos_lock); + otx2_qos_txschq_fill_cfg_tl(pfvf, node, cfg); + otx2_qos_txschq_fill_cfg_schq(pfvf, node, cfg); + mutex_unlock(&pfvf->qos.qos_lock); +} + +static int otx2_qos_txschq_push_cfg_schq(struct otx2_nic *pfvf, + struct otx2_qos_node *node, + struct otx2_qos_cfg *cfg) +{ + struct otx2_qos_node *tmp; + int ret; + + list_for_each_entry(tmp, &node->child_schq_list, list) { + ret = otx2_qos_txschq_config(pfvf, tmp); + if (ret) + return -EIO; + ret = otx2_qos_txschq_set_parent_topology(pfvf, tmp->parent); + if (ret) + return -EIO; + } + + return 0; +} + +static int otx2_qos_txschq_push_cfg_tl(struct otx2_nic *pfvf, + struct otx2_qos_node *node, + struct otx2_qos_cfg *cfg) +{ + struct otx2_qos_node *tmp; + int ret; + + list_for_each_entry(tmp, &node->child_list, list) { + ret = otx2_qos_txschq_push_cfg_tl(pfvf, tmp, cfg); + if (ret) + return -EIO; + ret = otx2_qos_txschq_config(pfvf, tmp); + if (ret) + return -EIO; + ret = otx2_qos_txschq_push_cfg_schq(pfvf, tmp, cfg); + if (ret) + return -EIO; + } + + ret = otx2_qos_txschq_set_parent_topology(pfvf, node); + if (ret) + return -EIO; + + return 0; +} + +static int otx2_qos_txschq_push_cfg(struct otx2_nic *pfvf, + struct otx2_qos_node *node, + struct otx2_qos_cfg *cfg) +{ + int ret; + + mutex_lock(&pfvf->qos.qos_lock); + ret = otx2_qos_txschq_push_cfg_tl(pfvf, node, cfg); + if (ret) + goto out; + ret = otx2_qos_txschq_push_cfg_schq(pfvf, node, cfg); +out: + mutex_unlock(&pfvf->qos.qos_lock); + return ret; +} + +static int otx2_qos_txschq_update_config(struct otx2_nic *pfvf, + struct otx2_qos_node *node, + struct otx2_qos_cfg *cfg) +{ + otx2_qos_txschq_fill_cfg(pfvf, node, cfg); + + return otx2_qos_txschq_push_cfg(pfvf, node, cfg); +} + +static int otx2_qos_txschq_update_root_cfg(struct otx2_nic *pfvf, + struct otx2_qos_node *root, + struct otx2_qos_cfg *cfg) +{ + root->schq = cfg->schq_list[root->level][0]; + return otx2_qos_txschq_config(pfvf, root); +} + +static void otx2_qos_free_cfg(struct otx2_nic *pfvf, struct otx2_qos_cfg *cfg) +{ + int lvl, idx, schq; + + for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) { + for (idx = 0; idx < cfg->schq[lvl]; idx++) { + schq = cfg->schq_list[lvl][idx]; + otx2_txschq_free_one(pfvf, lvl, schq); + } + } + + for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) { + for (idx = 0; idx < cfg->schq_contig[lvl]; idx++) { + schq = cfg->schq_contig_list[lvl][idx]; + otx2_txschq_free_one(pfvf, lvl, schq); + } + } +} + +static void otx2_qos_enadis_sq(struct otx2_nic *pfvf, + struct otx2_qos_node *node, + u16 qid) +{ + if (pfvf->qos.qid_to_sqmap[qid] != OTX2_QOS_INVALID_SQ) + otx2_qos_disable_sq(pfvf, qid); + + pfvf->qos.qid_to_sqmap[qid] = node->schq; + otx2_qos_enable_sq(pfvf, qid); +} + +static void otx2_qos_update_smq_schq(struct otx2_nic *pfvf, + struct otx2_qos_node *node, + bool action) +{ + struct otx2_qos_node *tmp; + + if (node->qid == OTX2_QOS_QID_INNER) + return; + + list_for_each_entry(tmp, &node->child_schq_list, list) { + if (tmp->level == NIX_TXSCH_LVL_MDQ) { + if (action == QOS_SMQ_FLUSH) + otx2_smq_flush(pfvf, tmp->schq); + else + otx2_qos_enadis_sq(pfvf, tmp, node->qid); + } + } +} + +static void __otx2_qos_update_smq(struct otx2_nic *pfvf, + struct otx2_qos_node *node, + bool action) +{ + struct otx2_qos_node *tmp; + + list_for_each_entry(tmp, &node->child_list, list) { + __otx2_qos_update_smq(pfvf, tmp, action); + if (tmp->qid == OTX2_QOS_QID_INNER) + continue; + if (tmp->level == NIX_TXSCH_LVL_MDQ) { + if (action == QOS_SMQ_FLUSH) + otx2_smq_flush(pfvf, tmp->schq); + else + otx2_qos_enadis_sq(pfvf, tmp, tmp->qid); + } else { + otx2_qos_update_smq_schq(pfvf, tmp, action); + } + } +} + +static void otx2_qos_update_smq(struct otx2_nic *pfvf, + struct otx2_qos_node *node, + bool action) +{ + mutex_lock(&pfvf->qos.qos_lock); + __otx2_qos_update_smq(pfvf, node, action); + otx2_qos_update_smq_schq(pfvf, node, action); + mutex_unlock(&pfvf->qos.qos_lock); +} + +static int otx2_qos_push_txschq_cfg(struct otx2_nic *pfvf, + struct otx2_qos_node *node, + struct otx2_qos_cfg *cfg) +{ + int ret; + + ret = otx2_qos_txschq_alloc(pfvf, cfg); + if (ret) + return -ENOSPC; + + if (!(pfvf->netdev->flags & IFF_UP)) { + otx2_qos_txschq_fill_cfg(pfvf, node, cfg); + return 0; + } + + ret = otx2_qos_txschq_update_config(pfvf, node, cfg); + if (ret) { + otx2_qos_free_cfg(pfvf, cfg); + return -EIO; + } + + otx2_qos_update_smq(pfvf, node, QOS_CFG_SQ); + + return 0; +} + +static int otx2_qos_update_tree(struct otx2_nic *pfvf, + struct otx2_qos_node *node, + struct otx2_qos_cfg *cfg) +{ + otx2_qos_prepare_txschq_cfg(pfvf, node->parent, cfg); + return otx2_qos_push_txschq_cfg(pfvf, node->parent, cfg); +} + +static int otx2_qos_root_add(struct otx2_nic *pfvf, u16 htb_maj_id, u16 htb_defcls, + struct netlink_ext_ack *extack) +{ + struct otx2_qos_cfg *new_cfg; + struct otx2_qos_node *root; + int err; + + netdev_dbg(pfvf->netdev, + "TC_HTB_CREATE: handle=0x%x defcls=0x%x\n", + htb_maj_id, htb_defcls); + + root = otx2_qos_alloc_root(pfvf); + if (IS_ERR(root)) { + err = PTR_ERR(root); + return err; + } + + /* allocate txschq queue */ + new_cfg = kzalloc(sizeof(*new_cfg), GFP_KERNEL); + if (!new_cfg) { + NL_SET_ERR_MSG_MOD(extack, "Memory allocation error"); + err = -ENOMEM; + goto free_root_node; + } + /* allocate htb root node */ + new_cfg->schq[root->level] = 1; + err = otx2_qos_txschq_alloc(pfvf, new_cfg); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Error allocating txschq"); + goto free_root_node; + } + + if (!(pfvf->netdev->flags & IFF_UP) || + root->level == NIX_TXSCH_LVL_TL1) { + root->schq = new_cfg->schq_list[root->level][0]; + goto out; + } + + /* update the txschq configuration in hw */ + err = otx2_qos_txschq_update_root_cfg(pfvf, root, new_cfg); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Error updating txschq configuration"); + goto txschq_free; + } + +out: + WRITE_ONCE(pfvf->qos.defcls, htb_defcls); + /* Pairs with smp_load_acquire() in ndo_select_queue */ + smp_store_release(&pfvf->qos.maj_id, htb_maj_id); + kfree(new_cfg); + return 0; + +txschq_free: + otx2_qos_free_cfg(pfvf, new_cfg); +free_root_node: + kfree(new_cfg); + otx2_qos_sw_node_delete(pfvf, root); + return err; +} + +static int otx2_qos_root_destroy(struct otx2_nic *pfvf) +{ + struct otx2_qos_node *root; + + netdev_dbg(pfvf->netdev, "TC_HTB_DESTROY\n"); + + /* find root node */ + root = otx2_sw_node_find(pfvf, OTX2_QOS_ROOT_CLASSID); + if (!root) + return -ENOENT; + + /* free the hw mappings */ + otx2_qos_destroy_node(pfvf, root); + + return 0; +} + +static int otx2_qos_validate_configuration(struct otx2_qos_node *parent, + struct netlink_ext_ack *extack, + struct otx2_nic *pfvf, + u64 prio) +{ + if (test_bit(prio, parent->prio_bmap)) { + NL_SET_ERR_MSG_MOD(extack, + "Static priority child with same priority exists"); + return -EEXIST; + } + + if (prio == TXSCH_TL1_DFLT_RR_PRIO) { + NL_SET_ERR_MSG_MOD(extack, + "Priority is reserved for Round Robin"); + return -EINVAL; + } + + return 0; +} + +static int otx2_qos_leaf_alloc_queue(struct otx2_nic *pfvf, u16 classid, + u32 parent_classid, u64 rate, u64 ceil, + u64 prio, struct netlink_ext_ack *extack) +{ + struct otx2_qos_cfg *old_cfg, *new_cfg; + struct otx2_qos_node *node, *parent; + int qid, ret, err; + + netdev_dbg(pfvf->netdev, + "TC_HTB_LEAF_ALLOC_QUEUE: classid=0x%x parent_classid=0x%x rate=%lld ceil=%lld prio=%lld\n", + classid, parent_classid, rate, ceil, prio); + + if (prio > OTX2_QOS_MAX_PRIO) { + NL_SET_ERR_MSG_MOD(extack, "Valid priority range 0 to 7"); + ret = -EOPNOTSUPP; + goto out; + } + + /* get parent node */ + parent = otx2_sw_node_find(pfvf, parent_classid); + if (!parent) { + NL_SET_ERR_MSG_MOD(extack, "parent node not found"); + ret = -ENOENT; + goto out; + } + if (parent->level == NIX_TXSCH_LVL_MDQ) { + NL_SET_ERR_MSG_MOD(extack, "HTB qos max levels reached"); + ret = -EOPNOTSUPP; + goto out; + } + + ret = otx2_qos_validate_configuration(parent, extack, pfvf, prio); + if (ret) + goto out; + + set_bit(prio, parent->prio_bmap); + + /* read current txschq configuration */ + old_cfg = kzalloc(sizeof(*old_cfg), GFP_KERNEL); + if (!old_cfg) { + NL_SET_ERR_MSG_MOD(extack, "Memory allocation error"); + ret = -ENOMEM; + goto reset_prio; + } + otx2_qos_read_txschq_cfg(pfvf, parent, old_cfg); + + /* allocate a new sq */ + qid = otx2_qos_get_qid(pfvf); + if (qid < 0) { + NL_SET_ERR_MSG_MOD(extack, "Reached max supported QOS SQ's"); + ret = -ENOMEM; + goto free_old_cfg; + } + + /* Actual SQ mapping will be updated after SMQ alloc */ + pfvf->qos.qid_to_sqmap[qid] = OTX2_QOS_INVALID_SQ; + + /* allocate and initialize a new child node */ + node = otx2_qos_sw_create_leaf_node(pfvf, parent, classid, prio, rate, + ceil, qid); + if (IS_ERR(node)) { + NL_SET_ERR_MSG_MOD(extack, "Unable to allocate leaf node"); + ret = PTR_ERR(node); + goto free_old_cfg; + } + + /* push new txschq config to hw */ + new_cfg = kzalloc(sizeof(*new_cfg), GFP_KERNEL); + if (!new_cfg) { + NL_SET_ERR_MSG_MOD(extack, "Memory allocation error"); + ret = -ENOMEM; + goto free_node; + } + ret = otx2_qos_update_tree(pfvf, node, new_cfg); + if (ret) { + NL_SET_ERR_MSG_MOD(extack, "HTB HW configuration error"); + kfree(new_cfg); + otx2_qos_sw_node_delete(pfvf, node); + /* restore the old qos tree */ + err = otx2_qos_txschq_update_config(pfvf, parent, old_cfg); + if (err) { + netdev_err(pfvf->netdev, + "Failed to restore txcshq configuration"); + goto free_old_cfg; + } + + otx2_qos_update_smq(pfvf, parent, QOS_CFG_SQ); + goto free_old_cfg; + } + + /* update tx_real_queues */ + otx2_qos_update_tx_netdev_queues(pfvf); + + /* free new txschq config */ + kfree(new_cfg); + + /* free old txschq config */ + otx2_qos_free_cfg(pfvf, old_cfg); + kfree(old_cfg); + + return pfvf->hw.tx_queues + qid; + +free_node: + otx2_qos_sw_node_delete(pfvf, node); +free_old_cfg: + kfree(old_cfg); +reset_prio: + clear_bit(prio, parent->prio_bmap); +out: + return ret; +} + +static int otx2_qos_leaf_to_inner(struct otx2_nic *pfvf, u16 classid, + u16 child_classid, u64 rate, u64 ceil, u64 prio, + struct netlink_ext_ack *extack) +{ + struct otx2_qos_cfg *old_cfg, *new_cfg; + struct otx2_qos_node *node, *child; + int ret, err; + u16 qid; + + netdev_dbg(pfvf->netdev, + "TC_HTB_LEAF_TO_INNER classid %04x, child %04x, rate %llu, ceil %llu\n", + classid, child_classid, rate, ceil); + + if (prio > OTX2_QOS_MAX_PRIO) { + NL_SET_ERR_MSG_MOD(extack, "Valid priority range 0 to 7"); + ret = -EOPNOTSUPP; + goto out; + } + + /* find node related to classid */ + node = otx2_sw_node_find(pfvf, classid); + if (!node) { + NL_SET_ERR_MSG_MOD(extack, "HTB node not found"); + ret = -ENOENT; + goto out; + } + /* check max qos txschq level */ + if (node->level == NIX_TXSCH_LVL_MDQ) { + NL_SET_ERR_MSG_MOD(extack, "HTB qos level not supported"); + ret = -EOPNOTSUPP; + goto out; + } + + set_bit(prio, node->prio_bmap); + + /* store the qid to assign to leaf node */ + qid = node->qid; + + /* read current txschq configuration */ + old_cfg = kzalloc(sizeof(*old_cfg), GFP_KERNEL); + if (!old_cfg) { + NL_SET_ERR_MSG_MOD(extack, "Memory allocation error"); + ret = -ENOMEM; + goto reset_prio; + } + otx2_qos_read_txschq_cfg(pfvf, node, old_cfg); + + /* delete the txschq nodes allocated for this node */ + otx2_qos_free_sw_node_schq(pfvf, node); + + /* mark this node as htb inner node */ + WRITE_ONCE(node->qid, OTX2_QOS_QID_INNER); + + /* allocate and initialize a new child node */ + child = otx2_qos_sw_create_leaf_node(pfvf, node, child_classid, + prio, rate, ceil, qid); + if (IS_ERR(child)) { + NL_SET_ERR_MSG_MOD(extack, "Unable to allocate leaf node"); + ret = PTR_ERR(child); + goto free_old_cfg; + } + + /* push new txschq config to hw */ + new_cfg = kzalloc(sizeof(*new_cfg), GFP_KERNEL); + if (!new_cfg) { + NL_SET_ERR_MSG_MOD(extack, "Memory allocation error"); + ret = -ENOMEM; + goto free_node; + } + ret = otx2_qos_update_tree(pfvf, child, new_cfg); + if (ret) { + NL_SET_ERR_MSG_MOD(extack, "HTB HW configuration error"); + kfree(new_cfg); + otx2_qos_sw_node_delete(pfvf, child); + /* restore the old qos tree */ + WRITE_ONCE(node->qid, qid); + err = otx2_qos_alloc_txschq_node(pfvf, node); + if (err) { + netdev_err(pfvf->netdev, + "Failed to restore old leaf node"); + goto free_old_cfg; + } + err = otx2_qos_txschq_update_config(pfvf, node, old_cfg); + if (err) { + netdev_err(pfvf->netdev, + "Failed to restore txcshq configuration"); + goto free_old_cfg; + } + otx2_qos_update_smq(pfvf, node, QOS_CFG_SQ); + goto free_old_cfg; + } + + /* free new txschq config */ + kfree(new_cfg); + + /* free old txschq config */ + otx2_qos_free_cfg(pfvf, old_cfg); + kfree(old_cfg); + + return 0; + +free_node: + otx2_qos_sw_node_delete(pfvf, child); +free_old_cfg: + kfree(old_cfg); +reset_prio: + clear_bit(prio, node->prio_bmap); +out: + return ret; +} + +static int otx2_qos_leaf_del(struct otx2_nic *pfvf, u16 *classid, + struct netlink_ext_ack *extack) +{ + struct otx2_qos_node *node, *parent; + u64 prio; + u16 qid; + + netdev_dbg(pfvf->netdev, "TC_HTB_LEAF_DEL classid %04x\n", *classid); + + /* find node related to classid */ + node = otx2_sw_node_find(pfvf, *classid); + if (!node) { + NL_SET_ERR_MSG_MOD(extack, "HTB node not found"); + return -ENOENT; + } + parent = node->parent; + prio = node->prio; + qid = node->qid; + + otx2_qos_disable_sq(pfvf, node->qid); + + otx2_qos_destroy_node(pfvf, node); + pfvf->qos.qid_to_sqmap[qid] = OTX2_QOS_INVALID_SQ; + + clear_bit(prio, parent->prio_bmap); + + return 0; +} + +static int otx2_qos_leaf_del_last(struct otx2_nic *pfvf, u16 classid, bool force, + struct netlink_ext_ack *extack) +{ + struct otx2_qos_node *node, *parent; + struct otx2_qos_cfg *new_cfg; + u64 prio; + int err; + u16 qid; + + netdev_dbg(pfvf->netdev, + "TC_HTB_LEAF_DEL_LAST classid %04x\n", classid); + + /* find node related to classid */ + node = otx2_sw_node_find(pfvf, classid); + if (!node) { + NL_SET_ERR_MSG_MOD(extack, "HTB node not found"); + return -ENOENT; + } + + /* save qid for use by parent */ + qid = node->qid; + prio = node->prio; + + parent = otx2_sw_node_find(pfvf, node->parent->classid); + if (!parent) { + NL_SET_ERR_MSG_MOD(extack, "parent node not found"); + return -ENOENT; + } + + /* destroy the leaf node */ + otx2_qos_destroy_node(pfvf, node); + pfvf->qos.qid_to_sqmap[qid] = OTX2_QOS_INVALID_SQ; + + clear_bit(prio, parent->prio_bmap); + + /* create downstream txschq entries to parent */ + err = otx2_qos_alloc_txschq_node(pfvf, parent); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "HTB failed to create txsch configuration"); + return err; + } + WRITE_ONCE(parent->qid, qid); + __set_bit(qid, pfvf->qos.qos_sq_bmap); + + /* push new txschq config to hw */ + new_cfg = kzalloc(sizeof(*new_cfg), GFP_KERNEL); + if (!new_cfg) { + NL_SET_ERR_MSG_MOD(extack, "Memory allocation error"); + return -ENOMEM; + } + /* fill txschq cfg and push txschq cfg to hw */ + otx2_qos_fill_cfg_schq(parent, new_cfg); + err = otx2_qos_push_txschq_cfg(pfvf, parent, new_cfg); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "HTB HW configuration error"); + kfree(new_cfg); + return err; + } + kfree(new_cfg); + + /* update tx_real_queues */ + otx2_qos_update_tx_netdev_queues(pfvf); + + return 0; +} + +void otx2_clean_qos_queues(struct otx2_nic *pfvf) +{ + struct otx2_qos_node *root; + + root = otx2_sw_node_find(pfvf, OTX2_QOS_ROOT_CLASSID); + if (!root) + return; + + otx2_qos_update_smq(pfvf, root, QOS_SMQ_FLUSH); +} + +void otx2_qos_config_txschq(struct otx2_nic *pfvf) +{ + struct otx2_qos_node *root; + int err; + + root = otx2_sw_node_find(pfvf, OTX2_QOS_ROOT_CLASSID); + if (!root) + return; + + err = otx2_qos_txschq_config(pfvf, root); + if (err) { + netdev_err(pfvf->netdev, "Error update txschq configuration\n"); + goto root_destroy; + } + + err = otx2_qos_txschq_push_cfg_tl(pfvf, root, NULL); + if (err) { + netdev_err(pfvf->netdev, "Error update txschq configuration\n"); + goto root_destroy; + } + + otx2_qos_update_smq(pfvf, root, QOS_CFG_SQ); + return; + +root_destroy: + netdev_err(pfvf->netdev, "Failed to update Scheduler/Shaping config in Hardware\n"); + /* Free resources allocated */ + otx2_qos_root_destroy(pfvf); +} + +int otx2_setup_tc_htb(struct net_device *ndev, struct tc_htb_qopt_offload *htb) +{ + struct otx2_nic *pfvf = netdev_priv(ndev); + int res; + + switch (htb->command) { + case TC_HTB_CREATE: + return otx2_qos_root_add(pfvf, htb->parent_classid, + htb->classid, htb->extack); + case TC_HTB_DESTROY: + return otx2_qos_root_destroy(pfvf); + case TC_HTB_LEAF_ALLOC_QUEUE: + res = otx2_qos_leaf_alloc_queue(pfvf, htb->classid, + htb->parent_classid, + htb->rate, htb->ceil, + htb->prio, htb->extack); + if (res < 0) + return res; + htb->qid = res; + return 0; + case TC_HTB_LEAF_TO_INNER: + return otx2_qos_leaf_to_inner(pfvf, htb->parent_classid, + htb->classid, htb->rate, + htb->ceil, htb->prio, + htb->extack); + case TC_HTB_LEAF_DEL: + return otx2_qos_leaf_del(pfvf, &htb->classid, htb->extack); + case TC_HTB_LEAF_DEL_LAST: + case TC_HTB_LEAF_DEL_LAST_FORCE: + return otx2_qos_leaf_del_last(pfvf, htb->classid, + htb->command == TC_HTB_LEAF_DEL_LAST_FORCE, + htb->extack); + case TC_HTB_LEAF_QUERY_QUEUE: + res = otx2_get_txq_by_classid(pfvf, htb->classid); + htb->qid = res; + return 0; + case TC_HTB_NODE_MODIFY: + fallthrough; + default: + return -EOPNOTSUPP; + } +} diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos.h b/drivers/net/ethernet/marvell/octeontx2/nic/qos.h new file mode 100644 index 000000000000..19773284be27 --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos.h @@ -0,0 +1,69 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell RVU Ethernet driver + * + * Copyright (C) 2023 Marvell. + * + */ +#ifndef OTX2_QOS_H +#define OTX2_QOS_H + +#include <linux/types.h> +#include <linux/netdevice.h> +#include <linux/rhashtable.h> + +#define OTX2_QOS_MAX_LVL 4 +#define OTX2_QOS_MAX_PRIO 7 +#define OTX2_QOS_MAX_LEAF_NODES 16 + +enum qos_smq_operations { + QOS_CFG_SQ, + QOS_SMQ_FLUSH, +}; + +u64 otx2_get_txschq_rate_regval(struct otx2_nic *nic, u64 maxrate, u32 burst); + +int otx2_setup_tc_htb(struct net_device *ndev, struct tc_htb_qopt_offload *htb); +int otx2_qos_get_qid(struct otx2_nic *pfvf); +void otx2_qos_free_qid(struct otx2_nic *pfvf, int qidx); +int otx2_qos_enable_sq(struct otx2_nic *pfvf, int qidx); +void otx2_qos_disable_sq(struct otx2_nic *pfvf, int qidx); + +struct otx2_qos_cfg { + u16 schq[NIX_TXSCH_LVL_CNT]; + u16 schq_contig[NIX_TXSCH_LVL_CNT]; + int static_node_pos[NIX_TXSCH_LVL_CNT]; + int dwrr_node_pos[NIX_TXSCH_LVL_CNT]; + u16 schq_contig_list[NIX_TXSCH_LVL_CNT][MAX_TXSCHQ_PER_FUNC]; + u16 schq_list[NIX_TXSCH_LVL_CNT][MAX_TXSCHQ_PER_FUNC]; +}; + +struct otx2_qos { + DECLARE_HASHTABLE(qos_hlist, order_base_2(OTX2_QOS_MAX_LEAF_NODES)); + struct mutex qos_lock; /* child list lock */ + u16 qid_to_sqmap[OTX2_QOS_MAX_LEAF_NODES]; + struct list_head qos_tree; + DECLARE_BITMAP(qos_sq_bmap, OTX2_QOS_MAX_LEAF_NODES); + u16 maj_id; + u16 defcls; + u8 link_cfg_lvl; /* LINKX_CFG CSRs mapped to TL3 or TL2's index ? */ +}; + +struct otx2_qos_node { + struct list_head list; /* list management */ + struct list_head child_list; + struct list_head child_schq_list; + struct hlist_node hlist; + DECLARE_BITMAP(prio_bmap, OTX2_QOS_MAX_PRIO + 1); + struct otx2_qos_node *parent; /* parent qos node */ + u64 rate; /* htb params */ + u64 ceil; + u32 classid; + u32 prio; + u16 schq; /* hw txschq */ + u16 qid; + u16 prio_anchor; + u8 level; +}; + + +#endif diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c b/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c new file mode 100644 index 000000000000..9d887bfc3108 --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c @@ -0,0 +1,296 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Marvell RVU Physical Function ethernet driver + * + * Copyright (C) 2023 Marvell. + * + */ + +#include <linux/netdevice.h> +#include <net/tso.h> + +#include "cn10k.h" +#include "otx2_reg.h" +#include "otx2_common.h" +#include "otx2_txrx.h" +#include "otx2_struct.h" + +#define OTX2_QOS_MAX_LEAF_NODES 16 + +static void otx2_qos_aura_pool_free(struct otx2_nic *pfvf, int pool_id) +{ + struct otx2_pool *pool; + + if (!pfvf->qset.pool) + return; + + pool = &pfvf->qset.pool[pool_id]; + qmem_free(pfvf->dev, pool->stack); + qmem_free(pfvf->dev, pool->fc_addr); + pool->stack = NULL; + pool->fc_addr = NULL; +} + +static int otx2_qos_sq_aura_pool_init(struct otx2_nic *pfvf, int qidx) +{ + struct otx2_qset *qset = &pfvf->qset; + int pool_id, stack_pages, num_sqbs; + struct otx2_hw *hw = &pfvf->hw; + struct otx2_snd_queue *sq; + struct otx2_pool *pool; + dma_addr_t bufptr; + int err, ptr; + u64 iova, pa; + + /* Calculate number of SQBs needed. + * + * For a 128byte SQE, and 4K size SQB, 31 SQEs will fit in one SQB. + * Last SQE is used for pointing to next SQB. + */ + num_sqbs = (hw->sqb_size / 128) - 1; + num_sqbs = (qset->sqe_cnt + num_sqbs) / num_sqbs; + + /* Get no of stack pages needed */ + stack_pages = + (num_sqbs + hw->stack_pg_ptrs - 1) / hw->stack_pg_ptrs; + + pool_id = otx2_get_pool_idx(pfvf, AURA_NIX_SQ, qidx); + pool = &pfvf->qset.pool[pool_id]; + + /* Initialize aura context */ + err = otx2_aura_init(pfvf, pool_id, pool_id, num_sqbs); + if (err) + return err; + + /* Initialize pool context */ + err = otx2_pool_init(pfvf, pool_id, stack_pages, + num_sqbs, hw->sqb_size, AURA_NIX_SQ); + if (err) + goto aura_free; + + /* Flush accumulated messages */ + err = otx2_sync_mbox_msg(&pfvf->mbox); + if (err) + goto pool_free; + + /* Allocate pointers and free them to aura/pool */ + sq = &qset->sq[qidx]; + sq->sqb_count = 0; + sq->sqb_ptrs = kcalloc(num_sqbs, sizeof(*sq->sqb_ptrs), GFP_KERNEL); + if (!sq->sqb_ptrs) { + err = -ENOMEM; + goto pool_free; + } + + for (ptr = 0; ptr < num_sqbs; ptr++) { + err = otx2_alloc_rbuf(pfvf, pool, &bufptr); + if (err) + goto sqb_free; + pfvf->hw_ops->aura_freeptr(pfvf, pool_id, bufptr); + sq->sqb_ptrs[sq->sqb_count++] = (u64)bufptr; + } + + return 0; + +sqb_free: + while (ptr--) { + if (!sq->sqb_ptrs[ptr]) + continue; + iova = sq->sqb_ptrs[ptr]; + pa = otx2_iova_to_phys(pfvf->iommu_domain, iova); + dma_unmap_page_attrs(pfvf->dev, iova, hw->sqb_size, + DMA_FROM_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC); + put_page(virt_to_page(phys_to_virt(pa))); + otx2_aura_allocptr(pfvf, pool_id); + } + sq->sqb_count = 0; + kfree(sq->sqb_ptrs); +pool_free: + qmem_free(pfvf->dev, pool->stack); +aura_free: + qmem_free(pfvf->dev, pool->fc_addr); + otx2_mbox_reset(&pfvf->mbox.mbox, 0); + return err; +} + +static void otx2_qos_sq_free_sqbs(struct otx2_nic *pfvf, int qidx) +{ + struct otx2_qset *qset = &pfvf->qset; + struct otx2_hw *hw = &pfvf->hw; + struct otx2_snd_queue *sq; + u64 iova, pa; + int sqb; + + sq = &qset->sq[qidx]; + if (!sq->sqb_ptrs) + return; + for (sqb = 0; sqb < sq->sqb_count; sqb++) { + if (!sq->sqb_ptrs[sqb]) + continue; + iova = sq->sqb_ptrs[sqb]; + pa = otx2_iova_to_phys(pfvf->iommu_domain, iova); + dma_unmap_page_attrs(pfvf->dev, iova, hw->sqb_size, + DMA_FROM_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC); + put_page(virt_to_page(phys_to_virt(pa))); + } + + sq->sqb_count = 0; + + sq = &qset->sq[qidx]; + qmem_free(pfvf->dev, sq->sqe); + qmem_free(pfvf->dev, sq->tso_hdrs); + kfree(sq->sg); + kfree(sq->sqb_ptrs); + qmem_free(pfvf->dev, sq->timestamps); + + memset((void *)sq, 0, sizeof(*sq)); +} + +/* send queue id */ +static void otx2_qos_sqb_flush(struct otx2_nic *pfvf, int qidx) +{ + int sqe_tail, sqe_head; + u64 incr, *ptr, val; + + ptr = (__force u64 *)otx2_get_regaddr(pfvf, NIX_LF_SQ_OP_STATUS); + incr = (u64)qidx << 32; + val = otx2_atomic64_add(incr, ptr); + sqe_head = (val >> 20) & 0x3F; + sqe_tail = (val >> 28) & 0x3F; + if (sqe_head != sqe_tail) + usleep_range(50, 60); +} + +static int otx2_qos_ctx_disable(struct otx2_nic *pfvf, u16 qidx, int aura_id) +{ + struct nix_cn10k_aq_enq_req *cn10k_sq_aq; + struct npa_aq_enq_req *aura_aq; + struct npa_aq_enq_req *pool_aq; + struct nix_aq_enq_req *sq_aq; + + if (test_bit(CN10K_LMTST, &pfvf->hw.cap_flag)) { + cn10k_sq_aq = otx2_mbox_alloc_msg_nix_cn10k_aq_enq(&pfvf->mbox); + if (!cn10k_sq_aq) + return -ENOMEM; + cn10k_sq_aq->qidx = qidx; + cn10k_sq_aq->sq.ena = 0; + cn10k_sq_aq->sq_mask.ena = 1; + cn10k_sq_aq->ctype = NIX_AQ_CTYPE_SQ; + cn10k_sq_aq->op = NIX_AQ_INSTOP_WRITE; + } else { + sq_aq = otx2_mbox_alloc_msg_nix_aq_enq(&pfvf->mbox); + if (!sq_aq) + return -ENOMEM; + sq_aq->qidx = qidx; + sq_aq->sq.ena = 0; + sq_aq->sq_mask.ena = 1; + sq_aq->ctype = NIX_AQ_CTYPE_SQ; + sq_aq->op = NIX_AQ_INSTOP_WRITE; + } + + aura_aq = otx2_mbox_alloc_msg_npa_aq_enq(&pfvf->mbox); + if (!aura_aq) { + otx2_mbox_reset(&pfvf->mbox.mbox, 0); + return -ENOMEM; + } + + aura_aq->aura_id = aura_id; + aura_aq->aura.ena = 0; + aura_aq->aura_mask.ena = 1; + aura_aq->ctype = NPA_AQ_CTYPE_AURA; + aura_aq->op = NPA_AQ_INSTOP_WRITE; + + pool_aq = otx2_mbox_alloc_msg_npa_aq_enq(&pfvf->mbox); + if (!pool_aq) { + otx2_mbox_reset(&pfvf->mbox.mbox, 0); + return -ENOMEM; + } + + pool_aq->aura_id = aura_id; + pool_aq->pool.ena = 0; + pool_aq->pool_mask.ena = 1; + + pool_aq->ctype = NPA_AQ_CTYPE_POOL; + pool_aq->op = NPA_AQ_INSTOP_WRITE; + + return otx2_sync_mbox_msg(&pfvf->mbox); +} + +int otx2_qos_get_qid(struct otx2_nic *pfvf) +{ + int qidx; + + qidx = find_first_zero_bit(pfvf->qos.qos_sq_bmap, + pfvf->hw.tc_tx_queues); + + return qidx == pfvf->hw.tc_tx_queues ? -ENOSPC : qidx; +} + +void otx2_qos_free_qid(struct otx2_nic *pfvf, int qidx) +{ + clear_bit(qidx, pfvf->qos.qos_sq_bmap); +} + +int otx2_qos_enable_sq(struct otx2_nic *pfvf, int qidx) +{ + struct otx2_hw *hw = &pfvf->hw; + int pool_id, sq_idx, err; + + if (pfvf->flags & OTX2_FLAG_INTF_DOWN) + return -EPERM; + + sq_idx = hw->non_qos_queues + qidx; + + mutex_lock(&pfvf->mbox.lock); + err = otx2_qos_sq_aura_pool_init(pfvf, sq_idx); + if (err) + goto out; + + pool_id = otx2_get_pool_idx(pfvf, AURA_NIX_SQ, sq_idx); + err = otx2_sq_init(pfvf, sq_idx, pool_id); + if (err) + goto out; +out: + mutex_unlock(&pfvf->mbox.lock); + return err; +} + +void otx2_qos_disable_sq(struct otx2_nic *pfvf, int qidx) +{ + struct otx2_qset *qset = &pfvf->qset; + struct otx2_hw *hw = &pfvf->hw; + struct otx2_snd_queue *sq; + struct otx2_cq_queue *cq; + int pool_id, sq_idx; + + sq_idx = hw->non_qos_queues + qidx; + + /* If the DOWN flag is set SQs are already freed */ + if (pfvf->flags & OTX2_FLAG_INTF_DOWN) + return; + + sq = &pfvf->qset.sq[sq_idx]; + if (!sq->sqb_ptrs) + return; + + if (sq_idx < hw->non_qos_queues || + sq_idx >= otx2_get_total_tx_queues(pfvf)) { + netdev_err(pfvf->netdev, "Send Queue is not a QoS queue\n"); + return; + } + + cq = &qset->cq[pfvf->hw.rx_queues + sq_idx]; + pool_id = otx2_get_pool_idx(pfvf, AURA_NIX_SQ, sq_idx); + + otx2_qos_sqb_flush(pfvf, sq_idx); + otx2_smq_flush(pfvf, otx2_get_smq_idx(pfvf, sq_idx)); + otx2_cleanup_tx_cqes(pfvf, cq); + + mutex_lock(&pfvf->mbox.lock); + otx2_qos_ctx_disable(pfvf, sq_idx, pool_id); + mutex_unlock(&pfvf->mbox.lock); + + otx2_qos_sq_free_sqbs(pfvf, sq_idx); + otx2_qos_aura_pool_free(pfvf, pool_id); +} diff --git a/drivers/net/ethernet/marvell/prestera/prestera_flower.c b/drivers/net/ethernet/marvell/prestera/prestera_flower.c index 91a478b75cbf..3e20e71b0f81 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_flower.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_flower.c @@ -148,6 +148,12 @@ static int prestera_flower_parse_meta(struct prestera_acl_rule *rule, __be16 key, mask; flow_rule_match_meta(f_rule, &match); + + if (match.mask->l2_miss) { + NL_SET_ERR_MSG_MOD(f->common.extack, "Can't match on \"l2_miss\""); + return -EOPNOTSUPP; + } + if (match.mask->ingress_ifindex != 0xFFFFFFFF) { NL_SET_ERR_MSG_MOD(f->common.extack, "Unsupported ingress ifindex mask"); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index a75fd072082c..834c644b67db 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -3269,18 +3269,14 @@ static int mtk_open(struct net_device *dev) eth->dsa_meta[i] = md_dst; } } else { - /* Hardware special tag parsing needs to be disabled if at least - * one MAC does not use DSA. + /* Hardware DSA untagging and VLAN RX offloading need to be + * disabled if at least one MAC does not use DSA. */ u32 val = mtk_r32(eth, MTK_CDMP_IG_CTRL); val &= ~MTK_CDMP_STAG_EN; mtk_w32(eth, val, MTK_CDMP_IG_CTRL); - val = mtk_r32(eth, MTK_CDMQ_IG_CTRL); - val &= ~MTK_CDMQ_STAG_EN; - mtk_w32(eth, val, MTK_CDMQ_IG_CTRL); - mtk_w32(eth, 0, MTK_CDMP_EG_CTRL); } diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 277738c50c56..61286b0d9b0c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -1374,16 +1374,13 @@ static int mlx4_mf_bond(struct mlx4_dev *dev) int nvfs; struct mlx4_slaves_pport slaves_port1; struct mlx4_slaves_pport slaves_port2; - DECLARE_BITMAP(slaves_port_1_2, MLX4_MFUNC_MAX); slaves_port1 = mlx4_phys_to_slaves_pport(dev, 1); slaves_port2 = mlx4_phys_to_slaves_pport(dev, 2); - bitmap_and(slaves_port_1_2, - slaves_port1.slaves, slaves_port2.slaves, - dev->persist->num_vfs + 1); /* only single port vfs are allowed */ - if (bitmap_weight(slaves_port_1_2, dev->persist->num_vfs + 1) > 1) { + if (bitmap_weight_and(slaves_port1.slaves, slaves_port2.slaves, + dev->persist->num_vfs + 1) > 1) { mlx4_warn(dev, "HA mode unsupported for dual ported VFs\n"); return -EINVAL; } @@ -3027,13 +3024,43 @@ no_msi: } } +static int mlx4_devlink_port_type_set(struct devlink_port *devlink_port, + enum devlink_port_type port_type) +{ + struct mlx4_port_info *info = container_of(devlink_port, + struct mlx4_port_info, + devlink_port); + enum mlx4_port_type mlx4_port_type; + + switch (port_type) { + case DEVLINK_PORT_TYPE_AUTO: + mlx4_port_type = MLX4_PORT_TYPE_AUTO; + break; + case DEVLINK_PORT_TYPE_ETH: + mlx4_port_type = MLX4_PORT_TYPE_ETH; + break; + case DEVLINK_PORT_TYPE_IB: + mlx4_port_type = MLX4_PORT_TYPE_IB; + break; + default: + return -EOPNOTSUPP; + } + + return __set_port_type(info, mlx4_port_type); +} + +static const struct devlink_port_ops mlx4_devlink_port_ops = { + .port_type_set = mlx4_devlink_port_type_set, +}; + static int mlx4_init_port_info(struct mlx4_dev *dev, int port) { struct devlink *devlink = priv_to_devlink(mlx4_priv(dev)); struct mlx4_port_info *info = &mlx4_priv(dev)->port[port]; int err; - err = devl_port_register(devlink, &info->devlink_port, port); + err = devl_port_register_with_ops(devlink, &info->devlink_port, port, + &mlx4_devlink_port_ops); if (err) return err; @@ -3877,31 +3904,6 @@ err_disable_pdev: return err; } -static int mlx4_devlink_port_type_set(struct devlink_port *devlink_port, - enum devlink_port_type port_type) -{ - struct mlx4_port_info *info = container_of(devlink_port, - struct mlx4_port_info, - devlink_port); - enum mlx4_port_type mlx4_port_type; - - switch (port_type) { - case DEVLINK_PORT_TYPE_AUTO: - mlx4_port_type = MLX4_PORT_TYPE_AUTO; - break; - case DEVLINK_PORT_TYPE_ETH: - mlx4_port_type = MLX4_PORT_TYPE_ETH; - break; - case DEVLINK_PORT_TYPE_IB: - mlx4_port_type = MLX4_PORT_TYPE_IB; - break; - default: - return -EOPNOTSUPP; - } - - return __set_port_type(info, mlx4_port_type); -} - static void mlx4_devlink_param_load_driverinit_values(struct devlink *devlink) { struct mlx4_priv *priv = devlink_priv(devlink); @@ -3986,7 +3988,6 @@ static int mlx4_devlink_reload_up(struct devlink *devlink, enum devlink_reload_a } static const struct devlink_ops mlx4_devlink_ops = { - .port_type_set = mlx4_devlink_port_type_set, .reload_actions = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT), .reload_down = mlx4_devlink_reload_down, .reload_up = mlx4_devlink_reload_up, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index d53de39539a8..d532883b42d7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -1920,9 +1920,10 @@ static void mlx5_cmd_err_trace(struct mlx5_core_dev *dev, u16 opcode, u16 op_mod static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status, u32 syndrome, int err) { + const char *namep = mlx5_command_str(opcode); struct mlx5_cmd_stats *stats; - if (!err) + if (!err || !(strcmp(namep, "unknown command opcode"))) return; stats = &dev->cmd.stats[opcode]; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index 4b607785d694..63635cc44479 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -162,9 +162,8 @@ static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change, return -EOPNOTSUPP; } - if (pci_num_vf(pdev)) { + if (mlx5_core_is_pf(dev) && pci_num_vf(pdev)) NL_SET_ERR_MSG_MOD(extack, "reload while VFs are present is unfavorable"); - } switch (action) { case DEVLINK_RELOAD_ACTION_DRIVER_REINIT: @@ -311,8 +310,6 @@ static const struct devlink_ops mlx5_devlink_ops = { .eswitch_inline_mode_get = mlx5_devlink_eswitch_inline_mode_get, .eswitch_encap_mode_set = mlx5_devlink_eswitch_encap_mode_set, .eswitch_encap_mode_get = mlx5_devlink_eswitch_encap_mode_get, - .port_function_hw_addr_get = mlx5_devlink_port_function_hw_addr_get, - .port_function_hw_addr_set = mlx5_devlink_port_function_hw_addr_set, .rate_leaf_tx_share_set = mlx5_esw_devlink_rate_leaf_tx_share_set, .rate_leaf_tx_max_set = mlx5_esw_devlink_rate_leaf_tx_max_set, .rate_node_tx_share_set = mlx5_esw_devlink_rate_node_tx_share_set, @@ -320,16 +317,9 @@ static const struct devlink_ops mlx5_devlink_ops = { .rate_node_new = mlx5_esw_devlink_rate_node_new, .rate_node_del = mlx5_esw_devlink_rate_node_del, .rate_leaf_parent_set = mlx5_esw_devlink_rate_parent_set, - .port_fn_roce_get = mlx5_devlink_port_fn_roce_get, - .port_fn_roce_set = mlx5_devlink_port_fn_roce_set, - .port_fn_migratable_get = mlx5_devlink_port_fn_migratable_get, - .port_fn_migratable_set = mlx5_devlink_port_fn_migratable_set, #endif #ifdef CONFIG_MLX5_SF_MANAGER .port_new = mlx5_devlink_sf_port_new, - .port_del = mlx5_devlink_sf_port_del, - .port_fn_state_get = mlx5_devlink_sf_port_fn_state_get, - .port_fn_state_set = mlx5_devlink_sf_port_fn_state_set, #endif .flash_update = mlx5_devlink_flash_update, .info_get = mlx5_devlink_info_get, @@ -464,27 +454,6 @@ static int mlx5_devlink_esw_multiport_get(struct devlink *devlink, u32 id, ctx->val.vbool = mlx5_lag_is_mpesw(dev); return 0; } - -static int mlx5_devlink_esw_multiport_validate(struct devlink *devlink, u32 id, - union devlink_param_value val, - struct netlink_ext_ack *extack) -{ - struct mlx5_core_dev *dev = devlink_priv(devlink); - - if (!MLX5_ESWITCH_MANAGER(dev)) { - NL_SET_ERR_MSG_MOD(extack, "E-Switch is unsupported"); - return -EOPNOTSUPP; - } - - if (mlx5_eswitch_mode(dev) != MLX5_ESWITCH_OFFLOADS) { - NL_SET_ERR_MSG_MOD(extack, - "E-Switch must be in switchdev mode"); - return -EBUSY; - } - - return 0; -} - #endif static int mlx5_devlink_eq_depth_validate(struct devlink *devlink, u32 id, @@ -563,7 +532,7 @@ static const struct devlink_param mlx5_devlink_params[] = { BIT(DEVLINK_PARAM_CMODE_RUNTIME), mlx5_devlink_esw_multiport_get, mlx5_devlink_esw_multiport_set, - mlx5_devlink_esw_multiport_validate), + NULL), #endif DEVLINK_PARAM_GENERIC(IO_EQ_SIZE, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), NULL, NULL, mlx5_devlink_eq_depth_validate), diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index f40497823e65..7c0f2adbea00 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -490,7 +490,7 @@ static void poll_trace(struct mlx5_fw_tracer *tracer, (u64)timestamp_low; break; default: - if (tracer_event->event_id >= tracer->str_db.first_string_trace || + if (tracer_event->event_id >= tracer->str_db.first_string_trace && tracer_event->event_id <= tracer->str_db.first_string_trace + tracer->str_db.num_string_trace) { tracer_event->type = TRACER_EVENT_TYPE_STRING; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c index 9114661cd967..b0128336ff01 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c @@ -76,6 +76,16 @@ int mlx5_reporter_vnic_diagnose_counters(struct mlx5_core_dev *dev, if (err) return err; + err = devlink_fmsg_u64_pair_put(fmsg, "generated_pkt_steering_fail", + VNIC_ENV_GET64(&vnic, generated_pkt_steering_fail)); + if (err) + return err; + + err = devlink_fmsg_u64_pair_put(fmsg, "handled_pkt_steering_fail", + VNIC_ENV_GET64(&vnic, handled_pkt_steering_fail)); + if (err) + return err; + err = devlink_fmsg_obj_nest_end(fmsg); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index b8987a404d75..ceabe57c511a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -327,6 +327,7 @@ struct mlx5e_params { unsigned int sw_mtu; int hard_mtu; bool ptp_rx; + __be32 terminate_lkey_be; }; static inline u8 mlx5e_get_dcb_num_tc(struct mlx5e_params *params) @@ -593,13 +594,6 @@ struct mlx5e_mpw_info { #define MLX5E_MAX_RX_FRAGS 4 -/* a single cache unit is capable to serve one napi call (for non-striding rq) - * or a MPWQE (for striding rq). - */ -#define MLX5E_CACHE_UNIT (MLX5_MPWRQ_MAX_PAGES_PER_WQE > NAPI_POLL_WEIGHT ? \ - MLX5_MPWRQ_MAX_PAGES_PER_WQE : NAPI_POLL_WEIGHT) -#define MLX5E_CACHE_SIZE (4 * roundup_pow_of_two(MLX5E_CACHE_UNIT)) - struct mlx5e_rq; typedef void (*mlx5e_fp_handle_rx_cqe)(struct mlx5e_rq*, struct mlx5_cqe64*); typedef struct sk_buff * diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c index 7ac1ad9c46de..7e8e96cc5cd0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c @@ -51,7 +51,7 @@ int mlx5e_port_query_buffer(struct mlx5e_priv *priv, if (err) goto out; - for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) { buffer = MLX5_ADDR_OF(pbmc_reg, out, buffer[i]); port_buffer->buffer[i].lossy = MLX5_GET(bufferx_reg, buffer, lossy); @@ -73,14 +73,24 @@ int mlx5e_port_query_buffer(struct mlx5e_priv *priv, port_buffer->buffer[i].lossy); } - port_buffer->headroom_size = total_used; + port_buffer->internal_buffers_size = 0; + for (i = MLX5E_MAX_NETWORK_BUFFER; i < MLX5E_TOTAL_BUFFERS; i++) { + buffer = MLX5_ADDR_OF(pbmc_reg, out, buffer[i]); + port_buffer->internal_buffers_size += + MLX5_GET(bufferx_reg, buffer, size) * port_buff_cell_sz; + } + port_buffer->port_buffer_size = MLX5_GET(pbmc_reg, out, port_buffer_size) * port_buff_cell_sz; - port_buffer->spare_buffer_size = - port_buffer->port_buffer_size - total_used; - - mlx5e_dbg(HW, priv, "total buffer size=%d, spare buffer size=%d\n", - port_buffer->port_buffer_size, + port_buffer->headroom_size = total_used; + port_buffer->spare_buffer_size = port_buffer->port_buffer_size - + port_buffer->internal_buffers_size - + port_buffer->headroom_size; + + mlx5e_dbg(HW, priv, + "total buffer size=%u, headroom buffer size=%u, internal buffers size=%u, spare buffer size=%u\n", + port_buffer->port_buffer_size, port_buffer->headroom_size, + port_buffer->internal_buffers_size, port_buffer->spare_buffer_size); out: kfree(out); @@ -206,11 +216,11 @@ static int port_update_pool_cfg(struct mlx5_core_dev *mdev, if (!MLX5_CAP_GEN(mdev, sbcam_reg)) return 0; - for (i = 0; i < MLX5E_MAX_BUFFER; i++) + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) lossless_buff_count += ((port_buffer->buffer[i].size) && (!(port_buffer->buffer[i].lossy))); - for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) { p = select_sbcm_params(&port_buffer->buffer[i], lossless_buff_count); err = mlx5e_port_set_sbcm(mdev, 0, i, MLX5_INGRESS_DIR, @@ -293,7 +303,7 @@ static int port_set_buffer(struct mlx5e_priv *priv, if (err) goto out; - for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) { void *buffer = MLX5_ADDR_OF(pbmc_reg, in, buffer[i]); u64 size = port_buffer->buffer[i].size; u64 xoff = port_buffer->buffer[i].xoff; @@ -351,7 +361,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer, { int i; - for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) { if (port_buffer->buffer[i].lossy) { port_buffer->buffer[i].xoff = 0; port_buffer->buffer[i].xon = 0; @@ -408,7 +418,7 @@ static int update_buffer_lossy(struct mlx5_core_dev *mdev, int err; int i; - for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) { prio_count = 0; lossy_count = 0; @@ -432,11 +442,11 @@ static int update_buffer_lossy(struct mlx5_core_dev *mdev, } if (changed) { - err = port_update_pool_cfg(mdev, port_buffer); + err = update_xoff_threshold(port_buffer, xoff, max_mtu, port_buff_cell_sz); if (err) return err; - err = update_xoff_threshold(port_buffer, xoff, max_mtu, port_buff_cell_sz); + err = port_update_pool_cfg(mdev, port_buffer); if (err) return err; @@ -515,7 +525,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, if (change & MLX5E_PORT_BUFFER_PRIO2BUFFER) { update_prio2buffer = true; - for (i = 0; i < MLX5E_MAX_BUFFER; i++) + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) mlx5e_dbg(HW, priv, "%s: requested to map prio[%d] to buffer %d\n", __func__, i, prio2buffer[i]); @@ -530,7 +540,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, } if (change & MLX5E_PORT_BUFFER_SIZE) { - for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) { mlx5e_dbg(HW, priv, "%s: buffer[%d]=%d\n", __func__, i, buffer_size[i]); if (!port_buffer.buffer[i].lossy && !buffer_size[i]) { mlx5e_dbg(HW, priv, "%s: lossless buffer[%d] size cannot be zero\n", @@ -544,7 +554,9 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, mlx5e_dbg(HW, priv, "%s: total buffer requested=%d\n", __func__, total_used); - if (total_used > port_buffer.port_buffer_size) + if (total_used > port_buffer.headroom_size && + (total_used - port_buffer.headroom_size) > + port_buffer.spare_buffer_size) return -EINVAL; update_buffer = true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h index a6ef118de758..f4a19ffbb641 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h @@ -35,7 +35,8 @@ #include "en.h" #include "port.h" -#define MLX5E_MAX_BUFFER 8 +#define MLX5E_MAX_NETWORK_BUFFER 8 +#define MLX5E_TOTAL_BUFFERS 10 #define MLX5E_DEFAULT_CABLE_LEN 7 /* 7 meters */ #define MLX5_BUFFER_SUPPORTED(mdev) (MLX5_CAP_GEN(mdev, pcam_reg) && \ @@ -60,8 +61,9 @@ struct mlx5e_bufferx_reg { struct mlx5e_port_buffer { u32 port_buffer_size; u32 spare_buffer_size; - u32 headroom_size; - struct mlx5e_bufferx_reg buffer[MLX5E_MAX_BUFFER]; + u32 headroom_size; /* Buffers 0-7 */ + u32 internal_buffers_size; /* Buffers 8-9 */ + struct mlx5e_bufferx_reg buffer[MLX5E_MAX_NETWORK_BUFFER]; }; int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index eb5abd0e55d9..3cbebfba582b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -175,6 +175,8 @@ static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int budget) /* ensure cq space is freed before enabling more cqes */ wmb(); + mlx5e_txqsq_wake(&ptpsq->txqsq); + return work_done == budget; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c index 2842195ee548..1874c2f0587f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c @@ -379,6 +379,12 @@ int mlx5e_htb_setup_tc(struct mlx5e_priv *priv, struct tc_htb_qopt_offload *htb_ if (!htb && htb_qopt->command != TC_HTB_CREATE) return -EINVAL; + if (htb_qopt->prio) { + NL_SET_ERR_MSG_MOD(htb_qopt->extack, + "prio parameter is not supported by device with HTB offload enabled."); + return -EOPNOTSUPP; + } + switch (htb_qopt->command) { case TC_HTB_CREATE: if (!mlx5_qos_is_supported(priv->mdev)) { @@ -515,4 +521,3 @@ int mlx5e_mqprio_rl_get_node_hw_id(struct mlx5e_mqprio_rl *rl, int tc, u32 *hw_i *hw_id = rl->leaves_id[tc]; return 0; } - diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c index fc923a99b6a4..0380a04c3691 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c @@ -84,7 +84,7 @@ mlx5e_tc_act_init_parse_state(struct mlx5e_tc_act_parse_state *parse_state, int mlx5e_tc_act_post_parse(struct mlx5e_tc_act_parse_state *parse_state, - struct flow_action *flow_action, + struct flow_action *flow_action, int from, int to, struct mlx5_flow_attr *attr, enum mlx5_flow_namespace_type ns_type) { @@ -96,6 +96,11 @@ mlx5e_tc_act_post_parse(struct mlx5e_tc_act_parse_state *parse_state, priv = parse_state->flow->priv; flow_action_for_each(i, act, flow_action) { + if (i < from) + continue; + else if (i > to) + break; + tc_act = mlx5e_tc_act_get(act->id, ns_type); if (!tc_act || !tc_act->post_parse) continue; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h index 0e6e1872ac62..d6c12d0ea55b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h @@ -112,7 +112,7 @@ mlx5e_tc_act_init_parse_state(struct mlx5e_tc_act_parse_state *parse_state, int mlx5e_tc_act_post_parse(struct mlx5e_tc_act_parse_state *parse_state, - struct flow_action *flow_action, + struct flow_action *flow_action, int from, int to, struct mlx5_flow_attr *attr, enum mlx5_flow_namespace_type ns_type); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act_stats.c index 07c1895a2b23..7aa926e542d3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act_stats.c @@ -25,8 +25,8 @@ struct mlx5e_tc_act_stats { static const struct rhashtable_params act_counters_ht_params = { .head_offset = offsetof(struct mlx5e_tc_act_stats, hash), - .key_offset = 0, - .key_len = offsetof(struct mlx5e_tc_act_stats, counter), + .key_offset = offsetof(struct mlx5e_tc_act_stats, tc_act_cookie), + .key_len = sizeof_field(struct mlx5e_tc_act_stats, tc_act_cookie), .automatic_shrinking = true, }; @@ -169,14 +169,11 @@ mlx5e_tc_act_stats_fill_stats(struct mlx5e_tc_act_stats_handle *handle, { struct rhashtable *ht = &handle->ht; struct mlx5e_tc_act_stats *item; - struct mlx5e_tc_act_stats key; u64 pkts, bytes, lastused; int err = 0; - key.tc_act_cookie = fl_act->cookie; - rcu_read_lock(); - item = rhashtable_lookup(ht, &key, act_counters_ht_params); + item = rhashtable_lookup(ht, &fl_act->cookie, act_counters_ht_params); if (!item) { rcu_read_unlock(); err = -ENOENT; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h index ba2b1f24ff14..6cc23af66b5b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h @@ -94,13 +94,13 @@ struct mlx5e_tc_flow { * destinations. */ struct encap_flow_item encaps[MLX5_MAX_FLOW_FWD_VPORTS]; - struct mlx5e_tc_flow *peer_flow; struct mlx5e_hairpin_entry *hpe; /* attached hairpin instance */ struct list_head hairpin; /* flows sharing the same hairpin */ - struct list_head peer; /* flows with peer flow */ + struct list_head peer[MLX5_MAX_PORTS]; /* flows with peer flow */ struct list_head unready; /* flows not ready to be offloaded (e.g * due to missing route) */ + struct list_head peer_flows; /* flows on peer */ struct net_device *orig_dev; /* netdev adding flow first */ int tmp_entry_index; struct list_head tmp_list; /* temporary flow list used by neigh update */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index 20c2d2ecaf93..f0c3464f037f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -492,6 +492,19 @@ void mlx5e_encap_put(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e) mlx5e_encap_dealloc(priv, e); } +static void mlx5e_encap_put_locked(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + + lockdep_assert_held(&esw->offloads.encap_tbl_lock); + + if (!refcount_dec_and_test(&e->refcnt)) + return; + list_del(&e->route_list); + hash_del_rcu(&e->encap_hlist); + mlx5e_encap_dealloc(priv, e); +} + static void mlx5e_decap_put(struct mlx5e_priv *priv, struct mlx5e_decap_entry *d) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; @@ -816,6 +829,8 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, uintptr_t hash_key; int err = 0; + lockdep_assert_held(&esw->offloads.encap_tbl_lock); + parse_attr = attr->parse_attr; tun_info = parse_attr->tun_info[out_index]; mpls_info = &parse_attr->mpls_info[out_index]; @@ -829,7 +844,6 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, hash_key = hash_encap_info(&key); - mutex_lock(&esw->offloads.encap_tbl_lock); e = mlx5e_encap_get(priv, &key, hash_key); /* must verify if encap is valid or not */ @@ -840,15 +854,6 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, goto out_err; } - mutex_unlock(&esw->offloads.encap_tbl_lock); - wait_for_completion(&e->res_ready); - - /* Protect against concurrent neigh update. */ - mutex_lock(&esw->offloads.encap_tbl_lock); - if (e->compl_result < 0) { - err = -EREMOTEIO; - goto out_err; - } goto attach_flow; } @@ -877,15 +882,12 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, INIT_LIST_HEAD(&e->flows); hash_add_rcu(esw->offloads.encap_tbl, &e->encap_hlist, hash_key); tbl_time_before = mlx5e_route_tbl_get_last_update(priv); - mutex_unlock(&esw->offloads.encap_tbl_lock); if (family == AF_INET) err = mlx5e_tc_tun_create_header_ipv4(priv, mirred_dev, e); else if (family == AF_INET6) err = mlx5e_tc_tun_create_header_ipv6(priv, mirred_dev, e); - /* Protect against concurrent neigh update. */ - mutex_lock(&esw->offloads.encap_tbl_lock); complete_all(&e->res_ready); if (err) { e->compl_result = err; @@ -920,18 +922,15 @@ attach_flow: } else { flow_flag_set(flow, SLOW); } - mutex_unlock(&esw->offloads.encap_tbl_lock); return err; out_err: - mutex_unlock(&esw->offloads.encap_tbl_lock); if (e) - mlx5e_encap_put(priv, e); + mlx5e_encap_put_locked(priv, e); return err; out_err_init: - mutex_unlock(&esw->offloads.encap_tbl_lock); kfree(tun_info); kfree(e); return err; @@ -1016,6 +1015,93 @@ out_err: return err; } +int mlx5e_tc_tun_encap_dests_set(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, + struct netlink_ext_ack *extack, + bool *vf_tun) +{ + struct mlx5e_tc_flow_parse_attr *parse_attr; + struct mlx5_esw_flow_attr *esw_attr; + struct net_device *encap_dev = NULL; + struct mlx5e_rep_priv *rpriv; + struct mlx5e_priv *out_priv; + struct mlx5_eswitch *esw; + int out_index; + int err = 0; + + if (!mlx5e_is_eswitch_flow(flow)) + return 0; + + parse_attr = attr->parse_attr; + esw_attr = attr->esw_attr; + *vf_tun = false; + + esw = priv->mdev->priv.eswitch; + mutex_lock(&esw->offloads.encap_tbl_lock); + for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { + struct net_device *out_dev; + int mirred_ifindex; + + if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)) + continue; + + mirred_ifindex = parse_attr->mirred_ifindex[out_index]; + out_dev = dev_get_by_index(dev_net(priv->netdev), mirred_ifindex); + if (!out_dev) { + NL_SET_ERR_MSG_MOD(extack, "Requested mirred device not found"); + err = -ENODEV; + goto out; + } + err = mlx5e_attach_encap(priv, flow, attr, out_dev, out_index, + extack, &encap_dev); + dev_put(out_dev); + if (err) + goto out; + + if (esw_attr->dests[out_index].flags & + MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE && + !esw_attr->dest_int_port) + *vf_tun = true; + + out_priv = netdev_priv(encap_dev); + rpriv = out_priv->ppriv; + esw_attr->dests[out_index].rep = rpriv->rep; + esw_attr->dests[out_index].mdev = out_priv->mdev; + } + + if (*vf_tun && esw_attr->out_count > 1) { + NL_SET_ERR_MSG_MOD(extack, "VF tunnel encap with mirroring is not supported"); + err = -EOPNOTSUPP; + goto out; + } + +out: + mutex_unlock(&esw->offloads.encap_tbl_lock); + return err; +} + +void mlx5e_tc_tun_encap_dests_unset(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr) +{ + struct mlx5_esw_flow_attr *esw_attr; + int out_index; + + if (!mlx5e_is_eswitch_flow(flow)) + return; + + esw_attr = attr->esw_attr; + + for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { + if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)) + continue; + + mlx5e_detach_encap(flow->priv, flow, attr, out_index); + kfree(attr->parse_attr->tun_info[out_index]); + } +} + static int cmp_route_info(struct mlx5e_route_key *a, struct mlx5e_route_key *b) { @@ -1369,11 +1455,13 @@ static void mlx5e_invalidate_encap(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow; list_for_each_entry(flow, encap_flows, tmp_list) { - struct mlx5_flow_attr *attr = flow->attr; struct mlx5_esw_flow_attr *esw_attr; + struct mlx5_flow_attr *attr; if (!mlx5e_is_offloaded_flow(flow)) continue; + + attr = mlx5e_tc_get_encap_attr(flow); esw_attr = attr->esw_attr; if (flow_flag_test(flow, SLOW)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h index 8ad273dde40e..5d7d67687cbc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h @@ -30,6 +30,15 @@ int mlx5e_attach_decap_route(struct mlx5e_priv *priv, void mlx5e_detach_decap_route(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow); +int mlx5e_tc_tun_encap_dests_set(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, + struct netlink_ext_ack *extack, + bool *vf_tun); +void mlx5e_tc_tun_encap_dests_unset(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr); + struct ip_tunnel_info *mlx5e_dup_tun_info(const struct ip_tunnel_info *tun_info); int mlx5e_tc_set_attr_rx_tun(struct mlx5e_tc_flow *flow, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index 47381e949f1f..879d698b6119 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -193,6 +193,8 @@ static inline u16 mlx5e_txqsq_get_next_pi(struct mlx5e_txqsq *sq, u16 size) return pi; } +void mlx5e_txqsq_wake(struct mlx5e_txqsq *sq); + static inline u16 mlx5e_shampo_get_cqe_header_index(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) { return be16_to_cpu(cqe->shampo.header_entry_index) & (rq->mpwqe.shampo->hd_per_wq - 1); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index 1f90594499c6..41c396e76457 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -150,10 +150,8 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb, inlen = MLX5_ST_SZ_BYTES(modify_tir_in); in = kvzalloc(inlen, GFP_KERNEL); - if (!in) { - err = -ENOMEM; - goto out; - } + if (!in) + return -ENOMEM; if (enable_uc_lb) lb_flags = MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST; @@ -171,14 +169,13 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb, tirn = tir->tirn; err = mlx5_core_modify_tir(mdev, tirn, in); if (err) - goto out; + break; } + mutex_unlock(&mdev->mlx5e_res.hw_objs.td.list_lock); -out: kvfree(in); if (err) netdev_err(priv->netdev, "refresh tir(0x%x) failed, %d\n", tirn, err); - mutex_unlock(&mdev->mlx5e_res.hw_objs.td.list_lock); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 89de92d06483..ebee52a8361a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -926,9 +926,10 @@ static int mlx5e_dcbnl_getbuffer(struct net_device *dev, if (err) return err; - for (i = 0; i < MLX5E_MAX_BUFFER; i++) + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) dcb_buffer->buffer_size[i] = port_buffer.buffer[i].size; - dcb_buffer->total_size = port_buffer.port_buffer_size; + dcb_buffer->total_size = port_buffer.port_buffer_size - + port_buffer.internal_buffers_size; return 0; } @@ -970,7 +971,7 @@ static int mlx5e_dcbnl_setbuffer(struct net_device *dev, if (err) return err; - for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) { if (port_buffer.buffer[i].size != dcb_buffer->buffer_size[i]) { changed |= MLX5E_PORT_BUFFER_SIZE; buffer_size = dcb_buffer->buffer_size; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 33bfe4d7338b..934b0d5ce1b3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -283,7 +283,7 @@ static int __mlx5e_add_vlan_rule(struct mlx5e_flow_steering *fs, if (IS_ERR(*rule_p)) { err = PTR_ERR(*rule_p); *rule_p = NULL; - fs_err(fs, "%s: add rule failed\n", __func__); + fs_err(fs, "add rule failed\n"); } return err; @@ -395,8 +395,7 @@ int mlx5e_add_vlan_trap(struct mlx5e_flow_steering *fs, int trap_id, int tir_num if (IS_ERR(rule)) { err = PTR_ERR(rule); fs->vlan->trap_rule = NULL; - fs_err(fs, "%s: add VLAN trap rule failed, err %d\n", - __func__, err); + fs_err(fs, "add VLAN trap rule failed, err %d\n", err); return err; } fs->vlan->trap_rule = rule; @@ -421,8 +420,7 @@ int mlx5e_add_mac_trap(struct mlx5e_flow_steering *fs, int trap_id, int tir_num) if (IS_ERR(rule)) { err = PTR_ERR(rule); fs->l2.trap_rule = NULL; - fs_err(fs, "%s: add MAC trap rule failed, err %d\n", - __func__, err); + fs_err(fs, "add MAC trap rule failed, err %d\n", err); return err; } fs->l2.trap_rule = rule; @@ -763,7 +761,7 @@ static int mlx5e_add_promisc_rule(struct mlx5e_flow_steering *fs) if (IS_ERR(*rule_p)) { err = PTR_ERR(*rule_p); *rule_p = NULL; - fs_err(fs, "%s: add promiscuous rule failed\n", __func__); + fs_err(fs, "add promiscuous rule failed\n"); } kvfree(spec); return err; @@ -995,7 +993,7 @@ static int mlx5e_add_l2_flow_rule(struct mlx5e_flow_steering *fs, ai->rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); if (IS_ERR(ai->rule)) { - fs_err(fs, "%s: add l2 rule(mac:%pM) failed\n", __func__, mv_dmac); + fs_err(fs, "add l2 rule(mac:%pM) failed\n", mv_dmac); err = PTR_ERR(ai->rule); ai->rule = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 2944691f06ad..a7c526ee5024 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -727,26 +727,6 @@ static void mlx5e_rq_free_shampo(struct mlx5e_rq *rq) mlx5e_rq_shampo_hd_free(rq); } -static __be32 mlx5e_get_terminate_scatter_list_mkey(struct mlx5_core_dev *dev) -{ - u32 out[MLX5_ST_SZ_DW(query_special_contexts_out)] = {}; - u32 in[MLX5_ST_SZ_DW(query_special_contexts_in)] = {}; - int res; - - if (!MLX5_CAP_GEN(dev, terminate_scatter_list_mkey)) - return MLX5_TERMINATE_SCATTER_LIST_LKEY; - - MLX5_SET(query_special_contexts_in, in, opcode, - MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS); - res = mlx5_cmd_exec_inout(dev, query_special_contexts, in, out); - if (res) - return MLX5_TERMINATE_SCATTER_LIST_LKEY; - - res = MLX5_GET(query_special_contexts_out, out, - terminate_scatter_list_mkey); - return cpu_to_be32(res); -} - static int mlx5e_alloc_rq(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, struct mlx5e_rq_param *rqp, @@ -908,7 +888,7 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params, /* check if num_frags is not a pow of two */ if (rq->wqe.info.num_frags < (1 << rq->wqe.info.log_num_frags)) { wqe->data[f].byte_count = 0; - wqe->data[f].lkey = mlx5e_get_terminate_scatter_list_mkey(mdev); + wqe->data[f].lkey = params->terminate_lkey_be; wqe->data[f].addr = 0; } } @@ -5007,6 +4987,8 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 /* RQ */ mlx5e_build_rq_params(mdev, params); + params->terminate_lkey_be = mlx5_core_get_terminate_scatter_list_mkey(mdev); + params->packet_merge.timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT); /* CQ moderation params */ @@ -5279,12 +5261,16 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev, mlx5e_timestamp_init(priv); + priv->dfs_root = debugfs_create_dir("nic", + mlx5_debugfs_get_dev_root(mdev)); + fs = mlx5e_fs_init(priv->profile, mdev, !test_bit(MLX5E_STATE_DESTROYING, &priv->state), priv->dfs_root); if (!fs) { err = -ENOMEM; mlx5_core_err(mdev, "FS initialization failed, %d\n", err); + debugfs_remove_recursive(priv->dfs_root); return err; } priv->fs = fs; @@ -5305,6 +5291,7 @@ static void mlx5e_nic_cleanup(struct mlx5e_priv *priv) mlx5e_health_destroy_reporters(priv); mlx5e_ktls_cleanup(priv); mlx5e_fs_cleanup(priv->fs); + debugfs_remove_recursive(priv->dfs_root); priv->fs = NULL; } @@ -5851,8 +5838,8 @@ void mlx5e_detach_netdev(struct mlx5e_priv *priv) } static int -mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mdev, - const struct mlx5e_profile *new_profile, void *new_ppriv) +mlx5e_netdev_init_profile(struct net_device *netdev, struct mlx5_core_dev *mdev, + const struct mlx5e_profile *new_profile, void *new_ppriv) { struct mlx5e_priv *priv = netdev_priv(netdev); int err; @@ -5868,6 +5855,25 @@ mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mde err = new_profile->init(priv->mdev, priv->netdev); if (err) goto priv_cleanup; + + return 0; + +priv_cleanup: + mlx5e_priv_cleanup(priv); + return err; +} + +static int +mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mdev, + const struct mlx5e_profile *new_profile, void *new_ppriv) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + int err; + + err = mlx5e_netdev_init_profile(netdev, mdev, new_profile, new_ppriv); + if (err) + return err; + err = mlx5e_attach_netdev(priv); if (err) goto profile_cleanup; @@ -5875,7 +5881,6 @@ mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mde profile_cleanup: new_profile->cleanup(priv); -priv_cleanup: mlx5e_priv_cleanup(priv); return err; } @@ -5894,6 +5899,12 @@ int mlx5e_netdev_change_profile(struct mlx5e_priv *priv, priv->profile->cleanup(priv); mlx5e_priv_cleanup(priv); + if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) { + mlx5e_netdev_init_profile(netdev, mdev, new_profile, new_ppriv); + set_bit(MLX5E_STATE_DESTROYING, &priv->state); + return -EIO; + } + err = mlx5e_netdev_attach_profile(netdev, mdev, new_profile, new_ppriv); if (err) { /* roll back to original profile */ netdev_warn(netdev, "%s: new profile init failed, %d\n", __func__, err); @@ -5955,8 +5966,11 @@ static int mlx5e_suspend(struct auxiliary_device *adev, pm_message_t state) struct net_device *netdev = priv->netdev; struct mlx5_core_dev *mdev = priv->mdev; - if (!netif_device_present(netdev)) + if (!netif_device_present(netdev)) { + if (test_bit(MLX5E_STATE_DESTROYING, &priv->state)) + mlx5e_destroy_mdev_resources(mdev); return -ENODEV; + } mlx5e_detach_netdev(priv); mlx5e_destroy_mdev_resources(mdev); @@ -6002,9 +6016,6 @@ static int mlx5e_probe(struct auxiliary_device *adev, priv->profile = profile; priv->ppriv = NULL; - priv->dfs_root = debugfs_create_dir("nic", - mlx5_debugfs_get_dev_root(priv->mdev)); - err = profile->init(mdev, netdev); if (err) { mlx5_core_err(mdev, "mlx5e_nic_profile init failed, %d\n", err); @@ -6033,7 +6044,6 @@ err_resume: err_profile_cleanup: profile->cleanup(priv); err_destroy_netdev: - debugfs_remove_recursive(priv->dfs_root); mlx5e_destroy_netdev(priv); err_devlink_port_unregister: mlx5e_devlink_port_unregister(mlx5e_dev); @@ -6053,7 +6063,6 @@ static void mlx5e_remove(struct auxiliary_device *adev) unregister_netdev(priv->netdev); mlx5e_suspend(adev, state); priv->profile->cleanup(priv); - debugfs_remove_recursive(priv->dfs_root); mlx5e_destroy_netdev(priv); mlx5e_devlink_port_unregister(mlx5e_dev); mlx5e_destroy_devlink(mlx5e_dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 1fc386eccaf8..965a8261c99b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -30,6 +30,7 @@ * SOFTWARE. */ +#include <linux/debugfs.h> #include <linux/mlx5/fs.h> #include <net/switchdev.h> #include <net/pkt_cls.h> @@ -373,7 +374,9 @@ static void mlx5e_sqs2vport_stop(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep) { struct mlx5e_rep_sq *rep_sq, *tmp; + struct mlx5e_rep_sq_peer *sq_peer; struct mlx5e_rep_priv *rpriv; + unsigned long i; if (esw->mode != MLX5_ESWITCH_OFFLOADS) return; @@ -381,31 +384,78 @@ static void mlx5e_sqs2vport_stop(struct mlx5_eswitch *esw, rpriv = mlx5e_rep_to_rep_priv(rep); list_for_each_entry_safe(rep_sq, tmp, &rpriv->vport_sqs_list, list) { mlx5_eswitch_del_send_to_vport_rule(rep_sq->send_to_vport_rule); - if (rep_sq->send_to_vport_rule_peer) - mlx5_eswitch_del_send_to_vport_rule(rep_sq->send_to_vport_rule_peer); + xa_for_each(&rep_sq->sq_peer, i, sq_peer) { + if (sq_peer->rule) + mlx5_eswitch_del_send_to_vport_rule(sq_peer->rule); + + xa_erase(&rep_sq->sq_peer, i); + kfree(sq_peer); + } + + xa_destroy(&rep_sq->sq_peer); list_del(&rep_sq->list); kfree(rep_sq); } } +static int mlx5e_sqs2vport_add_peers_rules(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep, + struct mlx5_devcom *devcom, + struct mlx5e_rep_sq *rep_sq, int i) +{ + struct mlx5_eswitch *peer_esw = NULL; + struct mlx5_flow_handle *flow_rule; + int tmp; + + mlx5_devcom_for_each_peer_entry(devcom, MLX5_DEVCOM_ESW_OFFLOADS, + peer_esw, tmp) { + int peer_rule_idx = mlx5_get_dev_index(peer_esw->dev); + struct mlx5e_rep_sq_peer *sq_peer; + int err; + + sq_peer = kzalloc(sizeof(*sq_peer), GFP_KERNEL); + if (!sq_peer) + return -ENOMEM; + + flow_rule = mlx5_eswitch_add_send_to_vport_rule(peer_esw, esw, + rep, rep_sq->sqn); + if (IS_ERR(flow_rule)) { + kfree(sq_peer); + return PTR_ERR(flow_rule); + } + + sq_peer->rule = flow_rule; + sq_peer->peer = peer_esw; + err = xa_insert(&rep_sq->sq_peer, peer_rule_idx, sq_peer, GFP_KERNEL); + if (err) { + kfree(sq_peer); + mlx5_eswitch_del_send_to_vport_rule(flow_rule); + return err; + } + } + + return 0; +} + static int mlx5e_sqs2vport_start(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep, u32 *sqns_array, int sqns_num) { - struct mlx5_eswitch *peer_esw = NULL; struct mlx5_flow_handle *flow_rule; struct mlx5e_rep_priv *rpriv; struct mlx5e_rep_sq *rep_sq; + struct mlx5_devcom *devcom; + bool devcom_locked = false; int err; int i; if (esw->mode != MLX5_ESWITCH_OFFLOADS) return 0; + devcom = esw->dev->priv.devcom; rpriv = mlx5e_rep_to_rep_priv(rep); - if (mlx5_devcom_is_paired(esw->dev->priv.devcom, MLX5_DEVCOM_ESW_OFFLOADS)) - peer_esw = mlx5_devcom_get_peer_data(esw->dev->priv.devcom, - MLX5_DEVCOM_ESW_OFFLOADS); + if (mlx5_devcom_comp_is_ready(devcom, MLX5_DEVCOM_ESW_OFFLOADS) && + mlx5_devcom_for_each_peer_begin(devcom, MLX5_DEVCOM_ESW_OFFLOADS)) + devcom_locked = true; for (i = 0; i < sqns_num; i++) { rep_sq = kzalloc(sizeof(*rep_sq), GFP_KERNEL); @@ -425,31 +475,30 @@ static int mlx5e_sqs2vport_start(struct mlx5_eswitch *esw, rep_sq->send_to_vport_rule = flow_rule; rep_sq->sqn = sqns_array[i]; - if (peer_esw) { - flow_rule = mlx5_eswitch_add_send_to_vport_rule(peer_esw, esw, - rep, sqns_array[i]); - if (IS_ERR(flow_rule)) { - err = PTR_ERR(flow_rule); + xa_init(&rep_sq->sq_peer); + if (devcom_locked) { + err = mlx5e_sqs2vport_add_peers_rules(esw, rep, devcom, rep_sq, i); + if (err) { mlx5_eswitch_del_send_to_vport_rule(rep_sq->send_to_vport_rule); + xa_destroy(&rep_sq->sq_peer); kfree(rep_sq); goto out_err; } - rep_sq->send_to_vport_rule_peer = flow_rule; } list_add(&rep_sq->list, &rpriv->vport_sqs_list); } - if (peer_esw) - mlx5_devcom_release_peer_data(esw->dev->priv.devcom, MLX5_DEVCOM_ESW_OFFLOADS); + if (devcom_locked) + mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); return 0; out_err: mlx5e_sqs2vport_stop(esw, rep); - if (peer_esw) - mlx5_devcom_release_peer_data(esw->dev->priv.devcom, MLX5_DEVCOM_ESW_OFFLOADS); + if (devcom_locked) + mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); return err; } @@ -812,11 +861,15 @@ static int mlx5e_init_ul_rep(struct mlx5_core_dev *mdev, { struct mlx5e_priv *priv = netdev_priv(netdev); + priv->dfs_root = debugfs_create_dir("nic", + mlx5_debugfs_get_dev_root(mdev)); + priv->fs = mlx5e_fs_init(priv->profile, mdev, !test_bit(MLX5E_STATE_DESTROYING, &priv->state), priv->dfs_root); if (!priv->fs) { netdev_err(priv->netdev, "FS allocation failed\n"); + debugfs_remove_recursive(priv->dfs_root); return -ENOMEM; } @@ -829,6 +882,7 @@ static int mlx5e_init_ul_rep(struct mlx5_core_dev *mdev, static void mlx5e_cleanup_rep(struct mlx5e_priv *priv) { mlx5e_fs_cleanup(priv->fs); + debugfs_remove_recursive(priv->dfs_root); priv->fs = NULL; } @@ -1524,17 +1578,24 @@ static void *mlx5e_vport_rep_get_proto_dev(struct mlx5_eswitch_rep *rep) return rpriv->netdev; } -static void mlx5e_vport_rep_event_unpair(struct mlx5_eswitch_rep *rep) +static void mlx5e_vport_rep_event_unpair(struct mlx5_eswitch_rep *rep, + struct mlx5_eswitch *peer_esw) { + int i = mlx5_get_dev_index(peer_esw->dev); struct mlx5e_rep_priv *rpriv; struct mlx5e_rep_sq *rep_sq; + WARN_ON_ONCE(!peer_esw); rpriv = mlx5e_rep_to_rep_priv(rep); list_for_each_entry(rep_sq, &rpriv->vport_sqs_list, list) { - if (!rep_sq->send_to_vport_rule_peer) + struct mlx5e_rep_sq_peer *sq_peer = xa_load(&rep_sq->sq_peer, i); + + if (!sq_peer || sq_peer->peer != peer_esw) continue; - mlx5_eswitch_del_send_to_vport_rule(rep_sq->send_to_vport_rule_peer); - rep_sq->send_to_vport_rule_peer = NULL; + + mlx5_eswitch_del_send_to_vport_rule(sq_peer->rule); + xa_erase(&rep_sq->sq_peer, i); + kfree(sq_peer); } } @@ -1542,24 +1603,52 @@ static int mlx5e_vport_rep_event_pair(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep, struct mlx5_eswitch *peer_esw) { + int i = mlx5_get_dev_index(peer_esw->dev); struct mlx5_flow_handle *flow_rule; + struct mlx5e_rep_sq_peer *sq_peer; struct mlx5e_rep_priv *rpriv; struct mlx5e_rep_sq *rep_sq; + int err; rpriv = mlx5e_rep_to_rep_priv(rep); list_for_each_entry(rep_sq, &rpriv->vport_sqs_list, list) { - if (rep_sq->send_to_vport_rule_peer) + sq_peer = xa_load(&rep_sq->sq_peer, i); + + if (sq_peer && sq_peer->peer) continue; - flow_rule = mlx5_eswitch_add_send_to_vport_rule(peer_esw, esw, rep, rep_sq->sqn); - if (IS_ERR(flow_rule)) + + flow_rule = mlx5_eswitch_add_send_to_vport_rule(peer_esw, esw, rep, + rep_sq->sqn); + if (IS_ERR(flow_rule)) { + err = PTR_ERR(flow_rule); goto err_out; - rep_sq->send_to_vport_rule_peer = flow_rule; + } + + if (sq_peer) { + sq_peer->rule = flow_rule; + sq_peer->peer = peer_esw; + continue; + } + sq_peer = kzalloc(sizeof(*sq_peer), GFP_KERNEL); + if (!sq_peer) { + err = -ENOMEM; + goto err_sq_alloc; + } + err = xa_insert(&rep_sq->sq_peer, i, sq_peer, GFP_KERNEL); + if (err) + goto err_xa; + sq_peer->rule = flow_rule; + sq_peer->peer = peer_esw; } return 0; +err_xa: + kfree(sq_peer); +err_sq_alloc: + mlx5_eswitch_del_send_to_vport_rule(flow_rule); err_out: - mlx5e_vport_rep_event_unpair(rep); - return PTR_ERR(flow_rule); + mlx5e_vport_rep_event_unpair(rep, peer_esw); + return err; } static int mlx5e_vport_rep_event(struct mlx5_eswitch *esw, @@ -1572,7 +1661,7 @@ static int mlx5e_vport_rep_event(struct mlx5_eswitch *esw, if (event == MLX5_SWITCHDEV_EVENT_PAIR) err = mlx5e_vport_rep_event_pair(esw, rep, data); else if (event == MLX5_SWITCHDEV_EVENT_UNPAIR) - mlx5e_vport_rep_event_unpair(rep); + mlx5e_vport_rep_event_unpair(rep, data); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index 80b7f5079a5a..70640fa1ad7b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -225,9 +225,14 @@ struct mlx5e_encap_entry { struct rcu_head rcu; }; +struct mlx5e_rep_sq_peer { + struct mlx5_flow_handle *rule; + void *peer; +}; + struct mlx5e_rep_sq { struct mlx5_flow_handle *send_to_vport_rule; - struct mlx5_flow_handle *send_to_vport_rule_peer; + struct xarray sq_peer; u32 sqn; struct list_head list; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 728b82ce4031..88631fb9f966 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1665,11 +1665,12 @@ bool mlx5e_tc_is_vf_tunnel(struct net_device *out_dev, struct net_device *route_ int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *route_dev, u16 *vport) { struct mlx5e_priv *out_priv, *route_priv; - struct mlx5_devcom *devcom = NULL; struct mlx5_core_dev *route_mdev; + struct mlx5_devcom *devcom; struct mlx5_eswitch *esw; u16 vhca_id; int err; + int i; out_priv = netdev_priv(out_dev); esw = out_priv->mdev->priv.eswitch; @@ -1677,112 +1678,27 @@ int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *ro route_mdev = route_priv->mdev; vhca_id = MLX5_CAP_GEN(route_mdev, vhca_id); - if (mlx5_lag_is_active(out_priv->mdev)) { - /* In lag case we may get devices from different eswitch instances. - * If we failed to get vport num, it means, mostly, that we on the wrong - * eswitch. - */ - err = mlx5_eswitch_vhca_id_to_vport(esw, vhca_id, vport); - if (err != -ENOENT) - return err; - - devcom = out_priv->mdev->priv.devcom; - esw = mlx5_devcom_get_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); - if (!esw) - return -ENODEV; - } - err = mlx5_eswitch_vhca_id_to_vport(esw, vhca_id, vport); - if (devcom) - mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); - return err; -} - -static int -set_encap_dests(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow, - struct mlx5_flow_attr *attr, - struct netlink_ext_ack *extack, - bool *vf_tun) -{ - struct mlx5e_tc_flow_parse_attr *parse_attr; - struct mlx5_esw_flow_attr *esw_attr; - struct net_device *encap_dev = NULL; - struct mlx5e_rep_priv *rpriv; - struct mlx5e_priv *out_priv; - int out_index; - int err = 0; - - if (!mlx5e_is_eswitch_flow(flow)) - return 0; - - parse_attr = attr->parse_attr; - esw_attr = attr->esw_attr; - *vf_tun = false; - - for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { - struct net_device *out_dev; - int mirred_ifindex; - - if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)) - continue; - - mirred_ifindex = parse_attr->mirred_ifindex[out_index]; - out_dev = dev_get_by_index(dev_net(priv->netdev), mirred_ifindex); - if (!out_dev) { - NL_SET_ERR_MSG_MOD(extack, "Requested mirred device not found"); - err = -ENODEV; - goto out; - } - err = mlx5e_attach_encap(priv, flow, attr, out_dev, out_index, - extack, &encap_dev); - dev_put(out_dev); - if (err) - goto out; - - if (esw_attr->dests[out_index].flags & - MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE && - !esw_attr->dest_int_port) - *vf_tun = true; + if (!err) + return err; - out_priv = netdev_priv(encap_dev); - rpriv = out_priv->ppriv; - esw_attr->dests[out_index].rep = rpriv->rep; - esw_attr->dests[out_index].mdev = out_priv->mdev; - } + if (!mlx5_lag_is_active(out_priv->mdev)) + return err; - if (*vf_tun && esw_attr->out_count > 1) { - NL_SET_ERR_MSG_MOD(extack, "VF tunnel encap with mirroring is not supported"); - err = -EOPNOTSUPP; - goto out; + rcu_read_lock(); + devcom = out_priv->mdev->priv.devcom; + err = -ENODEV; + mlx5_devcom_for_each_peer_entry_rcu(devcom, MLX5_DEVCOM_ESW_OFFLOADS, + esw, i) { + err = mlx5_eswitch_vhca_id_to_vport(esw, vhca_id, vport); + if (!err) + break; } + rcu_read_unlock(); -out: return err; } -static void -clean_encap_dests(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow, - struct mlx5_flow_attr *attr) -{ - struct mlx5_esw_flow_attr *esw_attr; - int out_index; - - if (!mlx5e_is_eswitch_flow(flow)) - return; - - esw_attr = attr->esw_attr; - - for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { - if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)) - continue; - - mlx5e_detach_encap(priv, flow, attr, out_index); - kfree(attr->parse_attr->tun_info[out_index]); - } -} - static int verify_attr_actions(u32 actions, struct netlink_ext_ack *extack) { @@ -1819,7 +1735,7 @@ post_process_attr(struct mlx5e_tc_flow *flow, if (err) goto err_out; - err = set_encap_dests(flow->priv, flow, attr, extack, &vf_tun); + err = mlx5e_tc_tun_encap_dests_set(flow->priv, flow, attr, extack, &vf_tun); if (err) goto err_out; @@ -2070,47 +1986,59 @@ void mlx5e_put_flow_list(struct mlx5e_priv *priv, struct list_head *flow_list) mlx5e_flow_put(priv, flow); } -static void __mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow) +static void mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow, + int peer_index) { struct mlx5_eswitch *esw = flow->priv->mdev->priv.eswitch; + struct mlx5e_tc_flow *peer_flow; + struct mlx5e_tc_flow *tmp; if (!flow_flag_test(flow, ESWITCH) || !flow_flag_test(flow, DUP)) return; mutex_lock(&esw->offloads.peer_mutex); - list_del(&flow->peer); + list_del(&flow->peer[peer_index]); mutex_unlock(&esw->offloads.peer_mutex); - flow_flag_clear(flow, DUP); - - if (refcount_dec_and_test(&flow->peer_flow->refcnt)) { - mlx5e_tc_del_fdb_flow(flow->peer_flow->priv, flow->peer_flow); - kfree(flow->peer_flow); + list_for_each_entry_safe(peer_flow, tmp, &flow->peer_flows, peer_flows) { + if (peer_index != mlx5_get_dev_index(peer_flow->priv->mdev)) + continue; + if (refcount_dec_and_test(&peer_flow->refcnt)) { + mlx5e_tc_del_fdb_flow(peer_flow->priv, peer_flow); + list_del(&peer_flow->peer_flows); + kfree(peer_flow); + } } - flow->peer_flow = NULL; + if (list_empty(&flow->peer_flows)) + flow_flag_clear(flow, DUP); } -static void mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow) +static void mlx5e_tc_del_fdb_peers_flow(struct mlx5e_tc_flow *flow) { - struct mlx5_core_dev *dev = flow->priv->mdev; - struct mlx5_devcom *devcom = dev->priv.devcom; - struct mlx5_eswitch *peer_esw; - - peer_esw = mlx5_devcom_get_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); - if (!peer_esw) - return; + int i; - __mlx5e_tc_del_fdb_peer_flow(flow); - mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + for (i = 0; i < MLX5_MAX_PORTS; i++) { + if (i == mlx5_get_dev_index(flow->priv->mdev)) + continue; + mlx5e_tc_del_fdb_peer_flow(flow, i); + } } static void mlx5e_tc_del_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow) { if (mlx5e_is_eswitch_flow(flow)) { - mlx5e_tc_del_fdb_peer_flow(flow); + struct mlx5_devcom *devcom = flow->priv->mdev->priv.devcom; + + if (!mlx5_devcom_for_each_peer_begin(devcom, MLX5_DEVCOM_ESW_OFFLOADS)) { + mlx5e_tc_del_fdb_flow(priv, flow); + return; + } + + mlx5e_tc_del_fdb_peers_flow(flow); + mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); mlx5e_tc_del_fdb_flow(priv, flow); } else { mlx5e_tc_del_nic_flow(priv, flow); @@ -2586,6 +2514,12 @@ static int mlx5e_flower_parse_meta(struct net_device *filter_dev, return 0; flow_rule_match_meta(rule, &match); + + if (match.mask->l2_miss) { + NL_SET_ERR_MSG_MOD(f->common.extack, "Can't match on \"l2_miss\""); + return -EOPNOTSUPP; + } + if (!match.mask->ingress_ifindex) return 0; @@ -3943,8 +3877,8 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state, struct mlx5_flow_attr *prev_attr; struct flow_action_entry *act; struct mlx5e_tc_act *tc_act; + int err, i, i_split = 0; bool is_missable; - int err, i; ns_type = mlx5e_get_flow_namespace(flow); list_add(&attr->list, &flow->attrs); @@ -3985,7 +3919,8 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state, i < flow_action->num_entries - 1)) { is_missable = tc_act->is_missable ? tc_act->is_missable(act) : false; - err = mlx5e_tc_act_post_parse(parse_state, flow_action, attr, ns_type); + err = mlx5e_tc_act_post_parse(parse_state, flow_action, i_split, i, attr, + ns_type); if (err) goto out_free_post_acts; @@ -3995,6 +3930,7 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state, goto out_free_post_acts; } + i_split = i + 1; list_add(&attr->list, &flow->attrs); } @@ -4009,7 +3945,7 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state, } } - err = mlx5e_tc_act_post_parse(parse_state, flow_action, attr, ns_type); + err = mlx5e_tc_act_post_parse(parse_state, flow_action, i_split, i, attr, ns_type); if (err) goto out_free_post_acts; @@ -4279,8 +4215,8 @@ static bool is_peer_flow_needed(struct mlx5e_tc_flow *flow) flow_flag_test(flow, INGRESS); bool act_is_encap = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT); - bool esw_paired = mlx5_devcom_is_paired(esw_attr->in_mdev->priv.devcom, - MLX5_DEVCOM_ESW_OFFLOADS); + bool esw_paired = mlx5_devcom_comp_is_ready(esw_attr->in_mdev->priv.devcom, + MLX5_DEVCOM_ESW_OFFLOADS); if (!esw_paired) return false; @@ -4323,7 +4259,7 @@ mlx5_free_flow_attr_actions(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *a if (attr->post_act_handle) mlx5e_tc_post_act_del(get_post_action(flow->priv), attr->post_act_handle); - clean_encap_dests(flow->priv, flow, attr); + mlx5e_tc_tun_encap_dests_unset(flow->priv, flow, attr); if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) mlx5_fc_destroy(counter_dev, attr->counter); @@ -4371,6 +4307,7 @@ mlx5e_alloc_flow(struct mlx5e_priv *priv, int attr_size, INIT_LIST_HEAD(&flow->hairpin); INIT_LIST_HEAD(&flow->l3_to_l2_reformat); INIT_LIST_HEAD(&flow->attrs); + INIT_LIST_HEAD(&flow->peer_flows); refcount_set(&flow->refcnt, 1); init_completion(&flow->init_done); init_completion(&flow->del_hw_done); @@ -4479,22 +4416,19 @@ out: static int mlx5e_tc_add_fdb_peer_flow(struct flow_cls_offload *f, struct mlx5e_tc_flow *flow, - unsigned long flow_flags) + unsigned long flow_flags, + struct mlx5_eswitch *peer_esw) { struct mlx5e_priv *priv = flow->priv, *peer_priv; - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch, *peer_esw; + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_esw_flow_attr *attr = flow->attr->esw_attr; - struct mlx5_devcom *devcom = priv->mdev->priv.devcom; struct mlx5e_tc_flow_parse_attr *parse_attr; + int i = mlx5_get_dev_index(peer_esw->dev); struct mlx5e_rep_priv *peer_urpriv; struct mlx5e_tc_flow *peer_flow; struct mlx5_core_dev *in_mdev; int err = 0; - peer_esw = mlx5_devcom_get_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); - if (!peer_esw) - return -ENODEV; - peer_urpriv = mlx5_eswitch_get_uplink_priv(peer_esw, REP_ETH); peer_priv = netdev_priv(peer_urpriv->netdev); @@ -4519,14 +4453,13 @@ static int mlx5e_tc_add_fdb_peer_flow(struct flow_cls_offload *f, goto out; } - flow->peer_flow = peer_flow; + list_add_tail(&peer_flow->peer_flows, &flow->peer_flows); flow_flag_set(flow, DUP); mutex_lock(&esw->offloads.peer_mutex); - list_add_tail(&flow->peer, &esw->offloads.peer_flows); + list_add_tail(&flow->peer[i], &esw->offloads.peer_flows[i]); mutex_unlock(&esw->offloads.peer_mutex); out: - mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); return err; } @@ -4537,30 +4470,48 @@ mlx5e_add_fdb_flow(struct mlx5e_priv *priv, struct net_device *filter_dev, struct mlx5e_tc_flow **__flow) { + struct mlx5_devcom *devcom = priv->mdev->priv.devcom; struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *in_rep = rpriv->rep; struct mlx5_core_dev *in_mdev = priv->mdev; + struct mlx5_eswitch *peer_esw; struct mlx5e_tc_flow *flow; int err; + int i; flow = __mlx5e_add_fdb_flow(priv, f, flow_flags, filter_dev, in_rep, in_mdev); if (IS_ERR(flow)) return PTR_ERR(flow); - if (is_peer_flow_needed(flow)) { - err = mlx5e_tc_add_fdb_peer_flow(f, flow, flow_flags); - if (err) { - mlx5e_tc_del_fdb_flow(priv, flow); - goto out; - } + if (!is_peer_flow_needed(flow)) { + *__flow = flow; + return 0; } - *__flow = flow; + if (!mlx5_devcom_for_each_peer_begin(devcom, MLX5_DEVCOM_ESW_OFFLOADS)) { + err = -ENODEV; + goto clean_flow; + } + mlx5_devcom_for_each_peer_entry(devcom, + MLX5_DEVCOM_ESW_OFFLOADS, + peer_esw, i) { + err = mlx5e_tc_add_fdb_peer_flow(f, flow, flow_flags, peer_esw); + if (err) + goto peer_clean; + } + + mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + + *__flow = flow; return 0; -out: +peer_clean: + mlx5e_tc_del_fdb_peers_flow(flow); + mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); +clean_flow: + mlx5e_tc_del_fdb_flow(priv, flow); return err; } @@ -4778,7 +4729,6 @@ int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv, { struct mlx5_devcom *devcom = priv->mdev->priv.devcom; struct rhashtable *tc_ht = get_tc_ht(priv, flags); - struct mlx5_eswitch *peer_esw; struct mlx5e_tc_flow *flow; struct mlx5_fc *counter; u64 lastuse = 0; @@ -4813,23 +4763,29 @@ int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv, /* Under multipath it's possible for one rule to be currently * un-offloaded while the other rule is offloaded. */ - peer_esw = mlx5_devcom_get_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); - if (!peer_esw) + if (!mlx5_devcom_for_each_peer_begin(devcom, MLX5_DEVCOM_ESW_OFFLOADS)) goto out; - if (flow_flag_test(flow, DUP) && - flow_flag_test(flow->peer_flow, OFFLOADED)) { - u64 bytes2; - u64 packets2; - u64 lastuse2; + if (flow_flag_test(flow, DUP)) { + struct mlx5e_tc_flow *peer_flow; - if (flow_flag_test(flow, USE_ACT_STATS)) { - f->use_act_stats = true; - } else { - counter = mlx5e_tc_get_counter(flow->peer_flow); + list_for_each_entry(peer_flow, &flow->peer_flows, peer_flows) { + u64 packets2; + u64 lastuse2; + u64 bytes2; + + if (!flow_flag_test(peer_flow, OFFLOADED)) + continue; + if (flow_flag_test(flow, USE_ACT_STATS)) { + f->use_act_stats = true; + break; + } + + counter = mlx5e_tc_get_counter(peer_flow); if (!counter) goto no_peer_counter; - mlx5_fc_query_cached(counter, &bytes2, &packets2, &lastuse2); + mlx5_fc_query_cached(counter, &bytes2, &packets2, + &lastuse2); bytes += bytes2; packets += packets2; @@ -4838,7 +4794,7 @@ int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv, } no_peer_counter: - mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); out: flow_stats_update(&f->stats, bytes, packets, 0, lastuse, FLOW_ACTION_HW_STATS_DELAYED); @@ -5301,6 +5257,8 @@ int mlx5e_tc_esw_init(struct mlx5_rep_uplink_priv *uplink_priv) goto err_action_counter; } + mlx5_esw_offloads_devcom_init(esw); + return 0; err_action_counter: @@ -5329,7 +5287,7 @@ void mlx5e_tc_esw_cleanup(struct mlx5_rep_uplink_priv *uplink_priv) priv = netdev_priv(rpriv->netdev); esw = priv->mdev->priv.eswitch; - mlx5e_tc_clean_fdb_peer_flows(esw); + mlx5_esw_offloads_devcom_cleanup(esw); mlx5e_tc_tun_cleanup(uplink_priv->encap); @@ -5354,9 +5312,14 @@ int mlx5e_tc_num_filters(struct mlx5e_priv *priv, unsigned long flags) void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw) { struct mlx5e_tc_flow *flow, *tmp; + int i; - list_for_each_entry_safe(flow, tmp, &esw->offloads.peer_flows, peer) - __mlx5e_tc_del_fdb_peer_flow(flow); + for (i = 0; i < MLX5_MAX_PORTS; i++) { + if (i == mlx5_get_dev_index(esw->dev)) + continue; + list_for_each_entry_safe(flow, tmp, &esw->offloads.peer_flows[i], peer[i]) + mlx5e_tc_del_fdb_peers_flow(flow); + } } void mlx5e_tc_reoffload_flows_work(struct work_struct *work) @@ -5643,22 +5606,43 @@ bool mlx5e_tc_update_skb_nic(struct mlx5_cqe64 *cqe, struct sk_buff *skb) 0, NULL); } +static struct mapping_ctx * +mlx5e_get_priv_obj_mapping(struct mlx5e_priv *priv) +{ + struct mlx5e_tc_table *tc; + struct mlx5_eswitch *esw; + struct mapping_ctx *ctx; + + if (is_mdev_switchdev_mode(priv->mdev)) { + esw = priv->mdev->priv.eswitch; + ctx = esw->offloads.reg_c0_obj_pool; + } else { + tc = mlx5e_fs_get_tc(priv->fs); + ctx = tc->mapping; + } + + return ctx; +} + int mlx5e_tc_action_miss_mapping_get(struct mlx5e_priv *priv, struct mlx5_flow_attr *attr, u64 act_miss_cookie, u32 *act_miss_mapping) { - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_mapped_obj mapped_obj = {}; + struct mlx5_eswitch *esw; struct mapping_ctx *ctx; int err; - ctx = esw->offloads.reg_c0_obj_pool; - + ctx = mlx5e_get_priv_obj_mapping(priv); mapped_obj.type = MLX5_MAPPED_OBJ_ACT_MISS; mapped_obj.act_miss_cookie = act_miss_cookie; err = mapping_add(ctx, &mapped_obj, act_miss_mapping); if (err) return err; + if (!is_mdev_switchdev_mode(priv->mdev)) + return 0; + + esw = priv->mdev->priv.eswitch; attr->act_id_restore_rule = esw_add_restore_rule(esw, *act_miss_mapping); if (IS_ERR(attr->act_id_restore_rule)) goto err_rule; @@ -5673,10 +5657,9 @@ err_rule: void mlx5e_tc_action_miss_mapping_put(struct mlx5e_priv *priv, struct mlx5_flow_attr *attr, u32 act_miss_mapping) { - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - struct mapping_ctx *ctx; + struct mapping_ctx *ctx = mlx5e_get_priv_obj_mapping(priv); - ctx = esw->offloads.reg_c0_obj_pool; - mlx5_del_flow_rules(attr->act_id_restore_rule); + if (is_mdev_switchdev_mode(priv->mdev)) + mlx5_del_flow_rules(attr->act_id_restore_rule); mapping_remove(ctx, act_miss_mapping); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index df5e780e8e6a..c7eb6b238c2b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -762,6 +762,17 @@ static void mlx5e_tx_wi_consume_fifo_skbs(struct mlx5e_txqsq *sq, struct mlx5e_t } } +void mlx5e_txqsq_wake(struct mlx5e_txqsq *sq) +{ + if (netif_tx_queue_stopped(sq->txq) && + mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, sq->stop_room) && + mlx5e_ptpsq_fifo_has_room(sq) && + !test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) { + netif_tx_wake_queue(sq->txq); + sq->stats->wake++; + } +} + bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) { struct mlx5e_sq_stats *stats; @@ -861,13 +872,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) netdev_tx_completed_queue(sq->txq, npkts, nbytes); - if (netif_tx_queue_stopped(sq->txq) && - mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, sq->stop_room) && - mlx5e_ptpsq_fifo_has_room(sq) && - !test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) { - netif_tx_wake_queue(sq->txq); - stats->wake++; - } + mlx5e_txqsq_wake(sq); return (i == MLX5E_TX_CQ_POLL_BUDGET); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index a50bfda18e96..a7d9b7cb4297 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -161,20 +161,22 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) } } + /* budget=0 means we may be in IRQ context, do as little as possible */ + if (unlikely(!budget)) + goto out; + busy |= mlx5e_poll_xdpsq_cq(&c->xdpsq.cq); if (c->xdp) busy |= mlx5e_poll_xdpsq_cq(&c->rq_xdpsq.cq); - if (likely(budget)) { /* budget=0 means: don't poll rx rings */ - if (xsk_open) - work_done = mlx5e_poll_rx_cq(&xskrq->cq, budget); + if (xsk_open) + work_done = mlx5e_poll_rx_cq(&xskrq->cq, budget); - if (likely(budget - work_done)) - work_done += mlx5e_poll_rx_cq(&rq->cq, budget - work_done); + if (likely(budget - work_done)) + work_done += mlx5e_poll_rx_cq(&rq->cq, budget - work_done); - busy |= work_done == budget; - } + busy |= work_done == budget; mlx5e_poll_ico_cq(&c->icosq.cq); if (mlx5e_poll_ico_cq(&c->async_icosq.cq)) @@ -205,7 +207,7 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) } ch_stats->aff_change++; aff_change = true; - if (budget && work_done == budget) + if (work_done == budget) work_done--; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 1c35d721a31d..3db4866d7880 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -824,7 +824,7 @@ static int comp_irqs_request_pci(struct mlx5_core_dev *dev) ncomp_eqs = table->num_comp_eqs; cpus = kcalloc(ncomp_eqs, sizeof(*cpus), GFP_KERNEL); if (!cpus) - ret = -ENOMEM; + return -ENOMEM; i = 0; rcu_read_lock(); @@ -1104,7 +1104,7 @@ void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev) struct mlx5_eq_table *table = dev->priv.eq_table; mutex_lock(&table->lock); /* sync with create/destroy_async_eq */ - mlx5_irq_table_destroy(dev); + mlx5_irq_table_free_irqs(dev); mutex_unlock(&table->lock); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c index 2e504c7461c6..24b1ca4e4ff8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c @@ -15,13 +15,27 @@ static void esw_acl_egress_ofld_fwd2vport_destroy(struct mlx5_vport *vport) vport->egress.offloads.fwd_rule = NULL; } -static void esw_acl_egress_ofld_bounce_rule_destroy(struct mlx5_vport *vport) +void esw_acl_egress_ofld_bounce_rule_destroy(struct mlx5_vport *vport, int rule_index) { - if (!vport->egress.offloads.bounce_rule) + struct mlx5_flow_handle *bounce_rule = + xa_load(&vport->egress.offloads.bounce_rules, rule_index); + + if (!bounce_rule) return; - mlx5_del_flow_rules(vport->egress.offloads.bounce_rule); - vport->egress.offloads.bounce_rule = NULL; + mlx5_del_flow_rules(bounce_rule); + xa_erase(&vport->egress.offloads.bounce_rules, rule_index); +} + +static void esw_acl_egress_ofld_bounce_rules_destroy(struct mlx5_vport *vport) +{ + struct mlx5_flow_handle *bounce_rule; + unsigned long i; + + xa_for_each(&vport->egress.offloads.bounce_rules, i, bounce_rule) { + mlx5_del_flow_rules(bounce_rule); + xa_erase(&vport->egress.offloads.bounce_rules, i); + } } static int esw_acl_egress_ofld_fwd2vport_create(struct mlx5_eswitch *esw, @@ -96,7 +110,7 @@ static void esw_acl_egress_ofld_rules_destroy(struct mlx5_vport *vport) { esw_acl_egress_vlan_destroy(vport); esw_acl_egress_ofld_fwd2vport_destroy(vport); - esw_acl_egress_ofld_bounce_rule_destroy(vport); + esw_acl_egress_ofld_bounce_rules_destroy(vport); } static int esw_acl_egress_ofld_groups_create(struct mlx5_eswitch *esw, @@ -194,6 +208,7 @@ int esw_acl_egress_ofld_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport vport->egress.acl = NULL; return err; } + vport->egress.type = VPORT_EGRESS_ACL_TYPE_DEFAULT; err = esw_acl_egress_ofld_groups_create(esw, vport); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c index 45b839116212..d599e50af346 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c @@ -35,7 +35,8 @@ esw_acl_table_create(struct mlx5_eswitch *esw, struct mlx5_vport *vport, int ns, } ft_attr.max_fte = size; - ft_attr.flags = MLX5_FLOW_TABLE_OTHER_VPORT; + if (vport_num || mlx5_core_is_ecpf(esw->dev)) + ft_attr.flags = MLX5_FLOW_TABLE_OTHER_VPORT; acl = mlx5_create_vport_flow_table(root_ns, &ft_attr, vport_num); if (IS_ERR(acl)) { err = PTR_ERR(acl); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h index c9f8469e9a47..536b04e83618 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ofld.h @@ -10,6 +10,7 @@ /* Eswitch acl egress external APIs */ int esw_acl_egress_ofld_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport); void esw_acl_egress_ofld_cleanup(struct mlx5_vport *vport); +void esw_acl_egress_ofld_bounce_rule_destroy(struct mlx5_vport *vport, int rule_index); int mlx5_esw_acl_egress_vport_bond(struct mlx5_eswitch *esw, u16 active_vport_num, u16 passive_vport_num); int mlx5_esw_acl_egress_vport_unbond(struct mlx5_eswitch *esw, u16 vport_num); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c index 1ba03e219111..bea7cc645461 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c @@ -647,22 +647,35 @@ mlx5_esw_bridge_ingress_flow_create(u16 vport_num, const unsigned char *addr, } static struct mlx5_flow_handle * -mlx5_esw_bridge_ingress_flow_peer_create(u16 vport_num, const unsigned char *addr, +mlx5_esw_bridge_ingress_flow_peer_create(u16 vport_num, u16 esw_owner_vhca_id, + const unsigned char *addr, struct mlx5_esw_bridge_vlan *vlan, u32 counter_id, struct mlx5_esw_bridge *bridge) { struct mlx5_devcom *devcom = bridge->br_offloads->esw->dev->priv.devcom; + struct mlx5_eswitch *tmp, *peer_esw = NULL; static struct mlx5_flow_handle *handle; - struct mlx5_eswitch *peer_esw; + int i; - peer_esw = mlx5_devcom_get_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); - if (!peer_esw) + if (!mlx5_devcom_for_each_peer_begin(devcom, MLX5_DEVCOM_ESW_OFFLOADS)) return ERR_PTR(-ENODEV); + mlx5_devcom_for_each_peer_entry(devcom, + MLX5_DEVCOM_ESW_OFFLOADS, + tmp, i) { + if (mlx5_esw_is_owner(tmp, vport_num, esw_owner_vhca_id)) { + peer_esw = tmp; + break; + } + } + if (!peer_esw) { + mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + return ERR_PTR(-ENODEV); + } + handle = mlx5_esw_bridge_ingress_flow_with_esw_create(vport_num, addr, vlan, counter_id, bridge, peer_esw); - - mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); return handle; } @@ -1369,8 +1382,9 @@ mlx5_esw_bridge_fdb_entry_init(struct net_device *dev, u16 vport_num, u16 esw_ow entry->ingress_counter = counter; handle = peer ? - mlx5_esw_bridge_ingress_flow_peer_create(vport_num, addr, vlan, - mlx5_fc_id(counter), bridge) : + mlx5_esw_bridge_ingress_flow_peer_create(vport_num, esw_owner_vhca_id, + addr, vlan, mlx5_fc_id(counter), + bridge) : mlx5_esw_bridge_ingress_flow_create(vport_num, addr, vlan, mlx5_fc_id(counter), bridge); if (IS_ERR(handle)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c index 2eae594a5e80..2455f8b93c1e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_mcast.c @@ -540,16 +540,29 @@ static struct mlx5_flow_handle * mlx5_esw_bridge_mcast_filter_flow_peer_create(struct mlx5_esw_bridge_port *port) { struct mlx5_devcom *devcom = port->bridge->br_offloads->esw->dev->priv.devcom; + struct mlx5_eswitch *tmp, *peer_esw = NULL; static struct mlx5_flow_handle *handle; - struct mlx5_eswitch *peer_esw; + int i; - peer_esw = mlx5_devcom_get_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); - if (!peer_esw) + if (!mlx5_devcom_for_each_peer_begin(devcom, MLX5_DEVCOM_ESW_OFFLOADS)) return ERR_PTR(-ENODEV); + mlx5_devcom_for_each_peer_entry(devcom, + MLX5_DEVCOM_ESW_OFFLOADS, + tmp, i) { + if (mlx5_esw_is_owner(tmp, port->vport_num, port->esw_owner_vhca_id)) { + peer_esw = tmp; + break; + } + } + if (!peer_esw) { + mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + return ERR_PTR(-ENODEV); + } + handle = mlx5_esw_bridge_mcast_flow_with_esw_create(port, peer_esw); - mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + mlx5_devcom_for_each_peer_end(devcom, MLX5_DEVCOM_ESW_OFFLOADS); return handle; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c index 084a910bb4e7..f370f67d9e33 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c @@ -65,6 +65,15 @@ static void mlx5_esw_dl_port_free(struct devlink_port *dl_port) kfree(dl_port); } +static const struct devlink_port_ops mlx5_esw_dl_port_ops = { + .port_fn_hw_addr_get = mlx5_devlink_port_fn_hw_addr_get, + .port_fn_hw_addr_set = mlx5_devlink_port_fn_hw_addr_set, + .port_fn_roce_get = mlx5_devlink_port_fn_roce_get, + .port_fn_roce_set = mlx5_devlink_port_fn_roce_set, + .port_fn_migratable_get = mlx5_devlink_port_fn_migratable_get, + .port_fn_migratable_set = mlx5_devlink_port_fn_migratable_set, +}; + int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_num) { struct mlx5_core_dev *dev = esw->dev; @@ -87,7 +96,8 @@ int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_ devlink = priv_to_devlink(dev); dl_port_index = mlx5_esw_vport_to_devlink_port_index(dev, vport_num); - err = devl_port_register(devlink, dl_port, dl_port_index); + err = devl_port_register_with_ops(devlink, dl_port, dl_port_index, + &mlx5_esw_dl_port_ops); if (err) goto reg_err; @@ -134,6 +144,20 @@ struct devlink_port *mlx5_esw_offloads_devlink_port(struct mlx5_eswitch *esw, u1 return IS_ERR(vport) ? ERR_CAST(vport) : vport->dl_port; } +static const struct devlink_port_ops mlx5_esw_dl_sf_port_ops = { +#ifdef CONFIG_MLX5_SF_MANAGER + .port_del = mlx5_devlink_sf_port_del, +#endif + .port_fn_hw_addr_get = mlx5_devlink_port_fn_hw_addr_get, + .port_fn_hw_addr_set = mlx5_devlink_port_fn_hw_addr_set, + .port_fn_roce_get = mlx5_devlink_port_fn_roce_get, + .port_fn_roce_set = mlx5_devlink_port_fn_roce_set, +#ifdef CONFIG_MLX5_SF_MANAGER + .port_fn_state_get = mlx5_devlink_sf_port_fn_state_get, + .port_fn_state_set = mlx5_devlink_sf_port_fn_state_set, +#endif +}; + int mlx5_esw_devlink_sf_port_register(struct mlx5_eswitch *esw, struct devlink_port *dl_port, u16 vport_num, u32 controller, u32 sfnum) { @@ -156,7 +180,8 @@ int mlx5_esw_devlink_sf_port_register(struct mlx5_eswitch *esw, struct devlink_p devlink_port_attrs_pci_sf_set(dl_port, controller, pfnum, sfnum, !!controller); devlink = priv_to_devlink(dev); dl_port_index = mlx5_esw_vport_to_devlink_port_index(dev, vport_num); - err = devl_port_register(devlink, dl_port, dl_port_index); + err = devl_port_register_with_ops(devlink, dl_port, dl_port_index, + &mlx5_esw_dl_sf_port_ops); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 901c53751b0a..ecd8864d5d11 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -92,7 +92,7 @@ mlx5_eswitch_get_vport(struct mlx5_eswitch *esw, u16 vport_num) { struct mlx5_vport *vport; - if (!esw || !MLX5_CAP_GEN(esw->dev, vport_group_manager)) + if (!esw) return ERR_PTR(-EPERM); vport = xa_load(&esw->vports, vport_num); @@ -113,7 +113,8 @@ static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport, opcode, MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT); MLX5_SET(modify_nic_vport_context_in, in, field_select.change_event, 1); MLX5_SET(modify_nic_vport_context_in, in, vport_number, vport); - MLX5_SET(modify_nic_vport_context_in, in, other_vport, 1); + if (vport || mlx5_core_is_ecpf(dev)) + MLX5_SET(modify_nic_vport_context_in, in, other_vport, 1); nic_vport_ctx = MLX5_ADDR_OF(modify_nic_vport_context_in, in, nic_vport_context); @@ -309,11 +310,12 @@ static int esw_add_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) fdb_add: /* SRIOV is enabled: Forward UC MAC to vport */ - if (esw->fdb_table.legacy.fdb && esw->mode == MLX5_ESWITCH_LEGACY) + if (esw->fdb_table.legacy.fdb && esw->mode == MLX5_ESWITCH_LEGACY) { vaddr->flow_rule = esw_fdb_set_vport_rule(esw, mac, vport); - esw_debug(esw->dev, "\tADDED UC MAC: vport[%d] %pM fr(%p)\n", - vport, mac, vaddr->flow_rule); + esw_debug(esw->dev, "\tADDED UC MAC: vport[%d] %pM fr(%p)\n", + vport, mac, vaddr->flow_rule); + } return 0; } @@ -710,6 +712,9 @@ void esw_vport_change_handle_locked(struct mlx5_vport *vport) struct mlx5_eswitch *esw = dev->priv.eswitch; u8 mac[ETH_ALEN]; + if (!MLX5_CAP_GEN(dev, log_max_l2_table)) + return; + mlx5_query_nic_vport_mac_address(dev, vport->vport, true, mac); esw_debug(dev, "vport[%d] Context Changed: perm mac: %pM\n", vport->vport, mac); @@ -946,7 +951,8 @@ void mlx5_esw_vport_disable(struct mlx5_eswitch *esw, u16 vport_num) vport->enabled = false; /* Disable events from this vport */ - arm_vport_context_events_cmd(esw->dev, vport->vport, 0); + if (MLX5_CAP_GEN(esw->dev, log_max_l2_table)) + arm_vport_context_events_cmd(esw->dev, vport->vport, 0); if (!mlx5_esw_is_manager_vport(esw, vport->vport) && MLX5_CAP_GEN(esw->dev, vhca_resource_manager)) @@ -1595,7 +1601,8 @@ static int mlx5_esw_vports_init(struct mlx5_eswitch *esw) idx++; } - if (mlx5_ecpf_vport_exists(dev)) { + if (mlx5_ecpf_vport_exists(dev) || + mlx5_core_is_ecpf_esw_manager(dev)) { err = mlx5_esw_vport_alloc(esw, idx, MLX5_VPORT_ECPF); if (err) goto err; @@ -1616,7 +1623,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) struct mlx5_eswitch *esw; int err; - if (!MLX5_VPORT_MANAGER(dev)) + if (!MLX5_VPORT_MANAGER(dev) && !MLX5_ESWITCH_MANAGER(dev)) return 0; esw = kzalloc(sizeof(*esw), GFP_KERNEL); @@ -1686,7 +1693,7 @@ abort: void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) { - if (!esw || !MLX5_VPORT_MANAGER(esw->dev)) + if (!esw) return; esw_info(esw->dev, "cleanup\n"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 1a042c981713..d3608f198e0a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -123,8 +123,14 @@ struct vport_ingress { } offloads; }; +enum vport_egress_acl_type { + VPORT_EGRESS_ACL_TYPE_DEFAULT, + VPORT_EGRESS_ACL_TYPE_SHARED_FDB, +}; + struct vport_egress { struct mlx5_flow_table *acl; + enum vport_egress_acl_type type; struct mlx5_flow_handle *allowed_vlan; struct mlx5_flow_group *vlan_grp; union { @@ -136,7 +142,7 @@ struct vport_egress { struct { struct mlx5_flow_group *fwd_grp; struct mlx5_flow_handle *fwd_rule; - struct mlx5_flow_handle *bounce_rule; + struct xarray bounce_rules; struct mlx5_flow_group *bounce_grp; } offloads; }; @@ -218,7 +224,7 @@ struct mlx5_eswitch_fdb { struct mlx5_flow_group *send_to_vport_grp; struct mlx5_flow_group *send_to_vport_meta_grp; struct mlx5_flow_group *peer_miss_grp; - struct mlx5_flow_handle **peer_miss_rules; + struct mlx5_flow_handle **peer_miss_rules[MLX5_MAX_PORTS]; struct mlx5_flow_group *miss_grp; struct mlx5_flow_handle **send_to_vport_meta_rules; struct mlx5_flow_handle *miss_rule_uni; @@ -249,7 +255,7 @@ struct mlx5_esw_offload { struct mlx5_flow_group *vport_rx_drop_group; struct mlx5_flow_handle *vport_rx_drop_rule; struct xarray vport_reps; - struct list_head peer_flows; + struct list_head peer_flows[MLX5_MAX_PORTS]; struct mutex peer_mutex; struct mutex encap_tbl_lock; /* protects encap_tbl */ DECLARE_HASHTABLE(encap_tbl, 8); @@ -337,11 +343,13 @@ struct mlx5_eswitch { int mode; u16 manager_vport; u16 first_host_vport; + u8 num_peers; struct mlx5_esw_functions esw_funcs; struct { u32 large_group_num; } params; struct blocking_notifier_head n_head; + bool paired[MLX5_MAX_PORTS]; }; void esw_offloads_disable(struct mlx5_eswitch *esw); @@ -369,6 +377,8 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs); void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf); void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw); void mlx5_eswitch_disable(struct mlx5_eswitch *esw); +void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw); +void mlx5_esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw); int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw, u16 vport, const u8 *mac); int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, @@ -503,12 +513,12 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, struct netlink_ext_ack *extack); int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, enum devlink_eswitch_encap_mode *encap); -int mlx5_devlink_port_function_hw_addr_get(struct devlink_port *port, - u8 *hw_addr, int *hw_addr_len, - struct netlink_ext_ack *extack); -int mlx5_devlink_port_function_hw_addr_set(struct devlink_port *port, - const u8 *hw_addr, int hw_addr_len, - struct netlink_ext_ack *extack); +int mlx5_devlink_port_fn_hw_addr_get(struct devlink_port *port, + u8 *hw_addr, int *hw_addr_len, + struct netlink_ext_ack *extack); +int mlx5_devlink_port_fn_hw_addr_set(struct devlink_port *port, + const u8 *hw_addr, int hw_addr_len, + struct netlink_ext_ack *extack); int mlx5_devlink_port_fn_roce_get(struct devlink_port *port, bool *is_enabled, struct netlink_ext_ack *extack); int mlx5_devlink_port_fn_roce_set(struct devlink_port *port, bool enable, @@ -575,6 +585,13 @@ mlx5_esw_is_manager_vport(const struct mlx5_eswitch *esw, u16 vport_num) return esw->manager_vport == vport_num; } +static inline bool mlx5_esw_is_owner(struct mlx5_eswitch *esw, u16 vport_num, + u16 esw_owner_vhca_id) +{ + return esw_owner_vhca_id == MLX5_CAP_GEN(esw->dev, vhca_id) || + (vport_num == MLX5_VPORT_UPLINK && mlx5_lag_is_master(esw->dev)); +} + static inline u16 mlx5_eswitch_first_host_vport_num(struct mlx5_core_dev *dev) { return mlx5_core_is_ecpf_esw_manager(dev) ? @@ -683,6 +700,14 @@ mlx5_esw_vporttbl_put(struct mlx5_eswitch *esw, struct mlx5_vport_tbl_attr *attr struct mlx5_flow_handle * esw_add_restore_rule(struct mlx5_eswitch *esw, u32 tag); +void mlx5_esw_set_flow_group_source_port(struct mlx5_eswitch *esw, + u32 *flow_group_in, + int match_params); + +void mlx5_esw_set_spec_source_port(struct mlx5_eswitch *esw, + u16 vport, + struct mlx5_flow_spec *spec); + int esw_offloads_load_rep(struct mlx5_eswitch *esw, u16 vport_num); void esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num); @@ -737,9 +762,9 @@ void esw_vport_change_handle_locked(struct mlx5_vport *vport); bool mlx5_esw_offloads_controller_valid(const struct mlx5_eswitch *esw, u32 controller); -int mlx5_eswitch_offloads_config_single_fdb(struct mlx5_eswitch *master_esw, - struct mlx5_eswitch *slave_esw); -void mlx5_eswitch_offloads_destroy_single_fdb(struct mlx5_eswitch *master_esw, +int mlx5_eswitch_offloads_single_fdb_add_one(struct mlx5_eswitch *master_esw, + struct mlx5_eswitch *slave_esw, int max_slaves); +void mlx5_eswitch_offloads_single_fdb_del_one(struct mlx5_eswitch *master_esw, struct mlx5_eswitch *slave_esw); int mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw); @@ -754,6 +779,13 @@ static inline int mlx5_eswitch_num_vfs(struct mlx5_eswitch *esw) return 0; } +static inline int mlx5_eswitch_get_npeers(struct mlx5_eswitch *esw) +{ + if (mlx5_esw_allowed(esw)) + return esw->num_peers; + return 0; +} + static inline struct mlx5_flow_table * mlx5_eswitch_get_slow_fdb(struct mlx5_eswitch *esw) { @@ -767,6 +799,8 @@ static inline void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) {} static inline int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs) { return 0; } static inline void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf) {} static inline void mlx5_eswitch_disable(struct mlx5_eswitch *esw) {} +static inline void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw) {} +static inline void mlx5_esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw) {} static inline bool mlx5_eswitch_is_funcs_handler(struct mlx5_core_dev *dev) { return false; } static inline int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, u16 vport, int link_state) { return 0; } @@ -789,16 +823,18 @@ mlx5_esw_vport_to_devlink_port_index(const struct mlx5_core_dev *dev, } static inline int -mlx5_eswitch_offloads_config_single_fdb(struct mlx5_eswitch *master_esw, - struct mlx5_eswitch *slave_esw) +mlx5_eswitch_offloads_single_fdb_add_one(struct mlx5_eswitch *master_esw, + struct mlx5_eswitch *slave_esw, int max_slaves) { return 0; } static inline void -mlx5_eswitch_offloads_destroy_single_fdb(struct mlx5_eswitch *master_esw, +mlx5_eswitch_offloads_single_fdb_del_one(struct mlx5_eswitch *master_esw, struct mlx5_eswitch *slave_esw) {} +static inline int mlx5_eswitch_get_npeers(struct mlx5_eswitch *esw) { return 0; } + static inline int mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 69215ffb9999..eafb098db6b0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -838,6 +838,7 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw, struct mlx5_flow_handle *flow_rule; struct mlx5_flow_spec *spec; void *misc; + u16 vport; spec = kvzalloc(sizeof(*spec), GFP_KERNEL); if (!spec) { @@ -847,20 +848,43 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw, misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); MLX5_SET(fte_match_set_misc, misc, source_sqn, sqn); - /* source vport is the esw manager */ - MLX5_SET(fte_match_set_misc, misc, source_port, from_esw->manager_vport); - if (MLX5_CAP_ESW(on_esw->dev, merged_eswitch)) - MLX5_SET(fte_match_set_misc, misc, source_eswitch_owner_vhca_id, - MLX5_CAP_GEN(from_esw->dev, vhca_id)); misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters); MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_sqn); - MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port); - if (MLX5_CAP_ESW(on_esw->dev, merged_eswitch)) - MLX5_SET_TO_ONES(fte_match_set_misc, misc, - source_eswitch_owner_vhca_id); spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS; + + /* source vport is the esw manager */ + vport = from_esw->manager_vport; + + if (mlx5_eswitch_vport_match_metadata_enabled(on_esw)) { + misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters_2); + MLX5_SET(fte_match_set_misc2, misc, metadata_reg_c_0, + mlx5_eswitch_get_vport_metadata_for_match(from_esw, vport)); + + misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters_2); + MLX5_SET(fte_match_set_misc2, misc, metadata_reg_c_0, + mlx5_eswitch_get_vport_metadata_mask()); + + spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2; + } else { + misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); + MLX5_SET(fte_match_set_misc, misc, source_port, vport); + + if (MLX5_CAP_ESW(on_esw->dev, merged_eswitch)) + MLX5_SET(fte_match_set_misc, misc, source_eswitch_owner_vhca_id, + MLX5_CAP_GEN(from_esw->dev, vhca_id)); + + misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters); + MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port); + + if (MLX5_CAP_ESW(on_esw->dev, merged_eswitch)) + MLX5_SET_TO_ONES(fte_match_set_misc, misc, + source_eswitch_owner_vhca_id); + + spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS; + } + dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT; dest.vport.num = rep->vport; dest.vport.vhca_id = MLX5_CAP_GEN(rep->esw->dev, vhca_id); @@ -1108,7 +1132,7 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, flows[vport->index] = flow; } - esw->fdb_table.offloads.peer_miss_rules = flows; + esw->fdb_table.offloads.peer_miss_rules[mlx5_get_dev_index(peer_dev)] = flows; kvfree(spec); return 0; @@ -1136,13 +1160,14 @@ alloc_flows_err: return err; } -static void esw_del_fdb_peer_miss_rules(struct mlx5_eswitch *esw) +static void esw_del_fdb_peer_miss_rules(struct mlx5_eswitch *esw, + struct mlx5_core_dev *peer_dev) { struct mlx5_flow_handle **flows; struct mlx5_vport *vport; unsigned long i; - flows = esw->fdb_table.offloads.peer_miss_rules; + flows = esw->fdb_table.offloads.peer_miss_rules[mlx5_get_dev_index(peer_dev)]; mlx5_esw_for_each_vf_vport(esw, i, vport, mlx5_core_max_vfs(esw->dev)) mlx5_del_flow_rules(flows[vport->index]); @@ -1269,8 +1294,10 @@ esw_add_restore_rule(struct mlx5_eswitch *esw, u32 tag) #define MAX_PF_SQ 256 #define MAX_SQ_NVPORTS 32 -static void esw_set_flow_group_source_port(struct mlx5_eswitch *esw, - u32 *flow_group_in) +void +mlx5_esw_set_flow_group_source_port(struct mlx5_eswitch *esw, + u32 *flow_group_in, + int match_params) { void *match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, @@ -1279,7 +1306,7 @@ static void esw_set_flow_group_source_port(struct mlx5_eswitch *esw, if (mlx5_eswitch_vport_match_metadata_enabled(esw)) { MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, - MLX5_MATCH_MISC_PARAMETERS_2); + MLX5_MATCH_MISC_PARAMETERS_2 | match_params); MLX5_SET(fte_match_param, match_criteria, misc_parameters_2.metadata_reg_c_0, @@ -1287,7 +1314,7 @@ static void esw_set_flow_group_source_port(struct mlx5_eswitch *esw, } else { MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, - MLX5_MATCH_MISC_PARAMETERS); + MLX5_MATCH_MISC_PARAMETERS | match_params); MLX5_SET_TO_ONES(fte_match_param, match_criteria, misc_parameters.source_port); @@ -1463,14 +1490,13 @@ esw_create_send_to_vport_group(struct mlx5_eswitch *esw, memset(flow_group_in, 0, inlen); - MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, - MLX5_MATCH_MISC_PARAMETERS); + mlx5_esw_set_flow_group_source_port(esw, flow_group_in, MLX5_MATCH_MISC_PARAMETERS); match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria); - MLX5_SET_TO_ONES(fte_match_param, match_criteria, misc_parameters.source_sqn); - MLX5_SET_TO_ONES(fte_match_param, match_criteria, misc_parameters.source_port); - if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) { + + if (!mlx5_eswitch_vport_match_metadata_enabled(esw) && + MLX5_CAP_ESW(esw->dev, merged_eswitch)) { MLX5_SET_TO_ONES(fte_match_param, match_criteria, misc_parameters.source_eswitch_owner_vhca_id); MLX5_SET(create_flow_group_in, flow_group_in, @@ -1548,6 +1574,7 @@ esw_create_peer_esw_miss_group(struct mlx5_eswitch *esw, u32 *flow_group_in, int *ix) { + int max_peer_ports = (esw->total_vports - 1) * (MLX5_MAX_PORTS - 1); int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); struct mlx5_flow_group *g; void *match_criteria; @@ -1558,7 +1585,7 @@ esw_create_peer_esw_miss_group(struct mlx5_eswitch *esw, memset(flow_group_in, 0, inlen); - esw_set_flow_group_source_port(esw, flow_group_in); + mlx5_esw_set_flow_group_source_port(esw, flow_group_in, 0); if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) { match_criteria = MLX5_ADDR_OF(create_flow_group_in, @@ -1574,8 +1601,8 @@ esw_create_peer_esw_miss_group(struct mlx5_eswitch *esw, MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, *ix); MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, - *ix + esw->total_vports - 1); - *ix += esw->total_vports; + *ix + max_peer_ports); + *ix += max_peer_ports + 1; g = mlx5_create_flow_group(fdb, flow_group_in); if (IS_ERR(g)) { @@ -1677,7 +1704,7 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw) * total vports of the peer (currently is also uses esw->total_vports). */ table_size = MLX5_MAX_PORTS * (esw->total_vports * MAX_SQ_NVPORTS + MAX_PF_SQ) + - esw->total_vports * 2 + MLX5_ESW_MISS_FLOWS; + esw->total_vports * MLX5_MAX_PORTS + MLX5_ESW_MISS_FLOWS; /* create the slow path fdb with encap set, so further table instances * can be created at run time while VFs are probed if the FW allows that. @@ -1845,7 +1872,7 @@ static int esw_create_vport_rx_group(struct mlx5_eswitch *esw) return -ENOMEM; /* create vport rx group */ - esw_set_flow_group_source_port(esw, flow_group_in); + mlx5_esw_set_flow_group_source_port(esw, flow_group_in, 0); MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0); MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, nvports - 1); @@ -1915,21 +1942,13 @@ static void esw_destroy_vport_rx_drop_group(struct mlx5_eswitch *esw) mlx5_destroy_flow_group(esw->offloads.vport_rx_drop_group); } -struct mlx5_flow_handle * -mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, u16 vport, - struct mlx5_flow_destination *dest) +void +mlx5_esw_set_spec_source_port(struct mlx5_eswitch *esw, + u16 vport, + struct mlx5_flow_spec *spec) { - struct mlx5_flow_act flow_act = {0}; - struct mlx5_flow_handle *flow_rule; - struct mlx5_flow_spec *spec; void *misc; - spec = kvzalloc(sizeof(*spec), GFP_KERNEL); - if (!spec) { - flow_rule = ERR_PTR(-ENOMEM); - goto out; - } - if (mlx5_eswitch_vport_match_metadata_enabled(esw)) { misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters_2); MLX5_SET(fte_match_set_misc2, misc, metadata_reg_c_0, @@ -1949,6 +1968,23 @@ mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, u16 vport, spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS; } +} + +struct mlx5_flow_handle * +mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, u16 vport, + struct mlx5_flow_destination *dest) +{ + struct mlx5_flow_act flow_act = {0}; + struct mlx5_flow_handle *flow_rule; + struct mlx5_flow_spec *spec; + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) { + flow_rule = ERR_PTR(-ENOMEM); + goto out; + } + + mlx5_esw_set_spec_source_port(esw, vport, spec); flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; flow_rule = mlx5_add_flow_rules(esw->offloads.ft_offloads, spec, @@ -2142,6 +2178,7 @@ static int esw_offloads_start(struct mlx5_eswitch *esw, "Failed setting eswitch to offloads"); esw->mode = MLX5_ESWITCH_LEGACY; mlx5_rescan_drivers(esw->dev); + return err; } if (esw->offloads.inline_mode == MLX5_INLINE_MODE_NONE) { if (mlx5_eswitch_inline_mode_get(esw, @@ -2151,7 +2188,7 @@ static int esw_offloads_start(struct mlx5_eswitch *esw, "Inline mode is different between vports"); } } - return err; + return 0; } static void mlx5_esw_offloads_rep_mark_set(struct mlx5_eswitch *esw, @@ -2476,6 +2513,7 @@ static int __esw_set_master_egress_rule(struct mlx5_core_dev *master, struct mlx5_vport *vport, struct mlx5_flow_table *acl) { + u16 slave_index = MLX5_CAP_GEN(slave, vhca_id); struct mlx5_flow_handle *flow_rule = NULL; struct mlx5_flow_destination dest = {}; struct mlx5_flow_act flow_act = {}; @@ -2491,8 +2529,7 @@ static int __esw_set_master_egress_rule(struct mlx5_core_dev *master, misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_UPLINK); - MLX5_SET(fte_match_set_misc, misc, source_eswitch_owner_vhca_id, - MLX5_CAP_GEN(slave, vhca_id)); + MLX5_SET(fte_match_set_misc, misc, source_eswitch_owner_vhca_id, slave_index); misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters); MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port); @@ -2507,44 +2544,35 @@ static int __esw_set_master_egress_rule(struct mlx5_core_dev *master, flow_rule = mlx5_add_flow_rules(acl, spec, &flow_act, &dest, 1); - if (IS_ERR(flow_rule)) + if (IS_ERR(flow_rule)) { err = PTR_ERR(flow_rule); - else - vport->egress.offloads.bounce_rule = flow_rule; + } else { + err = xa_insert(&vport->egress.offloads.bounce_rules, + slave_index, flow_rule, GFP_KERNEL); + if (err) + mlx5_del_flow_rules(flow_rule); + } kvfree(spec); return err; } -static int esw_set_master_egress_rule(struct mlx5_core_dev *master, - struct mlx5_core_dev *slave) +static int esw_master_egress_create_resources(struct mlx5_flow_namespace *egress_ns, + struct mlx5_vport *vport, size_t count) { int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); - struct mlx5_eswitch *esw = master->priv.eswitch; struct mlx5_flow_table_attr ft_attr = { - .max_fte = 1, .prio = 0, .level = 0, + .max_fte = count, .prio = 0, .level = 0, .flags = MLX5_FLOW_TABLE_OTHER_VPORT, }; - struct mlx5_flow_namespace *egress_ns; struct mlx5_flow_table *acl; struct mlx5_flow_group *g; - struct mlx5_vport *vport; void *match_criteria; u32 *flow_group_in; int err; - vport = mlx5_eswitch_get_vport(esw, esw->manager_vport); - if (IS_ERR(vport)) - return PTR_ERR(vport); - - egress_ns = mlx5_get_flow_vport_acl_namespace(master, - MLX5_FLOW_NAMESPACE_ESW_EGRESS, - vport->index); - if (!egress_ns) - return -EINVAL; - if (vport->egress.acl) - return -EINVAL; + return 0; flow_group_in = kvzalloc(inlen, GFP_KERNEL); if (!flow_group_in) @@ -2568,7 +2596,7 @@ static int esw_set_master_egress_rule(struct mlx5_core_dev *master, MLX5_SET(create_flow_group_in, flow_group_in, source_eswitch_owner_vhca_id_valid, 1); MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0); - MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 0); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, count); g = mlx5_create_flow_group(acl, flow_group_in); if (IS_ERR(g)) { @@ -2576,19 +2604,15 @@ static int esw_set_master_egress_rule(struct mlx5_core_dev *master, goto err_group; } - err = __esw_set_master_egress_rule(master, slave, vport, acl); - if (err) - goto err_rule; - vport->egress.acl = acl; vport->egress.offloads.bounce_grp = g; + vport->egress.type = VPORT_EGRESS_ACL_TYPE_SHARED_FDB; + xa_init_flags(&vport->egress.offloads.bounce_rules, XA_FLAGS_ALLOC); kvfree(flow_group_in); return 0; -err_rule: - mlx5_destroy_flow_group(g); err_group: mlx5_destroy_flow_table(acl); out: @@ -2596,18 +2620,70 @@ out: return err; } -static void esw_unset_master_egress_rule(struct mlx5_core_dev *dev) +static void esw_master_egress_destroy_resources(struct mlx5_vport *vport) +{ + mlx5_destroy_flow_group(vport->egress.offloads.bounce_grp); + mlx5_destroy_flow_table(vport->egress.acl); +} + +static int esw_set_master_egress_rule(struct mlx5_core_dev *master, + struct mlx5_core_dev *slave, size_t count) +{ + struct mlx5_eswitch *esw = master->priv.eswitch; + u16 slave_index = MLX5_CAP_GEN(slave, vhca_id); + struct mlx5_flow_namespace *egress_ns; + struct mlx5_vport *vport; + int err; + + vport = mlx5_eswitch_get_vport(esw, esw->manager_vport); + if (IS_ERR(vport)) + return PTR_ERR(vport); + + egress_ns = mlx5_get_flow_vport_acl_namespace(master, + MLX5_FLOW_NAMESPACE_ESW_EGRESS, + vport->index); + if (!egress_ns) + return -EINVAL; + + if (vport->egress.acl && vport->egress.type != VPORT_EGRESS_ACL_TYPE_SHARED_FDB) + return 0; + + err = esw_master_egress_create_resources(egress_ns, vport, count); + if (err) + return err; + + if (xa_load(&vport->egress.offloads.bounce_rules, slave_index)) + return -EINVAL; + + err = __esw_set_master_egress_rule(master, slave, vport, vport->egress.acl); + if (err) + goto err_rule; + + return 0; + +err_rule: + esw_master_egress_destroy_resources(vport); + return err; +} + +static void esw_unset_master_egress_rule(struct mlx5_core_dev *dev, + struct mlx5_core_dev *slave_dev) { struct mlx5_vport *vport; vport = mlx5_eswitch_get_vport(dev->priv.eswitch, dev->priv.eswitch->manager_vport); - esw_acl_egress_ofld_cleanup(vport); + esw_acl_egress_ofld_bounce_rule_destroy(vport, MLX5_CAP_GEN(slave_dev, vhca_id)); + + if (xa_empty(&vport->egress.offloads.bounce_rules)) { + esw_acl_egress_ofld_cleanup(vport); + xa_destroy(&vport->egress.offloads.bounce_rules); + } } -int mlx5_eswitch_offloads_config_single_fdb(struct mlx5_eswitch *master_esw, - struct mlx5_eswitch *slave_esw) +int mlx5_eswitch_offloads_single_fdb_add_one(struct mlx5_eswitch *master_esw, + struct mlx5_eswitch *slave_esw, int max_slaves) { int err; @@ -2617,7 +2693,7 @@ int mlx5_eswitch_offloads_config_single_fdb(struct mlx5_eswitch *master_esw, return err; err = esw_set_master_egress_rule(master_esw->dev, - slave_esw->dev); + slave_esw->dev, max_slaves); if (err) goto err_acl; @@ -2625,21 +2701,21 @@ int mlx5_eswitch_offloads_config_single_fdb(struct mlx5_eswitch *master_esw, err_acl: esw_set_slave_root_fdb(NULL, slave_esw->dev); - return err; } -void mlx5_eswitch_offloads_destroy_single_fdb(struct mlx5_eswitch *master_esw, +void mlx5_eswitch_offloads_single_fdb_del_one(struct mlx5_eswitch *master_esw, struct mlx5_eswitch *slave_esw) { - esw_unset_master_egress_rule(master_esw->dev); esw_set_slave_root_fdb(NULL, slave_esw->dev); + esw_unset_master_egress_rule(master_esw->dev, slave_esw->dev); } #define ESW_OFFLOADS_DEVCOM_PAIR (0) #define ESW_OFFLOADS_DEVCOM_UNPAIR (1) -static void mlx5_esw_offloads_rep_event_unpair(struct mlx5_eswitch *esw) +static void mlx5_esw_offloads_rep_event_unpair(struct mlx5_eswitch *esw, + struct mlx5_eswitch *peer_esw) { const struct mlx5_eswitch_rep_ops *ops; struct mlx5_eswitch_rep *rep; @@ -2652,18 +2728,19 @@ static void mlx5_esw_offloads_rep_event_unpair(struct mlx5_eswitch *esw) ops = esw->offloads.rep_ops[rep_type]; if (atomic_read(&rep->rep_data[rep_type].state) == REP_LOADED && ops->event) - ops->event(esw, rep, MLX5_SWITCHDEV_EVENT_UNPAIR, NULL); + ops->event(esw, rep, MLX5_SWITCHDEV_EVENT_UNPAIR, peer_esw); } } } -static void mlx5_esw_offloads_unpair(struct mlx5_eswitch *esw) +static void mlx5_esw_offloads_unpair(struct mlx5_eswitch *esw, + struct mlx5_eswitch *peer_esw) { #if IS_ENABLED(CONFIG_MLX5_CLS_ACT) mlx5e_tc_clean_fdb_peer_flows(esw); #endif - mlx5_esw_offloads_rep_event_unpair(esw); - esw_del_fdb_peer_miss_rules(esw); + mlx5_esw_offloads_rep_event_unpair(esw, peer_esw); + esw_del_fdb_peer_miss_rules(esw, peer_esw->dev); } static int mlx5_esw_offloads_pair(struct mlx5_eswitch *esw, @@ -2694,7 +2771,7 @@ static int mlx5_esw_offloads_pair(struct mlx5_eswitch *esw, return 0; err_out: - mlx5_esw_offloads_unpair(esw); + mlx5_esw_offloads_unpair(esw, peer_esw); return err; } @@ -2702,7 +2779,9 @@ static int mlx5_esw_offloads_set_ns_peer(struct mlx5_eswitch *esw, struct mlx5_eswitch *peer_esw, bool pair) { + u8 peer_idx = mlx5_get_dev_index(peer_esw->dev); struct mlx5_flow_root_namespace *peer_ns; + u8 idx = mlx5_get_dev_index(esw->dev); struct mlx5_flow_root_namespace *ns; int err; @@ -2710,18 +2789,18 @@ static int mlx5_esw_offloads_set_ns_peer(struct mlx5_eswitch *esw, ns = esw->dev->priv.steering->fdb_root_ns; if (pair) { - err = mlx5_flow_namespace_set_peer(ns, peer_ns); + err = mlx5_flow_namespace_set_peer(ns, peer_ns, peer_idx); if (err) return err; - err = mlx5_flow_namespace_set_peer(peer_ns, ns); + err = mlx5_flow_namespace_set_peer(peer_ns, ns, idx); if (err) { - mlx5_flow_namespace_set_peer(ns, NULL); + mlx5_flow_namespace_set_peer(ns, NULL, peer_idx); return err; } } else { - mlx5_flow_namespace_set_peer(ns, NULL); - mlx5_flow_namespace_set_peer(peer_ns, NULL); + mlx5_flow_namespace_set_peer(ns, NULL, peer_idx); + mlx5_flow_namespace_set_peer(peer_ns, NULL, idx); } return 0; @@ -2742,6 +2821,9 @@ static int mlx5_esw_offloads_devcom_event(int event, mlx5_eswitch_vport_match_metadata_enabled(peer_esw)) break; + if (esw->paired[mlx5_get_dev_index(peer_esw->dev)]) + break; + err = mlx5_esw_offloads_set_ns_peer(esw, peer_esw, true); if (err) goto err_out; @@ -2753,16 +2835,25 @@ static int mlx5_esw_offloads_devcom_event(int event, if (err) goto err_pair; - mlx5_devcom_set_paired(devcom, MLX5_DEVCOM_ESW_OFFLOADS, true); + esw->paired[mlx5_get_dev_index(peer_esw->dev)] = true; + peer_esw->paired[mlx5_get_dev_index(esw->dev)] = true; + esw->num_peers++; + peer_esw->num_peers++; + mlx5_devcom_comp_set_ready(devcom, MLX5_DEVCOM_ESW_OFFLOADS, true); break; case ESW_OFFLOADS_DEVCOM_UNPAIR: - if (!mlx5_devcom_is_paired(devcom, MLX5_DEVCOM_ESW_OFFLOADS)) + if (!esw->paired[mlx5_get_dev_index(peer_esw->dev)]) break; - mlx5_devcom_set_paired(devcom, MLX5_DEVCOM_ESW_OFFLOADS, false); - mlx5_esw_offloads_unpair(peer_esw); - mlx5_esw_offloads_unpair(esw); + peer_esw->num_peers--; + esw->num_peers--; + if (!esw->num_peers && !peer_esw->num_peers) + mlx5_devcom_comp_set_ready(devcom, MLX5_DEVCOM_ESW_OFFLOADS, false); + esw->paired[mlx5_get_dev_index(peer_esw->dev)] = false; + peer_esw->paired[mlx5_get_dev_index(esw->dev)] = false; + mlx5_esw_offloads_unpair(peer_esw, esw); + mlx5_esw_offloads_unpair(esw, peer_esw); mlx5_esw_offloads_set_ns_peer(esw, peer_esw, false); break; } @@ -2770,7 +2861,7 @@ static int mlx5_esw_offloads_devcom_event(int event, return 0; err_pair: - mlx5_esw_offloads_unpair(esw); + mlx5_esw_offloads_unpair(esw, peer_esw); err_peer: mlx5_esw_offloads_set_ns_peer(esw, peer_esw, false); err_out: @@ -2779,11 +2870,13 @@ err_out: return err; } -static void esw_offloads_devcom_init(struct mlx5_eswitch *esw) +void mlx5_esw_offloads_devcom_init(struct mlx5_eswitch *esw) { struct mlx5_devcom *devcom = esw->dev->priv.devcom; + int i; - INIT_LIST_HEAD(&esw->offloads.peer_flows); + for (i = 0; i < MLX5_MAX_PORTS; i++) + INIT_LIST_HEAD(&esw->offloads.peer_flows[i]); mutex_init(&esw->offloads.peer_mutex); if (!MLX5_CAP_ESW(esw->dev, merged_eswitch)) @@ -2797,12 +2890,14 @@ static void esw_offloads_devcom_init(struct mlx5_eswitch *esw) mlx5_esw_offloads_devcom_event, esw); + esw->num_peers = 0; mlx5_devcom_send_event(devcom, MLX5_DEVCOM_ESW_OFFLOADS, - ESW_OFFLOADS_DEVCOM_PAIR, esw); + ESW_OFFLOADS_DEVCOM_PAIR, + ESW_OFFLOADS_DEVCOM_UNPAIR, esw); } -static void esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw) +void mlx5_esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw) { struct mlx5_devcom *devcom = esw->dev->priv.devcom; @@ -2813,6 +2908,7 @@ static void esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw) return; mlx5_devcom_send_event(devcom, MLX5_DEVCOM_ESW_OFFLOADS, + ESW_OFFLOADS_DEVCOM_UNPAIR, ESW_OFFLOADS_DEVCOM_UNPAIR, esw); mlx5_devcom_unregister_component(devcom, MLX5_DEVCOM_ESW_OFFLOADS); @@ -2827,9 +2923,6 @@ bool mlx5_esw_vport_match_metadata_supported(const struct mlx5_eswitch *esw) MLX5_FDB_TO_VPORT_REG_C_0)) return false; - if (!MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source)) - return false; - return true; } @@ -3250,8 +3343,6 @@ int esw_offloads_enable(struct mlx5_eswitch *esw) if (err) goto err_vports; - esw_offloads_devcom_init(esw); - return 0; err_vports: @@ -3280,7 +3371,7 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw, /* If changing from switchdev to legacy mode without sriov enabled, * no need to create legacy fdb. */ - if (!mlx5_sriov_is_enabled(esw->dev)) + if (!mlx5_core_is_pf(esw->dev) || !mlx5_sriov_is_enabled(esw->dev)) return 0; err = mlx5_eswitch_enable_locked(esw, MLX5_ESWITCH_IGNORE_NUM_VFS); @@ -3292,7 +3383,6 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw, void esw_offloads_disable(struct mlx5_eswitch *esw) { - esw_offloads_devcom_cleanup(esw); mlx5_eswitch_disable_pf_vf_vports(esw); esw_offloads_unload_rep(esw, MLX5_VPORT_UPLINK); esw_set_passing_vport_metadata(esw, false); @@ -3922,9 +4012,9 @@ is_port_function_supported(struct mlx5_eswitch *esw, u16 vport_num) mlx5_esw_is_sf_vport(esw, vport_num); } -int mlx5_devlink_port_function_hw_addr_get(struct devlink_port *port, - u8 *hw_addr, int *hw_addr_len, - struct netlink_ext_ack *extack) +int mlx5_devlink_port_fn_hw_addr_get(struct devlink_port *port, + u8 *hw_addr, int *hw_addr_len, + struct netlink_ext_ack *extack) { struct mlx5_eswitch *esw; struct mlx5_vport *vport; @@ -3951,9 +4041,9 @@ int mlx5_devlink_port_function_hw_addr_get(struct devlink_port *port, return 0; } -int mlx5_devlink_port_function_hw_addr_set(struct devlink_port *port, - const u8 *hw_addr, int hw_addr_len, - struct netlink_ext_ack *extack) +int mlx5_devlink_port_fn_hw_addr_set(struct devlink_port *port, + const u8 *hw_addr, int hw_addr_len, + struct netlink_ext_ack *extack) { struct mlx5_eswitch *esw; u16 vport_num; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 144e59480686..8a10ed4d8cbb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -139,7 +139,8 @@ static void mlx5_cmd_stub_modify_header_dealloc(struct mlx5_flow_root_namespace } static int mlx5_cmd_stub_set_peer(struct mlx5_flow_root_namespace *ns, - struct mlx5_flow_root_namespace *peer_ns) + struct mlx5_flow_root_namespace *peer_ns, + u8 peer_idx) { return 0; } @@ -243,16 +244,22 @@ static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns, ft->type == FS_FT_FDB && mlx5_lag_is_shared_fdb(dev) && mlx5_lag_is_master(dev)) { - err = mlx5_cmd_set_slave_root_fdb(dev, - mlx5_lag_get_peer_mdev(dev), - !disconnect, (!disconnect) ? - ft->id : 0); - if (err && !disconnect) { - MLX5_SET(set_flow_table_root_in, in, op_mod, 0); - MLX5_SET(set_flow_table_root_in, in, table_id, - ns->root_ft->id); - mlx5_cmd_exec_in(dev, set_flow_table_root, in); + struct mlx5_core_dev *peer_dev; + int i; + + mlx5_lag_for_each_peer_mdev(dev, peer_dev, i) { + err = mlx5_cmd_set_slave_root_fdb(dev, peer_dev, !disconnect, + (!disconnect) ? ft->id : 0); + if (err && !disconnect) { + MLX5_SET(set_flow_table_root_in, in, op_mod, 0); + MLX5_SET(set_flow_table_root_in, in, table_id, + ns->root_ft->id); + mlx5_cmd_exec_in(dev, set_flow_table_root, in); + } + if (err) + break; } + } return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index 8ef4254b9ea1..b6b9a5a20591 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -93,7 +93,8 @@ struct mlx5_flow_cmds { struct mlx5_modify_hdr *modify_hdr); int (*set_peer)(struct mlx5_flow_root_namespace *ns, - struct mlx5_flow_root_namespace *peer_ns); + struct mlx5_flow_root_namespace *peer_ns, + u8 peer_idx); int (*create_ns)(struct mlx5_flow_root_namespace *ns); int (*destroy_ns)(struct mlx5_flow_root_namespace *ns); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 19da02c41616..4ef04aa28771 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -3620,7 +3620,8 @@ void mlx5_destroy_match_definer(struct mlx5_core_dev *dev, } int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns, - struct mlx5_flow_root_namespace *peer_ns) + struct mlx5_flow_root_namespace *peer_ns, + u8 peer_idx) { if (peer_ns && ns->mode != peer_ns->mode) { mlx5_core_err(ns->dev, @@ -3628,7 +3629,7 @@ int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns, return -EINVAL; } - return ns->cmds->set_peer(ns, peer_ns); + return ns->cmds->set_peer(ns, peer_ns, peer_idx); } /* This function should be called only at init stage of the namespace. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index f137a0611b77..200ec946409c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -295,7 +295,8 @@ void mlx5_fc_update_sampling_interval(struct mlx5_core_dev *dev, const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void); int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns, - struct mlx5_flow_root_namespace *peer_ns); + struct mlx5_flow_root_namespace *peer_ns, + u8 peer_idx); int mlx5_flow_namespace_set_mode(struct mlx5_flow_namespace *ns, enum mlx5_flow_steering_mode mode); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index 7bb7be01225a..fb2035a5ec99 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -196,14 +196,11 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) return err; } - if (MLX5_CAP_GEN(dev, vport_group_manager) && - MLX5_ESWITCH_MANAGER(dev)) { + if (MLX5_ESWITCH_MANAGER(dev)) { err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH_FLOW_TABLE); if (err) return err; - } - if (MLX5_ESWITCH_MANAGER(dev)) { err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index 5d331b940f4d..ffd7e17b8ebe 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -512,8 +512,11 @@ static void mlx5_lag_set_port_sel_mode_offloads(struct mlx5_lag *ldev, return; if (MLX5_CAP_PORT_SELECTION(dev0->dev, port_select_flow_table) && - tracker->tx_type == NETDEV_LAG_TX_TYPE_HASH) + tracker->tx_type == NETDEV_LAG_TX_TYPE_HASH) { + if (ldev->ports > 2) + ldev->buckets = MLX5_LAG_MAX_HASH_BUCKETS; set_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, flags); + } } static int mlx5_lag_set_flags(struct mlx5_lag *ldev, enum mlx5_lag_mode mode, @@ -550,6 +553,29 @@ char *mlx5_get_str_port_sel_mode(enum mlx5_lag_mode mode, unsigned long flags) } } +static int mlx5_lag_create_single_fdb(struct mlx5_lag *ldev) +{ + struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; + struct mlx5_eswitch *master_esw = dev0->priv.eswitch; + int err; + int i; + + for (i = MLX5_LAG_P1 + 1; i < ldev->ports; i++) { + struct mlx5_eswitch *slave_esw = ldev->pf[i].dev->priv.eswitch; + + err = mlx5_eswitch_offloads_single_fdb_add_one(master_esw, + slave_esw, ldev->ports); + if (err) + goto err; + } + return 0; +err: + for (; i > MLX5_LAG_P1; i--) + mlx5_eswitch_offloads_single_fdb_del_one(master_esw, + ldev->pf[i].dev->priv.eswitch); + return err; +} + static int mlx5_create_lag(struct mlx5_lag *ldev, struct lag_tracker *tracker, enum mlx5_lag_mode mode, @@ -557,7 +583,6 @@ static int mlx5_create_lag(struct mlx5_lag *ldev, { bool shared_fdb = test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &flags); struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; - struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev; u32 in[MLX5_ST_SZ_DW(destroy_lag_in)] = {}; int err; @@ -575,8 +600,7 @@ static int mlx5_create_lag(struct mlx5_lag *ldev, } if (shared_fdb) { - err = mlx5_eswitch_offloads_config_single_fdb(dev0->priv.eswitch, - dev1->priv.eswitch); + err = mlx5_lag_create_single_fdb(ldev); if (err) mlx5_core_err(dev0, "Can't enable single FDB mode\n"); else @@ -647,19 +671,21 @@ int mlx5_activate_lag(struct mlx5_lag *ldev, int mlx5_deactivate_lag(struct mlx5_lag *ldev) { struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; - struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev; + struct mlx5_eswitch *master_esw = dev0->priv.eswitch; u32 in[MLX5_ST_SZ_DW(destroy_lag_in)] = {}; bool roce_lag = __mlx5_lag_is_roce(ldev); unsigned long flags = ldev->mode_flags; int err; + int i; ldev->mode = MLX5_LAG_MODE_NONE; ldev->mode_flags = 0; mlx5_lag_mp_reset(ldev); if (test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &flags)) { - mlx5_eswitch_offloads_destroy_single_fdb(dev0->priv.eswitch, - dev1->priv.eswitch); + for (i = MLX5_LAG_P1 + 1; i < ldev->ports; i++) + mlx5_eswitch_offloads_single_fdb_del_one(master_esw, + ldev->pf[i].dev->priv.eswitch); clear_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &flags); } @@ -685,7 +711,7 @@ int mlx5_deactivate_lag(struct mlx5_lag *ldev) return 0; } -#define MLX5_LAG_OFFLOADS_SUPPORTED_PORTS 2 +#define MLX5_LAG_OFFLOADS_SUPPORTED_PORTS 4 bool mlx5_lag_check_prereq(struct mlx5_lag *ldev) { #ifdef CONFIG_MLX5_ESWITCH @@ -711,7 +737,7 @@ bool mlx5_lag_check_prereq(struct mlx5_lag *ldev) if (mlx5_eswitch_mode(ldev->pf[i].dev) != mode) return false; - if (mode == MLX5_ESWITCH_OFFLOADS && ldev->ports != MLX5_LAG_OFFLOADS_SUPPORTED_PORTS) + if (mode == MLX5_ESWITCH_OFFLOADS && ldev->ports > MLX5_LAG_OFFLOADS_SUPPORTED_PORTS) return false; #else for (i = 0; i < ldev->ports; i++) @@ -759,7 +785,6 @@ void mlx5_disable_lag(struct mlx5_lag *ldev) { bool shared_fdb = test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &ldev->mode_flags); struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; - struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev; bool roce_lag; int err; int i; @@ -784,28 +809,35 @@ void mlx5_disable_lag(struct mlx5_lag *ldev) if (shared_fdb || roce_lag) mlx5_lag_add_devices(ldev); - if (shared_fdb) { - if (!(dev0->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)) - mlx5_eswitch_reload_reps(dev0->priv.eswitch); - if (!(dev1->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)) - mlx5_eswitch_reload_reps(dev1->priv.eswitch); - } + if (shared_fdb) + for (i = 0; i < ldev->ports; i++) + if (!(ldev->pf[i].dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)) + mlx5_eswitch_reload_reps(ldev->pf[i].dev->priv.eswitch); } -bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev) +static bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev) { - struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; - struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev; - - if (is_mdev_switchdev_mode(dev0) && - is_mdev_switchdev_mode(dev1) && - mlx5_eswitch_vport_match_metadata_enabled(dev0->priv.eswitch) && - mlx5_eswitch_vport_match_metadata_enabled(dev1->priv.eswitch) && - mlx5_devcom_is_paired(dev0->priv.devcom, - MLX5_DEVCOM_ESW_OFFLOADS) && - MLX5_CAP_GEN(dev1, lag_native_fdb_selection) && - MLX5_CAP_ESW(dev1, root_ft_on_other_esw) && - MLX5_CAP_ESW(dev0, esw_shared_ingress_acl)) + struct mlx5_core_dev *dev; + int i; + + for (i = MLX5_LAG_P1 + 1; i < ldev->ports; i++) { + dev = ldev->pf[i].dev; + if (is_mdev_switchdev_mode(dev) && + mlx5_eswitch_vport_match_metadata_enabled(dev->priv.eswitch) && + MLX5_CAP_GEN(dev, lag_native_fdb_selection) && + MLX5_CAP_ESW(dev, root_ft_on_other_esw) && + mlx5_eswitch_get_npeers(dev->priv.eswitch) == + MLX5_CAP_GEN(dev, num_lag_ports) - 1) + continue; + return false; + } + + dev = ldev->pf[MLX5_LAG_P1].dev; + if (is_mdev_switchdev_mode(dev) && + mlx5_eswitch_vport_match_metadata_enabled(dev->priv.eswitch) && + mlx5_devcom_comp_is_ready(dev->priv.devcom, MLX5_DEVCOM_ESW_OFFLOADS) && + MLX5_CAP_ESW(dev, esw_shared_ingress_acl) && + mlx5_eswitch_get_npeers(dev->priv.eswitch) == MLX5_CAP_GEN(dev, num_lag_ports) - 1) return true; return false; @@ -842,7 +874,6 @@ static bool mlx5_lag_should_disable_lag(struct mlx5_lag *ldev, bool do_bond) static void mlx5_do_bond(struct mlx5_lag *ldev) { struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; - struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev; struct lag_tracker tracker = { }; bool do_bond, roce_lag; int err; @@ -883,20 +914,24 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) for (i = 1; i < ldev->ports; i++) mlx5_nic_vport_enable_roce(ldev->pf[i].dev); } else if (shared_fdb) { + int i; + dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; mlx5_rescan_drivers_locked(dev0); - err = mlx5_eswitch_reload_reps(dev0->priv.eswitch); - if (!err) - err = mlx5_eswitch_reload_reps(dev1->priv.eswitch); + for (i = 0; i < ldev->ports; i++) { + err = mlx5_eswitch_reload_reps(ldev->pf[i].dev->priv.eswitch); + if (err) + break; + } if (err) { dev0->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; mlx5_rescan_drivers_locked(dev0); mlx5_deactivate_lag(ldev); mlx5_lag_add_devices(ldev); - mlx5_eswitch_reload_reps(dev0->priv.eswitch); - mlx5_eswitch_reload_reps(dev1->priv.eswitch); + for (i = 0; i < ldev->ports; i++) + mlx5_eswitch_reload_reps(ldev->pf[i].dev->priv.eswitch); mlx5_core_err(dev0, "Failed to enable lag\n"); return; } @@ -1496,26 +1531,37 @@ u8 mlx5_lag_get_num_ports(struct mlx5_core_dev *dev) } EXPORT_SYMBOL(mlx5_lag_get_num_ports); -struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev) +struct mlx5_core_dev *mlx5_lag_get_next_peer_mdev(struct mlx5_core_dev *dev, int *i) { struct mlx5_core_dev *peer_dev = NULL; struct mlx5_lag *ldev; unsigned long flags; + int idx; spin_lock_irqsave(&lag_lock, flags); ldev = mlx5_lag_dev(dev); if (!ldev) goto unlock; - peer_dev = ldev->pf[MLX5_LAG_P1].dev == dev ? - ldev->pf[MLX5_LAG_P2].dev : - ldev->pf[MLX5_LAG_P1].dev; + if (*i == ldev->ports) + goto unlock; + for (idx = *i; idx < ldev->ports; idx++) + if (ldev->pf[idx].dev != dev) + break; + + if (idx == ldev->ports) { + *i = idx; + goto unlock; + } + *i = idx + 1; + + peer_dev = ldev->pf[idx].dev; unlock: spin_unlock_irqrestore(&lag_lock, flags); return peer_dev; } -EXPORT_SYMBOL(mlx5_lag_get_peer_mdev); +EXPORT_SYMBOL(mlx5_lag_get_next_peer_mdev); int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, u64 *values, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h index bc1f1dd3e283..d7e7fa2348a5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h @@ -111,7 +111,6 @@ int mlx5_activate_lag(struct mlx5_lag *ldev, bool shared_fdb); int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev, struct net_device *ndev); -bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev); char *mlx5_get_str_port_sel_mode(enum mlx5_lag_mode mode, unsigned long flags); void mlx5_infer_tx_enabled(struct lag_tracker *tracker, u8 num_ports, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c index d85a8dfc153d..976caa8e6922 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c @@ -14,6 +14,7 @@ static bool __mlx5_lag_is_multipath(struct mlx5_lag *ldev) return ldev->mode == MLX5_LAG_MODE_MULTIPATH; } +#define MLX5_LAG_MULTIPATH_OFFLOADS_SUPPORTED_PORTS 2 static bool mlx5_lag_multipath_check_prereq(struct mlx5_lag *ldev) { if (!mlx5_lag_is_ready(ldev)) @@ -22,6 +23,9 @@ static bool mlx5_lag_multipath_check_prereq(struct mlx5_lag *ldev) if (__mlx5_lag_is_active(ldev) && !__mlx5_lag_is_multipath(ldev)) return false; + if (ldev->ports > MLX5_LAG_MULTIPATH_OFFLOADS_SUPPORTED_PORTS) + return false; + return mlx5_esw_multipath_prereq(ldev->pf[MLX5_LAG_P1].dev, ldev->pf[MLX5_LAG_P2].dev); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c index 0c0ef600f643..0e869a76dfe4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c @@ -65,6 +65,7 @@ err_metadata: return err; } +#define MLX5_LAG_MPESW_OFFLOADS_SUPPORTED_PORTS 2 static int enable_mpesw(struct mlx5_lag *ldev) { struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; @@ -74,6 +75,9 @@ static int enable_mpesw(struct mlx5_lag *ldev) if (ldev->mode != MLX5_LAG_MODE_NONE) return -EINVAL; + if (ldev->ports > MLX5_LAG_MPESW_OFFLOADS_SUPPORTED_PORTS) + return -EOPNOTSUPP; + if (mlx5_eswitch_mode(dev0) != MLX5_ESWITCH_OFFLOADS || !MLX5_CAP_PORT_SELECTION(dev0, port_select_flow_table) || !MLX5_CAP_GEN(dev0, create_lag_when_not_master_up) || diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c index adefde3ea941..78c94b22bdc0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c @@ -3,6 +3,7 @@ #include <linux/mlx5/vport.h> #include "lib/devcom.h" +#include "mlx5_core.h" static LIST_HEAD(devcom_list); @@ -13,12 +14,12 @@ static LIST_HEAD(devcom_list); struct mlx5_devcom_component { struct { - void *data; + void __rcu *data; } device[MLX5_DEVCOM_PORTS_SUPPORTED]; mlx5_devcom_event_handler_t handler; struct rw_semaphore sem; - bool paired; + bool ready; }; struct mlx5_devcom_list { @@ -74,12 +75,14 @@ struct mlx5_devcom *mlx5_devcom_register_device(struct mlx5_core_dev *dev) if (!mlx5_core_is_pf(dev)) return NULL; - if (MLX5_CAP_GEN(dev, num_lag_ports) != MLX5_DEVCOM_PORTS_SUPPORTED) + if (MLX5_CAP_GEN(dev, num_lag_ports) > MLX5_DEVCOM_PORTS_SUPPORTED) return NULL; + mlx5_dev_list_lock(); sguid0 = mlx5_query_nic_system_image_guid(dev); list_for_each_entry(iter, &devcom_list, list) { - struct mlx5_core_dev *tmp_dev = NULL; + /* There is at least one device in iter */ + struct mlx5_core_dev *tmp_dev; idx = -1; for (i = 0; i < MLX5_DEVCOM_PORTS_SUPPORTED; i++) { @@ -102,8 +105,10 @@ struct mlx5_devcom *mlx5_devcom_register_device(struct mlx5_core_dev *dev) if (!priv) { priv = mlx5_devcom_list_alloc(); - if (!priv) - return ERR_PTR(-ENOMEM); + if (!priv) { + devcom = ERR_PTR(-ENOMEM); + goto out; + } idx = 0; new_priv = true; @@ -112,13 +117,16 @@ struct mlx5_devcom *mlx5_devcom_register_device(struct mlx5_core_dev *dev) priv->devs[idx] = dev; devcom = mlx5_devcom_alloc(priv, idx); if (!devcom) { - kfree(priv); - return ERR_PTR(-ENOMEM); + if (new_priv) + kfree(priv); + devcom = ERR_PTR(-ENOMEM); + goto out; } if (new_priv) list_add(&priv->list, &devcom_list); - +out: + mlx5_dev_list_unlock(); return devcom; } @@ -131,6 +139,7 @@ void mlx5_devcom_unregister_device(struct mlx5_devcom *devcom) if (IS_ERR_OR_NULL(devcom)) return; + mlx5_dev_list_lock(); priv = devcom->priv; priv->devs[devcom->idx] = NULL; @@ -141,10 +150,12 @@ void mlx5_devcom_unregister_device(struct mlx5_devcom *devcom) break; if (i != MLX5_DEVCOM_PORTS_SUPPORTED) - return; + goto out; list_del(&priv->list); kfree(priv); +out: + mlx5_dev_list_unlock(); } void mlx5_devcom_register_component(struct mlx5_devcom *devcom, @@ -162,7 +173,7 @@ void mlx5_devcom_register_component(struct mlx5_devcom *devcom, comp = &devcom->priv->components[id]; down_write(&comp->sem); comp->handler = handler; - comp->device[devcom->idx].data = data; + rcu_assign_pointer(comp->device[devcom->idx].data, data); up_write(&comp->sem); } @@ -176,13 +187,14 @@ void mlx5_devcom_unregister_component(struct mlx5_devcom *devcom, comp = &devcom->priv->components[id]; down_write(&comp->sem); - comp->device[devcom->idx].data = NULL; + RCU_INIT_POINTER(comp->device[devcom->idx].data, NULL); up_write(&comp->sem); + synchronize_rcu(); } int mlx5_devcom_send_event(struct mlx5_devcom *devcom, enum mlx5_devcom_components id, - int event, + int event, int rollback_event, void *event_data) { struct mlx5_devcom_component *comp; @@ -193,65 +205,140 @@ int mlx5_devcom_send_event(struct mlx5_devcom *devcom, comp = &devcom->priv->components[id]; down_write(&comp->sem); - for (i = 0; i < MLX5_DEVCOM_PORTS_SUPPORTED; i++) - if (i != devcom->idx && comp->device[i].data) { - err = comp->handler(event, comp->device[i].data, - event_data); - break; + for (i = 0; i < MLX5_DEVCOM_PORTS_SUPPORTED; i++) { + void *data = rcu_dereference_protected(comp->device[i].data, + lockdep_is_held(&comp->sem)); + + if (i != devcom->idx && data) { + err = comp->handler(event, data, event_data); + if (err) + goto rollback; } + } + + up_write(&comp->sem); + return 0; + +rollback: + while (i--) { + void *data = rcu_dereference_protected(comp->device[i].data, + lockdep_is_held(&comp->sem)); + + if (i != devcom->idx && data) + comp->handler(rollback_event, data, event_data); + } up_write(&comp->sem); return err; } -void mlx5_devcom_set_paired(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id, - bool paired) +void mlx5_devcom_comp_set_ready(struct mlx5_devcom *devcom, + enum mlx5_devcom_components id, + bool ready) { struct mlx5_devcom_component *comp; comp = &devcom->priv->components[id]; WARN_ON(!rwsem_is_locked(&comp->sem)); - comp->paired = paired; + WRITE_ONCE(comp->ready, ready); } -bool mlx5_devcom_is_paired(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id) +bool mlx5_devcom_comp_is_ready(struct mlx5_devcom *devcom, + enum mlx5_devcom_components id) { if (IS_ERR_OR_NULL(devcom)) return false; - return devcom->priv->components[id].paired; + return READ_ONCE(devcom->priv->components[id].ready); } -void *mlx5_devcom_get_peer_data(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id) +bool mlx5_devcom_for_each_peer_begin(struct mlx5_devcom *devcom, + enum mlx5_devcom_components id) { struct mlx5_devcom_component *comp; - int i; if (IS_ERR_OR_NULL(devcom)) - return NULL; + return false; comp = &devcom->priv->components[id]; down_read(&comp->sem); - if (!comp->paired) { + if (!READ_ONCE(comp->ready)) { up_read(&comp->sem); - return NULL; + return false; } - for (i = 0; i < MLX5_DEVCOM_PORTS_SUPPORTED; i++) - if (i != devcom->idx) - break; - - return comp->device[i].data; + return true; } -void mlx5_devcom_release_peer_data(struct mlx5_devcom *devcom, +void mlx5_devcom_for_each_peer_end(struct mlx5_devcom *devcom, enum mlx5_devcom_components id) { struct mlx5_devcom_component *comp = &devcom->priv->components[id]; up_read(&comp->sem); } + +void *mlx5_devcom_get_next_peer_data(struct mlx5_devcom *devcom, + enum mlx5_devcom_components id, + int *i) +{ + struct mlx5_devcom_component *comp; + void *ret; + int idx; + + comp = &devcom->priv->components[id]; + + if (*i == MLX5_DEVCOM_PORTS_SUPPORTED) + return NULL; + for (idx = *i; idx < MLX5_DEVCOM_PORTS_SUPPORTED; idx++) { + if (idx != devcom->idx) { + ret = rcu_dereference_protected(comp->device[idx].data, + lockdep_is_held(&comp->sem)); + if (ret) + break; + } + } + + if (idx == MLX5_DEVCOM_PORTS_SUPPORTED) { + *i = idx; + return NULL; + } + *i = idx + 1; + + return ret; +} + +void *mlx5_devcom_get_next_peer_data_rcu(struct mlx5_devcom *devcom, + enum mlx5_devcom_components id, + int *i) +{ + struct mlx5_devcom_component *comp; + void *ret; + int idx; + + comp = &devcom->priv->components[id]; + + if (*i == MLX5_DEVCOM_PORTS_SUPPORTED) + return NULL; + for (idx = *i; idx < MLX5_DEVCOM_PORTS_SUPPORTED; idx++) { + if (idx != devcom->idx) { + /* This can change concurrently, however 'data' pointer will remain + * valid for the duration of RCU read section. + */ + if (!READ_ONCE(comp->ready)) + return NULL; + ret = rcu_dereference(comp->device[idx].data); + if (ret) + break; + } + } + + if (idx == MLX5_DEVCOM_PORTS_SUPPORTED) { + *i = idx; + return NULL; + } + *i = idx + 1; + + return ret; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h index 94313c18bb64..d953a01b8eaa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h @@ -6,7 +6,7 @@ #include <linux/mlx5/driver.h> -#define MLX5_DEVCOM_PORTS_SUPPORTED 2 +#define MLX5_DEVCOM_PORTS_SUPPORTED 4 enum mlx5_devcom_components { MLX5_DEVCOM_ESW_OFFLOADS, @@ -30,19 +30,33 @@ void mlx5_devcom_unregister_component(struct mlx5_devcom *devcom, int mlx5_devcom_send_event(struct mlx5_devcom *devcom, enum mlx5_devcom_components id, - int event, + int event, int rollback_event, void *event_data); -void mlx5_devcom_set_paired(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id, - bool paired); -bool mlx5_devcom_is_paired(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id); +void mlx5_devcom_comp_set_ready(struct mlx5_devcom *devcom, + enum mlx5_devcom_components id, + bool ready); +bool mlx5_devcom_comp_is_ready(struct mlx5_devcom *devcom, + enum mlx5_devcom_components id); -void *mlx5_devcom_get_peer_data(struct mlx5_devcom *devcom, - enum mlx5_devcom_components id); -void mlx5_devcom_release_peer_data(struct mlx5_devcom *devcom, +bool mlx5_devcom_for_each_peer_begin(struct mlx5_devcom *devcom, + enum mlx5_devcom_components id); +void mlx5_devcom_for_each_peer_end(struct mlx5_devcom *devcom, enum mlx5_devcom_components id); +void *mlx5_devcom_get_next_peer_data(struct mlx5_devcom *devcom, + enum mlx5_devcom_components id, int *i); -#endif +#define mlx5_devcom_for_each_peer_entry(devcom, id, data, i) \ + for (i = 0, data = mlx5_devcom_get_next_peer_data(devcom, id, &i); \ + data; \ + data = mlx5_devcom_get_next_peer_data(devcom, id, &i)) + +void *mlx5_devcom_get_next_peer_data_rcu(struct mlx5_devcom *devcom, + enum mlx5_devcom_components id, int *i); +#define mlx5_devcom_for_each_peer_entry_rcu(devcom, id, data, i) \ + for (i = 0, data = mlx5_devcom_get_next_peer_data_rcu(devcom, id, &i); \ + data; \ + data = mlx5_devcom_get_next_peer_data_rcu(devcom, id, &i)) + +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c index 8ff16318e32d..4450091e181a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c @@ -99,7 +99,7 @@ int mlx5_mpfs_init(struct mlx5_core_dev *dev) int l2table_size = 1 << MLX5_CAP_GEN(dev, log_max_l2_table); struct mlx5_mpfs *mpfs; - if (!MLX5_ESWITCH_MANAGER(dev)) + if (!MLX5_ESWITCH_MANAGER(dev) || l2table_size == 1) return 0; mpfs = kzalloc(sizeof(*mpfs), GFP_KERNEL); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 995eb2d5ace0..d6ee016deae1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -923,7 +923,6 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev, } mlx5_pci_vsc_init(dev); - dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev); return 0; err_clr_master: @@ -1049,7 +1048,7 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) dev->dm = mlx5_dm_create(dev); if (IS_ERR(dev->dm)) - mlx5_core_warn(dev, "Failed to init device memory%d\n", err); + mlx5_core_warn(dev, "Failed to init device memory %ld\n", PTR_ERR(dev->dm)); dev->tracer = mlx5_fw_tracer_create(dev); dev->hv_vhca = mlx5_hv_vhca_create(dev); @@ -1155,6 +1154,7 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot, u64 timeout goto err_cmd_cleanup; } + dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev); mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_UP); mlx5_start_health_poll(dev); @@ -1802,15 +1802,16 @@ static void remove_one(struct pci_dev *pdev) struct devlink *devlink = priv_to_devlink(dev); set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state); - /* mlx5_drain_fw_reset() is using devlink APIs. Hence, we must drain - * fw_reset before unregistering the devlink. + /* mlx5_drain_fw_reset() and mlx5_drain_health_wq() are using + * devlink notify APIs. + * Hence, we must drain them before unregistering the devlink. */ mlx5_drain_fw_reset(dev); + mlx5_drain_health_wq(dev); devlink_unregister(devlink); mlx5_sriov_disable(pdev); mlx5_thermal_uninit(dev); mlx5_crdump_disable(dev); - mlx5_drain_health_wq(dev); mlx5_uninit_one(dev); mlx5_pci_close(dev); mlx5_mdev_uninit(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h index efd0c299c5c7..aa403a5ea34e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h @@ -15,6 +15,7 @@ int mlx5_irq_table_init(struct mlx5_core_dev *dev); void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev); int mlx5_irq_table_create(struct mlx5_core_dev *dev); void mlx5_irq_table_destroy(struct mlx5_core_dev *dev); +void mlx5_irq_table_free_irqs(struct mlx5_core_dev *dev); int mlx5_irq_table_get_num_comp(struct mlx5_irq_table *table); int mlx5_irq_table_get_sfs_vec(struct mlx5_irq_table *table); struct mlx5_irq_table *mlx5_irq_table_get(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c index 9d735c343a3b..678f0be81375 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c @@ -32,6 +32,7 @@ #include <linux/kernel.h> #include <linux/mlx5/driver.h> +#include <linux/mlx5/qp.h> #include "mlx5_core.h" int mlx5_core_create_mkey(struct mlx5_core_dev *dev, u32 *mkey, u32 *in, @@ -122,3 +123,23 @@ int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num) return mlx5_cmd_exec_in(dev, destroy_psv, in); } EXPORT_SYMBOL(mlx5_core_destroy_psv); + +__be32 mlx5_core_get_terminate_scatter_list_mkey(struct mlx5_core_dev *dev) +{ + u32 out[MLX5_ST_SZ_DW(query_special_contexts_out)] = {}; + u32 in[MLX5_ST_SZ_DW(query_special_contexts_in)] = {}; + u32 mkey; + + if (!MLX5_CAP_GEN(dev, terminate_scatter_list_mkey)) + return MLX5_TERMINATE_SCATTER_LIST_LKEY; + + MLX5_SET(query_special_contexts_in, in, opcode, + MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS); + if (mlx5_cmd_exec_inout(dev, query_special_contexts, in, out)) + return MLX5_TERMINATE_SCATTER_LIST_LKEY; + + mkey = MLX5_GET(query_special_contexts_out, out, + terminate_scatter_list_mkey); + return cpu_to_be32(mkey); +} +EXPORT_SYMBOL(mlx5_core_get_terminate_scatter_list_mkey); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 2245d3b2f393..843da89a9035 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -32,6 +32,7 @@ struct mlx5_irq { struct mlx5_irq_pool *pool; int refcount; struct msi_map map; + u32 pool_index; }; struct mlx5_irq_table { @@ -132,7 +133,7 @@ static void irq_release(struct mlx5_irq *irq) struct cpu_rmap *rmap; #endif - xa_erase(&pool->irqs, irq->map.index); + xa_erase(&pool->irqs, irq->pool_index); /* free_irq requires that affinity_hint and rmap will be cleared before * calling it. To satisfy this requirement, we call * irq_cpu_rmap_remove() to remove the notifier @@ -140,7 +141,7 @@ static void irq_release(struct mlx5_irq *irq) irq_update_affinity_hint(irq->map.virq, NULL); #ifdef CONFIG_RFS_ACCEL rmap = mlx5_eq_table_get_rmap(pool->dev); - if (rmap && irq->map.index) + if (rmap) irq_cpu_rmap_remove(rmap, irq->map.virq); #endif @@ -231,12 +232,13 @@ struct mlx5_irq *mlx5_irq_alloc(struct mlx5_irq_pool *pool, int i, if (!irq) return ERR_PTR(-ENOMEM); if (!i || !pci_msix_can_alloc_dyn(dev->pdev)) { - /* The vector at index 0 was already allocated. - * Just get the irq number. If dynamic irq is not supported - * vectors have also been allocated. + /* The vector at index 0 is always statically allocated. If + * dynamic irq is not supported all vectors are statically + * allocated. In both cases just get the irq number and set + * the index. */ irq->map.virq = pci_irq_vector(dev->pdev, i); - irq->map.index = 0; + irq->map.index = i; } else { irq->map = pci_msix_alloc_irq_at(dev->pdev, MSI_ANY_INDEX, af_desc); if (!irq->map.virq) { @@ -276,11 +278,11 @@ struct mlx5_irq *mlx5_irq_alloc(struct mlx5_irq_pool *pool, int i, } irq->pool = pool; irq->refcount = 1; - irq->map.index = i; - err = xa_err(xa_store(&pool->irqs, irq->map.index, irq, GFP_KERNEL)); + irq->pool_index = i; + err = xa_err(xa_store(&pool->irqs, irq->pool_index, irq, GFP_KERNEL)); if (err) { mlx5_core_err(dev, "Failed to alloc xa entry for irq(%u). err = %d\n", - irq->map.index, err); + irq->pool_index, err); goto err_xa; } return irq; @@ -567,13 +569,13 @@ int mlx5_irqs_request_vectors(struct mlx5_core_dev *dev, u16 *cpus, int nirqs, struct mlx5_irq *irq; int i; - af_desc.is_managed = 1; + af_desc.is_managed = false; for (i = 0; i < nirqs; i++) { + cpumask_clear(&af_desc.mask); cpumask_set_cpu(cpus[i], &af_desc.mask); irq = mlx5_irq_request(dev, i + 1, &af_desc, rmap); if (IS_ERR(irq)) break; - cpumask_clear(&af_desc.mask); irqs[i] = irq; } @@ -691,6 +693,24 @@ static void irq_pools_destroy(struct mlx5_irq_table *table) irq_pool_free(table->pcif_pool); } +static void mlx5_irq_pool_free_irqs(struct mlx5_irq_pool *pool) +{ + struct mlx5_irq *irq; + unsigned long index; + + xa_for_each(&pool->irqs, index, irq) + free_irq(irq->map.virq, &irq->nh); +} + +static void mlx5_irq_pools_free_irqs(struct mlx5_irq_table *table) +{ + if (table->sf_ctrl_pool) { + mlx5_irq_pool_free_irqs(table->sf_comp_pool); + mlx5_irq_pool_free_irqs(table->sf_ctrl_pool); + } + mlx5_irq_pool_free_irqs(table->pcif_pool); +} + /* irq_table API */ int mlx5_irq_table_init(struct mlx5_core_dev *dev) @@ -774,6 +794,17 @@ void mlx5_irq_table_destroy(struct mlx5_core_dev *dev) pci_free_irq_vectors(dev->pdev); } +void mlx5_irq_table_free_irqs(struct mlx5_core_dev *dev) +{ + struct mlx5_irq_table *table = dev->priv.irq_table; + + if (mlx5_core_is_sf(dev)) + return; + + mlx5_irq_pools_free_irqs(table); + pci_free_irq_vectors(dev->pdev); +} + int mlx5_irq_table_get_sfs_vec(struct mlx5_irq_table *table) { if (table->sf_comp_pool) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c index 540cf05f6373..a42f6cd99b74 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c @@ -30,9 +30,8 @@ static int mlx5_rdma_enable_roce_steering(struct mlx5_core_dev *dev) struct mlx5_flow_spec *spec; struct mlx5_flow_table *ft; struct mlx5_flow_group *fg; - void *match_criteria; + struct mlx5_eswitch *esw; u32 *flow_group_in; - void *misc; int err; if (!(MLX5_CAP_FLOWTABLE_RDMA_RX(dev, ft_support) && @@ -63,12 +62,8 @@ static int mlx5_rdma_enable_roce_steering(struct mlx5_core_dev *dev) goto free; } - MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, - MLX5_MATCH_MISC_PARAMETERS); - match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, - match_criteria); - MLX5_SET_TO_ONES(fte_match_param, match_criteria, - misc_parameters.source_port); + esw = dev->priv.eswitch; + mlx5_esw_set_flow_group_source_port(esw, flow_group_in, 0); fg = mlx5_create_flow_group(ft, flow_group_in); if (IS_ERR(fg)) { @@ -77,14 +72,7 @@ static int mlx5_rdma_enable_roce_steering(struct mlx5_core_dev *dev) goto destroy_flow_table; } - spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS; - misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, - misc_parameters); - MLX5_SET(fte_match_set_misc, misc, source_port, - dev->priv.eswitch->manager_vport); - misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, - misc_parameters); - MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port); + mlx5_esw_set_spec_source_port(esw, esw->manager_vport, spec); flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW; flow_rule = mlx5_add_flow_rules(ft, spec, &flow_act, NULL, 0); @@ -115,7 +103,7 @@ free: static void mlx5_rdma_del_roce_addr(struct mlx5_core_dev *dev) { - mlx5_core_roce_gid_set(dev, 0, 0, 0, + mlx5_core_roce_gid_set(dev, 0, MLX5_ROCE_VERSION_2, 0, NULL, NULL, false, 0, 1); } @@ -135,7 +123,7 @@ static int mlx5_rdma_add_roce_addr(struct mlx5_core_dev *dev) mlx5_rdma_make_default_gid(dev, &gid); return mlx5_core_roce_gid_set(dev, 0, - MLX5_ROCE_VERSION_1, + MLX5_ROCE_VERSION_2, 0, gid.raw, mac, false, 0, 1); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c index e2f26d0bc615..0692363cf80e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c @@ -63,6 +63,7 @@ static void mlx5_sf_dev_remove(struct auxiliary_device *adev) struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev); struct devlink *devlink = priv_to_devlink(sf_dev->mdev); + mlx5_drain_health_wq(sf_dev->mdev); devlink_unregister(devlink); mlx5_uninit_one(sf_dev->mdev); iounmap(sf_dev->mdev->iseg); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c index 7d955a4d9f14..9c02e5ea797c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c @@ -283,7 +283,7 @@ out: static int mlx5_sf_add(struct mlx5_core_dev *dev, struct mlx5_sf_table *table, const struct devlink_port_new_attrs *new_attr, struct netlink_ext_ack *extack, - unsigned int *new_port_index) + struct devlink_port **dl_port) { struct mlx5_eswitch *esw = dev->priv.eswitch; struct mlx5_sf *sf; @@ -297,7 +297,7 @@ static int mlx5_sf_add(struct mlx5_core_dev *dev, struct mlx5_sf_table *table, new_attr->controller, new_attr->sfnum); if (err) goto esw_err; - *new_port_index = sf->port_index; + *dl_port = &sf->dl_port; trace_mlx5_sf_add(dev, sf->port_index, sf->controller, sf->hw_fn_id, new_attr->sfnum); return 0; @@ -339,7 +339,7 @@ mlx5_sf_new_check_attr(struct mlx5_core_dev *dev, const struct devlink_port_new_ int mlx5_devlink_sf_port_new(struct devlink *devlink, const struct devlink_port_new_attrs *new_attr, struct netlink_ext_ack *extack, - unsigned int *new_port_index) + struct devlink_port **dl_port) { struct mlx5_core_dev *dev = devlink_priv(devlink); struct mlx5_sf_table *table; @@ -355,7 +355,7 @@ int mlx5_devlink_sf_port_new(struct devlink *devlink, "Port add is only supported in eswitch switchdev mode or SF ports are disabled."); return -EOPNOTSUPP; } - err = mlx5_sf_add(dev, table, new_attr, extack, new_port_index); + err = mlx5_sf_add(dev, table, new_attr, extack, dl_port); mlx5_sf_table_put(table); return err; } @@ -379,7 +379,8 @@ static void mlx5_sf_dealloc(struct mlx5_sf_table *table, struct mlx5_sf *sf) } } -int mlx5_devlink_sf_port_del(struct devlink *devlink, unsigned int port_index, +int mlx5_devlink_sf_port_del(struct devlink *devlink, + struct devlink_port *dl_port, struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_priv(devlink); @@ -394,7 +395,7 @@ int mlx5_devlink_sf_port_del(struct devlink *devlink, unsigned int port_index, "Port del is only supported in eswitch switchdev mode or SF ports are disabled."); return -EOPNOTSUPP; } - sf = mlx5_sf_lookup_by_index(table, port_index); + sf = mlx5_sf_lookup_by_index(table, dl_port->index); if (!sf) { err = -ENODEV; goto sf_err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h index 3a480e06ecc0..860f9ddb7107 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h @@ -21,8 +21,9 @@ void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev); int mlx5_devlink_sf_port_new(struct devlink *devlink, const struct devlink_port_new_attrs *add_attr, struct netlink_ext_ack *extack, - unsigned int *new_port_index); -int mlx5_devlink_sf_port_del(struct devlink *devlink, unsigned int port_index, + struct devlink_port **dl_port); +int mlx5_devlink_sf_port_del(struct devlink *devlink, + struct devlink_port *dl_port, struct netlink_ext_ack *extack); int mlx5_devlink_sf_port_fn_state_get(struct devlink_port *dl_port, enum devlink_port_fn_state *state, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index 20d7662c10fb..f07d00929162 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -74,9 +74,6 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs) struct mlx5_core_sriov *sriov = &dev->priv.sriov; int err, vf, num_msix_count; - if (!MLX5_ESWITCH_MANAGER(dev)) - goto enable_vfs_hca; - err = mlx5_eswitch_enable(dev->priv.eswitch, num_vfs); if (err) { mlx5_core_warn(dev, @@ -84,7 +81,6 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs) return err; } -enable_vfs_hca: num_msix_count = mlx5_get_default_msix_vec_count(dev, num_vfs); for (vf = 0; vf < num_vfs; vf++) { /* Notify the VF before its enablement to let it set diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index 0eb9a8d7f282..4e9bc1897a88 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -2071,8 +2071,9 @@ mlx5dr_action_create_dest_vport(struct mlx5dr_domain *dmn, struct mlx5dr_action *action; u8 peer_vport; - peer_vport = vhca_id_valid && (vhca_id != dmn->info.caps.gvmi); - vport_dmn = peer_vport ? dmn->peer_dmn : dmn; + peer_vport = vhca_id_valid && mlx5_core_is_pf(dmn->mdev) && + (vhca_id != dmn->info.caps.gvmi); + vport_dmn = peer_vport ? dmn->peer_dmn[vhca_id] : dmn; if (!vport_dmn) { mlx5dr_dbg(dmn, "No peer vport domain for given vhca_id\n"); return NULL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c index 3835ba3f4dda..1aa525e509f1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c @@ -117,6 +117,8 @@ int mlx5dr_cmd_query_device(struct mlx5_core_dev *mdev, caps->gvmi = MLX5_CAP_GEN(mdev, vhca_id); caps->flex_protocols = MLX5_CAP_GEN(mdev, flex_parser_protocols); caps->sw_format_ver = MLX5_CAP_GEN(mdev, steering_format_version); + caps->roce_caps.fl_rc_qp_when_roce_disabled = + MLX5_CAP_GEN(mdev, fl_rc_qp_when_roce_disabled); if (MLX5_CAP_GEN(mdev, roce)) { err = dr_cmd_query_nic_vport_roce_en(mdev, 0, &roce_en); @@ -124,7 +126,7 @@ int mlx5dr_cmd_query_device(struct mlx5_core_dev *mdev, return err; caps->roce_caps.roce_en = roce_en; - caps->roce_caps.fl_rc_qp_when_roce_disabled = + caps->roce_caps.fl_rc_qp_when_roce_disabled |= MLX5_CAP_ROCE(mdev, fl_rc_qp_when_roce_disabled); caps->roce_caps.fl_rc_qp_when_roce_enabled = MLX5_CAP_ROCE(mdev, fl_rc_qp_when_roce_enabled); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c index 9a2dfe6ebe31..75dc85dc24ef 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c @@ -555,17 +555,18 @@ int mlx5dr_domain_destroy(struct mlx5dr_domain *dmn) } void mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn, - struct mlx5dr_domain *peer_dmn) + struct mlx5dr_domain *peer_dmn, + u8 peer_idx) { mlx5dr_domain_lock(dmn); - if (dmn->peer_dmn) - refcount_dec(&dmn->peer_dmn->refcount); + if (dmn->peer_dmn[peer_idx]) + refcount_dec(&dmn->peer_dmn[peer_idx]->refcount); - dmn->peer_dmn = peer_dmn; + dmn->peer_dmn[peer_idx] = peer_dmn; - if (dmn->peer_dmn) - refcount_inc(&dmn->peer_dmn->refcount); + if (dmn->peer_dmn[peer_idx]) + refcount_inc(&dmn->peer_dmn[peer_idx]->refcount); mlx5dr_domain_unlock(dmn); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c index 13e06a6a6b22..d6947fe13d56 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c @@ -213,6 +213,8 @@ struct mlx5dr_ptrn_mgr *mlx5dr_ptrn_mgr_create(struct mlx5dr_domain *dmn) } INIT_LIST_HEAD(&mgr->ptrn_list); + mutex_init(&mgr->modify_hdr_mutex); + return mgr; free_mgr: @@ -237,5 +239,6 @@ void mlx5dr_ptrn_mgr_destroy(struct mlx5dr_ptrn_mgr *mgr) } mlx5dr_icm_pool_destroy(mgr->ptrn_icm_pool); + mutex_destroy(&mgr->modify_hdr_mutex); kfree(mgr); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c index 9413aaf51251..e94fbb015efa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c @@ -15,7 +15,8 @@ static u32 dr_ste_crc32_calc(const void *input_data, size_t length) { u32 crc = crc32(0, input_data, length); - return (__force u32)htonl(crc); + return (__force u32)((crc >> 24) & 0xff) | ((crc << 8) & 0xff0000) | + ((crc >> 8) & 0xff00) | ((crc << 24) & 0xff000000); } bool mlx5dr_ste_supp_ttl_cs_recalc(struct mlx5dr_cmd_caps *caps) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c index 2010d4ac6519..69d7a8f3c402 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c @@ -1647,6 +1647,7 @@ dr_ste_v0_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value, u8 *tag) { struct mlx5dr_match_misc *misc = &value->misc; + int id = misc->source_eswitch_owner_vhca_id; struct mlx5dr_cmd_vport_cap *vport_cap; struct mlx5dr_domain *dmn = sb->dmn; struct mlx5dr_domain *vport_dmn; @@ -1657,11 +1658,11 @@ dr_ste_v0_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value, if (sb->vhca_id_valid) { /* Find port GVMI based on the eswitch_owner_vhca_id */ - if (misc->source_eswitch_owner_vhca_id == dmn->info.caps.gvmi) + if (id == dmn->info.caps.gvmi) vport_dmn = dmn; - else if (dmn->peer_dmn && (misc->source_eswitch_owner_vhca_id == - dmn->peer_dmn->info.caps.gvmi)) - vport_dmn = dmn->peer_dmn; + else if (id < MLX5_MAX_PORTS && dmn->peer_dmn[id] && + (id == dmn->peer_dmn[id]->info.caps.gvmi)) + vport_dmn = dmn->peer_dmn[id]; else return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c index 4c0704ad166b..f4ef0b22b991 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c @@ -1979,6 +1979,7 @@ static int dr_ste_v1_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value, u8 *tag) { struct mlx5dr_match_misc *misc = &value->misc; + int id = misc->source_eswitch_owner_vhca_id; struct mlx5dr_cmd_vport_cap *vport_cap; struct mlx5dr_domain *dmn = sb->dmn; struct mlx5dr_domain *vport_dmn; @@ -1988,11 +1989,11 @@ static int dr_ste_v1_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value, if (sb->vhca_id_valid) { /* Find port GVMI based on the eswitch_owner_vhca_id */ - if (misc->source_eswitch_owner_vhca_id == dmn->info.caps.gvmi) + if (id == dmn->info.caps.gvmi) vport_dmn = dmn; - else if (dmn->peer_dmn && (misc->source_eswitch_owner_vhca_id == - dmn->peer_dmn->info.caps.gvmi)) - vport_dmn = dmn->peer_dmn; + else if (id < MLX5_MAX_PORTS && dmn->peer_dmn[id] && + (id == dmn->peer_dmn[id]->info.caps.gvmi)) + vport_dmn = dmn->peer_dmn[id]; else return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index 678a993ab053..1622dbbe6b97 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -935,7 +935,7 @@ struct mlx5dr_domain_info { }; struct mlx5dr_domain { - struct mlx5dr_domain *peer_dmn; + struct mlx5dr_domain *peer_dmn[MLX5_MAX_PORTS]; struct mlx5_core_dev *mdev; u32 pdn; struct mlx5_uars_page *uar; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c index 984653756779..c6fda1cbfcff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -770,14 +770,15 @@ restore_fte: } static int mlx5_cmd_dr_set_peer(struct mlx5_flow_root_namespace *ns, - struct mlx5_flow_root_namespace *peer_ns) + struct mlx5_flow_root_namespace *peer_ns, + u8 peer_idx) { struct mlx5dr_domain *peer_domain = NULL; if (peer_ns) peer_domain = peer_ns->fs_dr_domain.dr_domain; mlx5dr_domain_set_peer(ns->fs_dr_domain.dr_domain, - peer_domain); + peer_domain, peer_idx); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h index 9afd268a2573..5ba88f2ecb3f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h @@ -48,7 +48,8 @@ int mlx5dr_domain_destroy(struct mlx5dr_domain *domain); int mlx5dr_domain_sync(struct mlx5dr_domain *domain, u32 flags); void mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn, - struct mlx5dr_domain *peer_dmn); + struct mlx5dr_domain *peer_dmn, + u8 peer_idx); struct mlx5dr_table * mlx5dr_table_create(struct mlx5dr_domain *domain, u32 level, u32 flags, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index ba7e3df22413..bc66b078a8a1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -288,7 +288,8 @@ int mlx5_query_nic_vport_mac_list(struct mlx5_core_dev *dev, MLX5_CMD_OP_QUERY_NIC_VPORT_CONTEXT); MLX5_SET(query_nic_vport_context_in, in, allowed_list_type, list_type); MLX5_SET(query_nic_vport_context_in, in, vport_number, vport); - MLX5_SET(query_nic_vport_context_in, in, other_vport, 1); + if (vport || mlx5_core_is_ecpf(dev)) + MLX5_SET(query_nic_vport_context_in, in, other_vport, 1); err = mlx5_cmd_exec(dev, in, sizeof(in), out, out_sz); if (err) diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c index afa3b92a6905..0d5a41a2ae01 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c @@ -245,12 +245,6 @@ static bool mlxbf_gige_rx_packet(struct mlxbf_gige *priv, int *rx_pkts) skb = priv->rx_skb[rx_pi_rem]; - skb_put(skb, datalen); - - skb->ip_summed = CHECKSUM_NONE; /* device did not checksum packet */ - - skb->protocol = eth_type_trans(skb, netdev); - /* Alloc another RX SKB for this same index */ rx_skb = mlxbf_gige_alloc_skb(priv, MLXBF_GIGE_DEFAULT_BUF_SZ, &rx_buf_dma, DMA_FROM_DEVICE); @@ -259,6 +253,13 @@ static bool mlxbf_gige_rx_packet(struct mlxbf_gige *priv, int *rx_pkts) priv->rx_skb[rx_pi_rem] = rx_skb; dma_unmap_single(priv->dev, *rx_wqe_addr, MLXBF_GIGE_DEFAULT_BUF_SZ, DMA_FROM_DEVICE); + + skb_put(skb, datalen); + + skb->ip_summed = CHECKSUM_NONE; /* device did not checksum packet */ + + skb->protocol = eth_type_trans(skb, netdev); + *rx_wqe_addr = rx_buf_dma; } else if (rx_cqe & MLXBF_GIGE_RX_CQE_PKT_STATUS_MAC_ERR) { priv->stats.rx_mac_errors++; diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_format.h b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_format.h index b001e5258091..47f6cc0401c3 100644 --- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_format.h +++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_format.h @@ -44,7 +44,7 @@ MLXFW_MFA2_TLV(multi, struct mlxfw_mfa2_tlv_multi, MLXFW_MFA2_TLV_MULTI_PART); struct mlxfw_mfa2_tlv_psid { - u8 psid[0]; + DECLARE_FLEX_ARRAY(u8, psid); } __packed; MLXFW_MFA2_TLV_VARSIZE(psid, struct mlxfw_mfa2_tlv_psid, diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 22db0bb15c45..1ccf3b73ed72 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -1723,8 +1723,6 @@ static const struct devlink_ops mlxsw_devlink_ops = { BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE), .reload_down = mlxsw_devlink_core_bus_device_reload_down, .reload_up = mlxsw_devlink_core_bus_device_reload_up, - .port_split = mlxsw_devlink_port_split, - .port_unsplit = mlxsw_devlink_port_unsplit, .sb_pool_get = mlxsw_devlink_sb_pool_get, .sb_pool_set = mlxsw_devlink_sb_pool_set, .sb_port_pool_get = mlxsw_devlink_sb_port_pool_get, @@ -3116,6 +3114,11 @@ u64 mlxsw_core_res_get(struct mlxsw_core *mlxsw_core, } EXPORT_SYMBOL(mlxsw_core_res_get); +static const struct devlink_port_ops mlxsw_devlink_port_ops = { + .port_split = mlxsw_devlink_port_split, + .port_unsplit = mlxsw_devlink_port_unsplit, +}; + static int __mlxsw_core_port_init(struct mlxsw_core *mlxsw_core, u16 local_port, enum devlink_port_flavour flavour, u8 slot_index, u32 port_number, bool split, @@ -3150,7 +3153,8 @@ static int __mlxsw_core_port_init(struct mlxsw_core *mlxsw_core, u16 local_port, devlink_port_linecard_set(devlink_port, linecard->devlink_linecard); } - err = devl_port_register(devlink, devlink_port, local_port); + err = devl_port_register_with_ops(devlink, devlink_port, local_port, + &mlxsw_devlink_port_ops); if (err) memset(mlxsw_core_port, 0, sizeof(*mlxsw_core_port)); return err; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c index bd1a51a0a540..f0b2963ebac3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c @@ -42,6 +42,7 @@ static const struct mlxsw_afk_element_info mlxsw_afk_element_infos[] = { MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP_64_95, 0x34, 4), MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP_32_63, 0x38, 4), MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP_0_31, 0x3C, 4), + MLXSW_AFK_ELEMENT_INFO_U32(FDB_MISS, 0x40, 0, 1), }; struct mlxsw_afk { diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h index 3a037fe47211..65a4abadc7db 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h @@ -35,6 +35,7 @@ enum mlxsw_afk_element { MLXSW_AFK_ELEMENT_IP_DSCP, MLXSW_AFK_ELEMENT_VIRT_ROUTER_MSB, MLXSW_AFK_ELEMENT_VIRT_ROUTER_LSB, + MLXSW_AFK_ELEMENT_FDB_MISS, MLXSW_AFK_ELEMENT_MAX, }; @@ -69,7 +70,7 @@ struct mlxsw_afk_element_info { MLXSW_AFK_ELEMENT_INFO(MLXSW_AFK_ELEMENT_TYPE_BUF, \ _element, _offset, 0, _size) -#define MLXSW_AFK_ELEMENT_STORAGE_SIZE 0x40 +#define MLXSW_AFK_ELEMENT_STORAGE_SIZE 0x44 struct mlxsw_afk_element_inst { /* element instance in actual block */ enum mlxsw_afk_element element; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c index 00c32320f891..4dea39f2b304 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c @@ -123,10 +123,12 @@ const struct mlxsw_afk_ops mlxsw_sp1_afk_ops = { }; static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_mac_0[] = { + MLXSW_AFK_ELEMENT_INST_U32(FDB_MISS, 0x00, 3, 1), MLXSW_AFK_ELEMENT_INST_BUF(DMAC_0_31, 0x04, 4), }; static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_mac_1[] = { + MLXSW_AFK_ELEMENT_INST_U32(FDB_MISS, 0x00, 3, 1), MLXSW_AFK_ELEMENT_INST_BUF(SMAC_0_31, 0x04, 4), }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index 594cdcb90b3d..72917f09e806 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -281,39 +281,38 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, return 0; } -static int mlxsw_sp_flower_parse_meta(struct mlxsw_sp_acl_rule_info *rulei, - struct flow_cls_offload *f, - struct mlxsw_sp_flow_block *block) +static int +mlxsw_sp_flower_parse_meta_iif(struct mlxsw_sp_acl_rule_info *rulei, + const struct mlxsw_sp_flow_block *block, + const struct flow_match_meta *match, + struct netlink_ext_ack *extack) { - struct flow_rule *rule = flow_cls_offload_flow_rule(f); struct mlxsw_sp_port *mlxsw_sp_port; struct net_device *ingress_dev; - struct flow_match_meta match; - if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_META)) + if (!match->mask->ingress_ifindex) return 0; - flow_rule_match_meta(rule, &match); - if (match.mask->ingress_ifindex != 0xFFFFFFFF) { - NL_SET_ERR_MSG_MOD(f->common.extack, "Unsupported ingress ifindex mask"); + if (match->mask->ingress_ifindex != 0xFFFFFFFF) { + NL_SET_ERR_MSG_MOD(extack, "Unsupported ingress ifindex mask"); return -EINVAL; } ingress_dev = __dev_get_by_index(block->net, - match.key->ingress_ifindex); + match->key->ingress_ifindex); if (!ingress_dev) { - NL_SET_ERR_MSG_MOD(f->common.extack, "Can't find specified ingress port to match on"); + NL_SET_ERR_MSG_MOD(extack, "Can't find specified ingress port to match on"); return -EINVAL; } if (!mlxsw_sp_port_dev_check(ingress_dev)) { - NL_SET_ERR_MSG_MOD(f->common.extack, "Can't match on non-mlxsw ingress port"); + NL_SET_ERR_MSG_MOD(extack, "Can't match on non-mlxsw ingress port"); return -EINVAL; } mlxsw_sp_port = netdev_priv(ingress_dev); if (mlxsw_sp_port->mlxsw_sp != block->mlxsw_sp) { - NL_SET_ERR_MSG_MOD(f->common.extack, "Can't match on a port from different device"); + NL_SET_ERR_MSG_MOD(extack, "Can't match on a port from different device"); return -EINVAL; } @@ -321,9 +320,29 @@ static int mlxsw_sp_flower_parse_meta(struct mlxsw_sp_acl_rule_info *rulei, MLXSW_AFK_ELEMENT_SRC_SYS_PORT, mlxsw_sp_port->local_port, 0xFFFFFFFF); + return 0; } +static int mlxsw_sp_flower_parse_meta(struct mlxsw_sp_acl_rule_info *rulei, + struct flow_cls_offload *f, + struct mlxsw_sp_flow_block *block) +{ + struct flow_rule *rule = flow_cls_offload_flow_rule(f); + struct flow_match_meta match; + + if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_META)) + return 0; + + flow_rule_match_meta(rule, &match); + + mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_FDB_MISS, + match.key->l2_miss, match.mask->l2_miss); + + return mlxsw_sp_flower_parse_meta_iif(rulei, block, &match, + f->common.extack); +} + static void mlxsw_sp_flower_parse_ipv4(struct mlxsw_sp_acl_rule_info *rulei, struct flow_cls_offload *f) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c index d309b77a0194..bb8eeb86edf7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c @@ -11,10 +11,12 @@ #include "spectrum_nve.h" #define MLXSW_SP_NVE_VXLAN_IPV4_SUPPORTED_FLAGS (VXLAN_F_UDP_ZERO_CSUM_TX | \ - VXLAN_F_LEARN) + VXLAN_F_LEARN | \ + VXLAN_F_LOCALBYPASS) #define MLXSW_SP_NVE_VXLAN_IPV6_SUPPORTED_FLAGS (VXLAN_F_IPV6 | \ VXLAN_F_UDP_ZERO_CSUM6_TX | \ - VXLAN_F_UDP_ZERO_CSUM6_RX) + VXLAN_F_UDP_ZERO_CSUM6_RX | \ + VXLAN_F_LOCALBYPASS) static bool mlxsw_sp_nve_vxlan_ipv4_flags_check(const struct vxlan_config *cfg, struct netlink_ext_ack *extack) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 4a73e2fe95ef..7304e8a29cf9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -96,8 +96,8 @@ struct mlxsw_sp_rif_subport { struct mlxsw_sp_rif_ipip_lb { struct mlxsw_sp_rif common; struct mlxsw_sp_rif_ipip_lb_config lb_config; - u16 ul_vr_id; /* Reserved for Spectrum-2. */ - u16 ul_rif_id; /* Reserved for Spectrum. */ + u16 ul_vr_id; /* Spectrum-1. */ + u16 ul_rif_id; /* Spectrum-2+. */ }; struct mlxsw_sp_rif_params_ipip_lb { @@ -748,10 +748,11 @@ static bool mlxsw_sp_vr_is_used(const struct mlxsw_sp_vr *vr) static struct mlxsw_sp_vr *mlxsw_sp_vr_find_unused(struct mlxsw_sp *mlxsw_sp) { + int max_vrs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); struct mlxsw_sp_vr *vr; int i; - for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) { + for (i = 0; i < max_vrs; i++) { vr = &mlxsw_sp->router->vrs[i]; if (!mlxsw_sp_vr_is_used(vr)) return vr; @@ -792,12 +793,13 @@ static u32 mlxsw_sp_fix_tb_id(u32 tb_id) static struct mlxsw_sp_vr *mlxsw_sp_vr_find(struct mlxsw_sp *mlxsw_sp, u32 tb_id) { + int max_vrs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); struct mlxsw_sp_vr *vr; int i; tb_id = mlxsw_sp_fix_tb_id(tb_id); - for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) { + for (i = 0; i < max_vrs; i++) { vr = &mlxsw_sp->router->vrs[i]; if (mlxsw_sp_vr_is_used(vr) && vr->tb_id == tb_id) return vr; @@ -959,6 +961,7 @@ static int mlxsw_sp_vrs_lpm_tree_replace(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib *fib, struct mlxsw_sp_lpm_tree *new_tree) { + int max_vrs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); enum mlxsw_sp_l3proto proto = fib->proto; struct mlxsw_sp_lpm_tree *old_tree; u8 old_id, new_id = new_tree->id; @@ -968,7 +971,7 @@ static int mlxsw_sp_vrs_lpm_tree_replace(struct mlxsw_sp *mlxsw_sp, old_tree = mlxsw_sp->router->lpm.proto_trees[proto]; old_id = old_tree->id; - for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) { + for (i = 0; i < max_vrs; i++) { vr = &mlxsw_sp->router->vrs[i]; if (!mlxsw_sp_vr_lpm_tree_should_replace(vr, proto, old_id)) continue; @@ -7298,9 +7301,10 @@ static void mlxsw_sp_vr_fib_flush(struct mlxsw_sp *mlxsw_sp, static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp) { + int max_vrs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); int i, j; - for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) { + for (i = 0; i < max_vrs; i++) { struct mlxsw_sp_vr *vr = &mlxsw_sp->router->vrs[i]; if (!mlxsw_sp_vr_is_used(vr)) @@ -7699,9 +7703,10 @@ static struct mlxsw_sp_rif * mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp, const struct net_device *dev) { + int max_rifs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); int i; - for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) + for (i = 0; i < max_rifs; i++) if (mlxsw_sp->router->rifs[i] && mlxsw_sp->router->rifs[i]->dev == dev) return mlxsw_sp->router->rifs[i]; @@ -9724,7 +9729,7 @@ mlxsw_sp1_rif_ipip_lb_configure(struct mlxsw_sp_rif *rif, struct mlxsw_sp_vr *ul_vr; int err; - ul_vr = mlxsw_sp_vr_get(mlxsw_sp, ul_tb_id, NULL); + ul_vr = mlxsw_sp_vr_get(mlxsw_sp, ul_tb_id, extack); if (IS_ERR(ul_vr)) return PTR_ERR(ul_vr); @@ -9923,7 +9928,7 @@ mlxsw_sp2_rif_ipip_lb_configure(struct mlxsw_sp_rif *rif, struct mlxsw_sp_rif *ul_rif; int err; - ul_rif = mlxsw_sp_ul_rif_get(mlxsw_sp, ul_tb_id, NULL); + ul_rif = mlxsw_sp_ul_rif_get(mlxsw_sp, ul_tb_id, extack); if (IS_ERR(ul_rif)) return PTR_ERR(ul_rif); @@ -10041,11 +10046,12 @@ err_rifs_table_init: static void mlxsw_sp_rifs_fini(struct mlxsw_sp *mlxsw_sp) { + int max_rifs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); int i; WARN_ON_ONCE(atomic_read(&mlxsw_sp->router->rifs_count)); - for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) + for (i = 0; i < max_rifs; i++) WARN_ON_ONCE(mlxsw_sp->router->rifs[i]); devl_resource_occ_get_unregister(devlink, MLXSW_SP_RESOURCE_RIFS); diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 957d96a91a8a..f1bded993edc 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -160,16 +160,13 @@ static int lan743x_csr_init(struct lan743x_adapter *adapter) { struct lan743x_csr *csr = &adapter->csr; resource_size_t bar_start, bar_length; - int result; bar_start = pci_resource_start(adapter->pdev, 0); bar_length = pci_resource_len(adapter->pdev, 0); csr->csr_address = devm_ioremap(&adapter->pdev->dev, bar_start, bar_length); - if (!csr->csr_address) { - result = -ENOMEM; - goto clean_up; - } + if (!csr->csr_address) + return -ENOMEM; csr->id_rev = lan743x_csr_read(adapter, ID_REV); csr->fpga_rev = lan743x_csr_read(adapter, FPGA_REV); @@ -177,10 +174,8 @@ static int lan743x_csr_init(struct lan743x_adapter *adapter) "ID_REV = 0x%08X, FPGA_REV = %d.%d\n", csr->id_rev, FPGA_REV_GET_MAJOR_(csr->fpga_rev), FPGA_REV_GET_MINOR_(csr->fpga_rev)); - if (!ID_REV_IS_VALID_CHIP_ID_(csr->id_rev)) { - result = -ENODEV; - goto clean_up; - } + if (!ID_REV_IS_VALID_CHIP_ID_(csr->id_rev)) + return -ENODEV; csr->flags = LAN743X_CSR_FLAG_SUPPORTS_INTR_AUTO_SET_CLR; switch (csr->id_rev & ID_REV_CHIP_REV_MASK_) { @@ -193,12 +188,7 @@ static int lan743x_csr_init(struct lan743x_adapter *adapter) break; } - result = lan743x_csr_light_reset(adapter); - if (result) - goto clean_up; - return 0; -clean_up: - return result; + return lan743x_csr_light_reset(adapter); } static void lan743x_intr_software_isr(struct lan743x_adapter *adapter) diff --git a/drivers/net/ethernet/microchip/lan966x/Kconfig b/drivers/net/ethernet/microchip/lan966x/Kconfig index 571e6d4da1e9..f9ebffc04eb8 100644 --- a/drivers/net/ethernet/microchip/lan966x/Kconfig +++ b/drivers/net/ethernet/microchip/lan966x/Kconfig @@ -10,3 +10,14 @@ config LAN966X_SWITCH select VCAP help This driver supports the Lan966x network switch device. + +config LAN966X_DCB + bool "Data Center Bridging (DCB) support" + depends on LAN966X_SWITCH && DCB + default y + help + Say Y here if you want to use Data Center Bridging (DCB) in the + driver. This can be used to assign priority to traffic, based on + DSCP and PCP. + + If unsure, set to Y. diff --git a/drivers/net/ethernet/microchip/lan966x/Makefile b/drivers/net/ethernet/microchip/lan966x/Makefile index 7b0cda4ffa6b..3b6ac331691d 100644 --- a/drivers/net/ethernet/microchip/lan966x/Makefile +++ b/drivers/net/ethernet/microchip/lan966x/Makefile @@ -15,6 +15,7 @@ lan966x-switch-objs := lan966x_main.o lan966x_phylink.o lan966x_port.o \ lan966x_xdp.o lan966x_vcap_impl.o lan966x_vcap_ag_api.o \ lan966x_tc_flower.o lan966x_goto.o +lan966x-switch-$(CONFIG_LAN966X_DCB) += lan966x_dcb.o lan966x-switch-$(CONFIG_DEBUG_FS) += lan966x_vcap_debugfs.o # Provide include files diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_dcb.c b/drivers/net/ethernet/microchip/lan966x/lan966x_dcb.c new file mode 100644 index 000000000000..ed2d96d7908e --- /dev/null +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_dcb.c @@ -0,0 +1,365 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include "lan966x_main.h" + +enum lan966x_dcb_apptrust_values { + LAN966X_DCB_APPTRUST_EMPTY, + LAN966X_DCB_APPTRUST_DSCP, + LAN966X_DCB_APPTRUST_PCP, + LAN966X_DCB_APPTRUST_DSCP_PCP, + __LAN966X_DCB_APPTRUST_MAX +}; + +static const struct lan966x_dcb_apptrust { + u8 selectors[IEEE_8021QAZ_APP_SEL_MAX + 1]; + int nselectors; +} *lan966x_port_apptrust[NUM_PHYS_PORTS]; + +static const char *lan966x_dcb_apptrust_names[__LAN966X_DCB_APPTRUST_MAX] = { + [LAN966X_DCB_APPTRUST_EMPTY] = "empty", + [LAN966X_DCB_APPTRUST_DSCP] = "dscp", + [LAN966X_DCB_APPTRUST_PCP] = "pcp", + [LAN966X_DCB_APPTRUST_DSCP_PCP] = "dscp pcp" +}; + +/* Lan966x supported apptrust policies */ +static const struct lan966x_dcb_apptrust + lan966x_dcb_apptrust_policies[__LAN966X_DCB_APPTRUST_MAX] = { + /* Empty *must* be first */ + [LAN966X_DCB_APPTRUST_EMPTY] = { { 0 }, 0 }, + [LAN966X_DCB_APPTRUST_DSCP] = { { IEEE_8021QAZ_APP_SEL_DSCP }, 1 }, + [LAN966X_DCB_APPTRUST_PCP] = { { DCB_APP_SEL_PCP }, 1 }, + [LAN966X_DCB_APPTRUST_DSCP_PCP] = { { IEEE_8021QAZ_APP_SEL_DSCP, + DCB_APP_SEL_PCP }, 2 }, +}; + +static bool lan966x_dcb_apptrust_contains(int portno, u8 selector) +{ + const struct lan966x_dcb_apptrust *conf = lan966x_port_apptrust[portno]; + + for (int i = 0; i < conf->nselectors; i++) + if (conf->selectors[i] == selector) + return true; + + return false; +} + +static void lan966x_dcb_app_update(struct net_device *dev) +{ + struct dcb_ieee_app_prio_map dscp_rewr_map = {0}; + struct dcb_rewr_prio_pcp_map pcp_rewr_map = {0}; + struct lan966x_port *port = netdev_priv(dev); + struct lan966x_port_qos qos = {0}; + struct dcb_app app_itr; + bool dscp_rewr = false; + bool pcp_rewr = false; + + /* Get pcp ingress mapping */ + for (int i = 0; i < ARRAY_SIZE(qos.pcp.map); i++) { + app_itr.selector = DCB_APP_SEL_PCP; + app_itr.protocol = i; + qos.pcp.map[i] = dcb_getapp(dev, &app_itr); + } + + /* Get dscp ingress mapping */ + for (int i = 0; i < ARRAY_SIZE(qos.dscp.map); i++) { + app_itr.selector = IEEE_8021QAZ_APP_SEL_DSCP; + app_itr.protocol = i; + qos.dscp.map[i] = dcb_getapp(dev, &app_itr); + } + + /* Get default prio */ + qos.default_prio = dcb_ieee_getapp_default_prio_mask(dev); + if (qos.default_prio) + qos.default_prio = fls(qos.default_prio) - 1; + + /* Get pcp rewrite mapping */ + dcb_getrewr_prio_pcp_mask_map(dev, &pcp_rewr_map); + for (int i = 0; i < ARRAY_SIZE(pcp_rewr_map.map); i++) { + if (!pcp_rewr_map.map[i]) + continue; + + pcp_rewr = true; + qos.pcp_rewr.map[i] = fls(pcp_rewr_map.map[i]) - 1; + } + + /* Get dscp rewrite mapping */ + dcb_getrewr_prio_dscp_mask_map(dev, &dscp_rewr_map); + for (int i = 0; i < ARRAY_SIZE(dscp_rewr_map.map); i++) { + if (!dscp_rewr_map.map[i]) + continue; + + dscp_rewr = true; + qos.dscp_rewr.map[i] = fls64(dscp_rewr_map.map[i]) - 1; + } + + /* Enable use of pcp for queue classification */ + if (lan966x_dcb_apptrust_contains(port->chip_port, DCB_APP_SEL_PCP)) { + qos.pcp.enable = true; + + if (pcp_rewr) + qos.pcp_rewr.enable = true; + } + + /* Enable use of dscp for queue classification */ + if (lan966x_dcb_apptrust_contains(port->chip_port, IEEE_8021QAZ_APP_SEL_DSCP)) { + qos.dscp.enable = true; + + if (dscp_rewr) + qos.dscp_rewr.enable = true; + } + + lan966x_port_qos_set(port, &qos); +} + +/* DSCP mapping is global for all ports, so set and delete app entries are + * replicated for each port. + */ +static int lan966x_dcb_ieee_dscp_setdel(struct net_device *dev, + struct dcb_app *app, + int (*setdel)(struct net_device *, + struct dcb_app *)) +{ + struct lan966x_port *port = netdev_priv(dev); + struct lan966x *lan966x = port->lan966x; + int err; + + for (int i = 0; i < NUM_PHYS_PORTS; i++) { + port = lan966x->ports[i]; + if (!port) + continue; + + err = setdel(port->dev, app); + if (err) + return err; + } + + return 0; +} + +static int lan966x_dcb_app_validate(struct net_device *dev, + const struct dcb_app *app) +{ + int err = 0; + + switch (app->selector) { + /* Default priority checks */ + case IEEE_8021QAZ_APP_SEL_ETHERTYPE: + if (app->protocol) + err = -EINVAL; + else if (app->priority >= NUM_PRIO_QUEUES) + err = -ERANGE; + break; + /* Dscp checks */ + case IEEE_8021QAZ_APP_SEL_DSCP: + if (app->protocol >= LAN966X_PORT_QOS_DSCP_COUNT) + err = -EINVAL; + else if (app->priority >= NUM_PRIO_QUEUES) + err = -ERANGE; + break; + /* Pcp checks */ + case DCB_APP_SEL_PCP: + if (app->protocol >= LAN966X_PORT_QOS_PCP_DEI_COUNT) + err = -EINVAL; + else if (app->priority >= NUM_PRIO_QUEUES) + err = -ERANGE; + break; + default: + err = -EINVAL; + break; + } + + if (err) + netdev_err(dev, "Invalid entry: %d:%d\n", app->protocol, + app->priority); + + return err; +} + +static int lan966x_dcb_ieee_delapp(struct net_device *dev, struct dcb_app *app) +{ + int err; + + if (app->selector == IEEE_8021QAZ_APP_SEL_DSCP) + err = lan966x_dcb_ieee_dscp_setdel(dev, app, dcb_ieee_delapp); + else + err = dcb_ieee_delapp(dev, app); + + if (err) + return err; + + lan966x_dcb_app_update(dev); + + return 0; +} + +static int lan966x_dcb_ieee_setapp(struct net_device *dev, struct dcb_app *app) +{ + struct dcb_app app_itr; + int err; + u8 prio; + + err = lan966x_dcb_app_validate(dev, app); + if (err) + return err; + + /* Delete current mapping, if it exists */ + prio = dcb_getapp(dev, app); + if (prio) { + app_itr = *app; + app_itr.priority = prio; + lan966x_dcb_ieee_delapp(dev, &app_itr); + } + + if (app->selector == IEEE_8021QAZ_APP_SEL_DSCP) + err = lan966x_dcb_ieee_dscp_setdel(dev, app, dcb_ieee_setapp); + else + err = dcb_ieee_setapp(dev, app); + + if (err) + return err; + + lan966x_dcb_app_update(dev); + + return 0; +} + +static int lan966x_dcb_apptrust_validate(struct net_device *dev, + u8 *selectors, + int nselectors) +{ + for (int i = 0; i < ARRAY_SIZE(lan966x_dcb_apptrust_policies); i++) { + bool match; + + if (lan966x_dcb_apptrust_policies[i].nselectors != nselectors) + continue; + + match = true; + for (int j = 0; j < nselectors; j++) { + if (lan966x_dcb_apptrust_policies[i].selectors[j] != + *(selectors + j)) { + match = false; + break; + } + } + if (match) + return i; + } + + netdev_err(dev, "Valid apptrust configurations are:\n"); + for (int i = 0; i < ARRAY_SIZE(lan966x_dcb_apptrust_names); i++) + pr_info("order: %s\n", lan966x_dcb_apptrust_names[i]); + + return -EOPNOTSUPP; +} + +static int lan966x_dcb_setapptrust(struct net_device *dev, + u8 *selectors, + int nselectors) +{ + struct lan966x_port *port = netdev_priv(dev); + int idx; + + idx = lan966x_dcb_apptrust_validate(dev, selectors, nselectors); + if (idx < 0) + return idx; + + lan966x_port_apptrust[port->chip_port] = &lan966x_dcb_apptrust_policies[idx]; + lan966x_dcb_app_update(dev); + + return 0; +} + +static int lan966x_dcb_getapptrust(struct net_device *dev, u8 *selectors, + int *nselectors) +{ + struct lan966x_port *port = netdev_priv(dev); + const struct lan966x_dcb_apptrust *trust; + + trust = lan966x_port_apptrust[port->chip_port]; + + memcpy(selectors, trust->selectors, trust->nselectors); + *nselectors = trust->nselectors; + + return 0; +} + +static int lan966x_dcb_delrewr(struct net_device *dev, struct dcb_app *app) +{ + int err; + + if (app->selector == IEEE_8021QAZ_APP_SEL_DSCP) + err = lan966x_dcb_ieee_dscp_setdel(dev, app, dcb_delrewr); + else + err = dcb_delrewr(dev, app); + + if (err < 0) + return err; + + lan966x_dcb_app_update(dev); + + return 0; +} + +static int lan966x_dcb_setrewr(struct net_device *dev, struct dcb_app *app) +{ + struct dcb_app app_itr; + u16 proto; + int err; + + err = lan966x_dcb_app_validate(dev, app); + if (err) + goto out; + + /* Delete current mapping, if it exists. */ + proto = dcb_getrewr(dev, app); + if (proto) { + app_itr = *app; + app_itr.protocol = proto; + lan966x_dcb_delrewr(dev, &app_itr); + } + + if (app->selector == IEEE_8021QAZ_APP_SEL_DSCP) + err = lan966x_dcb_ieee_dscp_setdel(dev, app, dcb_setrewr); + else + err = dcb_setrewr(dev, app); + + if (err) + goto out; + + lan966x_dcb_app_update(dev); + +out: + return err; +} + +static const struct dcbnl_rtnl_ops lan966x_dcbnl_ops = { + .ieee_setapp = lan966x_dcb_ieee_setapp, + .ieee_delapp = lan966x_dcb_ieee_delapp, + .dcbnl_setapptrust = lan966x_dcb_setapptrust, + .dcbnl_getapptrust = lan966x_dcb_getapptrust, + .dcbnl_setrewr = lan966x_dcb_setrewr, + .dcbnl_delrewr = lan966x_dcb_delrewr, +}; + +void lan966x_dcb_init(struct lan966x *lan966x) +{ + for (int p = 0; p < lan966x->num_phys_ports; ++p) { + struct lan966x_port *port; + + port = lan966x->ports[p]; + if (!port) + continue; + + port->dev->dcbnl_ops = &lan966x_dcbnl_ops; + + lan966x_port_apptrust[port->chip_port] = + &lan966x_dcb_apptrust_policies[LAN966X_DCB_APPTRUST_DSCP_PCP]; + + /* Enable DSCP classification based on classified QoS class and + * DP, for all DSCP values, for all ports. + */ + lan966x_port_qos_dscp_rewr_mode_set(port, + LAN966X_PORT_QOS_REWR_DSCP_ALL); + } +} diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c index 2b6e046e1d10..f6931dfb3e68 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c @@ -1039,6 +1039,16 @@ static int lan966x_reset_switch(struct lan966x *lan966x) reset_control_reset(switch_reset); + /* Don't reinitialize the switch core, if it is already initialized. In + * case it is initialized twice, some pointers inside the queue system + * in HW will get corrupted and then after a while the queue system gets + * full and no traffic is passing through the switch. The issue is seen + * when loading and unloading the driver and sending traffic through the + * switch. + */ + if (lan_rd(lan966x, SYS_RESET_CFG) & SYS_RESET_CFG_CORE_ENA) + return 0; + lan_wr(SYS_RESET_CFG_CORE_ENA_SET(0), lan966x, SYS_RESET_CFG); lan_wr(SYS_RAM_INIT_RAM_INIT_SET(1), lan966x, SYS_RAM_INIT); ret = readx_poll_timeout(lan966x_ram_init, lan966x, @@ -1213,6 +1223,8 @@ static int lan966x_probe(struct platform_device *pdev) if (err) goto cleanup_fdma; + lan966x_dcb_init(lan966x); + return 0; cleanup_fdma: diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h index 882d5a08e7d5..27f272831ea5 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h @@ -104,6 +104,22 @@ #define LAN966X_VCAP_CID_ES0_L0 VCAP_CID_EGRESS_L0 /* ES0 lookup 0 */ #define LAN966X_VCAP_CID_ES0_MAX (VCAP_CID_EGRESS_L1 - 1) /* ES0 Max */ +#define LAN966X_PORT_QOS_PCP_COUNT 8 +#define LAN966X_PORT_QOS_DEI_COUNT 8 +#define LAN966X_PORT_QOS_PCP_DEI_COUNT \ + (LAN966X_PORT_QOS_PCP_COUNT + LAN966X_PORT_QOS_DEI_COUNT) + +#define LAN966X_PORT_QOS_DSCP_COUNT 64 + +/* Port PCP rewrite mode */ +#define LAN966X_PORT_REW_TAG_CTRL_CLASSIFIED 0 +#define LAN966X_PORT_REW_TAG_CTRL_MAPPED 2 + +/* Port DSCP rewrite mode */ +#define LAN966X_PORT_REW_DSCP_FRAME 0 +#define LAN966X_PORT_REW_DSCP_ANALIZER 1 +#define LAN966X_PORT_QOS_REWR_DSCP_ALL 3 + /* MAC table entry types. * ENTRYTYPE_NORMAL is subject to aging. * ENTRYTYPE_LOCKED is not subject to aging. @@ -392,6 +408,34 @@ struct lan966x_port_tc { struct flow_stats mirror_stat; }; +struct lan966x_port_qos_pcp { + u8 map[LAN966X_PORT_QOS_PCP_DEI_COUNT]; + bool enable; +}; + +struct lan966x_port_qos_dscp { + u8 map[LAN966X_PORT_QOS_DSCP_COUNT]; + bool enable; +}; + +struct lan966x_port_qos_pcp_rewr { + u16 map[NUM_PRIO_QUEUES]; + bool enable; +}; + +struct lan966x_port_qos_dscp_rewr { + u16 map[LAN966X_PORT_QOS_DSCP_COUNT]; + bool enable; +}; + +struct lan966x_port_qos { + struct lan966x_port_qos_pcp pcp; + struct lan966x_port_qos_dscp dscp; + struct lan966x_port_qos_pcp_rewr pcp_rewr; + struct lan966x_port_qos_dscp_rewr dscp_rewr; + u8 default_prio; +}; + struct lan966x_port { struct net_device *dev; struct lan966x *lan966x; @@ -456,6 +500,11 @@ int lan966x_port_pcs_set(struct lan966x_port *port, struct lan966x_port_config *config); void lan966x_port_init(struct lan966x_port *port); +void lan966x_port_qos_set(struct lan966x_port *port, + struct lan966x_port_qos *qos); +void lan966x_port_qos_dscp_rewr_mode_set(struct lan966x_port *port, + int mode); + int lan966x_mac_ip_learn(struct lan966x *lan966x, bool cpu_copy, const unsigned char mac[ETH_ALEN], @@ -680,6 +729,14 @@ int lan966x_goto_port_del(struct lan966x_port *port, unsigned long goto_id, struct netlink_ext_ack *extack); +#ifdef CONFIG_LAN966X_DCB +void lan966x_dcb_init(struct lan966x *lan966x); +#else +static inline void lan966x_dcb_init(struct lan966x *lan966x) +{ +} +#endif + static inline void __iomem *lan_addr(void __iomem *base[], int id, int tinst, int tcnt, int gbase, int ginst, diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_port.c b/drivers/net/ethernet/microchip/lan966x/lan966x_port.c index 0050fcb988b7..92108d354051 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_port.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_port.c @@ -394,6 +394,155 @@ int lan966x_port_pcs_set(struct lan966x_port *port, return 0; } +static void lan966x_port_qos_pcp_set(struct lan966x_port *port, + struct lan966x_port_qos_pcp *qos) +{ + u8 *pcp_itr = qos->map; + u8 pcp, dp; + + lan_rmw(ANA_QOS_CFG_QOS_PCP_ENA_SET(qos->enable), + ANA_QOS_CFG_QOS_PCP_ENA, + port->lan966x, ANA_QOS_CFG(port->chip_port)); + + /* Map PCP and DEI to priority */ + for (int i = 0; i < ARRAY_SIZE(qos->map); i++) { + pcp = *(pcp_itr + i); + dp = (i < LAN966X_PORT_QOS_PCP_COUNT) ? 0 : 1; + + lan_rmw(ANA_PCP_DEI_CFG_QOS_PCP_DEI_VAL_SET(pcp) | + ANA_PCP_DEI_CFG_DP_PCP_DEI_VAL_SET(dp), + ANA_PCP_DEI_CFG_QOS_PCP_DEI_VAL | + ANA_PCP_DEI_CFG_DP_PCP_DEI_VAL, + port->lan966x, + ANA_PCP_DEI_CFG(port->chip_port, i)); + } +} + +static void lan966x_port_qos_dscp_set(struct lan966x_port *port, + struct lan966x_port_qos_dscp *qos) +{ + struct lan966x *lan966x = port->lan966x; + + /* Enable/disable dscp for qos classification. */ + lan_rmw(ANA_QOS_CFG_QOS_DSCP_ENA_SET(qos->enable), + ANA_QOS_CFG_QOS_DSCP_ENA, + lan966x, ANA_QOS_CFG(port->chip_port)); + + /* Map each dscp value to priority and dp */ + for (int i = 0; i < ARRAY_SIZE(qos->map); i++) + lan_rmw(ANA_DSCP_CFG_DP_DSCP_VAL_SET(0) | + ANA_DSCP_CFG_QOS_DSCP_VAL_SET(*(qos->map + i)), + ANA_DSCP_CFG_DP_DSCP_VAL | + ANA_DSCP_CFG_QOS_DSCP_VAL, + lan966x, ANA_DSCP_CFG(i)); + + /* Set per-dscp trust */ + for (int i = 0; i < ARRAY_SIZE(qos->map); i++) + lan_rmw(ANA_DSCP_CFG_DSCP_TRUST_ENA_SET(qos->enable), + ANA_DSCP_CFG_DSCP_TRUST_ENA, + lan966x, ANA_DSCP_CFG(i)); +} + +static int lan966x_port_qos_default_set(struct lan966x_port *port, + struct lan966x_port_qos *qos) +{ + /* Set default prio and dp level */ + lan_rmw(ANA_QOS_CFG_DP_DEFAULT_VAL_SET(0) | + ANA_QOS_CFG_QOS_DEFAULT_VAL_SET(qos->default_prio), + ANA_QOS_CFG_DP_DEFAULT_VAL | + ANA_QOS_CFG_QOS_DEFAULT_VAL, + port->lan966x, ANA_QOS_CFG(port->chip_port)); + + /* Set default pcp and dei for untagged frames */ + lan_rmw(ANA_VLAN_CFG_VLAN_DEI_SET(0) | + ANA_VLAN_CFG_VLAN_PCP_SET(0), + ANA_VLAN_CFG_VLAN_DEI | + ANA_VLAN_CFG_VLAN_PCP, + port->lan966x, ANA_VLAN_CFG(port->chip_port)); + + return 0; +} + +static void lan966x_port_qos_pcp_rewr_set(struct lan966x_port *port, + struct lan966x_port_qos_pcp_rewr *qos) +{ + u8 mode = LAN966X_PORT_REW_TAG_CTRL_CLASSIFIED; + u8 pcp, dei; + + if (qos->enable) + mode = LAN966X_PORT_REW_TAG_CTRL_MAPPED; + + /* Map the values only if it is enabled otherwise will be the classified + * value + */ + lan_rmw(REW_TAG_CFG_TAG_PCP_CFG_SET(mode) | + REW_TAG_CFG_TAG_DEI_CFG_SET(mode), + REW_TAG_CFG_TAG_PCP_CFG | + REW_TAG_CFG_TAG_DEI_CFG, + port->lan966x, REW_TAG_CFG(port->chip_port)); + + /* Map each value to pcp and dei */ + for (int i = 0; i < ARRAY_SIZE(qos->map); i++) { + pcp = qos->map[i]; + if (pcp > LAN966X_PORT_QOS_PCP_COUNT) + dei = 1; + else + dei = 0; + + lan_rmw(REW_PCP_DEI_CFG_DEI_QOS_VAL_SET(dei) | + REW_PCP_DEI_CFG_PCP_QOS_VAL_SET(pcp), + REW_PCP_DEI_CFG_DEI_QOS_VAL | + REW_PCP_DEI_CFG_PCP_QOS_VAL, + port->lan966x, + REW_PCP_DEI_CFG(port->chip_port, + i + dei * LAN966X_PORT_QOS_PCP_COUNT)); + } +} + +static void lan966x_port_qos_dscp_rewr_set(struct lan966x_port *port, + struct lan966x_port_qos_dscp_rewr *qos) +{ + u16 dscp; + u8 mode; + + if (qos->enable) + mode = LAN966X_PORT_REW_DSCP_ANALIZER; + else + mode = LAN966X_PORT_REW_DSCP_FRAME; + + /* Enable the rewrite otherwise will use the values from the frame */ + lan_rmw(REW_DSCP_CFG_DSCP_REWR_CFG_SET(mode), + REW_DSCP_CFG_DSCP_REWR_CFG, + port->lan966x, REW_DSCP_CFG(port->chip_port)); + + /* Map each classified Qos class and DP to classified DSCP value */ + for (int i = 0; i < ARRAY_SIZE(qos->map); i++) { + dscp = qos->map[i]; + + lan_rmw(ANA_DSCP_REWR_CFG_DSCP_QOS_REWR_VAL_SET(dscp), + ANA_DSCP_REWR_CFG_DSCP_QOS_REWR_VAL, + port->lan966x, ANA_DSCP_REWR_CFG(i)); + } +} + +void lan966x_port_qos_dscp_rewr_mode_set(struct lan966x_port *port, + int mode) +{ + lan_rmw(ANA_QOS_CFG_DSCP_REWR_CFG_SET(mode), + ANA_QOS_CFG_DSCP_REWR_CFG, + port->lan966x, ANA_QOS_CFG(port->chip_port)); +} + +void lan966x_port_qos_set(struct lan966x_port *port, + struct lan966x_port_qos *qos) +{ + lan966x_port_qos_pcp_set(port, &qos->pcp); + lan966x_port_qos_dscp_set(port, &qos->dscp); + lan966x_port_qos_default_set(port, qos); + lan966x_port_qos_pcp_rewr_set(port, &qos->pcp_rewr); + lan966x_port_qos_dscp_rewr_set(port, &qos->dscp_rewr); +} + void lan966x_port_init(struct lan966x_port *port) { struct lan966x_port_config *config = &port->config; diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_regs.h b/drivers/net/ethernet/microchip/lan966x/lan966x_regs.h index 222039180276..4b553927d2e0 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_regs.h +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_regs.h @@ -283,6 +283,18 @@ enum lan966x_target { #define ANA_VLAN_CFG_VLAN_POP_CNT_GET(x)\ FIELD_GET(ANA_VLAN_CFG_VLAN_POP_CNT, x) +#define ANA_VLAN_CFG_VLAN_PCP GENMASK(15, 13) +#define ANA_VLAN_CFG_VLAN_PCP_SET(x)\ + FIELD_PREP(ANA_VLAN_CFG_VLAN_PCP, x) +#define ANA_VLAN_CFG_VLAN_PCP_GET(x)\ + FIELD_GET(ANA_VLAN_CFG_VLAN_PCP, x) + +#define ANA_VLAN_CFG_VLAN_DEI BIT(12) +#define ANA_VLAN_CFG_VLAN_DEI_SET(x)\ + FIELD_PREP(ANA_VLAN_CFG_VLAN_DEI, x) +#define ANA_VLAN_CFG_VLAN_DEI_GET(x)\ + FIELD_GET(ANA_VLAN_CFG_VLAN_DEI, x) + #define ANA_VLAN_CFG_VLAN_VID GENMASK(11, 0) #define ANA_VLAN_CFG_VLAN_VID_SET(x)\ FIELD_PREP(ANA_VLAN_CFG_VLAN_VID, x) @@ -316,6 +328,39 @@ enum lan966x_target { #define ANA_DROP_CFG_DROP_MC_SMAC_ENA_GET(x)\ FIELD_GET(ANA_DROP_CFG_DROP_MC_SMAC_ENA, x) +/* ANA:PORT:QOS_CFG */ +#define ANA_QOS_CFG(g) __REG(TARGET_ANA, 0, 1, 28672, g, 9, 128, 8, 0, 1, 4) + +#define ANA_QOS_CFG_DP_DEFAULT_VAL BIT(8) +#define ANA_QOS_CFG_DP_DEFAULT_VAL_SET(x)\ + FIELD_PREP(ANA_QOS_CFG_DP_DEFAULT_VAL, x) +#define ANA_QOS_CFG_DP_DEFAULT_VAL_GET(x)\ + FIELD_GET(ANA_QOS_CFG_DP_DEFAULT_VAL, x) + +#define ANA_QOS_CFG_QOS_DEFAULT_VAL GENMASK(7, 5) +#define ANA_QOS_CFG_QOS_DEFAULT_VAL_SET(x)\ + FIELD_PREP(ANA_QOS_CFG_QOS_DEFAULT_VAL, x) +#define ANA_QOS_CFG_QOS_DEFAULT_VAL_GET(x)\ + FIELD_GET(ANA_QOS_CFG_QOS_DEFAULT_VAL, x) + +#define ANA_QOS_CFG_QOS_DSCP_ENA BIT(4) +#define ANA_QOS_CFG_QOS_DSCP_ENA_SET(x)\ + FIELD_PREP(ANA_QOS_CFG_QOS_DSCP_ENA, x) +#define ANA_QOS_CFG_QOS_DSCP_ENA_GET(x)\ + FIELD_GET(ANA_QOS_CFG_QOS_DSCP_ENA, x) + +#define ANA_QOS_CFG_QOS_PCP_ENA BIT(3) +#define ANA_QOS_CFG_QOS_PCP_ENA_SET(x)\ + FIELD_PREP(ANA_QOS_CFG_QOS_PCP_ENA, x) +#define ANA_QOS_CFG_QOS_PCP_ENA_GET(x)\ + FIELD_GET(ANA_QOS_CFG_QOS_PCP_ENA, x) + +#define ANA_QOS_CFG_DSCP_REWR_CFG GENMASK(1, 0) +#define ANA_QOS_CFG_DSCP_REWR_CFG_SET(x)\ + FIELD_PREP(ANA_QOS_CFG_DSCP_REWR_CFG, x) +#define ANA_QOS_CFG_DSCP_REWR_CFG_GET(x)\ + FIELD_GET(ANA_QOS_CFG_DSCP_REWR_CFG, x) + /* ANA:PORT:VCAP_CFG */ #define ANA_VCAP_CFG(g) __REG(TARGET_ANA, 0, 1, 28672, g, 9, 128, 12, 0, 1, 4) @@ -415,6 +460,21 @@ enum lan966x_target { #define ANA_VCAP_S2_CFG_OAM_DIS_GET(x)\ FIELD_GET(ANA_VCAP_S2_CFG_OAM_DIS, x) +/* ANA:PORT:QOS_PCP_DEI_MAP_CFG */ +#define ANA_PCP_DEI_CFG(g, r) __REG(TARGET_ANA, 0, 1, 28672, g, 9, 128, 32, r, 16, 4) + +#define ANA_PCP_DEI_CFG_DP_PCP_DEI_VAL BIT(3) +#define ANA_PCP_DEI_CFG_DP_PCP_DEI_VAL_SET(x)\ + FIELD_PREP(ANA_PCP_DEI_CFG_DP_PCP_DEI_VAL, x) +#define ANA_PCP_DEI_CFG_DP_PCP_DEI_VAL_GET(x)\ + FIELD_GET(ANA_PCP_DEI_CFG_DP_PCP_DEI_VAL, x) + +#define ANA_PCP_DEI_CFG_QOS_PCP_DEI_VAL GENMASK(2, 0) +#define ANA_PCP_DEI_CFG_QOS_PCP_DEI_VAL_SET(x)\ + FIELD_PREP(ANA_PCP_DEI_CFG_QOS_PCP_DEI_VAL, x) +#define ANA_PCP_DEI_CFG_QOS_PCP_DEI_VAL_GET(x)\ + FIELD_GET(ANA_PCP_DEI_CFG_QOS_PCP_DEI_VAL, x) + /* ANA:PORT:CPU_FWD_CFG */ #define ANA_CPU_FWD_CFG(g) __REG(TARGET_ANA, 0, 1, 28672, g, 9, 128, 96, 0, 1, 4) @@ -478,6 +538,15 @@ enum lan966x_target { #define ANA_PORT_CFG_PORTID_VAL_GET(x)\ FIELD_GET(ANA_PORT_CFG_PORTID_VAL, x) +/* ANA:COMMON:DSCP_REWR_CFG */ +#define ANA_DSCP_REWR_CFG(r) __REG(TARGET_ANA, 0, 1, 31232, 0, 1, 552, 332, r, 16, 4) + +#define ANA_DSCP_REWR_CFG_DSCP_QOS_REWR_VAL GENMASK(5, 0) +#define ANA_DSCP_REWR_CFG_DSCP_QOS_REWR_VAL_SET(x)\ + FIELD_PREP(ANA_DSCP_REWR_CFG_DSCP_QOS_REWR_VAL, x) +#define ANA_DSCP_REWR_CFG_DSCP_QOS_REWR_VAL_GET(x)\ + FIELD_GET(ANA_DSCP_REWR_CFG_DSCP_QOS_REWR_VAL, x) + /* ANA:PORT:POL_CFG */ #define ANA_POL_CFG(g) __REG(TARGET_ANA, 0, 1, 28672, g, 9, 128, 116, 0, 1, 4) @@ -547,6 +616,33 @@ enum lan966x_target { #define ANA_AGGR_CFG_AC_IP4_TCPUDP_ENA_GET(x)\ FIELD_GET(ANA_AGGR_CFG_AC_IP4_TCPUDP_ENA, x) +/* ANA:COMMON:DSCP_CFG */ +#define ANA_DSCP_CFG(r) __REG(TARGET_ANA, 0, 1, 31232, 0, 1, 552, 76, r, 64, 4) + +#define ANA_DSCP_CFG_DP_DSCP_VAL BIT(11) +#define ANA_DSCP_CFG_DP_DSCP_VAL_SET(x)\ + FIELD_PREP(ANA_DSCP_CFG_DP_DSCP_VAL, x) +#define ANA_DSCP_CFG_DP_DSCP_VAL_GET(x)\ + FIELD_GET(ANA_DSCP_CFG_DP_DSCP_VAL, x) + +#define ANA_DSCP_CFG_QOS_DSCP_VAL GENMASK(10, 8) +#define ANA_DSCP_CFG_QOS_DSCP_VAL_SET(x)\ + FIELD_PREP(ANA_DSCP_CFG_QOS_DSCP_VAL, x) +#define ANA_DSCP_CFG_QOS_DSCP_VAL_GET(x)\ + FIELD_GET(ANA_DSCP_CFG_QOS_DSCP_VAL, x) + +#define ANA_DSCP_CFG_DSCP_TRUST_ENA BIT(1) +#define ANA_DSCP_CFG_DSCP_TRUST_ENA_SET(x)\ + FIELD_PREP(ANA_DSCP_CFG_DSCP_TRUST_ENA, x) +#define ANA_DSCP_CFG_DSCP_TRUST_ENA_GET(x)\ + FIELD_GET(ANA_DSCP_CFG_DSCP_TRUST_ENA, x) + +#define ANA_DSCP_CFG_DSCP_REWR_ENA BIT(0) +#define ANA_DSCP_CFG_DSCP_REWR_ENA_SET(x)\ + FIELD_PREP(ANA_DSCP_CFG_DSCP_REWR_ENA, x) +#define ANA_DSCP_CFG_DSCP_REWR_ENA_GET(x)\ + FIELD_GET(ANA_DSCP_CFG_DSCP_REWR_ENA, x) + /* ANA:POL:POL_PIR_CFG */ #define ANA_POL_PIR_CFG(g) __REG(TARGET_ANA, 0, 1, 16384, g, 345, 32, 0, 0, 1, 4) @@ -1468,6 +1564,18 @@ enum lan966x_target { #define REW_TAG_CFG_TAG_TPID_CFG_GET(x)\ FIELD_GET(REW_TAG_CFG_TAG_TPID_CFG, x) +#define REW_TAG_CFG_TAG_PCP_CFG GENMASK(3, 2) +#define REW_TAG_CFG_TAG_PCP_CFG_SET(x)\ + FIELD_PREP(REW_TAG_CFG_TAG_PCP_CFG, x) +#define REW_TAG_CFG_TAG_PCP_CFG_GET(x)\ + FIELD_GET(REW_TAG_CFG_TAG_PCP_CFG, x) + +#define REW_TAG_CFG_TAG_DEI_CFG GENMASK(1, 0) +#define REW_TAG_CFG_TAG_DEI_CFG_SET(x)\ + FIELD_PREP(REW_TAG_CFG_TAG_DEI_CFG, x) +#define REW_TAG_CFG_TAG_DEI_CFG_GET(x)\ + FIELD_GET(REW_TAG_CFG_TAG_DEI_CFG, x) + /* REW:PORT:PORT_CFG */ #define REW_PORT_CFG(g) __REG(TARGET_REW, 0, 1, 0, g, 10, 128, 8, 0, 1, 4) @@ -1483,6 +1591,30 @@ enum lan966x_target { #define REW_PORT_CFG_NO_REWRITE_GET(x)\ FIELD_GET(REW_PORT_CFG_NO_REWRITE, x) +/* REW:PORT:DSCP_CFG */ +#define REW_DSCP_CFG(g) __REG(TARGET_REW, 0, 1, 0, g, 10, 128, 12, 0, 1, 4) + +#define REW_DSCP_CFG_DSCP_REWR_CFG GENMASK(1, 0) +#define REW_DSCP_CFG_DSCP_REWR_CFG_SET(x)\ + FIELD_PREP(REW_DSCP_CFG_DSCP_REWR_CFG, x) +#define REW_DSCP_CFG_DSCP_REWR_CFG_GET(x)\ + FIELD_GET(REW_DSCP_CFG_DSCP_REWR_CFG, x) + +/* REW:PORT:PCP_DEI_QOS_MAP_CFG */ +#define REW_PCP_DEI_CFG(g, r) __REG(TARGET_REW, 0, 1, 0, g, 10, 128, 16, r, 16, 4) + +#define REW_PCP_DEI_CFG_DEI_QOS_VAL BIT(3) +#define REW_PCP_DEI_CFG_DEI_QOS_VAL_SET(x)\ + FIELD_PREP(REW_PCP_DEI_CFG_DEI_QOS_VAL, x) +#define REW_PCP_DEI_CFG_DEI_QOS_VAL_GET(x)\ + FIELD_GET(REW_PCP_DEI_CFG_DEI_QOS_VAL, x) + +#define REW_PCP_DEI_CFG_PCP_QOS_VAL GENMASK(2, 0) +#define REW_PCP_DEI_CFG_PCP_QOS_VAL_SET(x)\ + FIELD_PREP(REW_PCP_DEI_CFG_PCP_QOS_VAL, x) +#define REW_PCP_DEI_CFG_PCP_QOS_VAL_GET(x)\ + FIELD_GET(REW_PCP_DEI_CFG_PCP_QOS_VAL, x) + /* REW:COMMON:STAT_CFG */ #define REW_STAT_CFG __REG(TARGET_REW, 0, 1, 3072, 0, 1, 528, 520, 0, 1, 4) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_tc.c b/drivers/net/ethernet/microchip/lan966x/lan966x_tc.c index cf0cc7562d04..ee652f2d2359 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_tc.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_tc.c @@ -21,8 +21,14 @@ static int lan966x_tc_setup_qdisc_mqprio(struct lan966x_port *port, static int lan966x_tc_setup_qdisc_taprio(struct lan966x_port *port, struct tc_taprio_qopt_offload *taprio) { - return taprio->enable ? lan966x_taprio_add(port, taprio) : - lan966x_taprio_del(port); + switch (taprio->cmd) { + case TAPRIO_CMD_REPLACE: + return lan966x_taprio_add(port, taprio); + case TAPRIO_CMD_DESTROY: + return lan966x_taprio_del(port); + default: + return -EOPNOTSUPP; + } } static int lan966x_tc_setup_qdisc_tbf(struct lan966x_port *port, diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api.c b/drivers/net/ethernet/microchip/vcap/vcap_api.c index 5675b0962bc3..a418ad8e8770 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api.c +++ b/drivers/net/ethernet/microchip/vcap/vcap_api.c @@ -1121,7 +1121,7 @@ static void vcap_copy_to_client_actionfield(struct vcap_rule_internal *ri, vcap_copy_from_w32be(field->data.u128.value, value, field_size, width); break; - }; + } } else { switch (field->ctrl.type) { case VCAP_FIELD_BIT: @@ -1162,7 +1162,7 @@ static void vcap_copy_to_client_actionfield(struct vcap_rule_internal *ri, value, width, field_size); break; - }; + } } } @@ -1236,7 +1236,7 @@ static void vcap_copy_to_client_keyfield(struct vcap_rule_internal *ri, vcap_copy_from_w32be(field->data.u128.mask, mask, field_size, width); break; - }; + } } else { switch (field->ctrl.type) { case VCAP_FIELD_BIT: @@ -1284,7 +1284,7 @@ static void vcap_copy_to_client_keyfield(struct vcap_rule_internal *ri, value, mask, width, field_size); break; - }; + } } } diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 06d6292e09b3..d907727c7b7a 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -1279,8 +1279,6 @@ static void mana_poll_tx_cq(struct mana_cq *cq) if (comp_read < 1) return; - apc->eth_stats.tx_cqes = comp_read; - for (i = 0; i < comp_read; i++) { struct mana_tx_comp_oob *cqe_oob; @@ -1363,8 +1361,6 @@ static void mana_poll_tx_cq(struct mana_cq *cq) WARN_ON_ONCE(1); cq->work_done = pkt_transmitted; - - apc->eth_stats.tx_cqes -= pkt_transmitted; } static void mana_post_pkt_rxq(struct mana_rxq *rxq) @@ -1626,15 +1622,11 @@ static void mana_poll_rx_cq(struct mana_cq *cq) { struct gdma_comp *comp = cq->gdma_comp_buf; struct mana_rxq *rxq = cq->rxq; - struct mana_port_context *apc; int comp_read, i; - apc = netdev_priv(rxq->ndev); - comp_read = mana_gd_poll_cq(cq->gdma_cq, comp, CQE_POLLING_BUFFER); WARN_ON_ONCE(comp_read > CQE_POLLING_BUFFER); - apc->eth_stats.rx_cqes = comp_read; rxq->xdp_flush = false; for (i = 0; i < comp_read; i++) { @@ -1646,8 +1638,6 @@ static void mana_poll_rx_cq(struct mana_cq *cq) return; mana_process_rx_cqe(rxq, cq, &comp[i]); - - apc->eth_stats.rx_cqes--; } if (rxq->xdp_flush) diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c index a64c81410dc1..0dc78679f620 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c @@ -13,11 +13,9 @@ static const struct { } mana_eth_stats[] = { {"stop_queue", offsetof(struct mana_ethtool_stats, stop_queue)}, {"wake_queue", offsetof(struct mana_ethtool_stats, wake_queue)}, - {"tx_cqes", offsetof(struct mana_ethtool_stats, tx_cqes)}, {"tx_cq_err", offsetof(struct mana_ethtool_stats, tx_cqe_err)}, {"tx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, tx_cqe_unknown_type)}, - {"rx_cqes", offsetof(struct mana_ethtool_stats, rx_cqes)}, {"rx_coalesced_err", offsetof(struct mana_ethtool_stats, rx_coalesced_err)}, {"rx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, diff --git a/drivers/net/ethernet/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c index ee052404eb55..e0916afcddfb 100644 --- a/drivers/net/ethernet/mscc/ocelot_flower.c +++ b/drivers/net/ethernet/mscc/ocelot_flower.c @@ -592,6 +592,16 @@ ocelot_flower_parse_key(struct ocelot *ocelot, int port, bool ingress, return -EOPNOTSUPP; } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_META)) { + struct flow_match_meta match; + + flow_rule_match_meta(rule, &match); + if (match.mask->l2_miss) { + NL_SET_ERR_MSG_MOD(extack, "Can't match on \"l2_miss\""); + return -EOPNOTSUPP; + } + } + /* For VCAP ES0 (egress rewriter) we can match on the ingress port */ if (!ingress) { ret = ocelot_flower_parse_indev(ocelot, port, f, filter); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c index bf6bae557158..8c6954c58a88 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c @@ -311,8 +311,6 @@ nfp_devlink_flash_update(struct devlink *devlink, } const struct devlink_ops nfp_devlink_ops = { - .port_split = nfp_devlink_port_split, - .port_unsplit = nfp_devlink_port_unsplit, .sb_pool_get = nfp_devlink_sb_pool_get, .sb_pool_set = nfp_devlink_sb_pool_set, .eswitch_mode_get = nfp_devlink_eswitch_mode_get, @@ -321,6 +319,11 @@ const struct devlink_ops nfp_devlink_ops = { .flash_update = nfp_devlink_flash_update, }; +static const struct devlink_port_ops nfp_devlink_port_ops = { + .port_split = nfp_devlink_port_split, + .port_unsplit = nfp_devlink_port_unsplit, +}; + int nfp_devlink_port_register(struct nfp_app *app, struct nfp_port *port) { struct devlink_port_attrs attrs = {}; @@ -351,7 +354,8 @@ int nfp_devlink_port_register(struct nfp_app *app, struct nfp_port *port) devlink = priv_to_devlink(app->pf); - return devl_port_register(devlink, &port->dl_port, port->eth_id); + return devl_port_register_with_ops(devlink, &port->dl_port, + port->eth_id, &nfp_devlink_port_ops); } void nfp_devlink_port_unregister(struct nfp_port *port) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 62f0bf91d1e1..b7cce746b5c0 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -2418,6 +2418,8 @@ static void nfp_net_rss_init(struct nfp_net *nn) /* Enable IPv4/IPv6 TCP by default */ nn->rss_cfg = NFP_NET_CFG_RSS_IPV4_TCP | NFP_NET_CFG_RSS_IPV6_TCP | + NFP_NET_CFG_RSS_IPV4_UDP | + NFP_NET_CFG_RSS_IPV6_UDP | FIELD_PREP(NFP_NET_CFG_RSS_HFUNC, nn->rss_hfunc) | NFP_NET_CFG_RSS_MASK; } diff --git a/drivers/net/ethernet/netronome/nfp/nic/main.h b/drivers/net/ethernet/netronome/nfp/nic/main.h index 094374df42b8..38b8b10b03cd 100644 --- a/drivers/net/ethernet/netronome/nfp/nic/main.h +++ b/drivers/net/ethernet/netronome/nfp/nic/main.h @@ -8,7 +8,7 @@ #ifdef CONFIG_DCB /* DCB feature definitions */ -#define NFP_NET_MAX_DSCP 4 +#define NFP_NET_MAX_DSCP 64 #define NFP_NET_MAX_TC IEEE_8021QAZ_MAX_TCS #define NFP_NET_MAX_PRIO 8 #define NFP_DCB_CFG_STRIDE 256 diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c index 0605d1ee490d..7a549b834e97 100644 --- a/drivers/net/ethernet/nvidia/forcedeth.c +++ b/drivers/net/ethernet/nvidia/forcedeth.c @@ -6138,6 +6138,7 @@ static int nv_probe(struct pci_dev *pci_dev, const struct pci_device_id *id) return 0; out_error: + nv_mgmt_release_sema(dev); if (phystate_orig) writel(phystate|NVREG_ADAPTCTL_RUNNING, base + NvRegAdapterControl); out_freering: diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/Kconfig b/drivers/net/ethernet/oki-semi/pch_gbe/Kconfig index 4e18b64dceb9..9651cc714ef2 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/Kconfig +++ b/drivers/net/ethernet/oki-semi/pch_gbe/Kconfig @@ -5,7 +5,7 @@ config PCH_GBE tristate "OKI SEMICONDUCTOR IOH(ML7223/ML7831) GbE" - depends on PCI && (X86_32 || COMPILE_TEST) + depends on PCI && (MIPS_GENERIC || X86_32 || COMPILE_TEST) depends on PTP_1588_CLOCK select MII select PTP_1588_CLOCK_PCH diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 2edd6bf64a3c..7776d3bdd459 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -1903,7 +1903,7 @@ void qed_get_vport_stats(struct qed_dev *cdev, struct qed_eth_stats *stats) { u32 i; - if (!cdev) { + if (!cdev || cdev->recov_in_prog) { memset(stats, 0, sizeof(*stats)); return; } diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index f9931ecb7baa..4d83ceebdc49 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -269,6 +269,10 @@ struct qede_dev { #define QEDE_ERR_WARN 3 struct qede_dump_info dump_info; + struct delayed_work periodic_task; + unsigned long stats_coal_ticks; + u32 stats_coal_usecs; + spinlock_t stats_lock; /* lock for vport stats access */ }; enum QEDE_STATE { diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index 374a86b875a3..95820cf1cd6c 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -429,6 +429,8 @@ static void qede_get_ethtool_stats(struct net_device *dev, } } + spin_lock(&edev->stats_lock); + for (i = 0; i < QEDE_NUM_STATS; i++) { if (qede_is_irrelevant_stat(edev, i)) continue; @@ -438,6 +440,8 @@ static void qede_get_ethtool_stats(struct net_device *dev, buf++; } + spin_unlock(&edev->stats_lock); + __qede_unlock(edev); } @@ -829,6 +833,7 @@ out: coal->rx_coalesce_usecs = rx_coal; coal->tx_coalesce_usecs = tx_coal; + coal->stats_block_coalesce_usecs = edev->stats_coal_usecs; return rc; } @@ -842,6 +847,19 @@ int qede_set_coalesce(struct net_device *dev, struct ethtool_coalesce *coal, int i, rc = 0; u16 rxc, txc; + if (edev->stats_coal_usecs != coal->stats_block_coalesce_usecs) { + edev->stats_coal_usecs = coal->stats_block_coalesce_usecs; + if (edev->stats_coal_usecs) { + edev->stats_coal_ticks = usecs_to_jiffies(edev->stats_coal_usecs); + schedule_delayed_work(&edev->periodic_task, 0); + + DP_INFO(edev, "Configured stats coal ticks=%lu jiffies\n", + edev->stats_coal_ticks); + } else { + cancel_delayed_work_sync(&edev->periodic_task); + } + } + if (!netif_running(dev)) { DP_INFO(edev, "Interface is down\n"); return -EINVAL; @@ -2252,7 +2270,8 @@ out: } static const struct ethtool_ops qede_ethtool_ops = { - .supported_coalesce_params = ETHTOOL_COALESCE_USECS, + .supported_coalesce_params = ETHTOOL_COALESCE_USECS | + ETHTOOL_COALESCE_STATS_BLOCK_USECS, .get_link_ksettings = qede_get_link_ksettings, .set_link_ksettings = qede_set_link_ksettings, .get_drvinfo = qede_get_drvinfo, @@ -2303,7 +2322,8 @@ static const struct ethtool_ops qede_ethtool_ops = { }; static const struct ethtool_ops qede_vf_ethtool_ops = { - .supported_coalesce_params = ETHTOOL_COALESCE_USECS, + .supported_coalesce_params = ETHTOOL_COALESCE_USECS | + ETHTOOL_COALESCE_STATS_BLOCK_USECS, .get_link_ksettings = qede_get_link_ksettings, .get_drvinfo = qede_get_drvinfo, .get_msglevel = qede_get_msglevel, diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 4c6c685820e3..4b004a728190 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -307,6 +307,8 @@ void qede_fill_by_demand_stats(struct qede_dev *edev) edev->ops->get_vport_stats(edev->cdev, &stats); + spin_lock(&edev->stats_lock); + p_common->no_buff_discards = stats.common.no_buff_discards; p_common->packet_too_big_discard = stats.common.packet_too_big_discard; p_common->ttl0_discard = stats.common.ttl0_discard; @@ -404,6 +406,8 @@ void qede_fill_by_demand_stats(struct qede_dev *edev) p_ah->tx_1519_to_max_byte_packets = stats.ah.tx_1519_to_max_byte_packets; } + + spin_unlock(&edev->stats_lock); } static void qede_get_stats64(struct net_device *dev, @@ -412,9 +416,10 @@ static void qede_get_stats64(struct net_device *dev, struct qede_dev *edev = netdev_priv(dev); struct qede_stats_common *p_common; - qede_fill_by_demand_stats(edev); p_common = &edev->stats.common; + spin_lock(&edev->stats_lock); + stats->rx_packets = p_common->rx_ucast_pkts + p_common->rx_mcast_pkts + p_common->rx_bcast_pkts; stats->tx_packets = p_common->tx_ucast_pkts + p_common->tx_mcast_pkts + @@ -434,6 +439,8 @@ static void qede_get_stats64(struct net_device *dev, stats->collisions = edev->stats.bb.tx_total_collisions; stats->rx_crc_errors = p_common->rx_crc_errors; stats->rx_frame_errors = p_common->rx_align_errors; + + spin_unlock(&edev->stats_lock); } #ifdef CONFIG_QED_SRIOV @@ -1063,6 +1070,23 @@ static void qede_unlock(struct qede_dev *edev) rtnl_unlock(); } +static void qede_periodic_task(struct work_struct *work) +{ + struct qede_dev *edev = container_of(work, struct qede_dev, + periodic_task.work); + + qede_fill_by_demand_stats(edev); + schedule_delayed_work(&edev->periodic_task, edev->stats_coal_ticks); +} + +static void qede_init_periodic_task(struct qede_dev *edev) +{ + INIT_DELAYED_WORK(&edev->periodic_task, qede_periodic_task); + spin_lock_init(&edev->stats_lock); + edev->stats_coal_usecs = USEC_PER_SEC; + edev->stats_coal_ticks = usecs_to_jiffies(USEC_PER_SEC); +} + static void qede_sp_task(struct work_struct *work) { struct qede_dev *edev = container_of(work, struct qede_dev, @@ -1082,6 +1106,7 @@ static void qede_sp_task(struct work_struct *work) */ if (test_and_clear_bit(QEDE_SP_RECOVERY, &edev->sp_flags)) { + cancel_delayed_work_sync(&edev->periodic_task); #ifdef CONFIG_QED_SRIOV /* SRIOV must be disabled outside the lock to avoid a deadlock. * The recovery of the active VFs is currently not supported. @@ -1272,6 +1297,7 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level, */ INIT_DELAYED_WORK(&edev->sp_task, qede_sp_task); mutex_init(&edev->qede_lock); + qede_init_periodic_task(edev); rc = register_netdev(edev->ndev); if (rc) { @@ -1296,6 +1322,11 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level, edev->rx_copybreak = QEDE_RX_HDR_SIZE; qede_log_probe(edev); + + /* retain user config (for example - after recovery) */ + if (edev->stats_coal_usecs) + schedule_delayed_work(&edev->periodic_task, 0); + return 0; err4: @@ -1364,6 +1395,7 @@ static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode) unregister_netdev(ndev); cancel_delayed_work_sync(&edev->sp_task); + cancel_delayed_work_sync(&edev->periodic_task); edev->ops->common->set_power_state(cdev, PCI_D0); diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index a7e376e7e689..9445f04f8d48 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -616,10 +616,10 @@ struct rtl8169_private { struct work_struct work; } wk; - spinlock_t config25_lock; - spinlock_t mac_ocp_lock; + raw_spinlock_t config25_lock; + raw_spinlock_t mac_ocp_lock; - spinlock_t cfg9346_usage_lock; + raw_spinlock_t cfg9346_usage_lock; int cfg9346_usage_count; unsigned supports_gmii:1; @@ -671,20 +671,20 @@ static void rtl_lock_config_regs(struct rtl8169_private *tp) { unsigned long flags; - spin_lock_irqsave(&tp->cfg9346_usage_lock, flags); + raw_spin_lock_irqsave(&tp->cfg9346_usage_lock, flags); if (!--tp->cfg9346_usage_count) RTL_W8(tp, Cfg9346, Cfg9346_Lock); - spin_unlock_irqrestore(&tp->cfg9346_usage_lock, flags); + raw_spin_unlock_irqrestore(&tp->cfg9346_usage_lock, flags); } static void rtl_unlock_config_regs(struct rtl8169_private *tp) { unsigned long flags; - spin_lock_irqsave(&tp->cfg9346_usage_lock, flags); + raw_spin_lock_irqsave(&tp->cfg9346_usage_lock, flags); if (!tp->cfg9346_usage_count++) RTL_W8(tp, Cfg9346, Cfg9346_Unlock); - spin_unlock_irqrestore(&tp->cfg9346_usage_lock, flags); + raw_spin_unlock_irqrestore(&tp->cfg9346_usage_lock, flags); } static void rtl_pci_commit(struct rtl8169_private *tp) @@ -698,10 +698,10 @@ static void rtl_mod_config2(struct rtl8169_private *tp, u8 clear, u8 set) unsigned long flags; u8 val; - spin_lock_irqsave(&tp->config25_lock, flags); + raw_spin_lock_irqsave(&tp->config25_lock, flags); val = RTL_R8(tp, Config2); RTL_W8(tp, Config2, (val & ~clear) | set); - spin_unlock_irqrestore(&tp->config25_lock, flags); + raw_spin_unlock_irqrestore(&tp->config25_lock, flags); } static void rtl_mod_config5(struct rtl8169_private *tp, u8 clear, u8 set) @@ -709,10 +709,10 @@ static void rtl_mod_config5(struct rtl8169_private *tp, u8 clear, u8 set) unsigned long flags; u8 val; - spin_lock_irqsave(&tp->config25_lock, flags); + raw_spin_lock_irqsave(&tp->config25_lock, flags); val = RTL_R8(tp, Config5); RTL_W8(tp, Config5, (val & ~clear) | set); - spin_unlock_irqrestore(&tp->config25_lock, flags); + raw_spin_unlock_irqrestore(&tp->config25_lock, flags); } static bool rtl_is_8125(struct rtl8169_private *tp) @@ -899,9 +899,9 @@ static void r8168_mac_ocp_write(struct rtl8169_private *tp, u32 reg, u32 data) { unsigned long flags; - spin_lock_irqsave(&tp->mac_ocp_lock, flags); + raw_spin_lock_irqsave(&tp->mac_ocp_lock, flags); __r8168_mac_ocp_write(tp, reg, data); - spin_unlock_irqrestore(&tp->mac_ocp_lock, flags); + raw_spin_unlock_irqrestore(&tp->mac_ocp_lock, flags); } static u16 __r8168_mac_ocp_read(struct rtl8169_private *tp, u32 reg) @@ -919,9 +919,9 @@ static u16 r8168_mac_ocp_read(struct rtl8169_private *tp, u32 reg) unsigned long flags; u16 val; - spin_lock_irqsave(&tp->mac_ocp_lock, flags); + raw_spin_lock_irqsave(&tp->mac_ocp_lock, flags); val = __r8168_mac_ocp_read(tp, reg); - spin_unlock_irqrestore(&tp->mac_ocp_lock, flags); + raw_spin_unlock_irqrestore(&tp->mac_ocp_lock, flags); return val; } @@ -932,10 +932,10 @@ static void r8168_mac_ocp_modify(struct rtl8169_private *tp, u32 reg, u16 mask, unsigned long flags; u16 data; - spin_lock_irqsave(&tp->mac_ocp_lock, flags); + raw_spin_lock_irqsave(&tp->mac_ocp_lock, flags); data = __r8168_mac_ocp_read(tp, reg); __r8168_mac_ocp_write(tp, reg, (data & ~mask) | set); - spin_unlock_irqrestore(&tp->mac_ocp_lock, flags); + raw_spin_unlock_irqrestore(&tp->mac_ocp_lock, flags); } /* Work around a hw issue with RTL8168g PHY, the quirk disables @@ -1420,14 +1420,14 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts) r8168_mac_ocp_modify(tp, 0xc0b6, BIT(0), 0); } - spin_lock_irqsave(&tp->config25_lock, flags); + raw_spin_lock_irqsave(&tp->config25_lock, flags); for (i = 0; i < tmp; i++) { options = RTL_R8(tp, cfg[i].reg) & ~cfg[i].mask; if (wolopts & cfg[i].opt) options |= cfg[i].mask; RTL_W8(tp, cfg[i].reg, options); } - spin_unlock_irqrestore(&tp->config25_lock, flags); + raw_spin_unlock_irqrestore(&tp->config25_lock, flags); switch (tp->mac_version) { case RTL_GIGA_MAC_VER_02 ... RTL_GIGA_MAC_VER_06: @@ -5164,6 +5164,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) int jumbo_max, region, rc; enum mac_version chipset; struct net_device *dev; + u32 txconfig; u16 xid; dev = devm_alloc_etherdev(&pdev->dev, sizeof (*tp)); @@ -5179,9 +5180,9 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) tp->eee_adv = -1; tp->ocp_base = OCP_STD_PHY_BASE; - spin_lock_init(&tp->cfg9346_usage_lock); - spin_lock_init(&tp->config25_lock); - spin_lock_init(&tp->mac_ocp_lock); + raw_spin_lock_init(&tp->cfg9346_usage_lock); + raw_spin_lock_init(&tp->config25_lock); + raw_spin_lock_init(&tp->mac_ocp_lock); dev->tstats = devm_netdev_alloc_pcpu_stats(&pdev->dev, struct pcpu_sw_netstats); @@ -5195,38 +5196,35 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* enable device (incl. PCI PM wakeup and hotplug setup) */ rc = pcim_enable_device(pdev); - if (rc < 0) { - dev_err(&pdev->dev, "enable failure\n"); - return rc; - } + if (rc < 0) + return dev_err_probe(&pdev->dev, rc, "enable failure\n"); if (pcim_set_mwi(pdev) < 0) dev_info(&pdev->dev, "Mem-Wr-Inval unavailable\n"); /* use first MMIO region */ region = ffs(pci_select_bars(pdev, IORESOURCE_MEM)) - 1; - if (region < 0) { - dev_err(&pdev->dev, "no MMIO resource found\n"); - return -ENODEV; - } + if (region < 0) + return dev_err_probe(&pdev->dev, -ENODEV, "no MMIO resource found\n"); rc = pcim_iomap_regions(pdev, BIT(region), KBUILD_MODNAME); - if (rc < 0) { - dev_err(&pdev->dev, "cannot remap MMIO, aborting\n"); - return rc; - } + if (rc < 0) + return dev_err_probe(&pdev->dev, rc, "cannot remap MMIO, aborting\n"); tp->mmio_addr = pcim_iomap_table(pdev)[region]; - xid = (RTL_R32(tp, TxConfig) >> 20) & 0xfcf; + txconfig = RTL_R32(tp, TxConfig); + if (txconfig == ~0U) + return dev_err_probe(&pdev->dev, -EIO, "PCI read failed\n"); + + xid = (txconfig >> 20) & 0xfcf; /* Identify chip attached to board */ chipset = rtl8169_get_mac_version(xid, tp->supports_gmii); - if (chipset == RTL_GIGA_MAC_NONE) { - dev_err(&pdev->dev, "unknown chip XID %03x, contact r8169 maintainers (see MAINTAINERS file)\n", xid); - return -ENODEV; - } - + if (chipset == RTL_GIGA_MAC_NONE) + return dev_err_probe(&pdev->dev, -ENODEV, + "unknown chip XID %03x, contact r8169 maintainers (see MAINTAINERS file)\n", + xid); tp->mac_version = chipset; tp->dash_type = rtl_check_dash(tp); @@ -5246,10 +5244,9 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) rtl_hw_reset(tp); rc = rtl_alloc_irq(tp); - if (rc < 0) { - dev_err(&pdev->dev, "Can't allocate interrupt\n"); - return rc; - } + if (rc < 0) + return dev_err_probe(&pdev->dev, rc, "Can't allocate interrupt\n"); + tp->irq = pci_irq_vector(pdev, 0); INIT_WORK(&tp->wk.work, rtl_task); diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c index 29afaddb598d..aace87139cea 100644 --- a/drivers/net/ethernet/renesas/rswitch.c +++ b/drivers/net/ethernet/renesas/rswitch.c @@ -1485,7 +1485,7 @@ static netdev_tx_t rswitch_start_xmit(struct sk_buff *skb, struct net_device *nd if (rswitch_get_num_cur_queues(gq) >= gq->ring_size - 1) { netif_stop_subqueue(ndev, 0); - return ret; + return NETDEV_TX_BUSY; } if (skb_put_padto(skb, ETH_ZLEN)) diff --git a/drivers/net/ethernet/sfc/ef100_netdev.c b/drivers/net/ethernet/sfc/ef100_netdev.c index d916877b5a9a..274f3a2562ad 100644 --- a/drivers/net/ethernet/sfc/ef100_netdev.c +++ b/drivers/net/ethernet/sfc/ef100_netdev.c @@ -40,19 +40,26 @@ static int ef100_alloc_vis(struct efx_nic *efx, unsigned int *allocated_vis) unsigned int tx_vis = efx->n_tx_channels + efx->n_extra_tx_channels; unsigned int rx_vis = efx->n_rx_channels; unsigned int min_vis, max_vis; + int rc; EFX_WARN_ON_PARANOID(efx->tx_queues_per_channel != 1); tx_vis += efx->n_xdp_channels * efx->xdp_tx_per_channel; max_vis = max(rx_vis, tx_vis); - /* Currently don't handle resource starvation and only accept - * our maximum needs and no less. + /* We require at least a single complete TX channel worth of queues. */ + min_vis = efx->tx_queues_per_channel; + + rc = efx_mcdi_alloc_vis(efx, min_vis, max_vis, + NULL, allocated_vis); + + /* We retry allocating VIs by reallocating channels when we have not + * been able to allocate the maximum VIs. */ - min_vis = max_vis; + if (!rc && *allocated_vis < max_vis) + rc = -EAGAIN; - return efx_mcdi_alloc_vis(efx, min_vis, max_vis, - NULL, allocated_vis); + return rc; } static int ef100_remap_bar(struct efx_nic *efx, int max_vis) @@ -133,9 +140,41 @@ static int ef100_net_open(struct net_device *net_dev) goto fail; rc = ef100_alloc_vis(efx, &allocated_vis); - if (rc) + if (rc && rc != -EAGAIN) goto fail; + /* Try one more time but with the maximum number of channels + * equal to the allocated VIs, which would more likely succeed. + */ + if (rc == -EAGAIN) { + rc = efx_mcdi_free_vis(efx); + if (rc) + goto fail; + + efx_remove_interrupts(efx); + efx->max_channels = allocated_vis; + + rc = efx_probe_interrupts(efx); + if (rc) + goto fail; + + rc = efx_set_channels(efx); + if (rc) + goto fail; + + rc = ef100_alloc_vis(efx, &allocated_vis); + if (rc && rc != -EAGAIN) + goto fail; + + /* It should be very unlikely that we failed here again, but in + * such a case we return ENOSPC. + */ + if (rc == -EAGAIN) { + rc = -ENOSPC; + goto fail; + } + } + rc = efx_probe_channels(efx); if (rc) return rc; @@ -378,7 +417,9 @@ int ef100_probe_netdev(struct efx_probe_data *probe_data) efx->net_dev = net_dev; SET_NETDEV_DEV(net_dev, &efx->pci_dev->dev); - net_dev->features |= efx->type->offload_features; + /* enable all supported features except rx-fcs and rx-all */ + net_dev->features |= efx->type->offload_features & + ~(NETIF_F_RXFCS | NETIF_F_RXALL); net_dev->hw_features |= efx->type->offload_features; net_dev->hw_enc_features |= efx->type->offload_features; net_dev->vlan_features |= NETIF_F_HW_CSUM | NETIF_F_SG | diff --git a/drivers/net/ethernet/sfc/efx_devlink.c b/drivers/net/ethernet/sfc/efx_devlink.c index 381b805659d3..b82dad50a5b1 100644 --- a/drivers/net/ethernet/sfc/efx_devlink.c +++ b/drivers/net/ethernet/sfc/efx_devlink.c @@ -25,40 +25,6 @@ struct efx_devlink { }; #ifdef CONFIG_SFC_SRIOV -static void efx_devlink_del_port(struct devlink_port *dl_port) -{ - if (!dl_port) - return; - devl_port_unregister(dl_port); -} - -static int efx_devlink_add_port(struct efx_nic *efx, - struct mae_mport_desc *mport) -{ - bool external = false; - - if (!ef100_mport_on_local_intf(efx, mport)) - external = true; - - switch (mport->mport_type) { - case MAE_MPORT_DESC_MPORT_TYPE_VNIC: - if (mport->vf_idx != MAE_MPORT_DESC_VF_IDX_NULL) - devlink_port_attrs_pci_vf_set(&mport->dl_port, 0, mport->pf_idx, - mport->vf_idx, - external); - else - devlink_port_attrs_pci_pf_set(&mport->dl_port, 0, mport->pf_idx, - external); - break; - default: - /* MAE_MPORT_DESC_MPORT_ALIAS and UNDEFINED */ - return 0; - } - - mport->dl_port.index = mport->mport_id; - - return devl_port_register(efx->devlink, &mport->dl_port, mport->mport_id); -} static int efx_devlink_port_addr_get(struct devlink_port *port, u8 *hw_addr, int *hw_addr_len, @@ -158,6 +124,48 @@ static int efx_devlink_port_addr_set(struct devlink_port *port, return rc; } +static const struct devlink_port_ops sfc_devlink_port_ops = { + .port_fn_hw_addr_get = efx_devlink_port_addr_get, + .port_fn_hw_addr_set = efx_devlink_port_addr_set, +}; + +static void efx_devlink_del_port(struct devlink_port *dl_port) +{ + if (!dl_port) + return; + devl_port_unregister(dl_port); +} + +static int efx_devlink_add_port(struct efx_nic *efx, + struct mae_mport_desc *mport) +{ + bool external = false; + + if (!ef100_mport_on_local_intf(efx, mport)) + external = true; + + switch (mport->mport_type) { + case MAE_MPORT_DESC_MPORT_TYPE_VNIC: + if (mport->vf_idx != MAE_MPORT_DESC_VF_IDX_NULL) + devlink_port_attrs_pci_vf_set(&mport->dl_port, 0, mport->pf_idx, + mport->vf_idx, + external); + else + devlink_port_attrs_pci_pf_set(&mport->dl_port, 0, mport->pf_idx, + external); + break; + default: + /* MAE_MPORT_DESC_MPORT_ALIAS and UNDEFINED */ + return 0; + } + + mport->dl_port.index = mport->mport_id; + + return devl_port_register_with_ops(efx->devlink, &mport->dl_port, + mport->mport_id, + &sfc_devlink_port_ops); +} + #endif static int efx_devlink_info_nvram_partition(struct efx_nic *efx, @@ -171,9 +179,14 @@ static int efx_devlink_info_nvram_partition(struct efx_nic *efx, rc = efx_mcdi_nvram_metadata(efx, partition_type, NULL, version, NULL, 0); + + /* If the partition does not exist, that is not an error. */ + if (rc == -ENOENT) + return 0; + if (rc) { - netif_err(efx, drv, efx->net_dev, "mcdi nvram %s: failed\n", - version_name); + netif_err(efx, drv, efx->net_dev, "mcdi nvram %s: failed (rc=%d)\n", + version_name, rc); return rc; } @@ -187,36 +200,33 @@ static int efx_devlink_info_nvram_partition(struct efx_nic *efx, static int efx_devlink_info_stored_versions(struct efx_nic *efx, struct devlink_info_req *req) { - int rc; - - rc = efx_devlink_info_nvram_partition(efx, req, - NVRAM_PARTITION_TYPE_BUNDLE, - DEVLINK_INFO_VERSION_GENERIC_FW_BUNDLE_ID); - if (rc) - return rc; + int err; - rc = efx_devlink_info_nvram_partition(efx, req, - NVRAM_PARTITION_TYPE_MC_FIRMWARE, - DEVLINK_INFO_VERSION_GENERIC_FW_MGMT); - if (rc) - return rc; - - rc = efx_devlink_info_nvram_partition(efx, req, - NVRAM_PARTITION_TYPE_SUC_FIRMWARE, - EFX_DEVLINK_INFO_VERSION_FW_MGMT_SUC); - if (rc) - return rc; - - rc = efx_devlink_info_nvram_partition(efx, req, - NVRAM_PARTITION_TYPE_EXPANSION_ROM, - EFX_DEVLINK_INFO_VERSION_FW_EXPROM); - if (rc) - return rc; - - rc = efx_devlink_info_nvram_partition(efx, req, - NVRAM_PARTITION_TYPE_EXPANSION_UEFI, - EFX_DEVLINK_INFO_VERSION_FW_UEFI); - return rc; + /* We do not care here about the specific error but just if an error + * happened. The specific error will be reported inside the call + * through system messages, and if any error happened in any call + * below, we report it through extack. + */ + err = efx_devlink_info_nvram_partition(efx, req, + NVRAM_PARTITION_TYPE_BUNDLE, + DEVLINK_INFO_VERSION_GENERIC_FW_BUNDLE_ID); + + err |= efx_devlink_info_nvram_partition(efx, req, + NVRAM_PARTITION_TYPE_MC_FIRMWARE, + DEVLINK_INFO_VERSION_GENERIC_FW_MGMT); + + err |= efx_devlink_info_nvram_partition(efx, req, + NVRAM_PARTITION_TYPE_SUC_FIRMWARE, + EFX_DEVLINK_INFO_VERSION_FW_MGMT_SUC); + + err |= efx_devlink_info_nvram_partition(efx, req, + NVRAM_PARTITION_TYPE_EXPANSION_ROM, + EFX_DEVLINK_INFO_VERSION_FW_EXPROM); + + err |= efx_devlink_info_nvram_partition(efx, req, + NVRAM_PARTITION_TYPE_EXPANSION_UEFI, + EFX_DEVLINK_INFO_VERSION_FW_UEFI); + return err; } #define EFX_VER_FLAG(_f) \ @@ -587,37 +597,26 @@ static int efx_devlink_info_get(struct devlink *devlink, { struct efx_devlink *devlink_private = devlink_priv(devlink); struct efx_nic *efx = devlink_private->efx; - int rc; + int err; - /* Several different MCDI commands are used. We report first error - * through extack returning at that point. Specific error - * information via system messages. + /* Several different MCDI commands are used. We report if errors + * happened through extack. Specific error information via system + * messages inside the calls. */ - rc = efx_devlink_info_board_cfg(efx, req); - if (rc) { - NL_SET_ERR_MSG_MOD(extack, "Getting board info failed"); - return rc; - } - rc = efx_devlink_info_stored_versions(efx, req); - if (rc) { - NL_SET_ERR_MSG_MOD(extack, "Getting stored versions failed"); - return rc; - } - rc = efx_devlink_info_running_versions(efx, req); - if (rc) { - NL_SET_ERR_MSG_MOD(extack, "Getting running versions failed"); - return rc; - } + err = efx_devlink_info_board_cfg(efx, req); + + err |= efx_devlink_info_stored_versions(efx, req); + + err |= efx_devlink_info_running_versions(efx, req); + + if (err) + NL_SET_ERR_MSG_MOD(extack, "Errors when getting device info. Check system messages"); return 0; } static const struct devlink_ops sfc_devlink_ops = { .info_get = efx_devlink_info_get, -#ifdef CONFIG_SFC_SRIOV - .port_function_hw_addr_get = efx_devlink_port_addr_get, - .port_function_hw_addr_set = efx_devlink_port_addr_set, -#endif }; #ifdef CONFIG_SFC_SRIOV diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c index 6dfbdb39f2fe..bb9ec1e761d3 100644 --- a/drivers/net/ethernet/sfc/tc.c +++ b/drivers/net/ethernet/sfc/tc.c @@ -687,13 +687,12 @@ static int efx_tc_flower_replace_foreign(struct efx_nic *efx, if (!found) { /* We don't care. */ netif_dbg(efx, drv, efx->net_dev, "Ignoring foreign filter that doesn't egdev us\n"); - rc = -EOPNOTSUPP; - goto release; + return -EOPNOTSUPP; } rc = efx_mae_match_check_caps(efx, &match.mask, NULL); if (rc) - goto release; + return rc; if (efx_tc_match_is_encap(&match.mask)) { enum efx_encap_type type; @@ -702,8 +701,7 @@ static int efx_tc_flower_replace_foreign(struct efx_nic *efx, if (type == EFX_ENCAP_TYPE_NONE) { NL_SET_ERR_MSG_MOD(extack, "Egress encap match on unsupported tunnel device"); - rc = -EOPNOTSUPP; - goto release; + return -EOPNOTSUPP; } rc = efx_mae_check_encap_type_supported(efx, type); @@ -711,26 +709,25 @@ static int efx_tc_flower_replace_foreign(struct efx_nic *efx, NL_SET_ERR_MSG_FMT_MOD(extack, "Firmware reports no support for %s encap match", efx_tc_encap_type_name(type)); - goto release; + return rc; } rc = efx_tc_flower_record_encap_match(efx, &match, type, EFX_TC_EM_DIRECT, 0, 0, extack); if (rc) - goto release; + return rc; } else { /* This is not a tunnel decap rule, ignore it */ netif_dbg(efx, drv, efx->net_dev, "Ignoring foreign filter without encap match\n"); - rc = -EOPNOTSUPP; - goto release; + return -EOPNOTSUPP; } rule = kzalloc(sizeof(*rule), GFP_USER); if (!rule) { rc = -ENOMEM; - goto release; + goto out_free; } INIT_LIST_HEAD(&rule->acts.list); rule->cookie = tc->cookie; @@ -742,7 +739,7 @@ static int efx_tc_flower_replace_foreign(struct efx_nic *efx, "Ignoring already-offloaded rule (cookie %lx)\n", tc->cookie); rc = -EEXIST; - goto release; + goto out_free; } act = kzalloc(sizeof(*act), GFP_USER); @@ -907,6 +904,7 @@ release: efx_tc_match_action_ht_params); efx_tc_free_action_set_list(efx, &rule->acts, false); } +out_free: kfree(rule); if (match.encap) efx_tc_flower_release_encap_match(efx, match.encap); @@ -963,8 +961,7 @@ static int efx_tc_flower_replace(struct efx_nic *efx, return rc; if (efx_tc_match_is_encap(&match.mask)) { NL_SET_ERR_MSG_MOD(extack, "Ingress enc_key matches not supported"); - rc = -EOPNOTSUPP; - goto release; + return -EOPNOTSUPP; } if (tc->common.chain_index) { @@ -988,9 +985,9 @@ static int efx_tc_flower_replace(struct efx_nic *efx, if (old) { netif_dbg(efx, drv, efx->net_dev, "Already offloaded rule (cookie %lx)\n", tc->cookie); - rc = -EEXIST; NL_SET_ERR_MSG_MOD(extack, "Rule already offloaded"); - goto release; + kfree(rule); + return -EEXIST; } /* Parse actions */ diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig index 5f5a997f21f3..5583f0b055ec 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Kconfig +++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig @@ -158,6 +158,9 @@ config DWMAC_SOCFPGA default ARCH_INTEL_SOCFPGA depends on OF && (ARCH_INTEL_SOCFPGA || COMPILE_TEST) select MFD_SYSCON + select MDIO_REGMAP + select REGMAP_MMIO + select PCS_LYNX help Support for ethernet controller on Altera SOCFPGA diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile index 8738fdbb4b2d..7dd3d388068b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Makefile +++ b/drivers/net/ethernet/stmicro/stmmac/Makefile @@ -35,7 +35,7 @@ obj-$(CONFIG_DWMAC_IMX8) += dwmac-imx.o obj-$(CONFIG_DWMAC_TEGRA) += dwmac-tegra.o obj-$(CONFIG_DWMAC_VISCONTI) += dwmac-visconti.o stmmac-platform-objs:= stmmac_platform.o -dwmac-altr-socfpga-objs := altr_tse_pcs.o dwmac-socfpga.o +dwmac-altr-socfpga-objs := dwmac-socfpga.o obj-$(CONFIG_STMMAC_PCI) += stmmac-pci.o obj-$(CONFIG_DWMAC_INTEL) += dwmac-intel.o diff --git a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c deleted file mode 100644 index 00f6d347eaf7..000000000000 --- a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c +++ /dev/null @@ -1,257 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* Copyright Altera Corporation (C) 2016. All rights reserved. - * - * Author: Tien Hock Loh <thloh@altera.com> - */ - -#include <linux/mfd/syscon.h> -#include <linux/of.h> -#include <linux/of_address.h> -#include <linux/of_net.h> -#include <linux/phy.h> -#include <linux/regmap.h> -#include <linux/reset.h> -#include <linux/stmmac.h> - -#include "stmmac.h" -#include "stmmac_platform.h" -#include "altr_tse_pcs.h" - -#define SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_GMII_MII 0 -#define SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_RGMII BIT(1) -#define SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_RMII BIT(2) -#define SYSMGR_EMACGRP_CTRL_PHYSEL_WIDTH 2 -#define SYSMGR_EMACGRP_CTRL_PHYSEL_MASK GENMASK(1, 0) - -#define TSE_PCS_CONTROL_AN_EN_MASK BIT(12) -#define TSE_PCS_CONTROL_REG 0x00 -#define TSE_PCS_CONTROL_RESTART_AN_MASK BIT(9) -#define TSE_PCS_CTRL_AUTONEG_SGMII 0x1140 -#define TSE_PCS_IF_MODE_REG 0x28 -#define TSE_PCS_LINK_TIMER_0_REG 0x24 -#define TSE_PCS_LINK_TIMER_1_REG 0x26 -#define TSE_PCS_SIZE 0x40 -#define TSE_PCS_STATUS_AN_COMPLETED_MASK BIT(5) -#define TSE_PCS_STATUS_LINK_MASK 0x0004 -#define TSE_PCS_STATUS_REG 0x02 -#define TSE_PCS_SGMII_SPEED_1000 BIT(3) -#define TSE_PCS_SGMII_SPEED_100 BIT(2) -#define TSE_PCS_SGMII_SPEED_10 0x0 -#define TSE_PCS_SW_RST_MASK 0x8000 -#define TSE_PCS_PARTNER_ABILITY_REG 0x0A -#define TSE_PCS_PARTNER_DUPLEX_FULL 0x1000 -#define TSE_PCS_PARTNER_DUPLEX_HALF 0x0000 -#define TSE_PCS_PARTNER_DUPLEX_MASK 0x1000 -#define TSE_PCS_PARTNER_SPEED_MASK GENMASK(11, 10) -#define TSE_PCS_PARTNER_SPEED_1000 BIT(11) -#define TSE_PCS_PARTNER_SPEED_100 BIT(10) -#define TSE_PCS_PARTNER_SPEED_10 0x0000 -#define TSE_PCS_PARTNER_SPEED_1000 BIT(11) -#define TSE_PCS_PARTNER_SPEED_100 BIT(10) -#define TSE_PCS_PARTNER_SPEED_10 0x0000 -#define TSE_PCS_SGMII_SPEED_MASK GENMASK(3, 2) -#define TSE_PCS_SGMII_LINK_TIMER_0 0x0D40 -#define TSE_PCS_SGMII_LINK_TIMER_1 0x0003 -#define TSE_PCS_SW_RESET_TIMEOUT 100 -#define TSE_PCS_USE_SGMII_AN_MASK BIT(1) -#define TSE_PCS_USE_SGMII_ENA BIT(0) -#define TSE_PCS_IF_USE_SGMII 0x03 - -#define AUTONEGO_LINK_TIMER 20 - -static int tse_pcs_reset(void __iomem *base, struct tse_pcs *pcs) -{ - int counter = 0; - u16 val; - - val = readw(base + TSE_PCS_CONTROL_REG); - val |= TSE_PCS_SW_RST_MASK; - writew(val, base + TSE_PCS_CONTROL_REG); - - while (counter < TSE_PCS_SW_RESET_TIMEOUT) { - val = readw(base + TSE_PCS_CONTROL_REG); - val &= TSE_PCS_SW_RST_MASK; - if (val == 0) - break; - counter++; - udelay(1); - } - if (counter >= TSE_PCS_SW_RESET_TIMEOUT) { - dev_err(pcs->dev, "PCS could not get out of sw reset\n"); - return -ETIMEDOUT; - } - - return 0; -} - -int tse_pcs_init(void __iomem *base, struct tse_pcs *pcs) -{ - int ret = 0; - - writew(TSE_PCS_IF_USE_SGMII, base + TSE_PCS_IF_MODE_REG); - - writew(TSE_PCS_CTRL_AUTONEG_SGMII, base + TSE_PCS_CONTROL_REG); - - writew(TSE_PCS_SGMII_LINK_TIMER_0, base + TSE_PCS_LINK_TIMER_0_REG); - writew(TSE_PCS_SGMII_LINK_TIMER_1, base + TSE_PCS_LINK_TIMER_1_REG); - - ret = tse_pcs_reset(base, pcs); - if (ret == 0) - writew(SGMII_ADAPTER_ENABLE, - pcs->sgmii_adapter_base + SGMII_ADAPTER_CTRL_REG); - - return ret; -} - -static void pcs_link_timer_callback(struct tse_pcs *pcs) -{ - u16 val = 0; - void __iomem *tse_pcs_base = pcs->tse_pcs_base; - void __iomem *sgmii_adapter_base = pcs->sgmii_adapter_base; - - val = readw(tse_pcs_base + TSE_PCS_STATUS_REG); - val &= TSE_PCS_STATUS_LINK_MASK; - - if (val != 0) { - dev_dbg(pcs->dev, "Adapter: Link is established\n"); - writew(SGMII_ADAPTER_ENABLE, - sgmii_adapter_base + SGMII_ADAPTER_CTRL_REG); - } else { - mod_timer(&pcs->aneg_link_timer, jiffies + - msecs_to_jiffies(AUTONEGO_LINK_TIMER)); - } -} - -static void auto_nego_timer_callback(struct tse_pcs *pcs) -{ - u16 val = 0; - u16 speed = 0; - u16 duplex = 0; - void __iomem *tse_pcs_base = pcs->tse_pcs_base; - void __iomem *sgmii_adapter_base = pcs->sgmii_adapter_base; - - val = readw(tse_pcs_base + TSE_PCS_STATUS_REG); - val &= TSE_PCS_STATUS_AN_COMPLETED_MASK; - - if (val != 0) { - dev_dbg(pcs->dev, "Adapter: Auto Negotiation is completed\n"); - val = readw(tse_pcs_base + TSE_PCS_PARTNER_ABILITY_REG); - speed = val & TSE_PCS_PARTNER_SPEED_MASK; - duplex = val & TSE_PCS_PARTNER_DUPLEX_MASK; - - if (speed == TSE_PCS_PARTNER_SPEED_10 && - duplex == TSE_PCS_PARTNER_DUPLEX_FULL) - dev_dbg(pcs->dev, - "Adapter: Link Partner is Up - 10/Full\n"); - else if (speed == TSE_PCS_PARTNER_SPEED_100 && - duplex == TSE_PCS_PARTNER_DUPLEX_FULL) - dev_dbg(pcs->dev, - "Adapter: Link Partner is Up - 100/Full\n"); - else if (speed == TSE_PCS_PARTNER_SPEED_1000 && - duplex == TSE_PCS_PARTNER_DUPLEX_FULL) - dev_dbg(pcs->dev, - "Adapter: Link Partner is Up - 1000/Full\n"); - else if (speed == TSE_PCS_PARTNER_SPEED_10 && - duplex == TSE_PCS_PARTNER_DUPLEX_HALF) - dev_err(pcs->dev, - "Adapter does not support Half Duplex\n"); - else if (speed == TSE_PCS_PARTNER_SPEED_100 && - duplex == TSE_PCS_PARTNER_DUPLEX_HALF) - dev_err(pcs->dev, - "Adapter does not support Half Duplex\n"); - else if (speed == TSE_PCS_PARTNER_SPEED_1000 && - duplex == TSE_PCS_PARTNER_DUPLEX_HALF) - dev_err(pcs->dev, - "Adapter does not support Half Duplex\n"); - else - dev_err(pcs->dev, - "Adapter: Invalid Partner Speed and Duplex\n"); - - if (duplex == TSE_PCS_PARTNER_DUPLEX_FULL && - (speed == TSE_PCS_PARTNER_SPEED_10 || - speed == TSE_PCS_PARTNER_SPEED_100 || - speed == TSE_PCS_PARTNER_SPEED_1000)) - writew(SGMII_ADAPTER_ENABLE, - sgmii_adapter_base + SGMII_ADAPTER_CTRL_REG); - } else { - val = readw(tse_pcs_base + TSE_PCS_CONTROL_REG); - val |= TSE_PCS_CONTROL_RESTART_AN_MASK; - writew(val, tse_pcs_base + TSE_PCS_CONTROL_REG); - - tse_pcs_reset(tse_pcs_base, pcs); - mod_timer(&pcs->aneg_link_timer, jiffies + - msecs_to_jiffies(AUTONEGO_LINK_TIMER)); - } -} - -static void aneg_link_timer_callback(struct timer_list *t) -{ - struct tse_pcs *pcs = from_timer(pcs, t, aneg_link_timer); - - if (pcs->autoneg == AUTONEG_ENABLE) - auto_nego_timer_callback(pcs); - else if (pcs->autoneg == AUTONEG_DISABLE) - pcs_link_timer_callback(pcs); -} - -void tse_pcs_fix_mac_speed(struct tse_pcs *pcs, struct phy_device *phy_dev, - unsigned int speed) -{ - void __iomem *tse_pcs_base = pcs->tse_pcs_base; - u32 val; - - pcs->autoneg = phy_dev->autoneg; - - if (phy_dev->autoneg == AUTONEG_ENABLE) { - val = readw(tse_pcs_base + TSE_PCS_CONTROL_REG); - val |= TSE_PCS_CONTROL_AN_EN_MASK; - writew(val, tse_pcs_base + TSE_PCS_CONTROL_REG); - - val = readw(tse_pcs_base + TSE_PCS_IF_MODE_REG); - val |= TSE_PCS_USE_SGMII_AN_MASK; - writew(val, tse_pcs_base + TSE_PCS_IF_MODE_REG); - - val = readw(tse_pcs_base + TSE_PCS_CONTROL_REG); - val |= TSE_PCS_CONTROL_RESTART_AN_MASK; - - tse_pcs_reset(tse_pcs_base, pcs); - - timer_setup(&pcs->aneg_link_timer, aneg_link_timer_callback, - 0); - mod_timer(&pcs->aneg_link_timer, jiffies + - msecs_to_jiffies(AUTONEGO_LINK_TIMER)); - } else if (phy_dev->autoneg == AUTONEG_DISABLE) { - val = readw(tse_pcs_base + TSE_PCS_CONTROL_REG); - val &= ~TSE_PCS_CONTROL_AN_EN_MASK; - writew(val, tse_pcs_base + TSE_PCS_CONTROL_REG); - - val = readw(tse_pcs_base + TSE_PCS_IF_MODE_REG); - val &= ~TSE_PCS_USE_SGMII_AN_MASK; - writew(val, tse_pcs_base + TSE_PCS_IF_MODE_REG); - - val = readw(tse_pcs_base + TSE_PCS_IF_MODE_REG); - val &= ~TSE_PCS_SGMII_SPEED_MASK; - - switch (speed) { - case 1000: - val |= TSE_PCS_SGMII_SPEED_1000; - break; - case 100: - val |= TSE_PCS_SGMII_SPEED_100; - break; - case 10: - val |= TSE_PCS_SGMII_SPEED_10; - break; - default: - return; - } - writew(val, tse_pcs_base + TSE_PCS_IF_MODE_REG); - - tse_pcs_reset(tse_pcs_base, pcs); - - timer_setup(&pcs->aneg_link_timer, aneg_link_timer_callback, - 0); - mod_timer(&pcs->aneg_link_timer, jiffies + - msecs_to_jiffies(AUTONEGO_LINK_TIMER)); - } -} diff --git a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.h b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.h deleted file mode 100644 index 694ac25ef426..000000000000 --- a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.h +++ /dev/null @@ -1,29 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* Copyright Altera Corporation (C) 2016. All rights reserved. - * - * Author: Tien Hock Loh <thloh@altera.com> - */ - -#ifndef __TSE_PCS_H__ -#define __TSE_PCS_H__ - -#include <linux/phy.h> -#include <linux/timer.h> - -#define SGMII_ADAPTER_CTRL_REG 0x00 -#define SGMII_ADAPTER_ENABLE 0x0000 -#define SGMII_ADAPTER_DISABLE 0x0001 - -struct tse_pcs { - struct device *dev; - void __iomem *tse_pcs_base; - void __iomem *sgmii_adapter_base; - struct timer_list aneg_link_timer; - int autoneg; -}; - -int tse_pcs_init(void __iomem *base, struct tse_pcs *pcs); -void tse_pcs_fix_mac_speed(struct tse_pcs *pcs, struct phy_device *phy_dev, - unsigned int speed); - -#endif /* __TSE_PCS_H__ */ diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 4ad692c4116c..16e67c18b6f7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -519,6 +519,7 @@ struct mac_device_info { const struct stmmac_tc_ops *tc; const struct stmmac_mmc_ops *mmc; struct dw_xpcs *xpcs; + struct phylink_pcs *lynx_pcs; /* Lynx external PCS */ struct mii_regs mii; /* MII register Addresses */ struct mac_link link; void __iomem *pcsr; /* vpointer to device CSRs */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index 1db97a5209c4..c801838fae2a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -644,7 +644,8 @@ static int qcom_ethqos_probe(struct platform_device *pdev) plat_dat->fix_mac_speed = ethqos_fix_mac_speed; plat_dat->dump_debug_regs = rgmii_dump; plat_dat->has_gmac4 = 1; - plat_dat->dwmac4_addrs = &data->dwmac4_addrs; + if (ethqos->has_emac3) + plat_dat->dwmac4_addrs = &data->dwmac4_addrs; plat_dat->pmt = 1; plat_dat->tso_en = of_property_read_bool(np, "snps,tso"); if (of_device_is_compatible(np, "qcom,qcs404-ethqos")) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c index 6ee050300b31..6267bcb60206 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c @@ -10,14 +10,14 @@ #include <linux/of_net.h> #include <linux/phy.h> #include <linux/regmap.h> +#include <linux/mdio/mdio-regmap.h> +#include <linux/pcs-lynx.h> #include <linux/reset.h> #include <linux/stmmac.h> #include "stmmac.h" #include "stmmac_platform.h" -#include "altr_tse_pcs.h" - #define SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_GMII_MII 0x0 #define SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_RGMII 0x1 #define SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_RMII 0x2 @@ -37,6 +37,10 @@ #define EMAC_SPLITTER_CTRL_SPEED_100 0x3 #define EMAC_SPLITTER_CTRL_SPEED_1000 0x0 +#define SGMII_ADAPTER_CTRL_REG 0x00 +#define SGMII_ADAPTER_ENABLE 0x0000 +#define SGMII_ADAPTER_DISABLE 0x0001 + struct socfpga_dwmac; struct socfpga_dwmac_ops { int (*set_phy_mode)(struct socfpga_dwmac *dwmac_priv); @@ -50,16 +54,18 @@ struct socfpga_dwmac { struct reset_control *stmmac_rst; struct reset_control *stmmac_ocp_rst; void __iomem *splitter_base; + void __iomem *tse_pcs_base; + void __iomem *sgmii_adapter_base; bool f2h_ptp_ref_clk; - struct tse_pcs pcs; const struct socfpga_dwmac_ops *ops; + struct mdio_device *pcs_mdiodev; }; static void socfpga_dwmac_fix_mac_speed(void *priv, unsigned int speed) { struct socfpga_dwmac *dwmac = (struct socfpga_dwmac *)priv; void __iomem *splitter_base = dwmac->splitter_base; - void __iomem *sgmii_adapter_base = dwmac->pcs.sgmii_adapter_base; + void __iomem *sgmii_adapter_base = dwmac->sgmii_adapter_base; struct device *dev = dwmac->dev; struct net_device *ndev = dev_get_drvdata(dev); struct phy_device *phy_dev = ndev->phydev; @@ -89,11 +95,9 @@ static void socfpga_dwmac_fix_mac_speed(void *priv, unsigned int speed) writel(val, splitter_base + EMAC_SPLITTER_CTRL_REG); } - if (phy_dev && sgmii_adapter_base) { + if (phy_dev && sgmii_adapter_base) writew(SGMII_ADAPTER_ENABLE, sgmii_adapter_base + SGMII_ADAPTER_CTRL_REG); - tse_pcs_fix_mac_speed(&dwmac->pcs, phy_dev, speed); - } } static int socfpga_dwmac_parse_data(struct socfpga_dwmac *dwmac, struct device *dev) @@ -183,11 +187,11 @@ static int socfpga_dwmac_parse_data(struct socfpga_dwmac *dwmac, struct device * goto err_node_put; } - dwmac->pcs.sgmii_adapter_base = + dwmac->sgmii_adapter_base = devm_ioremap_resource(dev, &res_sgmii_adapter); - if (IS_ERR(dwmac->pcs.sgmii_adapter_base)) { - ret = PTR_ERR(dwmac->pcs.sgmii_adapter_base); + if (IS_ERR(dwmac->sgmii_adapter_base)) { + ret = PTR_ERR(dwmac->sgmii_adapter_base); goto err_node_put; } } @@ -205,11 +209,11 @@ static int socfpga_dwmac_parse_data(struct socfpga_dwmac *dwmac, struct device * goto err_node_put; } - dwmac->pcs.tse_pcs_base = + dwmac->tse_pcs_base = devm_ioremap_resource(dev, &res_tse_pcs); - if (IS_ERR(dwmac->pcs.tse_pcs_base)) { - ret = PTR_ERR(dwmac->pcs.tse_pcs_base); + if (IS_ERR(dwmac->tse_pcs_base)) { + ret = PTR_ERR(dwmac->tse_pcs_base); goto err_node_put; } } @@ -235,6 +239,13 @@ static int socfpga_get_plat_phymode(struct socfpga_dwmac *dwmac) return priv->plat->interface; } +static void socfpga_sgmii_config(struct socfpga_dwmac *dwmac, bool enable) +{ + u16 val = enable ? SGMII_ADAPTER_ENABLE : SGMII_ADAPTER_DISABLE; + + writew(val, dwmac->sgmii_adapter_base + SGMII_ADAPTER_CTRL_REG); +} + static int socfpga_set_phy_mode_common(int phymode, u32 *val) { switch (phymode) { @@ -310,12 +321,8 @@ static int socfpga_gen5_set_phy_mode(struct socfpga_dwmac *dwmac) */ reset_control_deassert(dwmac->stmmac_ocp_rst); reset_control_deassert(dwmac->stmmac_rst); - if (phymode == PHY_INTERFACE_MODE_SGMII) { - if (tse_pcs_init(dwmac->pcs.tse_pcs_base, &dwmac->pcs) != 0) { - dev_err(dwmac->dev, "Unable to initialize TSE PCS"); - return -EINVAL; - } - } + if (phymode == PHY_INTERFACE_MODE_SGMII) + socfpga_sgmii_config(dwmac, true); return 0; } @@ -367,12 +374,8 @@ static int socfpga_gen10_set_phy_mode(struct socfpga_dwmac *dwmac) */ reset_control_deassert(dwmac->stmmac_ocp_rst); reset_control_deassert(dwmac->stmmac_rst); - if (phymode == PHY_INTERFACE_MODE_SGMII) { - if (tse_pcs_init(dwmac->pcs.tse_pcs_base, &dwmac->pcs) != 0) { - dev_err(dwmac->dev, "Unable to initialize TSE PCS"); - return -EINVAL; - } - } + if (phymode == PHY_INTERFACE_MODE_SGMII) + socfpga_sgmii_config(dwmac, true); return 0; } @@ -443,6 +446,48 @@ static int socfpga_dwmac_probe(struct platform_device *pdev) if (ret) goto err_dvr_remove; + /* Create a regmap for the PCS so that it can be used by the PCS driver, + * if we have such a PCS + */ + if (dwmac->tse_pcs_base) { + struct regmap_config pcs_regmap_cfg; + struct mdio_regmap_config mrc; + struct regmap *pcs_regmap; + struct mii_bus *pcs_bus; + + memset(&pcs_regmap_cfg, 0, sizeof(pcs_regmap_cfg)); + memset(&mrc, 0, sizeof(mrc)); + + pcs_regmap_cfg.reg_bits = 16; + pcs_regmap_cfg.val_bits = 16; + pcs_regmap_cfg.reg_shift = REGMAP_UPSHIFT(1); + + pcs_regmap = devm_regmap_init_mmio(&pdev->dev, dwmac->tse_pcs_base, + &pcs_regmap_cfg); + if (IS_ERR(pcs_regmap)) { + ret = PTR_ERR(pcs_regmap); + goto err_dvr_remove; + } + + mrc.regmap = pcs_regmap; + mrc.parent = &pdev->dev; + mrc.valid_addr = 0x0; + mrc.autoscan = false; + + snprintf(mrc.name, MII_BUS_ID_SIZE, "%s-pcs-mii", ndev->name); + pcs_bus = devm_mdio_regmap_register(&pdev->dev, &mrc); + if (IS_ERR(pcs_bus)) { + ret = PTR_ERR(pcs_bus); + goto err_dvr_remove; + } + + stpriv->hw->lynx_pcs = lynx_pcs_create_mdiodev(pcs_bus, 0); + if (IS_ERR(stpriv->hw->lynx_pcs)) { + ret = PTR_ERR(stpriv->hw->lynx_pcs); + goto err_dvr_remove; + } + } + return 0; err_dvr_remove: @@ -453,6 +498,17 @@ err_remove_config_dt: return ret; } +static void socfpga_dwmac_remove(struct platform_device *pdev) +{ + struct net_device *ndev = platform_get_drvdata(pdev); + struct stmmac_priv *priv = netdev_priv(ndev); + struct phylink_pcs *pcs = priv->hw->lynx_pcs; + + stmmac_pltfr_remove(pdev); + + lynx_pcs_destroy(pcs); +} + #ifdef CONFIG_PM_SLEEP static int socfpga_dwmac_resume(struct device *dev) { @@ -524,7 +580,7 @@ MODULE_DEVICE_TABLE(of, socfpga_dwmac_match); static struct platform_driver socfpga_dwmac_driver = { .probe = socfpga_dwmac_probe, - .remove_new = stmmac_pltfr_remove, + .remove_new = socfpga_dwmac_remove, .driver = { .name = "socfpga-dwmac", .pm = &socfpga_dwmac_pm_ops, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 0fca81507a77..fa07b0d50b46 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -937,10 +937,13 @@ static struct phylink_pcs *stmmac_mac_select_pcs(struct phylink_config *config, { struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); - if (!priv->hw->xpcs) - return NULL; + if (priv->hw->xpcs) + return &priv->hw->xpcs->pcs; + + if (priv->hw->lynx_pcs) + return priv->hw->lynx_pcs; - return &priv->hw->xpcs->pcs; + return NULL; } static void stmmac_mac_config(struct phylink_config *config, unsigned int mode, @@ -3813,7 +3816,8 @@ static int __stmmac_open(struct net_device *dev, if (priv->hw->pcs != STMMAC_PCS_TBI && priv->hw->pcs != STMMAC_PCS_RTBI && (!priv->hw->xpcs || - xpcs_get_an_mode(priv->hw->xpcs, mode) != DW_AN_C73)) { + xpcs_get_an_mode(priv->hw->xpcs, mode) != DW_AN_C73) && + !priv->hw->lynx_pcs) { ret = stmmac_init_phy(dev); if (ret) { netdev_err(priv->dev, @@ -7233,8 +7237,7 @@ int stmmac_dvr_probe(struct device *device, ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM; ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | - NETDEV_XDP_ACT_XSK_ZEROCOPY | - NETDEV_XDP_ACT_NDO_XMIT; + NETDEV_XDP_ACT_XSK_ZEROCOPY; ret = stmmac_tc_init(priv, priv); if (!ret) { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index 6807c4c1a0a2..3db1cb0fd160 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -491,7 +491,6 @@ int stmmac_mdio_reset(struct mii_bus *bus) int stmmac_xpcs_setup(struct mii_bus *bus) { struct net_device *ndev = bus->priv; - struct mdio_device *mdiodev; struct stmmac_priv *priv; struct dw_xpcs *xpcs; int mode, addr; @@ -501,16 +500,10 @@ int stmmac_xpcs_setup(struct mii_bus *bus) /* Try to probe the XPCS by scanning all addresses. */ for (addr = 0; addr < PHY_MAX_ADDR; addr++) { - mdiodev = mdio_device_create(bus, addr); - if (IS_ERR(mdiodev)) + xpcs = xpcs_create_mdiodev(bus, addr, mode); + if (IS_ERR(xpcs)) continue; - xpcs = xpcs_create(mdiodev, mode); - if (IS_ERR_OR_NULL(xpcs)) { - mdio_device_free(mdiodev); - continue; - } - priv->hw->xpcs = xpcs; break; } @@ -669,10 +662,8 @@ int stmmac_mdio_unregister(struct net_device *ndev) if (!priv->mii) return 0; - if (priv->hw->xpcs) { - mdio_device_free(priv->hw->xpcs->mdiodev); + if (priv->hw->xpcs) xpcs_destroy(priv->hw->xpcs); - } mdiobus_unregister(priv->mii); priv->mii->priv = NULL; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 9d55226479b4..ac41ef4cbd2f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -966,8 +966,11 @@ static int tc_setup_taprio(struct stmmac_priv *priv, return -EOPNOTSUPP; } - if (!qopt->enable) + if (qopt->cmd == TAPRIO_CMD_DESTROY) goto disable; + else if (qopt->cmd != TAPRIO_CMD_REPLACE) + return -EOPNOTSUPP; + if (qopt->num_entries >= dep) return -EINVAL; if (!qopt->cycle_time) @@ -988,7 +991,7 @@ static int tc_setup_taprio(struct stmmac_priv *priv, mutex_lock(&priv->plat->est->lock); priv->plat->est->gcl_size = size; - priv->plat->est->enable = qopt->enable; + priv->plat->est->enable = qopt->cmd == TAPRIO_CMD_REPLACE; mutex_unlock(&priv->plat->est->lock); for (i = 0; i < size; i++) { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.c index 9d4d8c3dad0a..aa6f16d3df64 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.c @@ -117,6 +117,9 @@ int stmmac_xdp_set_prog(struct stmmac_priv *priv, struct bpf_prog *prog, return -EOPNOTSUPP; } + if (!prog) + xdp_features_clear_redirect_target(dev); + need_update = !!priv->xdp_prog != !!prog; if (if_running && need_update) stmmac_xdp_release(dev); @@ -131,5 +134,8 @@ int stmmac_xdp_set_prog(struct stmmac_priv *priv, struct bpf_prog *prog, if (if_running && need_update) stmmac_xdp_open(dev); + if (prog) + xdp_features_set_redirect_target(dev, false); + return 0; } diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index 2d52f54ebb45..b317b9486455 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -5073,6 +5073,8 @@ err_out_iounmap: cas_shutdown(cp); mutex_unlock(&cp->pm_mutex); + vfree(cp->fw_data); + pci_iounmap(pdev, cp->regs); diff --git a/drivers/net/ethernet/ti/am65-cpsw-qos.c b/drivers/net/ethernet/ti/am65-cpsw-qos.c index 3a908db6e5b2..eced87fa261c 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-qos.c +++ b/drivers/net/ethernet/ti/am65-cpsw-qos.c @@ -450,7 +450,7 @@ static int am65_cpsw_configure_taprio(struct net_device *ndev, am65_cpsw_est_update_state(ndev); - if (!est_new->taprio.enable) { + if (est_new->taprio.cmd == TAPRIO_CMD_DESTROY) { am65_cpsw_stop_est(ndev); return ret; } @@ -476,7 +476,7 @@ static int am65_cpsw_configure_taprio(struct net_device *ndev, am65_cpsw_est_set_sched_list(ndev, est_new); am65_cpsw_port_est_assign_buf_num(ndev, est_new->buf); - am65_cpsw_est_set(ndev, est_new->taprio.enable); + am65_cpsw_est_set(ndev, est_new->taprio.cmd == TAPRIO_CMD_REPLACE); if (tact == TACT_PROG) { ret = am65_cpsw_timer_set(ndev, est_new); @@ -520,7 +520,7 @@ static int am65_cpsw_set_taprio(struct net_device *ndev, void *type_data) am65_cpsw_cp_taprio(taprio, &est_new->taprio); ret = am65_cpsw_configure_taprio(ndev, est_new); if (!ret) { - if (taprio->enable) { + if (taprio->cmd == TAPRIO_CMD_REPLACE) { devm_kfree(&ndev->dev, port->qos.est_admin); port->qos.est_admin = est_new; @@ -564,8 +564,13 @@ purge_est: static int am65_cpsw_setup_taprio(struct net_device *ndev, void *type_data) { struct am65_cpsw_port *port = am65_ndev_to_port(ndev); + struct tc_taprio_qopt_offload *taprio = type_data; struct am65_cpsw_common *common = port->common; + if (taprio->cmd != TAPRIO_CMD_REPLACE && + taprio->cmd != TAPRIO_CMD_DESTROY) + return -EOPNOTSUPP; + if (!IS_ENABLED(CONFIG_TI_AM65_CPSW_TAS)) return -ENODEV; diff --git a/drivers/net/ethernet/wangxun/Kconfig b/drivers/net/ethernet/wangxun/Kconfig index c9d88673d306..39596cd13539 100644 --- a/drivers/net/ethernet/wangxun/Kconfig +++ b/drivers/net/ethernet/wangxun/Kconfig @@ -40,6 +40,16 @@ config NGBE config TXGBE tristate "Wangxun(R) 10GbE PCI Express adapters support" depends on PCI + depends on COMMON_CLK + select REGMAP + select I2C + select I2C_DESIGNWARE_PLATFORM + select PHYLINK + select HWMON if TXGBE=y + select SFP + select GPIOLIB + select GPIOLIB_IRQCHIP + select PCS_XPCS select LIBWX help This driver supports Wangxun(R) 10GbE PCI Express family of diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c index ca409b4054d0..39a9aeee7aab 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c @@ -1182,12 +1182,28 @@ static void wx_enable_sec_rx_path(struct wx *wx) WX_WRITE_FLUSH(wx); } +static void wx_vlan_strip_control(struct wx *wx, bool enable) +{ + int i, j; + + for (i = 0; i < wx->num_rx_queues; i++) { + struct wx_ring *ring = wx->rx_ring[i]; + + j = ring->reg_idx; + wr32m(wx, WX_PX_RR_CFG(j), WX_PX_RR_CFG_VLAN, + enable ? WX_PX_RR_CFG_VLAN : 0); + } +} + void wx_set_rx_mode(struct net_device *netdev) { struct wx *wx = netdev_priv(netdev); + netdev_features_t features; u32 fctrl, vmolr, vlnctrl; int count; + features = netdev->features; + /* Check for Promiscuous and All Multicast modes */ fctrl = rd32(wx, WX_PSR_CTL); fctrl &= ~(WX_PSR_CTL_UPE | WX_PSR_CTL_MPE); @@ -1254,6 +1270,13 @@ void wx_set_rx_mode(struct net_device *netdev) wr32(wx, WX_PSR_VLAN_CTL, vlnctrl); wr32(wx, WX_PSR_CTL, fctrl); wr32(wx, WX_PSR_VM_L2CTL(0), vmolr); + + if ((features & NETIF_F_HW_VLAN_CTAG_RX) && + (features & NETIF_F_HW_VLAN_STAG_RX)) + wx_vlan_strip_control(wx, true); + else + wx_vlan_strip_control(wx, false); + } EXPORT_SYMBOL(wx_set_rx_mode); @@ -1462,6 +1485,16 @@ static void wx_configure_tx(struct wx *wx) WX_MAC_TX_CFG_TE, WX_MAC_TX_CFG_TE); } +static void wx_restore_vlan(struct wx *wx) +{ + u16 vid = 1; + + wx_vlan_rx_add_vid(wx->netdev, htons(ETH_P_8021Q), 0); + + for_each_set_bit_from(vid, wx->active_vlans, VLAN_N_VID) + wx_vlan_rx_add_vid(wx->netdev, htons(ETH_P_8021Q), vid); +} + /** * wx_configure_rx - Configure Receive Unit after Reset * @wx: pointer to private structure @@ -1527,7 +1560,7 @@ void wx_configure(struct wx *wx) wx_configure_port(wx); wx_set_rx_mode(wx->netdev); - + wx_restore_vlan(wx); wx_enable_sec_rx_path(wx); wx_configure_tx(wx); @@ -1727,4 +1760,241 @@ int wx_sw_init(struct wx *wx) } EXPORT_SYMBOL(wx_sw_init); +/** + * wx_find_vlvf_slot - find the vlanid or the first empty slot + * @wx: pointer to hardware structure + * @vlan: VLAN id to write to VLAN filter + * + * return the VLVF index where this VLAN id should be placed + * + **/ +static int wx_find_vlvf_slot(struct wx *wx, u32 vlan) +{ + u32 bits = 0, first_empty_slot = 0; + int regindex; + + /* short cut the special case */ + if (vlan == 0) + return 0; + + /* Search for the vlan id in the VLVF entries. Save off the first empty + * slot found along the way + */ + for (regindex = 1; regindex < WX_PSR_VLAN_SWC_ENTRIES; regindex++) { + wr32(wx, WX_PSR_VLAN_SWC_IDX, regindex); + bits = rd32(wx, WX_PSR_VLAN_SWC); + if (!bits && !(first_empty_slot)) + first_empty_slot = regindex; + else if ((bits & 0x0FFF) == vlan) + break; + } + + if (regindex >= WX_PSR_VLAN_SWC_ENTRIES) { + if (first_empty_slot) + regindex = first_empty_slot; + else + regindex = -ENOMEM; + } + + return regindex; +} + +/** + * wx_set_vlvf - Set VLAN Pool Filter + * @wx: pointer to hardware structure + * @vlan: VLAN id to write to VLAN filter + * @vind: VMDq output index that maps queue to VLAN id in VFVFB + * @vlan_on: boolean flag to turn on/off VLAN in VFVF + * @vfta_changed: pointer to boolean flag which indicates whether VFTA + * should be changed + * + * Turn on/off specified bit in VLVF table. + **/ +static int wx_set_vlvf(struct wx *wx, u32 vlan, u32 vind, bool vlan_on, + bool *vfta_changed) +{ + int vlvf_index; + u32 vt, bits; + + /* If VT Mode is set + * Either vlan_on + * make sure the vlan is in VLVF + * set the vind bit in the matching VLVFB + * Or !vlan_on + * clear the pool bit and possibly the vind + */ + vt = rd32(wx, WX_CFG_PORT_CTL); + if (!(vt & WX_CFG_PORT_CTL_NUM_VT_MASK)) + return 0; + + vlvf_index = wx_find_vlvf_slot(wx, vlan); + if (vlvf_index < 0) + return vlvf_index; + + wr32(wx, WX_PSR_VLAN_SWC_IDX, vlvf_index); + if (vlan_on) { + /* set the pool bit */ + if (vind < 32) { + bits = rd32(wx, WX_PSR_VLAN_SWC_VM_L); + bits |= (1 << vind); + wr32(wx, WX_PSR_VLAN_SWC_VM_L, bits); + } else { + bits = rd32(wx, WX_PSR_VLAN_SWC_VM_H); + bits |= (1 << (vind - 32)); + wr32(wx, WX_PSR_VLAN_SWC_VM_H, bits); + } + } else { + /* clear the pool bit */ + if (vind < 32) { + bits = rd32(wx, WX_PSR_VLAN_SWC_VM_L); + bits &= ~(1 << vind); + wr32(wx, WX_PSR_VLAN_SWC_VM_L, bits); + bits |= rd32(wx, WX_PSR_VLAN_SWC_VM_H); + } else { + bits = rd32(wx, WX_PSR_VLAN_SWC_VM_H); + bits &= ~(1 << (vind - 32)); + wr32(wx, WX_PSR_VLAN_SWC_VM_H, bits); + bits |= rd32(wx, WX_PSR_VLAN_SWC_VM_L); + } + } + + if (bits) { + wr32(wx, WX_PSR_VLAN_SWC, (WX_PSR_VLAN_SWC_VIEN | vlan)); + if (!vlan_on && vfta_changed) + *vfta_changed = false; + } else { + wr32(wx, WX_PSR_VLAN_SWC, 0); + } + + return 0; +} + +/** + * wx_set_vfta - Set VLAN filter table + * @wx: pointer to hardware structure + * @vlan: VLAN id to write to VLAN filter + * @vind: VMDq output index that maps queue to VLAN id in VFVFB + * @vlan_on: boolean flag to turn on/off VLAN in VFVF + * + * Turn on/off specified VLAN in the VLAN filter table. + **/ +static int wx_set_vfta(struct wx *wx, u32 vlan, u32 vind, bool vlan_on) +{ + u32 bitindex, vfta, targetbit; + bool vfta_changed = false; + int regindex, ret; + + /* this is a 2 part operation - first the VFTA, then the + * VLVF and VLVFB if VT Mode is set + * We don't write the VFTA until we know the VLVF part succeeded. + */ + + /* Part 1 + * The VFTA is a bitstring made up of 128 32-bit registers + * that enable the particular VLAN id, much like the MTA: + * bits[11-5]: which register + * bits[4-0]: which bit in the register + */ + regindex = (vlan >> 5) & 0x7F; + bitindex = vlan & 0x1F; + targetbit = (1 << bitindex); + /* errata 5 */ + vfta = wx->mac.vft_shadow[regindex]; + if (vlan_on) { + if (!(vfta & targetbit)) { + vfta |= targetbit; + vfta_changed = true; + } + } else { + if ((vfta & targetbit)) { + vfta &= ~targetbit; + vfta_changed = true; + } + } + /* Part 2 + * Call wx_set_vlvf to set VLVFB and VLVF + */ + ret = wx_set_vlvf(wx, vlan, vind, vlan_on, &vfta_changed); + if (ret != 0) + return ret; + + if (vfta_changed) + wr32(wx, WX_PSR_VLAN_TBL(regindex), vfta); + wx->mac.vft_shadow[regindex] = vfta; + + return 0; +} + +/** + * wx_clear_vfta - Clear VLAN filter table + * @wx: pointer to hardware structure + * + * Clears the VLAN filer table, and the VMDq index associated with the filter + **/ +static void wx_clear_vfta(struct wx *wx) +{ + u32 offset; + + for (offset = 0; offset < wx->mac.vft_size; offset++) { + wr32(wx, WX_PSR_VLAN_TBL(offset), 0); + wx->mac.vft_shadow[offset] = 0; + } + + for (offset = 0; offset < WX_PSR_VLAN_SWC_ENTRIES; offset++) { + wr32(wx, WX_PSR_VLAN_SWC_IDX, offset); + wr32(wx, WX_PSR_VLAN_SWC, 0); + wr32(wx, WX_PSR_VLAN_SWC_VM_L, 0); + wr32(wx, WX_PSR_VLAN_SWC_VM_H, 0); + } +} + +int wx_vlan_rx_add_vid(struct net_device *netdev, + __be16 proto, u16 vid) +{ + struct wx *wx = netdev_priv(netdev); + + /* add VID to filter table */ + wx_set_vfta(wx, vid, VMDQ_P(0), true); + set_bit(vid, wx->active_vlans); + + return 0; +} +EXPORT_SYMBOL(wx_vlan_rx_add_vid); + +int wx_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) +{ + struct wx *wx = netdev_priv(netdev); + + /* remove VID from filter table */ + if (vid) + wx_set_vfta(wx, vid, VMDQ_P(0), false); + clear_bit(vid, wx->active_vlans); + + return 0; +} +EXPORT_SYMBOL(wx_vlan_rx_kill_vid); + +/** + * wx_start_hw - Prepare hardware for Tx/Rx + * @wx: pointer to hardware structure + * + * Starts the hardware using the generic start_hw function + * and the generation start_hw function. + * Then performs revision-specific operations, if any. + **/ +void wx_start_hw(struct wx *wx) +{ + int i; + + /* Clear the VLAN filter table */ + wx_clear_vfta(wx); + WX_WRITE_FLUSH(wx); + /* Clear the rate limiters */ + for (i = 0; i < wx->mac.max_tx_queues; i++) { + wr32(wx, WX_TDM_RP_IDX, i); + wr32(wx, WX_TDM_RP_RATE, 0); + } +} +EXPORT_SYMBOL(wx_start_hw); + MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.h b/drivers/net/ethernet/wangxun/libwx/wx_hw.h index c173c56f0ab5..1f93ca32c921 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.h @@ -26,10 +26,13 @@ void wx_set_rx_mode(struct net_device *netdev); int wx_change_mtu(struct net_device *netdev, int new_mtu); void wx_disable_rx_queue(struct wx *wx, struct wx_ring *ring); void wx_configure(struct wx *wx); +void wx_start_hw(struct wx *wx); int wx_disable_pcie_master(struct wx *wx); int wx_stop_adapter(struct wx *wx); void wx_reset_misc(struct wx *wx); int wx_get_pcie_msix_counts(struct wx *wx, u16 *msix_count, u16 max_msix_count); int wx_sw_init(struct wx *wx); +int wx_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid); +int wx_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid); #endif /* _WX_HW_H_ */ diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c index 1e8d8b7b0c62..2c3f08be8c37 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c @@ -2,14 +2,157 @@ /* Copyright (c) 2019 - 2022 Beijing WangXun Technology Co., Ltd. */ #include <linux/etherdevice.h> +#include <net/ip6_checksum.h> #include <net/page_pool.h> +#include <net/inet_ecn.h> #include <linux/iopoll.h> +#include <linux/sctp.h> #include <linux/pci.h> +#include <net/tcp.h> +#include <net/ip.h> #include "wx_type.h" #include "wx_lib.h" #include "wx_hw.h" +/* Lookup table mapping the HW PTYPE to the bit field for decoding */ +static struct wx_dec_ptype wx_ptype_lookup[256] = { + /* L2: mac */ + [0x11] = WX_PTT(L2, NONE, NONE, NONE, NONE, PAY2), + [0x12] = WX_PTT(L2, NONE, NONE, NONE, TS, PAY2), + [0x13] = WX_PTT(L2, NONE, NONE, NONE, NONE, PAY2), + [0x14] = WX_PTT(L2, NONE, NONE, NONE, NONE, PAY2), + [0x15] = WX_PTT(L2, NONE, NONE, NONE, NONE, NONE), + [0x16] = WX_PTT(L2, NONE, NONE, NONE, NONE, PAY2), + [0x17] = WX_PTT(L2, NONE, NONE, NONE, NONE, NONE), + + /* L2: ethertype filter */ + [0x18 ... 0x1F] = WX_PTT(L2, NONE, NONE, NONE, NONE, NONE), + + /* L3: ip non-tunnel */ + [0x21] = WX_PTT(IP, FGV4, NONE, NONE, NONE, PAY3), + [0x22] = WX_PTT(IP, IPV4, NONE, NONE, NONE, PAY3), + [0x23] = WX_PTT(IP, IPV4, NONE, NONE, UDP, PAY4), + [0x24] = WX_PTT(IP, IPV4, NONE, NONE, TCP, PAY4), + [0x25] = WX_PTT(IP, IPV4, NONE, NONE, SCTP, PAY4), + [0x29] = WX_PTT(IP, FGV6, NONE, NONE, NONE, PAY3), + [0x2A] = WX_PTT(IP, IPV6, NONE, NONE, NONE, PAY3), + [0x2B] = WX_PTT(IP, IPV6, NONE, NONE, UDP, PAY3), + [0x2C] = WX_PTT(IP, IPV6, NONE, NONE, TCP, PAY4), + [0x2D] = WX_PTT(IP, IPV6, NONE, NONE, SCTP, PAY4), + + /* L2: fcoe */ + [0x30 ... 0x34] = WX_PTT(FCOE, NONE, NONE, NONE, NONE, PAY3), + [0x38 ... 0x3C] = WX_PTT(FCOE, NONE, NONE, NONE, NONE, PAY3), + + /* IPv4 --> IPv4/IPv6 */ + [0x81] = WX_PTT(IP, IPV4, IPIP, FGV4, NONE, PAY3), + [0x82] = WX_PTT(IP, IPV4, IPIP, IPV4, NONE, PAY3), + [0x83] = WX_PTT(IP, IPV4, IPIP, IPV4, UDP, PAY4), + [0x84] = WX_PTT(IP, IPV4, IPIP, IPV4, TCP, PAY4), + [0x85] = WX_PTT(IP, IPV4, IPIP, IPV4, SCTP, PAY4), + [0x89] = WX_PTT(IP, IPV4, IPIP, FGV6, NONE, PAY3), + [0x8A] = WX_PTT(IP, IPV4, IPIP, IPV6, NONE, PAY3), + [0x8B] = WX_PTT(IP, IPV4, IPIP, IPV6, UDP, PAY4), + [0x8C] = WX_PTT(IP, IPV4, IPIP, IPV6, TCP, PAY4), + [0x8D] = WX_PTT(IP, IPV4, IPIP, IPV6, SCTP, PAY4), + + /* IPv4 --> GRE/NAT --> NONE/IPv4/IPv6 */ + [0x90] = WX_PTT(IP, IPV4, IG, NONE, NONE, PAY3), + [0x91] = WX_PTT(IP, IPV4, IG, FGV4, NONE, PAY3), + [0x92] = WX_PTT(IP, IPV4, IG, IPV4, NONE, PAY3), + [0x93] = WX_PTT(IP, IPV4, IG, IPV4, UDP, PAY4), + [0x94] = WX_PTT(IP, IPV4, IG, IPV4, TCP, PAY4), + [0x95] = WX_PTT(IP, IPV4, IG, IPV4, SCTP, PAY4), + [0x99] = WX_PTT(IP, IPV4, IG, FGV6, NONE, PAY3), + [0x9A] = WX_PTT(IP, IPV4, IG, IPV6, NONE, PAY3), + [0x9B] = WX_PTT(IP, IPV4, IG, IPV6, UDP, PAY4), + [0x9C] = WX_PTT(IP, IPV4, IG, IPV6, TCP, PAY4), + [0x9D] = WX_PTT(IP, IPV4, IG, IPV6, SCTP, PAY4), + + /* IPv4 --> GRE/NAT --> MAC --> NONE/IPv4/IPv6 */ + [0xA0] = WX_PTT(IP, IPV4, IGM, NONE, NONE, PAY3), + [0xA1] = WX_PTT(IP, IPV4, IGM, FGV4, NONE, PAY3), + [0xA2] = WX_PTT(IP, IPV4, IGM, IPV4, NONE, PAY3), + [0xA3] = WX_PTT(IP, IPV4, IGM, IPV4, UDP, PAY4), + [0xA4] = WX_PTT(IP, IPV4, IGM, IPV4, TCP, PAY4), + [0xA5] = WX_PTT(IP, IPV4, IGM, IPV4, SCTP, PAY4), + [0xA9] = WX_PTT(IP, IPV4, IGM, FGV6, NONE, PAY3), + [0xAA] = WX_PTT(IP, IPV4, IGM, IPV6, NONE, PAY3), + [0xAB] = WX_PTT(IP, IPV4, IGM, IPV6, UDP, PAY4), + [0xAC] = WX_PTT(IP, IPV4, IGM, IPV6, TCP, PAY4), + [0xAD] = WX_PTT(IP, IPV4, IGM, IPV6, SCTP, PAY4), + + /* IPv4 --> GRE/NAT --> MAC+VLAN --> NONE/IPv4/IPv6 */ + [0xB0] = WX_PTT(IP, IPV4, IGMV, NONE, NONE, PAY3), + [0xB1] = WX_PTT(IP, IPV4, IGMV, FGV4, NONE, PAY3), + [0xB2] = WX_PTT(IP, IPV4, IGMV, IPV4, NONE, PAY3), + [0xB3] = WX_PTT(IP, IPV4, IGMV, IPV4, UDP, PAY4), + [0xB4] = WX_PTT(IP, IPV4, IGMV, IPV4, TCP, PAY4), + [0xB5] = WX_PTT(IP, IPV4, IGMV, IPV4, SCTP, PAY4), + [0xB9] = WX_PTT(IP, IPV4, IGMV, FGV6, NONE, PAY3), + [0xBA] = WX_PTT(IP, IPV4, IGMV, IPV6, NONE, PAY3), + [0xBB] = WX_PTT(IP, IPV4, IGMV, IPV6, UDP, PAY4), + [0xBC] = WX_PTT(IP, IPV4, IGMV, IPV6, TCP, PAY4), + [0xBD] = WX_PTT(IP, IPV4, IGMV, IPV6, SCTP, PAY4), + + /* IPv6 --> IPv4/IPv6 */ + [0xC1] = WX_PTT(IP, IPV6, IPIP, FGV4, NONE, PAY3), + [0xC2] = WX_PTT(IP, IPV6, IPIP, IPV4, NONE, PAY3), + [0xC3] = WX_PTT(IP, IPV6, IPIP, IPV4, UDP, PAY4), + [0xC4] = WX_PTT(IP, IPV6, IPIP, IPV4, TCP, PAY4), + [0xC5] = WX_PTT(IP, IPV6, IPIP, IPV4, SCTP, PAY4), + [0xC9] = WX_PTT(IP, IPV6, IPIP, FGV6, NONE, PAY3), + [0xCA] = WX_PTT(IP, IPV6, IPIP, IPV6, NONE, PAY3), + [0xCB] = WX_PTT(IP, IPV6, IPIP, IPV6, UDP, PAY4), + [0xCC] = WX_PTT(IP, IPV6, IPIP, IPV6, TCP, PAY4), + [0xCD] = WX_PTT(IP, IPV6, IPIP, IPV6, SCTP, PAY4), + + /* IPv6 --> GRE/NAT -> NONE/IPv4/IPv6 */ + [0xD0] = WX_PTT(IP, IPV6, IG, NONE, NONE, PAY3), + [0xD1] = WX_PTT(IP, IPV6, IG, FGV4, NONE, PAY3), + [0xD2] = WX_PTT(IP, IPV6, IG, IPV4, NONE, PAY3), + [0xD3] = WX_PTT(IP, IPV6, IG, IPV4, UDP, PAY4), + [0xD4] = WX_PTT(IP, IPV6, IG, IPV4, TCP, PAY4), + [0xD5] = WX_PTT(IP, IPV6, IG, IPV4, SCTP, PAY4), + [0xD9] = WX_PTT(IP, IPV6, IG, FGV6, NONE, PAY3), + [0xDA] = WX_PTT(IP, IPV6, IG, IPV6, NONE, PAY3), + [0xDB] = WX_PTT(IP, IPV6, IG, IPV6, UDP, PAY4), + [0xDC] = WX_PTT(IP, IPV6, IG, IPV6, TCP, PAY4), + [0xDD] = WX_PTT(IP, IPV6, IG, IPV6, SCTP, PAY4), + + /* IPv6 --> GRE/NAT -> MAC -> NONE/IPv4/IPv6 */ + [0xE0] = WX_PTT(IP, IPV6, IGM, NONE, NONE, PAY3), + [0xE1] = WX_PTT(IP, IPV6, IGM, FGV4, NONE, PAY3), + [0xE2] = WX_PTT(IP, IPV6, IGM, IPV4, NONE, PAY3), + [0xE3] = WX_PTT(IP, IPV6, IGM, IPV4, UDP, PAY4), + [0xE4] = WX_PTT(IP, IPV6, IGM, IPV4, TCP, PAY4), + [0xE5] = WX_PTT(IP, IPV6, IGM, IPV4, SCTP, PAY4), + [0xE9] = WX_PTT(IP, IPV6, IGM, FGV6, NONE, PAY3), + [0xEA] = WX_PTT(IP, IPV6, IGM, IPV6, NONE, PAY3), + [0xEB] = WX_PTT(IP, IPV6, IGM, IPV6, UDP, PAY4), + [0xEC] = WX_PTT(IP, IPV6, IGM, IPV6, TCP, PAY4), + [0xED] = WX_PTT(IP, IPV6, IGM, IPV6, SCTP, PAY4), + + /* IPv6 --> GRE/NAT -> MAC--> NONE/IPv */ + [0xF0] = WX_PTT(IP, IPV6, IGMV, NONE, NONE, PAY3), + [0xF1] = WX_PTT(IP, IPV6, IGMV, FGV4, NONE, PAY3), + [0xF2] = WX_PTT(IP, IPV6, IGMV, IPV4, NONE, PAY3), + [0xF3] = WX_PTT(IP, IPV6, IGMV, IPV4, UDP, PAY4), + [0xF4] = WX_PTT(IP, IPV6, IGMV, IPV4, TCP, PAY4), + [0xF5] = WX_PTT(IP, IPV6, IGMV, IPV4, SCTP, PAY4), + [0xF9] = WX_PTT(IP, IPV6, IGMV, FGV6, NONE, PAY3), + [0xFA] = WX_PTT(IP, IPV6, IGMV, IPV6, NONE, PAY3), + [0xFB] = WX_PTT(IP, IPV6, IGMV, IPV6, UDP, PAY4), + [0xFC] = WX_PTT(IP, IPV6, IGMV, IPV6, TCP, PAY4), + [0xFD] = WX_PTT(IP, IPV6, IGMV, IPV6, SCTP, PAY4), +}; + +static struct wx_dec_ptype wx_decode_ptype(const u8 ptype) +{ + return wx_ptype_lookup[ptype]; +} + /* wx_test_staterr - tests bits in Rx descriptor status and error fields */ static __le32 wx_test_staterr(union wx_rx_desc *rx_desc, const u32 stat_err_bits) @@ -419,6 +562,116 @@ static bool wx_cleanup_headers(struct wx_ring *rx_ring, return false; } +static void wx_rx_hash(struct wx_ring *ring, + union wx_rx_desc *rx_desc, + struct sk_buff *skb) +{ + u16 rss_type; + + if (!(ring->netdev->features & NETIF_F_RXHASH)) + return; + + rss_type = le16_to_cpu(rx_desc->wb.lower.lo_dword.hs_rss.pkt_info) & + WX_RXD_RSSTYPE_MASK; + + if (!rss_type) + return; + + skb_set_hash(skb, le32_to_cpu(rx_desc->wb.lower.hi_dword.rss), + (WX_RSS_L4_TYPES_MASK & (1ul << rss_type)) ? + PKT_HASH_TYPE_L4 : PKT_HASH_TYPE_L3); +} + +/** + * wx_rx_checksum - indicate in skb if hw indicated a good cksum + * @ring: structure containing ring specific data + * @rx_desc: current Rx descriptor being processed + * @skb: skb currently being received and modified + **/ +static void wx_rx_checksum(struct wx_ring *ring, + union wx_rx_desc *rx_desc, + struct sk_buff *skb) +{ + struct wx_dec_ptype dptype = wx_decode_ptype(WX_RXD_PKTTYPE(rx_desc)); + + skb_checksum_none_assert(skb); + /* Rx csum disabled */ + if (!(ring->netdev->features & NETIF_F_RXCSUM)) + return; + + /* if IPv4 header checksum error */ + if ((wx_test_staterr(rx_desc, WX_RXD_STAT_IPCS) && + wx_test_staterr(rx_desc, WX_RXD_ERR_IPE)) || + (wx_test_staterr(rx_desc, WX_RXD_STAT_OUTERIPCS) && + wx_test_staterr(rx_desc, WX_RXD_ERR_OUTERIPER))) { + ring->rx_stats.csum_err++; + return; + } + + /* L4 checksum offload flag must set for the below code to work */ + if (!wx_test_staterr(rx_desc, WX_RXD_STAT_L4CS)) + return; + + /* Hardware can't guarantee csum if IPv6 Dest Header found */ + if (dptype.prot != WX_DEC_PTYPE_PROT_SCTP && WX_RXD_IPV6EX(rx_desc)) + return; + + /* if L4 checksum error */ + if (wx_test_staterr(rx_desc, WX_RXD_ERR_TCPE)) { + ring->rx_stats.csum_err++; + return; + } + + /* It must be a TCP or UDP or SCTP packet with a valid checksum */ + skb->ip_summed = CHECKSUM_UNNECESSARY; + + /* If there is an outer header present that might contain a checksum + * we need to bump the checksum level by 1 to reflect the fact that + * we are indicating we validated the inner checksum. + */ + if (dptype.etype >= WX_DEC_PTYPE_ETYPE_IG) + __skb_incr_checksum_unnecessary(skb); + ring->rx_stats.csum_good_cnt++; +} + +static void wx_rx_vlan(struct wx_ring *ring, union wx_rx_desc *rx_desc, + struct sk_buff *skb) +{ + u16 ethertype; + u8 idx = 0; + + if ((ring->netdev->features & + (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX)) && + wx_test_staterr(rx_desc, WX_RXD_STAT_VP)) { + idx = (le16_to_cpu(rx_desc->wb.lower.lo_dword.hs_rss.pkt_info) & + 0x1c0) >> 6; + ethertype = ring->q_vector->wx->tpid[idx]; + __vlan_hwaccel_put_tag(skb, htons(ethertype), + le16_to_cpu(rx_desc->wb.upper.vlan)); + } +} + +/** + * wx_process_skb_fields - Populate skb header fields from Rx descriptor + * @rx_ring: rx descriptor ring packet is being transacted on + * @rx_desc: pointer to the EOP Rx descriptor + * @skb: pointer to current skb being populated + * + * This function checks the ring, descriptor, and packet information in + * order to populate the hash, checksum, protocol, and + * other fields within the skb. + **/ +static void wx_process_skb_fields(struct wx_ring *rx_ring, + union wx_rx_desc *rx_desc, + struct sk_buff *skb) +{ + wx_rx_hash(rx_ring, rx_desc, skb); + wx_rx_checksum(rx_ring, rx_desc, skb); + wx_rx_vlan(rx_ring, rx_desc, skb); + skb_record_rx_queue(skb, rx_ring->queue_index); + skb->protocol = eth_type_trans(skb, rx_ring->netdev); +} + /** * wx_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf * @q_vector: structure containing interrupt and ring information @@ -486,8 +739,8 @@ static int wx_clean_rx_irq(struct wx_q_vector *q_vector, /* probably a little skewed due to removing CRC */ total_rx_bytes += skb->len; - skb_record_rx_queue(skb, rx_ring->queue_index); - skb->protocol = eth_type_trans(skb, rx_ring->netdev); + /* populate checksum, timestamp, VLAN, and protocol */ + wx_process_skb_fields(rx_ring, rx_desc, skb); napi_gro_receive(&q_vector->napi, skb); /* update budget accounting */ @@ -707,11 +960,50 @@ static int wx_maybe_stop_tx(struct wx_ring *tx_ring, u16 size) return 0; } +static u32 wx_tx_cmd_type(u32 tx_flags) +{ + /* set type for advanced descriptor with frame checksum insertion */ + u32 cmd_type = WX_TXD_DTYP_DATA | WX_TXD_IFCS; + + /* set HW vlan bit if vlan is present */ + cmd_type |= WX_SET_FLAG(tx_flags, WX_TX_FLAGS_HW_VLAN, WX_TXD_VLE); + /* set segmentation enable bits for TSO/FSO */ + cmd_type |= WX_SET_FLAG(tx_flags, WX_TX_FLAGS_TSO, WX_TXD_TSE); + /* set timestamp bit if present */ + cmd_type |= WX_SET_FLAG(tx_flags, WX_TX_FLAGS_TSTAMP, WX_TXD_MAC_TSTAMP); + cmd_type |= WX_SET_FLAG(tx_flags, WX_TX_FLAGS_LINKSEC, WX_TXD_LINKSEC); + + return cmd_type; +} + +static void wx_tx_olinfo_status(union wx_tx_desc *tx_desc, + u32 tx_flags, unsigned int paylen) +{ + u32 olinfo_status = paylen << WX_TXD_PAYLEN_SHIFT; + + /* enable L4 checksum for TSO and TX checksum offload */ + olinfo_status |= WX_SET_FLAG(tx_flags, WX_TX_FLAGS_CSUM, WX_TXD_L4CS); + /* enable IPv4 checksum for TSO */ + olinfo_status |= WX_SET_FLAG(tx_flags, WX_TX_FLAGS_IPV4, WX_TXD_IIPCS); + /* enable outer IPv4 checksum for TSO */ + olinfo_status |= WX_SET_FLAG(tx_flags, WX_TX_FLAGS_OUTER_IPV4, + WX_TXD_EIPCS); + /* Check Context must be set if Tx switch is enabled, which it + * always is for case where virtual functions are running + */ + olinfo_status |= WX_SET_FLAG(tx_flags, WX_TX_FLAGS_CC, WX_TXD_CC); + olinfo_status |= WX_SET_FLAG(tx_flags, WX_TX_FLAGS_IPSEC, + WX_TXD_IPSEC); + tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status); +} + static void wx_tx_map(struct wx_ring *tx_ring, - struct wx_tx_buffer *first) + struct wx_tx_buffer *first, + const u8 hdr_len) { struct sk_buff *skb = first->skb; struct wx_tx_buffer *tx_buffer; + u32 tx_flags = first->tx_flags; u16 i = tx_ring->next_to_use; unsigned int data_len, size; union wx_tx_desc *tx_desc; @@ -719,10 +1011,9 @@ static void wx_tx_map(struct wx_ring *tx_ring, dma_addr_t dma; u32 cmd_type; - cmd_type = WX_TXD_DTYP_DATA | WX_TXD_IFCS; + cmd_type = wx_tx_cmd_type(tx_flags); tx_desc = WX_TX_DESC(tx_ring, i); - - tx_desc->read.olinfo_status = cpu_to_le32(skb->len << WX_TXD_PAYLEN_SHIFT); + wx_tx_olinfo_status(tx_desc, tx_flags, skb->len - hdr_len); size = skb_headlen(skb); data_len = skb->data_len; @@ -838,12 +1129,399 @@ dma_error: tx_ring->next_to_use = i; } +static void wx_tx_ctxtdesc(struct wx_ring *tx_ring, u32 vlan_macip_lens, + u32 fcoe_sof_eof, u32 type_tucmd, u32 mss_l4len_idx) +{ + struct wx_tx_context_desc *context_desc; + u16 i = tx_ring->next_to_use; + + context_desc = WX_TX_CTXTDESC(tx_ring, i); + i++; + tx_ring->next_to_use = (i < tx_ring->count) ? i : 0; + + /* set bits to identify this as an advanced context descriptor */ + type_tucmd |= WX_TXD_DTYP_CTXT; + context_desc->vlan_macip_lens = cpu_to_le32(vlan_macip_lens); + context_desc->seqnum_seed = cpu_to_le32(fcoe_sof_eof); + context_desc->type_tucmd_mlhl = cpu_to_le32(type_tucmd); + context_desc->mss_l4len_idx = cpu_to_le32(mss_l4len_idx); +} + +static void wx_get_ipv6_proto(struct sk_buff *skb, int offset, u8 *nexthdr) +{ + struct ipv6hdr *hdr = (struct ipv6hdr *)(skb->data + offset); + + *nexthdr = hdr->nexthdr; + offset += sizeof(struct ipv6hdr); + while (ipv6_ext_hdr(*nexthdr)) { + struct ipv6_opt_hdr _hdr, *hp; + + if (*nexthdr == NEXTHDR_NONE) + return; + hp = skb_header_pointer(skb, offset, sizeof(_hdr), &_hdr); + if (!hp) + return; + if (*nexthdr == NEXTHDR_FRAGMENT) + break; + *nexthdr = hp->nexthdr; + } +} + +union network_header { + struct iphdr *ipv4; + struct ipv6hdr *ipv6; + void *raw; +}; + +static u8 wx_encode_tx_desc_ptype(const struct wx_tx_buffer *first) +{ + u8 tun_prot = 0, l4_prot = 0, ptype = 0; + struct sk_buff *skb = first->skb; + + if (skb->encapsulation) { + union network_header hdr; + + switch (first->protocol) { + case htons(ETH_P_IP): + tun_prot = ip_hdr(skb)->protocol; + ptype = WX_PTYPE_TUN_IPV4; + break; + case htons(ETH_P_IPV6): + wx_get_ipv6_proto(skb, skb_network_offset(skb), &tun_prot); + ptype = WX_PTYPE_TUN_IPV6; + break; + default: + return ptype; + } + + if (tun_prot == IPPROTO_IPIP) { + hdr.raw = (void *)inner_ip_hdr(skb); + ptype |= WX_PTYPE_PKT_IPIP; + } else if (tun_prot == IPPROTO_UDP) { + hdr.raw = (void *)inner_ip_hdr(skb); + if (skb->inner_protocol_type != ENCAP_TYPE_ETHER || + skb->inner_protocol != htons(ETH_P_TEB)) { + ptype |= WX_PTYPE_PKT_IG; + } else { + if (((struct ethhdr *)skb_inner_mac_header(skb))->h_proto + == htons(ETH_P_8021Q)) + ptype |= WX_PTYPE_PKT_IGMV; + else + ptype |= WX_PTYPE_PKT_IGM; + } + + } else if (tun_prot == IPPROTO_GRE) { + hdr.raw = (void *)inner_ip_hdr(skb); + if (skb->inner_protocol == htons(ETH_P_IP) || + skb->inner_protocol == htons(ETH_P_IPV6)) { + ptype |= WX_PTYPE_PKT_IG; + } else { + if (((struct ethhdr *)skb_inner_mac_header(skb))->h_proto + == htons(ETH_P_8021Q)) + ptype |= WX_PTYPE_PKT_IGMV; + else + ptype |= WX_PTYPE_PKT_IGM; + } + } else { + return ptype; + } + + switch (hdr.ipv4->version) { + case IPVERSION: + l4_prot = hdr.ipv4->protocol; + break; + case 6: + wx_get_ipv6_proto(skb, skb_inner_network_offset(skb), &l4_prot); + ptype |= WX_PTYPE_PKT_IPV6; + break; + default: + return ptype; + } + } else { + switch (first->protocol) { + case htons(ETH_P_IP): + l4_prot = ip_hdr(skb)->protocol; + ptype = WX_PTYPE_PKT_IP; + break; + case htons(ETH_P_IPV6): + wx_get_ipv6_proto(skb, skb_network_offset(skb), &l4_prot); + ptype = WX_PTYPE_PKT_IP | WX_PTYPE_PKT_IPV6; + break; + default: + return WX_PTYPE_PKT_MAC | WX_PTYPE_TYP_MAC; + } + } + switch (l4_prot) { + case IPPROTO_TCP: + ptype |= WX_PTYPE_TYP_TCP; + break; + case IPPROTO_UDP: + ptype |= WX_PTYPE_TYP_UDP; + break; + case IPPROTO_SCTP: + ptype |= WX_PTYPE_TYP_SCTP; + break; + default: + ptype |= WX_PTYPE_TYP_IP; + break; + } + + return ptype; +} + +static int wx_tso(struct wx_ring *tx_ring, struct wx_tx_buffer *first, + u8 *hdr_len, u8 ptype) +{ + u32 vlan_macip_lens, type_tucmd, mss_l4len_idx; + struct net_device *netdev = tx_ring->netdev; + u32 l4len, tunhdr_eiplen_tunlen = 0; + struct sk_buff *skb = first->skb; + bool enc = skb->encapsulation; + struct ipv6hdr *ipv6h; + struct tcphdr *tcph; + struct iphdr *iph; + u8 tun_prot = 0; + int err; + + if (skb->ip_summed != CHECKSUM_PARTIAL) + return 0; + + if (!skb_is_gso(skb)) + return 0; + + err = skb_cow_head(skb, 0); + if (err < 0) + return err; + + /* indicates the inner headers in the skbuff are valid. */ + iph = enc ? inner_ip_hdr(skb) : ip_hdr(skb); + if (iph->version == 4) { + tcph = enc ? inner_tcp_hdr(skb) : tcp_hdr(skb); + iph->tot_len = 0; + iph->check = 0; + tcph->check = ~csum_tcpudp_magic(iph->saddr, + iph->daddr, 0, + IPPROTO_TCP, 0); + first->tx_flags |= WX_TX_FLAGS_TSO | + WX_TX_FLAGS_CSUM | + WX_TX_FLAGS_IPV4 | + WX_TX_FLAGS_CC; + } else if (iph->version == 6 && skb_is_gso_v6(skb)) { + ipv6h = enc ? inner_ipv6_hdr(skb) : ipv6_hdr(skb); + tcph = enc ? inner_tcp_hdr(skb) : tcp_hdr(skb); + ipv6h->payload_len = 0; + tcph->check = ~csum_ipv6_magic(&ipv6h->saddr, + &ipv6h->daddr, 0, + IPPROTO_TCP, 0); + first->tx_flags |= WX_TX_FLAGS_TSO | + WX_TX_FLAGS_CSUM | + WX_TX_FLAGS_CC; + } + + /* compute header lengths */ + l4len = enc ? inner_tcp_hdrlen(skb) : tcp_hdrlen(skb); + *hdr_len = enc ? (skb_inner_transport_header(skb) - skb->data) : + skb_transport_offset(skb); + *hdr_len += l4len; + + /* update gso size and bytecount with header size */ + first->gso_segs = skb_shinfo(skb)->gso_segs; + first->bytecount += (first->gso_segs - 1) * *hdr_len; + + /* mss_l4len_id: use 0 as index for TSO */ + mss_l4len_idx = l4len << WX_TXD_L4LEN_SHIFT; + mss_l4len_idx |= skb_shinfo(skb)->gso_size << WX_TXD_MSS_SHIFT; + + /* vlan_macip_lens: HEADLEN, MACLEN, VLAN tag */ + if (enc) { + switch (first->protocol) { + case htons(ETH_P_IP): + tun_prot = ip_hdr(skb)->protocol; + first->tx_flags |= WX_TX_FLAGS_OUTER_IPV4; + break; + case htons(ETH_P_IPV6): + tun_prot = ipv6_hdr(skb)->nexthdr; + break; + default: + break; + } + switch (tun_prot) { + case IPPROTO_UDP: + tunhdr_eiplen_tunlen = WX_TXD_TUNNEL_UDP; + tunhdr_eiplen_tunlen |= ((skb_network_header_len(skb) >> 2) << + WX_TXD_OUTER_IPLEN_SHIFT) | + (((skb_inner_mac_header(skb) - + skb_transport_header(skb)) >> 1) << + WX_TXD_TUNNEL_LEN_SHIFT); + break; + case IPPROTO_GRE: + tunhdr_eiplen_tunlen = WX_TXD_TUNNEL_GRE; + tunhdr_eiplen_tunlen |= ((skb_network_header_len(skb) >> 2) << + WX_TXD_OUTER_IPLEN_SHIFT) | + (((skb_inner_mac_header(skb) - + skb_transport_header(skb)) >> 1) << + WX_TXD_TUNNEL_LEN_SHIFT); + break; + case IPPROTO_IPIP: + tunhdr_eiplen_tunlen = (((char *)inner_ip_hdr(skb) - + (char *)ip_hdr(skb)) >> 2) << + WX_TXD_OUTER_IPLEN_SHIFT; + break; + default: + break; + } + vlan_macip_lens = skb_inner_network_header_len(skb) >> 1; + } else { + vlan_macip_lens = skb_network_header_len(skb) >> 1; + } + + vlan_macip_lens |= skb_network_offset(skb) << WX_TXD_MACLEN_SHIFT; + vlan_macip_lens |= first->tx_flags & WX_TX_FLAGS_VLAN_MASK; + + type_tucmd = ptype << 24; + if (skb->vlan_proto == htons(ETH_P_8021AD) && + netdev->features & NETIF_F_HW_VLAN_STAG_TX) + type_tucmd |= WX_SET_FLAG(first->tx_flags, + WX_TX_FLAGS_HW_VLAN, + 0x1 << WX_TXD_TAG_TPID_SEL_SHIFT); + wx_tx_ctxtdesc(tx_ring, vlan_macip_lens, tunhdr_eiplen_tunlen, + type_tucmd, mss_l4len_idx); + + return 1; +} + +static void wx_tx_csum(struct wx_ring *tx_ring, struct wx_tx_buffer *first, + u8 ptype) +{ + u32 tunhdr_eiplen_tunlen = 0, vlan_macip_lens = 0; + struct net_device *netdev = tx_ring->netdev; + u32 mss_l4len_idx = 0, type_tucmd; + struct sk_buff *skb = first->skb; + u8 tun_prot = 0; + + if (skb->ip_summed != CHECKSUM_PARTIAL) { + if (!(first->tx_flags & WX_TX_FLAGS_HW_VLAN) && + !(first->tx_flags & WX_TX_FLAGS_CC)) + return; + vlan_macip_lens = skb_network_offset(skb) << + WX_TXD_MACLEN_SHIFT; + } else { + u8 l4_prot = 0; + union { + struct iphdr *ipv4; + struct ipv6hdr *ipv6; + u8 *raw; + } network_hdr; + union { + struct tcphdr *tcphdr; + u8 *raw; + } transport_hdr; + + if (skb->encapsulation) { + network_hdr.raw = skb_inner_network_header(skb); + transport_hdr.raw = skb_inner_transport_header(skb); + vlan_macip_lens = skb_network_offset(skb) << + WX_TXD_MACLEN_SHIFT; + switch (first->protocol) { + case htons(ETH_P_IP): + tun_prot = ip_hdr(skb)->protocol; + break; + case htons(ETH_P_IPV6): + tun_prot = ipv6_hdr(skb)->nexthdr; + break; + default: + return; + } + switch (tun_prot) { + case IPPROTO_UDP: + tunhdr_eiplen_tunlen = WX_TXD_TUNNEL_UDP; + tunhdr_eiplen_tunlen |= + ((skb_network_header_len(skb) >> 2) << + WX_TXD_OUTER_IPLEN_SHIFT) | + (((skb_inner_mac_header(skb) - + skb_transport_header(skb)) >> 1) << + WX_TXD_TUNNEL_LEN_SHIFT); + break; + case IPPROTO_GRE: + tunhdr_eiplen_tunlen = WX_TXD_TUNNEL_GRE; + tunhdr_eiplen_tunlen |= ((skb_network_header_len(skb) >> 2) << + WX_TXD_OUTER_IPLEN_SHIFT) | + (((skb_inner_mac_header(skb) - + skb_transport_header(skb)) >> 1) << + WX_TXD_TUNNEL_LEN_SHIFT); + break; + case IPPROTO_IPIP: + tunhdr_eiplen_tunlen = (((char *)inner_ip_hdr(skb) - + (char *)ip_hdr(skb)) >> 2) << + WX_TXD_OUTER_IPLEN_SHIFT; + break; + default: + break; + } + + } else { + network_hdr.raw = skb_network_header(skb); + transport_hdr.raw = skb_transport_header(skb); + vlan_macip_lens = skb_network_offset(skb) << + WX_TXD_MACLEN_SHIFT; + } + + switch (network_hdr.ipv4->version) { + case IPVERSION: + vlan_macip_lens |= (transport_hdr.raw - network_hdr.raw) >> 1; + l4_prot = network_hdr.ipv4->protocol; + break; + case 6: + vlan_macip_lens |= (transport_hdr.raw - network_hdr.raw) >> 1; + l4_prot = network_hdr.ipv6->nexthdr; + break; + default: + break; + } + + switch (l4_prot) { + case IPPROTO_TCP: + mss_l4len_idx = (transport_hdr.tcphdr->doff * 4) << + WX_TXD_L4LEN_SHIFT; + break; + case IPPROTO_SCTP: + mss_l4len_idx = sizeof(struct sctphdr) << + WX_TXD_L4LEN_SHIFT; + break; + case IPPROTO_UDP: + mss_l4len_idx = sizeof(struct udphdr) << + WX_TXD_L4LEN_SHIFT; + break; + default: + break; + } + + /* update TX checksum flag */ + first->tx_flags |= WX_TX_FLAGS_CSUM; + } + first->tx_flags |= WX_TX_FLAGS_CC; + /* vlan_macip_lens: MACLEN, VLAN tag */ + vlan_macip_lens |= first->tx_flags & WX_TX_FLAGS_VLAN_MASK; + + type_tucmd = ptype << 24; + if (skb->vlan_proto == htons(ETH_P_8021AD) && + netdev->features & NETIF_F_HW_VLAN_STAG_TX) + type_tucmd |= WX_SET_FLAG(first->tx_flags, + WX_TX_FLAGS_HW_VLAN, + 0x1 << WX_TXD_TAG_TPID_SEL_SHIFT); + wx_tx_ctxtdesc(tx_ring, vlan_macip_lens, tunhdr_eiplen_tunlen, + type_tucmd, mss_l4len_idx); +} + static netdev_tx_t wx_xmit_frame_ring(struct sk_buff *skb, struct wx_ring *tx_ring) { u16 count = TXD_USE_COUNT(skb_headlen(skb)); struct wx_tx_buffer *first; + u8 hdr_len = 0, ptype; unsigned short f; + u32 tx_flags = 0; + int tso; /* need: 1 descriptor per page * PAGE_SIZE/WX_MAX_DATA_PER_TXD, * + 1 desc for skb_headlen/WX_MAX_DATA_PER_TXD, @@ -864,7 +1542,29 @@ static netdev_tx_t wx_xmit_frame_ring(struct sk_buff *skb, first->bytecount = skb->len; first->gso_segs = 1; - wx_tx_map(tx_ring, first); + /* if we have a HW VLAN tag being added default to the HW one */ + if (skb_vlan_tag_present(skb)) { + tx_flags |= skb_vlan_tag_get(skb) << WX_TX_FLAGS_VLAN_SHIFT; + tx_flags |= WX_TX_FLAGS_HW_VLAN; + } + + /* record initial flags and protocol */ + first->tx_flags = tx_flags; + first->protocol = vlan_get_protocol(skb); + + ptype = wx_encode_tx_desc_ptype(first); + + tso = wx_tso(tx_ring, first, &hdr_len, ptype); + if (tso < 0) + goto out_drop; + else if (!tso) + wx_tx_csum(tx_ring, first, ptype); + wx_tx_map(tx_ring, first, hdr_len); + + return NETDEV_TX_OK; +out_drop: + dev_kfree_skb_any(first->skb); + first->skb = NULL; return NETDEV_TX_OK; } @@ -1348,7 +2048,8 @@ void wx_free_irq(struct wx *wx) free_irq(entry->vector, q_vector); } - free_irq(wx->msix_entries[vector].vector, wx); + if (wx->mac.type == wx_mac_em) + free_irq(wx->msix_entries[vector].vector, wx); } EXPORT_SYMBOL(wx_free_irq); @@ -2004,4 +2705,24 @@ void wx_get_stats64(struct net_device *netdev, } EXPORT_SYMBOL(wx_get_stats64); +int wx_set_features(struct net_device *netdev, netdev_features_t features) +{ + netdev_features_t changed = netdev->features ^ features; + struct wx *wx = netdev_priv(netdev); + + if (changed & NETIF_F_RXHASH) + wr32m(wx, WX_RDB_RA_CTL, WX_RDB_RA_CTL_RSS_EN, + WX_RDB_RA_CTL_RSS_EN); + else + wr32m(wx, WX_RDB_RA_CTL, WX_RDB_RA_CTL_RSS_EN, 0); + + if (changed & + (NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_STAG_RX)) + wx_set_rx_mode(netdev); + + return 1; +} +EXPORT_SYMBOL(wx_set_features); + MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.h b/drivers/net/ethernet/wangxun/libwx/wx_lib.h index 50ee41f1fa10..df1f4a5951f0 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_lib.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.h @@ -28,5 +28,6 @@ void wx_free_resources(struct wx *wx); int wx_setup_resources(struct wx *wx); void wx_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats); +int wx_set_features(struct net_device *netdev, netdev_features_t features); #endif /* _NGBE_LIB_H_ */ diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h index 32f952d93009..29dfb561887d 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_type.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h @@ -6,6 +6,8 @@ #include <linux/bitfield.h> #include <linux/netdevice.h> +#include <linux/if_vlan.h> +#include <net/ip.h> #define WX_NCSI_SUP 0x8000 #define WX_NCSI_MASK 0x8000 @@ -64,6 +66,8 @@ #define WX_CFG_PORT_CTL_QINQ BIT(2) #define WX_CFG_PORT_CTL_D_VLAN BIT(0) /* double vlan*/ #define WX_CFG_TAG_TPID(_i) (0x14430 + ((_i) * 4)) +#define WX_CFG_PORT_CTL_NUM_VT_MASK GENMASK(13, 12) /* number of TVs */ + /* GPIO Registers */ #define WX_GPIO_DR 0x14800 @@ -79,7 +83,9 @@ #define WX_GPIO_INTMASK 0x14834 #define WX_GPIO_INTTYPE_LEVEL 0x14838 #define WX_GPIO_POLARITY 0x1483C +#define WX_GPIO_INTSTATUS 0x14844 #define WX_GPIO_EOI 0x1484C +#define WX_GPIO_EXT 0x14850 /*********************** Transmit DMA registers **************************/ /* transmit global control */ @@ -87,6 +93,8 @@ /* TDM CTL BIT */ #define WX_TDM_CTL_TE BIT(0) /* Transmit Enable */ #define WX_TDM_PB_THRE(_i) (0x18020 + ((_i) * 4)) +#define WX_TDM_RP_IDX 0x1820C +#define WX_TDM_RP_RATE 0x18404 /***************************** RDB registers *********************************/ /* receive packet buffer */ @@ -105,6 +113,8 @@ #define WX_RDB_PL_CFG_L2HDR BIT(3) #define WX_RDB_PL_CFG_TUN_TUNHDR BIT(4) #define WX_RDB_PL_CFG_TUN_OUTL2HDR BIT(5) +#define WX_RDB_RA_CTL 0x194F4 +#define WX_RDB_RA_CTL_RSS_EN BIT(2) /* RSS Enable */ /******************************* PSR Registers *******************************/ /* psr control */ @@ -150,6 +160,9 @@ #define WX_PSR_LAN_FLEX_DW_H(_i) (0x15C04 + ((_i) * 16)) #define WX_PSR_LAN_FLEX_MSK(_i) (0x15C08 + ((_i) * 16)) +/* vlan tbl */ +#define WX_PSR_VLAN_TBL(_i) (0x16000 + ((_i) * 4)) + /* mac switcher */ #define WX_PSR_MAC_SWC_AD_L 0x16200 #define WX_PSR_MAC_SWC_AD_H 0x16204 @@ -161,6 +174,15 @@ #define WX_PSR_MAC_SWC_IDX 0x16210 #define WX_CLEAR_VMDQ_ALL 0xFFFFFFFFU +/* vlan switch */ +#define WX_PSR_VLAN_SWC 0x16220 +#define WX_PSR_VLAN_SWC_VM_L 0x16224 +#define WX_PSR_VLAN_SWC_VM_H 0x16228 +#define WX_PSR_VLAN_SWC_IDX 0x16230 /* 64 vlan entries */ +/* VLAN pool filtering masks */ +#define WX_PSR_VLAN_SWC_VIEN BIT(31) /* filter is valid */ +#define WX_PSR_VLAN_SWC_ENTRIES 64 + /********************************* RSEC **************************************/ /* general rsec */ #define WX_RSC_CTL 0x17000 @@ -255,6 +277,7 @@ #define WX_PX_RR_RP(_i) (0x0100C + ((_i) * 0x40)) #define WX_PX_RR_CFG(_i) (0x01010 + ((_i) * 0x40)) /* PX_RR_CFG bit definitions */ +#define WX_PX_RR_CFG_VLAN BIT(31) #define WX_PX_RR_CFG_SPLIT_MODE BIT(26) #define WX_PX_RR_CFG_RR_THER_SHIFT 16 #define WX_PX_RR_CFG_RR_HDR_SZ GENMASK(15, 12) @@ -296,6 +319,7 @@ #define WX_MAX_TXD 8192 #define WX_MAX_JUMBO_FRAME_SIZE 9432 /* max payload 9414 */ +#define VMDQ_P(p) p /* Supported Rx Buffer Sizes */ #define WX_RXBUFFER_256 256 /* Used for skb receive header */ @@ -315,17 +339,64 @@ #define TXD_USE_COUNT(S) DIV_ROUND_UP((S), WX_MAX_DATA_PER_TXD) #define DESC_NEEDED (MAX_SKB_FRAGS + 4) -/* Ether Types */ -#define WX_ETH_P_CNM 0x22E7 - #define WX_CFG_PORT_ST 0x14404 /******************* Receive Descriptor bit definitions **********************/ #define WX_RXD_STAT_DD BIT(0) /* Done */ #define WX_RXD_STAT_EOP BIT(1) /* End of Packet */ +#define WX_RXD_STAT_VP BIT(5) /* IEEE VLAN Pkt */ +#define WX_RXD_STAT_L4CS BIT(7) /* L4 xsum calculated */ +#define WX_RXD_STAT_IPCS BIT(8) /* IP xsum calculated */ +#define WX_RXD_STAT_OUTERIPCS BIT(10) /* Cloud IP xsum calculated*/ +#define WX_RXD_ERR_OUTERIPER BIT(26) /* CRC IP Header error */ #define WX_RXD_ERR_RXE BIT(29) /* Any MAC Error */ - +#define WX_RXD_ERR_TCPE BIT(30) /* TCP/UDP Checksum Error */ +#define WX_RXD_ERR_IPE BIT(31) /* IP Checksum Error */ + +/* RSS Hash results */ +#define WX_RXD_RSSTYPE_MASK GENMASK(3, 0) +#define WX_RXD_RSSTYPE_IPV4_TCP 0x00000001U +#define WX_RXD_RSSTYPE_IPV6_TCP 0x00000003U +#define WX_RXD_RSSTYPE_IPV4_SCTP 0x00000004U +#define WX_RXD_RSSTYPE_IPV6_SCTP 0x00000006U +#define WX_RXD_RSSTYPE_IPV4_UDP 0x00000007U +#define WX_RXD_RSSTYPE_IPV6_UDP 0x00000008U + +#define WX_RSS_L4_TYPES_MASK \ + ((1ul << WX_RXD_RSSTYPE_IPV4_TCP) | \ + (1ul << WX_RXD_RSSTYPE_IPV4_UDP) | \ + (1ul << WX_RXD_RSSTYPE_IPV4_SCTP) | \ + (1ul << WX_RXD_RSSTYPE_IPV6_TCP) | \ + (1ul << WX_RXD_RSSTYPE_IPV6_UDP) | \ + (1ul << WX_RXD_RSSTYPE_IPV6_SCTP)) +/* TUN */ +#define WX_PTYPE_TUN_IPV4 0x80 +#define WX_PTYPE_TUN_IPV6 0xC0 + +/* PKT for TUN */ +#define WX_PTYPE_PKT_IPIP 0x00 /* IP+IP */ +#define WX_PTYPE_PKT_IG 0x10 /* IP+GRE */ +#define WX_PTYPE_PKT_IGM 0x20 /* IP+GRE+MAC */ +#define WX_PTYPE_PKT_IGMV 0x30 /* IP+GRE+MAC+VLAN */ +/* PKT for !TUN */ +#define WX_PTYPE_PKT_MAC 0x10 +#define WX_PTYPE_PKT_IP 0x20 + +/* TYP for PKT=mac */ +#define WX_PTYPE_TYP_MAC 0x01 +/* TYP for PKT=ip */ +#define WX_PTYPE_PKT_IPV6 0x08 +#define WX_PTYPE_TYP_IPFRAG 0x01 +#define WX_PTYPE_TYP_IP 0x02 +#define WX_PTYPE_TYP_UDP 0x03 +#define WX_PTYPE_TYP_TCP 0x04 +#define WX_PTYPE_TYP_SCTP 0x05 + +#define WX_RXD_PKTTYPE(_rxd) \ + ((le32_to_cpu((_rxd)->wb.lower.lo_dword.data) >> 9) & 0xFF) +#define WX_RXD_IPV6EX(_rxd) \ + ((le32_to_cpu((_rxd)->wb.lower.lo_dword.data) >> 6) & 0x1) /*********************** Transmit Descriptor Config Masks ****************/ #define WX_TXD_STAT_DD BIT(0) /* Descriptor Done */ #define WX_TXD_DTYP_DATA 0 /* Adv Data Descriptor */ @@ -334,6 +405,113 @@ #define WX_TXD_IFCS BIT(25) /* Insert FCS */ #define WX_TXD_RS BIT(27) /* Report Status */ +/*********************** Adv Transmit Descriptor Config Masks ****************/ +#define WX_TXD_MAC_TSTAMP BIT(19) /* IEEE1588 time stamp */ +#define WX_TXD_DTYP_CTXT BIT(20) /* Adv Context Desc */ +#define WX_TXD_LINKSEC BIT(26) /* enable linksec */ +#define WX_TXD_VLE BIT(30) /* VLAN pkt enable */ +#define WX_TXD_TSE BIT(31) /* TCP Seg enable */ +#define WX_TXD_CC BIT(7) /* Check Context */ +#define WX_TXD_IPSEC BIT(8) /* enable ipsec esp */ +#define WX_TXD_L4CS BIT(9) +#define WX_TXD_IIPCS BIT(10) +#define WX_TXD_EIPCS BIT(11) +#define WX_TXD_PAYLEN_SHIFT 13 /* Adv desc PAYLEN shift */ +#define WX_TXD_MACLEN_SHIFT 9 /* Adv ctxt desc mac len shift */ +#define WX_TXD_TAG_TPID_SEL_SHIFT 11 + +#define WX_TXD_L4LEN_SHIFT 8 /* Adv ctxt L4LEN shift */ +#define WX_TXD_MSS_SHIFT 16 /* Adv ctxt MSS shift */ + +#define WX_TXD_OUTER_IPLEN_SHIFT 12 /* Adv ctxt OUTERIPLEN shift */ +#define WX_TXD_TUNNEL_LEN_SHIFT 21 /* Adv ctxt TUNNELLEN shift */ +#define WX_TXD_TUNNEL_TYPE_SHIFT 11 /* Adv Tx Desc Tunnel Type shift */ +#define WX_TXD_TUNNEL_UDP FIELD_PREP(BIT(WX_TXD_TUNNEL_TYPE_SHIFT), 0) +#define WX_TXD_TUNNEL_GRE FIELD_PREP(BIT(WX_TXD_TUNNEL_TYPE_SHIFT), 1) + +enum wx_tx_flags { + /* cmd_type flags */ + WX_TX_FLAGS_HW_VLAN = 0x01, + WX_TX_FLAGS_TSO = 0x02, + WX_TX_FLAGS_TSTAMP = 0x04, + + /* olinfo flags */ + WX_TX_FLAGS_CC = 0x08, + WX_TX_FLAGS_IPV4 = 0x10, + WX_TX_FLAGS_CSUM = 0x20, + WX_TX_FLAGS_OUTER_IPV4 = 0x100, + WX_TX_FLAGS_LINKSEC = 0x200, + WX_TX_FLAGS_IPSEC = 0x400, +}; + +/* VLAN info */ +#define WX_TX_FLAGS_VLAN_MASK GENMASK(31, 16) +#define WX_TX_FLAGS_VLAN_SHIFT 16 + +/* wx_dec_ptype.mac: outer mac */ +enum wx_dec_ptype_mac { + WX_DEC_PTYPE_MAC_IP = 0, + WX_DEC_PTYPE_MAC_L2 = 2, + WX_DEC_PTYPE_MAC_FCOE = 3, +}; + +/* wx_dec_ptype.[e]ip: outer&encaped ip */ +#define WX_DEC_PTYPE_IP_FRAG 0x4 +enum wx_dec_ptype_ip { + WX_DEC_PTYPE_IP_NONE = 0, + WX_DEC_PTYPE_IP_IPV4 = 1, + WX_DEC_PTYPE_IP_IPV6 = 2, + WX_DEC_PTYPE_IP_FGV4 = WX_DEC_PTYPE_IP_FRAG | WX_DEC_PTYPE_IP_IPV4, + WX_DEC_PTYPE_IP_FGV6 = WX_DEC_PTYPE_IP_FRAG | WX_DEC_PTYPE_IP_IPV6, +}; + +/* wx_dec_ptype.etype: encaped type */ +enum wx_dec_ptype_etype { + WX_DEC_PTYPE_ETYPE_NONE = 0, + WX_DEC_PTYPE_ETYPE_IPIP = 1, /* IP+IP */ + WX_DEC_PTYPE_ETYPE_IG = 2, /* IP+GRE */ + WX_DEC_PTYPE_ETYPE_IGM = 3, /* IP+GRE+MAC */ + WX_DEC_PTYPE_ETYPE_IGMV = 4, /* IP+GRE+MAC+VLAN */ +}; + +/* wx_dec_ptype.proto: payload proto */ +enum wx_dec_ptype_prot { + WX_DEC_PTYPE_PROT_NONE = 0, + WX_DEC_PTYPE_PROT_UDP = 1, + WX_DEC_PTYPE_PROT_TCP = 2, + WX_DEC_PTYPE_PROT_SCTP = 3, + WX_DEC_PTYPE_PROT_ICMP = 4, + WX_DEC_PTYPE_PROT_TS = 5, /* time sync */ +}; + +/* wx_dec_ptype.layer: payload layer */ +enum wx_dec_ptype_layer { + WX_DEC_PTYPE_LAYER_NONE = 0, + WX_DEC_PTYPE_LAYER_PAY2 = 1, + WX_DEC_PTYPE_LAYER_PAY3 = 2, + WX_DEC_PTYPE_LAYER_PAY4 = 3, +}; + +struct wx_dec_ptype { + u32 known:1; + u32 mac:2; /* outer mac */ + u32 ip:3; /* outer ip*/ + u32 etype:3; /* encaped type */ + u32 eip:3; /* encaped ip */ + u32 prot:4; /* payload proto */ + u32 layer:3; /* payload layer */ +}; + +/* macro to make the table lines short */ +#define WX_PTT(mac, ip, etype, eip, proto, layer)\ + {1, \ + WX_DEC_PTYPE_MAC_##mac, /* mac */\ + WX_DEC_PTYPE_IP_##ip, /* ip */ \ + WX_DEC_PTYPE_ETYPE_##etype, /* etype */\ + WX_DEC_PTYPE_IP_##eip, /* eip */\ + WX_DEC_PTYPE_PROT_##proto, /* proto */\ + WX_DEC_PTYPE_LAYER_##layer /* layer */} + /* Host Interface Command Structures */ struct wx_hic_hdr { u8 cmd; @@ -412,6 +590,8 @@ struct wx_mac_info { u32 mta_shadow[128]; s32 mc_filter_type; u32 mcft_size; + u32 vft_shadow[128]; + u32 vft_size; u32 num_rar_entries; u32 rx_pb_size; u32 tx_pb_size; @@ -508,10 +688,25 @@ union wx_rx_desc { } wb; /* writeback */ }; +struct wx_tx_context_desc { + __le32 vlan_macip_lens; + __le32 seqnum_seed; + __le32 type_tucmd_mlhl; + __le32 mss_l4len_idx; +}; + +/* if _flag is in _input, return _result */ +#define WX_SET_FLAG(_input, _flag, _result) \ + (((_flag) <= (_result)) ? \ + ((u32)((_input) & (_flag)) * ((_result) / (_flag))) : \ + ((u32)((_input) & (_flag)) / ((_flag) / (_result)))) + #define WX_RX_DESC(R, i) \ (&(((union wx_rx_desc *)((R)->desc))[i])) #define WX_TX_DESC(R, i) \ (&(((union wx_tx_desc *)((R)->desc))[i])) +#define WX_TX_CTXTDESC(R, i) \ + (&(((struct wx_tx_context_desc *)((R)->desc))[i])) /* wrapper around a pointer to a socket buffer, * so a DMA handle can be stored along with the buffer @@ -523,6 +718,8 @@ struct wx_tx_buffer { unsigned short gso_segs; DEFINE_DMA_UNMAP_ADDR(dma); DEFINE_DMA_UNMAP_LEN(len); + __be16 protocol; + u32 tx_flags; }; struct wx_rx_buffer { @@ -539,6 +736,11 @@ struct wx_queue_stats { u64 bytes; }; +struct wx_rx_queue_stats { + u64 csum_good_cnt; + u64 csum_err; +}; + /* iterator for handling rings in ring container */ #define wx_for_each_ring(posm, headm) \ for (posm = (headm).ring; posm; posm = posm->next) @@ -550,7 +752,6 @@ struct wx_ring_container { u8 count; /* total number of rings in vector */ u8 itr; /* current ITR setting for ring */ }; - struct wx_ring { struct wx_ring *next; /* pointer to next ring in q_vector */ struct wx_q_vector *q_vector; /* backpointer to host q_vector */ @@ -580,6 +781,9 @@ struct wx_ring { struct wx_queue_stats stats; struct u64_stats_sync syncp; + union { + struct wx_rx_queue_stats rx_stats; + }; } ____cacheline_internodealigned_in_smp; struct wx_q_vector { @@ -598,7 +802,7 @@ struct wx_q_vector { char name[IFNAMSIZ + 17]; /* for dynamic allocation of rings associated with this q_vector */ - struct wx_ring ring[0] ____cacheline_internodealigned_in_smp; + struct wx_ring ring[] ____cacheline_internodealigned_in_smp; }; enum wx_isb_idx { @@ -610,6 +814,9 @@ enum wx_isb_idx { }; struct wx { + unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; + + void *priv; u8 __iomem *hw_addr; struct pci_dev *pdev; struct net_device *netdev; @@ -642,6 +849,7 @@ struct wx { bool wol_enabled; bool ncsi_enabled; bool gpio_ctrl; + raw_spinlock_t gpio_lock; /* Tx fast path data */ int num_tx_queues; diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c index df6b870aa871..c99a5d3de72e 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c @@ -115,6 +115,7 @@ static int ngbe_sw_init(struct wx *wx) wx->mac.max_rx_queues = NGBE_MAX_RX_QUEUES; wx->mac.max_tx_queues = NGBE_MAX_TX_QUEUES; wx->mac.mcft_size = NGBE_MC_TBL_SIZE; + wx->mac.vft_size = NGBE_SP_VFT_TBL_SIZE; wx->mac.rx_pb_size = NGBE_RX_PB_SIZE; wx->mac.tx_pb_size = NGBE_TDB_PB_SZ; @@ -473,9 +474,12 @@ static const struct net_device_ops ngbe_netdev_ops = { .ndo_change_mtu = wx_change_mtu, .ndo_start_xmit = wx_xmit_frame, .ndo_set_rx_mode = wx_set_rx_mode, + .ndo_set_features = wx_set_features, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = wx_set_mac, .ndo_get_stats64 = wx_get_stats64, + .ndo_vlan_rx_add_vid = wx_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = wx_vlan_rx_kill_vid, }; /** @@ -551,12 +555,18 @@ static int ngbe_probe(struct pci_dev *pdev, ngbe_set_ethtool_ops(netdev); netdev->netdev_ops = &ngbe_netdev_ops; - netdev->features |= NETIF_F_HIGHDMA; - netdev->features = NETIF_F_SG; - + netdev->features = NETIF_F_SG | NETIF_F_IP_CSUM | + NETIF_F_TSO | NETIF_F_TSO6 | + NETIF_F_RXHASH | NETIF_F_RXCSUM; + netdev->features |= NETIF_F_SCTP_CRC | NETIF_F_TSO_MANGLEID; + netdev->vlan_features |= netdev->features; + netdev->features |= NETIF_F_IPV6_CSUM | NETIF_F_VLAN_FEATURES; /* copy netdev features into list of user selectable features */ - netdev->hw_features |= netdev->features | - NETIF_F_RXALL; + netdev->hw_features |= netdev->features | NETIF_F_RXALL; + netdev->hw_features |= NETIF_F_NTUPLE | NETIF_F_HW_TC; + netdev->features |= NETIF_F_HIGHDMA; + netdev->hw_features |= NETIF_F_GRO; + netdev->features |= NETIF_F_GRO; netdev->priv_flags |= IFF_UNICAST_FLT; netdev->priv_flags |= IFF_SUPP_NOFCS; diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h index 373d5af628cd..b70eca397b67 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h @@ -136,6 +136,7 @@ enum NGBE_MSCA_CMD_value { #define NGBE_RAR_ENTRIES 32 #define NGBE_RX_PB_SIZE 42 #define NGBE_MC_TBL_SIZE 128 +#define NGBE_SP_VFT_TBL_SIZE 128 #define NGBE_TDB_PB_SZ (20 * 1024) /* 160KB Packet Buffer */ /* TX/RX descriptor defines */ diff --git a/drivers/net/ethernet/wangxun/txgbe/Makefile b/drivers/net/ethernet/wangxun/txgbe/Makefile index 6db14a2cb2d0..7507f762edfe 100644 --- a/drivers/net/ethernet/wangxun/txgbe/Makefile +++ b/drivers/net/ethernet/wangxun/txgbe/Makefile @@ -8,4 +8,5 @@ obj-$(CONFIG_TXGBE) += txgbe.o txgbe-objs := txgbe_main.o \ txgbe_hw.o \ + txgbe_phy.o \ txgbe_ethtool.o diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c index d914e9a05404..859da112586a 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c @@ -6,11 +6,39 @@ #include <linux/netdevice.h> #include "../libwx/wx_ethtool.h" +#include "../libwx/wx_type.h" +#include "txgbe_type.h" #include "txgbe_ethtool.h" +static int txgbe_nway_reset(struct net_device *netdev) +{ + struct txgbe *txgbe = netdev_to_txgbe(netdev); + + return phylink_ethtool_nway_reset(txgbe->phylink); +} + +static int txgbe_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) +{ + struct txgbe *txgbe = netdev_to_txgbe(netdev); + + return phylink_ethtool_ksettings_get(txgbe->phylink, cmd); +} + +static int txgbe_set_link_ksettings(struct net_device *netdev, + const struct ethtool_link_ksettings *cmd) +{ + struct txgbe *txgbe = netdev_to_txgbe(netdev); + + return phylink_ethtool_ksettings_set(txgbe->phylink, cmd); +} + static const struct ethtool_ops txgbe_ethtool_ops = { .get_drvinfo = wx_get_drvinfo, + .nway_reset = txgbe_nway_reset, .get_link = ethtool_op_get_link, + .get_link_ksettings = txgbe_get_link_ksettings, + .set_link_ksettings = txgbe_set_link_ksettings, }; void txgbe_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c index 5b8a121fb496..46eba6d6188b 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c @@ -7,6 +7,7 @@ #include <linux/netdevice.h> #include <linux/string.h> #include <linux/etherdevice.h> +#include <linux/phylink.h> #include <net/ip.h> #include <linux/if_vlan.h> @@ -15,6 +16,7 @@ #include "../libwx/wx_hw.h" #include "txgbe_type.h" #include "txgbe_hw.h" +#include "txgbe_phy.h" #include "txgbe_ethtool.h" char txgbe_driver_name[] = "txgbe"; @@ -81,6 +83,8 @@ static int txgbe_enumerate_functions(struct wx *wx) **/ static void txgbe_irq_enable(struct wx *wx, bool queues) { + wr32(wx, WX_PX_MISC_IEN, TXGBE_PX_MISC_IEN_MASK); + /* unmask interrupt */ wx_intr_enable(wx, TXGBE_INTR_MISC(wx)); if (queues) @@ -128,17 +132,6 @@ static irqreturn_t txgbe_intr(int __always_unused irq, void *data) return IRQ_HANDLED; } -static irqreturn_t txgbe_msix_other(int __always_unused irq, void *data) -{ - struct wx *wx = data; - - /* re-enable the original interrupt state */ - if (netif_running(wx->netdev)) - txgbe_irq_enable(wx, false); - - return IRQ_HANDLED; -} - /** * txgbe_request_msix_irqs - Initialize MSI-X interrupts * @wx: board private structure @@ -170,13 +163,6 @@ static int txgbe_request_msix_irqs(struct wx *wx) } } - err = request_irq(wx->msix_entries[vector].vector, - txgbe_msix_other, 0, netdev->name, wx); - if (err) { - wx_err(wx, "request_irq for msix_other failed: %d\n", err); - goto free_queue_irqs; - } - return 0; free_queue_irqs: @@ -219,7 +205,8 @@ static int txgbe_request_irq(struct wx *wx) static void txgbe_up_complete(struct wx *wx) { - u32 reg; + struct net_device *netdev = wx->netdev; + struct txgbe *txgbe; wx_control_hw(wx, true); wx_configure_vectors(wx); @@ -228,24 +215,17 @@ static void txgbe_up_complete(struct wx *wx) smp_mb__before_atomic(); wx_napi_enable_all(wx); + txgbe = netdev_to_txgbe(netdev); + phylink_start(txgbe->phylink); + /* clear any pending interrupts, may auto mask */ rd32(wx, WX_PX_IC(0)); rd32(wx, WX_PX_IC(1)); rd32(wx, WX_PX_MISC_IC); txgbe_irq_enable(wx, true); - /* Configure MAC Rx and Tx when link is up */ - reg = rd32(wx, WX_MAC_RX_CFG); - wr32(wx, WX_MAC_RX_CFG, reg); - wr32(wx, WX_MAC_PKT_FLT, WX_MAC_PKT_FLT_PR); - reg = rd32(wx, WX_MAC_WDG_TIMEOUT); - wr32(wx, WX_MAC_WDG_TIMEOUT, reg); - reg = rd32(wx, WX_MAC_TX_CFG); - wr32(wx, WX_MAC_TX_CFG, (reg & ~WX_MAC_TX_CFG_SPEED_MASK) | WX_MAC_TX_CFG_SPEED_10G); - /* enable transmits */ - netif_tx_start_all_queues(wx->netdev); - netif_carrier_on(wx->netdev); + netif_tx_start_all_queues(netdev); } static void txgbe_reset(struct wx *wx) @@ -258,6 +238,7 @@ static void txgbe_reset(struct wx *wx) if (err != 0) wx_err(wx, "Hardware Error: %d\n", err); + wx_start_hw(wx); /* do not flush user set addresses */ memcpy(old_addr, &wx->mac_table[0].addr, netdev->addr_len); wx_flush_sw_mac_table(wx); @@ -279,7 +260,6 @@ static void txgbe_disable_device(struct wx *wx) wx_disable_rx_queue(wx, wx->rx_ring[i]); netif_tx_stop_all_queues(netdev); - netif_carrier_off(netdev); netif_tx_disable(netdev); wx_irq_disable(wx); @@ -310,8 +290,11 @@ static void txgbe_disable_device(struct wx *wx) static void txgbe_down(struct wx *wx) { + struct txgbe *txgbe = netdev_to_txgbe(wx->netdev); + txgbe_disable_device(wx); txgbe_reset(wx); + phylink_stop(txgbe->phylink); wx_clean_all_tx_rings(wx); wx_clean_all_rx_rings(wx); @@ -330,6 +313,7 @@ static int txgbe_sw_init(struct wx *wx) wx->mac.max_tx_queues = TXGBE_SP_MAX_TX_QUEUES; wx->mac.max_rx_queues = TXGBE_SP_MAX_RX_QUEUES; wx->mac.mcft_size = TXGBE_SP_MC_TBL_SIZE; + wx->mac.vft_size = TXGBE_SP_VFT_TBL_SIZE; wx->mac.rx_pb_size = TXGBE_SP_RX_PB_SIZE; wx->mac.tx_pb_size = TXGBE_SP_TDB_PB_SZ; @@ -455,7 +439,7 @@ static int txgbe_close(struct net_device *netdev) return 0; } -static void txgbe_dev_shutdown(struct pci_dev *pdev, bool *enable_wake) +static void txgbe_dev_shutdown(struct pci_dev *pdev) { struct wx *wx = pci_get_drvdata(pdev); struct net_device *netdev; @@ -475,12 +459,10 @@ static void txgbe_dev_shutdown(struct pci_dev *pdev, bool *enable_wake) static void txgbe_shutdown(struct pci_dev *pdev) { - bool wake; - - txgbe_dev_shutdown(pdev, &wake); + txgbe_dev_shutdown(pdev); if (system_state == SYSTEM_POWER_OFF) { - pci_wake_from_d3(pdev, wake); + pci_wake_from_d3(pdev, false); pci_set_power_state(pdev, PCI_D3hot); } } @@ -491,9 +473,12 @@ static const struct net_device_ops txgbe_netdev_ops = { .ndo_change_mtu = wx_change_mtu, .ndo_start_xmit = wx_xmit_frame, .ndo_set_rx_mode = wx_set_rx_mode, + .ndo_set_features = wx_set_features, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = wx_set_mac, .ndo_get_stats64 = wx_get_stats64, + .ndo_vlan_rx_add_vid = wx_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = wx_vlan_rx_kill_vid, }; /** @@ -513,6 +498,7 @@ static int txgbe_probe(struct pci_dev *pdev, struct net_device *netdev; int err, expected_gts; struct wx *wx = NULL; + struct txgbe *txgbe; u16 eeprom_verh = 0, eeprom_verl = 0, offset = 0; u16 eeprom_cfg_blkh = 0, eeprom_cfg_blkl = 0; @@ -596,11 +582,25 @@ static int txgbe_probe(struct pci_dev *pdev, goto err_free_mac_table; } - netdev->features |= NETIF_F_HIGHDMA; - netdev->features = NETIF_F_SG; - + netdev->features = NETIF_F_SG | + NETIF_F_TSO | + NETIF_F_TSO6 | + NETIF_F_RXHASH | + NETIF_F_RXCSUM | + NETIF_F_HW_CSUM; + + netdev->gso_partial_features = NETIF_F_GSO_ENCAP_ALL; + netdev->features |= netdev->gso_partial_features; + netdev->features |= NETIF_F_SCTP_CRC; + netdev->vlan_features |= netdev->features | NETIF_F_TSO_MANGLEID; + netdev->hw_enc_features |= netdev->vlan_features; + netdev->features |= NETIF_F_VLAN_FEATURES; /* copy netdev features into list of user selectable features */ netdev->hw_features |= netdev->features | NETIF_F_RXALL; + netdev->hw_features |= NETIF_F_NTUPLE | NETIF_F_HW_TC; + netdev->features |= NETIF_F_HIGHDMA; + netdev->hw_features |= NETIF_F_GRO; + netdev->features |= NETIF_F_GRO; netdev->priv_flags |= IFF_UNICAST_FLT; netdev->priv_flags |= IFF_SUPP_NOFCS; @@ -663,10 +663,23 @@ static int txgbe_probe(struct pci_dev *pdev, "0x%08x", etrack_id); } - err = register_netdev(netdev); + txgbe = devm_kzalloc(&pdev->dev, sizeof(*txgbe), GFP_KERNEL); + if (!txgbe) { + err = -ENOMEM; + goto err_release_hw; + } + + txgbe->wx = wx; + wx->priv = txgbe; + + err = txgbe_init_phy(txgbe); if (err) goto err_release_hw; + err = register_netdev(netdev); + if (err) + goto err_remove_phy; + pci_set_drvdata(pdev, wx); netif_tx_stop_all_queues(netdev); @@ -694,6 +707,8 @@ static int txgbe_probe(struct pci_dev *pdev, return 0; +err_remove_phy: + txgbe_remove_phy(txgbe); err_release_hw: wx_clear_interrupt_scheme(wx); wx_control_hw(wx, false); @@ -719,11 +734,14 @@ err_pci_disable_dev: static void txgbe_remove(struct pci_dev *pdev) { struct wx *wx = pci_get_drvdata(pdev); + struct txgbe *txgbe = wx->priv; struct net_device *netdev; netdev = wx->netdev; unregister_netdev(netdev); + txgbe_remove_phy(txgbe); + pci_release_selected_regions(pdev, pci_select_bars(pdev, IORESOURCE_MEM)); diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c new file mode 100644 index 000000000000..8779645a54be --- /dev/null +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c @@ -0,0 +1,673 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2015 - 2023 Beijing WangXun Technology Co., Ltd. */ + +#include <linux/gpio/machine.h> +#include <linux/gpio/driver.h> +#include <linux/gpio/property.h> +#include <linux/clk-provider.h> +#include <linux/clkdev.h> +#include <linux/i2c.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> +#include <linux/pcs/pcs-xpcs.h> +#include <linux/phylink.h> + +#include "../libwx/wx_type.h" +#include "../libwx/wx_lib.h" +#include "../libwx/wx_hw.h" +#include "txgbe_type.h" +#include "txgbe_phy.h" + +static int txgbe_swnodes_register(struct txgbe *txgbe) +{ + struct txgbe_nodes *nodes = &txgbe->nodes; + struct pci_dev *pdev = txgbe->wx->pdev; + struct software_node *swnodes; + u32 id; + + id = (pdev->bus->number << 8) | pdev->devfn; + + snprintf(nodes->gpio_name, sizeof(nodes->gpio_name), "txgbe_gpio-%x", id); + snprintf(nodes->i2c_name, sizeof(nodes->i2c_name), "txgbe_i2c-%x", id); + snprintf(nodes->sfp_name, sizeof(nodes->sfp_name), "txgbe_sfp-%x", id); + snprintf(nodes->phylink_name, sizeof(nodes->phylink_name), "txgbe_phylink-%x", id); + + swnodes = nodes->swnodes; + + /* GPIO 0: tx fault + * GPIO 1: tx disable + * GPIO 2: sfp module absent + * GPIO 3: rx signal lost + * GPIO 4: rate select, 1G(0) 10G(1) + * GPIO 5: rate select, 1G(0) 10G(1) + */ + nodes->gpio_props[0] = PROPERTY_ENTRY_STRING("pinctrl-names", "default"); + swnodes[SWNODE_GPIO] = NODE_PROP(nodes->gpio_name, nodes->gpio_props); + nodes->gpio0_ref[0] = SOFTWARE_NODE_REFERENCE(&swnodes[SWNODE_GPIO], 0, GPIO_ACTIVE_HIGH); + nodes->gpio1_ref[0] = SOFTWARE_NODE_REFERENCE(&swnodes[SWNODE_GPIO], 1, GPIO_ACTIVE_HIGH); + nodes->gpio2_ref[0] = SOFTWARE_NODE_REFERENCE(&swnodes[SWNODE_GPIO], 2, GPIO_ACTIVE_LOW); + nodes->gpio3_ref[0] = SOFTWARE_NODE_REFERENCE(&swnodes[SWNODE_GPIO], 3, GPIO_ACTIVE_HIGH); + nodes->gpio4_ref[0] = SOFTWARE_NODE_REFERENCE(&swnodes[SWNODE_GPIO], 4, GPIO_ACTIVE_HIGH); + nodes->gpio5_ref[0] = SOFTWARE_NODE_REFERENCE(&swnodes[SWNODE_GPIO], 5, GPIO_ACTIVE_HIGH); + + nodes->i2c_props[0] = PROPERTY_ENTRY_STRING("compatible", "snps,designware-i2c"); + nodes->i2c_props[1] = PROPERTY_ENTRY_BOOL("wx,i2c-snps-model"); + nodes->i2c_props[2] = PROPERTY_ENTRY_U32("clock-frequency", I2C_MAX_STANDARD_MODE_FREQ); + swnodes[SWNODE_I2C] = NODE_PROP(nodes->i2c_name, nodes->i2c_props); + nodes->i2c_ref[0] = SOFTWARE_NODE_REFERENCE(&swnodes[SWNODE_I2C]); + + nodes->sfp_props[0] = PROPERTY_ENTRY_STRING("compatible", "sff,sfp"); + nodes->sfp_props[1] = PROPERTY_ENTRY_REF_ARRAY("i2c-bus", nodes->i2c_ref); + nodes->sfp_props[2] = PROPERTY_ENTRY_REF_ARRAY("tx-fault-gpios", nodes->gpio0_ref); + nodes->sfp_props[3] = PROPERTY_ENTRY_REF_ARRAY("tx-disable-gpios", nodes->gpio1_ref); + nodes->sfp_props[4] = PROPERTY_ENTRY_REF_ARRAY("mod-def0-gpios", nodes->gpio2_ref); + nodes->sfp_props[5] = PROPERTY_ENTRY_REF_ARRAY("los-gpios", nodes->gpio3_ref); + nodes->sfp_props[6] = PROPERTY_ENTRY_REF_ARRAY("rate-select1-gpios", nodes->gpio4_ref); + nodes->sfp_props[7] = PROPERTY_ENTRY_REF_ARRAY("rate-select0-gpios", nodes->gpio5_ref); + swnodes[SWNODE_SFP] = NODE_PROP(nodes->sfp_name, nodes->sfp_props); + nodes->sfp_ref[0] = SOFTWARE_NODE_REFERENCE(&swnodes[SWNODE_SFP]); + + nodes->phylink_props[0] = PROPERTY_ENTRY_STRING("managed", "in-band-status"); + nodes->phylink_props[1] = PROPERTY_ENTRY_REF_ARRAY("sfp", nodes->sfp_ref); + swnodes[SWNODE_PHYLINK] = NODE_PROP(nodes->phylink_name, nodes->phylink_props); + + nodes->group[SWNODE_GPIO] = &swnodes[SWNODE_GPIO]; + nodes->group[SWNODE_I2C] = &swnodes[SWNODE_I2C]; + nodes->group[SWNODE_SFP] = &swnodes[SWNODE_SFP]; + nodes->group[SWNODE_PHYLINK] = &swnodes[SWNODE_PHYLINK]; + + return software_node_register_node_group(nodes->group); +} + +static int txgbe_pcs_read(struct mii_bus *bus, int addr, int devnum, int regnum) +{ + struct wx *wx = bus->priv; + u32 offset, val; + + if (addr) + return -EOPNOTSUPP; + + offset = devnum << 16 | regnum; + + /* Set the LAN port indicator to IDA_ADDR */ + wr32(wx, TXGBE_XPCS_IDA_ADDR, offset); + + /* Read the data from IDA_DATA register */ + val = rd32(wx, TXGBE_XPCS_IDA_DATA); + + return (u16)val; +} + +static int txgbe_pcs_write(struct mii_bus *bus, int addr, int devnum, int regnum, u16 val) +{ + struct wx *wx = bus->priv; + u32 offset; + + if (addr) + return -EOPNOTSUPP; + + offset = devnum << 16 | regnum; + + /* Set the LAN port indicator to IDA_ADDR */ + wr32(wx, TXGBE_XPCS_IDA_ADDR, offset); + + /* Write the data to IDA_DATA register */ + wr32(wx, TXGBE_XPCS_IDA_DATA, val); + + return 0; +} + +static int txgbe_mdio_pcs_init(struct txgbe *txgbe) +{ + struct mii_bus *mii_bus; + struct dw_xpcs *xpcs; + struct pci_dev *pdev; + struct wx *wx; + int ret = 0; + + wx = txgbe->wx; + pdev = wx->pdev; + + mii_bus = devm_mdiobus_alloc(&pdev->dev); + if (!mii_bus) + return -ENOMEM; + + mii_bus->name = "txgbe_pcs_mdio_bus"; + mii_bus->read_c45 = &txgbe_pcs_read; + mii_bus->write_c45 = &txgbe_pcs_write; + mii_bus->parent = &pdev->dev; + mii_bus->phy_mask = ~0; + mii_bus->priv = wx; + snprintf(mii_bus->id, MII_BUS_ID_SIZE, "txgbe_pcs-%x", + (pdev->bus->number << 8) | pdev->devfn); + + ret = devm_mdiobus_register(&pdev->dev, mii_bus); + if (ret) + return ret; + + xpcs = xpcs_create_mdiodev(mii_bus, 0, PHY_INTERFACE_MODE_10GBASER); + if (IS_ERR(xpcs)) + return PTR_ERR(xpcs); + + txgbe->xpcs = xpcs; + + return 0; +} + +static struct phylink_pcs *txgbe_phylink_mac_select(struct phylink_config *config, + phy_interface_t interface) +{ + struct txgbe *txgbe = netdev_to_txgbe(to_net_dev(config->dev)); + + return &txgbe->xpcs->pcs; +} + +static void txgbe_mac_config(struct phylink_config *config, unsigned int mode, + const struct phylink_link_state *state) +{ +} + +static void txgbe_mac_link_down(struct phylink_config *config, + unsigned int mode, phy_interface_t interface) +{ + struct wx *wx = netdev_priv(to_net_dev(config->dev)); + + wr32m(wx, WX_MAC_TX_CFG, WX_MAC_TX_CFG_TE, 0); +} + +static void txgbe_mac_link_up(struct phylink_config *config, + struct phy_device *phy, + unsigned int mode, phy_interface_t interface, + int speed, int duplex, + bool tx_pause, bool rx_pause) +{ + struct wx *wx = netdev_priv(to_net_dev(config->dev)); + u32 txcfg, wdg; + + txcfg = rd32(wx, WX_MAC_TX_CFG); + txcfg &= ~WX_MAC_TX_CFG_SPEED_MASK; + + switch (speed) { + case SPEED_10000: + txcfg |= WX_MAC_TX_CFG_SPEED_10G; + break; + case SPEED_1000: + case SPEED_100: + case SPEED_10: + txcfg |= WX_MAC_TX_CFG_SPEED_1G; + break; + default: + break; + } + + wr32(wx, WX_MAC_TX_CFG, txcfg | WX_MAC_TX_CFG_TE); + + /* Re configure MAC Rx */ + wr32m(wx, WX_MAC_RX_CFG, WX_MAC_RX_CFG_RE, WX_MAC_RX_CFG_RE); + wr32(wx, WX_MAC_PKT_FLT, WX_MAC_PKT_FLT_PR); + wdg = rd32(wx, WX_MAC_WDG_TIMEOUT); + wr32(wx, WX_MAC_WDG_TIMEOUT, wdg); +} + +static const struct phylink_mac_ops txgbe_mac_ops = { + .mac_select_pcs = txgbe_phylink_mac_select, + .mac_config = txgbe_mac_config, + .mac_link_down = txgbe_mac_link_down, + .mac_link_up = txgbe_mac_link_up, +}; + +static int txgbe_phylink_init(struct txgbe *txgbe) +{ + struct phylink_config *config; + struct fwnode_handle *fwnode; + struct wx *wx = txgbe->wx; + phy_interface_t phy_mode; + struct phylink *phylink; + + config = devm_kzalloc(&wx->pdev->dev, sizeof(*config), GFP_KERNEL); + if (!config) + return -ENOMEM; + + config->dev = &wx->netdev->dev; + config->type = PHYLINK_NETDEV; + config->mac_capabilities = MAC_10000FD | MAC_1000FD | MAC_SYM_PAUSE | MAC_ASYM_PAUSE; + phy_mode = PHY_INTERFACE_MODE_10GBASER; + __set_bit(PHY_INTERFACE_MODE_10GBASER, config->supported_interfaces); + fwnode = software_node_fwnode(txgbe->nodes.group[SWNODE_PHYLINK]); + phylink = phylink_create(config, fwnode, phy_mode, &txgbe_mac_ops); + if (IS_ERR(phylink)) + return PTR_ERR(phylink); + + txgbe->phylink = phylink; + + return 0; +} + +static int txgbe_gpio_get(struct gpio_chip *chip, unsigned int offset) +{ + struct wx *wx = gpiochip_get_data(chip); + int val; + + val = rd32m(wx, WX_GPIO_EXT, BIT(offset)); + + return !!(val & BIT(offset)); +} + +static int txgbe_gpio_get_direction(struct gpio_chip *chip, unsigned int offset) +{ + struct wx *wx = gpiochip_get_data(chip); + u32 val; + + val = rd32(wx, WX_GPIO_DDR); + if (BIT(offset) & val) + return GPIO_LINE_DIRECTION_OUT; + + return GPIO_LINE_DIRECTION_IN; +} + +static int txgbe_gpio_direction_in(struct gpio_chip *chip, unsigned int offset) +{ + struct wx *wx = gpiochip_get_data(chip); + unsigned long flags; + + raw_spin_lock_irqsave(&wx->gpio_lock, flags); + wr32m(wx, WX_GPIO_DDR, BIT(offset), 0); + raw_spin_unlock_irqrestore(&wx->gpio_lock, flags); + + return 0; +} + +static int txgbe_gpio_direction_out(struct gpio_chip *chip, unsigned int offset, + int val) +{ + struct wx *wx = gpiochip_get_data(chip); + unsigned long flags; + u32 set; + + set = val ? BIT(offset) : 0; + + raw_spin_lock_irqsave(&wx->gpio_lock, flags); + wr32m(wx, WX_GPIO_DR, BIT(offset), set); + wr32m(wx, WX_GPIO_DDR, BIT(offset), BIT(offset)); + raw_spin_unlock_irqrestore(&wx->gpio_lock, flags); + + return 0; +} + +static void txgbe_gpio_irq_ack(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + irq_hw_number_t hwirq = irqd_to_hwirq(d); + struct wx *wx = gpiochip_get_data(gc); + unsigned long flags; + + raw_spin_lock_irqsave(&wx->gpio_lock, flags); + wr32(wx, WX_GPIO_EOI, BIT(hwirq)); + raw_spin_unlock_irqrestore(&wx->gpio_lock, flags); +} + +static void txgbe_gpio_irq_mask(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + irq_hw_number_t hwirq = irqd_to_hwirq(d); + struct wx *wx = gpiochip_get_data(gc); + unsigned long flags; + + gpiochip_disable_irq(gc, hwirq); + + raw_spin_lock_irqsave(&wx->gpio_lock, flags); + wr32m(wx, WX_GPIO_INTMASK, BIT(hwirq), BIT(hwirq)); + raw_spin_unlock_irqrestore(&wx->gpio_lock, flags); +} + +static void txgbe_gpio_irq_unmask(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + irq_hw_number_t hwirq = irqd_to_hwirq(d); + struct wx *wx = gpiochip_get_data(gc); + unsigned long flags; + + gpiochip_enable_irq(gc, hwirq); + + raw_spin_lock_irqsave(&wx->gpio_lock, flags); + wr32m(wx, WX_GPIO_INTMASK, BIT(hwirq), 0); + raw_spin_unlock_irqrestore(&wx->gpio_lock, flags); +} + +static void txgbe_toggle_trigger(struct gpio_chip *gc, unsigned int offset) +{ + struct wx *wx = gpiochip_get_data(gc); + u32 pol, val; + + pol = rd32(wx, WX_GPIO_POLARITY); + val = rd32(wx, WX_GPIO_EXT); + + if (val & BIT(offset)) + pol &= ~BIT(offset); + else + pol |= BIT(offset); + + wr32(wx, WX_GPIO_POLARITY, pol); +} + +static int txgbe_gpio_set_type(struct irq_data *d, unsigned int type) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + irq_hw_number_t hwirq = irqd_to_hwirq(d); + struct wx *wx = gpiochip_get_data(gc); + u32 level, polarity, mask; + unsigned long flags; + + mask = BIT(hwirq); + + if (type & IRQ_TYPE_LEVEL_MASK) { + level = 0; + irq_set_handler_locked(d, handle_level_irq); + } else { + level = mask; + irq_set_handler_locked(d, handle_edge_irq); + } + + if (type == IRQ_TYPE_EDGE_RISING || type == IRQ_TYPE_LEVEL_HIGH) + polarity = mask; + else + polarity = 0; + + raw_spin_lock_irqsave(&wx->gpio_lock, flags); + + wr32m(wx, WX_GPIO_INTEN, mask, mask); + wr32m(wx, WX_GPIO_INTTYPE_LEVEL, mask, level); + if (type == IRQ_TYPE_EDGE_BOTH) + txgbe_toggle_trigger(gc, hwirq); + else + wr32m(wx, WX_GPIO_POLARITY, mask, polarity); + + raw_spin_unlock_irqrestore(&wx->gpio_lock, flags); + + return 0; +} + +static const struct irq_chip txgbe_gpio_irq_chip = { + .name = "txgbe_gpio_irq", + .irq_ack = txgbe_gpio_irq_ack, + .irq_mask = txgbe_gpio_irq_mask, + .irq_unmask = txgbe_gpio_irq_unmask, + .irq_set_type = txgbe_gpio_set_type, + .flags = IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, +}; + +static void txgbe_irq_handler(struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + struct wx *wx = irq_desc_get_handler_data(desc); + struct txgbe *txgbe = wx->priv; + irq_hw_number_t hwirq; + unsigned long gpioirq; + struct gpio_chip *gc; + unsigned long flags; + u32 eicr; + + eicr = wx_misc_isb(wx, WX_ISB_MISC); + + chained_irq_enter(chip, desc); + + gpioirq = rd32(wx, WX_GPIO_INTSTATUS); + + gc = txgbe->gpio; + for_each_set_bit(hwirq, &gpioirq, gc->ngpio) { + int gpio = irq_find_mapping(gc->irq.domain, hwirq); + u32 irq_type = irq_get_trigger_type(gpio); + + generic_handle_domain_irq(gc->irq.domain, hwirq); + + if ((irq_type & IRQ_TYPE_SENSE_MASK) == IRQ_TYPE_EDGE_BOTH) { + raw_spin_lock_irqsave(&wx->gpio_lock, flags); + txgbe_toggle_trigger(gc, hwirq); + raw_spin_unlock_irqrestore(&wx->gpio_lock, flags); + } + } + + chained_irq_exit(chip, desc); + + if (eicr & (TXGBE_PX_MISC_ETH_LK | TXGBE_PX_MISC_ETH_LKDN)) { + u32 reg = rd32(wx, TXGBE_CFG_PORT_ST); + + phylink_mac_change(txgbe->phylink, !!(reg & TXGBE_CFG_PORT_ST_LINK_UP)); + } + + /* unmask interrupt */ + wx_intr_enable(wx, TXGBE_INTR_MISC(wx)); +} + +static int txgbe_gpio_init(struct txgbe *txgbe) +{ + struct gpio_irq_chip *girq; + struct gpio_chip *gc; + struct device *dev; + struct wx *wx; + int ret; + + wx = txgbe->wx; + dev = &wx->pdev->dev; + + raw_spin_lock_init(&wx->gpio_lock); + + gc = devm_kzalloc(dev, sizeof(*gc), GFP_KERNEL); + if (!gc) + return -ENOMEM; + + gc->label = devm_kasprintf(dev, GFP_KERNEL, "txgbe_gpio-%x", + (wx->pdev->bus->number << 8) | wx->pdev->devfn); + if (!gc->label) + return -ENOMEM; + + gc->base = -1; + gc->ngpio = 6; + gc->owner = THIS_MODULE; + gc->parent = dev; + gc->fwnode = software_node_fwnode(txgbe->nodes.group[SWNODE_GPIO]); + gc->get = txgbe_gpio_get; + gc->get_direction = txgbe_gpio_get_direction; + gc->direction_input = txgbe_gpio_direction_in; + gc->direction_output = txgbe_gpio_direction_out; + + girq = &gc->irq; + gpio_irq_chip_set_chip(girq, &txgbe_gpio_irq_chip); + girq->parent_handler = txgbe_irq_handler; + girq->parent_handler_data = wx; + girq->num_parents = 1; + girq->parents = devm_kcalloc(dev, girq->num_parents, + sizeof(*girq->parents), GFP_KERNEL); + if (!girq->parents) + return -ENOMEM; + girq->parents[0] = wx->msix_entries[wx->num_q_vectors].vector; + girq->default_type = IRQ_TYPE_NONE; + girq->handler = handle_bad_irq; + + ret = devm_gpiochip_add_data(dev, gc, wx); + if (ret) + return ret; + + txgbe->gpio = gc; + + return 0; +} + +static int txgbe_clock_register(struct txgbe *txgbe) +{ + struct pci_dev *pdev = txgbe->wx->pdev; + struct clk_lookup *clock; + char clk_name[32]; + struct clk *clk; + + snprintf(clk_name, sizeof(clk_name), "i2c_designware.%d", + (pdev->bus->number << 8) | pdev->devfn); + + clk = clk_register_fixed_rate(NULL, clk_name, NULL, 0, 156250000); + if (IS_ERR(clk)) + return PTR_ERR(clk); + + clock = clkdev_create(clk, NULL, clk_name); + if (!clock) { + clk_unregister(clk); + return -ENOMEM; + } + + txgbe->clk = clk; + txgbe->clock = clock; + + return 0; +} + +static int txgbe_i2c_read(void *context, unsigned int reg, unsigned int *val) +{ + struct wx *wx = context; + + *val = rd32(wx, reg + TXGBE_I2C_BASE); + + return 0; +} + +static int txgbe_i2c_write(void *context, unsigned int reg, unsigned int val) +{ + struct wx *wx = context; + + wr32(wx, reg + TXGBE_I2C_BASE, val); + + return 0; +} + +static const struct regmap_config i2c_regmap_config = { + .reg_bits = 32, + .val_bits = 32, + .reg_read = txgbe_i2c_read, + .reg_write = txgbe_i2c_write, + .fast_io = true, +}; + +static int txgbe_i2c_register(struct txgbe *txgbe) +{ + struct platform_device_info info = {}; + struct platform_device *i2c_dev; + struct regmap *i2c_regmap; + struct pci_dev *pdev; + struct wx *wx; + + wx = txgbe->wx; + pdev = wx->pdev; + i2c_regmap = devm_regmap_init(&pdev->dev, NULL, wx, &i2c_regmap_config); + if (IS_ERR(i2c_regmap)) { + wx_err(wx, "failed to init I2C regmap\n"); + return PTR_ERR(i2c_regmap); + } + + info.parent = &pdev->dev; + info.fwnode = software_node_fwnode(txgbe->nodes.group[SWNODE_I2C]); + info.name = "i2c_designware"; + info.id = (pdev->bus->number << 8) | pdev->devfn; + + info.res = &DEFINE_RES_IRQ(pdev->irq); + info.num_res = 1; + i2c_dev = platform_device_register_full(&info); + if (IS_ERR(i2c_dev)) + return PTR_ERR(i2c_dev); + + txgbe->i2c_dev = i2c_dev; + + return 0; +} + +static int txgbe_sfp_register(struct txgbe *txgbe) +{ + struct pci_dev *pdev = txgbe->wx->pdev; + struct platform_device_info info = {}; + struct platform_device *sfp_dev; + + info.parent = &pdev->dev; + info.fwnode = software_node_fwnode(txgbe->nodes.group[SWNODE_SFP]); + info.name = "sfp"; + info.id = (pdev->bus->number << 8) | pdev->devfn; + sfp_dev = platform_device_register_full(&info); + if (IS_ERR(sfp_dev)) + return PTR_ERR(sfp_dev); + + txgbe->sfp_dev = sfp_dev; + + return 0; +} + +int txgbe_init_phy(struct txgbe *txgbe) +{ + int ret; + + ret = txgbe_swnodes_register(txgbe); + if (ret) { + wx_err(txgbe->wx, "failed to register software nodes\n"); + return ret; + } + + ret = txgbe_mdio_pcs_init(txgbe); + if (ret) { + wx_err(txgbe->wx, "failed to init mdio pcs: %d\n", ret); + goto err_unregister_swnode; + } + + ret = txgbe_phylink_init(txgbe); + if (ret) { + wx_err(txgbe->wx, "failed to init phylink\n"); + goto err_destroy_xpcs; + } + + ret = txgbe_gpio_init(txgbe); + if (ret) { + wx_err(txgbe->wx, "failed to init gpio\n"); + goto err_destroy_phylink; + } + + ret = txgbe_clock_register(txgbe); + if (ret) { + wx_err(txgbe->wx, "failed to register clock: %d\n", ret); + goto err_destroy_phylink; + } + + ret = txgbe_i2c_register(txgbe); + if (ret) { + wx_err(txgbe->wx, "failed to init i2c interface: %d\n", ret); + goto err_unregister_clk; + } + + ret = txgbe_sfp_register(txgbe); + if (ret) { + wx_err(txgbe->wx, "failed to register sfp\n"); + goto err_unregister_i2c; + } + + return 0; + +err_unregister_i2c: + platform_device_unregister(txgbe->i2c_dev); +err_unregister_clk: + clkdev_drop(txgbe->clock); + clk_unregister(txgbe->clk); +err_destroy_phylink: + phylink_destroy(txgbe->phylink); +err_destroy_xpcs: + xpcs_destroy(txgbe->xpcs); +err_unregister_swnode: + software_node_unregister_node_group(txgbe->nodes.group); + + return ret; +} + +void txgbe_remove_phy(struct txgbe *txgbe) +{ + platform_device_unregister(txgbe->sfp_dev); + platform_device_unregister(txgbe->i2c_dev); + clkdev_drop(txgbe->clock); + clk_unregister(txgbe->clk); + phylink_destroy(txgbe->phylink); + xpcs_destroy(txgbe->xpcs); + software_node_unregister_node_group(txgbe->nodes.group); +} diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.h new file mode 100644 index 000000000000..1ab592124986 --- /dev/null +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2015 - 2023 Beijing WangXun Technology Co., Ltd. */ + +#ifndef _TXGBE_PHY_H_ +#define _TXGBE_PHY_H_ + +int txgbe_init_phy(struct txgbe *txgbe); +void txgbe_remove_phy(struct txgbe *txgbe); + +#endif /* _TXGBE_NODE_H_ */ diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h index 63a1c733718d..51199c355f95 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h @@ -4,6 +4,8 @@ #ifndef _TXGBE_TYPE_H_ #define _TXGBE_TYPE_H_ +#include <linux/property.h> + /* Device IDs */ #define TXGBE_DEV_ID_SP1000 0x1001 #define TXGBE_DEV_ID_WX1820 0x2001 @@ -53,6 +55,39 @@ #define TXGBE_TS_CTL 0x10300 #define TXGBE_TS_CTL_EVAL_MD BIT(31) +/* GPIO register bit */ +#define TXGBE_GPIOBIT_0 BIT(0) /* I:tx fault */ +#define TXGBE_GPIOBIT_1 BIT(1) /* O:tx disabled */ +#define TXGBE_GPIOBIT_2 BIT(2) /* I:sfp module absent */ +#define TXGBE_GPIOBIT_3 BIT(3) /* I:rx signal lost */ +#define TXGBE_GPIOBIT_4 BIT(4) /* O:rate select, 1G(0) 10G(1) */ +#define TXGBE_GPIOBIT_5 BIT(5) /* O:rate select, 1G(0) 10G(1) */ + +/* Extended Interrupt Enable Set */ +#define TXGBE_PX_MISC_ETH_LKDN BIT(8) +#define TXGBE_PX_MISC_DEV_RST BIT(10) +#define TXGBE_PX_MISC_ETH_EVENT BIT(17) +#define TXGBE_PX_MISC_ETH_LK BIT(18) +#define TXGBE_PX_MISC_ETH_AN BIT(19) +#define TXGBE_PX_MISC_INT_ERR BIT(20) +#define TXGBE_PX_MISC_GPIO BIT(26) +#define TXGBE_PX_MISC_IEN_MASK \ + (TXGBE_PX_MISC_ETH_LKDN | TXGBE_PX_MISC_DEV_RST | \ + TXGBE_PX_MISC_ETH_EVENT | TXGBE_PX_MISC_ETH_LK | \ + TXGBE_PX_MISC_ETH_AN | TXGBE_PX_MISC_INT_ERR | \ + TXGBE_PX_MISC_GPIO) + +/* Port cfg registers */ +#define TXGBE_CFG_PORT_ST 0x14404 +#define TXGBE_CFG_PORT_ST_LINK_UP BIT(0) + +/* I2C registers */ +#define TXGBE_I2C_BASE 0x14900 + +/************************************** ETH PHY ******************************/ +#define TXGBE_XPCS_IDA_ADDR 0x13000 +#define TXGBE_XPCS_IDA_DATA 0x13004 + /* Part Number String Length */ #define TXGBE_PBANUM_LENGTH 32 @@ -77,6 +112,7 @@ #define TXGBE_SP_MAX_RX_QUEUES 128 #define TXGBE_SP_RAR_ENTRIES 128 #define TXGBE_SP_MC_TBL_SIZE 128 +#define TXGBE_SP_VFT_TBL_SIZE 128 #define TXGBE_SP_RX_PB_SIZE 512 #define TXGBE_SP_TDB_PB_SZ (160 * 1024) /* 160KB Packet Buffer */ @@ -99,4 +135,58 @@ extern char txgbe_driver_name[]; +static inline struct txgbe *netdev_to_txgbe(struct net_device *netdev) +{ + struct wx *wx = netdev_priv(netdev); + + return wx->priv; +} + +#define NODE_PROP(_NAME, _PROP) \ + (const struct software_node) { \ + .name = _NAME, \ + .properties = _PROP, \ + } + +enum txgbe_swnodes { + SWNODE_GPIO = 0, + SWNODE_I2C, + SWNODE_SFP, + SWNODE_PHYLINK, + SWNODE_MAX +}; + +struct txgbe_nodes { + char gpio_name[32]; + char i2c_name[32]; + char sfp_name[32]; + char phylink_name[32]; + struct property_entry gpio_props[1]; + struct property_entry i2c_props[3]; + struct property_entry sfp_props[8]; + struct property_entry phylink_props[2]; + struct software_node_ref_args i2c_ref[1]; + struct software_node_ref_args gpio0_ref[1]; + struct software_node_ref_args gpio1_ref[1]; + struct software_node_ref_args gpio2_ref[1]; + struct software_node_ref_args gpio3_ref[1]; + struct software_node_ref_args gpio4_ref[1]; + struct software_node_ref_args gpio5_ref[1]; + struct software_node_ref_args sfp_ref[1]; + struct software_node swnodes[SWNODE_MAX]; + const struct software_node *group[SWNODE_MAX + 1]; +}; + +struct txgbe { + struct wx *wx; + struct txgbe_nodes nodes; + struct dw_xpcs *xpcs; + struct phylink *phylink; + struct platform_device *sfp_dev; + struct platform_device *i2c_dev; + struct clk_lookup *clock; + struct clk *clk; + struct gpio_chip *gpio; +}; + #endif /* _TXGBE_TYPE_H_ */ diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 33d51e363913..c9dd69dbe1b8 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -74,6 +74,7 @@ struct ndis_recv_scale_cap { /* NDIS_RECEIVE_SCALE_CAPABILITIES */ #define NDIS_RSS_HASH_SECRET_KEY_MAX_SIZE_REVISION_2 40 #define ITAB_NUM 128 +#define ITAB_NUM_MAX 256 struct ndis_recv_scale_param { /* NDIS_RECEIVE_SCALE_PARAMETERS */ struct ndis_obj_header hdr; @@ -1034,7 +1035,9 @@ struct net_device_context { u32 tx_table[VRSS_SEND_TAB_SIZE]; - u16 rx_table[ITAB_NUM]; + u16 *rx_table; + + u32 rx_table_sz; /* Ethtool settings */ u8 duplex; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 0103ff914024..3ba3c8fb28a5 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -1747,7 +1747,9 @@ static u32 netvsc_get_rxfh_key_size(struct net_device *dev) static u32 netvsc_rss_indir_size(struct net_device *dev) { - return ITAB_NUM; + struct net_device_context *ndc = netdev_priv(dev); + + return ndc->rx_table_sz; } static int netvsc_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, @@ -1766,7 +1768,7 @@ static int netvsc_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, rndis_dev = ndev->extension; if (indir) { - for (i = 0; i < ITAB_NUM; i++) + for (i = 0; i < ndc->rx_table_sz; i++) indir[i] = ndc->rx_table[i]; } @@ -1792,11 +1794,11 @@ static int netvsc_set_rxfh(struct net_device *dev, const u32 *indir, rndis_dev = ndev->extension; if (indir) { - for (i = 0; i < ITAB_NUM; i++) + for (i = 0; i < ndc->rx_table_sz; i++) if (indir[i] >= ndev->num_chn) return -EINVAL; - for (i = 0; i < ITAB_NUM; i++) + for (i = 0; i < ndc->rx_table_sz; i++) ndc->rx_table[i] = indir[i]; } diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index eea777ec2541..af95947a87c5 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -21,6 +21,7 @@ #include <linux/rtnetlink.h> #include <linux/ucs2_string.h> #include <linux/string.h> +#include <linux/slab.h> #include "hyperv_net.h" #include "netvsc_trace.h" @@ -927,7 +928,7 @@ static int rndis_set_rss_param_msg(struct rndis_device *rdev, struct rndis_set_request *set; struct rndis_set_complete *set_complete; u32 extlen = sizeof(struct ndis_recv_scale_param) + - 4 * ITAB_NUM + NETVSC_HASH_KEYLEN; + 4 * ndc->rx_table_sz + NETVSC_HASH_KEYLEN; struct ndis_recv_scale_param *rssp; u32 *itab; u8 *keyp; @@ -953,7 +954,7 @@ static int rndis_set_rss_param_msg(struct rndis_device *rdev, rssp->hashinfo = NDIS_HASH_FUNC_TOEPLITZ | NDIS_HASH_IPV4 | NDIS_HASH_TCP_IPV4 | NDIS_HASH_IPV6 | NDIS_HASH_TCP_IPV6; - rssp->indirect_tabsize = 4*ITAB_NUM; + rssp->indirect_tabsize = 4 * ndc->rx_table_sz; rssp->indirect_taboffset = sizeof(struct ndis_recv_scale_param); rssp->hashkey_size = NETVSC_HASH_KEYLEN; rssp->hashkey_offset = rssp->indirect_taboffset + @@ -961,7 +962,7 @@ static int rndis_set_rss_param_msg(struct rndis_device *rdev, /* Set indirection table entries */ itab = (u32 *)(rssp + 1); - for (i = 0; i < ITAB_NUM; i++) + for (i = 0; i < ndc->rx_table_sz; i++) itab[i] = ndc->rx_table[i]; /* Set hask key values */ @@ -1548,6 +1549,18 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev, if (ret || rsscap.num_recv_que < 2) goto out; + if (rsscap.num_indirect_tabent && + rsscap.num_indirect_tabent <= ITAB_NUM_MAX) + ndc->rx_table_sz = rsscap.num_indirect_tabent; + else + ndc->rx_table_sz = ITAB_NUM; + + ndc->rx_table = kcalloc(ndc->rx_table_sz, sizeof(u16), GFP_KERNEL); + if (!ndc->rx_table) { + ret = -ENOMEM; + goto err_dev_remv; + } + /* This guarantees that num_possible_rss_qs <= num_online_cpus */ num_possible_rss_qs = min_t(u32, num_online_cpus(), rsscap.num_recv_que); @@ -1558,7 +1571,7 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev, net_device->num_chn = min(net_device->max_chn, device_info->num_chn); if (!netif_is_rxfh_configured(net)) { - for (i = 0; i < ITAB_NUM; i++) + for (i = 0; i < ndc->rx_table_sz; i++) ndc->rx_table[i] = ethtool_rxfh_indir_default( i, net_device->num_chn); } @@ -1596,11 +1609,19 @@ void rndis_filter_device_remove(struct hv_device *dev, struct netvsc_device *net_dev) { struct rndis_device *rndis_dev = net_dev->extension; + struct net_device *net = hv_get_drvdata(dev); + struct net_device_context *ndc; + + ndc = netdev_priv(net); /* Halt and release the rndis device */ rndis_filter_halt_device(net_dev, rndis_dev); netvsc_device_remove(dev); + + ndc->rx_table_sz = 0; + kfree(ndc->rx_table); + ndc->rx_table = NULL; } int rndis_filter_open(struct netvsc_device *nvdev) diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index 2ee80ed140b7..afa1d56d9095 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -119,7 +119,7 @@ enum ipa_status_field_id { }; /* Size in bytes of an IPA packet status structure */ -#define IPA_STATUS_SIZE sizeof(__le32[4]) +#define IPA_STATUS_SIZE sizeof(__le32[8]) /* IPA status structure decoder; looks up field values for a structure */ static u32 ipa_status_extract(struct ipa *ipa, const void *data, diff --git a/drivers/net/mdio/Kconfig b/drivers/net/mdio/Kconfig index 9ff2e6f22f3f..4a7a303be2f7 100644 --- a/drivers/net/mdio/Kconfig +++ b/drivers/net/mdio/Kconfig @@ -185,6 +185,17 @@ config MDIO_IPQ8064 This driver supports the MDIO interface found in the network interface units of the IPQ8064 SoC +config MDIO_REGMAP + tristate + help + This driver allows using MDIO devices that are not sitting on a + regular MDIO bus, but still exposes the standard 802.3 register + layout. It's regmap-based so that it can be used on integrated, + memory-mapped PHYs, SPI PHYs and so on. A new virtual MDIO bus is + created, and its read/write operations are mapped to the underlying + regmap. Users willing to use this driver must explicitly select + REGMAP. + config MDIO_THUNDER tristate "ThunderX SOCs MDIO buses" depends on 64BIT diff --git a/drivers/net/mdio/Makefile b/drivers/net/mdio/Makefile index 7d4cb4c11e4e..1015f0db4531 100644 --- a/drivers/net/mdio/Makefile +++ b/drivers/net/mdio/Makefile @@ -19,6 +19,7 @@ obj-$(CONFIG_MDIO_MOXART) += mdio-moxart.o obj-$(CONFIG_MDIO_MSCC_MIIM) += mdio-mscc-miim.o obj-$(CONFIG_MDIO_MVUSB) += mdio-mvusb.o obj-$(CONFIG_MDIO_OCTEON) += mdio-octeon.o +obj-$(CONFIG_MDIO_REGMAP) += mdio-regmap.o obj-$(CONFIG_MDIO_SUN4I) += mdio-sun4i.o obj-$(CONFIG_MDIO_THUNDER) += mdio-thunder.o obj-$(CONFIG_MDIO_XGENE) += mdio-xgene.o diff --git a/drivers/net/mdio/mdio-i2c.c b/drivers/net/mdio/mdio-i2c.c index 1e0c206d0f2e..da2001ea1f99 100644 --- a/drivers/net/mdio/mdio-i2c.c +++ b/drivers/net/mdio/mdio-i2c.c @@ -291,7 +291,8 @@ static int i2c_rollball_mii_cmd(struct mii_bus *bus, int bus_addr, u8 cmd, return i2c_transfer_rollball(i2c, msgs, ARRAY_SIZE(msgs)); } -static int i2c_mii_read_rollball(struct mii_bus *bus, int phy_id, int reg) +static int i2c_mii_read_rollball(struct mii_bus *bus, int phy_id, int devad, + int reg) { u8 buf[4], res[6]; int bus_addr, ret; @@ -302,7 +303,7 @@ static int i2c_mii_read_rollball(struct mii_bus *bus, int phy_id, int reg) return 0xffff; buf[0] = ROLLBALL_DATA_ADDR; - buf[1] = (reg >> 16) & 0x1f; + buf[1] = devad; buf[2] = (reg >> 8) & 0xff; buf[3] = reg & 0xff; @@ -322,8 +323,8 @@ static int i2c_mii_read_rollball(struct mii_bus *bus, int phy_id, int reg) return val; } -static int i2c_mii_write_rollball(struct mii_bus *bus, int phy_id, int reg, - u16 val) +static int i2c_mii_write_rollball(struct mii_bus *bus, int phy_id, int devad, + int reg, u16 val) { int bus_addr, ret; u8 buf[6]; @@ -333,7 +334,7 @@ static int i2c_mii_write_rollball(struct mii_bus *bus, int phy_id, int reg, return 0; buf[0] = ROLLBALL_DATA_ADDR; - buf[1] = (reg >> 16) & 0x1f; + buf[1] = devad; buf[2] = (reg >> 8) & 0xff; buf[3] = reg & 0xff; buf[4] = val >> 8; @@ -405,8 +406,8 @@ struct mii_bus *mdio_i2c_alloc(struct device *parent, struct i2c_adapter *i2c, return ERR_PTR(ret); } - mii->read = i2c_mii_read_rollball; - mii->write = i2c_mii_write_rollball; + mii->read_c45 = i2c_mii_read_rollball; + mii->write_c45 = i2c_mii_write_rollball; break; default: mii->read = i2c_mii_read_default_c22; diff --git a/drivers/net/mdio/mdio-regmap.c b/drivers/net/mdio/mdio-regmap.c new file mode 100644 index 000000000000..8a742a8d6387 --- /dev/null +++ b/drivers/net/mdio/mdio-regmap.c @@ -0,0 +1,93 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Driver for MMIO-Mapped MDIO devices. Some IPs expose internal PHYs or PCS + * within the MMIO-mapped area + * + * Copyright (C) 2023 Maxime Chevallier <maxime.chevallier@bootlin.com> + */ +#include <linux/bitfield.h> +#include <linux/delay.h> +#include <linux/mdio.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_mdio.h> +#include <linux/phy.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> +#include <linux/mdio/mdio-regmap.h> + +#define DRV_NAME "mdio-regmap" + +struct mdio_regmap_priv { + struct regmap *regmap; + u8 valid_addr; +}; + +static int mdio_regmap_read_c22(struct mii_bus *bus, int addr, int regnum) +{ + struct mdio_regmap_priv *ctx = bus->priv; + unsigned int val; + int ret; + + if (ctx->valid_addr != addr) + return -ENODEV; + + ret = regmap_read(ctx->regmap, regnum, &val); + if (ret < 0) + return ret; + + return val; +} + +static int mdio_regmap_write_c22(struct mii_bus *bus, int addr, int regnum, + u16 val) +{ + struct mdio_regmap_priv *ctx = bus->priv; + + if (ctx->valid_addr != addr) + return -ENODEV; + + return regmap_write(ctx->regmap, regnum, val); +} + +struct mii_bus *devm_mdio_regmap_register(struct device *dev, + const struct mdio_regmap_config *config) +{ + struct mdio_regmap_priv *mr; + struct mii_bus *mii; + int rc; + + if (!config->parent) + return ERR_PTR(-EINVAL); + + mii = devm_mdiobus_alloc_size(config->parent, sizeof(*mr)); + if (!mii) + return ERR_PTR(-ENOMEM); + + mr = mii->priv; + mr->regmap = config->regmap; + mr->valid_addr = config->valid_addr; + + mii->name = DRV_NAME; + strscpy(mii->id, config->name, MII_BUS_ID_SIZE); + mii->parent = config->parent; + mii->read = mdio_regmap_read_c22; + mii->write = mdio_regmap_write_c22; + + if (config->autoscan) + mii->phy_mask = ~BIT(config->valid_addr); + else + mii->phy_mask = ~0; + + rc = devm_mdiobus_register(dev, mii); + if (rc) { + dev_err(config->parent, "Cannot register MDIO bus![%s] (%d)\n", mii->id, rc); + return ERR_PTR(rc); + } + + return mii; +} +EXPORT_SYMBOL_GPL(devm_mdio_regmap_register); + +MODULE_DESCRIPTION("MDIO API over regmap"); +MODULE_AUTHOR("Maxime Chevallier <maxime.chevallier@bootlin.com>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/pcs/Kconfig b/drivers/net/pcs/Kconfig index 7c34fb7cbf7b..87cf308fc6d8 100644 --- a/drivers/net/pcs/Kconfig +++ b/drivers/net/pcs/Kconfig @@ -33,10 +33,4 @@ config PCS_RZN1_MIIC on RZ/N1 SoCs. This PCS converts MII to RMII/RGMII or can be set in pass-through mode for MII. -config PCS_ALTERA_TSE - tristate - help - This module provides helper functions for the Altera Triple Speed - Ethernet SGMII PCS, that can be found on the Intel Socfpga family. - endmenu diff --git a/drivers/net/pcs/Makefile b/drivers/net/pcs/Makefile index 9b9afd6b1c22..ea662a7989b2 100644 --- a/drivers/net/pcs/Makefile +++ b/drivers/net/pcs/Makefile @@ -7,4 +7,3 @@ obj-$(CONFIG_PCS_XPCS) += pcs_xpcs.o obj-$(CONFIG_PCS_LYNX) += pcs-lynx.o obj-$(CONFIG_PCS_MTK_LYNXI) += pcs-mtk-lynxi.o obj-$(CONFIG_PCS_RZN1_MIIC) += pcs-rzn1-miic.o -obj-$(CONFIG_PCS_ALTERA_TSE) += pcs-altera-tse.o diff --git a/drivers/net/pcs/pcs-altera-tse.c b/drivers/net/pcs/pcs-altera-tse.c deleted file mode 100644 index d616749761f4..000000000000 --- a/drivers/net/pcs/pcs-altera-tse.c +++ /dev/null @@ -1,160 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) 2022 Bootlin - * - * Maxime Chevallier <maxime.chevallier@bootlin.com> - */ - -#include <linux/netdevice.h> -#include <linux/phy.h> -#include <linux/phylink.h> -#include <linux/pcs-altera-tse.h> - -/* SGMII PCS register addresses - */ -#define SGMII_PCS_LINK_TIMER_0 0x12 -#define SGMII_PCS_LINK_TIMER_1 0x13 -#define SGMII_PCS_IF_MODE 0x14 -#define PCS_IF_MODE_SGMII_ENA BIT(0) -#define PCS_IF_MODE_USE_SGMII_AN BIT(1) -#define PCS_IF_MODE_SGMI_HALF_DUPLEX BIT(4) -#define PCS_IF_MODE_SGMI_PHY_AN BIT(5) -#define SGMII_PCS_SW_RESET_TIMEOUT 100 /* usecs */ - -struct altera_tse_pcs { - struct phylink_pcs pcs; - void __iomem *base; - int reg_width; -}; - -static struct altera_tse_pcs *phylink_pcs_to_tse_pcs(struct phylink_pcs *pcs) -{ - return container_of(pcs, struct altera_tse_pcs, pcs); -} - -static u16 tse_pcs_read(struct altera_tse_pcs *tse_pcs, int regnum) -{ - if (tse_pcs->reg_width == 4) - return readl(tse_pcs->base + regnum * 4); - else - return readw(tse_pcs->base + regnum * 2); -} - -static void tse_pcs_write(struct altera_tse_pcs *tse_pcs, int regnum, - u16 value) -{ - if (tse_pcs->reg_width == 4) - writel(value, tse_pcs->base + regnum * 4); - else - writew(value, tse_pcs->base + regnum * 2); -} - -static int tse_pcs_reset(struct altera_tse_pcs *tse_pcs) -{ - u16 bmcr; - - /* Reset PCS block */ - bmcr = tse_pcs_read(tse_pcs, MII_BMCR); - bmcr |= BMCR_RESET; - tse_pcs_write(tse_pcs, MII_BMCR, bmcr); - - return read_poll_timeout(tse_pcs_read, bmcr, (bmcr & BMCR_RESET), - 10, SGMII_PCS_SW_RESET_TIMEOUT, 1, - tse_pcs, MII_BMCR); -} - -static int alt_tse_pcs_validate(struct phylink_pcs *pcs, - unsigned long *supported, - const struct phylink_link_state *state) -{ - if (state->interface == PHY_INTERFACE_MODE_SGMII || - state->interface == PHY_INTERFACE_MODE_1000BASEX) - return 1; - - return -EINVAL; -} - -static int alt_tse_pcs_config(struct phylink_pcs *pcs, unsigned int mode, - phy_interface_t interface, - const unsigned long *advertising, - bool permit_pause_to_mac) -{ - struct altera_tse_pcs *tse_pcs = phylink_pcs_to_tse_pcs(pcs); - u32 ctrl, if_mode; - - ctrl = tse_pcs_read(tse_pcs, MII_BMCR); - if_mode = tse_pcs_read(tse_pcs, SGMII_PCS_IF_MODE); - - /* Set link timer to 1.6ms, as per the MegaCore Function User Guide */ - tse_pcs_write(tse_pcs, SGMII_PCS_LINK_TIMER_0, 0x0D40); - tse_pcs_write(tse_pcs, SGMII_PCS_LINK_TIMER_1, 0x03); - - if (interface == PHY_INTERFACE_MODE_SGMII) { - if_mode |= PCS_IF_MODE_USE_SGMII_AN | PCS_IF_MODE_SGMII_ENA; - } else if (interface == PHY_INTERFACE_MODE_1000BASEX) { - if_mode &= ~(PCS_IF_MODE_USE_SGMII_AN | PCS_IF_MODE_SGMII_ENA); - } - - ctrl |= (BMCR_SPEED1000 | BMCR_FULLDPLX | BMCR_ANENABLE); - - tse_pcs_write(tse_pcs, MII_BMCR, ctrl); - tse_pcs_write(tse_pcs, SGMII_PCS_IF_MODE, if_mode); - - return tse_pcs_reset(tse_pcs); -} - -static void alt_tse_pcs_get_state(struct phylink_pcs *pcs, - struct phylink_link_state *state) -{ - struct altera_tse_pcs *tse_pcs = phylink_pcs_to_tse_pcs(pcs); - u16 bmsr, lpa; - - bmsr = tse_pcs_read(tse_pcs, MII_BMSR); - lpa = tse_pcs_read(tse_pcs, MII_LPA); - - phylink_mii_c22_pcs_decode_state(state, bmsr, lpa); -} - -static void alt_tse_pcs_an_restart(struct phylink_pcs *pcs) -{ - struct altera_tse_pcs *tse_pcs = phylink_pcs_to_tse_pcs(pcs); - u16 bmcr; - - bmcr = tse_pcs_read(tse_pcs, MII_BMCR); - bmcr |= BMCR_ANRESTART; - tse_pcs_write(tse_pcs, MII_BMCR, bmcr); - - /* This PCS seems to require a soft reset to re-sync the AN logic */ - tse_pcs_reset(tse_pcs); -} - -static const struct phylink_pcs_ops alt_tse_pcs_ops = { - .pcs_validate = alt_tse_pcs_validate, - .pcs_get_state = alt_tse_pcs_get_state, - .pcs_config = alt_tse_pcs_config, - .pcs_an_restart = alt_tse_pcs_an_restart, -}; - -struct phylink_pcs *alt_tse_pcs_create(struct net_device *ndev, - void __iomem *pcs_base, int reg_width) -{ - struct altera_tse_pcs *tse_pcs; - - if (reg_width != 4 && reg_width != 2) - return ERR_PTR(-EINVAL); - - tse_pcs = devm_kzalloc(&ndev->dev, sizeof(*tse_pcs), GFP_KERNEL); - if (!tse_pcs) - return ERR_PTR(-ENOMEM); - - tse_pcs->pcs.ops = &alt_tse_pcs_ops; - tse_pcs->base = pcs_base; - tse_pcs->reg_width = reg_width; - - return &tse_pcs->pcs; -} -EXPORT_SYMBOL_GPL(alt_tse_pcs_create); - -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("Altera TSE PCS driver"); -MODULE_AUTHOR("Maxime Chevallier <maxime.chevallier@bootlin.com>"); diff --git a/drivers/net/pcs/pcs-lynx.c b/drivers/net/pcs/pcs-lynx.c index 622c3de3f3a8..fca48ebf0b81 100644 --- a/drivers/net/pcs/pcs-lynx.c +++ b/drivers/net/pcs/pcs-lynx.c @@ -6,6 +6,7 @@ #include <linux/mdio.h> #include <linux/phylink.h> #include <linux/pcs-lynx.h> +#include <linux/property.h> #define SGMII_CLOCK_PERIOD_NS 8 /* PCS is clocked at 125 MHz */ #define LINK_TIMER_VAL(ns) ((u32)((ns) / SGMII_CLOCK_PERIOD_NS)) @@ -34,14 +35,6 @@ enum sgmii_speed { #define phylink_pcs_to_lynx(pl_pcs) container_of((pl_pcs), struct lynx_pcs, pcs) #define lynx_to_phylink_pcs(lynx) (&(lynx)->pcs) -struct mdio_device *lynx_get_mdio_device(struct phylink_pcs *pcs) -{ - struct lynx_pcs *lynx = phylink_pcs_to_lynx(pcs); - - return lynx->mdio; -} -EXPORT_SYMBOL(lynx_get_mdio_device); - static void lynx_pcs_get_state_usxgmii(struct mdio_device *pcs, struct phylink_link_state *state) { @@ -315,26 +308,86 @@ static const struct phylink_pcs_ops lynx_pcs_phylink_ops = { .pcs_link_up = lynx_pcs_link_up, }; -struct phylink_pcs *lynx_pcs_create(struct mdio_device *mdio) +static struct phylink_pcs *lynx_pcs_create(struct mdio_device *mdio) { struct lynx_pcs *lynx; lynx = kzalloc(sizeof(*lynx), GFP_KERNEL); if (!lynx) - return NULL; + return ERR_PTR(-ENOMEM); + mdio_device_get(mdio); lynx->mdio = mdio; lynx->pcs.ops = &lynx_pcs_phylink_ops; lynx->pcs.poll = true; return lynx_to_phylink_pcs(lynx); } -EXPORT_SYMBOL(lynx_pcs_create); + +struct phylink_pcs *lynx_pcs_create_mdiodev(struct mii_bus *bus, int addr) +{ + struct mdio_device *mdio; + struct phylink_pcs *pcs; + + mdio = mdio_device_create(bus, addr); + if (IS_ERR(mdio)) + return ERR_CAST(mdio); + + pcs = lynx_pcs_create(mdio); + + /* lynx_create() has taken a refcount on the mdiodev if it was + * successful. If lynx_create() fails, this will free the mdio + * device here. In any case, we don't need to hold our reference + * anymore, and putting it here will allow mdio_device_put() in + * lynx_destroy() to automatically free the mdio device. + */ + mdio_device_put(mdio); + + return pcs; +} +EXPORT_SYMBOL(lynx_pcs_create_mdiodev); + +/* + * lynx_pcs_create_fwnode() creates a lynx PCS instance from the fwnode + * device indicated by node. + * + * Returns: + * -ENODEV if the fwnode is marked unavailable + * -EPROBE_DEFER if we fail to find the device + * -ENOMEM if we fail to allocate memory + * pointer to a phylink_pcs on success + */ +struct phylink_pcs *lynx_pcs_create_fwnode(struct fwnode_handle *node) +{ + struct mdio_device *mdio; + struct phylink_pcs *pcs; + + if (!fwnode_device_is_available(node)) + return ERR_PTR(-ENODEV); + + mdio = fwnode_mdio_find_device(node); + if (!mdio) + return ERR_PTR(-EPROBE_DEFER); + + pcs = lynx_pcs_create(mdio); + + /* lynx_create() has taken a refcount on the mdiodev if it was + * successful. If lynx_create() fails, this will free the mdio + * device here. In any case, we don't need to hold our reference + * anymore, and putting it here will allow mdio_device_put() in + * lynx_destroy() to automatically free the mdio device. + */ + mdio_device_put(mdio); + + return pcs; +} +EXPORT_SYMBOL_GPL(lynx_pcs_create_fwnode); void lynx_pcs_destroy(struct phylink_pcs *pcs) { struct lynx_pcs *lynx = phylink_pcs_to_lynx(pcs); + mdio_device_put(lynx->mdio); kfree(lynx); } EXPORT_SYMBOL(lynx_pcs_destroy); diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index f19d48c94fe0..e4e59aa9faf7 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -64,6 +64,16 @@ static const int xpcs_xlgmii_features[] = { __ETHTOOL_LINK_MODE_MASK_NBITS, }; +static const int xpcs_10gbaser_features[] = { + ETHTOOL_LINK_MODE_Pause_BIT, + ETHTOOL_LINK_MODE_Asym_Pause_BIT, + ETHTOOL_LINK_MODE_10000baseSR_Full_BIT, + ETHTOOL_LINK_MODE_10000baseLR_Full_BIT, + ETHTOOL_LINK_MODE_10000baseLRM_Full_BIT, + ETHTOOL_LINK_MODE_10000baseER_Full_BIT, + __ETHTOOL_LINK_MODE_MASK_NBITS, +}; + static const int xpcs_sgmii_features[] = { ETHTOOL_LINK_MODE_Pause_BIT, ETHTOOL_LINK_MODE_Asym_Pause_BIT, @@ -106,6 +116,10 @@ static const phy_interface_t xpcs_xlgmii_interfaces[] = { PHY_INTERFACE_MODE_XLGMII, }; +static const phy_interface_t xpcs_10gbaser_interfaces[] = { + PHY_INTERFACE_MODE_10GBASER, +}; + static const phy_interface_t xpcs_sgmii_interfaces[] = { PHY_INTERFACE_MODE_SGMII, }; @@ -123,6 +137,7 @@ enum { DW_XPCS_USXGMII, DW_XPCS_10GKR, DW_XPCS_XLGMII, + DW_XPCS_10GBASER, DW_XPCS_SGMII, DW_XPCS_1000BASEX, DW_XPCS_2500BASEX, @@ -246,6 +261,7 @@ static int xpcs_soft_reset(struct dw_xpcs *xpcs, switch (compat->an_mode) { case DW_AN_C73: + case DW_10GBASER: dev = MDIO_MMD_PCS; break; case DW_AN_C37_SGMII: @@ -271,15 +287,12 @@ static int xpcs_soft_reset(struct dw_xpcs *xpcs, }) static int xpcs_read_fault_c73(struct dw_xpcs *xpcs, - struct phylink_link_state *state) + struct phylink_link_state *state, + u16 pcs_stat1) { int ret; - ret = xpcs_read(xpcs, MDIO_MMD_PCS, MDIO_STAT1); - if (ret < 0) - return ret; - - if (ret & MDIO_STAT1_FAULT) { + if (pcs_stat1 & MDIO_STAT1_FAULT) { xpcs_warn(xpcs, state, "Link fault condition detected!\n"); return -EFAULT; } @@ -321,37 +334,6 @@ static int xpcs_read_fault_c73(struct dw_xpcs *xpcs, return 0; } -static int xpcs_read_link_c73(struct dw_xpcs *xpcs) -{ - bool link = true; - int ret; - - ret = xpcs_read(xpcs, MDIO_MMD_PCS, MDIO_STAT1); - if (ret < 0) - return ret; - - if (!(ret & MDIO_STAT1_LSTATUS)) - link = false; - - return link; -} - -static int xpcs_get_max_usxgmii_speed(const unsigned long *supported) -{ - int max = SPEED_UNKNOWN; - - if (phylink_test(supported, 1000baseKX_Full)) - max = SPEED_1000; - if (phylink_test(supported, 2500baseX_Full)) - max = SPEED_2500; - if (phylink_test(supported, 10000baseKX4_Full)) - max = SPEED_10000; - if (phylink_test(supported, 10000baseKR_Full)) - max = SPEED_10000; - - return max; -} - static void xpcs_config_usxgmii(struct dw_xpcs *xpcs, int speed) { int ret, speed_sel; @@ -478,16 +460,12 @@ static int xpcs_config_aneg_c73(struct dw_xpcs *xpcs, static int xpcs_aneg_done_c73(struct dw_xpcs *xpcs, struct phylink_link_state *state, - const struct xpcs_compat *compat) + const struct xpcs_compat *compat, u16 an_stat1) { int ret; - ret = xpcs_read(xpcs, MDIO_MMD_AN, MDIO_STAT1); - if (ret < 0) - return ret; - - if (ret & MDIO_AN_STAT1_COMPLETE) { - ret = xpcs_read(xpcs, MDIO_MMD_AN, DW_SR_AN_LP_ABL1); + if (an_stat1 & MDIO_AN_STAT1_COMPLETE) { + ret = xpcs_read(xpcs, MDIO_MMD_AN, MDIO_AN_LPA); if (ret < 0) return ret; @@ -504,64 +482,32 @@ static int xpcs_aneg_done_c73(struct dw_xpcs *xpcs, } static int xpcs_read_lpa_c73(struct dw_xpcs *xpcs, - struct phylink_link_state *state) + struct phylink_link_state *state, u16 an_stat1) { - int ret; - - ret = xpcs_read(xpcs, MDIO_MMD_AN, MDIO_STAT1); - if (ret < 0) - return ret; + u16 lpa[3]; + int i, ret; - if (!(ret & MDIO_AN_STAT1_LPABLE)) { + if (!(an_stat1 & MDIO_AN_STAT1_LPABLE)) { phylink_clear(state->lp_advertising, Autoneg); return 0; } phylink_set(state->lp_advertising, Autoneg); - /* Clause 73 outcome */ - ret = xpcs_read(xpcs, MDIO_MMD_AN, DW_SR_AN_LP_ABL3); - if (ret < 0) - return ret; - - if (ret & DW_C73_2500KX) - phylink_set(state->lp_advertising, 2500baseX_Full); - - ret = xpcs_read(xpcs, MDIO_MMD_AN, DW_SR_AN_LP_ABL2); - if (ret < 0) - return ret; - - if (ret & DW_C73_1000KX) - phylink_set(state->lp_advertising, 1000baseKX_Full); - if (ret & DW_C73_10000KX4) - phylink_set(state->lp_advertising, 10000baseKX4_Full); - if (ret & DW_C73_10000KR) - phylink_set(state->lp_advertising, 10000baseKR_Full); + /* Read Clause 73 link partner advertisement */ + for (i = ARRAY_SIZE(lpa); --i >= 0; ) { + ret = xpcs_read(xpcs, MDIO_MMD_AN, MDIO_AN_LPA + i); + if (ret < 0) + return ret; - ret = xpcs_read(xpcs, MDIO_MMD_AN, DW_SR_AN_LP_ABL1); - if (ret < 0) - return ret; + lpa[i] = ret; + } - if (ret & DW_C73_PAUSE) - phylink_set(state->lp_advertising, Pause); - if (ret & DW_C73_ASYM_PAUSE) - phylink_set(state->lp_advertising, Asym_Pause); + mii_c73_mod_linkmode(state->lp_advertising, lpa); - linkmode_and(state->lp_advertising, state->lp_advertising, - state->advertising); return 0; } -static void xpcs_resolve_lpa_c73(struct dw_xpcs *xpcs, - struct phylink_link_state *state) -{ - int max_speed = xpcs_get_max_usxgmii_speed(state->lp_advertising); - - state->pause = MLO_PAUSE_TX | MLO_PAUSE_RX; - state->speed = max_speed; - state->duplex = DUPLEX_FULL; -} - static int xpcs_get_max_xlgmii_speed(struct dw_xpcs *xpcs, struct phylink_link_state *state) { @@ -872,8 +818,10 @@ int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, return -ENODEV; switch (compat->an_mode) { + case DW_10GBASER: + break; case DW_AN_C73: - if (phylink_autoneg_inband(mode)) { + if (test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, advertising)) { ret = xpcs_config_aneg_c73(xpcs, compat); if (ret) return ret; @@ -924,13 +872,25 @@ static int xpcs_get_state_c73(struct dw_xpcs *xpcs, const struct xpcs_compat *compat) { bool an_enabled; + int pcs_stat1; + int an_stat1; int ret; + /* The link status bit is latching-low, so it is important to + * avoid unnecessary re-reads of this register to avoid missing + * a link-down event. + */ + pcs_stat1 = xpcs_read(xpcs, MDIO_MMD_PCS, MDIO_STAT1); + if (pcs_stat1 < 0) { + state->link = false; + return pcs_stat1; + } + /* Link needs to be read first ... */ - state->link = xpcs_read_link_c73(xpcs) > 0 ? 1 : 0; + state->link = !!(pcs_stat1 & MDIO_STAT1_LSTATUS); /* ... and then we check the faults. */ - ret = xpcs_read_fault_c73(xpcs, state); + ret = xpcs_read_fault_c73(xpcs, state, pcs_stat1); if (ret) { ret = xpcs_soft_reset(xpcs, compat); if (ret) @@ -941,15 +901,38 @@ static int xpcs_get_state_c73(struct dw_xpcs *xpcs, return xpcs_do_config(xpcs, state->interface, MLO_AN_INBAND, NULL); } + /* There is no point doing anything else if the link is down. */ + if (!state->link) + return 0; + an_enabled = linkmode_test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, state->advertising); - if (an_enabled && xpcs_aneg_done_c73(xpcs, state, compat)) { - state->an_complete = true; - xpcs_read_lpa_c73(xpcs, state); - xpcs_resolve_lpa_c73(xpcs, state); - } else if (an_enabled) { - state->link = 0; - } else if (state->link) { + if (an_enabled) { + /* The link status bit is latching-low, so it is important to + * avoid unnecessary re-reads of this register to avoid missing + * a link-down event. + */ + an_stat1 = xpcs_read(xpcs, MDIO_MMD_AN, MDIO_STAT1); + if (an_stat1 < 0) { + state->link = false; + return an_stat1; + } + + state->an_complete = xpcs_aneg_done_c73(xpcs, state, compat, + an_stat1); + if (!state->an_complete) { + state->link = false; + return 0; + } + + ret = xpcs_read_lpa_c73(xpcs, state, an_stat1); + if (ret < 0) { + state->link = false; + return ret; + } + + phylink_resolve_c73(state); + } else { xpcs_resolve_pma(xpcs, state); } @@ -1033,6 +1016,9 @@ static void xpcs_get_state(struct phylink_pcs *pcs, return; switch (compat->an_mode) { + case DW_10GBASER: + phylink_mii_c45_pcs_get_state(xpcs->mdiodev, state); + break; case DW_AN_C73: ret = xpcs_get_state_c73(xpcs, state, compat); if (ret) { @@ -1188,6 +1174,12 @@ static const struct xpcs_compat synopsys_xpcs_compat[DW_XPCS_INTERFACE_MAX] = { .num_interfaces = ARRAY_SIZE(xpcs_xlgmii_interfaces), .an_mode = DW_AN_C73, }, + [DW_XPCS_10GBASER] = { + .supported = xpcs_10gbaser_features, + .interface = xpcs_10gbaser_interfaces, + .num_interfaces = ARRAY_SIZE(xpcs_10gbaser_interfaces), + .an_mode = DW_10GBASER, + }, [DW_XPCS_SGMII] = { .supported = xpcs_sgmii_features, .interface = xpcs_sgmii_interfaces, @@ -1259,8 +1251,8 @@ static const struct phylink_pcs_ops xpcs_phylink_ops = { .pcs_link_up = xpcs_link_up, }; -struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev, - phy_interface_t interface) +static struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev, + phy_interface_t interface) { struct dw_xpcs *xpcs; u32 xpcs_id; @@ -1270,6 +1262,7 @@ struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev, if (!xpcs) return ERR_PTR(-ENOMEM); + mdio_device_get(mdiodev); xpcs->mdiodev = mdiodev; xpcs_id = xpcs_get_id(xpcs); @@ -1290,6 +1283,9 @@ struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev, } xpcs->pcs.ops = &xpcs_phylink_ops; + if (compat->an_mode == DW_10GBASER) + return xpcs; + xpcs->pcs.poll = true; ret = xpcs_soft_reset(xpcs, compat); @@ -1302,16 +1298,42 @@ struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev, ret = -ENODEV; out: + mdio_device_put(mdiodev); kfree(xpcs); return ERR_PTR(ret); } -EXPORT_SYMBOL_GPL(xpcs_create); void xpcs_destroy(struct dw_xpcs *xpcs) { + if (xpcs) + mdio_device_put(xpcs->mdiodev); kfree(xpcs); } EXPORT_SYMBOL_GPL(xpcs_destroy); +struct dw_xpcs *xpcs_create_mdiodev(struct mii_bus *bus, int addr, + phy_interface_t interface) +{ + struct mdio_device *mdiodev; + struct dw_xpcs *xpcs; + + mdiodev = mdio_device_create(bus, addr); + if (IS_ERR(mdiodev)) + return ERR_CAST(mdiodev); + + xpcs = xpcs_create(mdiodev, interface); + + /* xpcs_create() has taken a refcount on the mdiodev if it was + * successful. If xpcs_create() fails, this will free the mdio + * device here. In any case, we don't need to hold our reference + * anymore, and putting it here will allow mdio_device_put() in + * xpcs_destroy() to automatically free the mdio device. + */ + mdio_device_put(mdiodev); + + return xpcs; +} +EXPORT_SYMBOL_GPL(xpcs_create_mdiodev); + MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/pcs/pcs-xpcs.h b/drivers/net/pcs/pcs-xpcs.h index 770df50323a0..68c6b5a62088 100644 --- a/drivers/net/pcs/pcs-xpcs.h +++ b/drivers/net/pcs/pcs-xpcs.h @@ -32,9 +32,6 @@ #define DW_SR_AN_ADV1 0x10 #define DW_SR_AN_ADV2 0x11 #define DW_SR_AN_ADV3 0x12 -#define DW_SR_AN_LP_ABL1 0x13 -#define DW_SR_AN_LP_ABL2 0x14 -#define DW_SR_AN_LP_ABL3 0x15 /* Clause 73 Defines */ /* AN_LP_ABL1 */ diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 93b8efc79227..059bd06a8cce 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -243,9 +243,10 @@ config MICREL_PHY Supports the KSZ9021, VSC8201, KS8001 PHYs. config MICROCHIP_T1S_PHY - tristate "Microchip 10BASE-T1S Ethernet PHY" + tristate "Microchip 10BASE-T1S Ethernet PHYs" help - Currently supports the LAN8670, LAN8671, LAN8672 + Currently supports the LAN8670/1/2 Rev.B1 and LAN8650/1 Rev.B0 Internal + PHYs. config MICROCHIP_PHY tristate "Microchip PHYs" diff --git a/drivers/net/phy/bcm-phy-lib.c b/drivers/net/phy/bcm-phy-lib.c index 27c57f6ab211..876f28fd8256 100644 --- a/drivers/net/phy/bcm-phy-lib.c +++ b/drivers/net/phy/bcm-phy-lib.c @@ -496,18 +496,20 @@ EXPORT_SYMBOL_GPL(bcm_phy_downshift_set); struct bcm_phy_hw_stat { const char *string; - u8 reg; + int devad; + u16 reg; u8 shift; u8 bits; }; /* Counters freeze at either 0xffff or 0xff, better than nothing */ static const struct bcm_phy_hw_stat bcm_phy_hw_stats[] = { - { "phy_receive_errors", MII_BRCM_CORE_BASE12, 0, 16 }, - { "phy_serdes_ber_errors", MII_BRCM_CORE_BASE13, 8, 8 }, - { "phy_false_carrier_sense_errors", MII_BRCM_CORE_BASE13, 0, 8 }, - { "phy_local_rcvr_nok", MII_BRCM_CORE_BASE14, 8, 8 }, - { "phy_remote_rcv_nok", MII_BRCM_CORE_BASE14, 0, 8 }, + { "phy_receive_errors", -1, MII_BRCM_CORE_BASE12, 0, 16 }, + { "phy_serdes_ber_errors", -1, MII_BRCM_CORE_BASE13, 8, 8 }, + { "phy_false_carrier_sense_errors", -1, MII_BRCM_CORE_BASE13, 0, 8 }, + { "phy_local_rcvr_nok", -1, MII_BRCM_CORE_BASE14, 8, 8 }, + { "phy_remote_rcv_nok", -1, MII_BRCM_CORE_BASE14, 0, 8 }, + { "phy_lpi_count", MDIO_MMD_AN, BRCM_CL45VEN_EEE_LPI_CNT, 0, 16 }, }; int bcm_phy_get_sset_count(struct phy_device *phydev) @@ -536,7 +538,10 @@ static u64 bcm_phy_get_stat(struct phy_device *phydev, u64 *shadow, int val; u64 ret; - val = phy_read(phydev, stat.reg); + if (stat.devad < 0) + val = phy_read(phydev, stat.reg); + else + val = phy_read_mmd(phydev, stat.devad, stat.reg); if (val < 0) { ret = U64_MAX; } else { @@ -1028,6 +1033,39 @@ void bcm_phy_get_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol) } EXPORT_SYMBOL_GPL(bcm_phy_get_wol); +irqreturn_t bcm_phy_wol_isr(int irq, void *dev_id) +{ + return IRQ_HANDLED; +} +EXPORT_SYMBOL_GPL(bcm_phy_wol_isr); + +int bcm_phy_led_brightness_set(struct phy_device *phydev, + u8 index, enum led_brightness value) +{ + u8 led_num; + int ret; + u16 reg; + + if (index >= 4) + return -EINVAL; + + /* Two LEDS per register */ + led_num = index % 2; + reg = index >= 2 ? BCM54XX_SHD_LEDS2 : BCM54XX_SHD_LEDS1; + + ret = bcm_phy_read_shadow(phydev, reg); + if (ret < 0) + return ret; + + ret &= ~(BCM_LED_SRC_MASK << BCM54XX_SHD_LEDS_SHIFT(led_num)); + if (value == LED_OFF) + ret |= BCM_LED_SRC_OFF << BCM54XX_SHD_LEDS_SHIFT(led_num); + else + ret |= BCM_LED_SRC_ON << BCM54XX_SHD_LEDS_SHIFT(led_num); + return bcm_phy_write_shadow(phydev, reg, ret); +} +EXPORT_SYMBOL_GPL(bcm_phy_led_brightness_set); + MODULE_DESCRIPTION("Broadcom PHY Library"); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Broadcom Corporation"); diff --git a/drivers/net/phy/bcm-phy-lib.h b/drivers/net/phy/bcm-phy-lib.h index c6fed43ec913..b52189e45a84 100644 --- a/drivers/net/phy/bcm-phy-lib.h +++ b/drivers/net/phy/bcm-phy-lib.h @@ -8,6 +8,7 @@ #include <linux/brcmphy.h> #include <linux/phy.h> +#include <linux/interrupt.h> struct ethtool_wolinfo; @@ -115,5 +116,9 @@ static inline void bcm_ptp_stop(struct bcm_ptp_private *priv) int bcm_phy_set_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol); void bcm_phy_get_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol); +irqreturn_t bcm_phy_wol_isr(int irq, void *dev_id); + +int bcm_phy_led_brightness_set(struct phy_device *phydev, + u8 index, enum led_brightness value); #endif /* _LINUX_BCM_PHY_LIB_H */ diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index 418e6bc0e998..9f0a9c575bd7 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -414,13 +414,13 @@ static int bcm54xx_config_init(struct phy_device *phydev) * these settings will cause LOS to malfunction. */ if (!phy_on_sfp(phydev)) { - val = BCM5482_SHD_LEDS1_LED1(BCM_LED_SRC_MULTICOLOR1) | - BCM5482_SHD_LEDS1_LED3(BCM_LED_SRC_MULTICOLOR1); - bcm_phy_write_shadow(phydev, BCM5482_SHD_LEDS1, val); + val = BCM54XX_SHD_LEDS1_LED1(BCM_LED_SRC_MULTICOLOR1) | + BCM54XX_SHD_LEDS1_LED3(BCM_LED_SRC_MULTICOLOR1); + bcm_phy_write_shadow(phydev, BCM54XX_SHD_LEDS1, val); val = BCM_LED_MULTICOLOR_IN_PHASE | - BCM5482_SHD_LEDS1_LED1(BCM_LED_MULTICOLOR_LINK_ACT) | - BCM5482_SHD_LEDS1_LED3(BCM_LED_MULTICOLOR_LINK_ACT); + BCM54XX_SHD_LEDS1_LED1(BCM_LED_MULTICOLOR_LINK_ACT) | + BCM54XX_SHD_LEDS1_LED3(BCM_LED_MULTICOLOR_LINK_ACT); bcm_phy_write_exp(phydev, BCM_EXP_MULTICOLOR, val); } @@ -927,7 +927,14 @@ static int bcm54xx_phy_probe(struct phy_device *phydev) if (!IS_ERR(wakeup_gpio)) { priv->wake_irq = gpiod_to_irq(wakeup_gpio); - ret = irq_set_irq_type(priv->wake_irq, IRQ_TYPE_LEVEL_LOW); + + /* Dummy interrupt handler which is not enabled but is provided + * in order for the interrupt descriptor to be fully set-up. + */ + ret = devm_request_irq(&phydev->mdio.dev, priv->wake_irq, + bcm_phy_wol_isr, + IRQF_TRIGGER_LOW | IRQF_NO_AUTOEN, + dev_name(&phydev->mdio.dev), phydev); if (ret) return ret; } @@ -1024,6 +1031,7 @@ static struct phy_driver broadcom_drivers[] = { .resume = bcm54xx_resume, .get_wol = bcm54xx_phy_get_wol, .set_wol = bcm54xx_phy_set_wol, + .led_brightness_set = bcm_phy_led_brightness_set, }, { .phy_id = PHY_ID_BCM5461, .phy_id_mask = 0xfffffff0, @@ -1037,6 +1045,7 @@ static struct phy_driver broadcom_drivers[] = { .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, .link_change_notify = bcm54xx_link_change_notify, + .led_brightness_set = bcm_phy_led_brightness_set, }, { .phy_id = PHY_ID_BCM54612E, .phy_id_mask = 0xfffffff0, @@ -1050,6 +1059,7 @@ static struct phy_driver broadcom_drivers[] = { .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, .link_change_notify = bcm54xx_link_change_notify, + .led_brightness_set = bcm_phy_led_brightness_set, }, { .phy_id = PHY_ID_BCM54616S, .phy_id_mask = 0xfffffff0, @@ -1063,6 +1073,7 @@ static struct phy_driver broadcom_drivers[] = { .read_status = bcm54616s_read_status, .probe = bcm54616s_probe, .link_change_notify = bcm54xx_link_change_notify, + .led_brightness_set = bcm_phy_led_brightness_set, }, { .phy_id = PHY_ID_BCM5464, .phy_id_mask = 0xfffffff0, @@ -1078,6 +1089,7 @@ static struct phy_driver broadcom_drivers[] = { .suspend = genphy_suspend, .resume = genphy_resume, .link_change_notify = bcm54xx_link_change_notify, + .led_brightness_set = bcm_phy_led_brightness_set, }, { .phy_id = PHY_ID_BCM5481, .phy_id_mask = 0xfffffff0, @@ -1092,6 +1104,7 @@ static struct phy_driver broadcom_drivers[] = { .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, .link_change_notify = bcm54xx_link_change_notify, + .led_brightness_set = bcm_phy_led_brightness_set, }, { .phy_id = PHY_ID_BCM54810, .phy_id_mask = 0xfffffff0, @@ -1108,6 +1121,7 @@ static struct phy_driver broadcom_drivers[] = { .suspend = bcm54xx_suspend, .resume = bcm54xx_resume, .link_change_notify = bcm54xx_link_change_notify, + .led_brightness_set = bcm_phy_led_brightness_set, }, { .phy_id = PHY_ID_BCM54811, .phy_id_mask = 0xfffffff0, @@ -1124,6 +1138,7 @@ static struct phy_driver broadcom_drivers[] = { .suspend = bcm54xx_suspend, .resume = bcm54xx_resume, .link_change_notify = bcm54xx_link_change_notify, + .led_brightness_set = bcm_phy_led_brightness_set, }, { .phy_id = PHY_ID_BCM5482, .phy_id_mask = 0xfffffff0, @@ -1137,6 +1152,7 @@ static struct phy_driver broadcom_drivers[] = { .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, .link_change_notify = bcm54xx_link_change_notify, + .led_brightness_set = bcm_phy_led_brightness_set, }, { .phy_id = PHY_ID_BCM50610, .phy_id_mask = 0xfffffff0, @@ -1152,6 +1168,7 @@ static struct phy_driver broadcom_drivers[] = { .link_change_notify = bcm54xx_link_change_notify, .suspend = bcm54xx_suspend, .resume = bcm54xx_resume, + .led_brightness_set = bcm_phy_led_brightness_set, }, { .phy_id = PHY_ID_BCM50610M, .phy_id_mask = 0xfffffff0, @@ -1167,6 +1184,7 @@ static struct phy_driver broadcom_drivers[] = { .link_change_notify = bcm54xx_link_change_notify, .suspend = bcm54xx_suspend, .resume = bcm54xx_resume, + .led_brightness_set = bcm_phy_led_brightness_set, }, { .phy_id = PHY_ID_BCM57780, .phy_id_mask = 0xfffffff0, @@ -1180,6 +1198,7 @@ static struct phy_driver broadcom_drivers[] = { .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, .link_change_notify = bcm54xx_link_change_notify, + .led_brightness_set = bcm_phy_led_brightness_set, }, { .phy_id = PHY_ID_BCMAC131, .phy_id_mask = 0xfffffff0, @@ -1211,6 +1230,7 @@ static struct phy_driver broadcom_drivers[] = { .get_stats = bcm54xx_get_stats, .probe = bcm54xx_phy_probe, .link_change_notify = bcm54xx_link_change_notify, + .led_brightness_set = bcm_phy_led_brightness_set, }, { .phy_id = PHY_ID_BCM53125, .phy_id_mask = 0xfffffff0, @@ -1225,6 +1245,7 @@ static struct phy_driver broadcom_drivers[] = { .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, .link_change_notify = bcm54xx_link_change_notify, + .led_brightness_set = bcm_phy_led_brightness_set, }, { .phy_id = PHY_ID_BCM53128, .phy_id_mask = 0xfffffff0, @@ -1239,6 +1260,7 @@ static struct phy_driver broadcom_drivers[] = { .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, .link_change_notify = bcm54xx_link_change_notify, + .led_brightness_set = bcm_phy_led_brightness_set, }, { .phy_id = PHY_ID_BCM89610, .phy_id_mask = 0xfffffff0, diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index d75f526a20a4..76f5a2402fb0 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -44,6 +44,7 @@ #define DP83867_STRAP_STS1 0x006E #define DP83867_STRAP_STS2 0x006f #define DP83867_RGMIIDCTL 0x0086 +#define DP83867_DSP_FFE_CFG 0x012c #define DP83867_RXFCFG 0x0134 #define DP83867_RXFPMD1 0x0136 #define DP83867_RXFPMD2 0x0137 @@ -941,8 +942,27 @@ static int dp83867_phy_reset(struct phy_device *phydev) usleep_range(10, 20); - return phy_modify(phydev, MII_DP83867_PHYCTRL, + err = phy_modify(phydev, MII_DP83867_PHYCTRL, DP83867_PHYCR_FORCE_LINK_GOOD, 0); + if (err < 0) + return err; + + /* Configure the DSP Feedforward Equalizer Configuration register to + * improve short cable (< 1 meter) performance. This will not affect + * long cable performance. + */ + err = phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_DSP_FFE_CFG, + 0x0e81); + if (err < 0) + return err; + + err = phy_write(phydev, DP83867_CTRL, DP83867_SW_RESTART); + if (err < 0) + return err; + + usleep_range(10, 20); + + return 0; } static void dp83867_link_change_notify(struct phy_device *phydev) diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 3f81bb8dac44..6d18ea19e442 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -637,7 +637,7 @@ static int ksz8051_ksz8795_match_phy_device(struct phy_device *phydev, { int ret; - if ((phydev->phy_id & MICREL_PHY_ID_MASK) != PHY_ID_KSZ8051) + if (!phy_id_compare(phydev->phy_id, PHY_ID_KSZ8051, MICREL_PHY_ID_MASK)) return 0; ret = phy_read(phydev, MII_BMSR); @@ -1566,7 +1566,7 @@ static int ksz9x31_cable_test_fault_length(struct phy_device *phydev, u16 stat) * * distance to fault = (VCT_DATA - 22) * 4 / cable propagation velocity */ - if ((phydev->phy_id & MICREL_PHY_ID_MASK) == PHY_ID_KSZ9131) + if (phydev_id_compare(phydev, PHY_ID_KSZ9131)) dt = clamp(dt - 22, 0, 255); return (dt * 400) / 10; @@ -1774,6 +1774,79 @@ static int ksz886x_read_status(struct phy_device *phydev) return genphy_read_status(phydev); } +struct ksz9477_errata_write { + u8 dev_addr; + u8 reg_addr; + u16 val; +}; + +static const struct ksz9477_errata_write ksz9477_errata_writes[] = { + /* Register settings are needed to improve PHY receive performance */ + {0x01, 0x6f, 0xdd0b}, + {0x01, 0x8f, 0x6032}, + {0x01, 0x9d, 0x248c}, + {0x01, 0x75, 0x0060}, + {0x01, 0xd3, 0x7777}, + {0x1c, 0x06, 0x3008}, + {0x1c, 0x08, 0x2000}, + + /* Transmit waveform amplitude can be improved (1000BASE-T, 100BASE-TX, 10BASE-Te) */ + {0x1c, 0x04, 0x00d0}, + + /* Energy Efficient Ethernet (EEE) feature select must be manually disabled */ + {0x07, 0x3c, 0x0000}, + + /* Register settings are required to meet data sheet supply current specifications */ + {0x1c, 0x13, 0x6eff}, + {0x1c, 0x14, 0xe6ff}, + {0x1c, 0x15, 0x6eff}, + {0x1c, 0x16, 0xe6ff}, + {0x1c, 0x17, 0x00ff}, + {0x1c, 0x18, 0x43ff}, + {0x1c, 0x19, 0xc3ff}, + {0x1c, 0x1a, 0x6fff}, + {0x1c, 0x1b, 0x07ff}, + {0x1c, 0x1c, 0x0fff}, + {0x1c, 0x1d, 0xe7ff}, + {0x1c, 0x1e, 0xefff}, + {0x1c, 0x20, 0xeeee}, +}; + +static int ksz9477_config_init(struct phy_device *phydev) +{ + int err; + int i; + + /* Apply PHY settings to address errata listed in + * KSZ9477, KSZ9897, KSZ9896, KSZ9567, KSZ8565 + * Silicon Errata and Data Sheet Clarification documents. + * + * Document notes: Before configuring the PHY MMD registers, it is + * necessary to set the PHY to 100 Mbps speed with auto-negotiation + * disabled by writing to register 0xN100-0xN101. After writing the + * MMD registers, and after all errata workarounds that involve PHY + * register settings, write register 0xN100-0xN101 again to enable + * and restart auto-negotiation. + */ + err = phy_write(phydev, MII_BMCR, BMCR_SPEED100 | BMCR_FULLDPLX); + if (err) + return err; + + for (i = 0; i < ARRAY_SIZE(ksz9477_errata_writes); ++i) { + const struct ksz9477_errata_write *errata = &ksz9477_errata_writes[i]; + + err = phy_write_mmd(phydev, errata->dev_addr, errata->reg_addr, errata->val); + if (err) + return err; + } + + err = genphy_restart_aneg(phydev); + if (err) + return err; + + return kszphy_config_init(phydev); +} + static int kszphy_get_sset_count(struct phy_device *phydev) { return ARRAY_SIZE(kszphy_hw_stats); @@ -1998,7 +2071,7 @@ static __always_inline int ksz886x_cable_test_fault_length(struct phy_device *ph */ dt = FIELD_GET(data_mask, status); - if ((phydev->phy_id & MICREL_PHY_ID_MASK) == PHY_ID_LAN8814) + if (phydev_id_compare(phydev, PHY_ID_LAN8814)) return ((dt - 22) * 800) / 10; else return (dt * 400) / 10; @@ -4735,7 +4808,7 @@ static struct phy_driver ksphy_driver[] = { .phy_id_mask = MICREL_PHY_ID_MASK, .name = "Microchip KSZ9477", /* PHY_GBIT_FEATURES */ - .config_init = kszphy_config_init, + .config_init = ksz9477_config_init, .config_intr = kszphy_config_intr, .handle_interrupt = kszphy_handle_interrupt, .suspend = genphy_suspend, diff --git a/drivers/net/phy/microchip_t1s.c b/drivers/net/phy/microchip_t1s.c index 094967b3c111..534ca7d1b061 100644 --- a/drivers/net/phy/microchip_t1s.c +++ b/drivers/net/phy/microchip_t1s.c @@ -1,19 +1,29 @@ // SPDX-License-Identifier: GPL-2.0+ /* - * Driver for Microchip 10BASE-T1S LAN867X PHY + * Driver for Microchip 10BASE-T1S PHYs * * Support: Microchip Phys: - * lan8670, lan8671, lan8672 + * lan8670/1/2 Rev.B1 + * lan8650/1 Rev.B0 Internal PHYs */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/phy.h> -#define PHY_ID_LAN867X 0x0007C160 +#define PHY_ID_LAN867X_REVB1 0x0007C162 +#define PHY_ID_LAN865X_REVB0 0x0007C1B3 -#define LAN867X_REG_IRQ_1_CTL 0x001C -#define LAN867X_REG_IRQ_2_CTL 0x001D +#define LAN867X_REG_STS2 0x0019 + +#define LAN867x_RESET_COMPLETE_STS BIT(11) + +#define LAN865X_REG_CFGPARAM_ADDR 0x00D8 +#define LAN865X_REG_CFGPARAM_DATA 0x00D9 +#define LAN865X_REG_CFGPARAM_CTRL 0x00DA +#define LAN865X_REG_STS2 0x0019 + +#define LAN865X_CFGPARAM_READ_ENABLE BIT(1) /* The arrays below are pulled from the following table from AN1699 * Access MMD Address Value Mask @@ -31,72 +41,219 @@ * W 0x1F 0x0099 0x7F80 ------ */ -static const int lan867x_fixup_registers[12] = { +static const u32 lan867x_revb1_fixup_registers[12] = { 0x00D0, 0x00D1, 0x0084, 0x0085, 0x008A, 0x0087, 0x0088, 0x008B, 0x0080, 0x00F1, 0x0096, 0x0099, }; -static const int lan867x_fixup_values[12] = { +static const u16 lan867x_revb1_fixup_values[12] = { 0x0002, 0x0000, 0x3380, 0x0006, 0xC000, 0x801C, 0x033F, 0x0404, 0x0600, 0x2400, 0x2000, 0x7F80, }; -static const int lan867x_fixup_masks[12] = { +static const u16 lan867x_revb1_fixup_masks[12] = { 0x0E03, 0x0300, 0xFFC0, 0x000F, 0xF800, 0x801C, 0x1FFF, 0xFFFF, 0x0600, 0x7F00, 0x2000, 0xFFFF, }; -static int lan867x_config_init(struct phy_device *phydev) +/* LAN865x Rev.B0 configuration parameters from AN1760 */ +static const u32 lan865x_revb0_fixup_registers[28] = { + 0x0091, 0x0081, 0x0043, 0x0044, + 0x0045, 0x0053, 0x0054, 0x0055, + 0x0040, 0x0050, 0x00D0, 0x00E9, + 0x00F5, 0x00F4, 0x00F8, 0x00F9, + 0x00B0, 0x00B1, 0x00B2, 0x00B3, + 0x00B4, 0x00B5, 0x00B6, 0x00B7, + 0x00B8, 0x00B9, 0x00BA, 0x00BB, +}; + +static const u16 lan865x_revb0_fixup_values[28] = { + 0x9660, 0x00C0, 0x00FF, 0xFFFF, + 0x0000, 0x00FF, 0xFFFF, 0x0000, + 0x0002, 0x0002, 0x5F21, 0x9E50, + 0x1CF8, 0xC020, 0x9B00, 0x4E53, + 0x0103, 0x0910, 0x1D26, 0x002A, + 0x0103, 0x070D, 0x1720, 0x0027, + 0x0509, 0x0E13, 0x1C25, 0x002B, +}; + +static const u16 lan865x_revb0_fixup_cfg_regs[5] = { + 0x0084, 0x008A, 0x00AD, 0x00AE, 0x00AF +}; + +/* Pulled from AN1760 describing 'indirect read' + * + * write_register(0x4, 0x00D8, addr) + * write_register(0x4, 0x00DA, 0x2) + * return (int8)(read_register(0x4, 0x00D9)) + * + * 0x4 refers to memory map selector 4, which maps to MDIO_MMD_VEND2 + */ +static int lan865x_revb0_indirect_read(struct phy_device *phydev, u16 addr) +{ + int ret; + + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, LAN865X_REG_CFGPARAM_ADDR, + addr); + if (ret) + return ret; + + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, LAN865X_REG_CFGPARAM_CTRL, + LAN865X_CFGPARAM_READ_ENABLE); + if (ret) + return ret; + + return phy_read_mmd(phydev, MDIO_MMD_VEND2, LAN865X_REG_CFGPARAM_DATA); +} + +/* This is pulled straight from AN1760 from 'calculation of offset 1' & + * 'calculation of offset 2' + */ +static int lan865x_generate_cfg_offsets(struct phy_device *phydev, s8 offsets[2]) +{ + const u16 fixup_regs[2] = {0x0004, 0x0008}; + int ret; + + for (int i = 0; i < ARRAY_SIZE(fixup_regs); i++) { + ret = lan865x_revb0_indirect_read(phydev, fixup_regs[i]); + if (ret < 0) + return ret; + if (ret & BIT(4)) + offsets[i] = ret | 0xE0; + else + offsets[i] = ret; + } + + return 0; +} + +static int lan865x_read_cfg_params(struct phy_device *phydev, u16 cfg_params[]) +{ + int ret; + + for (int i = 0; i < ARRAY_SIZE(lan865x_revb0_fixup_cfg_regs); i++) { + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, + lan865x_revb0_fixup_cfg_regs[i]); + if (ret < 0) + return ret; + cfg_params[i] = (u16)ret; + } + + return 0; +} + +static int lan865x_write_cfg_params(struct phy_device *phydev, u16 cfg_params[]) { - /* HW quirk: Microchip states in the application note (AN1699) for the phy - * that a set of read-modify-write (rmw) operations has to be performed - * on a set of seemingly magic registers. - * The result of these operations is just described as 'optimal performance' - * Microchip gives no explanation as to what these mmd regs do, - * in fact they are marked as reserved in the datasheet. - * It is unclear if phy_modify_mmd would be safe to use or if a write - * really has to happen to each register. - * In order to exactly conform to what is stated in the AN phy_write_mmd is - * used, which might then write the same value back as read + modified. + int ret; + + for (int i = 0; i < ARRAY_SIZE(lan865x_revb0_fixup_cfg_regs); i++) { + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, + lan865x_revb0_fixup_cfg_regs[i], + cfg_params[i]); + if (ret) + return ret; + } + + return 0; +} + +static int lan865x_setup_cfgparam(struct phy_device *phydev) +{ + u16 cfg_params[ARRAY_SIZE(lan865x_revb0_fixup_cfg_regs)]; + u16 cfg_results[5]; + s8 offsets[2]; + int ret; + + ret = lan865x_generate_cfg_offsets(phydev, offsets); + if (ret) + return ret; + + ret = lan865x_read_cfg_params(phydev, cfg_params); + if (ret) + return ret; + + cfg_results[0] = (cfg_params[0] & 0x000F) | + FIELD_PREP(GENMASK(15, 10), 9 + offsets[0]) | + FIELD_PREP(GENMASK(15, 4), 14 + offsets[0]); + cfg_results[1] = (cfg_params[1] & 0x03FF) | + FIELD_PREP(GENMASK(15, 10), 40 + offsets[1]); + cfg_results[2] = (cfg_params[2] & 0xC0C0) | + FIELD_PREP(GENMASK(15, 8), 5 + offsets[0]) | + (9 + offsets[0]); + cfg_results[3] = (cfg_params[3] & 0xC0C0) | + FIELD_PREP(GENMASK(15, 8), 9 + offsets[0]) | + (14 + offsets[0]); + cfg_results[4] = (cfg_params[4] & 0xC0C0) | + FIELD_PREP(GENMASK(15, 8), 17 + offsets[0]) | + (22 + offsets[0]); + + return lan865x_write_cfg_params(phydev, cfg_results); +} + +static int lan865x_revb0_config_init(struct phy_device *phydev) +{ + int ret; + + /* Reference to AN1760 + * https://ww1.microchip.com/downloads/aemDocuments/documents/AIS/ProductDocuments/SupportingCollateral/AN-LAN8650-1-Configuration-60001760.pdf + */ + for (int i = 0; i < ARRAY_SIZE(lan865x_revb0_fixup_registers); i++) { + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, + lan865x_revb0_fixup_registers[i], + lan865x_revb0_fixup_values[i]); + if (ret) + return ret; + } + /* Function to calculate and write the configuration parameters in the + * 0x0084, 0x008A, 0x00AD, 0x00AE and 0x00AF registers (from AN1760) */ + return lan865x_setup_cfgparam(phydev); +} - int reg_value; +static int lan867x_revb1_config_init(struct phy_device *phydev) +{ int err; - int reg; - /* Read-Modified Write Pseudocode (from AN1699) - * current_val = read_register(mmd, addr) // Read current register value - * new_val = current_val AND (NOT mask) // Clear bit fields to be written - * new_val = new_val OR value // Set bits - * write_register(mmd, addr, new_val) // Write back updated register value + /* The chip completes a reset in 3us, we might get here earlier than + * that, as an added margin we'll conditionally sleep 5us. */ - for (int i = 0; i < ARRAY_SIZE(lan867x_fixup_registers); i++) { - reg = lan867x_fixup_registers[i]; - reg_value = phy_read_mmd(phydev, MDIO_MMD_VEND2, reg); - reg_value &= ~lan867x_fixup_masks[i]; - reg_value |= lan867x_fixup_values[i]; - err = phy_write_mmd(phydev, MDIO_MMD_VEND2, reg, reg_value); - if (err != 0) + err = phy_read_mmd(phydev, MDIO_MMD_VEND2, LAN867X_REG_STS2); + if (err < 0) + return err; + + if (!(err & LAN867x_RESET_COMPLETE_STS)) { + udelay(5); + err = phy_read_mmd(phydev, MDIO_MMD_VEND2, LAN867X_REG_STS2); + if (err < 0) return err; + if (!(err & LAN867x_RESET_COMPLETE_STS)) { + phydev_err(phydev, "PHY reset failed\n"); + return -ENODEV; + } } - /* None of the interrupts in the lan867x phy seem relevant. - * Other phys inspect the link status and call phy_trigger_machine - * in the interrupt handler. - * This phy does not support link status, and thus has no interrupt - * for it either. - * So we'll just disable all interrupts on the chip. + /* Reference to AN1699 + * https://ww1.microchip.com/downloads/aemDocuments/documents/AIS/ProductDocuments/SupportingCollateral/AN-LAN8670-1-2-config-60001699.pdf + * AN1699 says Read, Modify, Write, but the Write is not required if the + * register already has the required value. So it is safe to use + * phy_modify_mmd here. */ - err = phy_write_mmd(phydev, MDIO_MMD_VEND2, LAN867X_REG_IRQ_1_CTL, 0xFFFF); - if (err != 0) - return err; - return phy_write_mmd(phydev, MDIO_MMD_VEND2, LAN867X_REG_IRQ_2_CTL, 0xFFFF); + for (int i = 0; i < ARRAY_SIZE(lan867x_revb1_fixup_registers); i++) { + err = phy_modify_mmd(phydev, MDIO_MMD_VEND2, + lan867x_revb1_fixup_registers[i], + lan867x_revb1_fixup_masks[i], + lan867x_revb1_fixup_values[i]); + if (err) + return err; + } + + return 0; } -static int lan867x_read_status(struct phy_device *phydev) +static int lan86xx_read_status(struct phy_device *phydev) { /* The phy has some limitations, namely: * - always reports link up @@ -111,28 +268,39 @@ static int lan867x_read_status(struct phy_device *phydev) return 0; } -static struct phy_driver lan867x_driver[] = { +static struct phy_driver microchip_t1s_driver[] = { { - PHY_ID_MATCH_MODEL(PHY_ID_LAN867X), - .name = "LAN867X", + PHY_ID_MATCH_EXACT(PHY_ID_LAN867X_REVB1), + .name = "LAN867X Rev.B1", .features = PHY_BASIC_T1S_P2MP_FEATURES, - .config_init = lan867x_config_init, - .read_status = lan867x_read_status, + .config_init = lan867x_revb1_config_init, + .read_status = lan86xx_read_status, .get_plca_cfg = genphy_c45_plca_get_cfg, .set_plca_cfg = genphy_c45_plca_set_cfg, .get_plca_status = genphy_c45_plca_get_status, - } + }, + { + PHY_ID_MATCH_EXACT(PHY_ID_LAN865X_REVB0), + .name = "LAN865X Rev.B0 Internal Phy", + .features = PHY_BASIC_T1S_P2MP_FEATURES, + .config_init = lan865x_revb0_config_init, + .read_status = lan86xx_read_status, + .get_plca_cfg = genphy_c45_plca_get_cfg, + .set_plca_cfg = genphy_c45_plca_set_cfg, + .get_plca_status = genphy_c45_plca_get_status, + }, }; -module_phy_driver(lan867x_driver); +module_phy_driver(microchip_t1s_driver); static struct mdio_device_id __maybe_unused tbl[] = { - { PHY_ID_MATCH_MODEL(PHY_ID_LAN867X) }, + { PHY_ID_MATCH_EXACT(PHY_ID_LAN867X_REVB1) }, + { PHY_ID_MATCH_EXACT(PHY_ID_LAN865X_REVB0) }, { } }; MODULE_DEVICE_TABLE(mdio, tbl); -MODULE_DESCRIPTION("Microchip 10BASE-T1S lan867x Phy driver"); +MODULE_DESCRIPTION("Microchip 10BASE-T1S PHYs driver"); MODULE_AUTHOR("Ramón Nordin Rodriguez"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/phy/mscc/mscc.h b/drivers/net/phy/mscc/mscc.h index a50235fdf7d9..7a962050a4d4 100644 --- a/drivers/net/phy/mscc/mscc.h +++ b/drivers/net/phy/mscc/mscc.h @@ -179,6 +179,7 @@ enum rgmii_clock_delay { #define VSC8502_RGMII_CNTL 20 #define VSC8502_RGMII_RX_DELAY_MASK 0x0070 #define VSC8502_RGMII_TX_DELAY_MASK 0x0007 +#define VSC8502_RGMII_RX_CLK_DISABLE 0x0800 #define MSCC_PHY_WOL_LOWER_MAC_ADDR 21 #define MSCC_PHY_WOL_MID_MAC_ADDR 22 @@ -276,6 +277,7 @@ enum rgmii_clock_delay { /* Microsemi PHY ID's * Code assumes lowest nibble is 0 */ +#define PHY_ID_VSC8501 0x00070530 #define PHY_ID_VSC8502 0x00070630 #define PHY_ID_VSC8504 0x000704c0 #define PHY_ID_VSC8514 0x00070670 @@ -290,6 +292,7 @@ enum rgmii_clock_delay { #define PHY_ID_VSC8575 0x000707d0 #define PHY_ID_VSC8582 0x000707b0 #define PHY_ID_VSC8584 0x000707c0 +#define PHY_VENDOR_MSCC 0x00070400 #define MSCC_VDDMAC_1500 1500 #define MSCC_VDDMAC_1800 1800 diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c index 62bf99e45af1..669a4a7a28ce 100644 --- a/drivers/net/phy/mscc/mscc_main.c +++ b/drivers/net/phy/mscc/mscc_main.c @@ -107,6 +107,9 @@ static const struct vsc8531_edge_rate_table edge_table[] = { }; #endif +static const int vsc85xx_internal_delay[] = {200, 800, 1100, 1700, 2000, 2300, + 2600, 3400}; + static int vsc85xx_phy_read_page(struct phy_device *phydev) { return __phy_read(phydev, MSCC_EXT_PAGE_ACCESS); @@ -519,49 +522,69 @@ out_unlock: * * 2.0 ns (which causes the data to be sampled at exactly half way between * clock transitions at 1000 Mbps) if delays should be enabled */ -static int vsc85xx_rgmii_set_skews(struct phy_device *phydev, u32 rgmii_cntl, - u16 rgmii_rx_delay_mask, - u16 rgmii_tx_delay_mask) +static int vsc85xx_update_rgmii_cntl(struct phy_device *phydev, u32 rgmii_cntl, + u16 rgmii_rx_delay_mask, + u16 rgmii_tx_delay_mask) { u16 rgmii_rx_delay_pos = ffs(rgmii_rx_delay_mask) - 1; u16 rgmii_tx_delay_pos = ffs(rgmii_tx_delay_mask) - 1; + int delay_size = ARRAY_SIZE(vsc85xx_internal_delay); + struct device *dev = &phydev->mdio.dev; u16 reg_val = 0; - int rc; + u16 mask = 0; + s32 rx_delay; + s32 tx_delay; + int rc = 0; - mutex_lock(&phydev->lock); + /* For traffic to pass, the VSC8502 family needs the RX_CLK disable bit + * to be unset for all PHY modes, so do that as part of the paged + * register modification. + * For some family members (like VSC8530/31/40/41) this bit is reserved + * and read-only, and the RX clock is enabled by default. + */ + if (rgmii_cntl == VSC8502_RGMII_CNTL) + mask |= VSC8502_RGMII_RX_CLK_DISABLE; + + if (phy_interface_is_rgmii(phydev)) + mask |= rgmii_rx_delay_mask | rgmii_tx_delay_mask; + + rx_delay = phy_get_internal_delay(phydev, dev, vsc85xx_internal_delay, + delay_size, true); + if (rx_delay < 0) { + if (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID || + phydev->interface == PHY_INTERFACE_MODE_RGMII_ID) + rx_delay = RGMII_CLK_DELAY_2_0_NS; + else + rx_delay = RGMII_CLK_DELAY_0_2_NS; + } - if (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID || - phydev->interface == PHY_INTERFACE_MODE_RGMII_ID) - reg_val |= RGMII_CLK_DELAY_2_0_NS << rgmii_rx_delay_pos; - if (phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID || - phydev->interface == PHY_INTERFACE_MODE_RGMII_ID) - reg_val |= RGMII_CLK_DELAY_2_0_NS << rgmii_tx_delay_pos; + tx_delay = phy_get_internal_delay(phydev, dev, vsc85xx_internal_delay, + delay_size, false); + if (tx_delay < 0) { + if (phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID || + phydev->interface == PHY_INTERFACE_MODE_RGMII_ID) + rx_delay = RGMII_CLK_DELAY_2_0_NS; + else + rx_delay = RGMII_CLK_DELAY_0_2_NS; + } - rc = phy_modify_paged(phydev, MSCC_PHY_PAGE_EXTENDED_2, - rgmii_cntl, - rgmii_rx_delay_mask | rgmii_tx_delay_mask, - reg_val); + reg_val |= rx_delay << rgmii_rx_delay_pos; + reg_val |= tx_delay << rgmii_tx_delay_pos; - mutex_unlock(&phydev->lock); + if (mask) + rc = phy_modify_paged(phydev, MSCC_PHY_PAGE_EXTENDED_2, + rgmii_cntl, mask, reg_val); return rc; } static int vsc85xx_default_config(struct phy_device *phydev) { - int rc; - phydev->mdix_ctrl = ETH_TP_MDI_AUTO; - if (phy_interface_mode_is_rgmii(phydev->interface)) { - rc = vsc85xx_rgmii_set_skews(phydev, VSC8502_RGMII_CNTL, - VSC8502_RGMII_RX_DELAY_MASK, - VSC8502_RGMII_TX_DELAY_MASK); - if (rc) - return rc; - } - - return 0; + return vsc85xx_update_rgmii_cntl(phydev, VSC8502_RGMII_CNTL, + VSC8502_RGMII_RX_DELAY_MASK, + VSC8502_RGMII_TX_DELAY_MASK); } static int vsc85xx_get_tunable(struct phy_device *phydev, @@ -1758,13 +1781,11 @@ static int vsc8584_config_init(struct phy_device *phydev) if (ret) return ret; - if (phy_interface_is_rgmii(phydev)) { - ret = vsc85xx_rgmii_set_skews(phydev, VSC8572_RGMII_CNTL, - VSC8572_RGMII_RX_DELAY_MASK, - VSC8572_RGMII_TX_DELAY_MASK); - if (ret) - return ret; - } + ret = vsc85xx_update_rgmii_cntl(phydev, VSC8572_RGMII_CNTL, + VSC8572_RGMII_RX_DELAY_MASK, + VSC8572_RGMII_TX_DELAY_MASK); + if (ret) + return ret; ret = genphy_soft_reset(phydev); if (ret) @@ -2317,6 +2338,30 @@ static int vsc85xx_probe(struct phy_device *phydev) /* Microsemi VSC85xx PHYs */ static struct phy_driver vsc85xx_driver[] = { { + .phy_id = PHY_ID_VSC8501, + .name = "Microsemi GE VSC8501 SyncE", + .phy_id_mask = 0xfffffff0, + /* PHY_BASIC_FEATURES */ + .soft_reset = &genphy_soft_reset, + .config_init = &vsc85xx_config_init, + .config_aneg = &vsc85xx_config_aneg, + .read_status = &vsc85xx_read_status, + .handle_interrupt = vsc85xx_handle_interrupt, + .config_intr = &vsc85xx_config_intr, + .suspend = &genphy_suspend, + .resume = &genphy_resume, + .probe = &vsc85xx_probe, + .set_wol = &vsc85xx_wol_set, + .get_wol = &vsc85xx_wol_get, + .get_tunable = &vsc85xx_get_tunable, + .set_tunable = &vsc85xx_set_tunable, + .read_page = &vsc85xx_phy_read_page, + .write_page = &vsc85xx_phy_write_page, + .get_sset_count = &vsc85xx_get_sset_count, + .get_strings = &vsc85xx_get_strings, + .get_stats = &vsc85xx_get_stats, +}, +{ .phy_id = PHY_ID_VSC8502, .name = "Microsemi GE VSC8502 SyncE", .phy_id_mask = 0xfffffff0, @@ -2656,19 +2701,7 @@ static struct phy_driver vsc85xx_driver[] = { module_phy_driver(vsc85xx_driver); static struct mdio_device_id __maybe_unused vsc85xx_tbl[] = { - { PHY_ID_VSC8504, 0xfffffff0, }, - { PHY_ID_VSC8514, 0xfffffff0, }, - { PHY_ID_VSC8530, 0xfffffff0, }, - { PHY_ID_VSC8531, 0xfffffff0, }, - { PHY_ID_VSC8540, 0xfffffff0, }, - { PHY_ID_VSC8541, 0xfffffff0, }, - { PHY_ID_VSC8552, 0xfffffff0, }, - { PHY_ID_VSC856X, 0xfffffff0, }, - { PHY_ID_VSC8572, 0xfffffff0, }, - { PHY_ID_VSC8574, 0xfffffff0, }, - { PHY_ID_VSC8575, 0xfffffff0, }, - { PHY_ID_VSC8582, 0xfffffff0, }, - { PHY_ID_VSC8584, 0xfffffff0, }, + { PHY_ID_MATCH_VENDOR(PHY_VENDOR_MSCC) }, { } }; diff --git a/drivers/net/phy/mxl-gpy.c b/drivers/net/phy/mxl-gpy.c index 6301a9abfb95..ea1073adc5a1 100644 --- a/drivers/net/phy/mxl-gpy.c +++ b/drivers/net/phy/mxl-gpy.c @@ -274,13 +274,6 @@ static int gpy_config_init(struct phy_device *phydev) return ret < 0 ? ret : 0; } -static bool gpy_has_broken_mdint(struct phy_device *phydev) -{ - /* At least these PHYs are known to have broken interrupt handling */ - return phydev->drv->phy_id == PHY_ID_GPY215B || - phydev->drv->phy_id == PHY_ID_GPY215C; -} - static int gpy_probe(struct phy_device *phydev) { struct device *dev = &phydev->mdio.dev; @@ -300,8 +293,7 @@ static int gpy_probe(struct phy_device *phydev) phydev->priv = priv; mutex_init(&priv->mbox_lock); - if (gpy_has_broken_mdint(phydev) && - !device_property_present(dev, "maxlinear,use-broken-interrupts")) + if (!device_property_present(dev, "maxlinear,use-broken-interrupts")) phydev->dev_flags |= PHY_F_NO_IRQ; fw_version = phy_read(phydev, PHY_FWV); @@ -659,11 +651,9 @@ static irqreturn_t gpy_handle_interrupt(struct phy_device *phydev) * frame. Therefore, polling is the best we can do and won't do any more * harm. * It was observed that this bug happens on link state and link speed - * changes on a GPY215B and GYP215C independent of the firmware version - * (which doesn't mean that this list is exhaustive). + * changes independent of the firmware version. */ - if (gpy_has_broken_mdint(phydev) && - (reg & (PHY_IMASK_LSTC | PHY_IMASK_LSPC))) { + if (reg & (PHY_IMASK_LSTC | PHY_IMASK_LSPC)) { reg = gpy_mbox_read(phydev, REG_GPIO0_OUT); if (reg < 0) { phy_error(phydev); diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 0c0df38cd1ab..bdf00b2b2c1d 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -52,6 +52,7 @@ static const char *phy_state_to_str(enum phy_state st) PHY_STATE_STR(NOLINK) PHY_STATE_STR(CABLETEST) PHY_STATE_STR(HALTED) + PHY_STATE_STR(ERROR) } return NULL; @@ -1184,7 +1185,7 @@ void phy_stop_machine(struct phy_device *phydev) static void phy_process_error(struct phy_device *phydev) { mutex_lock(&phydev->lock); - phydev->state = PHY_HALTED; + phydev->state = PHY_ERROR; mutex_unlock(&phydev->lock); phy_trigger_machine(phydev); @@ -1198,10 +1199,10 @@ static void phy_error_precise(struct phy_device *phydev, } /** - * phy_error - enter HALTED state for this PHY device + * phy_error - enter ERROR state for this PHY device * @phydev: target phy_device struct * - * Moves the PHY to the HALTED state in response to a read + * Moves the PHY to the ERROR state in response to a read * or write error, and tells the controller the link is down. * Must not be called from interrupt context, or while the * phydev->lock is held. @@ -1326,7 +1327,8 @@ void phy_stop(struct phy_device *phydev) struct net_device *dev = phydev->attached_dev; enum phy_state old_state; - if (!phy_is_started(phydev) && phydev->state != PHY_DOWN) { + if (!phy_is_started(phydev) && phydev->state != PHY_DOWN && + phydev->state != PHY_ERROR) { WARN(1, "called from state %s\n", phy_state_to_str(phydev->state)); return; @@ -1443,6 +1445,7 @@ void phy_state_machine(struct work_struct *work) } break; case PHY_HALTED: + case PHY_ERROR: if (phydev->link) { phydev->link = 0; phy_link_down(phydev); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 8852b0c53114..2cad9cc3f6b8 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -454,8 +454,7 @@ int phy_unregister_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask) fixup = list_entry(pos, struct phy_fixup, list); if ((!strcmp(fixup->bus_id, bus_id)) && - ((fixup->phy_uid & phy_uid_mask) == - (phy_uid & phy_uid_mask))) { + phy_id_compare(fixup->phy_uid, phy_uid, phy_uid_mask)) { list_del(&fixup->list); kfree(fixup); ret = 0; @@ -491,8 +490,8 @@ static int phy_needs_fixup(struct phy_device *phydev, struct phy_fixup *fixup) if (strcmp(fixup->bus_id, PHY_ANY_ID) != 0) return 0; - if ((fixup->phy_uid & fixup->phy_uid_mask) != - (phydev->phy_id & fixup->phy_uid_mask)) + if (!phy_id_compare(phydev->phy_id, fixup->phy_uid, + fixup->phy_uid_mask)) if (fixup->phy_uid != PHY_ANY_UID) return 0; @@ -539,15 +538,14 @@ static int phy_bus_match(struct device *dev, struct device_driver *drv) if (phydev->c45_ids.device_ids[i] == 0xffffffff) continue; - if ((phydrv->phy_id & phydrv->phy_id_mask) == - (phydev->c45_ids.device_ids[i] & - phydrv->phy_id_mask)) + if (phy_id_compare(phydev->c45_ids.device_ids[i], + phydrv->phy_id, phydrv->phy_id_mask)) return 1; } return 0; } else { - return (phydrv->phy_id & phydrv->phy_id_mask) == - (phydev->phy_id & phydrv->phy_id_mask); + return phy_id_compare(phydev->phy_id, phydrv->phy_id, + phydrv->phy_id_mask); } } diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index cf53096047e6..1ae7868d2137 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -156,6 +156,23 @@ static const char *phylink_an_mode_str(unsigned int mode) return mode < ARRAY_SIZE(modestr) ? modestr[mode] : "unknown"; } +static unsigned int phylink_interface_signal_rate(phy_interface_t interface) +{ + switch (interface) { + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_1000BASEX: /* 1.25Mbd */ + return 1250; + case PHY_INTERFACE_MODE_2500BASEX: /* 3.125Mbd */ + return 3125; + case PHY_INTERFACE_MODE_5GBASER: /* 5.15625Mbd */ + return 5156; + case PHY_INTERFACE_MODE_10GBASER: /* 10.3125Mbd */ + return 10313; + default: + return 0; + } +} + /** * phylink_interface_max_speed() - get the maximum speed of a phy interface * @interface: phy interface mode defined by &typedef phy_interface_t @@ -695,14 +712,11 @@ static int phylink_validate(struct phylink *pl, unsigned long *supported, { const unsigned long *interfaces = pl->config->supported_interfaces; - if (!phy_interface_empty(interfaces)) { - if (state->interface == PHY_INTERFACE_MODE_NA) - return phylink_validate_mask(pl, supported, state, - interfaces); + if (state->interface == PHY_INTERFACE_MODE_NA) + return phylink_validate_mask(pl, supported, state, interfaces); - if (!test_bit(state->interface, interfaces)) - return -EINVAL; - } + if (!test_bit(state->interface, interfaces)) + return -EINVAL; return phylink_validate_mac_and_pcs(pl, supported, state); } @@ -963,11 +977,10 @@ static void phylink_apply_manual_flow(struct phylink *pl, state->pause = pl->link_config.pause; } -static void phylink_resolve_flow(struct phylink_link_state *state) +static void phylink_resolve_an_pause(struct phylink_link_state *state) { bool tx_pause, rx_pause; - state->pause = MLO_PAUSE_NONE; if (state->duplex == DUPLEX_FULL) { linkmode_resolve_pause(state->advertising, state->lp_advertising, @@ -979,6 +992,25 @@ static void phylink_resolve_flow(struct phylink_link_state *state) } } +static int phylink_pcs_config(struct phylink_pcs *pcs, unsigned int mode, + const struct phylink_link_state *state, + bool permit_pause_to_mac) +{ + if (!pcs) + return 0; + + return pcs->ops->pcs_config(pcs, mode, state->interface, + state->advertising, permit_pause_to_mac); +} + +static void phylink_pcs_link_up(struct phylink_pcs *pcs, unsigned int mode, + phy_interface_t interface, int speed, + int duplex) +{ + if (pcs && pcs->ops->pcs_link_up) + pcs->ops->pcs_link_up(pcs, mode, interface, speed, duplex); +} + static void phylink_pcs_poll_stop(struct phylink *pl) { if (pl->cfg_link_an_mode == MLO_AN_INBAND) @@ -1025,6 +1057,7 @@ static void phylink_major_config(struct phylink *pl, bool restart, { struct phylink_pcs *pcs = NULL; bool pcs_changed = false; + unsigned int rate_kbd; int err; phylink_dbg(pl, "major config %s\n", phy_modes(state->interface)); @@ -1061,18 +1094,15 @@ static void phylink_major_config(struct phylink *pl, bool restart, phylink_mac_config(pl, state); - if (pl->pcs) { - err = pl->pcs->ops->pcs_config(pl->pcs, pl->cur_link_an_mode, - state->interface, - state->advertising, - !!(pl->link_config.pause & - MLO_PAUSE_AN)); - if (err < 0) - phylink_err(pl, "pcs_config failed: %pe\n", - ERR_PTR(err)); - if (err > 0) - restart = true; - } + err = phylink_pcs_config(pl->pcs, pl->cur_link_an_mode, state, + !!(pl->link_config.pause & + MLO_PAUSE_AN)); + if (err < 0) + phylink_err(pl, "pcs_config failed: %pe\n", + ERR_PTR(err)); + else if (err > 0) + restart = true; + if (restart) phylink_mac_pcs_an_restart(pl); @@ -1084,6 +1114,12 @@ static void phylink_major_config(struct phylink *pl, bool restart, ERR_PTR(err)); } + if (pl->sfp_bus) { + rate_kbd = phylink_interface_signal_rate(state->interface); + if (rate_kbd) + sfp_upstream_set_signal_rate(pl->sfp_bus, rate_kbd); + } + phylink_pcs_poll_start(pl); } @@ -1117,11 +1153,9 @@ static int phylink_change_inband_advert(struct phylink *pl) * restart negotiation if the pcs_config() helper indicates that * the programmed advertisement has changed. */ - ret = pl->pcs->ops->pcs_config(pl->pcs, pl->cur_link_an_mode, - pl->link_config.interface, - pl->link_config.advertising, - !!(pl->link_config.pause & - MLO_PAUSE_AN)); + ret = phylink_pcs_config(pl->pcs, pl->cur_link_an_mode, + &pl->link_config, + !!(pl->link_config.pause & MLO_PAUSE_AN)); if (ret < 0) return ret; @@ -1172,7 +1206,8 @@ static void phylink_get_fixed_state(struct phylink *pl, else if (pl->link_gpio) state->link = !!gpiod_get_value_cansleep(pl->link_gpio); - phylink_resolve_flow(state); + state->pause = MLO_PAUSE_NONE; + phylink_resolve_an_pause(state); } static void phylink_mac_initial_config(struct phylink *pl, bool force_restart) @@ -1252,9 +1287,8 @@ static void phylink_link_up(struct phylink *pl, pl->cur_interface = link_state.interface; - if (pl->pcs && pl->pcs->ops->pcs_link_up) - pl->pcs->ops->pcs_link_up(pl->pcs, pl->cur_link_an_mode, - pl->cur_interface, speed, duplex); + phylink_pcs_link_up(pl->pcs, pl->cur_link_an_mode, pl->cur_interface, + speed, duplex); pl->mac_ops->mac_link_up(pl->config, pl->phydev, pl->cur_link_an_mode, pl->cur_interface, speed, duplex, @@ -1489,19 +1523,18 @@ struct phylink *phylink_create(struct phylink_config *config, struct phylink *pl; int ret; - if (mac_ops->mac_select_pcs && - mac_ops->mac_select_pcs(config, PHY_INTERFACE_MODE_NA) != - ERR_PTR(-EOPNOTSUPP)) - using_mac_select_pcs = true; - /* Validate the supplied configuration */ - if (using_mac_select_pcs && - phy_interface_empty(config->supported_interfaces)) { + if (phy_interface_empty(config->supported_interfaces)) { dev_err(config->dev, - "phylink: error: empty supported_interfaces but mac_select_pcs() method present\n"); + "phylink: error: empty supported_interfaces\n"); return ERR_PTR(-EINVAL); } + if (mac_ops->mac_select_pcs && + mac_ops->mac_select_pcs(config, PHY_INTERFACE_MODE_NA) != + ERR_PTR(-EOPNOTSUPP)) + using_mac_select_pcs = true; + pl = kzalloc(sizeof(*pl), GFP_KERNEL); if (!pl) return ERR_PTR(-ENOMEM); @@ -2227,6 +2260,12 @@ int phylink_ethtool_ksettings_set(struct phylink *pl, ASSERT_RTNL(); if (pl->phydev) { + struct ethtool_link_ksettings phy_kset = *kset; + + linkmode_and(phy_kset.link_modes.advertising, + phy_kset.link_modes.advertising, + pl->supported); + /* We can rely on phylib for this update; we also do not need * to update the pl->link_config settings: * - the configuration returned via ksettings_get() will come @@ -2245,11 +2284,10 @@ int phylink_ethtool_ksettings_set(struct phylink *pl, * the presence of a PHY, this should not be changed as that * should be determined from the media side advertisement. */ - return phy_ethtool_ksettings_set(pl->phydev, kset); + return phy_ethtool_ksettings_set(pl->phydev, &phy_kset); } config = pl->link_config; - /* Mask out unsupported advertisements */ linkmode_and(config.advertising, kset->link_modes.advertising, pl->supported); @@ -3127,8 +3165,8 @@ static void phylink_sfp_link_up(void *upstream) */ static bool phylink_phy_no_inband(struct phy_device *phy) { - return phy->is_c45 && - (phy->c45_ids.device_ids[1] & 0xfffffff0) == 0xae025150; + return phy->is_c45 && phy_id_compare(phy->c45_ids.device_ids[1], + 0xae025150, 0xfffffff0); } static int phylink_sfp_connect_phy(void *upstream, struct phy_device *phy) @@ -3192,10 +3230,48 @@ static const struct sfp_upstream_ops sfp_phylink_ops = { /* Helpers for MAC drivers */ +static struct { + int bit; + int speed; +} phylink_c73_priority_resolution[] = { + { ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, SPEED_100000 }, + { ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, SPEED_100000 }, + /* 100GBASE-KP4 and 100GBASE-CR10 not supported */ + { ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT, SPEED_40000 }, + { ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT, SPEED_40000 }, + { ETHTOOL_LINK_MODE_10000baseKR_Full_BIT, SPEED_10000 }, + { ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, SPEED_10000 }, + /* 5GBASE-KR not supported */ + { ETHTOOL_LINK_MODE_2500baseX_Full_BIT, SPEED_2500 }, + { ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, SPEED_1000 }, +}; + +void phylink_resolve_c73(struct phylink_link_state *state) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(phylink_c73_priority_resolution); i++) { + int bit = phylink_c73_priority_resolution[i].bit; + if (linkmode_test_bit(bit, state->advertising) && + linkmode_test_bit(bit, state->lp_advertising)) + break; + } + + if (i < ARRAY_SIZE(phylink_c73_priority_resolution)) { + state->speed = phylink_c73_priority_resolution[i].speed; + state->duplex = DUPLEX_FULL; + } else { + /* negotiation failure */ + state->link = false; + } + + phylink_resolve_an_pause(state); +} +EXPORT_SYMBOL_GPL(phylink_resolve_c73); + static void phylink_decode_c37_word(struct phylink_link_state *state, uint16_t config_reg, int speed) { - bool tx_pause, rx_pause; int fd_bit; if (speed == SPEED_2500) @@ -3214,13 +3290,7 @@ static void phylink_decode_c37_word(struct phylink_link_state *state, state->link = false; } - linkmode_resolve_pause(state->advertising, state->lp_advertising, - &tx_pause, &rx_pause); - - if (tx_pause) - state->pause |= MLO_PAUSE_TX; - if (rx_pause) - state->pause |= MLO_PAUSE_RX; + phylink_resolve_an_pause(state); } static void phylink_decode_sgmii_word(struct phylink_link_state *state, diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index 3d99fd6664d7..894172a3e15f 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -12,6 +12,7 @@ #include <linux/phy.h> #include <linux/module.h> #include <linux/delay.h> +#include <linux/clk.h> #define RTL821x_PHYSR 0x11 #define RTL821x_PHYSR_DUPLEX BIT(13) @@ -80,6 +81,7 @@ struct rtl821x_priv { u16 phycr1; u16 phycr2; bool has_phycr2; + struct clk *clk; }; static int rtl821x_read_page(struct phy_device *phydev) @@ -103,6 +105,11 @@ static int rtl821x_probe(struct phy_device *phydev) if (!priv) return -ENOMEM; + priv->clk = devm_clk_get_optional_enabled(dev, NULL); + if (IS_ERR(priv->clk)) + return dev_err_probe(dev, PTR_ERR(priv->clk), + "failed to get phy clock\n"); + ret = phy_read_paged(phydev, 0xa43, RTL8211F_PHYCR1); if (ret < 0) return ret; @@ -419,10 +426,31 @@ static int rtl8211f_config_init(struct phy_device *phydev) return genphy_soft_reset(phydev); } +static int rtl821x_suspend(struct phy_device *phydev) +{ + struct rtl821x_priv *priv = phydev->priv; + int ret = 0; + + if (!phydev->wol_enabled) { + ret = genphy_suspend(phydev); + + if (ret) + return ret; + + clk_disable_unprepare(priv->clk); + } + + return ret; +} + static int rtl821x_resume(struct phy_device *phydev) { + struct rtl821x_priv *priv = phydev->priv; int ret; + if (!phydev->wol_enabled) + clk_prepare_enable(priv->clk); + ret = genphy_resume(phydev); if (ret < 0) return ret; @@ -927,10 +955,11 @@ static struct phy_driver realtek_drvs[] = { .read_status = rtlgen_read_status, .config_intr = &rtl8211f_config_intr, .handle_interrupt = rtl8211f_handle_interrupt, - .suspend = genphy_suspend, + .suspend = rtl821x_suspend, .resume = rtl821x_resume, .read_page = rtl821x_read_page, .write_page = rtl821x_write_page, + .flags = PHY_ALWAYS_CALL_SUSPEND, }, { PHY_ID_MATCH_EXACT(RTL_8211FVD_PHYID), .name = "RTL8211F-VD Gigabit Ethernet", @@ -939,10 +968,11 @@ static struct phy_driver realtek_drvs[] = { .read_status = rtlgen_read_status, .config_intr = &rtl8211f_config_intr, .handle_interrupt = rtl8211f_handle_interrupt, - .suspend = genphy_suspend, + .suspend = rtl821x_suspend, .resume = rtl821x_resume, .read_page = rtl821x_read_page, .write_page = rtl821x_write_page, + .flags = PHY_ALWAYS_CALL_SUSPEND, }, { .name = "Generic FE-GE Realtek PHY", .match_phy_device = rtlgen_match_phy_device, diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index 9372e5a4cadc..e8dd47bffe43 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -576,6 +576,26 @@ static void sfp_upstream_clear(struct sfp_bus *bus) } /** + * sfp_upstream_set_signal_rate() - set data signalling rate + * @bus: a pointer to the &struct sfp_bus structure for the sfp module + * @rate_kbd: signalling rate in units of 1000 baud + * + * Configure the rate select settings on the SFP module for the signalling + * rate (not the same as the data rate). + * + * Locks that may be held: + * Phylink's state_mutex + * rtnl lock + * SFP's sm_mutex + */ +void sfp_upstream_set_signal_rate(struct sfp_bus *bus, unsigned int rate_kbd) +{ + if (bus->registered) + bus->socket_ops->set_signal_rate(bus->sfp, rate_kbd); +} +EXPORT_SYMBOL_GPL(sfp_upstream_set_signal_rate); + +/** * sfp_bus_find_fwnode() - parse and locate the SFP bus from fwnode * @fwnode: firmware node for the parent device (MAC or PHY) * diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 89636dc71e48..d855a18308d7 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -24,14 +24,18 @@ enum { GPIO_LOS, GPIO_TX_FAULT, GPIO_TX_DISABLE, - GPIO_RATE_SELECT, + GPIO_RS0, + GPIO_RS1, GPIO_MAX, SFP_F_PRESENT = BIT(GPIO_MODDEF0), SFP_F_LOS = BIT(GPIO_LOS), SFP_F_TX_FAULT = BIT(GPIO_TX_FAULT), SFP_F_TX_DISABLE = BIT(GPIO_TX_DISABLE), - SFP_F_RATE_SELECT = BIT(GPIO_RATE_SELECT), + SFP_F_RS0 = BIT(GPIO_RS0), + SFP_F_RS1 = BIT(GPIO_RS1), + + SFP_F_OUTPUTS = SFP_F_TX_DISABLE | SFP_F_RS0 | SFP_F_RS1, SFP_E_INSERT = 0, SFP_E_REMOVE, @@ -148,6 +152,7 @@ static const char *gpio_names[] = { "tx-fault", "tx-disable", "rate-select0", + "rate-select1", }; static const enum gpiod_flags gpio_flags[] = { @@ -156,6 +161,7 @@ static const enum gpiod_flags gpio_flags[] = { GPIOD_IN, GPIOD_ASIS, GPIOD_ASIS, + GPIOD_ASIS, }; /* t_start_up (SFF-8431) or t_init (SFF-8472) is the time required for a @@ -164,7 +170,6 @@ static const enum gpiod_flags gpio_flags[] = { * on board (for a copper SFP) time to initialise. */ #define T_WAIT msecs_to_jiffies(50) -#define T_WAIT_ROLLBALL msecs_to_jiffies(25000) #define T_START_UP msecs_to_jiffies(300) #define T_START_UP_BAD_GPON msecs_to_jiffies(60000) @@ -242,10 +247,18 @@ struct sfp { bool need_poll; + /* Access rules: + * state_hw_drive: st_mutex held + * state_hw_mask: st_mutex held + * state_soft_mask: st_mutex held + * state: st_mutex held unless reading input bits + */ struct mutex st_mutex; /* Protects state */ + unsigned int state_hw_drive; unsigned int state_hw_mask; unsigned int state_soft_mask; unsigned int state; + struct delayed_work poll; struct delayed_work timeout; struct mutex sm_mutex; /* Protects state machine */ @@ -262,6 +275,10 @@ struct sfp { unsigned int module_t_start_up; unsigned int module_t_wait; + unsigned int rate_kbd; + unsigned int rs_threshold_kbd; + unsigned int rs_state_mask; + bool have_a2; bool tx_fault_ignore; @@ -312,7 +329,7 @@ static bool sfp_module_supported(const struct sfp_eeprom_id *id) static const struct sff_data sfp_data = { .gpios = SFP_F_PRESENT | SFP_F_LOS | SFP_F_TX_FAULT | - SFP_F_TX_DISABLE | SFP_F_RATE_SELECT, + SFP_F_TX_DISABLE | SFP_F_RS0 | SFP_F_RS1, .module_supported = sfp_module_supported, }; @@ -333,6 +350,27 @@ static void sfp_fixup_ignore_tx_fault(struct sfp *sfp) sfp->tx_fault_ignore = true; } +// For 10GBASE-T short-reach modules +static void sfp_fixup_10gbaset_30m(struct sfp *sfp) +{ + sfp->id.base.connector = SFF8024_CONNECTOR_RJ45; + sfp->id.base.extended_cc = SFF8024_ECC_10GBASE_T_SR; +} + +static void sfp_fixup_rollball_proto(struct sfp *sfp, unsigned int secs) +{ + sfp->mdio_protocol = MDIO_I2C_ROLLBALL; + sfp->module_t_wait = msecs_to_jiffies(secs * 1000); +} + +static void sfp_fixup_fs_10gt(struct sfp *sfp) +{ + sfp_fixup_10gbaset_30m(sfp); + + // These SFPs need 4 seconds before the PHY can be accessed + sfp_fixup_rollball_proto(sfp, 4); +} + static void sfp_fixup_halny_gsfp(struct sfp *sfp) { /* Ignore the TX_FAULT and LOS signals on this module. @@ -344,8 +382,8 @@ static void sfp_fixup_halny_gsfp(struct sfp *sfp) static void sfp_fixup_rollball(struct sfp *sfp) { - sfp->mdio_protocol = MDIO_I2C_ROLLBALL; - sfp->module_t_wait = T_WAIT_ROLLBALL; + // Rollball SFPs need 25 seconds before the PHY can be accessed + sfp_fixup_rollball_proto(sfp, 25); } static void sfp_fixup_rollball_cc(struct sfp *sfp) @@ -410,6 +448,10 @@ static const struct sfp_quirk sfp_quirks[] = { SFP_QUIRK("ALCATELLUCENT", "3FE46541AA", sfp_quirk_2500basex, sfp_fixup_long_startup), + // Fiberstore SFP-10G-T doesn't identify as copper, and uses the + // Rollball protocol to talk to the PHY. + SFP_QUIRK_F("FS", "SFP-10G-T", sfp_fixup_fs_10gt), + SFP_QUIRK_F("HALNy", "HL-GSFP", sfp_fixup_halny_gsfp), // HG MXPD-483II-F 2.5G supports 2500Base-X, but incorrectly reports @@ -427,6 +469,11 @@ static const struct sfp_quirk sfp_quirks[] = { SFP_QUIRK_M("UBNT", "UF-INSTANT", sfp_quirk_ubnt_uf_instant), + // Walsun HXSX-ATR[CI]-1 don't identify as copper, and use the + // Rollball protocol to talk to the PHY. + SFP_QUIRK_F("Walsun", "HXSX-ATRC-1", sfp_fixup_fs_10gt), + SFP_QUIRK_F("Walsun", "HXSX-ATRI-1", sfp_fixup_fs_10gt), + SFP_QUIRK_F("OEM", "SFP-10G-T", sfp_fixup_rollball_cc), SFP_QUIRK_M("OEM", "SFP-2.5G-T", sfp_quirk_oem_2_5g), SFP_QUIRK_F("OEM", "RTSFP-10", sfp_fixup_rollball_cc), @@ -500,20 +547,37 @@ static unsigned int sff_gpio_get_state(struct sfp *sfp) static void sfp_gpio_set_state(struct sfp *sfp, unsigned int state) { - if (state & SFP_F_PRESENT) { - /* If the module is present, drive the signals */ - if (sfp->gpio[GPIO_TX_DISABLE]) + unsigned int drive; + + if (state & SFP_F_PRESENT) + /* If the module is present, drive the requested signals */ + drive = sfp->state_hw_drive; + else + /* Otherwise, let them float to the pull-ups */ + drive = 0; + + if (sfp->gpio[GPIO_TX_DISABLE]) { + if (drive & SFP_F_TX_DISABLE) gpiod_direction_output(sfp->gpio[GPIO_TX_DISABLE], state & SFP_F_TX_DISABLE); - if (state & SFP_F_RATE_SELECT) - gpiod_direction_output(sfp->gpio[GPIO_RATE_SELECT], - state & SFP_F_RATE_SELECT); - } else { - /* Otherwise, let them float to the pull-ups */ - if (sfp->gpio[GPIO_TX_DISABLE]) + else gpiod_direction_input(sfp->gpio[GPIO_TX_DISABLE]); - if (state & SFP_F_RATE_SELECT) - gpiod_direction_input(sfp->gpio[GPIO_RATE_SELECT]); + } + + if (sfp->gpio[GPIO_RS0]) { + if (drive & SFP_F_RS0) + gpiod_direction_output(sfp->gpio[GPIO_RS0], + state & SFP_F_RS0); + else + gpiod_direction_input(sfp->gpio[GPIO_RS0]); + } + + if (sfp->gpio[GPIO_RS1]) { + if (drive & SFP_F_RS1) + gpiod_direction_output(sfp->gpio[GPIO_RS1], + state & SFP_F_RS1); + else + gpiod_direction_input(sfp->gpio[GPIO_RS1]); } } @@ -675,16 +739,33 @@ static unsigned int sfp_soft_get_state(struct sfp *sfp) return state & sfp->state_soft_mask; } -static void sfp_soft_set_state(struct sfp *sfp, unsigned int state) +static void sfp_soft_set_state(struct sfp *sfp, unsigned int state, + unsigned int soft) { - u8 mask = SFP_STATUS_TX_DISABLE_FORCE; + u8 mask = 0; u8 val = 0; + if (soft & SFP_F_TX_DISABLE) + mask |= SFP_STATUS_TX_DISABLE_FORCE; if (state & SFP_F_TX_DISABLE) val |= SFP_STATUS_TX_DISABLE_FORCE; + if (soft & SFP_F_RS0) + mask |= SFP_STATUS_RS0_SELECT; + if (state & SFP_F_RS0) + val |= SFP_STATUS_RS0_SELECT; + + if (mask) + sfp_modify_u8(sfp, true, SFP_STATUS, mask, val); - sfp_modify_u8(sfp, true, SFP_STATUS, mask, val); + val = mask = 0; + if (soft & SFP_F_RS1) + mask |= SFP_EXT_STATUS_RS1_SELECT; + if (state & SFP_F_RS1) + val |= SFP_EXT_STATUS_RS1_SELECT; + + if (mask) + sfp_modify_u8(sfp, true, SFP_EXT_STATUS, mask, val); } static void sfp_soft_start_poll(struct sfp *sfp) @@ -692,27 +773,35 @@ static void sfp_soft_start_poll(struct sfp *sfp) const struct sfp_eeprom_id *id = &sfp->id; unsigned int mask = 0; - sfp->state_soft_mask = 0; if (id->ext.enhopts & SFP_ENHOPTS_SOFT_TX_DISABLE) mask |= SFP_F_TX_DISABLE; if (id->ext.enhopts & SFP_ENHOPTS_SOFT_TX_FAULT) mask |= SFP_F_TX_FAULT; if (id->ext.enhopts & SFP_ENHOPTS_SOFT_RX_LOS) mask |= SFP_F_LOS; + if (id->ext.enhopts & SFP_ENHOPTS_SOFT_RATE_SELECT) + mask |= sfp->rs_state_mask; + mutex_lock(&sfp->st_mutex); // Poll the soft state for hardware pins we want to ignore sfp->state_soft_mask = ~sfp->state_hw_mask & mask; if (sfp->state_soft_mask & (SFP_F_LOS | SFP_F_TX_FAULT) && !sfp->need_poll) mod_delayed_work(system_wq, &sfp->poll, poll_jiffies); + mutex_unlock(&sfp->st_mutex); } static void sfp_soft_stop_poll(struct sfp *sfp) { + mutex_lock(&sfp->st_mutex); sfp->state_soft_mask = 0; + mutex_unlock(&sfp->st_mutex); } +/* sfp_get_state() - must be called with st_mutex held, or in the + * initialisation path. + */ static unsigned int sfp_get_state(struct sfp *sfp) { unsigned int soft = sfp->state_soft_mask & (SFP_F_LOS | SFP_F_TX_FAULT); @@ -725,13 +814,26 @@ static unsigned int sfp_get_state(struct sfp *sfp) return state; } +/* sfp_set_state() - must be called with st_mutex held, or in the + * initialisation path. + */ static void sfp_set_state(struct sfp *sfp, unsigned int state) { + unsigned int soft; + sfp->set_state(sfp, state); - if (state & SFP_F_PRESENT && - sfp->state_soft_mask & SFP_F_TX_DISABLE) - sfp_soft_set_state(sfp, state); + soft = sfp->state_soft_mask & SFP_F_OUTPUTS; + if (state & SFP_F_PRESENT && soft) + sfp_soft_set_state(sfp, state, soft); +} + +static void sfp_mod_state(struct sfp *sfp, unsigned int mask, unsigned int set) +{ + mutex_lock(&sfp->st_mutex); + sfp->state = (sfp->state & ~mask) | set; + sfp_set_state(sfp, sfp->state); + mutex_unlock(&sfp->st_mutex); } static unsigned int sfp_check(void *buf, size_t len) @@ -1537,16 +1639,14 @@ static void sfp_module_tx_disable(struct sfp *sfp) { dev_dbg(sfp->dev, "tx disable %u -> %u\n", sfp->state & SFP_F_TX_DISABLE ? 1 : 0, 1); - sfp->state |= SFP_F_TX_DISABLE; - sfp_set_state(sfp, sfp->state); + sfp_mod_state(sfp, SFP_F_TX_DISABLE, SFP_F_TX_DISABLE); } static void sfp_module_tx_enable(struct sfp *sfp) { dev_dbg(sfp->dev, "tx disable %u -> %u\n", sfp->state & SFP_F_TX_DISABLE ? 1 : 0, 0); - sfp->state &= ~SFP_F_TX_DISABLE; - sfp_set_state(sfp, sfp->state); + sfp_mod_state(sfp, SFP_F_TX_DISABLE, 0); } #if IS_ENABLED(CONFIG_DEBUG_FS) @@ -1567,10 +1667,15 @@ static int sfp_debug_state_show(struct seq_file *s, void *data) sfp->sm_fault_retries); seq_printf(s, "PHY probe remaining retries: %d\n", sfp->sm_phy_retries); + seq_printf(s, "Signalling rate: %u kBd\n", sfp->rate_kbd); + seq_printf(s, "Rate select threshold: %u kBd\n", + sfp->rs_threshold_kbd); seq_printf(s, "moddef0: %d\n", !!(sfp->state & SFP_F_PRESENT)); seq_printf(s, "rx_los: %d\n", !!(sfp->state & SFP_F_LOS)); seq_printf(s, "tx_fault: %d\n", !!(sfp->state & SFP_F_TX_FAULT)); seq_printf(s, "tx_disable: %d\n", !!(sfp->state & SFP_F_TX_DISABLE)); + seq_printf(s, "rs0: %d\n", !!(sfp->state & SFP_F_RS0)); + seq_printf(s, "rs1: %d\n", !!(sfp->state & SFP_F_RS1)); return 0; } DEFINE_SHOW_ATTRIBUTE(sfp_debug_state); @@ -1599,16 +1704,18 @@ static void sfp_debugfs_exit(struct sfp *sfp) static void sfp_module_tx_fault_reset(struct sfp *sfp) { - unsigned int state = sfp->state; - - if (state & SFP_F_TX_DISABLE) - return; + unsigned int state; - sfp_set_state(sfp, state | SFP_F_TX_DISABLE); + mutex_lock(&sfp->st_mutex); + state = sfp->state; + if (!(state & SFP_F_TX_DISABLE)) { + sfp_set_state(sfp, state | SFP_F_TX_DISABLE); - udelay(T_RESET_US); + udelay(T_RESET_US); - sfp_set_state(sfp, state); + sfp_set_state(sfp, state); + } + mutex_unlock(&sfp->st_mutex); } /* SFP state machine */ @@ -1874,6 +1981,95 @@ static int sfp_sm_mod_hpower(struct sfp *sfp, bool enable) return 0; } +static void sfp_module_parse_rate_select(struct sfp *sfp) +{ + u8 rate_id; + + sfp->rs_threshold_kbd = 0; + sfp->rs_state_mask = 0; + + if (!(sfp->id.ext.options & cpu_to_be16(SFP_OPTIONS_RATE_SELECT))) + /* No support for RateSelect */ + return; + + /* Default to INF-8074 RateSelect operation. The signalling threshold + * rate is not well specified, so always select "Full Bandwidth", but + * SFF-8079 reveals that it is understood that RS0 will be low for + * 1.0625Gb/s and high for 2.125Gb/s. Choose a value half-way between. + * This method exists prior to SFF-8472. + */ + sfp->rs_state_mask = SFP_F_RS0; + sfp->rs_threshold_kbd = 1594; + + /* Parse the rate identifier, which is complicated due to history: + * SFF-8472 rev 9.5 marks this field as reserved. + * SFF-8079 references SFF-8472 rev 9.5 and defines bit 0. SFF-8472 + * compliance is not required. + * SFF-8472 rev 10.2 defines this field using values 0..4 + * SFF-8472 rev 11.0 redefines this field with bit 0 for SFF-8079 + * and even values. + */ + rate_id = sfp->id.base.rate_id; + if (rate_id == 0) + /* Unspecified */ + return; + + /* SFF-8472 rev 10.0..10.4 did not account for SFF-8079 using bit 0, + * and allocated value 3 to SFF-8431 independent tx/rx rate select. + * Convert this to a SFF-8472 rev 11.0 rate identifier. + */ + if (sfp->id.ext.sff8472_compliance >= SFP_SFF8472_COMPLIANCE_REV10_2 && + sfp->id.ext.sff8472_compliance < SFP_SFF8472_COMPLIANCE_REV11_0 && + rate_id == 3) + rate_id = SFF_RID_8431; + + if (rate_id & SFF_RID_8079) { + /* SFF-8079 RateSelect / Application Select in conjunction with + * SFF-8472 rev 9.5. SFF-8079 defines rate_id as a bitfield + * with only bit 0 used, which takes precedence over SFF-8472. + */ + if (!(sfp->id.ext.enhopts & SFP_ENHOPTS_APP_SELECT_SFF8079)) { + /* SFF-8079 Part 1 - rate selection between Fibre + * Channel 1.0625/2.125/4.25 Gbd modes. Note that RS0 + * is high for 2125, so we have to subtract 1 to + * include it. + */ + sfp->rs_threshold_kbd = 2125 - 1; + sfp->rs_state_mask = SFP_F_RS0; + } + return; + } + + /* SFF-8472 rev 9.5 does not define the rate identifier */ + if (sfp->id.ext.sff8472_compliance <= SFP_SFF8472_COMPLIANCE_REV9_5) + return; + + /* SFF-8472 rev 11.0 defines rate_id as a numerical value which will + * always have bit 0 clear due to SFF-8079's bitfield usage of rate_id. + */ + switch (rate_id) { + case SFF_RID_8431_RX_ONLY: + sfp->rs_threshold_kbd = 4250; + sfp->rs_state_mask = SFP_F_RS0; + break; + + case SFF_RID_8431_TX_ONLY: + sfp->rs_threshold_kbd = 4250; + sfp->rs_state_mask = SFP_F_RS1; + break; + + case SFF_RID_8431: + sfp->rs_threshold_kbd = 4250; + sfp->rs_state_mask = SFP_F_RS0 | SFP_F_RS1; + break; + + case SFF_RID_10G8G: + sfp->rs_threshold_kbd = 9000; + sfp->rs_state_mask = SFP_F_RS0 | SFP_F_RS1; + break; + } +} + /* GPON modules based on Realtek RTL8672 and RTL9601C chips (e.g. V-SOL * V2801F, CarlitoxxPro CPGOS03-0490, Ubiquiti U-Fiber Instant, ...) do * not support multibyte reads from the EEPROM. Each multi-byte read @@ -1953,6 +2149,7 @@ static int sfp_sm_mod_probe(struct sfp *sfp, bool report) /* SFP module inserted - read I2C data */ struct sfp_eeprom_id id; bool cotsworks_sfbg; + unsigned int mask; bool cotsworks; u8 check; int ret; @@ -2092,14 +2289,19 @@ static int sfp_sm_mod_probe(struct sfp *sfp, bool report) if (ret < 0) return ret; - /* Initialise state bits to use from hardware */ - sfp->state_hw_mask = SFP_F_PRESENT; + sfp_module_parse_rate_select(sfp); + + mask = SFP_F_PRESENT; if (sfp->gpio[GPIO_TX_DISABLE]) - sfp->state_hw_mask |= SFP_F_TX_DISABLE; + mask |= SFP_F_TX_DISABLE; if (sfp->gpio[GPIO_TX_FAULT]) - sfp->state_hw_mask |= SFP_F_TX_FAULT; + mask |= SFP_F_TX_FAULT; if (sfp->gpio[GPIO_LOS]) - sfp->state_hw_mask |= SFP_F_LOS; + mask |= SFP_F_LOS; + if (sfp->gpio[GPIO_RS0]) + mask |= SFP_F_RS0; + if (sfp->gpio[GPIO_RS1]) + mask |= SFP_F_RS1; sfp->module_t_start_up = T_START_UP; sfp->module_t_wait = T_WAIT; @@ -2117,8 +2319,17 @@ static int sfp_sm_mod_probe(struct sfp *sfp, bool report) sfp->mdio_protocol = MDIO_I2C_NONE; sfp->quirk = sfp_lookup_quirk(&id); + + mutex_lock(&sfp->st_mutex); + /* Initialise state bits to use from hardware */ + sfp->state_hw_mask = mask; + + /* We want to drive the rate select pins that the module is using */ + sfp->state_hw_drive |= sfp->rs_state_mask; + if (sfp->quirk && sfp->quirk->fixup) sfp->quirk->fixup(sfp); + mutex_unlock(&sfp->st_mutex); return 0; } @@ -2132,6 +2343,7 @@ static void sfp_sm_mod_remove(struct sfp *sfp) memset(&sfp->id, 0, sizeof(sfp->id)); sfp->module_power_mW = 0; + sfp->state_hw_drive = SFP_F_TX_DISABLE; sfp->have_a2 = false; dev_info(sfp->dev, "module removed\n"); @@ -2452,10 +2664,8 @@ static void sfp_sm_main(struct sfp *sfp, unsigned int event) } } -static void sfp_sm_event(struct sfp *sfp, unsigned int event) +static void __sfp_sm_event(struct sfp *sfp, unsigned int event) { - mutex_lock(&sfp->sm_mutex); - dev_dbg(sfp->dev, "SM: enter %s:%s:%s event %s\n", mod_state_to_str(sfp->sm_mod_state), dev_state_to_str(sfp->sm_dev_state), @@ -2470,7 +2680,12 @@ static void sfp_sm_event(struct sfp *sfp, unsigned int event) mod_state_to_str(sfp->sm_mod_state), dev_state_to_str(sfp->sm_dev_state), sm_state_to_str(sfp->sm_state)); +} +static void sfp_sm_event(struct sfp *sfp, unsigned int event) +{ + mutex_lock(&sfp->sm_mutex); + __sfp_sm_event(sfp, event); mutex_unlock(&sfp->sm_mutex); } @@ -2494,6 +2709,20 @@ static void sfp_stop(struct sfp *sfp) sfp_sm_event(sfp, SFP_E_DEV_DOWN); } +static void sfp_set_signal_rate(struct sfp *sfp, unsigned int rate_kbd) +{ + unsigned int set; + + sfp->rate_kbd = rate_kbd; + + if (rate_kbd > sfp->rs_threshold_kbd) + set = sfp->rs_state_mask; + else + set = 0; + + sfp_mod_state(sfp, SFP_F_RS0 | SFP_F_RS1, set); +} + static int sfp_module_info(struct sfp *sfp, struct ethtool_modinfo *modinfo) { /* locking... and check module is present */ @@ -2578,6 +2807,7 @@ static const struct sfp_socket_ops sfp_module_ops = { .detach = sfp_detach, .start = sfp_start, .stop = sfp_stop, + .set_signal_rate = sfp_set_signal_rate, .module_info = sfp_module_info, .module_eeprom = sfp_module_eeprom, .module_eeprom_by_page = sfp_module_eeprom_by_page, @@ -2596,6 +2826,7 @@ static void sfp_check_state(struct sfp *sfp) { unsigned int state, i, changed; + rtnl_lock(); mutex_lock(&sfp->st_mutex); state = sfp_get_state(sfp); changed = state ^ sfp->state; @@ -2609,23 +2840,24 @@ static void sfp_check_state(struct sfp *sfp) dev_dbg(sfp->dev, "%s %u -> %u\n", gpio_names[i], !!(sfp->state & BIT(i)), !!(state & BIT(i))); - state |= sfp->state & (SFP_F_TX_DISABLE | SFP_F_RATE_SELECT); + state |= sfp->state & SFP_F_OUTPUTS; sfp->state = state; + mutex_unlock(&sfp->st_mutex); - rtnl_lock(); + mutex_lock(&sfp->sm_mutex); if (changed & SFP_F_PRESENT) - sfp_sm_event(sfp, state & SFP_F_PRESENT ? - SFP_E_INSERT : SFP_E_REMOVE); + __sfp_sm_event(sfp, state & SFP_F_PRESENT ? + SFP_E_INSERT : SFP_E_REMOVE); if (changed & SFP_F_TX_FAULT) - sfp_sm_event(sfp, state & SFP_F_TX_FAULT ? - SFP_E_TX_FAULT : SFP_E_TX_CLEAR); + __sfp_sm_event(sfp, state & SFP_F_TX_FAULT ? + SFP_E_TX_FAULT : SFP_E_TX_CLEAR); if (changed & SFP_F_LOS) - sfp_sm_event(sfp, state & SFP_F_LOS ? - SFP_E_LOS_HIGH : SFP_E_LOS_LOW); + __sfp_sm_event(sfp, state & SFP_F_LOS ? + SFP_E_LOS_HIGH : SFP_E_LOS_LOW); + mutex_unlock(&sfp->sm_mutex); rtnl_unlock(); - mutex_unlock(&sfp->st_mutex); } static irqreturn_t sfp_irq(int irq, void *data) @@ -2643,6 +2875,8 @@ static void sfp_poll(struct work_struct *work) sfp_check_state(sfp); + // st_mutex doesn't need to be held here for state_soft_mask, + // it's unimportant if we race while reading this. if (sfp->state_soft_mask & (SFP_F_LOS | SFP_F_TX_FAULT) || sfp->need_poll) mod_delayed_work(system_wq, &sfp->poll, poll_jiffies); @@ -2748,6 +2982,7 @@ static int sfp_probe(struct platform_device *pdev) } sfp->state_hw_mask = SFP_F_PRESENT; + sfp->state_hw_drive = SFP_F_TX_DISABLE; sfp->get_state = sfp_gpio_get_state; sfp->set_state = sfp_gpio_set_state; @@ -2773,9 +3008,9 @@ static int sfp_probe(struct platform_device *pdev) */ sfp->state = sfp_get_state(sfp) | SFP_F_TX_DISABLE; - if (sfp->gpio[GPIO_RATE_SELECT] && - gpiod_get_value_cansleep(sfp->gpio[GPIO_RATE_SELECT])) - sfp->state |= SFP_F_RATE_SELECT; + if (sfp->gpio[GPIO_RS0] && + gpiod_get_value_cansleep(sfp->gpio[GPIO_RS0])) + sfp->state |= SFP_F_RS0; sfp_set_state(sfp, sfp->state); sfp_module_tx_disable(sfp); if (sfp->state & SFP_F_PRESENT) { diff --git a/drivers/net/phy/sfp.h b/drivers/net/phy/sfp.h index 6cf1643214d3..c7cb50d10099 100644 --- a/drivers/net/phy/sfp.h +++ b/drivers/net/phy/sfp.h @@ -19,6 +19,7 @@ struct sfp_socket_ops { void (*detach)(struct sfp *sfp); void (*start)(struct sfp *sfp); void (*stop)(struct sfp *sfp); + void (*set_signal_rate)(struct sfp *sfp, unsigned int rate_kbd); int (*module_info)(struct sfp *sfp, struct ethtool_modinfo *modinfo); int (*module_eeprom)(struct sfp *sfp, struct ethtool_eeprom *ee, u8 *data); diff --git a/drivers/net/ppp/Kconfig b/drivers/net/ppp/Kconfig index ac4d162d9455..8c9ed1889d1a 100644 --- a/drivers/net/ppp/Kconfig +++ b/drivers/net/ppp/Kconfig @@ -129,6 +129,40 @@ config PPPOE which contains instruction on how to use this driver (under the heading "Kernel mode PPPoE"). +choice + prompt "Number of PPPoE hash bits" + default PPPOE_HASH_BITS_4 + depends on PPPOE + help + Select the number of bits used for hashing PPPoE interfaces. + + Larger sizes reduces the risk of hash collisions at the cost + of slightly increased memory usage. + + This hash table is on a per outer ethernet interface. + +config PPPOE_HASH_BITS_1 + bool "1 bit (2 buckets)" + +config PPPOE_HASH_BITS_2 + bool "2 bits (4 buckets)" + +config PPPOE_HASH_BITS_4 + bool "4 bits (16 buckets)" + +config PPPOE_HASH_BITS_8 + bool "8 bits (256 buckets)" + +endchoice + +config PPPOE_HASH_BITS + int + default 1 if PPPOE_HASH_BITS_1 + default 2 if PPPOE_HASH_BITS_2 + default 4 if PPPOE_HASH_BITS_4 + default 8 if PPPOE_HASH_BITS_8 + default 4 + config PPTP tristate "PPP over IPv4 (PPTP)" depends on PPP && NET_IPGRE_DEMUX diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index ce2cbb5903d7..3b79c603b936 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -80,7 +80,7 @@ #include <linux/uaccess.h> -#define PPPOE_HASH_BITS 4 +#define PPPOE_HASH_BITS CONFIG_PPPOE_HASH_BITS #define PPPOE_HASH_SIZE (1 << PPPOE_HASH_BITS) #define PPPOE_HASH_MASK (PPPOE_HASH_SIZE - 1) diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index d10606f257c4..555b0b1e9a78 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1629,6 +1629,7 @@ static int team_init(struct net_device *dev) team->dev = dev; team_set_no_mode(team); + team->notifier_ctx = false; team->pcpu_stats = netdev_alloc_pcpu_stats(struct team_pcpu_stats); if (!team->pcpu_stats) @@ -3022,7 +3023,11 @@ static int team_device_event(struct notifier_block *unused, team_del_slave(port->team->dev, dev); break; case NETDEV_FEAT_CHANGE: - team_compute_features(port->team); + if (!port->team->notifier_ctx) { + port->team->notifier_ctx = true; + team_compute_features(port->team); + port->team->notifier_ctx = false; + } break; case NETDEV_PRECHANGEMTU: /* Forbid to change mtu of underlaying device */ diff --git a/drivers/net/tun.c b/drivers/net/tun.c index d4d0a41a905a..d75456adc62a 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1977,6 +1977,14 @@ napi_busy: int queue_len; spin_lock_bh(&queue->lock); + + if (unlikely(tfile->detached)) { + spin_unlock_bh(&queue->lock); + rcu_read_unlock(); + err = -EBUSY; + goto free_skb; + } + __skb_queue_tail(queue, skb); queue_len = skb_queue_len(queue); spin_unlock(&queue->lock); @@ -2512,6 +2520,13 @@ build: if (tfile->napi_enabled) { queue = &tfile->sk.sk_write_queue; spin_lock(&queue->lock); + + if (unlikely(tfile->detached)) { + spin_unlock(&queue->lock); + kfree_skb(skb); + return -EBUSY; + } + __skb_queue_tail(queue, skb); spin_unlock(&queue->lock); ret = 1; diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig index 4402eedb3d1a..3fd7dccf0f9c 100644 --- a/drivers/net/usb/Kconfig +++ b/drivers/net/usb/Kconfig @@ -583,12 +583,10 @@ config USB_IPHETH default n help Module used to share Internet connection (tethering) from your - iPhone (Original, 3G and 3GS) to your system. - Note that you need userspace libraries and programs that are needed - to pair your device with your system and that understand the iPhone - protocol. - - For more information: http://giagio.com/wiki/moin.cgi/iPhoneEthernetDriver + iPhone to your system. + Note that you need a corresponding userspace library/program + to pair your device with your system, for example usbmuxd + <https://github.com/libimobiledevice/usbmuxd>. config USB_SIERRA_NET tristate "USB-to-WWAN Driver for Sierra Wireless modems" diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 6ce8f4f0c70e..db05622f1f70 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -181,9 +181,12 @@ static u32 cdc_ncm_check_tx_max(struct usbnet *dev, u32 new_tx) else min = ctx->max_datagram_size + ctx->max_ndp_size + sizeof(struct usb_cdc_ncm_nth32); - max = min_t(u32, CDC_NCM_NTB_MAX_SIZE_TX, le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize)); - if (max == 0) + if (le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize) == 0) max = CDC_NCM_NTB_MAX_SIZE_TX; /* dwNtbOutMaxSize not set */ + else + max = clamp_t(u32, le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize), + USB_CDC_NCM_NTB_MIN_OUT_SIZE, + CDC_NCM_NTB_MAX_SIZE_TX); /* some devices set dwNtbOutMaxSize too low for the above default */ min = min(min, max); @@ -1244,6 +1247,9 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign) * further. */ if (skb_out == NULL) { + /* If even the smallest allocation fails, abort. */ + if (ctx->tx_curr_size == USB_CDC_NCM_NTB_MIN_OUT_SIZE) + goto alloc_failed; ctx->tx_low_mem_max_cnt = min(ctx->tx_low_mem_max_cnt + 1, (unsigned)CDC_NCM_LOW_MEM_MAX_CNT); ctx->tx_low_mem_val = ctx->tx_low_mem_max_cnt; @@ -1262,13 +1268,8 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign) skb_out = alloc_skb(ctx->tx_curr_size, GFP_ATOMIC); /* No allocation possible so we will abort */ - if (skb_out == NULL) { - if (skb != NULL) { - dev_kfree_skb_any(skb); - dev->net->stats.tx_dropped++; - } - goto exit_no_skb; - } + if (!skb_out) + goto alloc_failed; ctx->tx_low_mem_val--; } if (ctx->is_ndp16) { @@ -1461,6 +1462,11 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign) return skb_out; +alloc_failed: + if (skb) { + dev_kfree_skb_any(skb); + dev->net->stats.tx_dropped++; + } exit_no_skb: /* Start timer, if there is a remaining non-empty skb */ if (ctx->tx_curr_skb != NULL && n > 0) diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c index 6a769df0b421..687d70cfc556 100644 --- a/drivers/net/usb/ipheth.c +++ b/drivers/net/usb/ipheth.c @@ -52,6 +52,7 @@ #include <linux/ethtool.h> #include <linux/usb.h> #include <linux/workqueue.h> +#include <linux/usb/cdc.h> #define USB_VENDOR_APPLE 0x05ac @@ -59,8 +60,12 @@ #define IPHETH_USBINTF_SUBCLASS 253 #define IPHETH_USBINTF_PROTO 1 -#define IPHETH_BUF_SIZE 1514 #define IPHETH_IP_ALIGN 2 /* padding at front of URB */ +#define IPHETH_NCM_HEADER_SIZE (12 + 96) /* NCMH + NCM0 */ +#define IPHETH_TX_BUF_SIZE ETH_FRAME_LEN +#define IPHETH_RX_BUF_SIZE_LEGACY (IPHETH_IP_ALIGN + ETH_FRAME_LEN) +#define IPHETH_RX_BUF_SIZE_NCM 65536 + #define IPHETH_TX_TIMEOUT (5 * HZ) #define IPHETH_INTFNUM 2 @@ -71,6 +76,7 @@ #define IPHETH_CTRL_TIMEOUT (5 * HZ) #define IPHETH_CMD_GET_MACADDR 0x00 +#define IPHETH_CMD_ENABLE_NCM 0x04 #define IPHETH_CMD_CARRIER_CHECK 0x45 #define IPHETH_CARRIER_CHECK_TIMEOUT round_jiffies_relative(1 * HZ) @@ -97,6 +103,8 @@ struct ipheth_device { u8 bulk_out; struct delayed_work carrier_work; bool confirmed_pairing; + int (*rcvbulk_callback)(struct urb *urb); + size_t rx_buf_len; }; static int ipheth_rx_submit(struct ipheth_device *dev, gfp_t mem_flags); @@ -116,12 +124,12 @@ static int ipheth_alloc_urbs(struct ipheth_device *iphone) if (rx_urb == NULL) goto free_tx_urb; - tx_buf = usb_alloc_coherent(iphone->udev, IPHETH_BUF_SIZE, + tx_buf = usb_alloc_coherent(iphone->udev, IPHETH_TX_BUF_SIZE, GFP_KERNEL, &tx_urb->transfer_dma); if (tx_buf == NULL) goto free_rx_urb; - rx_buf = usb_alloc_coherent(iphone->udev, IPHETH_BUF_SIZE + IPHETH_IP_ALIGN, + rx_buf = usb_alloc_coherent(iphone->udev, iphone->rx_buf_len, GFP_KERNEL, &rx_urb->transfer_dma); if (rx_buf == NULL) goto free_tx_buf; @@ -134,7 +142,7 @@ static int ipheth_alloc_urbs(struct ipheth_device *iphone) return 0; free_tx_buf: - usb_free_coherent(iphone->udev, IPHETH_BUF_SIZE, tx_buf, + usb_free_coherent(iphone->udev, IPHETH_TX_BUF_SIZE, tx_buf, tx_urb->transfer_dma); free_rx_urb: usb_free_urb(rx_urb); @@ -146,9 +154,9 @@ error_nomem: static void ipheth_free_urbs(struct ipheth_device *iphone) { - usb_free_coherent(iphone->udev, IPHETH_BUF_SIZE + IPHETH_IP_ALIGN, iphone->rx_buf, + usb_free_coherent(iphone->udev, iphone->rx_buf_len, iphone->rx_buf, iphone->rx_urb->transfer_dma); - usb_free_coherent(iphone->udev, IPHETH_BUF_SIZE, iphone->tx_buf, + usb_free_coherent(iphone->udev, IPHETH_TX_BUF_SIZE, iphone->tx_buf, iphone->tx_urb->transfer_dma); usb_free_urb(iphone->rx_urb); usb_free_urb(iphone->tx_urb); @@ -160,15 +168,106 @@ static void ipheth_kill_urbs(struct ipheth_device *dev) usb_kill_urb(dev->rx_urb); } -static void ipheth_rcvbulk_callback(struct urb *urb) +static int ipheth_consume_skb(char *buf, int len, struct ipheth_device *dev) { - struct ipheth_device *dev; struct sk_buff *skb; - int status; + + skb = dev_alloc_skb(len); + if (!skb) { + dev->net->stats.rx_dropped++; + return -ENOMEM; + } + + skb_put_data(skb, buf, len); + skb->dev = dev->net; + skb->protocol = eth_type_trans(skb, dev->net); + + dev->net->stats.rx_packets++; + dev->net->stats.rx_bytes += len; + netif_rx(skb); + + return 0; +} + +static int ipheth_rcvbulk_callback_legacy(struct urb *urb) +{ + struct ipheth_device *dev; char *buf; int len; dev = urb->context; + + if (urb->actual_length <= IPHETH_IP_ALIGN) { + dev->net->stats.rx_length_errors++; + return -EINVAL; + } + len = urb->actual_length - IPHETH_IP_ALIGN; + buf = urb->transfer_buffer + IPHETH_IP_ALIGN; + + return ipheth_consume_skb(buf, len, dev); +} + +static int ipheth_rcvbulk_callback_ncm(struct urb *urb) +{ + struct usb_cdc_ncm_nth16 *ncmh; + struct usb_cdc_ncm_ndp16 *ncm0; + struct usb_cdc_ncm_dpe16 *dpe; + struct ipheth_device *dev; + int retval = -EINVAL; + char *buf; + int len; + + dev = urb->context; + + if (urb->actual_length < IPHETH_NCM_HEADER_SIZE) { + dev->net->stats.rx_length_errors++; + return retval; + } + + ncmh = urb->transfer_buffer; + if (ncmh->dwSignature != cpu_to_le32(USB_CDC_NCM_NTH16_SIGN) || + le16_to_cpu(ncmh->wNdpIndex) >= urb->actual_length) { + dev->net->stats.rx_errors++; + return retval; + } + + ncm0 = urb->transfer_buffer + le16_to_cpu(ncmh->wNdpIndex); + if (ncm0->dwSignature != cpu_to_le32(USB_CDC_NCM_NDP16_NOCRC_SIGN) || + le16_to_cpu(ncmh->wHeaderLength) + le16_to_cpu(ncm0->wLength) >= + urb->actual_length) { + dev->net->stats.rx_errors++; + return retval; + } + + dpe = ncm0->dpe16; + while (le16_to_cpu(dpe->wDatagramIndex) != 0 && + le16_to_cpu(dpe->wDatagramLength) != 0) { + if (le16_to_cpu(dpe->wDatagramIndex) >= urb->actual_length || + le16_to_cpu(dpe->wDatagramIndex) + + le16_to_cpu(dpe->wDatagramLength) > urb->actual_length) { + dev->net->stats.rx_length_errors++; + return retval; + } + + buf = urb->transfer_buffer + le16_to_cpu(dpe->wDatagramIndex); + len = le16_to_cpu(dpe->wDatagramLength); + + retval = ipheth_consume_skb(buf, len, dev); + if (retval != 0) + return retval; + + dpe++; + } + + return 0; +} + +static void ipheth_rcvbulk_callback(struct urb *urb) +{ + struct ipheth_device *dev; + int retval, status; + + dev = urb->context; if (dev == NULL) return; @@ -191,25 +290,27 @@ static void ipheth_rcvbulk_callback(struct urb *urb) dev->net->stats.rx_length_errors++; return; } - len = urb->actual_length - IPHETH_IP_ALIGN; - buf = urb->transfer_buffer + IPHETH_IP_ALIGN; - skb = dev_alloc_skb(len); - if (!skb) { - dev_err(&dev->intf->dev, "%s: dev_alloc_skb: -ENOMEM\n", - __func__); - dev->net->stats.rx_dropped++; + /* RX URBs starting with 0x00 0x01 do not encapsulate Ethernet frames, + * but rather are control frames. Their purpose is not documented, and + * they don't affect driver functionality, okay to drop them. + * There is usually just one 4-byte control frame as the very first + * URB received from the bulk IN endpoint. + */ + if (unlikely + (((char *)urb->transfer_buffer)[0] == 0 && + ((char *)urb->transfer_buffer)[1] == 1)) + goto rx_submit; + + retval = dev->rcvbulk_callback(urb); + if (retval != 0) { + dev_err(&dev->intf->dev, "%s: callback retval: %d\n", + __func__, retval); return; } - skb_put_data(skb, buf, len); - skb->dev = dev->net; - skb->protocol = eth_type_trans(skb, dev->net); - - dev->net->stats.rx_packets++; - dev->net->stats.rx_bytes += len; +rx_submit: dev->confirmed_pairing = true; - netif_rx(skb); ipheth_rx_submit(dev, GFP_ATOMIC); } @@ -310,6 +411,27 @@ static int ipheth_get_macaddr(struct ipheth_device *dev) return retval; } +static int ipheth_enable_ncm(struct ipheth_device *dev) +{ + struct usb_device *udev = dev->udev; + int retval; + + retval = usb_control_msg(udev, + usb_sndctrlpipe(udev, IPHETH_CTRL_ENDP), + IPHETH_CMD_ENABLE_NCM, /* request */ + 0x41, /* request type */ + 0x00, /* value */ + 0x02, /* index */ + NULL, + 0, + IPHETH_CTRL_TIMEOUT); + + dev_info(&dev->intf->dev, "%s: usb_control_msg: %d\n", + __func__, retval); + + return retval; +} + static int ipheth_rx_submit(struct ipheth_device *dev, gfp_t mem_flags) { struct usb_device *udev = dev->udev; @@ -317,7 +439,7 @@ static int ipheth_rx_submit(struct ipheth_device *dev, gfp_t mem_flags) usb_fill_bulk_urb(dev->rx_urb, udev, usb_rcvbulkpipe(udev, dev->bulk_in), - dev->rx_buf, IPHETH_BUF_SIZE + IPHETH_IP_ALIGN, + dev->rx_buf, dev->rx_buf_len, ipheth_rcvbulk_callback, dev); dev->rx_urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; @@ -365,7 +487,7 @@ static netdev_tx_t ipheth_tx(struct sk_buff *skb, struct net_device *net) int retval; /* Paranoid */ - if (skb->len > IPHETH_BUF_SIZE) { + if (skb->len > IPHETH_TX_BUF_SIZE) { WARN(1, "%s: skb too large: %d bytes\n", __func__, skb->len); dev->net->stats.tx_dropped++; dev_kfree_skb_any(skb); @@ -373,12 +495,10 @@ static netdev_tx_t ipheth_tx(struct sk_buff *skb, struct net_device *net) } memcpy(dev->tx_buf, skb->data, skb->len); - if (skb->len < IPHETH_BUF_SIZE) - memset(dev->tx_buf + skb->len, 0, IPHETH_BUF_SIZE - skb->len); usb_fill_bulk_urb(dev->tx_urb, udev, usb_sndbulkpipe(udev, dev->bulk_out), - dev->tx_buf, IPHETH_BUF_SIZE, + dev->tx_buf, skb->len, ipheth_sndbulk_callback, dev); dev->tx_urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; @@ -450,6 +570,8 @@ static int ipheth_probe(struct usb_interface *intf, dev->net = netdev; dev->intf = intf; dev->confirmed_pairing = false; + dev->rx_buf_len = IPHETH_RX_BUF_SIZE_LEGACY; + dev->rcvbulk_callback = ipheth_rcvbulk_callback_legacy; /* Set up endpoints */ hintf = usb_altnum_to_altsetting(intf, IPHETH_ALT_INTFNUM); if (hintf == NULL) { @@ -481,6 +603,12 @@ static int ipheth_probe(struct usb_interface *intf, if (retval) goto err_get_macaddr; + retval = ipheth_enable_ncm(dev); + if (!retval) { + dev->rx_buf_len = IPHETH_RX_BUF_SIZE_NCM; + dev->rcvbulk_callback = ipheth_rcvbulk_callback_ncm; + } + INIT_DELAYED_WORK(&dev->carrier_work, ipheth_carrier_check_work); retval = ipheth_alloc_urbs(dev); @@ -510,8 +638,8 @@ err_register_netdev: ipheth_free_urbs(dev); err_alloc_urbs: err_get_macaddr: -err_alloc_ctrl_buf: kfree(dev->ctrl_buf); +err_alloc_ctrl_buf: err_endpoints: free_netdev(netdev); return retval; diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 571e37e67f9c..f1865d047971 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1325,7 +1325,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x2001, 0x7e3d, 4)}, /* D-Link DWM-222 A2 */ {QMI_FIXED_INTF(0x2020, 0x2031, 4)}, /* Olicard 600 */ {QMI_FIXED_INTF(0x2020, 0x2033, 4)}, /* BroadMobi BM806U */ - {QMI_FIXED_INTF(0x2020, 0x2060, 4)}, /* BroadMobi BM818 */ + {QMI_QUIRK_SET_DTR(0x2020, 0x2060, 4)}, /* BroadMobi BM818 */ {QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)}, /* Sierra Wireless MC7700 */ {QMI_FIXED_INTF(0x114f, 0x68a2, 8)}, /* Sierra Wireless MC7750 */ {QMI_FIXED_INTF(0x1199, 0x68a2, 8)}, /* Sierra Wireless MC7710 in QMI mode */ diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 29eccc8ff41f..0db14f6b87d3 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -205,6 +205,8 @@ struct control_buf { __virtio16 vid; __virtio64 offloads; struct virtio_net_ctrl_rss rss; + struct virtio_net_ctrl_coal_tx coal_tx; + struct virtio_net_ctrl_coal_rx coal_rx; }; struct virtnet_info { @@ -1977,6 +1979,38 @@ static int virtnet_poll(struct napi_struct *napi, int budget) return received; } +static void virtnet_disable_queue_pair(struct virtnet_info *vi, int qp_index) +{ + virtnet_napi_tx_disable(&vi->sq[qp_index].napi); + napi_disable(&vi->rq[qp_index].napi); + xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq); +} + +static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index) +{ + struct net_device *dev = vi->dev; + int err; + + err = xdp_rxq_info_reg(&vi->rq[qp_index].xdp_rxq, dev, qp_index, + vi->rq[qp_index].napi.napi_id); + if (err < 0) + return err; + + err = xdp_rxq_info_reg_mem_model(&vi->rq[qp_index].xdp_rxq, + MEM_TYPE_PAGE_SHARED, NULL); + if (err < 0) + goto err_xdp_reg_mem_model; + + virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi); + virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi); + + return 0; + +err_xdp_reg_mem_model: + xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq); + return err; +} + static int virtnet_open(struct net_device *dev) { struct virtnet_info *vi = netdev_priv(dev); @@ -1990,22 +2024,20 @@ static int virtnet_open(struct net_device *dev) if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL)) schedule_delayed_work(&vi->refill, 0); - err = xdp_rxq_info_reg(&vi->rq[i].xdp_rxq, dev, i, vi->rq[i].napi.napi_id); + err = virtnet_enable_queue_pair(vi, i); if (err < 0) - return err; - - err = xdp_rxq_info_reg_mem_model(&vi->rq[i].xdp_rxq, - MEM_TYPE_PAGE_SHARED, NULL); - if (err < 0) { - xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq); - return err; - } - - virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); - virtnet_napi_tx_enable(vi, vi->sq[i].vq, &vi->sq[i].napi); + goto err_enable_qp; } return 0; + +err_enable_qp: + disable_delayed_refill(vi); + cancel_delayed_work_sync(&vi->refill); + + for (i--; i >= 0; i--) + virtnet_disable_queue_pair(vi, i); + return err; } static int virtnet_poll_tx(struct napi_struct *napi, int budget) @@ -2414,11 +2446,8 @@ static int virtnet_close(struct net_device *dev) /* Make sure refill_work doesn't re-enable napi! */ cancel_delayed_work_sync(&vi->refill); - for (i = 0; i < vi->max_queue_pairs; i++) { - virtnet_napi_tx_disable(&vi->sq[i].napi); - napi_disable(&vi->rq[i].napi); - xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq); - } + for (i = 0; i < vi->max_queue_pairs; i++) + virtnet_disable_queue_pair(vi, i); return 0; } @@ -3016,12 +3045,10 @@ static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi, struct ethtool_coalesce *ec) { struct scatterlist sgs_tx, sgs_rx; - struct virtio_net_ctrl_coal_tx coal_tx; - struct virtio_net_ctrl_coal_rx coal_rx; - coal_tx.tx_usecs = cpu_to_le32(ec->tx_coalesce_usecs); - coal_tx.tx_max_packets = cpu_to_le32(ec->tx_max_coalesced_frames); - sg_init_one(&sgs_tx, &coal_tx, sizeof(coal_tx)); + vi->ctrl->coal_tx.tx_usecs = cpu_to_le32(ec->tx_coalesce_usecs); + vi->ctrl->coal_tx.tx_max_packets = cpu_to_le32(ec->tx_max_coalesced_frames); + sg_init_one(&sgs_tx, &vi->ctrl->coal_tx, sizeof(vi->ctrl->coal_tx)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL, VIRTIO_NET_CTRL_NOTF_COAL_TX_SET, @@ -3032,9 +3059,9 @@ static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi, vi->tx_usecs = ec->tx_coalesce_usecs; vi->tx_max_packets = ec->tx_max_coalesced_frames; - coal_rx.rx_usecs = cpu_to_le32(ec->rx_coalesce_usecs); - coal_rx.rx_max_packets = cpu_to_le32(ec->rx_max_coalesced_frames); - sg_init_one(&sgs_rx, &coal_rx, sizeof(coal_rx)); + vi->ctrl->coal_rx.rx_usecs = cpu_to_le32(ec->rx_coalesce_usecs); + vi->ctrl->coal_rx.rx_max_packets = cpu_to_le32(ec->rx_max_coalesced_frames); + sg_init_one(&sgs_rx, &vi->ctrl->coal_rx, sizeof(vi->ctrl->coal_rx)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL, VIRTIO_NET_CTRL_NOTF_COAL_RX_SET, diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.c b/drivers/net/wwan/iosm/iosm_ipc_imem.c index c066b0040a3f..829515a601b3 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem.c +++ b/drivers/net/wwan/iosm/iosm_ipc_imem.c @@ -565,24 +565,32 @@ static void ipc_imem_run_state_worker(struct work_struct *instance) struct ipc_mux_config mux_cfg; struct iosm_imem *ipc_imem; u8 ctrl_chl_idx = 0; + int ret; ipc_imem = container_of(instance, struct iosm_imem, run_state_worker); if (ipc_imem->phase != IPC_P_RUN) { dev_err(ipc_imem->dev, "Modem link down. Exit run state worker."); - return; + goto err_out; } if (test_and_clear_bit(IOSM_DEVLINK_INIT, &ipc_imem->flag)) ipc_devlink_deinit(ipc_imem->ipc_devlink); - if (!ipc_imem_setup_cp_mux_cap_init(ipc_imem, &mux_cfg)) - ipc_imem->mux = ipc_mux_init(&mux_cfg, ipc_imem); + ret = ipc_imem_setup_cp_mux_cap_init(ipc_imem, &mux_cfg); + if (ret < 0) + goto err_out; + + ipc_imem->mux = ipc_mux_init(&mux_cfg, ipc_imem); + if (!ipc_imem->mux) + goto err_out; + + ret = ipc_imem_wwan_channel_init(ipc_imem, mux_cfg.protocol); + if (ret < 0) + goto err_ipc_mux_deinit; - ipc_imem_wwan_channel_init(ipc_imem, mux_cfg.protocol); - if (ipc_imem->mux) - ipc_imem->mux->wwan = ipc_imem->wwan; + ipc_imem->mux->wwan = ipc_imem->wwan; while (ctrl_chl_idx < IPC_MEM_MAX_CHANNELS) { if (!ipc_chnl_cfg_get(&chnl_cfg_port, ctrl_chl_idx)) { @@ -622,6 +630,13 @@ static void ipc_imem_run_state_worker(struct work_struct *instance) /* Complete all memory stores after setting bit */ smp_mb__after_atomic(); + + return; + +err_ipc_mux_deinit: + ipc_mux_deinit(ipc_imem->mux); +err_out: + ipc_uevent_send(ipc_imem->dev, UEVENT_CD_READY_LINK_DOWN); } static void ipc_imem_handle_irq(struct iosm_imem *ipc_imem, int irq) diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c index 66b90cc4c346..109cf8930488 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c +++ b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c @@ -77,8 +77,8 @@ out: } /* Initialize wwan channel */ -void ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, - enum ipc_mux_protocol mux_type) +int ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, + enum ipc_mux_protocol mux_type) { struct ipc_chnl_cfg chnl_cfg = { 0 }; @@ -87,7 +87,7 @@ void ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, /* If modem version is invalid (0xffffffff), do not initialize WWAN. */ if (ipc_imem->cp_version == -1) { dev_err(ipc_imem->dev, "invalid CP version"); - return; + return -EIO; } ipc_chnl_cfg_get(&chnl_cfg, ipc_imem->nr_of_channels); @@ -104,9 +104,13 @@ void ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, /* WWAN registration. */ ipc_imem->wwan = ipc_wwan_init(ipc_imem, ipc_imem->dev); - if (!ipc_imem->wwan) + if (!ipc_imem->wwan) { dev_err(ipc_imem->dev, "failed to register the ipc_wwan interfaces"); + return -ENOMEM; + } + + return 0; } /* Map SKB to DMA for transfer */ diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h index f8afb217d9e2..026c5bd0f999 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h +++ b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h @@ -91,9 +91,11 @@ int ipc_imem_sys_wwan_transmit(struct iosm_imem *ipc_imem, int if_id, * MUX. * @ipc_imem: Pointer to iosm_imem struct. * @mux_type: Type of mux protocol. + * + * Return: 0 on success and failure value on error */ -void ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, - enum ipc_mux_protocol mux_type); +int ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, + enum ipc_mux_protocol mux_type); /** * ipc_imem_sys_devlink_open - Open a Flash/CD Channel link to CP diff --git a/drivers/net/wwan/t7xx/t7xx_pci.c b/drivers/net/wwan/t7xx/t7xx_pci.c index 226fc1703e90..91256e005b84 100644 --- a/drivers/net/wwan/t7xx/t7xx_pci.c +++ b/drivers/net/wwan/t7xx/t7xx_pci.c @@ -45,6 +45,7 @@ #define T7XX_PCI_IREG_BASE 0 #define T7XX_PCI_EREG_BASE 2 +#define T7XX_INIT_TIMEOUT 20 #define PM_SLEEP_DIS_TIMEOUT_MS 20 #define PM_ACK_TIMEOUT_MS 1500 #define PM_AUTOSUSPEND_MS 20000 @@ -96,6 +97,7 @@ static int t7xx_pci_pm_init(struct t7xx_pci_dev *t7xx_dev) spin_lock_init(&t7xx_dev->md_pm_lock); init_completion(&t7xx_dev->sleep_lock_acquire); init_completion(&t7xx_dev->pm_sr_ack); + init_completion(&t7xx_dev->init_done); atomic_set(&t7xx_dev->md_pm_state, MTK_PM_INIT); device_init_wakeup(&pdev->dev, true); @@ -124,6 +126,7 @@ void t7xx_pci_pm_init_late(struct t7xx_pci_dev *t7xx_dev) pm_runtime_mark_last_busy(&t7xx_dev->pdev->dev); pm_runtime_allow(&t7xx_dev->pdev->dev); pm_runtime_put_noidle(&t7xx_dev->pdev->dev); + complete_all(&t7xx_dev->init_done); } static int t7xx_pci_pm_reinit(struct t7xx_pci_dev *t7xx_dev) @@ -529,6 +532,20 @@ static void t7xx_pci_shutdown(struct pci_dev *pdev) __t7xx_pci_pm_suspend(pdev); } +static int t7xx_pci_pm_prepare(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct t7xx_pci_dev *t7xx_dev; + + t7xx_dev = pci_get_drvdata(pdev); + if (!wait_for_completion_timeout(&t7xx_dev->init_done, T7XX_INIT_TIMEOUT * HZ)) { + dev_warn(dev, "Not ready for system sleep.\n"); + return -ETIMEDOUT; + } + + return 0; +} + static int t7xx_pci_pm_suspend(struct device *dev) { return __t7xx_pci_pm_suspend(to_pci_dev(dev)); @@ -555,6 +572,7 @@ static int t7xx_pci_pm_runtime_resume(struct device *dev) } static const struct dev_pm_ops t7xx_pci_pm_ops = { + .prepare = t7xx_pci_pm_prepare, .suspend = t7xx_pci_pm_suspend, .resume = t7xx_pci_pm_resume, .resume_noirq = t7xx_pci_pm_resume_noirq, diff --git a/drivers/net/wwan/t7xx/t7xx_pci.h b/drivers/net/wwan/t7xx/t7xx_pci.h index 112efa534eac..f08f1ab74469 100644 --- a/drivers/net/wwan/t7xx/t7xx_pci.h +++ b/drivers/net/wwan/t7xx/t7xx_pci.h @@ -69,6 +69,7 @@ struct t7xx_pci_dev { struct t7xx_modem *md; struct t7xx_ccmni_ctrl *ccmni_ctlb; bool rgu_pci_irq_en; + struct completion init_done; /* Low Power Items */ struct list_head md_pm_entities; diff --git a/drivers/nfc/fdp/i2c.c b/drivers/nfc/fdp/i2c.c index 1e0f2297f9c6..c1896a1d978c 100644 --- a/drivers/nfc/fdp/i2c.c +++ b/drivers/nfc/fdp/i2c.c @@ -359,7 +359,7 @@ static struct i2c_driver fdp_nci_i2c_driver = { .name = FDP_I2C_DRIVER_NAME, .acpi_match_table = fdp_nci_i2c_acpi_match, }, - .probe_new = fdp_nci_i2c_probe, + .probe = fdp_nci_i2c_probe, .remove = fdp_nci_i2c_remove, }; module_i2c_driver(fdp_nci_i2c_driver); diff --git a/drivers/nfc/microread/i2c.c b/drivers/nfc/microread/i2c.c index e72b358a2a12..642df4e0ce24 100644 --- a/drivers/nfc/microread/i2c.c +++ b/drivers/nfc/microread/i2c.c @@ -286,7 +286,7 @@ static struct i2c_driver microread_i2c_driver = { .driver = { .name = MICROREAD_I2C_DRIVER_NAME, }, - .probe_new = microread_i2c_probe, + .probe = microread_i2c_probe, .remove = microread_i2c_remove, .id_table = microread_i2c_id, }; diff --git a/drivers/nfc/nfcmrvl/i2c.c b/drivers/nfc/nfcmrvl/i2c.c index 164e2ab859fd..74553134c1b1 100644 --- a/drivers/nfc/nfcmrvl/i2c.c +++ b/drivers/nfc/nfcmrvl/i2c.c @@ -258,7 +258,7 @@ static const struct i2c_device_id nfcmrvl_i2c_id_table[] = { MODULE_DEVICE_TABLE(i2c, nfcmrvl_i2c_id_table); static struct i2c_driver nfcmrvl_i2c_driver = { - .probe_new = nfcmrvl_i2c_probe, + .probe = nfcmrvl_i2c_probe, .id_table = nfcmrvl_i2c_id_table, .remove = nfcmrvl_i2c_remove, .driver = { diff --git a/drivers/nfc/nfcsim.c b/drivers/nfc/nfcsim.c index 44eeb17ae48d..a55381f80cd6 100644 --- a/drivers/nfc/nfcsim.c +++ b/drivers/nfc/nfcsim.c @@ -336,10 +336,6 @@ static struct dentry *nfcsim_debugfs_root; static void nfcsim_debugfs_init(void) { nfcsim_debugfs_root = debugfs_create_dir("nfcsim", NULL); - - if (!nfcsim_debugfs_root) - pr_err("Could not create debugfs entry\n"); - } static void nfcsim_debugfs_remove(void) diff --git a/drivers/nfc/nxp-nci/i2c.c b/drivers/nfc/nxp-nci/i2c.c index d4c299be7949..baddaf242d18 100644 --- a/drivers/nfc/nxp-nci/i2c.c +++ b/drivers/nfc/nxp-nci/i2c.c @@ -348,7 +348,7 @@ static struct i2c_driver nxp_nci_i2c_driver = { .acpi_match_table = ACPI_PTR(acpi_id), .of_match_table = of_nxp_nci_i2c_match, }, - .probe_new = nxp_nci_i2c_probe, + .probe = nxp_nci_i2c_probe, .id_table = nxp_nci_i2c_id_table, .remove = nxp_nci_i2c_remove, }; diff --git a/drivers/nfc/pn533/i2c.c b/drivers/nfc/pn533/i2c.c index 1503a98f0405..438ab9553f7a 100644 --- a/drivers/nfc/pn533/i2c.c +++ b/drivers/nfc/pn533/i2c.c @@ -259,7 +259,7 @@ static struct i2c_driver pn533_i2c_driver = { .name = PN533_I2C_DRIVER_NAME, .of_match_table = of_match_ptr(of_pn533_i2c_match), }, - .probe_new = pn533_i2c_probe, + .probe = pn533_i2c_probe, .id_table = pn533_i2c_id_table, .remove = pn533_i2c_remove, }; diff --git a/drivers/nfc/pn544/i2c.c b/drivers/nfc/pn544/i2c.c index 8b0d910bee06..3f6d74832bac 100644 --- a/drivers/nfc/pn544/i2c.c +++ b/drivers/nfc/pn544/i2c.c @@ -953,7 +953,7 @@ static struct i2c_driver pn544_hci_i2c_driver = { .of_match_table = of_match_ptr(of_pn544_i2c_match), .acpi_match_table = ACPI_PTR(pn544_hci_i2c_acpi_match), }, - .probe_new = pn544_hci_i2c_probe, + .probe = pn544_hci_i2c_probe, .id_table = pn544_hci_i2c_id_table, .remove = pn544_hci_i2c_remove, }; diff --git a/drivers/nfc/s3fwrn5/i2c.c b/drivers/nfc/s3fwrn5/i2c.c index 2517ae71f9a4..720d4a72493c 100644 --- a/drivers/nfc/s3fwrn5/i2c.c +++ b/drivers/nfc/s3fwrn5/i2c.c @@ -261,7 +261,7 @@ static struct i2c_driver s3fwrn5_i2c_driver = { .name = S3FWRN5_I2C_DRIVER_NAME, .of_match_table = of_match_ptr(of_s3fwrn5_i2c_match), }, - .probe_new = s3fwrn5_i2c_probe, + .probe = s3fwrn5_i2c_probe, .remove = s3fwrn5_i2c_remove, .id_table = s3fwrn5_i2c_id_table, }; diff --git a/drivers/nfc/st-nci/i2c.c b/drivers/nfc/st-nci/i2c.c index 6b5eed8a1fbe..d20a337e90b4 100644 --- a/drivers/nfc/st-nci/i2c.c +++ b/drivers/nfc/st-nci/i2c.c @@ -283,7 +283,7 @@ static struct i2c_driver st_nci_i2c_driver = { .of_match_table = of_match_ptr(of_st_nci_i2c_match), .acpi_match_table = ACPI_PTR(st_nci_i2c_acpi_match), }, - .probe_new = st_nci_i2c_probe, + .probe = st_nci_i2c_probe, .id_table = st_nci_i2c_id_table, .remove = st_nci_i2c_remove, }; diff --git a/drivers/nfc/st21nfca/i2c.c b/drivers/nfc/st21nfca/i2c.c index 55f7a2391bb1..064a63db288b 100644 --- a/drivers/nfc/st21nfca/i2c.c +++ b/drivers/nfc/st21nfca/i2c.c @@ -597,7 +597,7 @@ static struct i2c_driver st21nfca_hci_i2c_driver = { .of_match_table = of_match_ptr(of_st21nfca_i2c_match), .acpi_match_table = ACPI_PTR(st21nfca_hci_i2c_acpi_match), }, - .probe_new = st21nfca_hci_i2c_probe, + .probe = st21nfca_hci_i2c_probe, .id_table = st21nfca_hci_i2c_id_table, .remove = st21nfca_hci_i2c_remove, }; diff --git a/drivers/nvme/host/constants.c b/drivers/nvme/host/constants.c index bc523ca02254..5e4f8848dce0 100644 --- a/drivers/nvme/host/constants.c +++ b/drivers/nvme/host/constants.c @@ -21,7 +21,7 @@ static const char * const nvme_ops[] = { [nvme_cmd_resv_release] = "Reservation Release", [nvme_cmd_zone_mgmt_send] = "Zone Management Send", [nvme_cmd_zone_mgmt_recv] = "Zone Management Receive", - [nvme_cmd_zone_append] = "Zone Management Append", + [nvme_cmd_zone_append] = "Zone Append", }; static const char * const nvme_admin_ops[] = { diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index ccb6eb1282f8..3ec38e2b9173 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -397,7 +397,16 @@ void nvme_complete_rq(struct request *req) trace_nvme_complete_rq(req); nvme_cleanup_cmd(req); - if (ctrl->kas) + /* + * Completions of long-running commands should not be able to + * defer sending of periodic keep alives, since the controller + * may have completed processing such commands a long time ago + * (arbitrarily close to command submission time). + * req->deadline - req->timeout is the command submission time + * in jiffies. + */ + if (ctrl->kas && + req->deadline - req->timeout >= ctrl->ka_last_check_time) ctrl->comp_seen = true; switch (nvme_decide_disposition(req)) { @@ -1115,7 +1124,7 @@ u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode) } EXPORT_SYMBOL_NS_GPL(nvme_passthru_start, NVME_TARGET_PASSTHRU); -void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects, +void nvme_passthru_end(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u32 effects, struct nvme_command *cmd, int status) { if (effects & NVME_CMD_EFFECTS_CSE_MASK) { @@ -1132,6 +1141,8 @@ void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects, nvme_queue_scan(ctrl); flush_work(&ctrl->scan_work); } + if (ns) + return; switch (cmd->common.opcode) { case nvme_admin_set_features: @@ -1161,9 +1172,25 @@ EXPORT_SYMBOL_NS_GPL(nvme_passthru_end, NVME_TARGET_PASSTHRU); * The host should send Keep Alive commands at half of the Keep Alive Timeout * accounting for transport roundtrip times [..]. */ +static unsigned long nvme_keep_alive_work_period(struct nvme_ctrl *ctrl) +{ + unsigned long delay = ctrl->kato * HZ / 2; + + /* + * When using Traffic Based Keep Alive, we need to run + * nvme_keep_alive_work at twice the normal frequency, as one + * command completion can postpone sending a keep alive command + * by up to twice the delay between runs. + */ + if (ctrl->ctratt & NVME_CTRL_ATTR_TBKAS) + delay /= 2; + return delay; +} + static void nvme_queue_keep_alive_work(struct nvme_ctrl *ctrl) { - queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ / 2); + queue_delayed_work(nvme_wq, &ctrl->ka_work, + nvme_keep_alive_work_period(ctrl)); } static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq, @@ -1172,6 +1199,20 @@ static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq, struct nvme_ctrl *ctrl = rq->end_io_data; unsigned long flags; bool startka = false; + unsigned long rtt = jiffies - (rq->deadline - rq->timeout); + unsigned long delay = nvme_keep_alive_work_period(ctrl); + + /* + * Subtract off the keepalive RTT so nvme_keep_alive_work runs + * at the desired frequency. + */ + if (rtt <= delay) { + delay -= rtt; + } else { + dev_warn(ctrl->device, "long keepalive RTT (%u ms)\n", + jiffies_to_msecs(rtt)); + delay = 0; + } blk_mq_free_request(rq); @@ -1182,6 +1223,7 @@ static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq, return RQ_END_IO_NONE; } + ctrl->ka_last_check_time = jiffies; ctrl->comp_seen = false; spin_lock_irqsave(&ctrl->lock, flags); if (ctrl->state == NVME_CTRL_LIVE || @@ -1189,7 +1231,7 @@ static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq, startka = true; spin_unlock_irqrestore(&ctrl->lock, flags); if (startka) - nvme_queue_keep_alive_work(ctrl); + queue_delayed_work(nvme_wq, &ctrl->ka_work, delay); return RQ_END_IO_NONE; } @@ -1200,6 +1242,8 @@ static void nvme_keep_alive_work(struct work_struct *work) bool comp_seen = ctrl->comp_seen; struct request *rq; + ctrl->ka_last_check_time = jiffies; + if ((ctrl->ctratt & NVME_CTRL_ATTR_TBKAS) && comp_seen) { dev_dbg(ctrl->device, "reschedule traffic based keep-alive timer\n"); @@ -3585,6 +3629,9 @@ static ssize_t nvme_sysfs_delete(struct device *dev, { struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + if (!test_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags)) + return -EBUSY; + if (device_remove_file_self(dev, attr)) nvme_delete_ctrl_sync(ctrl); return count; @@ -5045,7 +5092,7 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl) * that were missed. We identify persistent discovery controllers by * checking that they started once before, hence are reconnecting back. */ - if (test_and_set_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags) && + if (test_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags) && nvme_discovery_ctrl(ctrl)) nvme_change_uevent(ctrl, "NVME_EVENT=rediscover"); @@ -5056,6 +5103,7 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl) } nvme_change_uevent(ctrl, "NVME_EVENT=connected"); + set_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags); } EXPORT_SYMBOL_GPL(nvme_start_ctrl); diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c index 9e6e56c20ec9..316f3e4ca7cc 100644 --- a/drivers/nvme/host/hwmon.c +++ b/drivers/nvme/host/hwmon.c @@ -163,7 +163,9 @@ static umode_t nvme_hwmon_is_visible(const void *_data, case hwmon_temp_max: case hwmon_temp_min: if ((!channel && data->ctrl->wctemp) || - (channel && data->log->temp_sensor[channel - 1])) { + (channel && data->log->temp_sensor[channel - 1] && + !(data->ctrl->quirks & + NVME_QUIRK_NO_SECONDARY_TEMP_THRESH))) { if (data->ctrl->quirks & NVME_QUIRK_NO_TEMP_THRESH_CHANGE) return 0444; diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index 81c5c9e38477..f15e7330b75a 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -254,7 +254,7 @@ static int nvme_submit_user_cmd(struct request_queue *q, blk_mq_free_request(req); if (effects) - nvme_passthru_end(ctrl, effects, cmd, ret); + nvme_passthru_end(ctrl, ns, effects, cmd, ret); return ret; } diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 9171452e2f6d..2bc159a318ff 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -884,7 +884,6 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head) { if (!head->disk) return; - blk_mark_disk_dead(head->disk); /* make sure all pending bios are cleaned up */ kblockd_schedule_work(&head->requeue_work); flush_work(&head->requeue_work); diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index bf46f122e9e1..8657811f8b88 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -149,6 +149,11 @@ enum nvme_quirks { * Reports garbage in the namespace identifiers (eui64, nguid, uuid). */ NVME_QUIRK_BOGUS_NID = (1 << 18), + + /* + * No temperature thresholds for channels other than 0 (Composite). + */ + NVME_QUIRK_NO_SECONDARY_TEMP_THRESH = (1 << 19), }; /* @@ -323,6 +328,7 @@ struct nvme_ctrl { struct delayed_work ka_work; struct delayed_work failfast_work; struct nvme_command ka_cmd; + unsigned long ka_last_check_time; struct work_struct fw_act_work; unsigned long events; @@ -1072,7 +1078,7 @@ u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode); u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode); int nvme_execute_rq(struct request *rq, bool at_head); -void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects, +void nvme_passthru_end(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u32 effects, struct nvme_command *cmd, int status); struct nvme_ctrl *nvme_ctrl_from_file(struct file *file); struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 7f25c0fe3a0b..492f319ebdf3 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2956,7 +2956,7 @@ static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev, * over a single page. */ dev->ctrl.max_hw_sectors = min_t(u32, - NVME_MAX_KB_SZ << 1, dma_max_mapping_size(&pdev->dev) >> 9); + NVME_MAX_KB_SZ << 1, dma_opt_mapping_size(&pdev->dev) >> 9); dev->ctrl.max_segments = NVME_MAX_SEGS; /* @@ -3402,6 +3402,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, { PCI_DEVICE(0x2646, 0x2263), /* KINGSTON A2000 NVMe SSD */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, + { PCI_DEVICE(0x2646, 0x5013), /* Kingston KC3000, Kingston FURY Renegade */ + .driver_data = NVME_QUIRK_NO_SECONDARY_TEMP_THRESH, }, { PCI_DEVICE(0x2646, 0x5018), /* KINGSTON OM8SFP4xxxxP OS21012 NVMe SSD */ .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE(0x2646, 0x5016), /* KINGSTON OM3PGP4xxxxP OS21011 NVMe SSD */ @@ -3422,6 +3424,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1e4B, 0x1202), /* MAXIO MAP1202 */ .driver_data = NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x1e4B, 0x1602), /* MAXIO MAP1602 */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1cc1, 0x5350), /* ADATA XPG GAMMIX S50 */ .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1dbe, 0x5236), /* ADATA XPG GAMMIX S70 */ @@ -3441,6 +3445,10 @@ static const struct pci_device_id nvme_id_table[] = { NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_DEVICE(0x10ec, 0x5763), /* TEAMGROUP T-FORCE CARDEA ZERO Z330 SSD */ .driver_data = NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x1e4b, 0x1602), /* HS-SSD-FUTURE 2048G */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x10ec, 0x5765), /* TEAMGROUP MP33 2TB SSD */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0061), .driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0065), diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index 511c980d538d..71a9c1cc57f5 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -243,7 +243,7 @@ static void nvmet_passthru_execute_cmd_work(struct work_struct *w) blk_mq_free_request(rq); if (effects) - nvme_passthru_end(ctrl, effects, req->cmd, status); + nvme_passthru_end(ctrl, ns, effects, req->cmd, status); } static enum rq_end_io_ret nvmet_passthru_req_done(struct request *rq, diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index f4e2a88729fd..c525867760bf 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -6003,8 +6003,9 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x56c1, aspm_l1_acceptable_latency #ifdef CONFIG_PCIE_DPC /* - * Intel Tiger Lake and Alder Lake BIOS has a bug that clears the DPC - * RP PIO Log Size of the integrated Thunderbolt PCIe Root Ports. + * Intel Ice Lake, Tiger Lake and Alder Lake BIOS has a bug that clears + * the DPC RP PIO Log Size of the integrated Thunderbolt PCIe Root + * Ports. */ static void dpc_log_size(struct pci_dev *dev) { @@ -6027,6 +6028,10 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x461f, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x462f, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x463f, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x466e, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8a1d, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8a1f, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8a21, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8a23, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a23, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a25, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a27, dpc_log_size); diff --git a/drivers/phy/amlogic/phy-meson-g12a-mipi-dphy-analog.c b/drivers/phy/amlogic/phy-meson-g12a-mipi-dphy-analog.c index c14089fa7db4..cabdddbbabfd 100644 --- a/drivers/phy/amlogic/phy-meson-g12a-mipi-dphy-analog.c +++ b/drivers/phy/amlogic/phy-meson-g12a-mipi-dphy-analog.c @@ -70,7 +70,7 @@ static int phy_g12a_mipi_dphy_analog_power_on(struct phy *phy) HHI_MIPI_CNTL1_BANDGAP); regmap_write(priv->regmap, HHI_MIPI_CNTL2, - FIELD_PREP(HHI_MIPI_CNTL2_DIF_TX_CTL0, 0x459) | + FIELD_PREP(HHI_MIPI_CNTL2_DIF_TX_CTL0, 0x45a) | FIELD_PREP(HHI_MIPI_CNTL2_DIF_TX_CTL1, 0x2680)); reg = DSI_LANE_CLK; diff --git a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c index caa953780bee..8aa7251de4a9 100644 --- a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c +++ b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c @@ -237,11 +237,11 @@ static int mtk_hdmi_pll_calc(struct mtk_hdmi_phy *hdmi_phy, struct clk_hw *hw, */ if (tmds_clk < 54 * MEGA) txposdiv = 8; - else if (tmds_clk >= 54 * MEGA && tmds_clk < 148.35 * MEGA) + else if (tmds_clk >= 54 * MEGA && (tmds_clk * 100) < 14835 * MEGA) txposdiv = 4; - else if (tmds_clk >= 148.35 * MEGA && tmds_clk < 296.7 * MEGA) + else if ((tmds_clk * 100) >= 14835 * MEGA && (tmds_clk * 10) < 2967 * MEGA) txposdiv = 2; - else if (tmds_clk >= 296.7 * MEGA && tmds_clk <= 594 * MEGA) + else if ((tmds_clk * 10) >= 2967 * MEGA && tmds_clk <= 594 * MEGA) txposdiv = 1; else return -EINVAL; @@ -324,12 +324,12 @@ static int mtk_hdmi_pll_drv_setting(struct clk_hw *hw) clk_channel_bias = 0x34; /* 20mA */ impedance_en = 0xf; impedance = 0x36; /* 100ohm */ - } else if (pixel_clk >= 74.175 * MEGA && pixel_clk <= 300 * MEGA) { + } else if (((u64)pixel_clk * 1000) >= 74175 * MEGA && pixel_clk <= 300 * MEGA) { data_channel_bias = 0x34; /* 20mA */ clk_channel_bias = 0x2c; /* 16mA */ impedance_en = 0xf; impedance = 0x36; /* 100ohm */ - } else if (pixel_clk >= 27 * MEGA && pixel_clk < 74.175 * MEGA) { + } else if (pixel_clk >= 27 * MEGA && ((u64)pixel_clk * 1000) < 74175 * MEGA) { data_channel_bias = 0x14; /* 10mA */ clk_channel_bias = 0x14; /* 10mA */ impedance_en = 0x0; diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c index 6850e04c329b..87b17e5877ab 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c @@ -2472,7 +2472,7 @@ static int qmp_combo_com_init(struct qmp_combo *qmp) ret = regulator_bulk_enable(cfg->num_vregs, qmp->vregs); if (ret) { dev_err(qmp->dev, "failed to enable regulators, err=%d\n", ret); - goto err_unlock; + goto err_decrement_count; } ret = reset_control_bulk_assert(cfg->num_resets, qmp->resets); @@ -2522,7 +2522,8 @@ err_assert_reset: reset_control_bulk_assert(cfg->num_resets, qmp->resets); err_disable_regulators: regulator_bulk_disable(cfg->num_vregs, qmp->vregs); -err_unlock: +err_decrement_count: + qmp->init_count--; mutex_unlock(&qmp->phy_mutex); return ret; diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcie-msm8996.c b/drivers/phy/qualcomm/phy-qcom-qmp-pcie-msm8996.c index 09824be088c9..0c603bc06e09 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcie-msm8996.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcie-msm8996.c @@ -379,7 +379,7 @@ static int qmp_pcie_msm8996_com_init(struct qmp_phy *qphy) ret = regulator_bulk_enable(cfg->num_vregs, qmp->vregs); if (ret) { dev_err(qmp->dev, "failed to enable regulators, err=%d\n", ret); - goto err_unlock; + goto err_decrement_count; } ret = reset_control_bulk_assert(cfg->num_resets, qmp->resets); @@ -409,7 +409,8 @@ err_assert_reset: reset_control_bulk_assert(cfg->num_resets, qmp->resets); err_disable_regulators: regulator_bulk_disable(cfg->num_vregs, qmp->vregs); -err_unlock: +err_decrement_count: + qmp->init_count--; mutex_unlock(&qmp->phy_mutex); return ret; diff --git a/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c b/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c index a59063596214..6c237f3cc66d 100644 --- a/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c +++ b/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c @@ -115,11 +115,11 @@ struct phy_override_seq { * * @cfg_ahb_clk: AHB2PHY interface clock * @ref_clk: phy reference clock - * @iface_clk: phy interface clock * @phy_reset: phy reset control * @vregs: regulator supplies bulk data * @phy_initialized: if PHY has been initialized correctly * @mode: contains the current mode the PHY is in + * @update_seq_cfg: tuning parameters for phy init */ struct qcom_snps_hsphy { struct phy *phy; diff --git a/drivers/platform/mellanox/mlxbf-pmc.c b/drivers/platform/mellanox/mlxbf-pmc.c index c2c9b0d3244c..be967d797c28 100644 --- a/drivers/platform/mellanox/mlxbf-pmc.c +++ b/drivers/platform/mellanox/mlxbf-pmc.c @@ -1348,9 +1348,8 @@ static int mlxbf_pmc_map_counters(struct device *dev) for (i = 0; i < pmc->total_blocks; ++i) { if (strstr(pmc->block_name[i], "tile")) { - ret = sscanf(pmc->block_name[i], "tile%d", &tile_num); - if (ret < 0) - return ret; + if (sscanf(pmc->block_name[i], "tile%d", &tile_num) != 1) + return -EINVAL; if (tile_num >= pmc->tile_count) continue; diff --git a/drivers/platform/surface/aggregator/controller.c b/drivers/platform/surface/aggregator/controller.c index 535581c0471c..7fc602e01487 100644 --- a/drivers/platform/surface/aggregator/controller.c +++ b/drivers/platform/surface/aggregator/controller.c @@ -825,7 +825,7 @@ static int ssam_cplt_init(struct ssam_cplt *cplt, struct device *dev) cplt->dev = dev; - cplt->wq = create_workqueue(SSAM_CPLT_WQ_NAME); + cplt->wq = alloc_workqueue(SSAM_CPLT_WQ_NAME, WQ_UNBOUND | WQ_MEM_RECLAIM, 0); if (!cplt->wq) return -ENOMEM; diff --git a/drivers/platform/surface/surface_aggregator_tabletsw.c b/drivers/platform/surface/surface_aggregator_tabletsw.c index 8f52b62d1c19..c0a1a5869246 100644 --- a/drivers/platform/surface/surface_aggregator_tabletsw.c +++ b/drivers/platform/surface/surface_aggregator_tabletsw.c @@ -210,6 +210,7 @@ enum ssam_kip_cover_state { SSAM_KIP_COVER_STATE_LAPTOP = 0x03, SSAM_KIP_COVER_STATE_FOLDED_CANVAS = 0x04, SSAM_KIP_COVER_STATE_FOLDED_BACK = 0x05, + SSAM_KIP_COVER_STATE_BOOK = 0x06, }; static const char *ssam_kip_cover_state_name(struct ssam_tablet_sw *sw, @@ -231,6 +232,9 @@ static const char *ssam_kip_cover_state_name(struct ssam_tablet_sw *sw, case SSAM_KIP_COVER_STATE_FOLDED_BACK: return "folded-back"; + case SSAM_KIP_COVER_STATE_BOOK: + return "book"; + default: dev_warn(&sw->sdev->dev, "unknown KIP cover state: %u\n", state->state); return "<unknown>"; @@ -244,6 +248,7 @@ static bool ssam_kip_cover_state_is_tablet_mode(struct ssam_tablet_sw *sw, case SSAM_KIP_COVER_STATE_DISCONNECTED: case SSAM_KIP_COVER_STATE_FOLDED_CANVAS: case SSAM_KIP_COVER_STATE_FOLDED_BACK: + case SSAM_KIP_COVER_STATE_BOOK: return true; case SSAM_KIP_COVER_STATE_CLOSED: @@ -335,6 +340,7 @@ enum ssam_pos_state_cover { SSAM_POS_COVER_LAPTOP = 0x03, SSAM_POS_COVER_FOLDED_CANVAS = 0x04, SSAM_POS_COVER_FOLDED_BACK = 0x05, + SSAM_POS_COVER_BOOK = 0x06, }; enum ssam_pos_state_sls { @@ -367,6 +373,9 @@ static const char *ssam_pos_state_name_cover(struct ssam_tablet_sw *sw, u32 stat case SSAM_POS_COVER_FOLDED_BACK: return "folded-back"; + case SSAM_POS_COVER_BOOK: + return "book"; + default: dev_warn(&sw->sdev->dev, "unknown device posture for type-cover: %u\n", state); return "<unknown>"; @@ -416,6 +425,7 @@ static bool ssam_pos_state_is_tablet_mode_cover(struct ssam_tablet_sw *sw, u32 s case SSAM_POS_COVER_DISCONNECTED: case SSAM_POS_COVER_FOLDED_CANVAS: case SSAM_POS_COVER_FOLDED_BACK: + case SSAM_POS_COVER_BOOK: return true; case SSAM_POS_COVER_CLOSED: diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c index d5bb775dadcf..ee5f124f78b6 100644 --- a/drivers/platform/x86/amd/pmf/core.c +++ b/drivers/platform/x86/amd/pmf/core.c @@ -245,24 +245,29 @@ static const struct pci_device_id pmf_pci_ids[] = { { } }; -int amd_pmf_init_metrics_table(struct amd_pmf_dev *dev) +static void amd_pmf_set_dram_addr(struct amd_pmf_dev *dev) { u64 phys_addr; u32 hi, low; - INIT_DELAYED_WORK(&dev->work_buffer, amd_pmf_get_metrics); + phys_addr = virt_to_phys(dev->buf); + hi = phys_addr >> 32; + low = phys_addr & GENMASK(31, 0); + + amd_pmf_send_cmd(dev, SET_DRAM_ADDR_HIGH, 0, hi, NULL); + amd_pmf_send_cmd(dev, SET_DRAM_ADDR_LOW, 0, low, NULL); +} +int amd_pmf_init_metrics_table(struct amd_pmf_dev *dev) +{ /* Get Metrics Table Address */ dev->buf = kzalloc(sizeof(dev->m_table), GFP_KERNEL); if (!dev->buf) return -ENOMEM; - phys_addr = virt_to_phys(dev->buf); - hi = phys_addr >> 32; - low = phys_addr & GENMASK(31, 0); + INIT_DELAYED_WORK(&dev->work_buffer, amd_pmf_get_metrics); - amd_pmf_send_cmd(dev, SET_DRAM_ADDR_HIGH, 0, hi, NULL); - amd_pmf_send_cmd(dev, SET_DRAM_ADDR_LOW, 0, low, NULL); + amd_pmf_set_dram_addr(dev); /* * Start collecting the metrics data after a small delay @@ -273,6 +278,18 @@ int amd_pmf_init_metrics_table(struct amd_pmf_dev *dev) return 0; } +static int amd_pmf_resume_handler(struct device *dev) +{ + struct amd_pmf_dev *pdev = dev_get_drvdata(dev); + + if (pdev->buf) + amd_pmf_set_dram_addr(pdev); + + return 0; +} + +static DEFINE_SIMPLE_DEV_PM_OPS(amd_pmf_pm, NULL, amd_pmf_resume_handler); + static void amd_pmf_init_features(struct amd_pmf_dev *dev) { int ret; @@ -413,6 +430,7 @@ static struct platform_driver amd_pmf_driver = { .name = "amd-pmf", .acpi_match_table = amd_pmf_acpi_ids, .dev_groups = amd_pmf_driver_groups, + .pm = pm_sleep_ptr(&amd_pmf_pm), }, .probe = amd_pmf_probe, .remove_new = amd_pmf_remove, diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index e2c9a68d12df..fdf7da06af30 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -555,6 +555,7 @@ static const struct key_entry asus_nb_wmi_keymap[] = { { KE_KEY, 0x71, { KEY_F13 } }, /* General-purpose button */ { KE_IGNORE, 0x79, }, /* Charger type dectection notification */ { KE_KEY, 0x7a, { KEY_ALS_TOGGLE } }, /* Ambient Light Sensor Toggle */ + { KE_IGNORE, 0x7B, }, /* Charger connect/disconnect notification */ { KE_KEY, 0x7c, { KEY_MICMUTE } }, { KE_KEY, 0x7D, { KEY_BLUETOOTH } }, /* Bluetooth Enable */ { KE_KEY, 0x7E, { KEY_BLUETOOTH } }, /* Bluetooth Disable */ @@ -584,6 +585,7 @@ static const struct key_entry asus_nb_wmi_keymap[] = { { KE_KEY, 0xAE, { KEY_FN_F5 } }, /* Fn+F5 fan mode on 2020+ */ { KE_KEY, 0xB3, { KEY_PROG4 } }, /* AURA */ { KE_KEY, 0xB5, { KEY_CALC } }, + { KE_IGNORE, 0xC0, }, /* External display connect/disconnect notification */ { KE_KEY, 0xC4, { KEY_KBDILLUMUP } }, { KE_KEY, 0xC5, { KEY_KBDILLUMDOWN } }, { KE_IGNORE, 0xC6, }, /* Ambient Light Sensor notification */ diff --git a/drivers/platform/x86/intel/ifs/load.c b/drivers/platform/x86/intel/ifs/load.c index 61dffb4c8a1d..e6ae8265f3a3 100644 --- a/drivers/platform/x86/intel/ifs/load.c +++ b/drivers/platform/x86/intel/ifs/load.c @@ -208,7 +208,7 @@ static int scan_chunks_sanity_check(struct device *dev) continue; reinit_completion(&ifs_done); local_work.dev = dev; - INIT_WORK(&local_work.w, copy_hashes_authenticate_chunks); + INIT_WORK_ONSTACK(&local_work.w, copy_hashes_authenticate_chunks); schedule_work_on(cpu, &local_work.w); wait_for_completion(&ifs_done); if (ifsd->loading_error) { diff --git a/drivers/platform/x86/intel/int3472/clk_and_regulator.c b/drivers/platform/x86/intel/int3472/clk_and_regulator.c index 1086c3d83494..399f0623ca1b 100644 --- a/drivers/platform/x86/intel/int3472/clk_and_regulator.c +++ b/drivers/platform/x86/intel/int3472/clk_and_regulator.c @@ -101,9 +101,11 @@ int skl_int3472_register_clock(struct int3472_discrete_device *int3472, int3472->clock.ena_gpio = acpi_get_and_request_gpiod(path, agpio->pin_table[0], "int3472,clk-enable"); - if (IS_ERR(int3472->clock.ena_gpio)) - return dev_err_probe(int3472->dev, PTR_ERR(int3472->clock.ena_gpio), - "getting clk-enable GPIO\n"); + if (IS_ERR(int3472->clock.ena_gpio)) { + ret = PTR_ERR(int3472->clock.ena_gpio); + int3472->clock.ena_gpio = NULL; + return dev_err_probe(int3472->dev, ret, "getting clk-enable GPIO\n"); + } if (polarity == GPIO_ACTIVE_LOW) gpiod_toggle_active_low(int3472->clock.ena_gpio); @@ -199,8 +201,9 @@ int skl_int3472_register_regulator(struct int3472_discrete_device *int3472, int3472->regulator.gpio = acpi_get_and_request_gpiod(path, agpio->pin_table[0], "int3472,regulator"); if (IS_ERR(int3472->regulator.gpio)) { - dev_err(int3472->dev, "Failed to get regulator GPIO line\n"); - return PTR_ERR(int3472->regulator.gpio); + ret = PTR_ERR(int3472->regulator.gpio); + int3472->regulator.gpio = NULL; + return dev_err_probe(int3472->dev, ret, "getting regulator GPIO\n"); } /* Ensure the pin is in output mode and non-active state */ diff --git a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c index e0572a29212e..02fe360a59c7 100644 --- a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c +++ b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c @@ -304,14 +304,13 @@ struct isst_if_pkg_info { static struct isst_if_cpu_info *isst_cpu_info; static struct isst_if_pkg_info *isst_pkg_info; -#define ISST_MAX_PCI_DOMAINS 8 - static struct pci_dev *_isst_if_get_pci_dev(int cpu, int bus_no, int dev, int fn) { struct pci_dev *matched_pci_dev = NULL; struct pci_dev *pci_dev = NULL; + struct pci_dev *_pci_dev = NULL; int no_matches = 0, pkg_id; - int i, bus_number; + int bus_number; if (bus_no < 0 || bus_no >= ISST_MAX_BUS_NUMBER || cpu < 0 || cpu >= nr_cpu_ids || cpu >= num_possible_cpus()) @@ -323,12 +322,11 @@ static struct pci_dev *_isst_if_get_pci_dev(int cpu, int bus_no, int dev, int fn if (bus_number < 0) return NULL; - for (i = 0; i < ISST_MAX_PCI_DOMAINS; ++i) { - struct pci_dev *_pci_dev; + for_each_pci_dev(_pci_dev) { int node; - _pci_dev = pci_get_domain_bus_and_slot(i, bus_number, PCI_DEVFN(dev, fn)); - if (!_pci_dev) + if (_pci_dev->bus->number != bus_number || + _pci_dev->devfn != PCI_DEVFN(dev, fn)) continue; ++no_matches; diff --git a/drivers/power/supply/ab8500_btemp.c b/drivers/power/supply/ab8500_btemp.c index 307ee6f71042..6f83e99d2eb7 100644 --- a/drivers/power/supply/ab8500_btemp.c +++ b/drivers/power/supply/ab8500_btemp.c @@ -624,10 +624,8 @@ static int ab8500_btemp_get_ext_psy_data(struct device *dev, void *data) */ static void ab8500_btemp_external_power_changed(struct power_supply *psy) { - struct ab8500_btemp *di = power_supply_get_drvdata(psy); - - class_for_each_device(power_supply_class, NULL, - di->btemp_psy, ab8500_btemp_get_ext_psy_data); + class_for_each_device(power_supply_class, NULL, psy, + ab8500_btemp_get_ext_psy_data); } /* ab8500 btemp driver interrupts and their respective isr */ diff --git a/drivers/power/supply/ab8500_fg.c b/drivers/power/supply/ab8500_fg.c index 41a7bff9ac37..53560fbb6dcd 100644 --- a/drivers/power/supply/ab8500_fg.c +++ b/drivers/power/supply/ab8500_fg.c @@ -2407,10 +2407,8 @@ out: */ static void ab8500_fg_external_power_changed(struct power_supply *psy) { - struct ab8500_fg *di = power_supply_get_drvdata(psy); - - class_for_each_device(power_supply_class, NULL, - di->fg_psy, ab8500_fg_get_ext_psy_data); + class_for_each_device(power_supply_class, NULL, psy, + ab8500_fg_get_ext_psy_data); } /** diff --git a/drivers/power/supply/axp288_fuel_gauge.c b/drivers/power/supply/axp288_fuel_gauge.c index 05f413178462..3be6f3b10ea4 100644 --- a/drivers/power/supply/axp288_fuel_gauge.c +++ b/drivers/power/supply/axp288_fuel_gauge.c @@ -507,7 +507,7 @@ static void fuel_gauge_external_power_changed(struct power_supply *psy) mutex_lock(&info->lock); info->valid = 0; /* Force updating of the cached registers */ mutex_unlock(&info->lock); - power_supply_changed(info->bat); + power_supply_changed(psy); } static struct power_supply_desc fuel_gauge_desc = { diff --git a/drivers/power/supply/bq24190_charger.c b/drivers/power/supply/bq24190_charger.c index de67b985f0a9..dc33f00fcc06 100644 --- a/drivers/power/supply/bq24190_charger.c +++ b/drivers/power/supply/bq24190_charger.c @@ -1262,6 +1262,7 @@ static void bq24190_input_current_limit_work(struct work_struct *work) bq24190_charger_set_property(bdi->charger, POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT, &val); + power_supply_changed(bdi->charger); } /* Sync the input-current-limit with our parent supply (if we have one) */ diff --git a/drivers/power/supply/bq25890_charger.c b/drivers/power/supply/bq25890_charger.c index 22cde35eb144..f8636cf86505 100644 --- a/drivers/power/supply/bq25890_charger.c +++ b/drivers/power/supply/bq25890_charger.c @@ -750,7 +750,7 @@ static void bq25890_charger_external_power_changed(struct power_supply *psy) if (bq->chip_version != BQ25892) return; - ret = power_supply_get_property_from_supplier(bq->charger, + ret = power_supply_get_property_from_supplier(psy, POWER_SUPPLY_PROP_USB_TYPE, &val); if (ret) @@ -775,6 +775,7 @@ static void bq25890_charger_external_power_changed(struct power_supply *psy) } bq25890_field_write(bq, F_IINLIM, input_current_limit); + power_supply_changed(psy); } static int bq25890_get_chip_state(struct bq25890_device *bq, @@ -1106,6 +1107,8 @@ static void bq25890_pump_express_work(struct work_struct *data) dev_info(bq->dev, "Hi-voltage charging requested, input voltage is %d mV\n", voltage); + power_supply_changed(bq->charger); + return; error_print: bq25890_field_write(bq, F_PUMPX_EN, 0); diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 5ff6f44fd47b..4296600e8912 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -1083,10 +1083,8 @@ static int poll_interval_param_set(const char *val, const struct kernel_param *k return ret; mutex_lock(&bq27xxx_list_lock); - list_for_each_entry(di, &bq27xxx_battery_devices, list) { - cancel_delayed_work_sync(&di->work); - schedule_delayed_work(&di->work, 0); - } + list_for_each_entry(di, &bq27xxx_battery_devices, list) + mod_delayed_work(system_wq, &di->work, 0); mutex_unlock(&bq27xxx_list_lock); return ret; @@ -1761,60 +1759,6 @@ static int bq27xxx_battery_read_health(struct bq27xxx_device_info *di) return POWER_SUPPLY_HEALTH_GOOD; } -void bq27xxx_battery_update(struct bq27xxx_device_info *di) -{ - struct bq27xxx_reg_cache cache = {0, }; - bool has_singe_flag = di->opts & BQ27XXX_O_ZERO; - - cache.flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, has_singe_flag); - if ((cache.flags & 0xff) == 0xff) - cache.flags = -1; /* read error */ - if (cache.flags >= 0) { - cache.temperature = bq27xxx_battery_read_temperature(di); - if (di->regs[BQ27XXX_REG_TTE] != INVALID_REG_ADDR) - cache.time_to_empty = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTE); - if (di->regs[BQ27XXX_REG_TTECP] != INVALID_REG_ADDR) - cache.time_to_empty_avg = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTECP); - if (di->regs[BQ27XXX_REG_TTF] != INVALID_REG_ADDR) - cache.time_to_full = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTF); - - cache.charge_full = bq27xxx_battery_read_fcc(di); - cache.capacity = bq27xxx_battery_read_soc(di); - if (di->regs[BQ27XXX_REG_AE] != INVALID_REG_ADDR) - cache.energy = bq27xxx_battery_read_energy(di); - di->cache.flags = cache.flags; - cache.health = bq27xxx_battery_read_health(di); - if (di->regs[BQ27XXX_REG_CYCT] != INVALID_REG_ADDR) - cache.cycle_count = bq27xxx_battery_read_cyct(di); - - /* We only have to read charge design full once */ - if (di->charge_design_full <= 0) - di->charge_design_full = bq27xxx_battery_read_dcap(di); - } - - if ((di->cache.capacity != cache.capacity) || - (di->cache.flags != cache.flags)) - power_supply_changed(di->bat); - - if (memcmp(&di->cache, &cache, sizeof(cache)) != 0) - di->cache = cache; - - di->last_update = jiffies; -} -EXPORT_SYMBOL_GPL(bq27xxx_battery_update); - -static void bq27xxx_battery_poll(struct work_struct *work) -{ - struct bq27xxx_device_info *di = - container_of(work, struct bq27xxx_device_info, - work.work); - - bq27xxx_battery_update(di); - - if (poll_interval > 0) - schedule_delayed_work(&di->work, poll_interval * HZ); -} - static bool bq27xxx_battery_is_full(struct bq27xxx_device_info *di, int flags) { if (di->opts & BQ27XXX_O_ZERO) @@ -1833,7 +1777,8 @@ static bool bq27xxx_battery_is_full(struct bq27xxx_device_info *di, int flags) static int bq27xxx_battery_current_and_status( struct bq27xxx_device_info *di, union power_supply_propval *val_curr, - union power_supply_propval *val_status) + union power_supply_propval *val_status, + struct bq27xxx_reg_cache *cache) { bool single_flags = (di->opts & BQ27XXX_O_ZERO); int curr; @@ -1845,10 +1790,14 @@ static int bq27xxx_battery_current_and_status( return curr; } - flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, single_flags); - if (flags < 0) { - dev_err(di->dev, "error reading flags\n"); - return flags; + if (cache) { + flags = cache->flags; + } else { + flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, single_flags); + if (flags < 0) { + dev_err(di->dev, "error reading flags\n"); + return flags; + } } if (di->opts & BQ27XXX_O_ZERO) { @@ -1883,6 +1832,78 @@ static int bq27xxx_battery_current_and_status( return 0; } +static void bq27xxx_battery_update_unlocked(struct bq27xxx_device_info *di) +{ + union power_supply_propval status = di->last_status; + struct bq27xxx_reg_cache cache = {0, }; + bool has_singe_flag = di->opts & BQ27XXX_O_ZERO; + + cache.flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, has_singe_flag); + if ((cache.flags & 0xff) == 0xff) + cache.flags = -1; /* read error */ + if (cache.flags >= 0) { + cache.temperature = bq27xxx_battery_read_temperature(di); + if (di->regs[BQ27XXX_REG_TTE] != INVALID_REG_ADDR) + cache.time_to_empty = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTE); + if (di->regs[BQ27XXX_REG_TTECP] != INVALID_REG_ADDR) + cache.time_to_empty_avg = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTECP); + if (di->regs[BQ27XXX_REG_TTF] != INVALID_REG_ADDR) + cache.time_to_full = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTF); + + cache.charge_full = bq27xxx_battery_read_fcc(di); + cache.capacity = bq27xxx_battery_read_soc(di); + if (di->regs[BQ27XXX_REG_AE] != INVALID_REG_ADDR) + cache.energy = bq27xxx_battery_read_energy(di); + di->cache.flags = cache.flags; + cache.health = bq27xxx_battery_read_health(di); + if (di->regs[BQ27XXX_REG_CYCT] != INVALID_REG_ADDR) + cache.cycle_count = bq27xxx_battery_read_cyct(di); + + /* + * On gauges with signed current reporting the current must be + * checked to detect charging <-> discharging status changes. + */ + if (!(di->opts & BQ27XXX_O_ZERO)) + bq27xxx_battery_current_and_status(di, NULL, &status, &cache); + + /* We only have to read charge design full once */ + if (di->charge_design_full <= 0) + di->charge_design_full = bq27xxx_battery_read_dcap(di); + } + + if ((di->cache.capacity != cache.capacity) || + (di->cache.flags != cache.flags) || + (di->last_status.intval != status.intval)) { + di->last_status.intval = status.intval; + power_supply_changed(di->bat); + } + + if (memcmp(&di->cache, &cache, sizeof(cache)) != 0) + di->cache = cache; + + di->last_update = jiffies; + + if (!di->removed && poll_interval > 0) + mod_delayed_work(system_wq, &di->work, poll_interval * HZ); +} + +void bq27xxx_battery_update(struct bq27xxx_device_info *di) +{ + mutex_lock(&di->lock); + bq27xxx_battery_update_unlocked(di); + mutex_unlock(&di->lock); +} +EXPORT_SYMBOL_GPL(bq27xxx_battery_update); + +static void bq27xxx_battery_poll(struct work_struct *work) +{ + struct bq27xxx_device_info *di = + container_of(work, struct bq27xxx_device_info, + work.work); + + bq27xxx_battery_update(di); +} + /* * Get the average power in µW * Return < 0 if something fails. @@ -1985,10 +2006,8 @@ static int bq27xxx_battery_get_property(struct power_supply *psy, struct bq27xxx_device_info *di = power_supply_get_drvdata(psy); mutex_lock(&di->lock); - if (time_is_before_jiffies(di->last_update + 5 * HZ)) { - cancel_delayed_work_sync(&di->work); - bq27xxx_battery_poll(&di->work.work); - } + if (time_is_before_jiffies(di->last_update + 5 * HZ)) + bq27xxx_battery_update_unlocked(di); mutex_unlock(&di->lock); if (psp != POWER_SUPPLY_PROP_PRESENT && di->cache.flags < 0) @@ -1996,7 +2015,7 @@ static int bq27xxx_battery_get_property(struct power_supply *psy, switch (psp) { case POWER_SUPPLY_PROP_STATUS: - ret = bq27xxx_battery_current_and_status(di, NULL, val); + ret = bq27xxx_battery_current_and_status(di, NULL, val, NULL); break; case POWER_SUPPLY_PROP_VOLTAGE_NOW: ret = bq27xxx_battery_voltage(di, val); @@ -2005,7 +2024,7 @@ static int bq27xxx_battery_get_property(struct power_supply *psy, val->intval = di->cache.flags < 0 ? 0 : 1; break; case POWER_SUPPLY_PROP_CURRENT_NOW: - ret = bq27xxx_battery_current_and_status(di, val, NULL); + ret = bq27xxx_battery_current_and_status(di, val, NULL, NULL); break; case POWER_SUPPLY_PROP_CAPACITY: ret = bq27xxx_simple_value(di->cache.capacity, val); @@ -2078,8 +2097,8 @@ static void bq27xxx_external_power_changed(struct power_supply *psy) { struct bq27xxx_device_info *di = power_supply_get_drvdata(psy); - cancel_delayed_work_sync(&di->work); - schedule_delayed_work(&di->work, 0); + /* After charger plug in/out wait 0.5s for things to stabilize */ + mod_delayed_work(system_wq, &di->work, HZ / 2); } int bq27xxx_battery_setup(struct bq27xxx_device_info *di) @@ -2127,22 +2146,18 @@ EXPORT_SYMBOL_GPL(bq27xxx_battery_setup); void bq27xxx_battery_teardown(struct bq27xxx_device_info *di) { - /* - * power_supply_unregister call bq27xxx_battery_get_property which - * call bq27xxx_battery_poll. - * Make sure that bq27xxx_battery_poll will not call - * schedule_delayed_work again after unregister (which cause OOPS). - */ - poll_interval = 0; - - cancel_delayed_work_sync(&di->work); - - power_supply_unregister(di->bat); - mutex_lock(&bq27xxx_list_lock); list_del(&di->list); mutex_unlock(&bq27xxx_list_lock); + /* Set removed to avoid bq27xxx_battery_update() re-queuing the work */ + mutex_lock(&di->lock); + di->removed = true; + mutex_unlock(&di->lock); + + cancel_delayed_work_sync(&di->work); + + power_supply_unregister(di->bat); mutex_destroy(&di->lock); } EXPORT_SYMBOL_GPL(bq27xxx_battery_teardown); diff --git a/drivers/power/supply/bq27xxx_battery_i2c.c b/drivers/power/supply/bq27xxx_battery_i2c.c index f8768997333b..6d3c74876339 100644 --- a/drivers/power/supply/bq27xxx_battery_i2c.c +++ b/drivers/power/supply/bq27xxx_battery_i2c.c @@ -179,7 +179,7 @@ static int bq27xxx_battery_i2c_probe(struct i2c_client *client) i2c_set_clientdata(client, di); if (client->irq) { - ret = devm_request_threaded_irq(&client->dev, client->irq, + ret = request_threaded_irq(client->irq, NULL, bq27xxx_battery_irq_handler_thread, IRQF_ONESHOT, di->name, di); @@ -209,6 +209,7 @@ static void bq27xxx_battery_i2c_remove(struct i2c_client *client) { struct bq27xxx_device_info *di = i2c_get_clientdata(client); + free_irq(client->irq, di); bq27xxx_battery_teardown(di); mutex_lock(&battery_mutex); diff --git a/drivers/power/supply/mt6360_charger.c b/drivers/power/supply/mt6360_charger.c index 92e48e3a4853..1305cba61edd 100644 --- a/drivers/power/supply/mt6360_charger.c +++ b/drivers/power/supply/mt6360_charger.c @@ -796,7 +796,9 @@ static int mt6360_charger_probe(struct platform_device *pdev) mci->vinovp = 6500000; mutex_init(&mci->chgdet_lock); platform_set_drvdata(pdev, mci); - devm_work_autocancel(&pdev->dev, &mci->chrdet_work, mt6360_chrdet_work); + ret = devm_work_autocancel(&pdev->dev, &mci->chrdet_work, mt6360_chrdet_work); + if (ret) + return dev_err_probe(&pdev->dev, ret, "Failed to set delayed work\n"); ret = device_property_read_u32(&pdev->dev, "richtek,vinovp-microvolt", &mci->vinovp); if (ret) diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index ab986dbace16..3791aec69ddc 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -348,6 +348,10 @@ static int __power_supply_is_system_supplied(struct device *dev, void *data) struct power_supply *psy = dev_get_drvdata(dev); unsigned int *count = data; + if (!psy->desc->get_property(psy, POWER_SUPPLY_PROP_SCOPE, &ret)) + if (ret.intval == POWER_SUPPLY_SCOPE_DEVICE) + return 0; + (*count)++; if (psy->desc->type != POWER_SUPPLY_TYPE_BATTERY) if (!psy->desc->get_property(psy, POWER_SUPPLY_PROP_ONLINE, @@ -366,8 +370,8 @@ int power_supply_is_system_supplied(void) __power_supply_is_system_supplied); /* - * If no power class device was found at all, most probably we are - * running on a desktop system, so assume we are on mains power. + * If no system scope power class device was found at all, most probably we + * are running on a desktop system, so assume we are on mains power. */ if (count == 0) return 1; @@ -573,7 +577,7 @@ int power_supply_get_battery_info(struct power_supply *psy, struct power_supply_battery_info *info; struct device_node *battery_np = NULL; struct fwnode_reference_args args; - struct fwnode_handle *fwnode; + struct fwnode_handle *fwnode = NULL; const char *value; int err, len, index; const __be32 *list; @@ -585,7 +589,7 @@ int power_supply_get_battery_info(struct power_supply *psy, return -ENODEV; fwnode = fwnode_handle_get(of_fwnode_handle(battery_np)); - } else { + } else if (psy->dev.parent) { err = fwnode_property_get_reference_args( dev_fwnode(psy->dev.parent), "monitored-battery", NULL, 0, 0, &args); @@ -595,6 +599,9 @@ int power_supply_get_battery_info(struct power_supply *psy, fwnode = args.fwnode; } + if (!fwnode) + return -ENOENT; + err = fwnode_property_read_string(fwnode, "compatible", &value); if (err) goto out_put_node; diff --git a/drivers/power/supply/power_supply_leds.c b/drivers/power/supply/power_supply_leds.c index 702bf83f6e6d..0674483279d7 100644 --- a/drivers/power/supply/power_supply_leds.c +++ b/drivers/power/supply/power_supply_leds.c @@ -35,8 +35,9 @@ static void power_supply_update_bat_leds(struct power_supply *psy) led_trigger_event(psy->charging_full_trig, LED_FULL); led_trigger_event(psy->charging_trig, LED_OFF); led_trigger_event(psy->full_trig, LED_FULL); - led_trigger_event(psy->charging_blink_full_solid_trig, - LED_FULL); + /* Going from blink to LED on requires a LED_OFF event to stop blink */ + led_trigger_event(psy->charging_blink_full_solid_trig, LED_OFF); + led_trigger_event(psy->charging_blink_full_solid_trig, LED_FULL); break; case POWER_SUPPLY_STATUS_CHARGING: led_trigger_event(psy->charging_full_trig, LED_FULL); diff --git a/drivers/power/supply/power_supply_sysfs.c b/drivers/power/supply/power_supply_sysfs.c index ba3b125cd66e..06e5b6b0e255 100644 --- a/drivers/power/supply/power_supply_sysfs.c +++ b/drivers/power/supply/power_supply_sysfs.c @@ -286,7 +286,8 @@ static ssize_t power_supply_show_property(struct device *dev, if (ret < 0) { if (ret == -ENODATA) - dev_dbg(dev, "driver has no data for `%s' property\n", + dev_dbg_ratelimited(dev, + "driver has no data for `%s' property\n", attr->attr.name); else if (ret != -ENODEV && ret != -EAGAIN) dev_err_ratelimited(dev, diff --git a/drivers/power/supply/rt9467-charger.c b/drivers/power/supply/rt9467-charger.c index 73f744a3155d..ea33693b6977 100644 --- a/drivers/power/supply/rt9467-charger.c +++ b/drivers/power/supply/rt9467-charger.c @@ -1023,7 +1023,7 @@ static int rt9467_request_interrupt(struct rt9467_chg_data *data) for (i = 0; i < num_chg_irqs; i++) { virq = regmap_irq_get_virq(data->irq_chip_data, chg_irqs[i].hwirq); if (virq <= 0) - return dev_err_probe(dev, virq, "Failed to get (%s) irq\n", + return dev_err_probe(dev, -EINVAL, "Failed to get (%s) irq\n", chg_irqs[i].name); ret = devm_request_threaded_irq(dev, virq, NULL, chg_irqs[i].handler, diff --git a/drivers/power/supply/sbs-charger.c b/drivers/power/supply/sbs-charger.c index 75ebcbf0a788..a14e89ac0369 100644 --- a/drivers/power/supply/sbs-charger.c +++ b/drivers/power/supply/sbs-charger.c @@ -24,7 +24,7 @@ #define SBS_CHARGER_REG_STATUS 0x13 #define SBS_CHARGER_REG_ALARM_WARNING 0x16 -#define SBS_CHARGER_STATUS_CHARGE_INHIBITED BIT(1) +#define SBS_CHARGER_STATUS_CHARGE_INHIBITED BIT(0) #define SBS_CHARGER_STATUS_RES_COLD BIT(9) #define SBS_CHARGER_STATUS_RES_HOT BIT(10) #define SBS_CHARGER_STATUS_BATTERY_PRESENT BIT(14) diff --git a/drivers/power/supply/sc27xx_fuel_gauge.c b/drivers/power/supply/sc27xx_fuel_gauge.c index 632977f84b95..bd23c4d9fed4 100644 --- a/drivers/power/supply/sc27xx_fuel_gauge.c +++ b/drivers/power/supply/sc27xx_fuel_gauge.c @@ -733,13 +733,6 @@ static int sc27xx_fgu_set_property(struct power_supply *psy, return ret; } -static void sc27xx_fgu_external_power_changed(struct power_supply *psy) -{ - struct sc27xx_fgu_data *data = power_supply_get_drvdata(psy); - - power_supply_changed(data->battery); -} - static int sc27xx_fgu_property_is_writeable(struct power_supply *psy, enum power_supply_property psp) { @@ -774,7 +767,7 @@ static const struct power_supply_desc sc27xx_fgu_desc = { .num_properties = ARRAY_SIZE(sc27xx_fgu_props), .get_property = sc27xx_fgu_get_property, .set_property = sc27xx_fgu_set_property, - .external_power_changed = sc27xx_fgu_external_power_changed, + .external_power_changed = power_supply_changed, .property_is_writeable = sc27xx_fgu_property_is_writeable, .no_thermal = true, }; diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig index b00201d81313..32dff1b4f891 100644 --- a/drivers/ptp/Kconfig +++ b/drivers/ptp/Kconfig @@ -102,7 +102,7 @@ config PTP_1588_CLOCK_INES config PTP_1588_CLOCK_PCH tristate "Intel PCH EG20T as PTP clock" - depends on X86_32 || COMPILE_TEST + depends on MIPS_GENERIC || X86_32 || COMPILE_TEST depends on HAS_IOMEM && PCI depends on NET depends on PTP_1588_CLOCK diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index dc741ac156c3..698ab7f5004b 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -5256,7 +5256,7 @@ static void rdev_init_debugfs(struct regulator_dev *rdev) } rdev->debugfs = debugfs_create_dir(rname, debugfs_root); - if (!rdev->debugfs) { + if (IS_ERR(rdev->debugfs)) { rdev_warn(rdev, "Failed to create debugfs directory\n"); return; } @@ -6178,7 +6178,7 @@ static int __init regulator_init(void) ret = class_register(®ulator_class); debugfs_root = debugfs_create_dir("regulator", NULL); - if (!debugfs_root) + if (IS_ERR(debugfs_root)) pr_warn("regulator: Failed to create debugfs directory\n"); #ifdef CONFIG_DEBUG_FS diff --git a/drivers/regulator/mt6359-regulator.c b/drivers/regulator/mt6359-regulator.c index 1849566784ab..3eb86ec21d08 100644 --- a/drivers/regulator/mt6359-regulator.c +++ b/drivers/regulator/mt6359-regulator.c @@ -951,9 +951,12 @@ static int mt6359_regulator_probe(struct platform_device *pdev) struct regulator_config config = {}; struct regulator_dev *rdev; struct mt6359_regulator_info *mt6359_info; - int i, hw_ver; + int i, hw_ver, ret; + + ret = regmap_read(mt6397->regmap, MT6359P_HWCID, &hw_ver); + if (ret) + return ret; - regmap_read(mt6397->regmap, MT6359P_HWCID, &hw_ver); if (hw_ver >= MT6359P_CHIP_VER) mt6359_info = mt6359p_regulators; else diff --git a/drivers/regulator/pca9450-regulator.c b/drivers/regulator/pca9450-regulator.c index 87a746dcb516..e75dd92f86ca 100644 --- a/drivers/regulator/pca9450-regulator.c +++ b/drivers/regulator/pca9450-regulator.c @@ -264,7 +264,7 @@ static const struct pca9450_regulator_desc pca9450a_regulators[] = { .vsel_reg = PCA9450_REG_BUCK2OUT_DVS0, .vsel_mask = BUCK2OUT_DVS0_MASK, .enable_reg = PCA9450_REG_BUCK2CTRL, - .enable_mask = BUCK1_ENMODE_MASK, + .enable_mask = BUCK2_ENMODE_MASK, .ramp_reg = PCA9450_REG_BUCK2CTRL, .ramp_mask = BUCK2_RAMP_MASK, .ramp_delay_table = pca9450_dvs_buck_ramp_table, @@ -502,7 +502,7 @@ static const struct pca9450_regulator_desc pca9450bc_regulators[] = { .vsel_reg = PCA9450_REG_BUCK2OUT_DVS0, .vsel_mask = BUCK2OUT_DVS0_MASK, .enable_reg = PCA9450_REG_BUCK2CTRL, - .enable_mask = BUCK1_ENMODE_MASK, + .enable_mask = BUCK2_ENMODE_MASK, .ramp_reg = PCA9450_REG_BUCK2CTRL, .ramp_mask = BUCK2_RAMP_MASK, .ramp_delay_table = pca9450_dvs_buck_ramp_table, diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index ade1369fe5ed..113c509bf6d0 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -127,6 +127,8 @@ static int prepare_itcw(struct itcw *, unsigned int, unsigned int, int, struct dasd_device *, struct dasd_device *, unsigned int, int, unsigned int, unsigned int, unsigned int, unsigned int); +static int dasd_eckd_query_pprc_status(struct dasd_device *, + struct dasd_pprc_data_sc4 *); /* initial attempt at a probe function. this can be simplified once * the other detection code is gone */ @@ -3733,6 +3735,26 @@ static int count_exts(unsigned int from, unsigned int to, int trks_per_ext) return count; } +static int dasd_in_copy_relation(struct dasd_device *device) +{ + struct dasd_pprc_data_sc4 *temp; + int rc; + + if (!dasd_eckd_pprc_enabled(device)) + return 0; + + temp = kzalloc(sizeof(*temp), GFP_KERNEL); + if (!temp) + return -ENOMEM; + + rc = dasd_eckd_query_pprc_status(device, temp); + if (!rc) + rc = temp->dev_info[0].state; + + kfree(temp); + return rc; +} + /* * Release allocated space for a given range or an entire volume. */ @@ -3749,6 +3771,7 @@ dasd_eckd_dso_ras(struct dasd_device *device, struct dasd_block *block, int cur_to_trk, cur_from_trk; struct dasd_ccw_req *cqr; u32 beg_cyl, end_cyl; + int copy_relation; struct ccw1 *ccw; int trks_per_ext; size_t ras_size; @@ -3760,6 +3783,10 @@ dasd_eckd_dso_ras(struct dasd_device *device, struct dasd_block *block, if (dasd_eckd_ras_sanity_checks(device, first_trk, last_trk)) return ERR_PTR(-EINVAL); + copy_relation = dasd_in_copy_relation(device); + if (copy_relation < 0) + return ERR_PTR(copy_relation); + rq = req ? blk_mq_rq_to_pdu(req) : NULL; features = &private->features; @@ -3788,9 +3815,11 @@ dasd_eckd_dso_ras(struct dasd_device *device, struct dasd_block *block, /* * This bit guarantees initialisation of tracks within an extent that is * not fully specified, but is only supported with a certain feature - * subset. + * subset and for devices not in a copy relation. */ - ras_data->op_flags.guarantee_init = !!(features->feature[56] & 0x01); + if (features->feature[56] & 0x01 && !copy_relation) + ras_data->op_flags.guarantee_init = 1; + ras_data->lss = private->conf.ned->ID; ras_data->dev_addr = private->conf.ned->unit_addr; ras_data->nr_exts = nr_exts; diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index 8eb089b99cde..d5c43e9b5128 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -1111,6 +1111,8 @@ static void io_subchannel_verify(struct subchannel *sch) cdev = sch_get_cdev(sch); if (cdev) dev_fsm_event(cdev, DEV_EVENT_VERIFY); + else + css_schedule_eval(sch->schid); } static void io_subchannel_terminate_path(struct subchannel *sch, u8 mask) diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h index 5ea6249d8180..641f0dbb65a9 100644 --- a/drivers/s390/cio/qdio.h +++ b/drivers/s390/cio/qdio.h @@ -95,7 +95,7 @@ static inline int do_sqbs(u64 token, unsigned char state, int queue, " lgr 1,%[token]\n" " .insn rsy,0xeb000000008a,%[qs],%[ccq],0(%[state])" : [ccq] "+&d" (_ccq), [qs] "+&d" (_queuestart) - : [state] "d" ((unsigned long)state), [token] "d" (token) + : [state] "a" ((unsigned long)state), [token] "d" (token) : "memory", "cc", "1"); *count = _ccq & 0xff; *start = _queuestart & 0xff; diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index 5a05d1cdfec2..a8def50c149b 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -1293,6 +1293,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, return PTR_ERR(kkey); rc = pkey_keyblob2pkey(kkey, ktp.keylen, &ktp.protkey); DEBUG_DBG("%s pkey_keyblob2pkey()=%d\n", __func__, rc); + memzero_explicit(kkey, ktp.keylen); kfree(kkey); if (rc) break; @@ -1426,6 +1427,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, kkey, ktp.keylen, &ktp.protkey); DEBUG_DBG("%s pkey_keyblob2pkey2()=%d\n", __func__, rc); kfree(apqns); + memzero_explicit(kkey, ktp.keylen); kfree(kkey); if (rc) break; @@ -1552,6 +1554,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, protkey, &protkeylen); DEBUG_DBG("%s pkey_keyblob2pkey3()=%d\n", __func__, rc); kfree(apqns); + memzero_explicit(kkey, ktp.keylen); kfree(kkey); if (rc) { kfree(protkey); diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c index 8acb9eba691b..1399b5dc646c 100644 --- a/drivers/s390/net/ism_drv.c +++ b/drivers/s390/net/ism_drv.c @@ -660,7 +660,7 @@ static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (ret) goto err_disable; - ret = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)); + ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (ret) goto err_resource; diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index df5e5b7fdcfe..84aa3571be6d 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -3796,6 +3796,7 @@ struct qla_qpair { uint64_t retry_term_jiff; struct qla_tgt_counters tgt_counters; uint16_t cpuid; + bool cpu_mapped; struct qla_fw_resources fwres ____cacheline_aligned; struct qla_buf_pool buf_pool; u32 cmd_cnt; diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index ec0423ec6681..1a955c3ff3d6 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -9426,6 +9426,9 @@ struct qla_qpair *qla2xxx_create_qpair(struct scsi_qla_host *vha, int qos, qpair->rsp->req = qpair->req; qpair->rsp->qpair = qpair; + if (!qpair->cpu_mapped) + qla_cpu_update(qpair, raw_smp_processor_id()); + if (IS_T10_PI_CAPABLE(ha) && ql2xenabledif) { if (ha->fw_attributes & BIT_4) qpair->difdix_supported = 1; diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h index cce6e425c121..7b42558a8839 100644 --- a/drivers/scsi/qla2xxx/qla_inline.h +++ b/drivers/scsi/qla2xxx/qla_inline.h @@ -539,11 +539,14 @@ qla_mapq_init_qp_cpu_map(struct qla_hw_data *ha, if (!ha->qp_cpu_map) return; mask = pci_irq_get_affinity(ha->pdev, msix->vector_base0); + if (!mask) + return; qpair->cpuid = cpumask_first(mask); for_each_cpu(cpu, mask) { ha->qp_cpu_map[cpu] = qpair; } msix->cpuid = qpair->cpuid; + qpair->cpu_mapped = true; } static inline void diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 71feda2cdb63..245e3a5d81fd 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -3770,6 +3770,9 @@ void qla24xx_process_response_queue(struct scsi_qla_host *vha, if (rsp->qpair->cpuid != smp_processor_id() || !rsp->qpair->rcv_intr) { rsp->qpair->rcv_intr = 1; + + if (!rsp->qpair->cpu_mapped) + qla_cpu_update(rsp->qpair, raw_smp_processor_id()); } #define __update_rsp_in(_is_shadow_hba, _rsp, _rsp_in) \ diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index b7c569a42aa4..0226c9279cef 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1463,6 +1463,8 @@ static int scsi_dispatch_cmd(struct scsi_cmnd *cmd) struct Scsi_Host *host = cmd->device->host; int rtn = 0; + atomic_inc(&cmd->device->iorequest_cnt); + /* check if the device is still usable */ if (unlikely(cmd->device->sdev_state == SDEV_DEL)) { /* in SDEV_DEL we error all commands. DID_NO_CONNECT @@ -1483,6 +1485,7 @@ static int scsi_dispatch_cmd(struct scsi_cmnd *cmd) */ SCSI_LOG_MLQUEUE(3, scmd_printk(KERN_INFO, cmd, "queuecommand : device blocked\n")); + atomic_dec(&cmd->device->iorequest_cnt); return SCSI_MLQUEUE_DEVICE_BUSY; } @@ -1515,6 +1518,7 @@ static int scsi_dispatch_cmd(struct scsi_cmnd *cmd) trace_scsi_dispatch_cmd_start(cmd); rtn = host->hostt->queuecommand(host, cmd); if (rtn) { + atomic_dec(&cmd->device->iorequest_cnt); trace_scsi_dispatch_cmd_error(cmd, rtn); if (rtn != SCSI_MLQUEUE_DEVICE_BUSY && rtn != SCSI_MLQUEUE_TARGET_BUSY) @@ -1761,7 +1765,6 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx, goto out_dec_host_busy; } - atomic_inc(&cmd->device->iorequest_cnt); return BLK_STS_OK; out_dec_host_busy: diff --git a/drivers/scsi/stex.c b/drivers/scsi/stex.c index 5b230e149c3d..8ffb75be99bc 100644 --- a/drivers/scsi/stex.c +++ b/drivers/scsi/stex.c @@ -109,7 +109,9 @@ enum { TASK_ATTRIBUTE_HEADOFQUEUE = 0x1, TASK_ATTRIBUTE_ORDERED = 0x2, TASK_ATTRIBUTE_ACA = 0x4, +}; +enum { SS_STS_NORMAL = 0x80000000, SS_STS_DONE = 0x40000000, SS_STS_HANDSHAKE = 0x20000000, @@ -121,7 +123,9 @@ enum { SS_I2H_REQUEST_RESET = 0x2000, SS_MU_OPERATIONAL = 0x80000000, +}; +enum { STEX_CDB_LENGTH = 16, STATUS_VAR_LEN = 128, diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index d9ce379c4d2e..e6bc622954cf 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1780,7 +1780,7 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) length = scsi_bufflen(scmnd); payload = (struct vmbus_packet_mpb_array *)&cmd_request->mpb; - payload_sz = sizeof(cmd_request->mpb); + payload_sz = 0; if (scsi_sg_count(scmnd)) { unsigned long offset_in_hvpg = offset_in_hvpage(sgl->offset); @@ -1789,10 +1789,10 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) unsigned long hvpfn, hvpfns_to_add; int j, i = 0, sg_count; - if (hvpg_count > MAX_PAGE_BUFFER_COUNT) { + payload_sz = (hvpg_count * sizeof(u64) + + sizeof(struct vmbus_packet_mpb_array)); - payload_sz = (hvpg_count * sizeof(u64) + - sizeof(struct vmbus_packet_mpb_array)); + if (hvpg_count > MAX_PAGE_BUFFER_COUNT) { payload = kzalloc(payload_sz, GFP_ATOMIC); if (!payload) return SCSI_MLQUEUE_DEVICE_BUSY; diff --git a/drivers/soc/fsl/qe/Kconfig b/drivers/soc/fsl/qe/Kconfig index 7268c2fbcbc1..e0d096607fef 100644 --- a/drivers/soc/fsl/qe/Kconfig +++ b/drivers/soc/fsl/qe/Kconfig @@ -36,7 +36,7 @@ config UCC config CPM_TSA tristate "CPM TSA support" depends on OF && HAS_IOMEM - depends on CPM1 || COMPILE_TEST + depends on CPM1 || (CPM && COMPILE_TEST) help Freescale CPM Time Slot Assigner (TSA) controller. @@ -47,7 +47,7 @@ config CPM_TSA config CPM_QMC tristate "CPM QMC support" depends on OF && HAS_IOMEM - depends on CPM1 || (FSL_SOC && COMPILE_TEST) + depends on CPM1 || (FSL_SOC && CPM && COMPILE_TEST) depends on CPM_TSA help Freescale CPM QUICC Multichannel Controller diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c index ac85d5562212..26e663369319 100644 --- a/drivers/spi/spi-cadence.c +++ b/drivers/spi/spi-cadence.c @@ -12,6 +12,7 @@ #include <linux/gpio/consumer.h> #include <linux/interrupt.h> #include <linux/io.h> +#include <linux/kernel.h> #include <linux/module.h> #include <linux/of_irq.h> #include <linux/of_address.h> @@ -301,49 +302,43 @@ static int cdns_spi_setup_transfer(struct spi_device *spi, } /** - * cdns_spi_fill_tx_fifo - Fills the TX FIFO with as many bytes as possible + * cdns_spi_process_fifo - Fills the TX FIFO, and drain the RX FIFO * @xspi: Pointer to the cdns_spi structure + * @ntx: Number of bytes to pack into the TX FIFO + * @nrx: Number of bytes to drain from the RX FIFO */ -static void cdns_spi_fill_tx_fifo(struct cdns_spi *xspi) +static void cdns_spi_process_fifo(struct cdns_spi *xspi, int ntx, int nrx) { - unsigned long trans_cnt = 0; + ntx = clamp(ntx, 0, xspi->tx_bytes); + nrx = clamp(nrx, 0, xspi->rx_bytes); - while ((trans_cnt < xspi->tx_fifo_depth) && - (xspi->tx_bytes > 0)) { + xspi->tx_bytes -= ntx; + xspi->rx_bytes -= nrx; + while (ntx || nrx) { /* When xspi in busy condition, bytes may send failed, * then spi control did't work thoroughly, add one byte delay */ - if (cdns_spi_read(xspi, CDNS_SPI_ISR) & - CDNS_SPI_IXR_TXFULL) + if (cdns_spi_read(xspi, CDNS_SPI_ISR) & CDNS_SPI_IXR_TXFULL) udelay(10); - if (xspi->txbuf) - cdns_spi_write(xspi, CDNS_SPI_TXD, *xspi->txbuf++); - else - cdns_spi_write(xspi, CDNS_SPI_TXD, 0); + if (ntx) { + if (xspi->txbuf) + cdns_spi_write(xspi, CDNS_SPI_TXD, *xspi->txbuf++); + else + cdns_spi_write(xspi, CDNS_SPI_TXD, 0); - xspi->tx_bytes--; - trans_cnt++; - } -} + ntx--; + } -/** - * cdns_spi_read_rx_fifo - Reads the RX FIFO with as many bytes as possible - * @xspi: Pointer to the cdns_spi structure - * @count: Read byte count - */ -static void cdns_spi_read_rx_fifo(struct cdns_spi *xspi, unsigned long count) -{ - u8 data; - - /* Read out the data from the RX FIFO */ - while (count > 0) { - data = cdns_spi_read(xspi, CDNS_SPI_RXD); - if (xspi->rxbuf) - *xspi->rxbuf++ = data; - xspi->rx_bytes--; - count--; + if (nrx) { + u8 data = cdns_spi_read(xspi, CDNS_SPI_RXD); + + if (xspi->rxbuf) + *xspi->rxbuf++ = data; + + nrx--; + } } } @@ -381,33 +376,22 @@ static irqreturn_t cdns_spi_irq(int irq, void *dev_id) spi_finalize_current_transfer(ctlr); status = IRQ_HANDLED; } else if (intr_status & CDNS_SPI_IXR_TXOW) { - int trans_cnt = cdns_spi_read(xspi, CDNS_SPI_THLD); + int threshold = cdns_spi_read(xspi, CDNS_SPI_THLD); + int trans_cnt = xspi->rx_bytes - xspi->tx_bytes; + + if (threshold > 1) + trans_cnt -= threshold; + /* Set threshold to one if number of pending are * less than half fifo */ if (xspi->tx_bytes < xspi->tx_fifo_depth >> 1) cdns_spi_write(xspi, CDNS_SPI_THLD, 1); - while (trans_cnt) { - cdns_spi_read_rx_fifo(xspi, 1); - - if (xspi->tx_bytes) { - if (xspi->txbuf) - cdns_spi_write(xspi, CDNS_SPI_TXD, - *xspi->txbuf++); - else - cdns_spi_write(xspi, CDNS_SPI_TXD, 0); - xspi->tx_bytes--; - } - trans_cnt--; - } - if (!xspi->tx_bytes) { - /* Fixed delay due to controller limitation with - * RX_NEMPTY incorrect status - * Xilinx AR:65885 contains more details - */ - udelay(10); - cdns_spi_read_rx_fifo(xspi, xspi->rx_bytes); + if (xspi->tx_bytes) { + cdns_spi_process_fifo(xspi, trans_cnt, trans_cnt); + } else { + cdns_spi_process_fifo(xspi, 0, trans_cnt); cdns_spi_write(xspi, CDNS_SPI_IDR, CDNS_SPI_IXR_DEFAULT); spi_finalize_current_transfer(ctlr); @@ -450,16 +434,17 @@ static int cdns_transfer_one(struct spi_controller *ctlr, xspi->tx_bytes = transfer->len; xspi->rx_bytes = transfer->len; - if (!spi_controller_is_slave(ctlr)) + if (!spi_controller_is_slave(ctlr)) { cdns_spi_setup_transfer(spi, transfer); + } else { + /* Set TX empty threshold to half of FIFO depth + * only if TX bytes are more than half FIFO depth. + */ + if (xspi->tx_bytes > xspi->tx_fifo_depth) + cdns_spi_write(xspi, CDNS_SPI_THLD, xspi->tx_fifo_depth >> 1); + } - /* Set TX empty threshold to half of FIFO depth - * only if TX bytes are more than half FIFO depth. - */ - if (xspi->tx_bytes > (xspi->tx_fifo_depth >> 1)) - cdns_spi_write(xspi, CDNS_SPI_THLD, xspi->tx_fifo_depth >> 1); - - cdns_spi_fill_tx_fifo(xspi); + cdns_spi_process_fifo(xspi, xspi->tx_fifo_depth, 0); spi_transfer_delay_exec(transfer); cdns_spi_write(xspi, CDNS_SPI_IER, CDNS_SPI_IXR_DEFAULT); diff --git a/drivers/spi/spi-dw-mmio.c b/drivers/spi/spi-dw-mmio.c index 5e6faa98aa85..5f2aee69c1c1 100644 --- a/drivers/spi/spi-dw-mmio.c +++ b/drivers/spi/spi-dw-mmio.c @@ -264,17 +264,17 @@ static void dw_spi_elba_set_cs(struct spi_device *spi, bool enable) struct regmap *syscon = dwsmmio->priv; u8 cs; - cs = spi->chip_select; + cs = spi_get_chipselect(spi, 0); if (cs < 2) - dw_spi_elba_override_cs(syscon, spi->chip_select, enable); + dw_spi_elba_override_cs(syscon, spi_get_chipselect(spi, 0), enable); /* * The DW SPI controller needs a native CS bit selected to start * the serial engine. */ - spi->chip_select = 0; + spi_set_chipselect(spi, 0, 0); dw_spi_set_cs(spi, enable); - spi->chip_select = cs; + spi_get_chipselect(spi, cs); } static int dw_spi_elba_init(struct platform_device *pdev, diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c index f2341ab99556..4b70038ceb6b 100644 --- a/drivers/spi/spi-fsl-lpspi.c +++ b/drivers/spi/spi-fsl-lpspi.c @@ -910,9 +910,14 @@ static int fsl_lpspi_probe(struct platform_device *pdev) ret = fsl_lpspi_dma_init(&pdev->dev, fsl_lpspi, controller); if (ret == -EPROBE_DEFER) goto out_pm_get; - if (ret < 0) dev_err(&pdev->dev, "dma setup error %d, use pio\n", ret); + else + /* + * disable LPSPI module IRQ when enable DMA mode successfully, + * to prevent the unexpected LPSPI module IRQ events. + */ + disable_irq(irq); ret = devm_spi_register_controller(&pdev->dev, controller); if (ret < 0) { diff --git a/drivers/spi/spi-geni-qcom.c b/drivers/spi/spi-geni-qcom.c index ba7be505ec4e..a98b781b103a 100644 --- a/drivers/spi/spi-geni-qcom.c +++ b/drivers/spi/spi-geni-qcom.c @@ -294,6 +294,8 @@ static void spi_geni_set_cs(struct spi_device *slv, bool set_flag) mas->cs_flag = set_flag; /* set xfer_mode to FIFO to complete cs_done in isr */ mas->cur_xfer_mode = GENI_SE_FIFO; + geni_se_select_mode(se, mas->cur_xfer_mode); + reinit_completion(&mas->cs_done); if (set_flag) geni_se_setup_m_cmd(se, SPI_CS_ASSERT, 0); diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c index 21c321f43766..d7432e2219d8 100644 --- a/drivers/spi/spi-mt65xx.c +++ b/drivers/spi/spi-mt65xx.c @@ -1275,6 +1275,9 @@ static int mtk_spi_remove(struct platform_device *pdev) struct mtk_spi *mdata = spi_master_get_devdata(master); int ret; + if (mdata->use_spimem && !completion_done(&mdata->spimem_done)) + complete(&mdata->spimem_done); + ret = pm_runtime_resume_and_get(&pdev->dev); if (ret < 0) return ret; diff --git a/drivers/spi/spi-qup.c b/drivers/spi/spi-qup.c index 944ef6b42bce..00e5e88e72c4 100644 --- a/drivers/spi/spi-qup.c +++ b/drivers/spi/spi-qup.c @@ -1028,23 +1028,8 @@ static int spi_qup_probe(struct platform_device *pdev) return -ENXIO; } - ret = clk_prepare_enable(cclk); - if (ret) { - dev_err(dev, "cannot enable core clock\n"); - return ret; - } - - ret = clk_prepare_enable(iclk); - if (ret) { - clk_disable_unprepare(cclk); - dev_err(dev, "cannot enable iface clock\n"); - return ret; - } - master = spi_alloc_master(dev, sizeof(struct spi_qup)); if (!master) { - clk_disable_unprepare(cclk); - clk_disable_unprepare(iclk); dev_err(dev, "cannot allocate master\n"); return -ENOMEM; } @@ -1092,6 +1077,19 @@ static int spi_qup_probe(struct platform_device *pdev) spin_lock_init(&controller->lock); init_completion(&controller->done); + ret = clk_prepare_enable(cclk); + if (ret) { + dev_err(dev, "cannot enable core clock\n"); + goto error_dma; + } + + ret = clk_prepare_enable(iclk); + if (ret) { + clk_disable_unprepare(cclk); + dev_err(dev, "cannot enable iface clock\n"); + goto error_dma; + } + iomode = readl_relaxed(base + QUP_IO_M_MODES); size = QUP_IO_M_OUTPUT_BLOCK_SIZE(iomode); @@ -1121,7 +1119,7 @@ static int spi_qup_probe(struct platform_device *pdev) ret = spi_qup_set_state(controller, QUP_STATE_RESET); if (ret) { dev_err(dev, "cannot set RESET state\n"); - goto error_dma; + goto error_clk; } writel_relaxed(0, base + QUP_OPERATIONAL); @@ -1145,7 +1143,7 @@ static int spi_qup_probe(struct platform_device *pdev) ret = devm_request_irq(dev, irq, spi_qup_qup_irq, IRQF_TRIGGER_HIGH, pdev->name, controller); if (ret) - goto error_dma; + goto error_clk; pm_runtime_set_autosuspend_delay(dev, MSEC_PER_SEC); pm_runtime_use_autosuspend(dev); @@ -1160,11 +1158,12 @@ static int spi_qup_probe(struct platform_device *pdev) disable_pm: pm_runtime_disable(&pdev->dev); +error_clk: + clk_disable_unprepare(cclk); + clk_disable_unprepare(iclk); error_dma: spi_qup_release_dma(master); error: - clk_disable_unprepare(cclk); - clk_disable_unprepare(iclk); spi_master_put(master); return ret; } diff --git a/drivers/staging/media/atomisp/i2c/atomisp-ov2680.c b/drivers/staging/media/atomisp/i2c/atomisp-ov2680.c index 63de214916f5..c079368019e8 100644 --- a/drivers/staging/media/atomisp/i2c/atomisp-ov2680.c +++ b/drivers/staging/media/atomisp/i2c/atomisp-ov2680.c @@ -373,7 +373,7 @@ static int ov2680_get_fmt(struct v4l2_subdev *sd, static int ov2680_detect(struct i2c_client *client) { struct i2c_adapter *adapter = client->adapter; - u32 high, low; + u32 high = 0, low = 0; int ret; u16 id; u8 revision; @@ -383,7 +383,7 @@ static int ov2680_detect(struct i2c_client *client) ret = ov_read_reg8(client, OV2680_SC_CMMN_CHIP_ID_H, &high); if (ret) { - dev_err(&client->dev, "sensor_id_high = 0x%x\n", high); + dev_err(&client->dev, "sensor_id_high read failed (%d)\n", ret); return -ENODEV; } ret = ov_read_reg8(client, OV2680_SC_CMMN_CHIP_ID_L, &low); diff --git a/drivers/staging/media/imx/imx8mq-mipi-csi2.c b/drivers/staging/media/imx/imx8mq-mipi-csi2.c index 32700cb8bc4d..ca2efcc21efe 100644 --- a/drivers/staging/media/imx/imx8mq-mipi-csi2.c +++ b/drivers/staging/media/imx/imx8mq-mipi-csi2.c @@ -354,7 +354,7 @@ static int imx8mq_mipi_csi_start_stream(struct csi_state *state, struct v4l2_subdev_state *sd_state) { int ret; - u32 hs_settle; + u32 hs_settle = 0; ret = imx8mq_mipi_csi_sw_reset(state); if (ret) diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 834cce50f9b0..b516c2893420 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -364,8 +364,6 @@ struct iscsi_np *iscsit_add_np( init_completion(&np->np_restart_comp); INIT_LIST_HEAD(&np->np_list); - timer_setup(&np->np_login_timer, iscsi_handle_login_thread_timeout, 0); - ret = iscsi_target_setup_login_socket(np, sockaddr); if (ret != 0) { kfree(np); diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index 274bdd7845ca..90b870f234f0 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -811,59 +811,6 @@ void iscsi_post_login_handler( iscsit_dec_conn_usage_count(conn); } -void iscsi_handle_login_thread_timeout(struct timer_list *t) -{ - struct iscsi_np *np = from_timer(np, t, np_login_timer); - - spin_lock_bh(&np->np_thread_lock); - pr_err("iSCSI Login timeout on Network Portal %pISpc\n", - &np->np_sockaddr); - - if (np->np_login_timer_flags & ISCSI_TF_STOP) { - spin_unlock_bh(&np->np_thread_lock); - return; - } - - if (np->np_thread) - send_sig(SIGINT, np->np_thread, 1); - - np->np_login_timer_flags &= ~ISCSI_TF_RUNNING; - spin_unlock_bh(&np->np_thread_lock); -} - -static void iscsi_start_login_thread_timer(struct iscsi_np *np) -{ - /* - * This used the TA_LOGIN_TIMEOUT constant because at this - * point we do not have access to ISCSI_TPG_ATTRIB(tpg)->login_timeout - */ - spin_lock_bh(&np->np_thread_lock); - np->np_login_timer_flags &= ~ISCSI_TF_STOP; - np->np_login_timer_flags |= ISCSI_TF_RUNNING; - mod_timer(&np->np_login_timer, jiffies + TA_LOGIN_TIMEOUT * HZ); - - pr_debug("Added timeout timer to iSCSI login request for" - " %u seconds.\n", TA_LOGIN_TIMEOUT); - spin_unlock_bh(&np->np_thread_lock); -} - -static void iscsi_stop_login_thread_timer(struct iscsi_np *np) -{ - spin_lock_bh(&np->np_thread_lock); - if (!(np->np_login_timer_flags & ISCSI_TF_RUNNING)) { - spin_unlock_bh(&np->np_thread_lock); - return; - } - np->np_login_timer_flags |= ISCSI_TF_STOP; - spin_unlock_bh(&np->np_thread_lock); - - del_timer_sync(&np->np_login_timer); - - spin_lock_bh(&np->np_thread_lock); - np->np_login_timer_flags &= ~ISCSI_TF_RUNNING; - spin_unlock_bh(&np->np_thread_lock); -} - int iscsit_setup_np( struct iscsi_np *np, struct sockaddr_storage *sockaddr) @@ -1123,10 +1070,13 @@ static struct iscsit_conn *iscsit_alloc_conn(struct iscsi_np *np) spin_lock_init(&conn->nopin_timer_lock); spin_lock_init(&conn->response_queue_lock); spin_lock_init(&conn->state_lock); + spin_lock_init(&conn->login_worker_lock); + spin_lock_init(&conn->login_timer_lock); timer_setup(&conn->nopin_response_timer, iscsit_handle_nopin_response_timeout, 0); timer_setup(&conn->nopin_timer, iscsit_handle_nopin_timeout, 0); + timer_setup(&conn->login_timer, iscsit_login_timeout, 0); if (iscsit_conn_set_transport(conn, np->np_transport) < 0) goto free_conn; @@ -1304,7 +1254,7 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) goto new_sess_out; } - iscsi_start_login_thread_timer(np); + iscsit_start_login_timer(conn, current); pr_debug("Moving to TARG_CONN_STATE_XPT_UP.\n"); conn->conn_state = TARG_CONN_STATE_XPT_UP; @@ -1417,8 +1367,6 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) if (ret < 0) goto new_sess_out; - iscsi_stop_login_thread_timer(np); - if (ret == 1) { tpg_np = conn->tpg_np; @@ -1434,7 +1382,7 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) new_sess_out: new_sess = true; old_sess_out: - iscsi_stop_login_thread_timer(np); + iscsit_stop_login_timer(conn); tpg_np = conn->tpg_np; iscsi_target_login_sess_out(conn, zero_tsih, new_sess); new_sess = false; @@ -1448,7 +1396,6 @@ old_sess_out: return 1; exit: - iscsi_stop_login_thread_timer(np); spin_lock_bh(&np->np_thread_lock); np->np_thread_state = ISCSI_NP_THREAD_EXIT; spin_unlock_bh(&np->np_thread_lock); diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c index 24040c118e49..fa3fb5f4e6bc 100644 --- a/drivers/target/iscsi/iscsi_target_nego.c +++ b/drivers/target/iscsi/iscsi_target_nego.c @@ -535,25 +535,6 @@ static void iscsi_target_login_drop(struct iscsit_conn *conn, struct iscsi_login iscsi_target_login_sess_out(conn, zero_tsih, true); } -struct conn_timeout { - struct timer_list timer; - struct iscsit_conn *conn; -}; - -static void iscsi_target_login_timeout(struct timer_list *t) -{ - struct conn_timeout *timeout = from_timer(timeout, t, timer); - struct iscsit_conn *conn = timeout->conn; - - pr_debug("Entering iscsi_target_login_timeout >>>>>>>>>>>>>>>>>>>\n"); - - if (conn->login_kworker) { - pr_debug("Sending SIGINT to conn->login_kworker %s/%d\n", - conn->login_kworker->comm, conn->login_kworker->pid); - send_sig(SIGINT, conn->login_kworker, 1); - } -} - static void iscsi_target_do_login_rx(struct work_struct *work) { struct iscsit_conn *conn = container_of(work, @@ -562,12 +543,15 @@ static void iscsi_target_do_login_rx(struct work_struct *work) struct iscsi_np *np = login->np; struct iscsi_portal_group *tpg = conn->tpg; struct iscsi_tpg_np *tpg_np = conn->tpg_np; - struct conn_timeout timeout; int rc, zero_tsih = login->zero_tsih; bool state; pr_debug("entering iscsi_target_do_login_rx, conn: %p, %s:%d\n", conn, current->comm, current->pid); + + spin_lock(&conn->login_worker_lock); + set_bit(LOGIN_FLAGS_WORKER_RUNNING, &conn->login_flags); + spin_unlock(&conn->login_worker_lock); /* * If iscsi_target_do_login_rx() has been invoked by ->sk_data_ready() * before initial PDU processing in iscsi_target_start_negotiation() @@ -597,19 +581,16 @@ static void iscsi_target_do_login_rx(struct work_struct *work) goto err; } - conn->login_kworker = current; allow_signal(SIGINT); - - timeout.conn = conn; - timer_setup_on_stack(&timeout.timer, iscsi_target_login_timeout, 0); - mod_timer(&timeout.timer, jiffies + TA_LOGIN_TIMEOUT * HZ); - pr_debug("Starting login timer for %s/%d\n", current->comm, current->pid); + rc = iscsit_set_login_timer_kworker(conn, current); + if (rc < 0) { + /* The login timer has already expired */ + pr_debug("iscsi_target_do_login_rx, login failed\n"); + goto err; + } rc = conn->conn_transport->iscsit_get_login_rx(conn, login); - del_timer_sync(&timeout.timer); - destroy_timer_on_stack(&timeout.timer); flush_signals(current); - conn->login_kworker = NULL; if (rc < 0) goto err; @@ -646,7 +627,17 @@ static void iscsi_target_do_login_rx(struct work_struct *work) if (iscsi_target_sk_check_and_clear(conn, LOGIN_FLAGS_WRITE_ACTIVE)) goto err; + + /* + * Set the login timer thread pointer to NULL to prevent the + * login process from getting stuck if the initiator + * stops sending data. + */ + rc = iscsit_set_login_timer_kworker(conn, NULL); + if (rc < 0) + goto err; } else if (rc == 1) { + iscsit_stop_login_timer(conn); cancel_delayed_work(&conn->login_work); iscsi_target_nego_release(conn); iscsi_post_login_handler(np, conn, zero_tsih); @@ -656,6 +647,7 @@ static void iscsi_target_do_login_rx(struct work_struct *work) err: iscsi_target_restore_sock_callbacks(conn); + iscsit_stop_login_timer(conn); cancel_delayed_work(&conn->login_work); iscsi_target_login_drop(conn, login); iscsit_deaccess_np(np, tpg, tpg_np); @@ -1130,6 +1122,7 @@ int iscsi_target_locate_portal( iscsi_target_set_sock_callbacks(conn); login->np = np; + conn->tpg = NULL; login_req = (struct iscsi_login_req *) login->req; payload_length = ntoh24(login_req->dlength); @@ -1197,7 +1190,6 @@ int iscsi_target_locate_portal( */ sessiontype = strncmp(s_buf, DISCOVERY, 9); if (!sessiontype) { - conn->tpg = iscsit_global->discovery_tpg; if (!login->leading_connection) goto get_target; @@ -1214,9 +1206,11 @@ int iscsi_target_locate_portal( * Serialize access across the discovery struct iscsi_portal_group to * process login attempt. */ + conn->tpg = iscsit_global->discovery_tpg; if (iscsit_access_np(np, conn->tpg) < 0) { iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR, ISCSI_LOGIN_STATUS_SVC_UNAVAILABLE); + conn->tpg = NULL; ret = -1; goto out; } @@ -1368,14 +1362,30 @@ int iscsi_target_start_negotiation( * and perform connection cleanup now. */ ret = iscsi_target_do_login(conn, login); - if (!ret && iscsi_target_sk_check_and_clear(conn, LOGIN_FLAGS_INITIAL_PDU)) - ret = -1; + if (!ret) { + spin_lock(&conn->login_worker_lock); + + if (iscsi_target_sk_check_and_clear(conn, LOGIN_FLAGS_INITIAL_PDU)) + ret = -1; + else if (!test_bit(LOGIN_FLAGS_WORKER_RUNNING, &conn->login_flags)) { + if (iscsit_set_login_timer_kworker(conn, NULL) < 0) { + /* + * The timeout has expired already. + * Schedule login_work to perform the cleanup. + */ + schedule_delayed_work(&conn->login_work, 0); + } + } + + spin_unlock(&conn->login_worker_lock); + } if (ret < 0) { iscsi_target_restore_sock_callbacks(conn); iscsi_remove_failed_auth_entry(conn); } if (ret != 0) { + iscsit_stop_login_timer(conn); cancel_delayed_work_sync(&conn->login_work); iscsi_target_nego_release(conn); } diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c index 26dc8ed3045b..b14835fcb033 100644 --- a/drivers/target/iscsi/iscsi_target_util.c +++ b/drivers/target/iscsi/iscsi_target_util.c @@ -1040,6 +1040,57 @@ void iscsit_stop_nopin_timer(struct iscsit_conn *conn) spin_unlock_bh(&conn->nopin_timer_lock); } +void iscsit_login_timeout(struct timer_list *t) +{ + struct iscsit_conn *conn = from_timer(conn, t, login_timer); + struct iscsi_login *login = conn->login; + + pr_debug("Entering iscsi_target_login_timeout >>>>>>>>>>>>>>>>>>>\n"); + + spin_lock_bh(&conn->login_timer_lock); + login->login_failed = 1; + + if (conn->login_kworker) { + pr_debug("Sending SIGINT to conn->login_kworker %s/%d\n", + conn->login_kworker->comm, conn->login_kworker->pid); + send_sig(SIGINT, conn->login_kworker, 1); + } else { + schedule_delayed_work(&conn->login_work, 0); + } + spin_unlock_bh(&conn->login_timer_lock); +} + +void iscsit_start_login_timer(struct iscsit_conn *conn, struct task_struct *kthr) +{ + pr_debug("Login timer started\n"); + + conn->login_kworker = kthr; + mod_timer(&conn->login_timer, jiffies + TA_LOGIN_TIMEOUT * HZ); +} + +int iscsit_set_login_timer_kworker(struct iscsit_conn *conn, struct task_struct *kthr) +{ + struct iscsi_login *login = conn->login; + int ret = 0; + + spin_lock_bh(&conn->login_timer_lock); + if (login->login_failed) { + /* The timer has already expired */ + ret = -1; + } else { + conn->login_kworker = kthr; + } + spin_unlock_bh(&conn->login_timer_lock); + + return ret; +} + +void iscsit_stop_login_timer(struct iscsit_conn *conn) +{ + pr_debug("Login timer stopped\n"); + timer_delete_sync(&conn->login_timer); +} + int iscsit_send_tx_data( struct iscsit_cmd *cmd, struct iscsit_conn *conn, diff --git a/drivers/target/iscsi/iscsi_target_util.h b/drivers/target/iscsi/iscsi_target_util.h index 33ea799a0850..24b8e577575a 100644 --- a/drivers/target/iscsi/iscsi_target_util.h +++ b/drivers/target/iscsi/iscsi_target_util.h @@ -56,6 +56,10 @@ extern void iscsit_handle_nopin_timeout(struct timer_list *t); extern void __iscsit_start_nopin_timer(struct iscsit_conn *); extern void iscsit_start_nopin_timer(struct iscsit_conn *); extern void iscsit_stop_nopin_timer(struct iscsit_conn *); +extern void iscsit_login_timeout(struct timer_list *t); +extern void iscsit_start_login_timer(struct iscsit_conn *, struct task_struct *kthr); +extern void iscsit_stop_login_timer(struct iscsit_conn *); +extern int iscsit_set_login_timer_kworker(struct iscsit_conn *, struct task_struct *kthr); extern int iscsit_send_tx_data(struct iscsit_cmd *, struct iscsit_conn *, int); extern int iscsit_fe_sendpage_sg(struct iscsit_cmd *, struct iscsit_conn *); extern int iscsit_tx_login_rsp(struct iscsit_conn *, u8, u8); diff --git a/drivers/tee/optee/smc_abi.c b/drivers/tee/optee/smc_abi.c index 49702cb08f4f..3861ae06d902 100644 --- a/drivers/tee/optee/smc_abi.c +++ b/drivers/tee/optee/smc_abi.c @@ -1004,8 +1004,10 @@ static u32 get_async_notif_value(optee_invoke_fn *invoke_fn, bool *value_valid, invoke_fn(OPTEE_SMC_GET_ASYNC_NOTIF_VALUE, 0, 0, 0, 0, 0, 0, 0, &res); - if (res.a0) + if (res.a0) { + *value_valid = false; return 0; + } *value_valid = (res.a2 & OPTEE_SMC_ASYNC_NOTIF_VALUE_VALID); *value_pending = (res.a2 & OPTEE_SMC_ASYNC_NOTIF_VALUE_PENDING); return res.a1; diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c index 810231b59dcd..5e1164226ada 100644 --- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c +++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c @@ -131,7 +131,7 @@ static ssize_t available_uuids_show(struct device *dev, for (i = 0; i < INT3400_THERMAL_MAXIMUM_UUID; i++) { if (priv->uuid_bitmap & (1 << i)) - length += sysfs_emit_at(buf, length, int3400_thermal_uuids[i]); + length += sysfs_emit_at(buf, length, "%s\n", int3400_thermal_uuids[i]); } return length; @@ -149,7 +149,7 @@ static ssize_t current_uuid_show(struct device *dev, for (i = 0; i <= INT3400_THERMAL_CRITICAL; i++) { if (priv->os_uuid_mask & BIT(i)) - length += sysfs_emit_at(buf, length, int3400_thermal_uuids[i]); + length += sysfs_emit_at(buf, length, "%s\n", int3400_thermal_uuids[i]); } if (length) diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index d76e923fbc6a..c0aee5dc5237 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -54,6 +54,21 @@ static int ring_interrupt_index(const struct tb_ring *ring) return bit; } +static void nhi_mask_interrupt(struct tb_nhi *nhi, int mask, int ring) +{ + if (nhi->quirks & QUIRK_AUTO_CLEAR_INT) + return; + iowrite32(mask, nhi->iobase + REG_RING_INTERRUPT_MASK_CLEAR_BASE + ring); +} + +static void nhi_clear_interrupt(struct tb_nhi *nhi, int ring) +{ + if (nhi->quirks & QUIRK_AUTO_CLEAR_INT) + ioread32(nhi->iobase + REG_RING_NOTIFY_BASE + ring); + else + iowrite32(~0, nhi->iobase + REG_RING_INT_CLEAR + ring); +} + /* * ring_interrupt_active() - activate/deactivate interrupts for a single ring * @@ -61,8 +76,8 @@ static int ring_interrupt_index(const struct tb_ring *ring) */ static void ring_interrupt_active(struct tb_ring *ring, bool active) { - int reg = REG_RING_INTERRUPT_BASE + - ring_interrupt_index(ring) / 32 * 4; + int index = ring_interrupt_index(ring) / 32 * 4; + int reg = REG_RING_INTERRUPT_BASE + index; int interrupt_bit = ring_interrupt_index(ring) & 31; int mask = 1 << interrupt_bit; u32 old, new; @@ -123,7 +138,11 @@ static void ring_interrupt_active(struct tb_ring *ring, bool active) "interrupt for %s %d is already %s\n", RING_TYPE(ring), ring->hop, active ? "enabled" : "disabled"); - iowrite32(new, ring->nhi->iobase + reg); + + if (active) + iowrite32(new, ring->nhi->iobase + reg); + else + nhi_mask_interrupt(ring->nhi, mask, index); } /* @@ -136,11 +155,11 @@ static void nhi_disable_interrupts(struct tb_nhi *nhi) int i = 0; /* disable interrupts */ for (i = 0; i < RING_INTERRUPT_REG_COUNT(nhi); i++) - iowrite32(0, nhi->iobase + REG_RING_INTERRUPT_BASE + 4 * i); + nhi_mask_interrupt(nhi, ~0, 4 * i); /* clear interrupt status bits */ for (i = 0; i < RING_NOTIFY_REG_COUNT(nhi); i++) - ioread32(nhi->iobase + REG_RING_NOTIFY_BASE + 4 * i); + nhi_clear_interrupt(nhi, 4 * i); } /* ring helper methods */ diff --git a/drivers/thunderbolt/nhi_regs.h b/drivers/thunderbolt/nhi_regs.h index faef165a919c..6ba295815477 100644 --- a/drivers/thunderbolt/nhi_regs.h +++ b/drivers/thunderbolt/nhi_regs.h @@ -93,6 +93,8 @@ struct ring_desc { #define REG_RING_INTERRUPT_BASE 0x38200 #define RING_INTERRUPT_REG_COUNT(nhi) ((31 + 2 * nhi->hop_count) / 32) +#define REG_RING_INTERRUPT_MASK_CLEAR_BASE 0x38208 + #define REG_INT_THROTTLING_RATE 0x38c00 /* Interrupt Vector Allocation */ diff --git a/drivers/tty/serial/8250/8250_bcm7271.c b/drivers/tty/serial/8250/8250_bcm7271.c index f801b1f5b46c..af0e1c070187 100644 --- a/drivers/tty/serial/8250/8250_bcm7271.c +++ b/drivers/tty/serial/8250/8250_bcm7271.c @@ -1012,7 +1012,7 @@ static int brcmuart_probe(struct platform_device *pdev) of_property_read_u32(np, "clock-frequency", &clk_rate); /* See if a Baud clock has been specified */ - baud_mux_clk = of_clk_get_by_name(np, "sw_baud"); + baud_mux_clk = devm_clk_get(dev, "sw_baud"); if (IS_ERR(baud_mux_clk)) { if (PTR_ERR(baud_mux_clk) == -EPROBE_DEFER) { ret = -EPROBE_DEFER; @@ -1032,7 +1032,7 @@ static int brcmuart_probe(struct platform_device *pdev) if (clk_rate == 0) { dev_err(dev, "clock-frequency or clk not defined\n"); ret = -EINVAL; - goto release_dma; + goto err_clk_disable; } dev_dbg(dev, "DMA is %senabled\n", priv->dma_enabled ? "" : "not "); @@ -1119,6 +1119,8 @@ err1: serial8250_unregister_port(priv->line); err: brcmuart_free_bufs(dev, priv); +err_clk_disable: + clk_disable_unprepare(baud_mux_clk); release_dma: if (priv->dma_enabled) brcmuart_arbitration(priv, 0); @@ -1133,6 +1135,7 @@ static int brcmuart_remove(struct platform_device *pdev) hrtimer_cancel(&priv->hrt); serial8250_unregister_port(priv->line); brcmuart_free_bufs(&pdev->dev, priv); + clk_disable_unprepare(priv->baud_mux_clk); if (priv->dma_enabled) brcmuart_arbitration(priv, 0); return 0; diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c index 64770c62bbec..b406cba10b0e 100644 --- a/drivers/tty/serial/8250/8250_exar.c +++ b/drivers/tty/serial/8250/8250_exar.c @@ -40,9 +40,13 @@ #define PCI_DEVICE_ID_COMMTECH_4224PCIE 0x0020 #define PCI_DEVICE_ID_COMMTECH_4228PCIE 0x0021 #define PCI_DEVICE_ID_COMMTECH_4222PCIE 0x0022 + #define PCI_DEVICE_ID_EXAR_XR17V4358 0x4358 #define PCI_DEVICE_ID_EXAR_XR17V8358 0x8358 +#define PCI_SUBDEVICE_ID_USR_2980 0x0128 +#define PCI_SUBDEVICE_ID_USR_2981 0x0129 + #define PCI_DEVICE_ID_SEALEVEL_710xC 0x1001 #define PCI_DEVICE_ID_SEALEVEL_720xC 0x1002 #define PCI_DEVICE_ID_SEALEVEL_740xC 0x1004 @@ -829,6 +833,15 @@ static const struct exar8250_board pbn_exar_XR17V8358 = { (kernel_ulong_t)&bd \ } +#define USR_DEVICE(devid, sdevid, bd) { \ + PCI_DEVICE_SUB( \ + PCI_VENDOR_ID_USR, \ + PCI_DEVICE_ID_EXAR_##devid, \ + PCI_VENDOR_ID_EXAR, \ + PCI_SUBDEVICE_ID_USR_##sdevid), 0, 0, \ + (kernel_ulong_t)&bd \ + } + static const struct pci_device_id exar_pci_tbl[] = { EXAR_DEVICE(ACCESSIO, COM_2S, pbn_exar_XR17C15x), EXAR_DEVICE(ACCESSIO, COM_4S, pbn_exar_XR17C15x), @@ -853,6 +866,10 @@ static const struct pci_device_id exar_pci_tbl[] = { IBM_DEVICE(XR17C152, SATURN_SERIAL_ONE_PORT, pbn_exar_ibm_saturn), + /* USRobotics USR298x-OEM PCI Modems */ + USR_DEVICE(XR17C152, 2980, pbn_exar_XR17C15x), + USR_DEVICE(XR17C152, 2981, pbn_exar_XR17C15x), + /* Exar Corp. XR17C15[248] Dual/Quad/Octal UART */ EXAR_DEVICE(EXAR, XR17C152, pbn_exar_XR17C15x), EXAR_DEVICE(EXAR, XR17C154, pbn_exar_XR17C15x), diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index c55be6fda0ca..e80c4f6551a1 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -1920,6 +1920,8 @@ pci_moxa_setup(struct serial_private *priv, #define PCI_SUBDEVICE_ID_SIIG_DUAL_30 0x2530 #define PCI_VENDOR_ID_ADVANTECH 0x13fe #define PCI_DEVICE_ID_INTEL_CE4100_UART 0x2e66 +#define PCI_DEVICE_ID_ADVANTECH_PCI1600 0x1600 +#define PCI_DEVICE_ID_ADVANTECH_PCI1600_1611 0x1611 #define PCI_DEVICE_ID_ADVANTECH_PCI3620 0x3620 #define PCI_DEVICE_ID_ADVANTECH_PCI3618 0x3618 #define PCI_DEVICE_ID_ADVANTECH_PCIf618 0xf618 @@ -4085,6 +4087,9 @@ static SIMPLE_DEV_PM_OPS(pciserial_pm_ops, pciserial_suspend_one, pciserial_resume_one); static const struct pci_device_id serial_pci_tbl[] = { + { PCI_VENDOR_ID_ADVANTECH, PCI_DEVICE_ID_ADVANTECH_PCI1600, + PCI_DEVICE_ID_ADVANTECH_PCI1600_1611, PCI_ANY_ID, 0, 0, + pbn_b0_4_921600 }, /* Advantech use PCI_DEVICE_ID_ADVANTECH_PCI3620 (0x3620) as 'PCI_SUBVENDOR_ID' */ { PCI_VENDOR_ID_ADVANTECH, PCI_DEVICE_ID_ADVANTECH_PCI3620, PCI_DEVICE_ID_ADVANTECH_PCI3620, 0x0001, 0, 0, diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index fe8d79c4ae95..c153ba3a018a 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -669,6 +669,7 @@ EXPORT_SYMBOL_GPL(serial8250_em485_supported); /** * serial8250_em485_config() - generic ->rs485_config() callback * @port: uart port + * @termios: termios structure * @rs485: rs485 settings * * Generic callback usable by 8250 uart drivers to activate rs485 settings diff --git a/drivers/tty/serial/8250/8250_tegra.c b/drivers/tty/serial/8250/8250_tegra.c index 2509e7f74ccf..89956bbf34d9 100644 --- a/drivers/tty/serial/8250/8250_tegra.c +++ b/drivers/tty/serial/8250/8250_tegra.c @@ -113,13 +113,15 @@ static int tegra_uart_probe(struct platform_device *pdev) ret = serial8250_register_8250_port(&port8250); if (ret < 0) - goto err_clkdisable; + goto err_ctrl_assert; platform_set_drvdata(pdev, uart); uart->line = ret; return 0; +err_ctrl_assert: + reset_control_assert(uart->rst); err_clkdisable: clk_disable_unprepare(uart->clk); diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 398e5aac2e77..3e3fb377d90d 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -762,7 +762,7 @@ config SERIAL_PMACZILOG_CONSOLE config SERIAL_CPM tristate "CPM SCC/SMC serial port support" - depends on CPM2 || CPM1 || (PPC32 && COMPILE_TEST) + depends on CPM2 || CPM1 select SERIAL_CORE help This driver supports the SCC and SMC serial ports on Motorola diff --git a/drivers/tty/serial/arc_uart.c b/drivers/tty/serial/arc_uart.c index 59e25f2b6632..4b2512eef577 100644 --- a/drivers/tty/serial/arc_uart.c +++ b/drivers/tty/serial/arc_uart.c @@ -606,10 +606,11 @@ static int arc_serial_probe(struct platform_device *pdev) } uart->baud = val; - port->membase = of_iomap(np, 0); - if (!port->membase) + port->membase = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(port->membase)) { /* No point of dev_err since UART itself is hosed here */ - return -ENXIO; + return PTR_ERR(port->membase); + } port->irq = irq_of_parse_and_map(np, 0); diff --git a/drivers/tty/serial/cpm_uart/cpm_uart.h b/drivers/tty/serial/cpm_uart/cpm_uart.h index 0577618e78c0..46c03ed71c31 100644 --- a/drivers/tty/serial/cpm_uart/cpm_uart.h +++ b/drivers/tty/serial/cpm_uart/cpm_uart.h @@ -19,8 +19,6 @@ struct gpio_desc; #include "cpm_uart_cpm2.h" #elif defined(CONFIG_CPM1) #include "cpm_uart_cpm1.h" -#elif defined(CONFIG_COMPILE_TEST) -#include "cpm_uart_cpm2.h" #endif #define SERIAL_CPM_MAJOR 204 diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index c91916e13648..7486a2b8556c 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -1495,34 +1495,36 @@ static void lpuart_break_ctl(struct uart_port *port, int break_state) static void lpuart32_break_ctl(struct uart_port *port, int break_state) { - unsigned long temp, modem; - struct tty_struct *tty; - unsigned int cflag = 0; - - tty = tty_port_tty_get(&port->state->port); - if (tty) { - cflag = tty->termios.c_cflag; - tty_kref_put(tty); - } + unsigned long temp; - temp = lpuart32_read(port, UARTCTRL) & ~UARTCTRL_SBK; - modem = lpuart32_read(port, UARTMODIR); + temp = lpuart32_read(port, UARTCTRL); + /* + * LPUART IP now has two known bugs, one is CTS has higher priority than the + * break signal, which causes the break signal sending through UARTCTRL_SBK + * may impacted by the CTS input if the HW flow control is enabled. It + * exists on all platforms we support in this driver. + * Another bug is i.MX8QM LPUART may have an additional break character + * being sent after SBK was cleared. + * To avoid above two bugs, we use Transmit Data Inversion function to send + * the break signal instead of UARTCTRL_SBK. + */ if (break_state != 0) { - temp |= UARTCTRL_SBK; /* - * LPUART CTS has higher priority than SBK, need to disable CTS before - * asserting SBK to avoid any interference if flow control is enabled. + * Disable the transmitter to prevent any data from being sent out + * during break, then invert the TX line to send break. */ - if (cflag & CRTSCTS && modem & UARTMODIR_TXCTSE) - lpuart32_write(port, modem & ~UARTMODIR_TXCTSE, UARTMODIR); + temp &= ~UARTCTRL_TE; + lpuart32_write(port, temp, UARTCTRL); + temp |= UARTCTRL_TXINV; + lpuart32_write(port, temp, UARTCTRL); } else { - /* Re-enable the CTS when break off. */ - if (cflag & CRTSCTS && !(modem & UARTMODIR_TXCTSE)) - lpuart32_write(port, modem | UARTMODIR_TXCTSE, UARTMODIR); + /* Disable the TXINV to turn off break and re-enable transmitter. */ + temp &= ~UARTCTRL_TXINV; + lpuart32_write(port, temp, UARTCTRL); + temp |= UARTCTRL_TE; + lpuart32_write(port, temp, UARTCTRL); } - - lpuart32_write(port, temp, UARTCTRL); } static void lpuart_setup_watermark(struct lpuart_port *sport) diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c index 08dc3e2a729c..8582479f0211 100644 --- a/drivers/tty/serial/qcom_geni_serial.c +++ b/drivers/tty/serial/qcom_geni_serial.c @@ -1664,19 +1664,18 @@ static int qcom_geni_serial_probe(struct platform_device *pdev) uport->private_data = &port->private_data; platform_set_drvdata(pdev, port); - ret = uart_add_one_port(drv, uport); - if (ret) - return ret; - irq_set_status_flags(uport->irq, IRQ_NOAUTOEN); ret = devm_request_irq(uport->dev, uport->irq, qcom_geni_serial_isr, IRQF_TRIGGER_HIGH, port->name, uport); if (ret) { dev_err(uport->dev, "Failed to get IRQ ret %d\n", ret); - uart_remove_one_port(drv, uport); return ret; } + ret = uart_add_one_port(drv, uport); + if (ret) + return ret; + /* * Set pm_runtime status as ACTIVE so that wakeup_irq gets * enabled/disabled from dev_pm_arm_wake_irq during system diff --git a/drivers/tty/vt/vc_screen.c b/drivers/tty/vt/vc_screen.c index 498ba9c0ee93..829c4be66f3b 100644 --- a/drivers/tty/vt/vc_screen.c +++ b/drivers/tty/vt/vc_screen.c @@ -656,10 +656,17 @@ vcs_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) } } - /* The vcs_size might have changed while we slept to grab - * the user buffer, so recheck. + /* The vc might have been freed or vcs_size might have changed + * while we slept to grab the user buffer, so recheck. * Return data written up to now on failure. */ + vc = vcs_vc(inode, &viewed); + if (!vc) { + if (written) + break; + ret = -ENXIO; + goto unlock_out; + } size = vcs_size(vc, attr, false); if (size < 0) { if (written) diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c index 202ff71e1b58..51b3c6ae781d 100644 --- a/drivers/ufs/core/ufs-mcq.c +++ b/drivers/ufs/core/ufs-mcq.c @@ -150,7 +150,8 @@ static int ufshcd_mcq_config_nr_queues(struct ufs_hba *hba) u32 hba_maxq, rem, tot_queues; struct Scsi_Host *host = hba->host; - hba_maxq = FIELD_GET(MAX_QUEUE_SUP, hba->mcq_capabilities); + /* maxq is 0 based value */ + hba_maxq = FIELD_GET(MAX_QUEUE_SUP, hba->mcq_capabilities) + 1; tot_queues = UFS_MCQ_NUM_DEV_CMD_QUEUES + read_queues + poll_queues + rw_queues; @@ -265,7 +266,7 @@ static int ufshcd_mcq_get_tag(struct ufs_hba *hba, addr = (le64_to_cpu(cqe->command_desc_base_addr) & CQE_UCD_BA) - hba->ucdl_dma_addr; - return div_u64(addr, sizeof(struct utp_transfer_cmd_desc)); + return div_u64(addr, ufshcd_get_ucd_size(hba)); } static void ufshcd_mcq_process_cqe(struct ufs_hba *hba, diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 17d7bb875fee..e7e79f515e14 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -2849,10 +2849,10 @@ static void ufshcd_map_queues(struct Scsi_Host *shost) static void ufshcd_init_lrb(struct ufs_hba *hba, struct ufshcd_lrb *lrb, int i) { struct utp_transfer_cmd_desc *cmd_descp = (void *)hba->ucdl_base_addr + - i * sizeof_utp_transfer_cmd_desc(hba); + i * ufshcd_get_ucd_size(hba); struct utp_transfer_req_desc *utrdlp = hba->utrdl_base_addr; dma_addr_t cmd_desc_element_addr = hba->ucdl_dma_addr + - i * sizeof_utp_transfer_cmd_desc(hba); + i * ufshcd_get_ucd_size(hba); u16 response_offset = offsetof(struct utp_transfer_cmd_desc, response_upiu); u16 prdt_offset = offsetof(struct utp_transfer_cmd_desc, prd_table); @@ -3761,7 +3761,7 @@ static int ufshcd_memory_alloc(struct ufs_hba *hba) size_t utmrdl_size, utrdl_size, ucdl_size; /* Allocate memory for UTP command descriptors */ - ucdl_size = sizeof_utp_transfer_cmd_desc(hba) * hba->nutrs; + ucdl_size = ufshcd_get_ucd_size(hba) * hba->nutrs; hba->ucdl_base_addr = dmam_alloc_coherent(hba->dev, ucdl_size, &hba->ucdl_dma_addr, @@ -3861,7 +3861,7 @@ static void ufshcd_host_memory_configure(struct ufs_hba *hba) prdt_offset = offsetof(struct utp_transfer_cmd_desc, prd_table); - cmd_desc_size = sizeof_utp_transfer_cmd_desc(hba); + cmd_desc_size = ufshcd_get_ucd_size(hba); cmd_desc_dma_addr = hba->ucdl_dma_addr; for (i = 0; i < hba->nutrs; i++) { @@ -8452,7 +8452,7 @@ static void ufshcd_release_sdb_queue(struct ufs_hba *hba, int nutrs) { size_t ucdl_size, utrdl_size; - ucdl_size = sizeof(struct utp_transfer_cmd_desc) * nutrs; + ucdl_size = ufshcd_get_ucd_size(hba) * nutrs; dmam_free_coherent(hba->dev, ucdl_size, hba->ucdl_base_addr, hba->ucdl_dma_addr); @@ -9459,8 +9459,16 @@ static int __ufshcd_wl_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op) * that performance might be impacted. */ ret = ufshcd_urgent_bkops(hba); - if (ret) + if (ret) { + /* + * If return err in suspend flow, IO will hang. + * Trigger error handler and break suspend for + * error recovery. + */ + ufshcd_force_error_recovery(hba); + ret = -EBUSY; goto enable_scaling; + } } else { /* make sure that auto bkops is disabled */ ufshcd_disable_auto_bkops(hba); diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c index ccfaebca6faa..1dcadef933e3 100644 --- a/drivers/usb/cdns3/cdns3-gadget.c +++ b/drivers/usb/cdns3/cdns3-gadget.c @@ -2097,6 +2097,19 @@ int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable) else priv_ep->trb_burst_size = 16; + /* + * In versions preceding DEV_VER_V2, for example, iMX8QM, there exit the bugs + * in the DMA. These bugs occur when the trb_burst_size exceeds 16 and the + * address is not aligned to 128 Bytes (which is a product of the 64-bit AXI + * and AXI maximum burst length of 16 or 0xF+1, dma_axi_ctrl0[3:0]). This + * results in data corruption when it crosses the 4K border. The corruption + * specifically occurs from the position (4K - (address & 0x7F)) to 4K. + * + * So force trb_burst_size to 16 at such platform. + */ + if (priv_dev->dev_ver < DEV_VER_V2) + priv_ep->trb_burst_size = 16; + mult = min_t(u8, mult, EP_CFG_MULT_MAX); buffering = min_t(u8, buffering, EP_CFG_BUFFERING_MAX); maxburst = min_t(u8, maxburst, EP_CFG_MAXBURST_MAX); diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c index 4bb6d304eb4b..311007b1d904 100644 --- a/drivers/usb/class/usbtmc.c +++ b/drivers/usb/class/usbtmc.c @@ -1928,6 +1928,8 @@ static int usbtmc_ioctl_request(struct usbtmc_device_data *data, if (request.req.wLength > USBTMC_BUFSIZE) return -EMSGSIZE; + if (request.req.wLength == 0) /* Length-0 requests are never IN */ + request.req.bRequestType &= ~USB_DIR_IN; is_in = request.req.bRequestType & USB_DIR_IN; diff --git a/drivers/usb/core/buffer.c b/drivers/usb/core/buffer.c index fbb087b728dc..268ccbec88f9 100644 --- a/drivers/usb/core/buffer.c +++ b/drivers/usb/core/buffer.c @@ -172,3 +172,44 @@ void hcd_buffer_free( } dma_free_coherent(hcd->self.sysdev, size, addr, dma); } + +void *hcd_buffer_alloc_pages(struct usb_hcd *hcd, + size_t size, gfp_t mem_flags, dma_addr_t *dma) +{ + if (size == 0) + return NULL; + + if (hcd->localmem_pool) + return gen_pool_dma_alloc_align(hcd->localmem_pool, + size, dma, PAGE_SIZE); + + /* some USB hosts just use PIO */ + if (!hcd_uses_dma(hcd)) { + *dma = DMA_MAPPING_ERROR; + return (void *)__get_free_pages(mem_flags, + get_order(size)); + } + + return dma_alloc_coherent(hcd->self.sysdev, + size, dma, mem_flags); +} + +void hcd_buffer_free_pages(struct usb_hcd *hcd, + size_t size, void *addr, dma_addr_t dma) +{ + if (!addr) + return; + + if (hcd->localmem_pool) { + gen_pool_free(hcd->localmem_pool, + (unsigned long)addr, size); + return; + } + + if (!hcd_uses_dma(hcd)) { + free_pages((unsigned long)addr, get_order(size)); + return; + } + + dma_free_coherent(hcd->self.sysdev, size, addr, dma); +} diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index e501a03d6c70..fcf68818e999 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -186,6 +186,7 @@ static int connected(struct usb_dev_state *ps) static void dec_usb_memory_use_count(struct usb_memory *usbm, int *count) { struct usb_dev_state *ps = usbm->ps; + struct usb_hcd *hcd = bus_to_hcd(ps->dev->bus); unsigned long flags; spin_lock_irqsave(&ps->lock, flags); @@ -194,8 +195,8 @@ static void dec_usb_memory_use_count(struct usb_memory *usbm, int *count) list_del(&usbm->memlist); spin_unlock_irqrestore(&ps->lock, flags); - usb_free_coherent(ps->dev, usbm->size, usbm->mem, - usbm->dma_handle); + hcd_buffer_free_pages(hcd, usbm->size, + usbm->mem, usbm->dma_handle); usbfs_decrease_memory_usage( usbm->size + sizeof(struct usb_memory)); kfree(usbm); @@ -234,7 +235,7 @@ static int usbdev_mmap(struct file *file, struct vm_area_struct *vma) size_t size = vma->vm_end - vma->vm_start; void *mem; unsigned long flags; - dma_addr_t dma_handle; + dma_addr_t dma_handle = DMA_MAPPING_ERROR; int ret; ret = usbfs_increase_memory_usage(size + sizeof(struct usb_memory)); @@ -247,8 +248,8 @@ static int usbdev_mmap(struct file *file, struct vm_area_struct *vma) goto error_decrease_mem; } - mem = usb_alloc_coherent(ps->dev, size, GFP_USER | __GFP_NOWARN, - &dma_handle); + mem = hcd_buffer_alloc_pages(hcd, + size, GFP_USER | __GFP_NOWARN, &dma_handle); if (!mem) { ret = -ENOMEM; goto error_free_usbm; @@ -264,7 +265,14 @@ static int usbdev_mmap(struct file *file, struct vm_area_struct *vma) usbm->vma_use_count = 1; INIT_LIST_HEAD(&usbm->memlist); - if (hcd->localmem_pool || !hcd_uses_dma(hcd)) { + /* + * In DMA-unavailable cases, hcd_buffer_alloc_pages allocates + * normal pages and assigns DMA_MAPPING_ERROR to dma_handle. Check + * whether we are in such cases, and then use remap_pfn_range (or + * dma_mmap_coherent) to map normal (or DMA) pages into the user + * space, respectively. + */ + if (dma_handle == DMA_MAPPING_ERROR) { if (remap_pfn_range(vma, vma->vm_start, virt_to_phys(usbm->mem) >> PAGE_SHIFT, size, vma->vm_page_prot) < 0) { diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 0beaab932e7d..7b2ce013cc5b 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1137,7 +1137,7 @@ static int dwc3_core_init(struct dwc3 *dwc) dwc3_set_incr_burst_type(dwc); - dwc3_phy_power_on(dwc); + ret = dwc3_phy_power_on(dwc); if (ret) goto err_exit_phy; diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index d56457c02996..1f043c31a096 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -1116,6 +1116,7 @@ struct dwc3_scratchpad_array { * @dis_metastability_quirk: set to disable metastability quirk. * @dis_split_quirk: set to disable split boundary. * @wakeup_configured: set if the device is configured for remote wakeup. + * @suspended: set to track suspend event due to U3/L2. * @imod_interval: set the interrupt moderation interval in 250ns * increments or 0 to disable. * @max_cfg_eps: current max number of IN eps used across all USB configs. @@ -1332,6 +1333,7 @@ struct dwc3 { unsigned dis_split_quirk:1; unsigned async_callbacks:1; unsigned wakeup_configured:1; + unsigned suspended:1; u16 imod_interval; diff --git a/drivers/usb/dwc3/debugfs.c b/drivers/usb/dwc3/debugfs.c index e4a2560b9dc0..ebf03468fac4 100644 --- a/drivers/usb/dwc3/debugfs.c +++ b/drivers/usb/dwc3/debugfs.c @@ -332,6 +332,11 @@ static int dwc3_lsp_show(struct seq_file *s, void *unused) unsigned int current_mode; unsigned long flags; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GSTS); @@ -350,6 +355,8 @@ static int dwc3_lsp_show(struct seq_file *s, void *unused) } spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -395,6 +402,11 @@ static int dwc3_mode_show(struct seq_file *s, void *unused) struct dwc3 *dwc = s->private; unsigned long flags; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GCTL); @@ -414,6 +426,8 @@ static int dwc3_mode_show(struct seq_file *s, void *unused) seq_printf(s, "UNKNOWN %08x\n", DWC3_GCTL_PRTCAP(reg)); } + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -463,6 +477,11 @@ static int dwc3_testmode_show(struct seq_file *s, void *unused) struct dwc3 *dwc = s->private; unsigned long flags; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_DCTL); @@ -493,6 +512,8 @@ static int dwc3_testmode_show(struct seq_file *s, void *unused) seq_printf(s, "UNKNOWN %d\n", reg); } + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -509,6 +530,7 @@ static ssize_t dwc3_testmode_write(struct file *file, unsigned long flags; u32 testmode = 0; char buf[32]; + int ret; if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count))) return -EFAULT; @@ -526,10 +548,16 @@ static ssize_t dwc3_testmode_write(struct file *file, else testmode = 0; + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; + spin_lock_irqsave(&dwc->lock, flags); dwc3_gadget_set_test_mode(dwc, testmode); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return count; } @@ -548,12 +576,18 @@ static int dwc3_link_state_show(struct seq_file *s, void *unused) enum dwc3_link_state state; u32 reg; u8 speed; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GSTS); if (DWC3_GSTS_CURMOD(reg) != DWC3_GSTS_CURMOD_DEVICE) { seq_puts(s, "Not available\n"); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); return 0; } @@ -566,6 +600,8 @@ static int dwc3_link_state_show(struct seq_file *s, void *unused) dwc3_gadget_hs_link_string(state)); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -584,6 +620,7 @@ static ssize_t dwc3_link_state_write(struct file *file, char buf[32]; u32 reg; u8 speed; + int ret; if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count))) return -EFAULT; @@ -603,10 +640,15 @@ static ssize_t dwc3_link_state_write(struct file *file, else return -EINVAL; + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; + spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GSTS); if (DWC3_GSTS_CURMOD(reg) != DWC3_GSTS_CURMOD_DEVICE) { spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); return -EINVAL; } @@ -616,12 +658,15 @@ static ssize_t dwc3_link_state_write(struct file *file, if (speed < DWC3_DSTS_SUPERSPEED && state != DWC3_LINK_STATE_RECOV) { spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); return -EINVAL; } dwc3_gadget_set_link_state(dwc, state); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return count; } @@ -645,6 +690,11 @@ static int dwc3_tx_fifo_size_show(struct seq_file *s, void *unused) unsigned long flags; u32 mdwidth; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_TXFIFO); @@ -657,6 +707,8 @@ static int dwc3_tx_fifo_size_show(struct seq_file *s, void *unused) seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -667,6 +719,11 @@ static int dwc3_rx_fifo_size_show(struct seq_file *s, void *unused) unsigned long flags; u32 mdwidth; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_RXFIFO); @@ -679,6 +736,8 @@ static int dwc3_rx_fifo_size_show(struct seq_file *s, void *unused) seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -688,12 +747,19 @@ static int dwc3_tx_request_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_TXREQQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -703,12 +769,19 @@ static int dwc3_rx_request_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_RXREQQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -718,12 +791,19 @@ static int dwc3_rx_info_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_RXINFOQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -733,12 +813,19 @@ static int dwc3_descriptor_fetch_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_DESCFETCHQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -748,12 +835,19 @@ static int dwc3_event_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_EVENTQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -798,6 +892,11 @@ static int dwc3_trb_ring_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; int i; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); if (dep->number <= 1) { @@ -827,6 +926,8 @@ static int dwc3_trb_ring_show(struct seq_file *s, void *unused) out: spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -839,6 +940,11 @@ static int dwc3_ep_info_register_show(struct seq_file *s, void *unused) u32 lower_32_bits; u32 upper_32_bits; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = DWC3_GDBGLSPMUX_EPSELECT(dep->number); @@ -851,6 +957,8 @@ static int dwc3_ep_info_register_show(struct seq_file *s, void *unused) seq_printf(s, "0x%016llx\n", ep_info); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -910,6 +1018,7 @@ void dwc3_debugfs_init(struct dwc3 *dwc) dwc->regset->regs = dwc3_regs; dwc->regset->nregs = ARRAY_SIZE(dwc3_regs); dwc->regset->base = dwc->regs - DWC3_GLOBALS_REGS_START; + dwc->regset->dev = dwc->dev; root = debugfs_create_dir(dev_name(dwc->dev), usb_debug_root); dwc->debug_root = root; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index c0ca4d12f95d..d831f5acf7b5 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2440,6 +2440,7 @@ static int dwc3_gadget_func_wakeup(struct usb_gadget *g, int intf_id) return -EINVAL; } dwc3_resume_gadget(dwc); + dwc->suspended = false; dwc->link_state = DWC3_LINK_STATE_U0; } @@ -2699,6 +2700,21 @@ static int dwc3_gadget_soft_disconnect(struct dwc3 *dwc) return ret; } +static int dwc3_gadget_soft_connect(struct dwc3 *dwc) +{ + /* + * In the Synopsys DWC_usb31 1.90a programming guide section + * 4.1.9, it specifies that for a reconnect after a + * device-initiated disconnect requires a core soft reset + * (DCTL.CSftRst) before enabling the run/stop bit. + */ + dwc3_core_soft_reset(dwc); + + dwc3_event_buffers_setup(dwc); + __dwc3_gadget_start(dwc); + return dwc3_gadget_run_stop(dwc, true); +} + static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on) { struct dwc3 *dwc = gadget_to_dwc(g); @@ -2737,21 +2753,10 @@ static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on) synchronize_irq(dwc->irq_gadget); - if (!is_on) { + if (!is_on) ret = dwc3_gadget_soft_disconnect(dwc); - } else { - /* - * In the Synopsys DWC_usb31 1.90a programming guide section - * 4.1.9, it specifies that for a reconnect after a - * device-initiated disconnect requires a core soft reset - * (DCTL.CSftRst) before enabling the run/stop bit. - */ - dwc3_core_soft_reset(dwc); - - dwc3_event_buffers_setup(dwc); - __dwc3_gadget_start(dwc); - ret = dwc3_gadget_run_stop(dwc, true); - } + else + ret = dwc3_gadget_soft_connect(dwc); pm_runtime_put(dwc->dev); @@ -3938,6 +3943,8 @@ static void dwc3_gadget_disconnect_interrupt(struct dwc3 *dwc) { int reg; + dwc->suspended = false; + dwc3_gadget_set_link_state(dwc, DWC3_LINK_STATE_RX_DET); reg = dwc3_readl(dwc->regs, DWC3_DCTL); @@ -3962,6 +3969,8 @@ static void dwc3_gadget_reset_interrupt(struct dwc3 *dwc) { u32 reg; + dwc->suspended = false; + /* * Ideally, dwc3_reset_gadget() would trigger the function * drivers to stop any active transfers through ep disable. @@ -4180,6 +4189,8 @@ static void dwc3_gadget_conndone_interrupt(struct dwc3 *dwc) static void dwc3_gadget_wakeup_interrupt(struct dwc3 *dwc, unsigned int evtinfo) { + dwc->suspended = false; + /* * TODO take core out of low power mode when that's * implemented. @@ -4277,6 +4288,7 @@ static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc, if (dwc->gadget->wakeup_armed) { dwc3_gadget_enable_linksts_evts(dwc, false); dwc3_resume_gadget(dwc); + dwc->suspended = false; } break; case DWC3_LINK_STATE_U1: @@ -4303,8 +4315,10 @@ static void dwc3_gadget_suspend_interrupt(struct dwc3 *dwc, { enum dwc3_link_state next = evtinfo & DWC3_LINK_STATE_MASK; - if (dwc->link_state != next && next == DWC3_LINK_STATE_U3) + if (!dwc->suspended && next == DWC3_LINK_STATE_U3) { + dwc->suspended = true; dwc3_suspend_gadget(dwc); + } dwc->link_state = next; } @@ -4655,42 +4669,39 @@ void dwc3_gadget_exit(struct dwc3 *dwc) int dwc3_gadget_suspend(struct dwc3 *dwc) { unsigned long flags; + int ret; if (!dwc->gadget_driver) return 0; - dwc3_gadget_run_stop(dwc, false); + ret = dwc3_gadget_soft_disconnect(dwc); + if (ret) + goto err; spin_lock_irqsave(&dwc->lock, flags); dwc3_disconnect_gadget(dwc); - __dwc3_gadget_stop(dwc); spin_unlock_irqrestore(&dwc->lock, flags); return 0; + +err: + /* + * Attempt to reset the controller's state. Likely no + * communication can be established until the host + * performs a port reset. + */ + if (dwc->softconnect) + dwc3_gadget_soft_connect(dwc); + + return ret; } int dwc3_gadget_resume(struct dwc3 *dwc) { - int ret; - if (!dwc->gadget_driver || !dwc->softconnect) return 0; - ret = __dwc3_gadget_start(dwc); - if (ret < 0) - goto err0; - - ret = dwc3_gadget_run_stop(dwc, true); - if (ret < 0) - goto err1; - - return 0; - -err1: - __dwc3_gadget_stop(dwc); - -err0: - return ret; + return dwc3_gadget_soft_connect(dwc); } void dwc3_gadget_process_pending_events(struct dwc3 *dwc) diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index a13c946e0663..f41a385a5c42 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -3535,6 +3535,7 @@ static void ffs_func_unbind(struct usb_configuration *c, /* Drain any pending AIO completions */ drain_workqueue(ffs->io_completion_wq); + ffs_event_add(ffs, FUNCTIONFS_UNBIND); if (!--opts->refcnt) functionfs_unbind(ffs); @@ -3559,7 +3560,6 @@ static void ffs_func_unbind(struct usb_configuration *c, func->function.ssp_descriptors = NULL; func->interfaces_nums = NULL; - ffs_event_add(ffs, FUNCTIONFS_UNBIND); } static struct usb_function *ffs_alloc(struct usb_function_instance *fi) diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c index 6956ad8ba8dd..a366abb45623 100644 --- a/drivers/usb/gadget/function/u_ether.c +++ b/drivers/usb/gadget/function/u_ether.c @@ -17,6 +17,7 @@ #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/if_vlan.h> +#include <linux/string_helpers.h> #include <linux/usb/composite.h> #include "u_ether.h" @@ -965,6 +966,8 @@ int gether_get_host_addr_cdc(struct net_device *net, char *host_addr, int len) dev = netdev_priv(net); snprintf(host_addr, len, "%pm", dev->host_mac); + string_upper(host_addr, host_addr); + return strlen(host_addr); } EXPORT_SYMBOL_GPL(gether_get_host_addr_cdc); diff --git a/drivers/usb/gadget/udc/amd5536udc_pci.c b/drivers/usb/gadget/udc/amd5536udc_pci.c index c80f9bd51b75..a36913ae31f9 100644 --- a/drivers/usb/gadget/udc/amd5536udc_pci.c +++ b/drivers/usb/gadget/udc/amd5536udc_pci.c @@ -170,6 +170,9 @@ static int udc_pci_probe( retval = -ENODEV; goto err_probe; } + + udc = dev; + return 0; err_probe: diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 4641153e9706..52e6d2e84e35 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -37,10 +37,6 @@ static const struct bus_type gadget_bus_type; * @vbus: for udcs who care about vbus status, this value is real vbus status; * for udcs who do not care about vbus status, this value is always true * @started: the UDC's started state. True if the UDC had started. - * @connect_lock: protects udc->vbus, udc->started, gadget->connect, gadget->deactivate related - * functions. usb_gadget_connect_locked, usb_gadget_disconnect_locked, - * usb_udc_connect_control_locked, usb_gadget_udc_start_locked, usb_gadget_udc_stop_locked are - * called with this lock held. * * This represents the internal data structure which is used by the UDC-class * to hold information about udc driver and gadget together. @@ -52,7 +48,6 @@ struct usb_udc { struct list_head list; bool vbus; bool started; - struct mutex connect_lock; }; static struct class *udc_class; @@ -692,9 +687,17 @@ out: } EXPORT_SYMBOL_GPL(usb_gadget_vbus_disconnect); -/* Internal version of usb_gadget_connect needs to be called with connect_lock held. */ -static int usb_gadget_connect_locked(struct usb_gadget *gadget) - __must_hold(&gadget->udc->connect_lock) +/** + * usb_gadget_connect - software-controlled connect to USB host + * @gadget:the peripheral being connected + * + * Enables the D+ (or potentially D-) pullup. The host will start + * enumerating this gadget when the pullup is active and a VBUS session + * is active (the link is powered). + * + * Returns zero on success, else negative errno. + */ +int usb_gadget_connect(struct usb_gadget *gadget) { int ret = 0; @@ -703,15 +706,10 @@ static int usb_gadget_connect_locked(struct usb_gadget *gadget) goto out; } - if (gadget->connected) - goto out; - - if (gadget->deactivated || !gadget->udc->started) { + if (gadget->deactivated) { /* * If gadget is deactivated we only save new state. * Gadget will be connected automatically after activation. - * - * udc first needs to be started before gadget can be pulled up. */ gadget->connected = true; goto out; @@ -726,32 +724,22 @@ out: return ret; } +EXPORT_SYMBOL_GPL(usb_gadget_connect); /** - * usb_gadget_connect - software-controlled connect to USB host - * @gadget:the peripheral being connected + * usb_gadget_disconnect - software-controlled disconnect from USB host + * @gadget:the peripheral being disconnected * - * Enables the D+ (or potentially D-) pullup. The host will start - * enumerating this gadget when the pullup is active and a VBUS session - * is active (the link is powered). + * Disables the D+ (or potentially D-) pullup, which the host may see + * as a disconnect (when a VBUS session is active). Not all systems + * support software pullup controls. + * + * Following a successful disconnect, invoke the ->disconnect() callback + * for the current gadget driver so that UDC drivers don't need to. * * Returns zero on success, else negative errno. */ -int usb_gadget_connect(struct usb_gadget *gadget) -{ - int ret; - - mutex_lock(&gadget->udc->connect_lock); - ret = usb_gadget_connect_locked(gadget); - mutex_unlock(&gadget->udc->connect_lock); - - return ret; -} -EXPORT_SYMBOL_GPL(usb_gadget_connect); - -/* Internal version of usb_gadget_disconnect needs to be called with connect_lock held. */ -static int usb_gadget_disconnect_locked(struct usb_gadget *gadget) - __must_hold(&gadget->udc->connect_lock) +int usb_gadget_disconnect(struct usb_gadget *gadget) { int ret = 0; @@ -763,12 +751,10 @@ static int usb_gadget_disconnect_locked(struct usb_gadget *gadget) if (!gadget->connected) goto out; - if (gadget->deactivated || !gadget->udc->started) { + if (gadget->deactivated) { /* * If gadget is deactivated we only save new state. * Gadget will stay disconnected after activation. - * - * udc should have been started before gadget being pulled down. */ gadget->connected = false; goto out; @@ -788,30 +774,6 @@ out: return ret; } - -/** - * usb_gadget_disconnect - software-controlled disconnect from USB host - * @gadget:the peripheral being disconnected - * - * Disables the D+ (or potentially D-) pullup, which the host may see - * as a disconnect (when a VBUS session is active). Not all systems - * support software pullup controls. - * - * Following a successful disconnect, invoke the ->disconnect() callback - * for the current gadget driver so that UDC drivers don't need to. - * - * Returns zero on success, else negative errno. - */ -int usb_gadget_disconnect(struct usb_gadget *gadget) -{ - int ret; - - mutex_lock(&gadget->udc->connect_lock); - ret = usb_gadget_disconnect_locked(gadget); - mutex_unlock(&gadget->udc->connect_lock); - - return ret; -} EXPORT_SYMBOL_GPL(usb_gadget_disconnect); /** @@ -832,11 +794,10 @@ int usb_gadget_deactivate(struct usb_gadget *gadget) if (gadget->deactivated) goto out; - mutex_lock(&gadget->udc->connect_lock); if (gadget->connected) { - ret = usb_gadget_disconnect_locked(gadget); + ret = usb_gadget_disconnect(gadget); if (ret) - goto unlock; + goto out; /* * If gadget was being connected before deactivation, we want @@ -846,8 +807,6 @@ int usb_gadget_deactivate(struct usb_gadget *gadget) } gadget->deactivated = true; -unlock: - mutex_unlock(&gadget->udc->connect_lock); out: trace_usb_gadget_deactivate(gadget, ret); @@ -871,7 +830,6 @@ int usb_gadget_activate(struct usb_gadget *gadget) if (!gadget->deactivated) goto out; - mutex_lock(&gadget->udc->connect_lock); gadget->deactivated = false; /* @@ -879,8 +837,7 @@ int usb_gadget_activate(struct usb_gadget *gadget) * while it was being deactivated, we call usb_gadget_connect(). */ if (gadget->connected) - ret = usb_gadget_connect_locked(gadget); - mutex_unlock(&gadget->udc->connect_lock); + ret = usb_gadget_connect(gadget); out: trace_usb_gadget_activate(gadget, ret); @@ -1121,13 +1078,12 @@ EXPORT_SYMBOL_GPL(usb_gadget_set_state); /* ------------------------------------------------------------------------- */ -/* Acquire connect_lock before calling this function. */ -static void usb_udc_connect_control_locked(struct usb_udc *udc) __must_hold(&udc->connect_lock) +static void usb_udc_connect_control(struct usb_udc *udc) { - if (udc->vbus && udc->started) - usb_gadget_connect_locked(udc->gadget); + if (udc->vbus) + usb_gadget_connect(udc->gadget); else - usb_gadget_disconnect_locked(udc->gadget); + usb_gadget_disconnect(udc->gadget); } /** @@ -1143,12 +1099,10 @@ void usb_udc_vbus_handler(struct usb_gadget *gadget, bool status) { struct usb_udc *udc = gadget->udc; - mutex_lock(&udc->connect_lock); if (udc) { udc->vbus = status; - usb_udc_connect_control_locked(udc); + usb_udc_connect_control(udc); } - mutex_unlock(&udc->connect_lock); } EXPORT_SYMBOL_GPL(usb_udc_vbus_handler); @@ -1170,7 +1124,7 @@ void usb_gadget_udc_reset(struct usb_gadget *gadget, EXPORT_SYMBOL_GPL(usb_gadget_udc_reset); /** - * usb_gadget_udc_start_locked - tells usb device controller to start up + * usb_gadget_udc_start - tells usb device controller to start up * @udc: The UDC to be started * * This call is issued by the UDC Class driver when it's about @@ -1181,11 +1135,8 @@ EXPORT_SYMBOL_GPL(usb_gadget_udc_reset); * necessary to have it powered on. * * Returns zero on success, else negative errno. - * - * Caller should acquire connect_lock before invoking this function. */ -static inline int usb_gadget_udc_start_locked(struct usb_udc *udc) - __must_hold(&udc->connect_lock) +static inline int usb_gadget_udc_start(struct usb_udc *udc) { int ret; @@ -1202,7 +1153,7 @@ static inline int usb_gadget_udc_start_locked(struct usb_udc *udc) } /** - * usb_gadget_udc_stop_locked - tells usb device controller we don't need it anymore + * usb_gadget_udc_stop - tells usb device controller we don't need it anymore * @udc: The UDC to be stopped * * This call is issued by the UDC Class driver after calling @@ -1211,11 +1162,8 @@ static inline int usb_gadget_udc_start_locked(struct usb_udc *udc) * The details are implementation specific, but it can go as * far as powering off UDC completely and disable its data * line pullups. - * - * Caller should acquire connect lock before invoking this function. */ -static inline void usb_gadget_udc_stop_locked(struct usb_udc *udc) - __must_hold(&udc->connect_lock) +static inline void usb_gadget_udc_stop(struct usb_udc *udc) { if (!udc->started) { dev_err(&udc->dev, "UDC had already stopped\n"); @@ -1374,7 +1322,6 @@ int usb_add_gadget(struct usb_gadget *gadget) udc->gadget = gadget; gadget->udc = udc; - mutex_init(&udc->connect_lock); udc->started = false; @@ -1576,15 +1523,11 @@ static int gadget_bind_driver(struct device *dev) if (ret) goto err_bind; - mutex_lock(&udc->connect_lock); - ret = usb_gadget_udc_start_locked(udc); - if (ret) { - mutex_unlock(&udc->connect_lock); + ret = usb_gadget_udc_start(udc); + if (ret) goto err_start; - } usb_gadget_enable_async_callbacks(udc); - usb_udc_connect_control_locked(udc); - mutex_unlock(&udc->connect_lock); + usb_udc_connect_control(udc); kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE); return 0; @@ -1615,14 +1558,12 @@ static void gadget_unbind_driver(struct device *dev) kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE); - mutex_lock(&udc->connect_lock); - usb_gadget_disconnect_locked(gadget); + usb_gadget_disconnect(gadget); usb_gadget_disable_async_callbacks(udc); if (gadget->irq) synchronize_irq(gadget->irq); udc->driver->unbind(gadget); - usb_gadget_udc_stop_locked(udc); - mutex_unlock(&udc->connect_lock); + usb_gadget_udc_stop(udc); mutex_lock(&udc_lock); driver->is_bound = false; @@ -1708,15 +1649,11 @@ static ssize_t soft_connect_store(struct device *dev, } if (sysfs_streq(buf, "connect")) { - mutex_lock(&udc->connect_lock); - usb_gadget_udc_start_locked(udc); - usb_gadget_connect_locked(udc->gadget); - mutex_unlock(&udc->connect_lock); + usb_gadget_udc_start(udc); + usb_gadget_connect(udc->gadget); } else if (sysfs_streq(buf, "disconnect")) { - mutex_lock(&udc->connect_lock); - usb_gadget_disconnect_locked(udc->gadget); - usb_gadget_udc_stop_locked(udc); - mutex_unlock(&udc->connect_lock); + usb_gadget_disconnect(udc->gadget); + usb_gadget_udc_stop(udc); } else { dev_err(dev, "unsupported command '%s'\n", buf); ret = -EINVAL; diff --git a/drivers/usb/host/uhci-pci.c b/drivers/usb/host/uhci-pci.c index 3592f757fe05..7bd2fddde770 100644 --- a/drivers/usb/host/uhci-pci.c +++ b/drivers/usb/host/uhci-pci.c @@ -119,11 +119,13 @@ static int uhci_pci_init(struct usb_hcd *hcd) uhci->rh_numports = uhci_count_ports(hcd); - /* Intel controllers report the OverCurrent bit active on. - * VIA controllers report it active off, so we'll adjust the - * bit value. (It's not standardized in the UHCI spec.) + /* + * Intel controllers report the OverCurrent bit active on. VIA + * and ZHAOXIN controllers report it active off, so we'll adjust + * the bit value. (It's not standardized in the UHCI spec.) */ - if (to_pci_dev(uhci_dev(uhci))->vendor == PCI_VENDOR_ID_VIA) + if (to_pci_dev(uhci_dev(uhci))->vendor == PCI_VENDOR_ID_VIA || + to_pci_dev(uhci_dev(uhci))->vendor == PCI_VENDOR_ID_ZHAOXIN) uhci->oc_low = 1; /* HP's server management chip requires a longer port reset delay. */ diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index ddb79f23fb3b..79b3691f373f 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -13,6 +13,7 @@ #include <linux/module.h> #include <linux/acpi.h> #include <linux/reset.h> +#include <linux/suspend.h> #include "xhci.h" #include "xhci-trace.h" @@ -387,7 +388,7 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) if (pdev->vendor == PCI_VENDOR_ID_AMD && pdev->device == PCI_DEVICE_ID_AMD_RENOIR_XHCI) - xhci->quirks |= XHCI_BROKEN_D3COLD; + xhci->quirks |= XHCI_BROKEN_D3COLD_S2I; if (pdev->vendor == PCI_VENDOR_ID_INTEL) { xhci->quirks |= XHCI_LPM_SUPPORT; @@ -801,9 +802,16 @@ static int xhci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup) * Systems with the TI redriver that loses port status change events * need to have the registers polled during D3, so avoid D3cold. */ - if (xhci->quirks & (XHCI_COMP_MODE_QUIRK | XHCI_BROKEN_D3COLD)) + if (xhci->quirks & XHCI_COMP_MODE_QUIRK) pci_d3cold_disable(pdev); +#ifdef CONFIG_SUSPEND + /* d3cold is broken, but only when s2idle is used */ + if (pm_suspend_target_state == PM_SUSPEND_TO_IDLE && + xhci->quirks & (XHCI_BROKEN_D3COLD_S2I)) + pci_d3cold_disable(pdev); +#endif + if (xhci->quirks & XHCI_PME_STUCK_QUIRK) xhci_pme_quirk(hcd); diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 1ad12d5a4857..2bc82b3a2f98 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -276,6 +276,26 @@ static void inc_enq(struct xhci_hcd *xhci, struct xhci_ring *ring, trace_xhci_inc_enq(ring); } +static int xhci_num_trbs_to(struct xhci_segment *start_seg, union xhci_trb *start, + struct xhci_segment *end_seg, union xhci_trb *end, + unsigned int num_segs) +{ + union xhci_trb *last_on_seg; + int num = 0; + int i = 0; + + do { + if (start_seg == end_seg && end >= start) + return num + (end - start); + last_on_seg = &start_seg->trbs[TRBS_PER_SEGMENT - 1]; + num += last_on_seg - start; + start_seg = start_seg->next; + start = start_seg->trbs; + } while (i++ <= num_segs); + + return -EINVAL; +} + /* * Check to see if there's room to enqueue num_trbs on the ring and make sure * enqueue pointer will not advance into dequeue segment. See rules above. @@ -2140,6 +2160,7 @@ static int finish_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, u32 trb_comp_code) { struct xhci_ep_ctx *ep_ctx; + int trbs_freed; ep_ctx = xhci_get_ep_ctx(xhci, ep->vdev->out_ctx, ep->ep_index); @@ -2209,9 +2230,15 @@ static int finish_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, } /* Update ring dequeue pointer */ + trbs_freed = xhci_num_trbs_to(ep_ring->deq_seg, ep_ring->dequeue, + td->last_trb_seg, td->last_trb, + ep_ring->num_segs); + if (trbs_freed < 0) + xhci_dbg(xhci, "Failed to count freed trbs at TD finish\n"); + else + ep_ring->num_trbs_free += trbs_freed; ep_ring->dequeue = td->last_trb; ep_ring->deq_seg = td->last_trb_seg; - ep_ring->num_trbs_free += td->num_trbs - 1; inc_deq(xhci, ep_ring); return xhci_td_cleanup(xhci, td, ep_ring, td->status); diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 08d721921b7b..6b690ec91ff3 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1901,7 +1901,7 @@ struct xhci_hcd { #define XHCI_DISABLE_SPARSE BIT_ULL(38) #define XHCI_SG_TRB_CACHE_SIZE_QUIRK BIT_ULL(39) #define XHCI_NO_SOFT_RETRY BIT_ULL(40) -#define XHCI_BROKEN_D3COLD BIT_ULL(41) +#define XHCI_BROKEN_D3COLD_S2I BIT_ULL(41) #define XHCI_EP_CTX_BROKEN_DCS BIT_ULL(42) #define XHCI_SUSPEND_RESUME_CLKS BIT_ULL(43) #define XHCI_RESET_TO_DEFAULT BIT_ULL(44) diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index 8931df5a85fd..c54e9805da53 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -406,22 +406,25 @@ static DEF_SCSI_QCMD(queuecommand) ***********************************************************************/ /* Command timeout and abort */ -static int command_abort(struct scsi_cmnd *srb) +static int command_abort_matching(struct us_data *us, struct scsi_cmnd *srb_match) { - struct us_data *us = host_to_us(srb->device->host); - - usb_stor_dbg(us, "%s called\n", __func__); - /* * us->srb together with the TIMED_OUT, RESETTING, and ABORTING * bits are protected by the host lock. */ scsi_lock(us_to_host(us)); - /* Is this command still active? */ - if (us->srb != srb) { + /* is there any active pending command to abort ? */ + if (!us->srb) { scsi_unlock(us_to_host(us)); usb_stor_dbg(us, "-- nothing to abort\n"); + return SUCCESS; + } + + /* Does the command match the passed srb if any ? */ + if (srb_match && us->srb != srb_match) { + scsi_unlock(us_to_host(us)); + usb_stor_dbg(us, "-- pending command mismatch\n"); return FAILED; } @@ -444,6 +447,14 @@ static int command_abort(struct scsi_cmnd *srb) return SUCCESS; } +static int command_abort(struct scsi_cmnd *srb) +{ + struct us_data *us = host_to_us(srb->device->host); + + usb_stor_dbg(us, "%s called\n", __func__); + return command_abort_matching(us, srb); +} + /* * This invokes the transport reset mechanism to reset the state of the * device @@ -455,6 +466,9 @@ static int device_reset(struct scsi_cmnd *srb) usb_stor_dbg(us, "%s called\n", __func__); + /* abort any pending command before reset */ + command_abort_matching(us, NULL); + /* lock the device pointers and do the reset */ mutex_lock(&(us->dev_mutex)); result = us->transport_reset(us); diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c index 8f3e884222ad..66de880b28d0 100644 --- a/drivers/usb/typec/altmodes/displayport.c +++ b/drivers/usb/typec/altmodes/displayport.c @@ -516,6 +516,10 @@ static ssize_t pin_assignment_show(struct device *dev, mutex_unlock(&dp->lock); + /* get_current_pin_assignments can return 0 when no matching pin assignments are found */ + if (len == 0) + len++; + buf[len - 1] = '\n'; return len; } diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c index 8b075ca82ef6..603dbd44deba 100644 --- a/drivers/usb/typec/tipd/core.c +++ b/drivers/usb/typec/tipd/core.c @@ -886,6 +886,9 @@ static void tps6598x_remove(struct i2c_client *client) { struct tps6598x *tps = i2c_get_clientdata(client); + if (!client->irq) + cancel_delayed_work_sync(&tps->wq_poll); + tps6598x_disconnect(tps, 0); typec_unregister_port(tps->port); usb_role_switch_put(tps->role_sw); @@ -917,7 +920,7 @@ static int __maybe_unused tps6598x_resume(struct device *dev) enable_irq(client->irq); } - if (client->irq) + if (!client->irq) queue_delayed_work(system_power_efficient_wq, &tps->wq_poll, msecs_to_jiffies(POLL_INTERVAL)); diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 3d4dd9420c30..0d2f805468e1 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -860,6 +860,11 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data, if (ret) goto pin_unwind; + if (!pfn_valid(phys_pfn)) { + ret = -EINVAL; + goto pin_unwind; + } + ret = vfio_add_to_pfn_list(dma, iova, phys_pfn); if (ret) { if (put_pfn(phys_pfn, dma->prot) && do_accounting) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index a92af08e7864..074273020849 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -256,7 +256,7 @@ void vhost_work_queue(struct vhost_dev *dev, struct vhost_work *work) * test_and_set_bit() implies a memory barrier. */ llist_add(&work->node, &dev->worker->work_list); - wake_up_process(dev->worker->vtsk->task); + vhost_task_wake(dev->worker->vtsk); } } EXPORT_SYMBOL_GPL(vhost_work_queue); @@ -333,31 +333,19 @@ static void vhost_vq_reset(struct vhost_dev *dev, __vhost_vq_meta_reset(vq); } -static int vhost_worker(void *data) +static bool vhost_worker(void *data) { struct vhost_worker *worker = data; struct vhost_work *work, *work_next; struct llist_node *node; - for (;;) { - /* mb paired w/ kthread_stop */ - set_current_state(TASK_INTERRUPTIBLE); - - if (vhost_task_should_stop(worker->vtsk)) { - __set_current_state(TASK_RUNNING); - break; - } - - node = llist_del_all(&worker->work_list); - if (!node) - schedule(); - + node = llist_del_all(&worker->work_list); + if (node) { node = llist_reverse_order(node); /* make sure flag is seen after deletion */ smp_wmb(); llist_for_each_entry_safe(work, work_next, node, node) { clear_bit(VHOST_WORK_QUEUED, &work->flags); - __set_current_state(TASK_RUNNING); kcov_remote_start_common(worker->kcov_handle); work->fn(work); kcov_remote_stop(); @@ -365,7 +353,7 @@ static int vhost_worker(void *data) } } - return 0; + return !!node; } static void vhost_vq_free_iovecs(struct vhost_virtqueue *vq) diff --git a/drivers/video/fbdev/68328fb.c b/drivers/video/fbdev/68328fb.c index 3ccf46f8ffd0..07d6e8dc686b 100644 --- a/drivers/video/fbdev/68328fb.c +++ b/drivers/video/fbdev/68328fb.c @@ -124,7 +124,7 @@ static u_long get_line_length(int xres_virtual, int bpp) * First part, xxxfb_check_var, must not write anything * to hardware, it should only verify and adjust var. * This means it doesn't alter par but it does use hardware - * data from it to check this var. + * data from it to check this var. */ static int mc68x328fb_check_var(struct fb_var_screeninfo *var, @@ -182,7 +182,7 @@ static int mc68x328fb_check_var(struct fb_var_screeninfo *var, /* * Now that we checked it we alter var. The reason being is that the video - * mode passed in might not work but slight changes to it might make it + * mode passed in might not work but slight changes to it might make it * work. This way we let the user know what is acceptable. */ switch (var->bits_per_pixel) { @@ -257,8 +257,8 @@ static int mc68x328fb_check_var(struct fb_var_screeninfo *var, } /* This routine actually sets the video mode. It's in here where we - * the hardware state info->par and fix which can be affected by the - * change in par. For this driver it doesn't do much. + * the hardware state info->par and fix which can be affected by the + * change in par. For this driver it doesn't do much. */ static int mc68x328fb_set_par(struct fb_info *info) { @@ -295,7 +295,7 @@ static int mc68x328fb_setcolreg(u_int regno, u_int red, u_int green, u_int blue, * {hardwarespecific} contains width of RAMDAC * cmap[X] is programmed to (X << red.offset) | (X << green.offset) | (X << blue.offset) * RAMDAC[X] is programmed to (red, green, blue) - * + * * Pseudocolor: * uses offset = 0 && length = RAMDAC register width. * var->{color}.offset is 0 @@ -384,7 +384,7 @@ static int mc68x328fb_pan_display(struct fb_var_screeninfo *var, } /* - * Most drivers don't need their own mmap function + * Most drivers don't need their own mmap function */ static int mc68x328fb_mmap(struct fb_info *info, struct vm_area_struct *vma) diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig index 96e91570cdd3..0fdf5f46802c 100644 --- a/drivers/video/fbdev/Kconfig +++ b/drivers/video/fbdev/Kconfig @@ -124,7 +124,7 @@ config FB_PROVIDE_GET_FB_UNMAPPED_AREA depends on FB help Allow generic frame-buffer to provide get_fb_unmapped_area - function. + function to provide shareable character device support on nommu. menuconfig FB_FOREIGN_ENDIAN bool "Framebuffer foreign endianness support" diff --git a/drivers/video/fbdev/arcfb.c b/drivers/video/fbdev/arcfb.c index 45e64016db32..08d15e408413 100644 --- a/drivers/video/fbdev/arcfb.c +++ b/drivers/video/fbdev/arcfb.c @@ -523,7 +523,7 @@ static int arcfb_probe(struct platform_device *dev) info = framebuffer_alloc(sizeof(struct arcfb_par), &dev->dev); if (!info) - goto err; + goto err_fb_alloc; info->screen_base = (char __iomem *)videomemory; info->fbops = &arcfb_ops; @@ -535,7 +535,7 @@ static int arcfb_probe(struct platform_device *dev) if (!dio_addr || !cio_addr || !c2io_addr) { printk(KERN_WARNING "no IO addresses supplied\n"); - goto err1; + goto err_addr; } par->dio_addr = dio_addr; par->cio_addr = cio_addr; @@ -551,12 +551,12 @@ static int arcfb_probe(struct platform_device *dev) printk(KERN_INFO "arcfb: Failed req IRQ %d\n", par->irq); retval = -EBUSY; - goto err1; + goto err_addr; } } retval = register_framebuffer(info); if (retval < 0) - goto err1; + goto err_register_fb; platform_set_drvdata(dev, info); fb_info(info, "Arc frame buffer device, using %dK of video memory\n", videomemorysize >> 10); @@ -580,14 +580,17 @@ static int arcfb_probe(struct platform_device *dev) } return 0; -err1: + +err_register_fb: + free_irq(par->irq, info); +err_addr: framebuffer_release(info); -err: +err_fb_alloc: vfree(videomemory); return retval; } -static int arcfb_remove(struct platform_device *dev) +static void arcfb_remove(struct platform_device *dev) { struct fb_info *info = platform_get_drvdata(dev); @@ -598,12 +601,11 @@ static int arcfb_remove(struct platform_device *dev) vfree((void __force *)info->screen_base); framebuffer_release(info); } - return 0; } static struct platform_driver arcfb_driver = { .probe = arcfb_probe, - .remove = arcfb_remove, + .remove_new = arcfb_remove, .driver = { .name = "arcfb", }, diff --git a/drivers/video/fbdev/atmel_lcdfb.c b/drivers/video/fbdev/atmel_lcdfb.c index 8187a7c4f910..987c5f5f0241 100644 --- a/drivers/video/fbdev/atmel_lcdfb.c +++ b/drivers/video/fbdev/atmel_lcdfb.c @@ -317,7 +317,7 @@ static inline void atmel_lcdfb_free_video_memory(struct atmel_lcdfb_info *sinfo) /** * atmel_lcdfb_alloc_video_memory - Allocate framebuffer memory * @sinfo: the frame buffer to allocate memory for - * + * * This function is called only from the atmel_lcdfb_probe() * so no locking by fb_info->mm_lock around smem_len setting is needed. */ diff --git a/drivers/video/fbdev/aty/atyfb_base.c b/drivers/video/fbdev/aty/atyfb_base.c index b02e4e645035..cba2b113b28b 100644 --- a/drivers/video/fbdev/aty/atyfb_base.c +++ b/drivers/video/fbdev/aty/atyfb_base.c @@ -3498,11 +3498,6 @@ static int atyfb_setup_generic(struct pci_dev *pdev, struct fb_info *info, if (ret) goto atyfb_setup_generic_fail; #endif - if (!(aty_ld_le32(CRTC_GEN_CNTL, par) & CRTC_EXT_DISP_EN)) - par->clk_wr_offset = (inb(R_GENMO) & 0x0CU) >> 2; - else - par->clk_wr_offset = aty_ld_8(CLOCK_CNTL, par) & 0x03U; - /* according to ATI, we should use clock 3 for acelerated mode */ par->clk_wr_offset = 3; diff --git a/drivers/video/fbdev/au1100fb.c b/drivers/video/fbdev/au1100fb.c index 519313b8bb00..648d6cac86e8 100644 --- a/drivers/video/fbdev/au1100fb.c +++ b/drivers/video/fbdev/au1100fb.c @@ -520,13 +520,10 @@ failed: return -ENODEV; } -int au1100fb_drv_remove(struct platform_device *dev) +void au1100fb_drv_remove(struct platform_device *dev) { struct au1100fb_device *fbdev = NULL; - if (!dev) - return -ENODEV; - fbdev = platform_get_drvdata(dev); #if !defined(CONFIG_FRAMEBUFFER_CONSOLE) && defined(CONFIG_LOGO) @@ -543,8 +540,6 @@ int au1100fb_drv_remove(struct platform_device *dev) clk_disable_unprepare(fbdev->lcdclk); clk_put(fbdev->lcdclk); } - - return 0; } #ifdef CONFIG_PM @@ -593,9 +588,9 @@ static struct platform_driver au1100fb_driver = { .name = "au1100-lcd", }, .probe = au1100fb_drv_probe, - .remove = au1100fb_drv_remove, + .remove_new = au1100fb_drv_remove, .suspend = au1100fb_drv_suspend, - .resume = au1100fb_drv_resume, + .resume = au1100fb_drv_resume, }; module_platform_driver(au1100fb_driver); diff --git a/drivers/video/fbdev/au1200fb.c b/drivers/video/fbdev/au1200fb.c index b6b22fa4a8a0..aed88ce45bf0 100644 --- a/drivers/video/fbdev/au1200fb.c +++ b/drivers/video/fbdev/au1200fb.c @@ -1765,7 +1765,7 @@ failed: return ret; } -static int au1200fb_drv_remove(struct platform_device *dev) +static void au1200fb_drv_remove(struct platform_device *dev) { struct au1200fb_platdata *pd = platform_get_drvdata(dev); struct fb_info *fbi; @@ -1788,8 +1788,6 @@ static int au1200fb_drv_remove(struct platform_device *dev) } free_irq(platform_get_irq(dev, 0), (void *)dev); - - return 0; } #ifdef CONFIG_PM @@ -1840,7 +1838,7 @@ static struct platform_driver au1200fb_driver = { .pm = AU1200FB_PMOPS, }, .probe = au1200fb_drv_probe, - .remove = au1200fb_drv_remove, + .remove_new = au1200fb_drv_remove, }; module_platform_driver(au1200fb_driver); diff --git a/drivers/video/fbdev/broadsheetfb.c b/drivers/video/fbdev/broadsheetfb.c index 55e62dd96f9b..b518cacbf7cd 100644 --- a/drivers/video/fbdev/broadsheetfb.c +++ b/drivers/video/fbdev/broadsheetfb.c @@ -1193,7 +1193,7 @@ err: } -static int broadsheetfb_remove(struct platform_device *dev) +static void broadsheetfb_remove(struct platform_device *dev) { struct fb_info *info = platform_get_drvdata(dev); @@ -1209,12 +1209,11 @@ static int broadsheetfb_remove(struct platform_device *dev) module_put(par->board->owner); framebuffer_release(info); } - return 0; } static struct platform_driver broadsheetfb_driver = { .probe = broadsheetfb_probe, - .remove = broadsheetfb_remove, + .remove_new = broadsheetfb_remove, .driver = { .name = "broadsheetfb", }, diff --git a/drivers/video/fbdev/bw2.c b/drivers/video/fbdev/bw2.c index 9cbadcd18b25..025d663dc6fd 100644 --- a/drivers/video/fbdev/bw2.c +++ b/drivers/video/fbdev/bw2.c @@ -352,7 +352,7 @@ out_err: return err; } -static int bw2_remove(struct platform_device *op) +static void bw2_remove(struct platform_device *op) { struct fb_info *info = dev_get_drvdata(&op->dev); struct bw2_par *par = info->par; @@ -363,8 +363,6 @@ static int bw2_remove(struct platform_device *op) of_iounmap(&op->resource[0], info->screen_base, info->fix.smem_len); framebuffer_release(info); - - return 0; } static const struct of_device_id bw2_match[] = { @@ -381,7 +379,7 @@ static struct platform_driver bw2_driver = { .of_match_table = bw2_match, }, .probe = bw2_probe, - .remove = bw2_remove, + .remove_new = bw2_remove, }; static int __init bw2_init(void) diff --git a/drivers/video/fbdev/cg14.c b/drivers/video/fbdev/cg14.c index a028ede39c12..832a82f45c80 100644 --- a/drivers/video/fbdev/cg14.c +++ b/drivers/video/fbdev/cg14.c @@ -512,7 +512,7 @@ static int cg14_probe(struct platform_device *op) is_8mb = (resource_size(&op->resource[1]) == (8 * 1024 * 1024)); BUILD_BUG_ON(sizeof(par->mmap_map) != sizeof(__cg14_mmap_map)); - + memcpy(&par->mmap_map, &__cg14_mmap_map, sizeof(par->mmap_map)); for (i = 0; i < CG14_MMAP_ENTRIES; i++) { diff --git a/drivers/video/fbdev/controlfb.c b/drivers/video/fbdev/controlfb.c index 77dbf94aae5f..82eeb139c4eb 100644 --- a/drivers/video/fbdev/controlfb.c +++ b/drivers/video/fbdev/controlfb.c @@ -113,14 +113,14 @@ struct fb_info_control { struct fb_info info; struct fb_par_control par; u32 pseudo_palette[16]; - + struct cmap_regs __iomem *cmap_regs; unsigned long cmap_regs_phys; - + struct control_regs __iomem *control_regs; unsigned long control_regs_phys; unsigned long control_regs_size; - + __u8 __iomem *frame_buffer; unsigned long frame_buffer_phys; unsigned long fb_orig_base; @@ -196,7 +196,7 @@ static void set_control_clock(unsigned char *params) while (!req.complete) cuda_poll(); } -#endif +#endif } /* @@ -233,19 +233,19 @@ static void control_set_hardware(struct fb_info_control *p, struct fb_par_contro if (p->par.xoffset != par->xoffset || p->par.yoffset != par->yoffset) set_screen_start(par->xoffset, par->yoffset, p); - + return; } - + p->par = *par; cmode = p->par.cmode; r = &par->regvals; - + /* Turn off display */ out_le32(CNTRL_REG(p,ctrl), 0x400 | par->ctrl); - + set_control_clock(r->clock_params); - + RADACAL_WRITE(0x20, r->radacal_ctrl); RADACAL_WRITE(0x21, p->control_use_bank2 ? 0 : 1); RADACAL_WRITE(0x10, 0); @@ -254,7 +254,7 @@ static void control_set_hardware(struct fb_info_control *p, struct fb_par_contro rp = &p->control_regs->vswin; for (i = 0; i < 16; ++i, ++rp) out_le32(&rp->r, r->regs[i]); - + out_le32(CNTRL_REG(p,pitch), par->pitch); out_le32(CNTRL_REG(p,mode), r->mode); out_le32(CNTRL_REG(p,vram_attr), p->vram_attr); @@ -366,7 +366,7 @@ static int read_control_sense(struct fb_info_control *p) sense |= (in_le32(CNTRL_REG(p,mon_sense)) & 0x180) >> 7; out_le32(CNTRL_REG(p,mon_sense), 077); /* turn off drivers */ - + return sense; } @@ -558,9 +558,9 @@ static int control_var_to_par(struct fb_var_screeninfo *var, static void control_par_to_var(struct fb_par_control *par, struct fb_var_screeninfo *var) { struct control_regints *rv; - + rv = (struct control_regints *) par->regvals.regs; - + memset(var, 0, sizeof(*var)); var->xres = par->xres; var->yres = par->yres; @@ -568,7 +568,7 @@ static void control_par_to_var(struct fb_par_control *par, struct fb_var_screeni var->yres_virtual = par->vyres; var->xoffset = par->xoffset; var->yoffset = par->yoffset; - + switch(par->cmode) { default: case CMODE_8: @@ -634,7 +634,7 @@ static int controlfb_check_var (struct fb_var_screeninfo *var, struct fb_info *i err = control_var_to_par(var, &par, info); if (err) - return err; + return err; control_par_to_var(&par, var); return 0; @@ -655,7 +655,7 @@ static int controlfb_set_par (struct fb_info *info) " control_var_to_par: %d.\n", err); return err; } - + control_set_hardware(p, &par); info->fix.visual = (p->par.cmode == CMODE_8) ? @@ -840,7 +840,7 @@ static int __init init_control(struct fb_info_control *p) int full, sense, vmode, cmode, vyres; struct fb_var_screeninfo var; int rc; - + printk(KERN_INFO "controlfb: "); full = p->total_vram == 0x400000; diff --git a/drivers/video/fbdev/core/bitblit.c b/drivers/video/fbdev/core/bitblit.c index f98e8f298bc1..8587c9da0670 100644 --- a/drivers/video/fbdev/core/bitblit.c +++ b/drivers/video/fbdev/core/bitblit.c @@ -247,6 +247,9 @@ static void bit_cursor(struct vc_data *vc, struct fb_info *info, int mode, cursor.set = 0; + if (!vc->vc_font.data) + return; + c = scr_readw((u16 *) vc->vc_pos); attribute = get_attribute(info, c); src = vc->vc_font.data + ((c & charmask) * (w * vc->vc_font.height)); diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index e808dc86001c..28739f1cb5e7 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -1468,7 +1468,7 @@ __releases(&info->lock) } #if defined(CONFIG_FB_PROVIDE_GET_FB_UNMAPPED_AREA) && !defined(CONFIG_MMU) -unsigned long get_fb_unmapped_area(struct file *filp, +static unsigned long get_fb_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { diff --git a/drivers/video/fbdev/core/modedb.c b/drivers/video/fbdev/core/modedb.c index 23cf8eba785d..f7e019dded0f 100644 --- a/drivers/video/fbdev/core/modedb.c +++ b/drivers/video/fbdev/core/modedb.c @@ -257,6 +257,11 @@ static const struct fb_videomode modedb[] = { { NULL, 72, 480, 300, 33386, 40, 24, 11, 19, 80, 3, 0, FB_VMODE_DOUBLE }, + /* 1920x1080 @ 60 Hz, 67.3 kHz hsync */ + { NULL, 60, 1920, 1080, 6734, 148, 88, 36, 4, 44, 5, 0, + FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT, + FB_VMODE_NONINTERLACED }, + /* 1920x1200 @ 60 Hz, 74.5 Khz hsync */ { NULL, 60, 1920, 1200, 5177, 128, 336, 1, 38, 208, 3, FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT, diff --git a/drivers/video/fbdev/g364fb.c b/drivers/video/fbdev/g364fb.c index 05837a3b985c..c5b7673ddc6c 100644 --- a/drivers/video/fbdev/g364fb.c +++ b/drivers/video/fbdev/g364fb.c @@ -6,7 +6,7 @@ * * This driver is based on tgafb.c * - * Copyright (C) 1997 Geert Uytterhoeven + * Copyright (C) 1997 Geert Uytterhoeven * Copyright (C) 1995 Jay Estabrook * * This file is subject to the terms and conditions of the GNU General Public @@ -28,7 +28,7 @@ #include <asm/io.h> #include <asm/jazz.h> -/* +/* * Various defines for the G364 */ #define G364_MEM_BASE 0xe4400000 @@ -125,7 +125,7 @@ static const struct fb_ops g364fb_ops = { * * This call looks only at xoffset, yoffset and the FB_VMODE_YWRAP flag */ -static int g364fb_pan_display(struct fb_var_screeninfo *var, +static int g364fb_pan_display(struct fb_var_screeninfo *var, struct fb_info *info) { if (var->xoffset || diff --git a/drivers/video/fbdev/hgafb.c b/drivers/video/fbdev/hgafb.c index 20bdab738ab7..0af58018441d 100644 --- a/drivers/video/fbdev/hgafb.c +++ b/drivers/video/fbdev/hgafb.c @@ -1,6 +1,6 @@ /* * linux/drivers/video/hgafb.c -- Hercules graphics adaptor frame buffer device - * + * * Created 25 Nov 1999 by Ferenc Bakonyi (fero@drama.obuda.kando.hu) * Based on skeletonfb.c by Geert Uytterhoeven and * mdacon.c by Andrew Apted @@ -8,14 +8,14 @@ * History: * * - Revision 0.1.8 (23 Oct 2002): Ported to new framebuffer api. - * - * - Revision 0.1.7 (23 Jan 2001): fix crash resulting from MDA only cards + * + * - Revision 0.1.7 (23 Jan 2001): fix crash resulting from MDA only cards * being detected as Hercules. (Paul G.) * - Revision 0.1.6 (17 Aug 2000): new style structs * documentation * - Revision 0.1.5 (13 Mar 2000): spinlocks instead of saveflags();cli();etc * minor fixes - * - Revision 0.1.4 (24 Jan 2000): fixed a bug in hga_card_detect() for + * - Revision 0.1.4 (24 Jan 2000): fixed a bug in hga_card_detect() for * HGA-only systems * - Revision 0.1.3 (22 Jan 2000): modified for the new fb_info structure * screen is cleared after rmmod @@ -143,7 +143,7 @@ static bool nologo = 0; static void write_hga_b(unsigned int val, unsigned char reg) { - outb_p(reg, HGA_INDEX_PORT); + outb_p(reg, HGA_INDEX_PORT); outb_p(val, HGA_VALUE_PORT); } @@ -155,7 +155,7 @@ static void write_hga_w(unsigned int val, unsigned char reg) static int test_hga_b(unsigned char val, unsigned char reg) { - outb_p(reg, HGA_INDEX_PORT); + outb_p(reg, HGA_INDEX_PORT); outb (val, HGA_VALUE_PORT); udelay(20); val = (inb_p(HGA_VALUE_PORT) == val); return val; @@ -244,7 +244,7 @@ static void hga_show_logo(struct fb_info *info) void __iomem *dest = hga_vram; char *logo = linux_logo_bw; int x, y; - + for (y = 134; y < 134 + 80 ; y++) * this needs some cleanup * for (x = 0; x < 10 ; x++) writeb(~*(logo++),(dest + HGA_ROWADDR(y) + x + 40)); @@ -255,7 +255,7 @@ static void hga_pan(unsigned int xoffset, unsigned int yoffset) { unsigned int base; unsigned long flags; - + base = (yoffset / 8) * 90 + xoffset; spin_lock_irqsave(&hga_reg_lock, flags); write_hga_w(base, 0x0c); /* start address */ @@ -310,7 +310,7 @@ static int hga_card_detect(void) /* Ok, there is definitely a card registering at the correct * memory location, so now we do an I/O port test. */ - + if (!test_hga_b(0x66, 0x0f)) /* cursor low register */ goto error; @@ -321,7 +321,7 @@ static int hga_card_detect(void) * bit of the status register is changing. This test lasts for * approximately 1/10th of a second. */ - + p_save = q_save = inb_p(HGA_STATUS_PORT) & HGA_STATUS_VSYNC; for (count=0; count < 50000 && p_save == q_save; count++) { @@ -329,7 +329,7 @@ static int hga_card_detect(void) udelay(2); } - if (p_save == q_save) + if (p_save == q_save) goto error; switch (inb_p(HGA_STATUS_PORT) & 0x70) { @@ -415,7 +415,7 @@ static int hgafb_setcolreg(u_int regno, u_int red, u_int green, u_int blue, * @info:pointer to fb_info object containing info for current hga board * * This function looks only at xoffset, yoffset and the %FB_VMODE_YWRAP - * flag in @var. If input parameters are correct it calls hga_pan() to + * flag in @var. If input parameters are correct it calls hga_pan() to * program the hardware. @info->var is updated to the new values. * A zero is returned on success and %-EINVAL for failure. */ @@ -442,9 +442,9 @@ static int hgafb_pan_display(struct fb_var_screeninfo *var, * hgafb_blank - (un)blank the screen * @blank_mode:blanking method to use * @info:unused - * - * Blank the screen if blank_mode != 0, else unblank. - * Implements VESA suspend and powerdown modes on hardware that supports + * + * Blank the screen if blank_mode != 0, else unblank. + * Implements VESA suspend and powerdown modes on hardware that supports * disabling hsync/vsync: * @blank_mode == 2 means suspend vsync, * @blank_mode == 3 means suspend hsync, @@ -539,15 +539,15 @@ static const struct fb_ops hgafb_ops = { .fb_copyarea = hgafb_copyarea, .fb_imageblit = hgafb_imageblit, }; - + /* ------------------------------------------------------------------------- * * * Functions in fb_info - * + * * ------------------------------------------------------------------------- */ /* ------------------------------------------------------------------------- */ - + /* * Initialization */ diff --git a/drivers/video/fbdev/hpfb.c b/drivers/video/fbdev/hpfb.c index cdd44e5deafe..77fbff47b1a8 100644 --- a/drivers/video/fbdev/hpfb.c +++ b/drivers/video/fbdev/hpfb.c @@ -92,7 +92,7 @@ static int hpfb_setcolreg(unsigned regno, unsigned red, unsigned green, if (regno >= info->cmap.len) return 1; - + while (in_be16(fb_regs + 0x6002) & 0x4) udelay(1); out_be16(fb_regs + 0x60ba, 0xff); @@ -143,7 +143,7 @@ static void topcat_blit(int x0, int y0, int x1, int y1, int w, int h, int rr) out_8(fb_regs + WMOVE, fb_bitmask); } -static void hpfb_copyarea(struct fb_info *info, const struct fb_copyarea *area) +static void hpfb_copyarea(struct fb_info *info, const struct fb_copyarea *area) { topcat_blit(area->sx, area->sy, area->dx, area->dy, area->width, area->height, RR_COPY); } @@ -315,7 +315,7 @@ unmap_screen_base: return ret; } -/* +/* * Check that the secondary ID indicates that we have some hope of working with this * framebuffer. The catseye boards are pretty much like topcats and we can muddle through. */ @@ -323,7 +323,7 @@ unmap_screen_base: #define topcat_sid_ok(x) (((x) == DIO_ID2_LRCATSEYE) || ((x) == DIO_ID2_HRCCATSEYE) \ || ((x) == DIO_ID2_HRMCATSEYE) || ((x) == DIO_ID2_TOPCAT)) -/* +/* * Initialise the framebuffer */ static int hpfb_dio_probe(struct dio_dev *d, const struct dio_device_id *ent) diff --git a/drivers/video/fbdev/i810/i810_dvt.c b/drivers/video/fbdev/i810/i810_dvt.c index b4b3670667ab..2082b5c92e8f 100644 --- a/drivers/video/fbdev/i810/i810_dvt.c +++ b/drivers/video/fbdev/i810/i810_dvt.c @@ -14,6 +14,7 @@ #include "i810_regs.h" #include "i810.h" +#include "i810_main.h" struct mode_registers std_modes[] = { /* 640x480 @ 60Hz */ @@ -276,7 +277,7 @@ void i810fb_fill_var_timings(struct fb_var_screeninfo *var) var->upper_margin = total - (yres + var->lower_margin + var->vsync_len); } -u32 i810_get_watermark(struct fb_var_screeninfo *var, +u32 i810_get_watermark(const struct fb_var_screeninfo *var, struct i810fb_par *par) { struct mode_registers *params = &par->regs; diff --git a/drivers/video/fbdev/imsttfb.c b/drivers/video/fbdev/imsttfb.c index bea45647184e..ee7d01ad1406 100644 --- a/drivers/video/fbdev/imsttfb.c +++ b/drivers/video/fbdev/imsttfb.c @@ -1347,7 +1347,7 @@ static const struct fb_ops imsttfb_ops = { .fb_ioctl = imsttfb_ioctl, }; -static void init_imstt(struct fb_info *info) +static int init_imstt(struct fb_info *info) { struct imstt_par *par = info->par; __u32 i, tmp, *ip, *end; @@ -1420,7 +1420,7 @@ static void init_imstt(struct fb_info *info) || !(compute_imstt_regvals(par, info->var.xres, info->var.yres))) { printk("imsttfb: %ux%ux%u not supported\n", info->var.xres, info->var.yres, info->var.bits_per_pixel); framebuffer_release(info); - return; + return -ENODEV; } sprintf(info->fix.id, "IMS TT (%s)", par->ramdac == IBM ? "IBM" : "TVP"); @@ -1452,16 +1452,21 @@ static void init_imstt(struct fb_info *info) FBINFO_HWACCEL_FILLRECT | FBINFO_HWACCEL_YPAN; - fb_alloc_cmap(&info->cmap, 0, 0); + if (fb_alloc_cmap(&info->cmap, 0, 0)) { + framebuffer_release(info); + return -ENODEV; + } if (register_framebuffer(info) < 0) { + fb_dealloc_cmap(&info->cmap); framebuffer_release(info); - return; + return -ENODEV; } tmp = (read_reg_le32(par->dc_regs, SSTATUS) & 0x0f00) >> 8; fb_info(info, "%s frame buffer; %uMB vram; chip version %u\n", info->fix.id, info->fix.smem_len >> 20, tmp); + return 0; } static int imsttfb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) @@ -1529,10 +1534,12 @@ static int imsttfb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (!par->cmap_regs) goto error; info->pseudo_palette = par->palette; - init_imstt(info); + ret = init_imstt(info); + if (ret) + goto error; pci_set_drvdata(pdev, info); - return 0; + return ret; error: if (par->dc_regs) diff --git a/drivers/video/fbdev/macfb.c b/drivers/video/fbdev/macfb.c index 312e35c9aa6c..44ff860a3f37 100644 --- a/drivers/video/fbdev/macfb.c +++ b/drivers/video/fbdev/macfb.c @@ -339,7 +339,7 @@ static int civic_setpalette(unsigned int regno, unsigned int red, { unsigned long flags; int clut_status; - + local_irq_save(flags); /* Set the register address */ @@ -439,7 +439,7 @@ static int macfb_setcolreg(unsigned regno, unsigned red, unsigned green, * (according to the entries in the `var' structure). * Return non-zero for invalid regno. */ - + if (regno >= fb_info->cmap.len) return 1; @@ -548,7 +548,7 @@ static int __init macfb_init(void) return -ENODEV; macfb_setup(option); - if (!MACH_IS_MAC) + if (!MACH_IS_MAC) return -ENODEV; if (mac_bi_data.id == MAC_MODEL_Q630 || @@ -644,7 +644,7 @@ static int __init macfb_init(void) err = -EINVAL; goto fail_unmap; } - + /* * We take a wild guess that if the video physical address is * in nubus slot space, that the nubus card is driving video. @@ -774,7 +774,7 @@ static int __init macfb_init(void) civic_cmap_regs = ioremap(CIVIC_BASE, 0x1000); break; - + /* * Assorted weirdos * We think this may be like the LC II diff --git a/drivers/video/fbdev/matrox/matroxfb_maven.c b/drivers/video/fbdev/matrox/matroxfb_maven.c index 727a10a59811..b15a8ad92ba7 100644 --- a/drivers/video/fbdev/matrox/matroxfb_maven.c +++ b/drivers/video/fbdev/matrox/matroxfb_maven.c @@ -1291,7 +1291,7 @@ static struct i2c_driver maven_driver={ .driver = { .name = "maven", }, - .probe_new = maven_probe, + .probe = maven_probe, .remove = maven_remove, .id_table = maven_id, }; diff --git a/drivers/video/fbdev/maxinefb.c b/drivers/video/fbdev/maxinefb.c index ae1a42bcb0ea..4e6b05232ae2 100644 --- a/drivers/video/fbdev/maxinefb.c +++ b/drivers/video/fbdev/maxinefb.c @@ -138,7 +138,7 @@ int __init maxinefb_init(void) *(volatile unsigned char *)fboff = 0x0; maxinefb_fix.smem_start = fb_start; - + /* erase hardware cursor */ for (i = 0; i < 512; i++) { maxinefb_ims332_write_register(IMS332_REG_CURSOR_RAM + i, diff --git a/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td043mtea1.c b/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td043mtea1.c index 1eaa35c27835..477789cff8e0 100644 --- a/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td043mtea1.c +++ b/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td043mtea1.c @@ -491,7 +491,8 @@ static int tpo_td043_probe(struct spi_device *spi) ddata->vcc_reg = devm_regulator_get(&spi->dev, "vcc"); if (IS_ERR(ddata->vcc_reg)) { - r = dev_err_probe(&spi->dev, r, "failed to get LCD VCC regulator\n"); + r = dev_err_probe(&spi->dev, PTR_ERR(ddata->vcc_reg), + "failed to get LCD VCC regulator\n"); goto err_regulator; } diff --git a/drivers/video/fbdev/p9100.c b/drivers/video/fbdev/p9100.c index 3e44f9516318..0876962c52eb 100644 --- a/drivers/video/fbdev/p9100.c +++ b/drivers/video/fbdev/p9100.c @@ -65,7 +65,7 @@ static const struct fb_ops p9100_ops = { #define P9100_FB_OFF 0x0UL /* 3 bits: 2=8bpp 3=16bpp 5=32bpp 7=24bpp */ -#define SYS_CONFIG_PIXELSIZE_SHIFT 26 +#define SYS_CONFIG_PIXELSIZE_SHIFT 26 #define SCREENPAINT_TIMECTL1_ENABLE_VIDEO 0x20 /* 0 = off, 1 = on */ @@ -110,7 +110,7 @@ struct p9100_regs { u32 vram_xxx[25]; /* Registers for IBM RGB528 Palette */ - u32 ramdac_cmap_wridx; + u32 ramdac_cmap_wridx; u32 ramdac_palette_data; u32 ramdac_pixel_mask; u32 ramdac_palette_rdaddr; diff --git a/drivers/video/fbdev/platinumfb.c b/drivers/video/fbdev/platinumfb.c index 82f019f0a0d6..f8283fcd5edb 100644 --- a/drivers/video/fbdev/platinumfb.c +++ b/drivers/video/fbdev/platinumfb.c @@ -52,17 +52,17 @@ struct fb_info_platinum { __u8 red, green, blue; } palette[256]; u32 pseudo_palette[16]; - + volatile struct cmap_regs __iomem *cmap_regs; unsigned long cmap_regs_phys; - + volatile struct platinum_regs __iomem *platinum_regs; unsigned long platinum_regs_phys; - + __u8 __iomem *frame_buffer; volatile __u8 __iomem *base_frame_buffer; unsigned long frame_buffer_phys; - + unsigned long total_vram; int clktype; int dactype; @@ -133,7 +133,7 @@ static int platinumfb_set_par (struct fb_info *info) platinum_set_hardware(pinfo); init = platinum_reg_init[pinfo->vmode-1]; - + if ((pinfo->vmode == VMODE_832_624_75) && (pinfo->cmode > CMODE_8)) offset = 0x10; @@ -214,7 +214,7 @@ static int platinumfb_setcolreg(u_int regno, u_int red, u_int green, u_int blue, break; } } - + return 0; } @@ -269,7 +269,7 @@ static void platinum_set_hardware(struct fb_info_platinum *pinfo) struct platinum_regvals *init; int i; int vmode, cmode; - + vmode = pinfo->vmode; cmode = pinfo->cmode; @@ -436,7 +436,7 @@ static int read_platinum_sense(struct fb_info_platinum *info) * This routine takes a user-supplied var, and picks the best vmode/cmode from it. * It also updates the var structure to the actual mode data obtained */ -static int platinum_var_to_par(struct fb_var_screeninfo *var, +static int platinum_var_to_par(struct fb_var_screeninfo *var, struct fb_info_platinum *pinfo, int check_only) { @@ -478,12 +478,12 @@ static int platinum_var_to_par(struct fb_var_screeninfo *var, pinfo->yoffset = 0; pinfo->vxres = pinfo->xres; pinfo->vyres = pinfo->yres; - + return 0; } -/* +/* * Parse user specified options (`video=platinumfb:') */ static int __init platinumfb_setup(char *options) @@ -624,7 +624,7 @@ static int platinumfb_probe(struct platform_device* odev) break; } dev_set_drvdata(&odev->dev, info); - + rc = platinum_init_fb(info); if (rc != 0) { iounmap(pinfo->frame_buffer); @@ -640,9 +640,9 @@ static void platinumfb_remove(struct platform_device* odev) { struct fb_info *info = dev_get_drvdata(&odev->dev); struct fb_info_platinum *pinfo = info->par; - + unregister_framebuffer (info); - + /* Unmap frame buffer and registers */ iounmap(pinfo->frame_buffer); iounmap(pinfo->platinum_regs); @@ -656,7 +656,7 @@ static void platinumfb_remove(struct platform_device* odev) framebuffer_release(info); } -static struct of_device_id platinumfb_match[] = +static struct of_device_id platinumfb_match[] = { { .name = "platinum", @@ -664,7 +664,7 @@ static struct of_device_id platinumfb_match[] = {}, }; -static struct platform_driver platinum_driver = +static struct platform_driver platinum_driver = { .driver = { .name = "platinumfb", diff --git a/drivers/video/fbdev/sa1100fb.c b/drivers/video/fbdev/sa1100fb.c index b1b8ccdbac4a..a2408bf00ca0 100644 --- a/drivers/video/fbdev/sa1100fb.c +++ b/drivers/video/fbdev/sa1100fb.c @@ -57,14 +57,14 @@ * - Driver appears to be working for Brutus 320x200x8bpp mode. Other * resolutions are working, but only the 8bpp mode is supported. * Changes need to be made to the palette encode and decode routines - * to support 4 and 16 bpp modes. + * to support 4 and 16 bpp modes. * Driver is not designed to be a module. The FrameBuffer is statically - * allocated since dynamic allocation of a 300k buffer cannot be - * guaranteed. + * allocated since dynamic allocation of a 300k buffer cannot be + * guaranteed. * * 1999/06/17: * - FrameBuffer memory is now allocated at run-time when the - * driver is initialized. + * driver is initialized. * * 2000/04/10: Nicolas Pitre <nico@fluxnic.net> * - Big cleanup for dynamic selection of machine type at run time. @@ -74,8 +74,8 @@ * * 2000/08/07: Tak-Shing Chan <tchan.rd@idthk.com> * Jeff Sutherland <jsutherland@accelent.com> - * - Resolved an issue caused by a change made to the Assabet's PLD - * earlier this year which broke the framebuffer driver for newer + * - Resolved an issue caused by a change made to the Assabet's PLD + * earlier this year which broke the framebuffer driver for newer * Phase 4 Assabets. Some other parameters were changed to optimize * for the Sharp display. * @@ -102,7 +102,7 @@ * 2000/11/23: Eric Peng <ericpeng@coventive.com> * - Freebird add * - * 2001/02/07: Jamey Hicks <jamey.hicks@compaq.com> + * 2001/02/07: Jamey Hicks <jamey.hicks@compaq.com> * Cliff Brake <cbrake@accelent.com> * - Added PM callback * @@ -500,7 +500,7 @@ sa1100fb_set_cmap(struct fb_cmap *cmap, int kspc, int con, * the shortest recovery time * Suspend * This refers to a level of power management in which substantial power - * reduction is achieved by the display. The display can have a longer + * reduction is achieved by the display. The display can have a longer * recovery time from this state than from the Stand-by state * Off * This indicates that the display is consuming the lowest level of power @@ -522,9 +522,9 @@ sa1100fb_set_cmap(struct fb_cmap *cmap, int kspc, int con, */ /* * sa1100fb_blank(): - * Blank the display by setting all palette values to zero. Note, the + * Blank the display by setting all palette values to zero. Note, the * 12 and 16 bpp modes don't really use the palette, so this will not - * blank the display in all modes. + * blank the display in all modes. */ static int sa1100fb_blank(int blank, struct fb_info *info) { @@ -603,8 +603,8 @@ static inline unsigned int get_pcd(struct sa1100fb_info *fbi, /* * sa1100fb_activate_var(): - * Configures LCD Controller based on entries in var parameter. Settings are - * only written to the controller if changes were made. + * Configures LCD Controller based on entries in var parameter. Settings are + * only written to the controller if changes were made. */ static int sa1100fb_activate_var(struct fb_var_screeninfo *var, struct sa1100fb_info *fbi) { @@ -747,7 +747,7 @@ static void sa1100fb_setup_gpio(struct sa1100fb_info *fbi) * * SA1110 spec update nr. 25 says we can and should * clear LDD15 to 12 for 4 or 8bpp modes with active - * panels. + * panels. */ if ((fbi->reg_lccr0 & LCCR0_CMS) == LCCR0_Color && (fbi->reg_lccr0 & (LCCR0_Dual|LCCR0_Act)) != 0) { @@ -1020,9 +1020,9 @@ static int sa1100fb_resume(struct platform_device *dev) /* * sa1100fb_map_video_memory(): - * Allocates the DRAM memory for the frame buffer. This buffer is - * remapped into a non-cached, non-buffered, memory region to - * allow palette and pixel writes to occur without flushing the + * Allocates the DRAM memory for the frame buffer. This buffer is + * remapped into a non-cached, non-buffered, memory region to + * allow palette and pixel writes to occur without flushing the * cache. Once this area is remapped, all virtual memory * access to the video memory should occur at the new region. */ diff --git a/drivers/video/fbdev/ssd1307fb.c b/drivers/video/fbdev/ssd1307fb.c index 046b9990d27c..132d1a205011 100644 --- a/drivers/video/fbdev/ssd1307fb.c +++ b/drivers/video/fbdev/ssd1307fb.c @@ -844,7 +844,7 @@ static const struct i2c_device_id ssd1307fb_i2c_id[] = { MODULE_DEVICE_TABLE(i2c, ssd1307fb_i2c_id); static struct i2c_driver ssd1307fb_driver = { - .probe_new = ssd1307fb_probe, + .probe = ssd1307fb_probe, .remove = ssd1307fb_remove, .id_table = ssd1307fb_i2c_id, .driver = { diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c index ef8a4c5fc687..686a234f3899 100644 --- a/drivers/video/fbdev/stifb.c +++ b/drivers/video/fbdev/stifb.c @@ -1,11 +1,11 @@ /* - * linux/drivers/video/stifb.c - - * Low level Frame buffer driver for HP workstations with + * linux/drivers/video/stifb.c - + * Low level Frame buffer driver for HP workstations with * STI (standard text interface) video firmware. * * Copyright (C) 2001-2006 Helge Deller <deller@gmx.de> * Portions Copyright (C) 2001 Thomas Bogendoerfer <tsbogend@alpha.franken.de> - * + * * Based on: * - linux/drivers/video/artistfb.c -- Artist frame buffer driver * Copyright (C) 2000 Philipp Rumpf <prumpf@tux.org> @@ -14,7 +14,7 @@ * - HP Xhp cfb-based X11 window driver for XFree86 * (c)Copyright 1992 Hewlett-Packard Co. * - * + * * The following graphics display devices (NGLE family) are supported by this driver: * * HPA4070A known as "HCRX", a 1280x1024 color device with 8 planes @@ -30,7 +30,7 @@ * supports 1280x1024 color displays with 8 planes. * HP710G same as HP710C, 1280x1024 grayscale only * HP710L same as HP710C, 1024x768 color only - * HP712 internal graphics support on HP9000s712 SPU, supports 640x480, + * HP712 internal graphics support on HP9000s712 SPU, supports 640x480, * 1024x768 or 1280x1024 color displays on 8 planes (Artist) * * This file is subject to the terms and conditions of the GNU General Public @@ -92,7 +92,7 @@ typedef struct { __s32 misc_video_end; } video_setup_t; -typedef struct { +typedef struct { __s16 sizeof_ngle_data; __s16 x_size_visible; /* visible screen dim in pixels */ __s16 y_size_visible; @@ -177,10 +177,10 @@ static int __initdata stifb_bpp_pref[MAX_STI_ROMS]; #endif /* DEBUG_STIFB_REGS */ -#define ENABLE 1 /* for enabling/disabling screen */ +#define ENABLE 1 /* for enabling/disabling screen */ #define DISABLE 0 -#define NGLE_LOCK(fb_info) do { } while (0) +#define NGLE_LOCK(fb_info) do { } while (0) #define NGLE_UNLOCK(fb_info) do { } while (0) static void @@ -198,9 +198,9 @@ SETUP_HW(struct stifb_info *fb) static void SETUP_FB(struct stifb_info *fb) -{ +{ unsigned int reg10_value = 0; - + SETUP_HW(fb); switch (fb->id) { @@ -210,15 +210,15 @@ SETUP_FB(struct stifb_info *fb) reg10_value = 0x13601000; break; case S9000_ID_A1439A: - if (fb->info.var.bits_per_pixel == 32) + if (fb->info.var.bits_per_pixel == 32) reg10_value = 0xBBA0A000; - else + else reg10_value = 0x13601000; break; case S9000_ID_HCRX: if (fb->info.var.bits_per_pixel == 32) reg10_value = 0xBBA0A000; - else + else reg10_value = 0x13602000; break; case S9000_ID_TIMBER: @@ -243,7 +243,7 @@ START_IMAGE_COLORMAP_ACCESS(struct stifb_info *fb) } static void -WRITE_IMAGE_COLOR(struct stifb_info *fb, int index, int color) +WRITE_IMAGE_COLOR(struct stifb_info *fb, int index, int color) { SETUP_HW(fb); WRITE_WORD(((0x100+index)<<2), fb, REG_3); @@ -251,30 +251,30 @@ WRITE_IMAGE_COLOR(struct stifb_info *fb, int index, int color) } static void -FINISH_IMAGE_COLORMAP_ACCESS(struct stifb_info *fb) -{ +FINISH_IMAGE_COLORMAP_ACCESS(struct stifb_info *fb) +{ WRITE_WORD(0x400, fb, REG_2); if (fb->info.var.bits_per_pixel == 32) { WRITE_WORD(0x83000100, fb, REG_1); } else { if (fb->id == S9000_ID_ARTIST || fb->id == CRT_ID_VISUALIZE_EG) WRITE_WORD(0x80000100, fb, REG_26); - else + else WRITE_WORD(0x80000100, fb, REG_1); } SETUP_FB(fb); } static void -SETUP_RAMDAC(struct stifb_info *fb) +SETUP_RAMDAC(struct stifb_info *fb) { SETUP_HW(fb); WRITE_WORD(0x04000000, fb, 0x1020); WRITE_WORD(0xff000000, fb, 0x1028); } -static void -CRX24_SETUP_RAMDAC(struct stifb_info *fb) +static void +CRX24_SETUP_RAMDAC(struct stifb_info *fb) { SETUP_HW(fb); WRITE_WORD(0x04000000, fb, 0x1000); @@ -286,14 +286,14 @@ CRX24_SETUP_RAMDAC(struct stifb_info *fb) } #if 0 -static void +static void HCRX_SETUP_RAMDAC(struct stifb_info *fb) { WRITE_WORD(0xffffffff, fb, REG_32); } #endif -static void +static void CRX24_SET_OVLY_MASK(struct stifb_info *fb) { SETUP_HW(fb); @@ -314,7 +314,7 @@ ENABLE_DISABLE_DISPLAY(struct stifb_info *fb, int enable) WRITE_WORD(value, fb, 0x1038); } -static void +static void CRX24_ENABLE_DISABLE_DISPLAY(struct stifb_info *fb, int enable) { unsigned int value = enable ? 0x10000000 : 0x30000000; @@ -325,11 +325,11 @@ CRX24_ENABLE_DISABLE_DISPLAY(struct stifb_info *fb, int enable) } static void -ARTIST_ENABLE_DISABLE_DISPLAY(struct stifb_info *fb, int enable) +ARTIST_ENABLE_DISABLE_DISPLAY(struct stifb_info *fb, int enable) { u32 DregsMiscVideo = REG_21; u32 DregsMiscCtl = REG_27; - + SETUP_HW(fb); if (enable) { WRITE_WORD(READ_WORD(fb, DregsMiscVideo) | 0x0A000000, fb, DregsMiscVideo); @@ -344,7 +344,7 @@ ARTIST_ENABLE_DISABLE_DISPLAY(struct stifb_info *fb, int enable) (READ_BYTE(fb, REG_16b3) - 1) #define HYPER_CONFIG_PLANES_24 0x00000100 - + #define IS_24_DEVICE(fb) \ (fb->deviceSpecificConfig & HYPER_CONFIG_PLANES_24) @@ -470,15 +470,15 @@ SETUP_ATTR_ACCESS(struct stifb_info *fb, unsigned BufferNumber) } static void -SET_ATTR_SIZE(struct stifb_info *fb, int width, int height) +SET_ATTR_SIZE(struct stifb_info *fb, int width, int height) { - /* REG_6 seems to have special values when run on a + /* REG_6 seems to have special values when run on a RDI precisionbook parisc laptop (INTERNAL_EG_DX1024 or INTERNAL_EG_X1024). The values are: 0x2f0: internal (LCD) & external display enabled 0x2a0: external display only 0x000: zero on standard artist graphic cards - */ + */ WRITE_WORD(0x00000000, fb, REG_6); WRITE_WORD((width<<16) | height, fb, REG_9); WRITE_WORD(0x05000000, fb, REG_6); @@ -486,7 +486,7 @@ SET_ATTR_SIZE(struct stifb_info *fb, int width, int height) } static void -FINISH_ATTR_ACCESS(struct stifb_info *fb) +FINISH_ATTR_ACCESS(struct stifb_info *fb) { SETUP_HW(fb); WRITE_WORD(0x00000000, fb, REG_12); @@ -499,7 +499,7 @@ elkSetupPlanes(struct stifb_info *fb) SETUP_FB(fb); } -static void +static void ngleSetupAttrPlanes(struct stifb_info *fb, int BufferNumber) { SETUP_ATTR_ACCESS(fb, BufferNumber); @@ -519,7 +519,7 @@ rattlerSetupPlanes(struct stifb_info *fb) * read mask register for overlay planes, not image planes). */ CRX24_SETUP_RAMDAC(fb); - + /* change fb->id temporarily to fool SETUP_FB() */ saved_id = fb->id; fb->id = CRX24_OVERLAY_PLANES; @@ -565,7 +565,7 @@ setNgleLutBltCtl(struct stifb_info *fb, int offsetWithinLut, int length) lutBltCtl.all = 0x80000000; lutBltCtl.fields.length = length; - switch (fb->id) + switch (fb->id) { case S9000_ID_A1439A: /* CRX24 */ if (fb->var.bits_per_pixel == 8) { @@ -576,12 +576,12 @@ setNgleLutBltCtl(struct stifb_info *fb, int offsetWithinLut, int length) lutBltCtl.fields.lutOffset = 0 * 256; } break; - + case S9000_ID_ARTIST: lutBltCtl.fields.lutType = NGLE_CMAP_INDEXED0_TYPE; lutBltCtl.fields.lutOffset = 0 * 256; break; - + default: lutBltCtl.fields.lutType = NGLE_CMAP_INDEXED0_TYPE; lutBltCtl.fields.lutOffset = 0; @@ -596,7 +596,7 @@ setNgleLutBltCtl(struct stifb_info *fb, int offsetWithinLut, int length) #endif static NgleLutBltCtl -setHyperLutBltCtl(struct stifb_info *fb, int offsetWithinLut, int length) +setHyperLutBltCtl(struct stifb_info *fb, int offsetWithinLut, int length) { NgleLutBltCtl lutBltCtl; @@ -633,7 +633,7 @@ static void hyperUndoITE(struct stifb_info *fb) /* Hardware setup for full-depth write to "magic" location */ GET_FIFO_SLOTS(fb, nFreeFifoSlots, 7); - NGLE_QUICK_SET_DST_BM_ACCESS(fb, + NGLE_QUICK_SET_DST_BM_ACCESS(fb, BA(IndexedDcd, Otc04, Ots08, AddrLong, BAJustPoint(0), BINovly, BAIndexBase(0))); NGLE_QUICK_SET_IMAGE_BITMAP_OP(fb, @@ -653,13 +653,13 @@ static void hyperUndoITE(struct stifb_info *fb) NGLE_UNLOCK(fb); } -static void +static void ngleDepth8_ClearImagePlanes(struct stifb_info *fb) { /* FIXME! */ } -static void +static void ngleDepth24_ClearImagePlanes(struct stifb_info *fb) { /* FIXME! */ @@ -675,7 +675,7 @@ ngleResetAttrPlanes(struct stifb_info *fb, unsigned int ctlPlaneReg) NGLE_LOCK(fb); GET_FIFO_SLOTS(fb, nFreeFifoSlots, 4); - NGLE_QUICK_SET_DST_BM_ACCESS(fb, + NGLE_QUICK_SET_DST_BM_ACCESS(fb, BA(IndexedDcd, Otc32, OtsIndirect, AddrLong, BAJustPoint(0), BINattr, BAIndexBase(0))); @@ -713,22 +713,22 @@ ngleResetAttrPlanes(struct stifb_info *fb, unsigned int ctlPlaneReg) /**** Finally, set the Control Plane Register back to zero: ****/ GET_FIFO_SLOTS(fb, nFreeFifoSlots, 1); NGLE_QUICK_SET_CTL_PLN_REG(fb, 0); - + NGLE_UNLOCK(fb); } - + static void ngleClearOverlayPlanes(struct stifb_info *fb, int mask, int data) { int nFreeFifoSlots = 0; u32 packed_dst; u32 packed_len; - + NGLE_LOCK(fb); /* Hardware setup */ GET_FIFO_SLOTS(fb, nFreeFifoSlots, 8); - NGLE_QUICK_SET_DST_BM_ACCESS(fb, + NGLE_QUICK_SET_DST_BM_ACCESS(fb, BA(IndexedDcd, Otc04, Ots08, AddrLong, BAJustPoint(0), BINovly, BAIndexBase(0))); @@ -736,23 +736,23 @@ ngleClearOverlayPlanes(struct stifb_info *fb, int mask, int data) NGLE_REALLY_SET_IMAGE_FG_COLOR(fb, data); NGLE_REALLY_SET_IMAGE_PLANEMASK(fb, mask); - + packed_dst = 0; packed_len = (fb->info.var.xres << 16) | fb->info.var.yres; NGLE_SET_DSTXY(fb, packed_dst); - - /* Write zeroes to overlay planes */ + + /* Write zeroes to overlay planes */ NGLE_QUICK_SET_IMAGE_BITMAP_OP(fb, IBOvals(RopSrc, MaskAddrOffset(0), BitmapExtent08, StaticReg(0), DataDynamic, MaskOtc, BGx(0), FGx(0))); - + SET_LENXY_START_RECFILL(fb, packed_len); NGLE_UNLOCK(fb); } -static void +static void hyperResetPlanes(struct stifb_info *fb, int enable) { unsigned int controlPlaneReg; @@ -783,7 +783,7 @@ hyperResetPlanes(struct stifb_info *fb, int enable) ngleClearOverlayPlanes(fb, 0xff, 255); /************************************************** - ** Also need to counteract ITE settings + ** Also need to counteract ITE settings **************************************************/ hyperUndoITE(fb); break; @@ -803,13 +803,13 @@ hyperResetPlanes(struct stifb_info *fb, int enable) ngleResetAttrPlanes(fb, controlPlaneReg); break; } - + NGLE_UNLOCK(fb); } /* Return pointer to in-memory structure holding ELK device-dependent ROM values. */ -static void +static void ngleGetDeviceRomData(struct stifb_info *fb) { #if 0 @@ -821,7 +821,7 @@ XXX: FIXME: !!! char *pCard8; int i; char *mapOrigin = NULL; - + int romTableIdx; pPackedDevRomData = fb->ngle_rom; @@ -888,7 +888,7 @@ SETUP_HCRX(struct stifb_info *fb) /* Initialize Hyperbowl registers */ GET_FIFO_SLOTS(fb, nFreeFifoSlots, 7); - + if (IS_24_DEVICE(fb)) { hyperbowl = (fb->info.var.bits_per_pixel == 32) ? HYPERBOWL_MODE01_8_24_LUT0_TRANSPARENT_LUT1_OPAQUE : @@ -897,9 +897,9 @@ SETUP_HCRX(struct stifb_info *fb) /* First write to Hyperbowl must happen twice (bug) */ WRITE_WORD(hyperbowl, fb, REG_40); WRITE_WORD(hyperbowl, fb, REG_40); - + WRITE_WORD(HYPERBOWL_MODE2_8_24, fb, REG_39); - + WRITE_WORD(0x014c0148, fb, REG_42); /* Set lut 0 to be the direct color */ WRITE_WORD(0x404c4048, fb, REG_43); WRITE_WORD(0x034c0348, fb, REG_44); @@ -990,7 +990,7 @@ stifb_setcolreg(u_int regno, u_int red, u_int green, 0, /* Offset w/i LUT */ 256); /* Load entire LUT */ NGLE_BINC_SET_SRCADDR(fb, - NGLE_LONG_FB_ADDRESS(0, 0x100, 0)); + NGLE_LONG_FB_ADDRESS(0, 0x100, 0)); /* 0x100 is same as used in WRITE_IMAGE_COLOR() */ START_COLORMAPLOAD(fb, lutBltCtl.all); SETUP_FB(fb); @@ -1028,7 +1028,7 @@ stifb_blank(int blank_mode, struct fb_info *info) ENABLE_DISABLE_DISPLAY(fb, enable); break; } - + SETUP_FB(fb); return 0; } @@ -1114,15 +1114,15 @@ stifb_init_display(struct stifb_info *fb) /* HCRX specific initialization */ SETUP_HCRX(fb); - + /* if (id == S9000_ID_HCRX) hyperInitSprite(fb); else ngleInitSprite(fb); */ - - /* Initialize the image planes. */ + + /* Initialize the image planes. */ switch (id) { case S9000_ID_HCRX: hyperResetPlanes(fb, ENABLE); @@ -1194,7 +1194,7 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) fb = kzalloc(sizeof(*fb), GFP_ATOMIC); if (!fb) return -ENOMEM; - + info = &fb->info; /* set struct to a known state */ @@ -1235,7 +1235,7 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) dev_name, fb->id); goto out_err0; } - + /* default to 8 bpp on most graphic chips */ bpp = 8; xres = sti_onscreen_x(fb->sti); @@ -1256,7 +1256,7 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) fb->id = S9000_ID_A1659A; break; case S9000_ID_TIMBER: /* HP9000/710 Any (may be a grayscale device) */ - if (strstr(dev_name, "GRAYSCALE") || + if (strstr(dev_name, "GRAYSCALE") || strstr(dev_name, "Grayscale") || strstr(dev_name, "grayscale")) var->grayscale = 1; @@ -1295,16 +1295,16 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) case CRT_ID_VISUALIZE_EG: case S9000_ID_ARTIST: /* Artist */ break; - default: + default: #ifdef FALLBACK_TO_1BPP - printk(KERN_WARNING + printk(KERN_WARNING "stifb: Unsupported graphics card (id=0x%08x) " "- now trying 1bpp mode instead\n", fb->id); bpp = 1; /* default to 1 bpp */ break; #else - printk(KERN_WARNING + printk(KERN_WARNING "stifb: Unsupported graphics card (id=0x%08x) " "- skipping.\n", fb->id); @@ -1320,11 +1320,11 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) fix->line_length = (fb->sti->glob_cfg->total_x * bpp) / 8; if (!fix->line_length) fix->line_length = 2048; /* default */ - + /* limit fbsize to max visible screen size */ if (fix->smem_len > yres*fix->line_length) fix->smem_len = ALIGN(yres*fix->line_length, 4*1024*1024); - + fix->accel = FB_ACCEL_NONE; switch (bpp) { @@ -1350,7 +1350,7 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) default: break; } - + var->xres = var->xres_virtual = xres; var->yres = var->yres_virtual = yres; var->bits_per_pixel = bpp; @@ -1379,7 +1379,7 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) fix->smem_start, fix->smem_start+fix->smem_len); goto out_err2; } - + if (!request_mem_region(fix->mmio_start, fix->mmio_len, "stifb mmio")) { printk(KERN_ERR "stifb: cannot reserve sti mmio region 0x%04lx-0x%04lx\n", fix->mmio_start, fix->mmio_start+fix->mmio_len); @@ -1393,11 +1393,11 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) fb_info(&fb->info, "%s %dx%d-%d frame buffer device, %s, id: %04x, mmio: 0x%04lx\n", fix->id, - var->xres, + var->xres, var->yres, var->bits_per_pixel, dev_name, - fb->id, + fb->id, fix->mmio_start); return 0; @@ -1413,6 +1413,7 @@ out_err1: iounmap(info->screen_base); out_err0: kfree(fb); + sti->info = NULL; return -ENXIO; } @@ -1426,7 +1427,7 @@ static int __init stifb_init(void) struct sti_struct *sti; struct sti_struct *def_sti; int i; - + #ifndef MODULE char *option = NULL; @@ -1438,7 +1439,7 @@ static int __init stifb_init(void) printk(KERN_INFO "stifb: disabled by \"stifb=off\" kernel parameter\n"); return -ENXIO; } - + def_sti = sti_get_rom(0); if (def_sti) { for (i = 1; i <= MAX_STI_ROMS; i++) { @@ -1472,7 +1473,7 @@ stifb_cleanup(void) { struct sti_struct *sti; int i; - + for (i = 1; i <= MAX_STI_ROMS; i++) { sti = sti_get_rom(i); if (!sti) @@ -1495,10 +1496,10 @@ int __init stifb_setup(char *options) { int i; - + if (!options || !*options) return 1; - + if (strncmp(options, "off", 3) == 0) { stifb_disabled = 1; options += 3; diff --git a/drivers/video/fbdev/udlfb.c b/drivers/video/fbdev/udlfb.c index 216d49c9d47e..dabc30a09f96 100644 --- a/drivers/video/fbdev/udlfb.c +++ b/drivers/video/fbdev/udlfb.c @@ -27,6 +27,8 @@ #include <video/udlfb.h> #include "edid.h" +#define OUT_EP_NUM 1 /* The endpoint number we will use */ + static const struct fb_fix_screeninfo dlfb_fix = { .id = "udlfb", .type = FB_TYPE_PACKED_PIXELS, @@ -1541,24 +1543,16 @@ static const struct device_attribute fb_device_attrs[] = { static int dlfb_select_std_channel(struct dlfb_data *dlfb) { int ret; - void *buf; static const u8 set_def_chn[] = { 0x57, 0xCD, 0xDC, 0xA7, 0x1C, 0x88, 0x5E, 0x15, 0x60, 0xFE, 0xC6, 0x97, 0x16, 0x3D, 0x47, 0xF2 }; - buf = kmemdup(set_def_chn, sizeof(set_def_chn), GFP_KERNEL); - - if (!buf) - return -ENOMEM; - - ret = usb_control_msg(dlfb->udev, usb_sndctrlpipe(dlfb->udev, 0), - NR_USB_REQUEST_CHANNEL, + ret = usb_control_msg_send(dlfb->udev, 0, NR_USB_REQUEST_CHANNEL, (USB_DIR_OUT | USB_TYPE_VENDOR), 0, 0, - buf, sizeof(set_def_chn), USB_CTRL_SET_TIMEOUT); - - kfree(buf); + &set_def_chn, sizeof(set_def_chn), USB_CTRL_SET_TIMEOUT, + GFP_KERNEL); return ret; } @@ -1652,7 +1646,7 @@ static int dlfb_usb_probe(struct usb_interface *intf, struct fb_info *info; int retval; struct usb_device *usbdev = interface_to_usbdev(intf); - struct usb_endpoint_descriptor *out; + static u8 out_ep[] = {OUT_EP_NUM + USB_DIR_OUT, 0}; /* usb initialization */ dlfb = kzalloc(sizeof(*dlfb), GFP_KERNEL); @@ -1666,9 +1660,9 @@ static int dlfb_usb_probe(struct usb_interface *intf, dlfb->udev = usb_get_dev(usbdev); usb_set_intfdata(intf, dlfb); - retval = usb_find_common_endpoints(intf->cur_altsetting, NULL, &out, NULL, NULL); - if (retval) { - dev_err(&intf->dev, "Device should have at lease 1 bulk endpoint!\n"); + if (!usb_check_bulk_endpoints(intf, out_ep)) { + dev_err(&intf->dev, "Invalid DisplayLink device!\n"); + retval = -EINVAL; goto error; } @@ -1927,7 +1921,8 @@ retry: } /* urb->transfer_buffer_length set to actual before submit */ - usb_fill_bulk_urb(urb, dlfb->udev, usb_sndbulkpipe(dlfb->udev, 1), + usb_fill_bulk_urb(urb, dlfb->udev, + usb_sndbulkpipe(dlfb->udev, OUT_EP_NUM), buf, size, dlfb_urb_completion, unode); urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; diff --git a/drivers/video/fbdev/valkyriefb.c b/drivers/video/fbdev/valkyriefb.c index 1007023a5e88..b166b7cfe0e5 100644 --- a/drivers/video/fbdev/valkyriefb.c +++ b/drivers/video/fbdev/valkyriefb.c @@ -1,7 +1,7 @@ /* * valkyriefb.c -- frame buffer device for the PowerMac 'valkyrie' display * - * Created 8 August 1998 by + * Created 8 August 1998 by * Martin Costabel <costabel@wanadoo.fr> and Kevin Schoedel * * Vmode-switching changes and vmode 15/17 modifications created 29 August @@ -77,13 +77,13 @@ struct fb_info_valkyrie { struct fb_par_valkyrie par; struct cmap_regs __iomem *cmap_regs; unsigned long cmap_regs_phys; - + struct valkyrie_regs __iomem *valkyrie_regs; unsigned long valkyrie_regs_phys; - + __u8 __iomem *frame_buffer; unsigned long frame_buffer_phys; - + int sense; unsigned long total_vram; @@ -244,7 +244,7 @@ static inline int valkyrie_vram_reqd(int video_mode, int color_mode) { int pitch; struct valkyrie_regvals *init = valkyrie_reg_init[video_mode-1]; - + if ((pitch = init->pitch[color_mode]) == 0) pitch = 2 * init->pitch[0]; return init->vres * pitch; @@ -467,7 +467,7 @@ static int valkyrie_var_to_par(struct fb_var_screeninfo *var, printk(KERN_ERR "valkyriefb: vmode %d not valid.\n", vmode); return -EINVAL; } - + if (cmode != CMODE_8 && cmode != CMODE_16) { printk(KERN_ERR "valkyriefb: cmode %d not valid.\n", cmode); return -EINVAL; @@ -516,7 +516,7 @@ static void valkyrie_init_fix(struct fb_fix_screeninfo *fix, struct fb_info_valk fix->ywrapstep = 0; fix->ypanstep = 0; fix->xpanstep = 0; - + } /* Fix must already be inited above */ diff --git a/drivers/video/fbdev/vfb.c b/drivers/video/fbdev/vfb.c index a94573997d15..6f1990969361 100644 --- a/drivers/video/fbdev/vfb.c +++ b/drivers/video/fbdev/vfb.c @@ -111,7 +111,7 @@ static u_long get_line_length(int xres_virtual, int bpp) * First part, xxxfb_check_var, must not write anything * to hardware, it should only verify and adjust var. * This means it doesn't alter par but it does use hardware - * data from it to check this var. + * data from it to check this var. */ static int vfb_check_var(struct fb_var_screeninfo *var, @@ -169,7 +169,7 @@ static int vfb_check_var(struct fb_var_screeninfo *var, /* * Now that we checked it we alter var. The reason being is that the video - * mode passed in might not work but slight changes to it might make it + * mode passed in might not work but slight changes to it might make it * work. This way we let the user know what is acceptable. */ switch (var->bits_per_pixel) { @@ -235,8 +235,8 @@ static int vfb_check_var(struct fb_var_screeninfo *var, } /* This routine actually sets the video mode. It's in here where we - * the hardware state info->par and fix which can be affected by the - * change in par. For this driver it doesn't do much. + * the hardware state info->par and fix which can be affected by the + * change in par. For this driver it doesn't do much. */ static int vfb_set_par(struct fb_info *info) { @@ -379,7 +379,7 @@ static int vfb_pan_display(struct fb_var_screeninfo *var, } /* - * Most drivers don't need their own mmap function + * Most drivers don't need their own mmap function */ static int vfb_mmap(struct fb_info *info, diff --git a/drivers/xen/pvcalls-back.c b/drivers/xen/pvcalls-back.c index 1f5219e12cc3..7beaf2c41fbb 100644 --- a/drivers/xen/pvcalls-back.c +++ b/drivers/xen/pvcalls-back.c @@ -325,8 +325,10 @@ static struct sock_mapping *pvcalls_new_active_socket( void *page; map = kzalloc(sizeof(*map), GFP_KERNEL); - if (map == NULL) + if (map == NULL) { + sock_release(sock); return NULL; + } map->fedata = fedata; map->sock = sock; @@ -418,10 +420,8 @@ static int pvcalls_back_connect(struct xenbus_device *dev, req->u.connect.ref, req->u.connect.evtchn, sock); - if (!map) { + if (!map) ret = -EFAULT; - sock_release(sock); - } out: rsp = RING_GET_RESPONSE(&fedata->ring, fedata->ring.rsp_prod_pvt++); @@ -561,7 +561,6 @@ static void __pvcalls_back_accept(struct work_struct *work) sock); if (!map) { ret = -EFAULT; - sock_release(sock); goto out_error; } diff --git a/fs/Kconfig b/fs/Kconfig index cc07a0cd3172..18d034ec7953 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -368,14 +368,7 @@ config NFS_V4_2_SSC_HELPER source "net/sunrpc/Kconfig" source "fs/ceph/Kconfig" -source "fs/cifs/Kconfig" -source "fs/ksmbd/Kconfig" - -config SMBFS_COMMON - tristate - default y if CIFS=y || SMB_SERVER=y - default m if CIFS=m || SMB_SERVER=m - +source "fs/smb/Kconfig" source "fs/coda/Kconfig" source "fs/afs/Kconfig" source "fs/9p/Kconfig" diff --git a/fs/Makefile b/fs/Makefile index 834f1c3dba46..5bfdbf0d7037 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -95,9 +95,7 @@ obj-$(CONFIG_LOCKD) += lockd/ obj-$(CONFIG_NLS) += nls/ obj-y += unicode/ obj-$(CONFIG_SYSV_FS) += sysv/ -obj-$(CONFIG_SMBFS_COMMON) += smbfs_common/ -obj-$(CONFIG_CIFS) += cifs/ -obj-$(CONFIG_SMB_SERVER) += ksmbd/ +obj-$(CONFIG_SMBFS) += smb/ obj-$(CONFIG_HPFS_FS) += hpfs/ obj-$(CONFIG_NTFS_FS) += ntfs/ obj-$(CONFIG_NTFS3_FS) += ntfs3/ diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 4dd97afa536c..5219182e52e1 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -1358,6 +1358,7 @@ static int afs_mkdir(struct mnt_idmap *idmap, struct inode *dir, op->dentry = dentry; op->create.mode = S_IFDIR | mode; op->create.reason = afs_edit_dir_for_mkdir; + op->mtime = current_time(dir); op->ops = &afs_mkdir_operation; return afs_do_sync_operation(op); } @@ -1661,6 +1662,7 @@ static int afs_create(struct mnt_idmap *idmap, struct inode *dir, op->dentry = dentry; op->create.mode = S_IFREG | mode; op->create.reason = afs_edit_dir_for_create; + op->mtime = current_time(dir); op->ops = &afs_create_operation; return afs_do_sync_operation(op); @@ -1796,6 +1798,7 @@ static int afs_symlink(struct mnt_idmap *idmap, struct inode *dir, op->ops = &afs_symlink_operation; op->create.reason = afs_edit_dir_for_symlink; op->create.symlink = content; + op->mtime = current_time(dir); return afs_do_sync_operation(op); error: diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index e54f0884802a..79336fa853db 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -45,7 +45,8 @@ static int check_extent_in_eb(struct btrfs_backref_walk_ctx *ctx, int root_count; bool cached; - if (!btrfs_file_extent_compression(eb, fi) && + if (!ctx->ignore_extent_item_pos && + !btrfs_file_extent_compression(eb, fi) && !btrfs_file_extent_encryption(eb, fi) && !btrfs_file_extent_other_encoding(eb, fi)) { u64 data_offset; @@ -552,7 +553,7 @@ static int add_all_parents(struct btrfs_backref_walk_ctx *ctx, count++; else goto next; - if (!ctx->ignore_extent_item_pos) { + if (!ctx->skip_inode_ref_list) { ret = check_extent_in_eb(ctx, &key, eb, fi, &eie); if (ret == BTRFS_ITERATE_EXTENT_INODES_STOP || ret < 0) @@ -564,7 +565,7 @@ static int add_all_parents(struct btrfs_backref_walk_ctx *ctx, eie, (void **)&old, GFP_NOFS); if (ret < 0) break; - if (!ret && !ctx->ignore_extent_item_pos) { + if (!ret && !ctx->skip_inode_ref_list) { while (old->next) old = old->next; old->next = eie; @@ -1606,7 +1607,7 @@ again: goto out; } if (ref->count && ref->parent) { - if (!ctx->ignore_extent_item_pos && !ref->inode_list && + if (!ctx->skip_inode_ref_list && !ref->inode_list && ref->level == 0) { struct btrfs_tree_parent_check check = { 0 }; struct extent_buffer *eb; @@ -1647,7 +1648,7 @@ again: (void **)&eie, GFP_NOFS); if (ret < 0) goto out; - if (!ret && !ctx->ignore_extent_item_pos) { + if (!ret && !ctx->skip_inode_ref_list) { /* * We've recorded that parent, so we must extend * its inode list here. @@ -1743,7 +1744,7 @@ int btrfs_find_all_leafs(struct btrfs_backref_walk_ctx *ctx) static int btrfs_find_all_roots_safe(struct btrfs_backref_walk_ctx *ctx) { const u64 orig_bytenr = ctx->bytenr; - const bool orig_ignore_extent_item_pos = ctx->ignore_extent_item_pos; + const bool orig_skip_inode_ref_list = ctx->skip_inode_ref_list; bool roots_ulist_allocated = false; struct ulist_iterator uiter; int ret = 0; @@ -1764,7 +1765,7 @@ static int btrfs_find_all_roots_safe(struct btrfs_backref_walk_ctx *ctx) roots_ulist_allocated = true; } - ctx->ignore_extent_item_pos = true; + ctx->skip_inode_ref_list = true; ULIST_ITER_INIT(&uiter); while (1) { @@ -1789,7 +1790,7 @@ static int btrfs_find_all_roots_safe(struct btrfs_backref_walk_ctx *ctx) ulist_free(ctx->refs); ctx->refs = NULL; ctx->bytenr = orig_bytenr; - ctx->ignore_extent_item_pos = orig_ignore_extent_item_pos; + ctx->skip_inode_ref_list = orig_skip_inode_ref_list; return ret; } @@ -1912,7 +1913,7 @@ int btrfs_is_data_extent_shared(struct btrfs_inode *inode, u64 bytenr, goto out_trans; } - walk_ctx.ignore_extent_item_pos = true; + walk_ctx.skip_inode_ref_list = true; walk_ctx.trans = trans; walk_ctx.fs_info = fs_info; walk_ctx.refs = &ctx->refs; diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h index ef6bbea3f456..1616e3e3f1e4 100644 --- a/fs/btrfs/backref.h +++ b/fs/btrfs/backref.h @@ -60,6 +60,12 @@ struct btrfs_backref_walk_ctx { * @extent_item_pos is ignored. */ bool ignore_extent_item_pos; + /* + * If true and bytenr corresponds to a data extent, then the inode list + * (each member describing inode number, file offset and root) is not + * added to each reference added to the @refs ulist. + */ + bool skip_inode_ref_list; /* A valid transaction handle or NULL. */ struct btrfs_trans_handle *trans; /* diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c index 5379c4714905..b3ad0f51e616 100644 --- a/fs/btrfs/bio.c +++ b/fs/btrfs/bio.c @@ -330,7 +330,7 @@ static void btrfs_end_bio_work(struct work_struct *work) if (bbio->inode && !(bbio->bio.bi_opf & REQ_META)) btrfs_check_read_bio(bbio, bbio->bio.bi_private); else - bbio->end_io(bbio); + btrfs_orig_bbio_end_io(bbio); } static void btrfs_simple_end_io(struct bio *bio) @@ -811,10 +811,6 @@ void btrfs_submit_repair_write(struct btrfs_bio *bbio, int mirror_num, bool dev_ goto fail; if (dev_replace) { - if (btrfs_op(&bbio->bio) == BTRFS_MAP_WRITE && btrfs_is_zoned(fs_info)) { - bbio->bio.bi_opf &= ~REQ_OP_WRITE; - bbio->bio.bi_opf |= REQ_OP_ZONE_APPEND; - } ASSERT(smap.dev == fs_info->dev_replace.srcdev); smap.dev = fs_info->dev_replace.tgtdev; } diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 957ad1c31c4f..590b03560265 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -2818,10 +2818,20 @@ int btrfs_inc_block_group_ro(struct btrfs_block_group *cache, } ret = inc_block_group_ro(cache, 0); - if (!do_chunk_alloc || ret == -ETXTBSY) - goto unlock_out; if (!ret) goto out; + if (ret == -ETXTBSY) + goto unlock_out; + + /* + * Skip chunk alloction if the bg is SYSTEM, this is to avoid system + * chunk allocation storm to exhaust the system chunk array. Otherwise + * we still want to try our best to mark the block group read-only. + */ + if (!do_chunk_alloc && ret == -ENOSPC && + (cache->flags & BTRFS_BLOCK_GROUP_SYSTEM)) + goto unlock_out; + alloc_flags = btrfs_get_alloc_profile(fs_info, cache->space_info->flags); ret = btrfs_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE); if (ret < 0) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 59ea049fe7ee..2b1b227505f3 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -96,7 +96,7 @@ static void csum_tree_block(struct extent_buffer *buf, u8 *result) crypto_shash_update(shash, kaddr + BTRFS_CSUM_SIZE, first_page_part - BTRFS_CSUM_SIZE); - for (i = 1; i < num_pages; i++) { + for (i = 1; i < num_pages && INLINE_EXTENT_BUFFER_PAGES > 1; i++) { kaddr = page_address(buf->pages[i]); crypto_shash_update(shash, kaddr, PAGE_SIZE); } @@ -3121,23 +3121,34 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info) { int ret; const bool cache_opt = btrfs_test_opt(fs_info, SPACE_CACHE); - bool clear_free_space_tree = false; + bool rebuild_free_space_tree = false; if (btrfs_test_opt(fs_info, CLEAR_CACHE) && btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) { - clear_free_space_tree = true; + rebuild_free_space_tree = true; } else if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) && !btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID)) { btrfs_warn(fs_info, "free space tree is invalid"); - clear_free_space_tree = true; + rebuild_free_space_tree = true; } - if (clear_free_space_tree) { - btrfs_info(fs_info, "clearing free space tree"); - ret = btrfs_clear_free_space_tree(fs_info); + if (rebuild_free_space_tree) { + btrfs_info(fs_info, "rebuilding free space tree"); + ret = btrfs_rebuild_free_space_tree(fs_info); if (ret) { btrfs_warn(fs_info, - "failed to clear free space tree: %d", ret); + "failed to rebuild free space tree: %d", ret); + goto out; + } + } + + if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) && + !btrfs_test_opt(fs_info, FREE_SPACE_TREE)) { + btrfs_info(fs_info, "disabling free space tree"); + ret = btrfs_delete_free_space_tree(fs_info); + if (ret) { + btrfs_warn(fs_info, + "failed to disable free space tree: %d", ret); goto out; } } @@ -4925,7 +4936,11 @@ static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root) */ inode = igrab(&btrfs_inode->vfs_inode); if (inode) { + unsigned int nofs_flag; + + nofs_flag = memalloc_nofs_save(); invalidate_inode_pages2(inode->i_mapping); + memalloc_nofs_restore(nofs_flag); iput(inode); } spin_lock(&root->delalloc_lock); @@ -5031,7 +5046,12 @@ static void btrfs_cleanup_bg_io(struct btrfs_block_group *cache) inode = cache->io_ctl.inode; if (inode) { + unsigned int nofs_flag; + + nofs_flag = memalloc_nofs_save(); invalidate_inode_pages2(inode->i_mapping); + memalloc_nofs_restore(nofs_flag); + BTRFS_I(inode)->generation = 0; cache->io_ctl.inode = NULL; iput(inode); diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index cd4cce9ba443..d1cd0a692f8e 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -792,7 +792,9 @@ blk_status_t btrfs_csum_one_bio(struct btrfs_bio *bbio) sums = kvzalloc(btrfs_ordered_sum_size(fs_info, bytes_left), GFP_KERNEL); memalloc_nofs_restore(nofs_flag); - BUG_ON(!sums); /* -ENOMEM */ + if (!sums) + return BLK_STS_RESOURCE; + sums->len = bytes_left; ordered = btrfs_lookup_ordered_extent(inode, offset); diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index d84cef89cdff..cf98a3c05480 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -870,15 +870,16 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, } spin_lock(&ctl->tree_lock); ret = link_free_space(ctl, e); - ctl->total_bitmaps++; - recalculate_thresholds(ctl); - spin_unlock(&ctl->tree_lock); if (ret) { + spin_unlock(&ctl->tree_lock); btrfs_err(fs_info, "Duplicate entries in free space cache, dumping"); kmem_cache_free(btrfs_free_space_cachep, e); goto free_cache; } + ctl->total_bitmaps++; + recalculate_thresholds(ctl); + spin_unlock(&ctl->tree_lock); list_add_tail(&e->list, &bitmaps); } diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index 4d155a48ec59..b21da1446f2a 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -1252,7 +1252,7 @@ out: return ret; } -int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info) +int btrfs_delete_free_space_tree(struct btrfs_fs_info *fs_info) { struct btrfs_trans_handle *trans; struct btrfs_root *tree_root = fs_info->tree_root; @@ -1298,6 +1298,54 @@ abort: return ret; } +int btrfs_rebuild_free_space_tree(struct btrfs_fs_info *fs_info) +{ + struct btrfs_trans_handle *trans; + struct btrfs_key key = { + .objectid = BTRFS_FREE_SPACE_TREE_OBJECTID, + .type = BTRFS_ROOT_ITEM_KEY, + .offset = 0, + }; + struct btrfs_root *free_space_root = btrfs_global_root(fs_info, &key); + struct rb_node *node; + int ret; + + trans = btrfs_start_transaction(free_space_root, 1); + if (IS_ERR(trans)) + return PTR_ERR(trans); + + set_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); + set_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); + + ret = clear_free_space_tree(trans, free_space_root); + if (ret) + goto abort; + + node = rb_first_cached(&fs_info->block_group_cache_tree); + while (node) { + struct btrfs_block_group *block_group; + + block_group = rb_entry(node, struct btrfs_block_group, + cache_node); + ret = populate_free_space_tree(trans, block_group); + if (ret) + goto abort; + node = rb_next(node); + } + + btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE); + btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID); + clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); + + ret = btrfs_commit_transaction(trans); + clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); + return ret; +abort: + btrfs_abort_transaction(trans, ret); + btrfs_end_transaction(trans); + return ret; +} + static int __add_block_group_free_space(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path) diff --git a/fs/btrfs/free-space-tree.h b/fs/btrfs/free-space-tree.h index dc2463e4cfe3..6d5551d0ced8 100644 --- a/fs/btrfs/free-space-tree.h +++ b/fs/btrfs/free-space-tree.h @@ -18,7 +18,8 @@ struct btrfs_caching_control; void set_free_space_tree_thresholds(struct btrfs_block_group *block_group); int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info); -int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info); +int btrfs_delete_free_space_tree(struct btrfs_fs_info *fs_info); +int btrfs_rebuild_free_space_tree(struct btrfs_fs_info *fs_info); int load_free_space_tree(struct btrfs_caching_control *caching_ctl); int add_block_group_free_space(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 57d070025c7a..19c707bc8801 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3108,6 +3108,9 @@ int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) btrfs_rewrite_logical_zoned(ordered_extent); btrfs_zone_finish_endio(fs_info, ordered_extent->disk_bytenr, ordered_extent->disk_num_bytes); + } else if (btrfs_is_data_reloc_root(inode->root)) { + btrfs_zone_finish_endio(fs_info, ordered_extent->disk_bytenr, + ordered_extent->disk_num_bytes); } if (test_bit(BTRFS_ORDERED_TRUNCATED, &ordered_extent->flags)) { diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index b93c96213304..497b9dbd8a13 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -151,10 +151,10 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type) pr_cont("shared data backref parent %llu count %u\n", offset, btrfs_shared_data_ref_count(eb, sref)); /* - * offset is supposed to be a tree block which - * must be aligned to nodesize. + * Offset is supposed to be a tree block which must be + * aligned to sectorsize. */ - if (!IS_ALIGNED(offset, eb->fs_info->nodesize)) + if (!IS_ALIGNED(offset, eb->fs_info->sectorsize)) pr_info( "\t\t\t(parent %llu not aligned to sectorsize %u)\n", offset, eb->fs_info->sectorsize); diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 09b1988d1791..59a06499c647 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -3422,7 +3422,7 @@ int add_data_references(struct reloc_control *rc, btrfs_release_path(path); ctx.bytenr = extent_key->objectid; - ctx.ignore_extent_item_pos = true; + ctx.skip_inode_ref_list = true; ctx.fs_info = rc->extent_root->fs_info; ret = btrfs_find_all_leafs(&ctx); diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 836725a19661..7c666517d3d3 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -1137,6 +1137,35 @@ static void scrub_write_endio(struct btrfs_bio *bbio) wake_up(&stripe->io_wait); } +static void scrub_submit_write_bio(struct scrub_ctx *sctx, + struct scrub_stripe *stripe, + struct btrfs_bio *bbio, bool dev_replace) +{ + struct btrfs_fs_info *fs_info = sctx->fs_info; + u32 bio_len = bbio->bio.bi_iter.bi_size; + u32 bio_off = (bbio->bio.bi_iter.bi_sector << SECTOR_SHIFT) - + stripe->logical; + + fill_writer_pointer_gap(sctx, stripe->physical + bio_off); + atomic_inc(&stripe->pending_io); + btrfs_submit_repair_write(bbio, stripe->mirror_num, dev_replace); + if (!btrfs_is_zoned(fs_info)) + return; + /* + * For zoned writeback, queue depth must be 1, thus we must wait for + * the write to finish before the next write. + */ + wait_scrub_stripe_io(stripe); + + /* + * And also need to update the write pointer if write finished + * successfully. + */ + if (!test_bit(bio_off >> fs_info->sectorsize_bits, + &stripe->write_error_bitmap)) + sctx->write_pointer += bio_len; +} + /* * Submit the write bio(s) for the sectors specified by @write_bitmap. * @@ -1155,7 +1184,6 @@ static void scrub_write_sectors(struct scrub_ctx *sctx, struct scrub_stripe *str { struct btrfs_fs_info *fs_info = stripe->bg->fs_info; struct btrfs_bio *bbio = NULL; - const bool zoned = btrfs_is_zoned(fs_info); int sector_nr; for_each_set_bit(sector_nr, &write_bitmap, stripe->nr_sectors) { @@ -1168,13 +1196,7 @@ static void scrub_write_sectors(struct scrub_ctx *sctx, struct scrub_stripe *str /* Cannot merge with previous sector, submit the current one. */ if (bbio && sector_nr && !test_bit(sector_nr - 1, &write_bitmap)) { - fill_writer_pointer_gap(sctx, stripe->physical + - (sector_nr << fs_info->sectorsize_bits)); - atomic_inc(&stripe->pending_io); - btrfs_submit_repair_write(bbio, stripe->mirror_num, dev_replace); - /* For zoned writeback, queue depth must be 1. */ - if (zoned) - wait_scrub_stripe_io(stripe); + scrub_submit_write_bio(sctx, stripe, bbio, dev_replace); bbio = NULL; } if (!bbio) { @@ -1187,14 +1209,8 @@ static void scrub_write_sectors(struct scrub_ctx *sctx, struct scrub_stripe *str ret = bio_add_page(&bbio->bio, page, fs_info->sectorsize, pgoff); ASSERT(ret == fs_info->sectorsize); } - if (bbio) { - fill_writer_pointer_gap(sctx, bbio->bio.bi_iter.bi_sector << - SECTOR_SHIFT); - atomic_inc(&stripe->pending_io); - btrfs_submit_repair_write(bbio, stripe->mirror_num, dev_replace); - if (zoned) - wait_scrub_stripe_io(stripe); - } + if (bbio) + scrub_submit_write_bio(sctx, stripe, bbio, dev_replace); } /* @@ -2518,13 +2534,20 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, if (ret == 0) { ro_set = 1; - } else if (ret == -ENOSPC && !sctx->is_dev_replace) { + } else if (ret == -ENOSPC && !sctx->is_dev_replace && + !(cache->flags & BTRFS_BLOCK_GROUP_RAID56_MASK)) { /* * btrfs_inc_block_group_ro return -ENOSPC when it * failed in creating new chunk for metadata. * It is not a problem for scrub, because * metadata are always cowed, and our scrub paused * commit_transactions. + * + * For RAID56 chunks, we have to mark them read-only + * for scrub, as later we would use our own cache + * out of RAID56 realm. + * Thus we want the RAID56 bg to be marked RO to + * prevent RMW from screwing up out cache. */ ro_set = 0; } else if (ret == -ETXTBSY) { diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 0f2f915e42b0..ec18e2210602 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -828,8 +828,7 @@ out: ret = -EINVAL; } if (btrfs_fs_compat_ro(info, BLOCK_GROUP_TREE) && - (btrfs_test_opt(info, CLEAR_CACHE) || - !btrfs_test_opt(info, FREE_SPACE_TREE))) { + !btrfs_test_opt(info, FREE_SPACE_TREE)) { btrfs_err(info, "cannot disable free space tree with block-group-tree feature"); ret = -EINVAL; } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 9b212e8c70cc..d2755d5e338b 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -6158,7 +6158,7 @@ static int log_delayed_deletions_incremental(struct btrfs_trans_handle *trans, { struct btrfs_root *log = inode->root->log_root; const struct btrfs_delayed_item *curr; - u64 last_range_start; + u64 last_range_start = 0; u64 last_range_end = 0; struct btrfs_key key; diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index d51057608fc3..39828af4a4e8 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -122,10 +122,9 @@ static int sb_write_pointer(struct block_device *bdev, struct blk_zone *zones, int i; for (i = 0; i < BTRFS_NR_SB_LOG_ZONES; i++) { - u64 bytenr; - - bytenr = ((zones[i].start + zones[i].len) - << SECTOR_SHIFT) - BTRFS_SUPER_INFO_SIZE; + u64 zone_end = (zones[i].start + zones[i].capacity) << SECTOR_SHIFT; + u64 bytenr = ALIGN_DOWN(zone_end, BTRFS_SUPER_INFO_SIZE) - + BTRFS_SUPER_INFO_SIZE; page[i] = read_cache_page_gfp(mapping, bytenr >> PAGE_SHIFT, GFP_NOFS); @@ -1610,11 +1609,11 @@ void btrfs_redirty_list_add(struct btrfs_transaction *trans, !list_empty(&eb->release_list)) return; + memzero_extent_buffer(eb, 0, eb->len); + set_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags); set_extent_buffer_dirty(eb); set_extent_bits_nowait(&trans->dirty_pages, eb->start, eb->start + eb->len - 1, EXTENT_DIRTY); - memzero_extent_buffer(eb, 0, eb->len); - set_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags); spin_lock(&trans->releasing_ebs_lock); list_add_tail(&eb->release_list, &trans->releasing_ebs); diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 29cf00220b09..4c0f22acf53d 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -3942,7 +3942,7 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg) struct dentry *dentry; struct ceph_cap *cap; char *path; - int pathlen = 0, err = 0; + int pathlen = 0, err; u64 pathbase; u64 snap_follows; @@ -3965,6 +3965,7 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg) cap = __get_cap_for_mds(ci, mds); if (!cap) { spin_unlock(&ci->i_ceph_lock); + err = 0; goto out_err; } dout(" adding %p ino %llx.%llx cap %p %lld %s\n", diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 87007203f130..0b236ebd989f 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -1111,6 +1111,19 @@ skip_inode: continue; adjust_snap_realm_parent(mdsc, child, realm->ino); } + } else { + /* + * In the non-split case both 'num_split_inos' and + * 'num_split_realms' should be 0, making this a no-op. + * However the MDS happens to populate 'split_realms' list + * in one of the UPDATE op cases by mistake. + * + * Skip both lists just in case to ensure that 'p' is + * positioned at the start of realm info, as expected by + * ceph_update_snap_trace(). + */ + p += sizeof(u64) * num_split_inos; + p += sizeof(u64) * num_split_realms; } /* diff --git a/fs/coredump.c b/fs/coredump.c index ece7badf701b..88740c51b942 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -371,7 +371,9 @@ static int zap_process(struct task_struct *start, int exit_code) if (t != current && !(t->flags & PF_POSTCOREDUMP)) { sigaddset(&t->pending.signal, SIGKILL); signal_wake_up(t, 1); - nr++; + /* The vhost_worker does not particpate in coredumps */ + if ((t->flags & (PF_USER_WORKER | PF_IO_WORKER)) != PF_USER_WORKER) + nr++; } } diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig index 704fb59577e0..f259d92c9720 100644 --- a/fs/erofs/Kconfig +++ b/fs/erofs/Kconfig @@ -121,6 +121,7 @@ config EROFS_FS_PCPU_KTHREAD config EROFS_FS_PCPU_KTHREAD_HIPRI bool "EROFS high priority per-CPU kthread workers" depends on EROFS_FS_ZIP && EROFS_FS_PCPU_KTHREAD + default y help This permits EROFS to configure per-CPU kthread workers to run at higher priority. diff --git a/fs/erofs/Makefile b/fs/erofs/Makefile index 99bbc597a3e9..a3a98fc3e481 100644 --- a/fs/erofs/Makefile +++ b/fs/erofs/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_EROFS_FS) += erofs.o -erofs-objs := super.o inode.o data.o namei.o dir.o utils.o pcpubuf.o sysfs.o +erofs-objs := super.o inode.o data.o namei.o dir.o utils.o sysfs.o erofs-$(CONFIG_EROFS_FS_XATTR) += xattr.o -erofs-$(CONFIG_EROFS_FS_ZIP) += decompressor.o zmap.o zdata.o +erofs-$(CONFIG_EROFS_FS_ZIP) += decompressor.o zmap.o zdata.o pcpubuf.o erofs-$(CONFIG_EROFS_FS_ZIP_LZMA) += decompressor_lzma.o erofs-$(CONFIG_EROFS_FS_ONDEMAND) += fscache.o diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index af0431a40647..1e39c03357d1 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -472,12 +472,6 @@ static inline void *erofs_vm_map_ram(struct page **pages, unsigned int count) return NULL; } -void *erofs_get_pcpubuf(unsigned int requiredpages); -void erofs_put_pcpubuf(void *ptr); -int erofs_pcpubuf_growsize(unsigned int nrpages); -void __init erofs_pcpubuf_init(void); -void erofs_pcpubuf_exit(void); - int erofs_register_sysfs(struct super_block *sb); void erofs_unregister_sysfs(struct super_block *sb); int __init erofs_init_sysfs(void); @@ -512,6 +506,11 @@ int z_erofs_load_lz4_config(struct super_block *sb, struct z_erofs_lz4_cfgs *lz4, int len); int z_erofs_map_blocks_iter(struct inode *inode, struct erofs_map_blocks *map, int flags); +void *erofs_get_pcpubuf(unsigned int requiredpages); +void erofs_put_pcpubuf(void *ptr); +int erofs_pcpubuf_growsize(unsigned int nrpages); +void __init erofs_pcpubuf_init(void); +void erofs_pcpubuf_exit(void); #else static inline void erofs_shrinker_register(struct super_block *sb) {} static inline void erofs_shrinker_unregister(struct super_block *sb) {} @@ -529,6 +528,8 @@ static inline int z_erofs_load_lz4_config(struct super_block *sb, } return 0; } +static inline void erofs_pcpubuf_init(void) {} +static inline void erofs_pcpubuf_exit(void) {} #endif /* !CONFIG_EROFS_FS_ZIP */ #ifdef CONFIG_EROFS_FS_ZIP_LZMA diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c index cd80499351e0..bbfe7ce170d2 100644 --- a/fs/erofs/xattr.c +++ b/fs/erofs/xattr.c @@ -675,7 +675,7 @@ int erofs_xattr_prefixes_init(struct super_block *sb) if (!pfs) return -ENOMEM; - if (erofs_sb_has_fragments(sbi)) + if (sbi->packed_inode) buf.inode = sbi->packed_inode; else erofs_init_metabuf(&buf, sb); diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 45f21db2303a..160b3da43aec 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -369,8 +369,6 @@ static struct kthread_worker *erofs_init_percpu_worker(int cpu) return worker; if (IS_ENABLED(CONFIG_EROFS_FS_PCPU_KTHREAD_HIPRI)) sched_set_fifo_low(worker->task); - else - sched_set_normal(worker->task, 0); return worker; } diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 094269488183..c1edde817be8 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -305,6 +305,38 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, return desc; } +static ext4_fsblk_t ext4_valid_block_bitmap_padding(struct super_block *sb, + ext4_group_t block_group, + struct buffer_head *bh) +{ + ext4_grpblk_t next_zero_bit; + unsigned long bitmap_size = sb->s_blocksize * 8; + unsigned int offset = num_clusters_in_group(sb, block_group); + + if (bitmap_size <= offset) + return 0; + + next_zero_bit = ext4_find_next_zero_bit(bh->b_data, bitmap_size, offset); + + return (next_zero_bit < bitmap_size ? next_zero_bit : 0); +} + +struct ext4_group_info *ext4_get_group_info(struct super_block *sb, + ext4_group_t group) +{ + struct ext4_group_info **grp_info; + long indexv, indexh; + + if (unlikely(group >= EXT4_SB(sb)->s_groups_count)) { + ext4_error(sb, "invalid group %u", group); + return NULL; + } + indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb)); + indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1); + grp_info = sbi_array_rcu_deref(EXT4_SB(sb), s_group_info, indexv); + return grp_info[indexh]; +} + /* * Return the block number which was discovered to be invalid, or 0 if * the block bitmap is valid. @@ -379,7 +411,7 @@ static int ext4_validate_block_bitmap(struct super_block *sb, if (buffer_verified(bh)) return 0; - if (EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) + if (!grp || EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) return -EFSCORRUPTED; ext4_lock_group(sb, block_group); @@ -402,6 +434,15 @@ static int ext4_validate_block_bitmap(struct super_block *sb, EXT4_GROUP_INFO_BBITMAP_CORRUPT); return -EFSCORRUPTED; } + blk = ext4_valid_block_bitmap_padding(sb, block_group, bh); + if (unlikely(blk != 0)) { + ext4_unlock_group(sb, block_group); + ext4_error(sb, "bg %u: block %llu: padding at end of block bitmap is not set", + block_group, blk); + ext4_mark_group_bitmap_corrupted(sb, block_group, + EXT4_GROUP_INFO_BBITMAP_CORRUPT); + return -EFSCORRUPTED; + } set_buffer_verified(bh); verified: ext4_unlock_group(sb, block_group); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 18cb2680dc39..8104a21b001a 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -918,11 +918,13 @@ do { \ * where the second inode has larger inode number * than the first * I_DATA_SEM_QUOTA - Used for quota inodes only + * I_DATA_SEM_EA - Used for ea_inodes only */ enum { I_DATA_SEM_NORMAL = 0, I_DATA_SEM_OTHER, I_DATA_SEM_QUOTA, + I_DATA_SEM_EA }; @@ -1684,6 +1686,30 @@ static inline struct ext4_inode_info *EXT4_I(struct inode *inode) return container_of(inode, struct ext4_inode_info, vfs_inode); } +static inline int ext4_writepages_down_read(struct super_block *sb) +{ + percpu_down_read(&EXT4_SB(sb)->s_writepages_rwsem); + return memalloc_nofs_save(); +} + +static inline void ext4_writepages_up_read(struct super_block *sb, int ctx) +{ + memalloc_nofs_restore(ctx); + percpu_up_read(&EXT4_SB(sb)->s_writepages_rwsem); +} + +static inline int ext4_writepages_down_write(struct super_block *sb) +{ + percpu_down_write(&EXT4_SB(sb)->s_writepages_rwsem); + return memalloc_nofs_save(); +} + +static inline void ext4_writepages_up_write(struct super_block *sb, int ctx) +{ + memalloc_nofs_restore(ctx); + percpu_up_write(&EXT4_SB(sb)->s_writepages_rwsem); +} + static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) { return ino == EXT4_ROOT_INO || @@ -2625,6 +2651,8 @@ extern void ext4_check_blocks_bitmap(struct super_block *); extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb, ext4_group_t block_group, struct buffer_head ** bh); +extern struct ext4_group_info *ext4_get_group_info(struct super_block *sb, + ext4_group_t group); extern int ext4_should_retry_alloc(struct super_block *sb, int *retries); extern struct buffer_head *ext4_read_block_bitmap_nowait(struct super_block *sb, @@ -2875,7 +2903,8 @@ typedef enum { EXT4_IGET_NORMAL = 0, EXT4_IGET_SPECIAL = 0x0001, /* OK to iget a system inode */ EXT4_IGET_HANDLE = 0x0002, /* Inode # is from a handle */ - EXT4_IGET_BAD = 0x0004 /* Allow to iget a bad inode */ + EXT4_IGET_BAD = 0x0004, /* Allow to iget a bad inode */ + EXT4_IGET_EA_INODE = 0x0008 /* Inode should contain an EA value */ } ext4_iget_flags; extern struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, @@ -3232,19 +3261,6 @@ static inline void ext4_isize_set(struct ext4_inode *raw_inode, loff_t i_size) raw_inode->i_size_high = cpu_to_le32(i_size >> 32); } -static inline -struct ext4_group_info *ext4_get_group_info(struct super_block *sb, - ext4_group_t group) -{ - struct ext4_group_info **grp_info; - long indexv, indexh; - BUG_ON(group >= EXT4_SB(sb)->s_groups_count); - indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb)); - indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1); - grp_info = sbi_array_rcu_deref(EXT4_SB(sb), s_group_info, indexv); - return grp_info[indexh]; -} - /* * Reading s_groups_count requires using smp_rmb() afterwards. See * the locking protocol documented in the comments of ext4_group_add() diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index 7bc221038c6c..595abb9e7d74 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -267,14 +267,12 @@ static void __es_find_extent_range(struct inode *inode, /* see if the extent has been cached */ es->es_lblk = es->es_len = es->es_pblk = 0; - if (tree->cache_es) { - es1 = tree->cache_es; - if (in_range(lblk, es1->es_lblk, es1->es_len)) { - es_debug("%u cached by [%u/%u) %llu %x\n", - lblk, es1->es_lblk, es1->es_len, - ext4_es_pblock(es1), ext4_es_status(es1)); - goto out; - } + es1 = READ_ONCE(tree->cache_es); + if (es1 && in_range(lblk, es1->es_lblk, es1->es_len)) { + es_debug("%u cached by [%u/%u) %llu %x\n", + lblk, es1->es_lblk, es1->es_len, + ext4_es_pblock(es1), ext4_es_status(es1)); + goto out; } es1 = __es_tree_search(&tree->root, lblk); @@ -293,7 +291,7 @@ out: } if (es1 && matching_fn(es1)) { - tree->cache_es = es1; + WRITE_ONCE(tree->cache_es, es1); es->es_lblk = es1->es_lblk; es->es_len = es1->es_len; es->es_pblk = es1->es_pblk; @@ -931,14 +929,12 @@ int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk, /* find extent in cache firstly */ es->es_lblk = es->es_len = es->es_pblk = 0; - if (tree->cache_es) { - es1 = tree->cache_es; - if (in_range(lblk, es1->es_lblk, es1->es_len)) { - es_debug("%u cached by [%u/%u)\n", - lblk, es1->es_lblk, es1->es_len); - found = 1; - goto out; - } + es1 = READ_ONCE(tree->cache_es); + if (es1 && in_range(lblk, es1->es_lblk, es1->es_len)) { + es_debug("%u cached by [%u/%u)\n", + lblk, es1->es_lblk, es1->es_len); + found = 1; + goto out; } node = tree->root.rb_node; diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index f65fdb27ce14..2a143209aa0c 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -108,6 +108,13 @@ static int ext4_fsync_journal(struct inode *inode, bool datasync, journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; tid_t commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid; + /* + * Fastcommit does not really support fsync on directories or other + * special files. Force a full commit. + */ + if (!S_ISREG(inode->i_mode)) + return ext4_force_commit(inode->i_sb); + if (journal->j_flags & JBD2_BARRIER && !jbd2_trans_will_send_data_barrier(journal, commit_tid)) *needs_barrier = true; diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c index 147b5241dd94..46c3423ddfa1 100644 --- a/fs/ext4/hash.c +++ b/fs/ext4/hash.c @@ -277,7 +277,11 @@ static int __ext4fs_dirhash(const struct inode *dir, const char *name, int len, } default: hinfo->hash = 0; - return -1; + hinfo->minor_hash = 0; + ext4_warning(dir->i_sb, + "invalid/unsupported hash tree version %u", + hinfo->hash_version); + return -EINVAL; } hash = hash & ~1; if (hash == (EXT4_HTREE_EOF_32BIT << 1)) diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 787ab89c2c26..754f961cd9fd 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -91,7 +91,7 @@ static int ext4_validate_inode_bitmap(struct super_block *sb, if (buffer_verified(bh)) return 0; - if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) + if (!grp || EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) return -EFSCORRUPTED; ext4_lock_group(sb, block_group); @@ -293,7 +293,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) } if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) { grp = ext4_get_group_info(sb, block_group); - if (unlikely(EXT4_MB_GRP_IBITMAP_CORRUPT(grp))) { + if (!grp || unlikely(EXT4_MB_GRP_IBITMAP_CORRUPT(grp))) { fatal = -EFSCORRUPTED; goto error_return; } @@ -1046,7 +1046,7 @@ got_group: * Skip groups with already-known suspicious inode * tables */ - if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) + if (!grp || EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) goto next_group; } @@ -1183,6 +1183,10 @@ got: if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) { grp = ext4_get_group_info(sb, group); + if (!grp) { + err = -EFSCORRUPTED; + goto out; + } down_read(&grp->alloc_sem); /* * protect vs itable * lazyinit @@ -1526,7 +1530,7 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group, } gdp = ext4_get_group_desc(sb, group, &group_desc_bh); - if (!gdp) + if (!gdp || !grp) goto out; /* diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 859bc4e2c9b0..5854bd5a3352 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -34,6 +34,7 @@ static int get_max_inline_xattr_value_size(struct inode *inode, struct ext4_xattr_ibody_header *header; struct ext4_xattr_entry *entry; struct ext4_inode *raw_inode; + void *end; int free, min_offs; if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) @@ -57,14 +58,23 @@ static int get_max_inline_xattr_value_size(struct inode *inode, raw_inode = ext4_raw_inode(iloc); header = IHDR(inode, raw_inode); entry = IFIRST(header); + end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; /* Compute min_offs. */ - for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) { + while (!IS_LAST_ENTRY(entry)) { + void *next = EXT4_XATTR_NEXT(entry); + + if (next >= end) { + EXT4_ERROR_INODE(inode, + "corrupt xattr in inline inode"); + return 0; + } if (!entry->e_value_inum && entry->e_value_size) { size_t offs = le16_to_cpu(entry->e_value_offs); if (offs < min_offs) min_offs = offs; } + entry = next; } free = min_offs - ((void *)entry - (void *)IFIRST(header)) - sizeof(__u32); @@ -350,7 +360,7 @@ static int ext4_update_inline_data(handle_t *handle, struct inode *inode, error = ext4_xattr_ibody_get(inode, i.name_index, i.name, value, len); - if (error == -ENODATA) + if (error < 0) goto out; BUFFER_TRACE(is.iloc.bh, "get_write_access"); @@ -1175,6 +1185,7 @@ static int ext4_finish_convert_inline_dir(handle_t *handle, ext4_initialize_dirent_tail(dir_block, inode->i_sb->s_blocksize); set_buffer_uptodate(dir_block); + unlock_buffer(dir_block); err = ext4_handle_dirty_dirblock(handle, inode, dir_block); if (err) return err; @@ -1249,6 +1260,7 @@ static int ext4_convert_inline_data_nolock(handle_t *handle, if (!S_ISDIR(inode->i_mode)) { memcpy(data_bh->b_data, buf, inline_size); set_buffer_uptodate(data_bh); + unlock_buffer(data_bh); error = ext4_handle_dirty_metadata(handle, inode, data_bh); } else { @@ -1256,7 +1268,6 @@ static int ext4_convert_inline_data_nolock(handle_t *handle, buf, inline_size); } - unlock_buffer(data_bh); out_restore: if (error) ext4_restore_inline_data(handle, inode, iloc, buf, inline_size); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 0d5ba922e411..02de439bf1f0 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2783,11 +2783,12 @@ static int ext4_writepages(struct address_space *mapping, .can_map = 1, }; int ret; + int alloc_ctx; if (unlikely(ext4_forced_shutdown(EXT4_SB(sb)))) return -EIO; - percpu_down_read(&EXT4_SB(sb)->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_read(sb); ret = ext4_do_writepages(&mpd); /* * For data=journal writeback we could have come across pages marked @@ -2796,7 +2797,7 @@ static int ext4_writepages(struct address_space *mapping, */ if (!ret && mpd.journalled_more_data) ret = ext4_do_writepages(&mpd); - percpu_up_read(&EXT4_SB(sb)->s_writepages_rwsem); + ext4_writepages_up_read(sb, alloc_ctx); return ret; } @@ -2824,17 +2825,18 @@ static int ext4_dax_writepages(struct address_space *mapping, long nr_to_write = wbc->nr_to_write; struct inode *inode = mapping->host; struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb); + int alloc_ctx; if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; - percpu_down_read(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_read(inode->i_sb); trace_ext4_writepages(inode, wbc); ret = dax_writeback_mapping_range(mapping, sbi->s_daxdev, wbc); trace_ext4_writepages_result(inode, wbc, ret, nr_to_write - wbc->nr_to_write); - percpu_up_read(&sbi->s_writepages_rwsem); + ext4_writepages_up_read(inode->i_sb, alloc_ctx); return ret; } @@ -3375,7 +3377,7 @@ static int ext4_iomap_overwrite_begin(struct inode *inode, loff_t offset, */ flags &= ~IOMAP_WRITE; ret = ext4_iomap_begin(inode, offset, length, flags, iomap, srcmap); - WARN_ON_ONCE(iomap->type != IOMAP_MAPPED); + WARN_ON_ONCE(!ret && iomap->type != IOMAP_MAPPED); return ret; } @@ -4639,6 +4641,24 @@ static inline void ext4_inode_set_iversion_queried(struct inode *inode, u64 val) inode_set_iversion_queried(inode, val); } +static const char *check_igot_inode(struct inode *inode, ext4_iget_flags flags) + +{ + if (flags & EXT4_IGET_EA_INODE) { + if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) + return "missing EA_INODE flag"; + if (ext4_test_inode_state(inode, EXT4_STATE_XATTR) || + EXT4_I(inode)->i_file_acl) + return "ea_inode with extended attributes"; + } else { + if ((EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) + return "unexpected EA_INODE flag"; + } + if (is_bad_inode(inode) && !(flags & EXT4_IGET_BAD)) + return "unexpected bad inode w/o EXT4_IGET_BAD"; + return NULL; +} + struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, ext4_iget_flags flags, const char *function, unsigned int line) @@ -4648,6 +4668,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, struct ext4_inode_info *ei; struct ext4_super_block *es = EXT4_SB(sb)->s_es; struct inode *inode; + const char *err_str; journal_t *journal = EXT4_SB(sb)->s_journal; long ret; loff_t size; @@ -4675,8 +4696,14 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + if (!(inode->i_state & I_NEW)) { + if ((err_str = check_igot_inode(inode, flags)) != NULL) { + ext4_error_inode(inode, function, line, 0, err_str); + iput(inode); + return ERR_PTR(-EFSCORRUPTED); + } return inode; + } ei = EXT4_I(inode); iloc.bh = NULL; @@ -4942,10 +4969,9 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, if (IS_CASEFOLDED(inode) && !ext4_has_feature_casefold(inode->i_sb)) ext4_error_inode(inode, function, line, 0, "casefold flag without casefold feature"); - if (is_bad_inode(inode) && !(flags & EXT4_IGET_BAD)) { - ext4_error_inode(inode, function, line, 0, - "bad inode without EXT4_IGET_BAD flag"); - ret = -EUCLEAN; + if ((err_str = check_igot_inode(inode, flags)) != NULL) { + ext4_error_inode(inode, function, line, 0, err_str); + ret = -EFSCORRUPTED; goto bad_inode; } @@ -5928,7 +5954,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) journal_t *journal; handle_t *handle; int err; - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + int alloc_ctx; /* * We have to be very careful here: changing a data block's @@ -5966,7 +5992,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) } } - percpu_down_write(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_write(inode->i_sb); jbd2_journal_lock_updates(journal); /* @@ -5983,7 +6009,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) err = jbd2_journal_flush(journal, 0); if (err < 0) { jbd2_journal_unlock_updates(journal); - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(inode->i_sb, alloc_ctx); return err; } ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA); @@ -5991,7 +6017,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) ext4_set_aops(inode); jbd2_journal_unlock_updates(journal); - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(inode->i_sb, alloc_ctx); if (val) filemap_invalidate_unlock(inode->i_mapping); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 78259bddbc4d..20f67a260df5 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -745,6 +745,8 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file, MB_CHECK_ASSERT(e4b->bd_info->bb_fragments == fragments); grp = ext4_get_group_info(sb, e4b->bd_group); + if (!grp) + return NULL; list_for_each(cur, &grp->bb_prealloc_list) { ext4_group_t groupnr; struct ext4_prealloc_space *pa; @@ -1060,9 +1062,9 @@ mb_set_largest_free_order(struct super_block *sb, struct ext4_group_info *grp) static noinline_for_stack void ext4_mb_generate_buddy(struct super_block *sb, - void *buddy, void *bitmap, ext4_group_t group) + void *buddy, void *bitmap, ext4_group_t group, + struct ext4_group_info *grp) { - struct ext4_group_info *grp = ext4_get_group_info(sb, group); struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_grpblk_t max = EXT4_CLUSTERS_PER_GROUP(sb); ext4_grpblk_t i = 0; @@ -1181,6 +1183,8 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) break; grinfo = ext4_get_group_info(sb, group); + if (!grinfo) + continue; /* * If page is uptodate then we came here after online resize * which added some new uninitialized group info structs, so @@ -1246,6 +1250,10 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) group, page->index, i * blocksize); trace_ext4_mb_buddy_bitmap_load(sb, group); grinfo = ext4_get_group_info(sb, group); + if (!grinfo) { + err = -EFSCORRUPTED; + goto out; + } grinfo->bb_fragments = 0; memset(grinfo->bb_counters, 0, sizeof(*grinfo->bb_counters) * @@ -1256,7 +1264,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) ext4_lock_group(sb, group); /* init the buddy */ memset(data, 0xff, blocksize); - ext4_mb_generate_buddy(sb, data, incore, group); + ext4_mb_generate_buddy(sb, data, incore, group, grinfo); ext4_unlock_group(sb, group); incore = NULL; } else { @@ -1370,6 +1378,9 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group, gfp_t gfp) might_sleep(); mb_debug(sb, "init group %u\n", group); this_grp = ext4_get_group_info(sb, group); + if (!this_grp) + return -EFSCORRUPTED; + /* * This ensures that we don't reinit the buddy cache * page which map to the group from which we are already @@ -1444,6 +1455,8 @@ ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group, blocks_per_page = PAGE_SIZE / sb->s_blocksize; grp = ext4_get_group_info(sb, group); + if (!grp) + return -EFSCORRUPTED; e4b->bd_blkbits = sb->s_blocksize_bits; e4b->bd_info = grp; @@ -2049,7 +2062,7 @@ static void ext4_mb_check_limits(struct ext4_allocation_context *ac, if (bex->fe_len < gex->fe_len) return; - if (finish_group) + if (finish_group || ac->ac_found > sbi->s_mb_min_to_scan) ext4_mb_use_best_found(ac, e4b); } @@ -2061,6 +2074,20 @@ static void ext4_mb_check_limits(struct ext4_allocation_context *ac, * in the context. Later, the best found extent will be used, if * mballoc can't find good enough extent. * + * The algorithm used is roughly as follows: + * + * * If free extent found is exactly as big as goal, then + * stop the scan and use it immediately + * + * * If free extent found is smaller than goal, then keep retrying + * upto a max of sbi->s_mb_max_to_scan times (default 200). After + * that stop scanning and use whatever we have. + * + * * If free extent found is bigger than goal, then keep retrying + * upto a max of sbi->s_mb_min_to_scan times (default 10) before + * stopping the scan and using the extent. + * + * * FIXME: real allocation policy is to be designed yet! */ static void ext4_mb_measure_extent(struct ext4_allocation_context *ac, @@ -2159,6 +2186,8 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); struct ext4_free_extent ex; + if (!grp) + return -EFSCORRUPTED; if (!(ac->ac_flags & (EXT4_MB_HINT_TRY_GOAL | EXT4_MB_HINT_GOAL_ONLY))) return 0; if (grp->bb_free == 0) @@ -2385,7 +2414,7 @@ static bool ext4_mb_good_group(struct ext4_allocation_context *ac, BUG_ON(cr < 0 || cr >= 4); - if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) + if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp) || !grp)) return false; free = grp->bb_free; @@ -2454,6 +2483,8 @@ static int ext4_mb_good_group_nolock(struct ext4_allocation_context *ac, ext4_grpblk_t free; int ret = 0; + if (!grp) + return -EFSCORRUPTED; if (sbi->s_mb_stats) atomic64_inc(&sbi->s_bal_cX_groups_considered[ac->ac_criteria]); if (should_lock) { @@ -2534,7 +2565,7 @@ ext4_group_t ext4_mb_prefetch(struct super_block *sb, ext4_group_t group, * prefetch once, so we avoid getblk() call, which can * be expensive. */ - if (!EXT4_MB_GRP_TEST_AND_SET_READ(grp) && + if (gdp && grp && !EXT4_MB_GRP_TEST_AND_SET_READ(grp) && EXT4_MB_GRP_NEED_INIT(grp) && ext4_free_group_clusters(sb, gdp) > 0 && !(ext4_has_group_desc_csum(sb) && @@ -2578,7 +2609,7 @@ void ext4_mb_prefetch_fini(struct super_block *sb, ext4_group_t group, gdp = ext4_get_group_desc(sb, group, NULL); grp = ext4_get_group_info(sb, group); - if (EXT4_MB_GRP_NEED_INIT(grp) && + if (grp && gdp && EXT4_MB_GRP_NEED_INIT(grp) && ext4_free_group_clusters(sb, gdp) > 0 && !(ext4_has_group_desc_csum(sb) && (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) { @@ -2837,6 +2868,8 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) sizeof(struct ext4_group_info); grinfo = ext4_get_group_info(sb, group); + if (!grinfo) + return 0; /* Load the group info in memory only if not already loaded. */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grinfo))) { err = ext4_mb_load_buddy(sb, group, &e4b); @@ -2847,7 +2880,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) buddy_loaded = 1; } - memcpy(&sg, ext4_get_group_info(sb, group), i); + memcpy(&sg, grinfo, i); if (buddy_loaded) ext4_mb_unload_buddy(&e4b); @@ -3208,8 +3241,12 @@ static int ext4_mb_init_backend(struct super_block *sb) err_freebuddy: cachep = get_groupinfo_cache(sb->s_blocksize_bits); - while (i-- > 0) - kmem_cache_free(cachep, ext4_get_group_info(sb, i)); + while (i-- > 0) { + struct ext4_group_info *grp = ext4_get_group_info(sb, i); + + if (grp) + kmem_cache_free(cachep, grp); + } i = sbi->s_group_info_size; rcu_read_lock(); group_info = rcu_dereference(sbi->s_group_info); @@ -3522,6 +3559,8 @@ int ext4_mb_release(struct super_block *sb) for (i = 0; i < ngroups; i++) { cond_resched(); grinfo = ext4_get_group_info(sb, i); + if (!grinfo) + continue; mb_group_bb_bitmap_free(grinfo); ext4_lock_group(sb, i); count = ext4_mb_cleanup_pa(grinfo); @@ -4606,6 +4645,8 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, struct ext4_free_data *entry; grp = ext4_get_group_info(sb, group); + if (!grp) + return; n = rb_first(&(grp->bb_free_root)); while (n) { @@ -4633,6 +4674,9 @@ void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, int preallocated = 0; int len; + if (!grp) + return; + /* all form of preallocation discards first load group, * so the only competing code is preallocation use. * we don't need any locking here @@ -4869,6 +4913,8 @@ adjust_bex: ei = EXT4_I(ac->ac_inode); grp = ext4_get_group_info(sb, ac->ac_b_ex.fe_group); + if (!grp) + return; pa->pa_node_lock.inode_lock = &ei->i_prealloc_lock; pa->pa_inode = ac->ac_inode; @@ -4918,6 +4964,8 @@ ext4_mb_new_group_pa(struct ext4_allocation_context *ac) atomic_add(pa->pa_free, &EXT4_SB(sb)->s_mb_preallocated); grp = ext4_get_group_info(sb, ac->ac_b_ex.fe_group); + if (!grp) + return; lg = ac->ac_lg; BUG_ON(lg == NULL); @@ -5013,7 +5061,11 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b, trace_ext4_mb_release_group_pa(sb, pa); BUG_ON(pa->pa_deleted == 0); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit); - BUG_ON(group != e4b->bd_group && pa->pa_len != 0); + if (unlikely(group != e4b->bd_group && pa->pa_len != 0)) { + ext4_warning(sb, "bad group: expected %u, group %u, pa_start %llu", + e4b->bd_group, group, pa->pa_pstart); + return 0; + } mb_free_blocks(pa->pa_inode, e4b, bit, pa->pa_len); atomic_add(pa->pa_len, &EXT4_SB(sb)->s_mb_discarded); trace_ext4_mballoc_discard(sb, NULL, group, bit, pa->pa_len); @@ -5043,6 +5095,8 @@ ext4_mb_discard_group_preallocations(struct super_block *sb, int err; int free = 0; + if (!grp) + return 0; mb_debug(sb, "discard preallocation for group %u\n", group); if (list_empty(&grp->bb_prealloc_list)) goto out_dbg; @@ -5297,6 +5351,9 @@ static inline void ext4_mb_show_pa(struct super_block *sb) struct ext4_prealloc_space *pa; ext4_grpblk_t start; struct list_head *cur; + + if (!grp) + continue; ext4_lock_group(sb, i); list_for_each(cur, &grp->bb_prealloc_list) { pa = list_entry(cur, struct ext4_prealloc_space, @@ -6064,6 +6121,7 @@ static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode, struct buffer_head *bitmap_bh = NULL; struct super_block *sb = inode->i_sb; struct ext4_group_desc *gdp; + struct ext4_group_info *grp; unsigned int overflow; ext4_grpblk_t bit; struct buffer_head *gd_bh; @@ -6089,8 +6147,8 @@ do_more: overflow = 0; ext4_get_group_no_and_offset(sb, block, &block_group, &bit); - if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT( - ext4_get_group_info(sb, block_group)))) + grp = ext4_get_group_info(sb, block_group); + if (unlikely(!grp || EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) return; /* @@ -6692,6 +6750,8 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) for (group = first_group; group <= last_group; group++) { grp = ext4_get_group_info(sb, group); + if (!grp) + continue; /* We only do this if the grp has never been initialized */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { ret = ext4_mb_init_group(sb, group, GFP_NOFS); diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index a19a9661646e..d98ac2af8199 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -408,7 +408,6 @@ static int free_ext_block(handle_t *handle, struct inode *inode) int ext4_ext_migrate(struct inode *inode) { - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); handle_t *handle; int retval = 0, i; __le32 *i_data; @@ -418,6 +417,7 @@ int ext4_ext_migrate(struct inode *inode) unsigned long max_entries; __u32 goal, tmp_csum_seed; uid_t owner[2]; + int alloc_ctx; /* * If the filesystem does not support extents, or the inode @@ -434,7 +434,7 @@ int ext4_ext_migrate(struct inode *inode) */ return retval; - percpu_down_write(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_write(inode->i_sb); /* * Worst case we can touch the allocation bitmaps and a block @@ -586,7 +586,7 @@ out_tmp_inode: unlock_new_inode(tmp_inode); iput(tmp_inode); out_unlock: - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(inode->i_sb, alloc_ctx); return retval; } @@ -605,6 +605,7 @@ int ext4_ind_migrate(struct inode *inode) ext4_fsblk_t blk; handle_t *handle; int ret, ret2 = 0; + int alloc_ctx; if (!ext4_has_feature_extents(inode->i_sb) || (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) @@ -621,7 +622,7 @@ int ext4_ind_migrate(struct inode *inode) if (test_opt(inode->i_sb, DELALLOC)) ext4_alloc_da_blocks(inode); - percpu_down_write(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_write(inode->i_sb); handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1); if (IS_ERR(handle)) { @@ -665,6 +666,6 @@ errout: ext4_journal_stop(handle); up_write(&EXT4_I(inode)->i_data_sem); out_unlock: - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(inode->i_sb, alloc_ctx); return ret; } diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index 4022bc713421..0aaf38ffcb6e 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -39,28 +39,36 @@ static void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp) * Write the MMP block using REQ_SYNC to try to get the block on-disk * faster. */ -static int write_mmp_block(struct super_block *sb, struct buffer_head *bh) +static int write_mmp_block_thawed(struct super_block *sb, + struct buffer_head *bh) { struct mmp_struct *mmp = (struct mmp_struct *)(bh->b_data); - /* - * We protect against freezing so that we don't create dirty buffers - * on frozen filesystem. - */ - sb_start_write(sb); ext4_mmp_csum_set(sb, mmp); lock_buffer(bh); bh->b_end_io = end_buffer_write_sync; get_bh(bh); submit_bh(REQ_OP_WRITE | REQ_SYNC | REQ_META | REQ_PRIO, bh); wait_on_buffer(bh); - sb_end_write(sb); if (unlikely(!buffer_uptodate(bh))) return -EIO; - return 0; } +static int write_mmp_block(struct super_block *sb, struct buffer_head *bh) +{ + int err; + + /* + * We protect against freezing so that we don't create dirty buffers + * on frozen filesystem. + */ + sb_start_write(sb); + err = write_mmp_block_thawed(sb, bh); + sb_end_write(sb); + return err; +} + /* * Read the MMP block. It _must_ be read from disk and hence we clear the * uptodate flag on the buffer. @@ -344,7 +352,11 @@ skip: seq = mmp_new_seq(); mmp->mmp_seq = cpu_to_le32(seq); - retval = write_mmp_block(sb, bh); + /* + * On mount / remount we are protected against fs freezing (by s_umount + * semaphore) and grabbing freeze protection upsets lockdep + */ + retval = write_mmp_block_thawed(sb, bh); if (retval) goto failed; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index a5010b5b8a8c..45b579805c95 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -674,7 +674,7 @@ static struct stats dx_show_leaf(struct inode *dir, len = de->name_len; if (!IS_ENCRYPTED(dir)) { /* Directory is not encrypted */ - ext4fs_dirhash(dir, de->name, + (void) ext4fs_dirhash(dir, de->name, de->name_len, &h); printk("%*.s:(U)%x.%u ", len, name, h.hash, @@ -709,8 +709,9 @@ static struct stats dx_show_leaf(struct inode *dir, if (IS_CASEFOLDED(dir)) h.hash = EXT4_DIRENT_HASH(de); else - ext4fs_dirhash(dir, de->name, - de->name_len, &h); + (void) ext4fs_dirhash(dir, + de->name, + de->name_len, &h); printk("%*.s:(E)%x.%u ", len, name, h.hash, (unsigned) ((char *) de - base)); @@ -720,7 +721,8 @@ static struct stats dx_show_leaf(struct inode *dir, #else int len = de->name_len; char *name = de->name; - ext4fs_dirhash(dir, de->name, de->name_len, &h); + (void) ext4fs_dirhash(dir, de->name, + de->name_len, &h); printk("%*.s:%x.%u ", len, name, h.hash, (unsigned) ((char *) de - base)); #endif @@ -849,8 +851,14 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, hinfo->seed = EXT4_SB(dir->i_sb)->s_hash_seed; /* hash is already computed for encrypted casefolded directory */ if (fname && fname_name(fname) && - !(IS_ENCRYPTED(dir) && IS_CASEFOLDED(dir))) - ext4fs_dirhash(dir, fname_name(fname), fname_len(fname), hinfo); + !(IS_ENCRYPTED(dir) && IS_CASEFOLDED(dir))) { + int ret = ext4fs_dirhash(dir, fname_name(fname), + fname_len(fname), hinfo); + if (ret < 0) { + ret_err = ERR_PTR(ret); + goto fail; + } + } hash = hinfo->hash; if (root->info.unused_flags & 1) { @@ -1111,7 +1119,12 @@ static int htree_dirblock_to_tree(struct file *dir_file, hinfo->minor_hash = 0; } } else { - ext4fs_dirhash(dir, de->name, de->name_len, hinfo); + err = ext4fs_dirhash(dir, de->name, + de->name_len, hinfo); + if (err < 0) { + count = err; + goto errout; + } } if ((hinfo->hash < start_hash) || ((hinfo->hash == start_hash) && @@ -1313,8 +1326,12 @@ static int dx_make_map(struct inode *dir, struct buffer_head *bh, if (de->name_len && de->inode) { if (ext4_hash_in_dirent(dir)) h.hash = EXT4_DIRENT_HASH(de); - else - ext4fs_dirhash(dir, de->name, de->name_len, &h); + else { + int err = ext4fs_dirhash(dir, de->name, + de->name_len, &h); + if (err < 0) + return err; + } map_tail--; map_tail->hash = h.hash; map_tail->offs = ((char *) de - base)>>2; @@ -1452,10 +1469,9 @@ int ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname, hinfo->hash_version = DX_HASH_SIPHASH; hinfo->seed = NULL; if (cf_name->name) - ext4fs_dirhash(dir, cf_name->name, cf_name->len, hinfo); + return ext4fs_dirhash(dir, cf_name->name, cf_name->len, hinfo); else - ext4fs_dirhash(dir, iname->name, iname->len, hinfo); - return 0; + return ext4fs_dirhash(dir, iname->name, iname->len, hinfo); } #endif @@ -2298,10 +2314,15 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, fname->hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed; /* casefolded encrypted hashes are computed on fname setup */ - if (!ext4_hash_in_dirent(dir)) - ext4fs_dirhash(dir, fname_name(fname), - fname_len(fname), &fname->hinfo); - + if (!ext4_hash_in_dirent(dir)) { + int err = ext4fs_dirhash(dir, fname_name(fname), + fname_len(fname), &fname->hinfo); + if (err < 0) { + brelse(bh2); + brelse(bh); + return err; + } + } memset(frames, 0, sizeof(frames)); frame = frames; frame->entries = entries; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index d39f386e9baf..56a5d1c469fc 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1048,6 +1048,8 @@ void ext4_mark_group_bitmap_corrupted(struct super_block *sb, struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL); int ret; + if (!grp || !gdp) + return; if (flags & EXT4_GROUP_INFO_BBITMAP_CORRUPT) { ret = ext4_test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state); @@ -3238,11 +3240,9 @@ static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group, crc = crc16(crc, (__u8 *)gdp, offset); offset += sizeof(gdp->bg_checksum); /* skip checksum */ /* for checksum of struct ext4_group_desc do the rest...*/ - if (ext4_has_feature_64bit(sb) && - offset < le16_to_cpu(sbi->s_es->s_desc_size)) + if (ext4_has_feature_64bit(sb) && offset < sbi->s_desc_size) crc = crc16(crc, (__u8 *)gdp + offset, - le16_to_cpu(sbi->s_es->s_desc_size) - - offset); + sbi->s_desc_size - offset); out: return cpu_to_le16(crc); @@ -5684,8 +5684,9 @@ static int ext4_fill_super(struct super_block *sb, struct fs_context *fc) descr = "out journal"; if (___ratelimit(&ext4_mount_msg_ratelimit, "EXT4-fs mount")) - ext4_msg(sb, KERN_INFO, "mounted filesystem %pU with%s. " - "Quota mode: %s.", &sb->s_uuid, descr, + ext4_msg(sb, KERN_INFO, "mounted filesystem %pU %s with%s. " + "Quota mode: %s.", &sb->s_uuid, + sb_rdonly(sb) ? "ro" : "r/w", descr, ext4_quota_mode(sb)); /* Update the s_overhead_clusters if necessary */ @@ -6387,6 +6388,7 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) struct ext4_mount_options old_opts; ext4_group_t g; int err = 0; + int enable_rw = 0; #ifdef CONFIG_QUOTA int enable_quota = 0; int i, j; @@ -6573,7 +6575,7 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) if (err) goto restore_opts; - sb->s_flags &= ~SB_RDONLY; + enable_rw = 1; if (ext4_has_feature_mmp(sb)) { err = ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block)); @@ -6587,18 +6589,6 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) } /* - * Reinitialize lazy itable initialization thread based on - * current settings - */ - if (sb_rdonly(sb) || !test_opt(sb, INIT_INODE_TABLE)) - ext4_unregister_li_request(sb); - else { - ext4_group_t first_not_zeroed; - first_not_zeroed = ext4_has_uninit_itable(sb); - ext4_register_li_request(sb, first_not_zeroed); - } - - /* * Handle creation of system zone data early because it can fail. * Releasing of existing data is done when we are sure remount will * succeed. @@ -6616,9 +6606,6 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) } #ifdef CONFIG_QUOTA - /* Release old quota file names */ - for (i = 0; i < EXT4_MAXQUOTAS; i++) - kfree(old_opts.s_qf_names[i]); if (enable_quota) { if (sb_any_quota_suspended(sb)) dquot_resume(sb, -1); @@ -6628,16 +6615,41 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) goto restore_opts; } } + /* Release old quota file names */ + for (i = 0; i < EXT4_MAXQUOTAS; i++) + kfree(old_opts.s_qf_names[i]); #endif if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks) ext4_release_system_zone(sb); + if (enable_rw) + sb->s_flags &= ~SB_RDONLY; + + /* + * Reinitialize lazy itable initialization thread based on + * current settings + */ + if (sb_rdonly(sb) || !test_opt(sb, INIT_INODE_TABLE)) + ext4_unregister_li_request(sb); + else { + ext4_group_t first_not_zeroed; + first_not_zeroed = ext4_has_uninit_itable(sb); + ext4_register_li_request(sb, first_not_zeroed); + } + if (!ext4_has_feature_mmp(sb) || sb_rdonly(sb)) ext4_stop_mmpd(sbi); return 0; restore_opts: + /* + * If there was a failing r/w to ro transition, we may need to + * re-enable quota + */ + if ((sb->s_flags & SB_RDONLY) && !(old_sb_flags & SB_RDONLY) && + sb_any_quota_suspended(sb)) + dquot_resume(sb, -1); sb->s_flags = old_sb_flags; sbi->s_mount_opt = old_opts.s_mount_opt; sbi->s_mount_opt2 = old_opts.s_mount_opt2; @@ -6678,8 +6690,9 @@ static int ext4_reconfigure(struct fs_context *fc) if (ret < 0) return ret; - ext4_msg(sb, KERN_INFO, "re-mounted %pU. Quota mode: %s.", - &sb->s_uuid, ext4_quota_mode(sb)); + ext4_msg(sb, KERN_INFO, "re-mounted %pU %s. Quota mode: %s.", + &sb->s_uuid, sb_rdonly(sb) ? "ro" : "r/w", + ext4_quota_mode(sb)); return 0; } diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index dadad29bd81b..13d7f17a9c8c 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -121,7 +121,11 @@ ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array, #ifdef CONFIG_LOCKDEP void ext4_xattr_inode_set_class(struct inode *ea_inode) { + struct ext4_inode_info *ei = EXT4_I(ea_inode); + lockdep_set_subclass(&ea_inode->i_rwsem, 1); + (void) ei; /* shut up clang warning if !CONFIG_LOCKDEP */ + lockdep_set_subclass(&ei->i_data_sem, I_DATA_SEM_EA); } #endif @@ -433,7 +437,7 @@ static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino, return -EFSCORRUPTED; } - inode = ext4_iget(parent->i_sb, ea_ino, EXT4_IGET_NORMAL); + inode = ext4_iget(parent->i_sb, ea_ino, EXT4_IGET_EA_INODE); if (IS_ERR(inode)) { err = PTR_ERR(inode); ext4_error(parent->i_sb, @@ -441,23 +445,6 @@ static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino, err); return err; } - - if (is_bad_inode(inode)) { - ext4_error(parent->i_sb, - "error while reading EA inode %lu is_bad_inode", - ea_ino); - err = -EIO; - goto error; - } - - if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) { - ext4_error(parent->i_sb, - "EA inode %lu does not have EXT4_EA_INODE_FL flag", - ea_ino); - err = -EINVAL; - goto error; - } - ext4_xattr_inode_set_class(inode); /* @@ -478,9 +465,6 @@ static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino, *ea_inode = inode; return 0; -error: - iput(inode); - return err; } /* Remove entry from mbcache when EA inode is getting evicted */ @@ -1556,11 +1540,11 @@ ext4_xattr_inode_cache_find(struct inode *inode, const void *value, while (ce) { ea_inode = ext4_iget(inode->i_sb, ce->e_value, - EXT4_IGET_NORMAL); - if (!IS_ERR(ea_inode) && - !is_bad_inode(ea_inode) && - (EXT4_I(ea_inode)->i_flags & EXT4_EA_INODE_FL) && - i_size_read(ea_inode) == value_len && + EXT4_IGET_EA_INODE); + if (IS_ERR(ea_inode)) + goto next_entry; + ext4_xattr_inode_set_class(ea_inode); + if (i_size_read(ea_inode) == value_len && !ext4_xattr_inode_read(ea_inode, ea_data, value_len) && !ext4_xattr_inode_verify_hashes(ea_inode, NULL, ea_data, value_len) && @@ -1570,9 +1554,8 @@ ext4_xattr_inode_cache_find(struct inode *inode, const void *value, kvfree(ea_data); return ea_inode; } - - if (!IS_ERR(ea_inode)) - iput(ea_inode); + iput(ea_inode); + next_entry: ce = mb_cache_entry_find_next(ea_inode_cache, ce); } kvfree(ea_data); @@ -2614,6 +2597,7 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, .in_inode = !!entry->e_value_inum, }; struct ext4_xattr_ibody_header *header = IHDR(inode, raw_inode); + int needs_kvfree = 0; int error; is = kzalloc(sizeof(struct ext4_xattr_ibody_find), GFP_NOFS); @@ -2636,7 +2620,7 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, error = -ENOMEM; goto out; } - + needs_kvfree = 1; error = ext4_xattr_inode_get(inode, entry, buffer, value_size); if (error) goto out; @@ -2675,7 +2659,7 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, out: kfree(b_entry_name); - if (entry->e_value_inum && buffer) + if (needs_kvfree && buffer) kvfree(buffer); if (is) brelse(is->iloc.bh); diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 300844f50dcd..cb62c8f07d1e 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -784,9 +784,13 @@ static inline bool should_fault_in_pages(struct iov_iter *i, if (!user_backed_iter(i)) return false; + /* + * Try to fault in multiple pages initially. When that doesn't result + * in any progress, fall back to a single page. + */ size = PAGE_SIZE; offs = offset_in_page(iocb->ki_pos); - if (*prev_count != count || !*window_size) { + if (*prev_count != count) { size_t nr_dirtied; nr_dirtied = max(current->nr_dirtied_pause - @@ -870,6 +874,7 @@ static ssize_t gfs2_file_direct_write(struct kiocb *iocb, struct iov_iter *from, struct gfs2_inode *ip = GFS2_I(inode); size_t prev_count = 0, window_size = 0; size_t written = 0; + bool enough_retries; ssize_t ret; /* @@ -913,11 +918,17 @@ retry: if (ret > 0) written = ret; + enough_retries = prev_count == iov_iter_count(from) && + window_size <= PAGE_SIZE; if (should_fault_in_pages(from, iocb, &prev_count, &window_size)) { gfs2_glock_dq(gh); window_size -= fault_in_iov_iter_readable(from, window_size); - if (window_size) - goto retry; + if (window_size) { + if (!enough_retries) + goto retry; + /* fall back to buffered I/O */ + ret = 0; + } } out_unlock: if (gfs2_holder_queued(gh)) diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index bb94949bc223..04ba95b83d16 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -77,9 +77,9 @@ static const unsigned long nlm_grace_period_min = 0; static const unsigned long nlm_grace_period_max = 240; static const unsigned long nlm_timeout_min = 3; static const unsigned long nlm_timeout_max = 20; -static const int nlm_port_min = 0, nlm_port_max = 65535; #ifdef CONFIG_SYSCTL +static const int nlm_port_min = 0, nlm_port_max = 65535; static struct ctl_table_header * nlm_sysctl_table; #endif diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c index 8a4c86687429..2ff07ba655a0 100644 --- a/fs/netfs/iterator.c +++ b/fs/netfs/iterator.c @@ -101,269 +101,3 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len, return npages; } EXPORT_SYMBOL_GPL(netfs_extract_user_iter); - -/* - * Extract and pin a list of up to sg_max pages from UBUF- or IOVEC-class - * iterators, and add them to the scatterlist. - */ -static ssize_t netfs_extract_user_to_sg(struct iov_iter *iter, - ssize_t maxsize, - struct sg_table *sgtable, - unsigned int sg_max, - iov_iter_extraction_t extraction_flags) -{ - struct scatterlist *sg = sgtable->sgl + sgtable->nents; - struct page **pages; - unsigned int npages; - ssize_t ret = 0, res; - size_t len, off; - - /* We decant the page list into the tail of the scatterlist */ - pages = (void *)sgtable->sgl + array_size(sg_max, sizeof(struct scatterlist)); - pages -= sg_max; - - do { - res = iov_iter_extract_pages(iter, &pages, maxsize, sg_max, - extraction_flags, &off); - if (res < 0) - goto failed; - - len = res; - maxsize -= len; - ret += len; - npages = DIV_ROUND_UP(off + len, PAGE_SIZE); - sg_max -= npages; - - for (; npages > 0; npages--) { - struct page *page = *pages; - size_t seg = min_t(size_t, PAGE_SIZE - off, len); - - *pages++ = NULL; - sg_set_page(sg, page, seg, off); - sgtable->nents++; - sg++; - len -= seg; - off = 0; - } - } while (maxsize > 0 && sg_max > 0); - - return ret; - -failed: - while (sgtable->nents > sgtable->orig_nents) - put_page(sg_page(&sgtable->sgl[--sgtable->nents])); - return res; -} - -/* - * Extract up to sg_max pages from a BVEC-type iterator and add them to the - * scatterlist. The pages are not pinned. - */ -static ssize_t netfs_extract_bvec_to_sg(struct iov_iter *iter, - ssize_t maxsize, - struct sg_table *sgtable, - unsigned int sg_max, - iov_iter_extraction_t extraction_flags) -{ - const struct bio_vec *bv = iter->bvec; - struct scatterlist *sg = sgtable->sgl + sgtable->nents; - unsigned long start = iter->iov_offset; - unsigned int i; - ssize_t ret = 0; - - for (i = 0; i < iter->nr_segs; i++) { - size_t off, len; - - len = bv[i].bv_len; - if (start >= len) { - start -= len; - continue; - } - - len = min_t(size_t, maxsize, len - start); - off = bv[i].bv_offset + start; - - sg_set_page(sg, bv[i].bv_page, len, off); - sgtable->nents++; - sg++; - sg_max--; - - ret += len; - maxsize -= len; - if (maxsize <= 0 || sg_max == 0) - break; - start = 0; - } - - if (ret > 0) - iov_iter_advance(iter, ret); - return ret; -} - -/* - * Extract up to sg_max pages from a KVEC-type iterator and add them to the - * scatterlist. This can deal with vmalloc'd buffers as well as kmalloc'd or - * static buffers. The pages are not pinned. - */ -static ssize_t netfs_extract_kvec_to_sg(struct iov_iter *iter, - ssize_t maxsize, - struct sg_table *sgtable, - unsigned int sg_max, - iov_iter_extraction_t extraction_flags) -{ - const struct kvec *kv = iter->kvec; - struct scatterlist *sg = sgtable->sgl + sgtable->nents; - unsigned long start = iter->iov_offset; - unsigned int i; - ssize_t ret = 0; - - for (i = 0; i < iter->nr_segs; i++) { - struct page *page; - unsigned long kaddr; - size_t off, len, seg; - - len = kv[i].iov_len; - if (start >= len) { - start -= len; - continue; - } - - kaddr = (unsigned long)kv[i].iov_base + start; - off = kaddr & ~PAGE_MASK; - len = min_t(size_t, maxsize, len - start); - kaddr &= PAGE_MASK; - - maxsize -= len; - ret += len; - do { - seg = min_t(size_t, len, PAGE_SIZE - off); - if (is_vmalloc_or_module_addr((void *)kaddr)) - page = vmalloc_to_page((void *)kaddr); - else - page = virt_to_page(kaddr); - - sg_set_page(sg, page, len, off); - sgtable->nents++; - sg++; - sg_max--; - - len -= seg; - kaddr += PAGE_SIZE; - off = 0; - } while (len > 0 && sg_max > 0); - - if (maxsize <= 0 || sg_max == 0) - break; - start = 0; - } - - if (ret > 0) - iov_iter_advance(iter, ret); - return ret; -} - -/* - * Extract up to sg_max folios from an XARRAY-type iterator and add them to - * the scatterlist. The pages are not pinned. - */ -static ssize_t netfs_extract_xarray_to_sg(struct iov_iter *iter, - ssize_t maxsize, - struct sg_table *sgtable, - unsigned int sg_max, - iov_iter_extraction_t extraction_flags) -{ - struct scatterlist *sg = sgtable->sgl + sgtable->nents; - struct xarray *xa = iter->xarray; - struct folio *folio; - loff_t start = iter->xarray_start + iter->iov_offset; - pgoff_t index = start / PAGE_SIZE; - ssize_t ret = 0; - size_t offset, len; - XA_STATE(xas, xa, index); - - rcu_read_lock(); - - xas_for_each(&xas, folio, ULONG_MAX) { - if (xas_retry(&xas, folio)) - continue; - if (WARN_ON(xa_is_value(folio))) - break; - if (WARN_ON(folio_test_hugetlb(folio))) - break; - - offset = offset_in_folio(folio, start); - len = min_t(size_t, maxsize, folio_size(folio) - offset); - - sg_set_page(sg, folio_page(folio, 0), len, offset); - sgtable->nents++; - sg++; - sg_max--; - - maxsize -= len; - ret += len; - if (maxsize <= 0 || sg_max == 0) - break; - } - - rcu_read_unlock(); - if (ret > 0) - iov_iter_advance(iter, ret); - return ret; -} - -/** - * netfs_extract_iter_to_sg - Extract pages from an iterator and add ot an sglist - * @iter: The iterator to extract from - * @maxsize: The amount of iterator to copy - * @sgtable: The scatterlist table to fill in - * @sg_max: Maximum number of elements in @sgtable that may be filled - * @extraction_flags: Flags to qualify the request - * - * Extract the page fragments from the given amount of the source iterator and - * add them to a scatterlist that refers to all of those bits, to a maximum - * addition of @sg_max elements. - * - * The pages referred to by UBUF- and IOVEC-type iterators are extracted and - * pinned; BVEC-, KVEC- and XARRAY-type are extracted but aren't pinned; PIPE- - * and DISCARD-type are not supported. - * - * No end mark is placed on the scatterlist; that's left to the caller. - * - * @extraction_flags can have ITER_ALLOW_P2PDMA set to request peer-to-peer DMA - * be allowed on the pages extracted. - * - * If successul, @sgtable->nents is updated to include the number of elements - * added and the number of bytes added is returned. @sgtable->orig_nents is - * left unaltered. - * - * The iov_iter_extract_mode() function should be used to query how cleanup - * should be performed. - */ -ssize_t netfs_extract_iter_to_sg(struct iov_iter *iter, size_t maxsize, - struct sg_table *sgtable, unsigned int sg_max, - iov_iter_extraction_t extraction_flags) -{ - if (maxsize == 0) - return 0; - - switch (iov_iter_type(iter)) { - case ITER_UBUF: - case ITER_IOVEC: - return netfs_extract_user_to_sg(iter, maxsize, sgtable, sg_max, - extraction_flags); - case ITER_BVEC: - return netfs_extract_bvec_to_sg(iter, maxsize, sgtable, sg_max, - extraction_flags); - case ITER_KVEC: - return netfs_extract_kvec_to_sg(iter, maxsize, sgtable, sg_max, - extraction_flags); - case ITER_XARRAY: - return netfs_extract_xarray_to_sg(iter, maxsize, sgtable, sg_max, - extraction_flags); - default: - pr_err("%s(%u) unsupported\n", __func__, iov_iter_type(iter)); - WARN_ON_ONCE(1); - return -EIO; - } -} -EXPORT_SYMBOL_GPL(netfs_extract_iter_to_sg); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index e63c1d46f189..8f3112e71a6a 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -317,7 +317,7 @@ static int nfs_readdir_folio_array_append(struct folio *folio, name = nfs_readdir_copy_name(entry->name, entry->len); - array = kmap_atomic(folio_page(folio, 0)); + array = kmap_local_folio(folio, 0); if (!name) goto out; ret = nfs_readdir_array_can_expand(array); @@ -340,7 +340,7 @@ static int nfs_readdir_folio_array_append(struct folio *folio, nfs_readdir_array_set_eof(array); out: *cookie = array->last_cookie; - kunmap_atomic(array); + kunmap_local(array); return ret; } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 18f25ff4bff7..d3665390c4cb 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5437,10 +5437,18 @@ static bool nfs4_read_plus_not_supported(struct rpc_task *task, return false; } -static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) +static inline void nfs4_read_plus_scratch_free(struct nfs_pgio_header *hdr) { - if (hdr->res.scratch) + if (hdr->res.scratch) { kfree(hdr->res.scratch); + hdr->res.scratch = NULL; + } +} + +static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) +{ + nfs4_read_plus_scratch_free(hdr); + if (!nfs4_sequence_done(task, &hdr->res.seq_res)) return -EAGAIN; if (nfs4_read_stateid_changed(task, &hdr->args)) diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 7b8f17ee5224..b4fd7a7062d5 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -153,18 +153,6 @@ static int exports_net_open(struct net *net, struct file *file) return 0; } -static int exports_proc_open(struct inode *inode, struct file *file) -{ - return exports_net_open(current->nsproxy->net_ns, file); -} - -static const struct proc_ops exports_proc_ops = { - .proc_open = exports_proc_open, - .proc_read = seq_read, - .proc_lseek = seq_lseek, - .proc_release = seq_release, -}; - static int exports_nfsd_open(struct inode *inode, struct file *file) { return exports_net_open(inode->i_sb->s_fs_info, file); @@ -702,16 +690,11 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred if (err != 0 || fd < 0) return -EINVAL; - if (svc_alien_sock(net, fd)) { - printk(KERN_ERR "%s: socket net is different to NFSd's one\n", __func__); - return -EINVAL; - } - err = nfsd_create_serv(net); if (err != 0) return err; - err = svc_addsock(nn->nfsd_serv, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred); + err = svc_addsock(nn->nfsd_serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred); if (err >= 0 && !nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1)) @@ -1458,6 +1441,19 @@ static struct file_system_type nfsd_fs_type = { MODULE_ALIAS_FS("nfsd"); #ifdef CONFIG_PROC_FS + +static int exports_proc_open(struct inode *inode, struct file *file) +{ + return exports_net_open(current->nsproxy->net_ns, file); +} + +static const struct proc_ops exports_proc_ops = { + .proc_open = exports_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = seq_release, +}; + static int create_proc_exports_entry(void) { struct proc_dir_entry *entry; diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index 4183819ea082..72a906a053dc 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -1365,19 +1365,19 @@ TRACE_EVENT(nfsd_cb_setup, __field(u32, cl_id) __field(unsigned long, authflavor) __sockaddr(addr, clp->cl_cb_conn.cb_addrlen) - __array(unsigned char, netid, 8) + __string(netid, netid) ), TP_fast_assign( __entry->cl_boot = clp->cl_clientid.cl_boot; __entry->cl_id = clp->cl_clientid.cl_id; - strlcpy(__entry->netid, netid, sizeof(__entry->netid)); + __assign_str(netid, netid); __entry->authflavor = authflavor; __assign_sockaddr(addr, &clp->cl_cb_conn.cb_addr, clp->cl_cb_conn.cb_addrlen) ), TP_printk("addr=%pISpc client %08x:%08x proto=%s flavor=%s", __get_sockaddr(addr), __entry->cl_boot, __entry->cl_id, - __entry->netid, show_nfsd_authflavor(__entry->authflavor)) + __get_str(netid), show_nfsd_authflavor(__entry->authflavor)) ); TRACE_EVENT(nfsd_cb_setup_err, diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index bb9d47172162..db67f8e19344 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -536,7 +536,15 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, inode_lock(inode); for (retries = 1;;) { - host_err = __nfsd_setattr(dentry, iap); + struct iattr attrs; + + /* + * notify_change() can alter its iattr argument, making + * @iap unsuitable for submission multiple times. Make a + * copy for every loop iteration. + */ + attrs = *iap; + host_err = __nfsd_setattr(dentry, &attrs); if (host_err != -EAGAIN || !retries--) break; if (!nfsd_wait_for_delegreturn(rqstp, inode)) diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 1310d2d5feb3..a8ce522ac747 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -917,6 +917,7 @@ void nilfs_evict_inode(struct inode *inode) struct nilfs_transaction_info ti; struct super_block *sb = inode->i_sb; struct nilfs_inode_info *ii = NILFS_I(inode); + struct the_nilfs *nilfs; int ret; if (inode->i_nlink || !ii->i_root || unlikely(is_bad_inode(inode))) { @@ -929,6 +930,23 @@ void nilfs_evict_inode(struct inode *inode) truncate_inode_pages_final(&inode->i_data); + nilfs = sb->s_fs_info; + if (unlikely(sb_rdonly(sb) || !nilfs->ns_writer)) { + /* + * If this inode is about to be disposed after the file system + * has been degraded to read-only due to file system corruption + * or after the writer has been detached, do not make any + * changes that cause writes, just clear it. + * Do this check after read-locking ns_segctor_sem by + * nilfs_transaction_begin() in order to avoid a race with + * the writer detach operation. + */ + clear_inode(inode); + nilfs_clear_inode(inode); + nilfs_transaction_abort(sb); + return; + } + /* TODO: some of the following operations may fail. */ nilfs_truncate_bmap(ii, 0); nilfs_mark_inode_dirty(inode); diff --git a/fs/pipe.c b/fs/pipe.c index ceb17d2dfa19..2d88f73f585a 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -342,7 +342,8 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) break; if (ret) break; - if (filp->f_flags & O_NONBLOCK) { + if ((filp->f_flags & O_NONBLOCK) || + (iocb->ki_flags & IOCB_NOWAIT)) { ret = -EAGAIN; break; } @@ -547,7 +548,8 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) continue; /* Wait for buffer space to become available. */ - if (filp->f_flags & O_NONBLOCK) { + if ((filp->f_flags & O_NONBLOCK) || + (iocb->ki_flags & IOCB_NOWAIT)) { if (!ret) ret = -EAGAIN; break; diff --git a/fs/smb/Kconfig b/fs/smb/Kconfig new file mode 100644 index 000000000000..ef425789fa6a --- /dev/null +++ b/fs/smb/Kconfig @@ -0,0 +1,11 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# smbfs configuration + +source "fs/smb/client/Kconfig" +source "fs/smb/server/Kconfig" + +config SMBFS + tristate + default y if CIFS=y || SMB_SERVER=y + default m if CIFS=m || SMB_SERVER=m diff --git a/fs/smb/Makefile b/fs/smb/Makefile new file mode 100644 index 000000000000..9a1bf59a1a65 --- /dev/null +++ b/fs/smb/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_SMBFS) += common/ +obj-$(CONFIG_CIFS) += client/ +obj-$(CONFIG_SMB_SERVER) += server/ diff --git a/fs/cifs/Kconfig b/fs/smb/client/Kconfig index 4c0d53bf931a..4c0d53bf931a 100644 --- a/fs/cifs/Kconfig +++ b/fs/smb/client/Kconfig diff --git a/fs/cifs/Makefile b/fs/smb/client/Makefile index 304a7f6cc13a..304a7f6cc13a 100644 --- a/fs/cifs/Makefile +++ b/fs/smb/client/Makefile diff --git a/fs/cifs/asn1.c b/fs/smb/client/asn1.c index b5724ef9f182..b5724ef9f182 100644 --- a/fs/cifs/asn1.c +++ b/fs/smb/client/asn1.c diff --git a/fs/cifs/cached_dir.c b/fs/smb/client/cached_dir.c index bfc964b36c72..bfc964b36c72 100644 --- a/fs/cifs/cached_dir.c +++ b/fs/smb/client/cached_dir.c diff --git a/fs/cifs/cached_dir.h b/fs/smb/client/cached_dir.h index 2f4e764c9ca9..2f4e764c9ca9 100644 --- a/fs/cifs/cached_dir.h +++ b/fs/smb/client/cached_dir.h diff --git a/fs/cifs/cifs_debug.c b/fs/smb/client/cifs_debug.c index d4ed200a9471..5034b862cec2 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/smb/client/cifs_debug.c @@ -108,7 +108,7 @@ static void cifs_debug_tcon(struct seq_file *m, struct cifs_tcon *tcon) if ((tcon->seal) || (tcon->ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA) || (tcon->share_flags & SHI1005_FLAGS_ENCRYPT_DATA)) - seq_printf(m, " Encrypted"); + seq_puts(m, " encrypted"); if (tcon->nocase) seq_printf(m, " nocase"); if (tcon->unix_ext) @@ -415,8 +415,12 @@ skip_rdma: /* dump session id helpful for use with network trace */ seq_printf(m, " SessionId: 0x%llx", ses->Suid); - if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA) + if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA) { seq_puts(m, " encrypted"); + /* can help in debugging to show encryption type */ + if (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM) + seq_puts(m, "(gcm256)"); + } if (ses->sign) seq_puts(m, " signed"); diff --git a/fs/cifs/cifs_debug.h b/fs/smb/client/cifs_debug.h index ce5cfd236fdb..ce5cfd236fdb 100644 --- a/fs/cifs/cifs_debug.h +++ b/fs/smb/client/cifs_debug.h diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/smb/client/cifs_dfs_ref.c index 0329a907bdfe..0329a907bdfe 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/smb/client/cifs_dfs_ref.c diff --git a/fs/cifs/cifs_fs_sb.h b/fs/smb/client/cifs_fs_sb.h index 651759192280..651759192280 100644 --- a/fs/cifs/cifs_fs_sb.h +++ b/fs/smb/client/cifs_fs_sb.h diff --git a/fs/cifs/cifs_ioctl.h b/fs/smb/client/cifs_ioctl.h index 332588e77c31..332588e77c31 100644 --- a/fs/cifs/cifs_ioctl.h +++ b/fs/smb/client/cifs_ioctl.h diff --git a/fs/cifs/cifs_spnego.c b/fs/smb/client/cifs_spnego.c index 6f3285f1dfee..6f3285f1dfee 100644 --- a/fs/cifs/cifs_spnego.c +++ b/fs/smb/client/cifs_spnego.c diff --git a/fs/cifs/cifs_spnego.h b/fs/smb/client/cifs_spnego.h index e4d751b0c812..e4d751b0c812 100644 --- a/fs/cifs/cifs_spnego.h +++ b/fs/smb/client/cifs_spnego.h diff --git a/fs/cifs/cifs_spnego_negtokeninit.asn1 b/fs/smb/client/cifs_spnego_negtokeninit.asn1 index 181c083887d5..181c083887d5 100644 --- a/fs/cifs/cifs_spnego_negtokeninit.asn1 +++ b/fs/smb/client/cifs_spnego_negtokeninit.asn1 diff --git a/fs/cifs/cifs_swn.c b/fs/smb/client/cifs_swn.c index 7233c6a7e6d7..7233c6a7e6d7 100644 --- a/fs/cifs/cifs_swn.c +++ b/fs/smb/client/cifs_swn.c diff --git a/fs/cifs/cifs_swn.h b/fs/smb/client/cifs_swn.h index 8a9d2a5c9077..8a9d2a5c9077 100644 --- a/fs/cifs/cifs_swn.h +++ b/fs/smb/client/cifs_swn.h diff --git a/fs/cifs/cifs_unicode.c b/fs/smb/client/cifs_unicode.c index e7582dd79179..e7582dd79179 100644 --- a/fs/cifs/cifs_unicode.c +++ b/fs/smb/client/cifs_unicode.c diff --git a/fs/cifs/cifs_unicode.h b/fs/smb/client/cifs_unicode.h index 80b3d845419f..80b3d845419f 100644 --- a/fs/cifs/cifs_unicode.h +++ b/fs/smb/client/cifs_unicode.h diff --git a/fs/cifs/cifs_uniupr.h b/fs/smb/client/cifs_uniupr.h index 7b272fcdf0d3..7b272fcdf0d3 100644 --- a/fs/cifs/cifs_uniupr.h +++ b/fs/smb/client/cifs_uniupr.h diff --git a/fs/cifs/cifsacl.c b/fs/smb/client/cifsacl.c index f5b6df82e857..f5b6df82e857 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/smb/client/cifsacl.c diff --git a/fs/cifs/cifsacl.h b/fs/smb/client/cifsacl.h index ccbfc754bd3c..ccbfc754bd3c 100644 --- a/fs/cifs/cifsacl.h +++ b/fs/smb/client/cifsacl.h diff --git a/fs/cifs/cifsencrypt.c b/fs/smb/client/cifsencrypt.c index 357bd27a7fd1..ef4c2e3c9fa6 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/smb/client/cifsencrypt.c @@ -21,7 +21,7 @@ #include <linux/random.h> #include <linux/highmem.h> #include <linux/fips.h> -#include "../smbfs_common/arc4.h" +#include "../common/arc4.h" #include <crypto/aead.h> /* diff --git a/fs/cifs/cifsfs.c b/fs/smb/client/cifsfs.c index 32f7c81a7b89..43a4d8603db3 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -246,7 +246,7 @@ cifs_read_super(struct super_block *sb) if (cifs_sb->ctx->rasize) sb->s_bdi->ra_pages = cifs_sb->ctx->rasize / PAGE_SIZE; else - sb->s_bdi->ra_pages = cifs_sb->ctx->rsize / PAGE_SIZE; + sb->s_bdi->ra_pages = 2 * (cifs_sb->ctx->rsize / PAGE_SIZE); sb->s_blocksize = CIFS_MAX_MSGSIZE; sb->s_blocksize_bits = 14; /* default 2**14 = CIFS_MAX_MSGSIZE */ @@ -744,6 +744,7 @@ static void cifs_umount_begin(struct super_block *sb) spin_unlock(&tcon->tc_lock); spin_unlock(&cifs_tcp_ses_lock); + cifs_close_all_deferred_files(tcon); /* cancel_brl_requests(tcon); */ /* BB mark all brl mids as exiting */ /* cancel_notify_requests(tcon); */ if (tcon->ses && tcon->ses->server) { @@ -759,6 +760,20 @@ static void cifs_umount_begin(struct super_block *sb) return; } +static int cifs_freeze(struct super_block *sb) +{ + struct cifs_sb_info *cifs_sb = CIFS_SB(sb); + struct cifs_tcon *tcon; + + if (cifs_sb == NULL) + return 0; + + tcon = cifs_sb_master_tcon(cifs_sb); + + cifs_close_all_deferred_files(tcon); + return 0; +} + #ifdef CONFIG_CIFS_STATS2 static int cifs_show_stats(struct seq_file *s, struct dentry *root) { @@ -797,6 +812,7 @@ static const struct super_operations cifs_super_ops = { as opens */ .show_options = cifs_show_options, .umount_begin = cifs_umount_begin, + .freeze_fs = cifs_freeze, #ifdef CONFIG_CIFS_STATS2 .show_stats = cifs_show_stats, #endif diff --git a/fs/cifs/cifsfs.h b/fs/smb/client/cifsfs.h index 74cd6fafb33e..74cd6fafb33e 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/smb/client/cifsfs.h diff --git a/fs/cifs/cifsglob.h b/fs/smb/client/cifsglob.h index 414685c5d530..0d84bb1a8cd9 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -24,7 +24,7 @@ #include "cifsacl.h" #include <crypto/internal/hash.h> #include <uapi/linux/cifs/cifs_mount.h> -#include "../smbfs_common/smb2pdu.h" +#include "../common/smb2pdu.h" #include "smb2pdu.h" #include <linux/filelock.h> @@ -424,8 +424,8 @@ struct smb_version_operations { /* check for STATUS_NETWORK_SESSION_EXPIRED */ bool (*is_session_expired)(char *); /* send oplock break response */ - int (*oplock_response)(struct cifs_tcon *, struct cifs_fid *, - struct cifsInodeInfo *); + int (*oplock_response)(struct cifs_tcon *tcon, __u64 persistent_fid, __u64 volatile_fid, + __u16 net_fid, struct cifsInodeInfo *cifs_inode); /* query remote filesystem */ int (*queryfs)(const unsigned int, struct cifs_tcon *, struct cifs_sb_info *, struct kstatfs *); diff --git a/fs/cifs/cifspdu.h b/fs/smb/client/cifspdu.h index 445e3eaebcc1..e17222fec9d2 100644 --- a/fs/cifs/cifspdu.h +++ b/fs/smb/client/cifspdu.h @@ -11,7 +11,7 @@ #include <net/sock.h> #include <asm/unaligned.h> -#include "../smbfs_common/smbfsctl.h" +#include "../common/smbfsctl.h" #define CIFS_PROT 0 #define POSIX_PROT (CIFS_PROT+1) diff --git a/fs/cifs/cifsproto.h b/fs/smb/client/cifsproto.h index c1c704990b98..c1c704990b98 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/smb/client/cifsproto.h diff --git a/fs/cifs/cifsroot.c b/fs/smb/client/cifsroot.c index 56ec1b233f52..56ec1b233f52 100644 --- a/fs/cifs/cifsroot.c +++ b/fs/smb/client/cifsroot.c diff --git a/fs/cifs/cifssmb.c b/fs/smb/client/cifssmb.c index 9d963caec35c..9d963caec35c 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/smb/client/cifssmb.c diff --git a/fs/cifs/connect.c b/fs/smb/client/connect.c index eeeed6fda13b..8e9a672320ab 100644 --- a/fs/cifs/connect.c +++ b/fs/smb/client/connect.c @@ -2709,6 +2709,13 @@ cifs_match_super(struct super_block *sb, void *data) spin_lock(&cifs_tcp_ses_lock); cifs_sb = CIFS_SB(sb); + + /* We do not want to use a superblock that has been shutdown */ + if (CIFS_MOUNT_SHUTDOWN & cifs_sb->mnt_cifs_flags) { + spin_unlock(&cifs_tcp_ses_lock); + return 0; + } + tlink = cifs_get_tlink(cifs_sb_master_tlink(cifs_sb)); if (tlink == NULL) { /* can not match superblock if tlink were ever null */ diff --git a/fs/cifs/dfs.c b/fs/smb/client/dfs.c index a93dbca1411b..2f93bf8c3325 100644 --- a/fs/cifs/dfs.c +++ b/fs/smb/client/dfs.c @@ -303,7 +303,7 @@ int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs) if (!nodfs) { rc = dfs_get_referral(mnt_ctx, ctx->UNC + 1, NULL, NULL); if (rc) { - if (rc != -ENOENT && rc != -EOPNOTSUPP) + if (rc != -ENOENT && rc != -EOPNOTSUPP && rc != -EIO) goto out; nodfs = true; } diff --git a/fs/cifs/dfs.h b/fs/smb/client/dfs.h index 1c90df5ecfbd..1c90df5ecfbd 100644 --- a/fs/cifs/dfs.h +++ b/fs/smb/client/dfs.h diff --git a/fs/cifs/dfs_cache.c b/fs/smb/client/dfs_cache.c index 1513b2709889..1513b2709889 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/smb/client/dfs_cache.c diff --git a/fs/cifs/dfs_cache.h b/fs/smb/client/dfs_cache.h index c6d89cd6d4fd..c6d89cd6d4fd 100644 --- a/fs/cifs/dfs_cache.h +++ b/fs/smb/client/dfs_cache.h diff --git a/fs/cifs/dir.c b/fs/smb/client/dir.c index 30b1e1bfd204..30b1e1bfd204 100644 --- a/fs/cifs/dir.c +++ b/fs/smb/client/dir.c diff --git a/fs/cifs/dns_resolve.c b/fs/smb/client/dns_resolve.c index 8bf8978bc5d6..8bf8978bc5d6 100644 --- a/fs/cifs/dns_resolve.c +++ b/fs/smb/client/dns_resolve.c diff --git a/fs/cifs/dns_resolve.h b/fs/smb/client/dns_resolve.h index 6eb0c15a2440..6eb0c15a2440 100644 --- a/fs/cifs/dns_resolve.h +++ b/fs/smb/client/dns_resolve.h diff --git a/fs/cifs/export.c b/fs/smb/client/export.c index 37c28415df1e..37c28415df1e 100644 --- a/fs/cifs/export.c +++ b/fs/smb/client/export.c diff --git a/fs/cifs/file.c b/fs/smb/client/file.c index c5fcefdfd797..df88b8c04d03 100644 --- a/fs/cifs/file.c +++ b/fs/smb/client/file.c @@ -3353,9 +3353,10 @@ static size_t cifs_limit_bvec_subset(const struct iov_iter *iter, size_t max_siz while (n && ix < nbv) { len = min3(n, bvecs[ix].bv_len - skip, max_size); span += len; + max_size -= len; nsegs++; ix++; - if (span >= max_size || nsegs >= max_segs) + if (max_size == 0 || nsegs >= max_segs) break; skip = 0; n -= len; @@ -4881,9 +4882,9 @@ void cifs_oplock_break(struct work_struct *work) struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); struct TCP_Server_Info *server = tcon->ses->server; int rc = 0; - bool purge_cache = false; - struct cifs_deferred_close *dclose; - bool is_deferred = false; + bool purge_cache = false, oplock_break_cancelled; + __u64 persistent_fid, volatile_fid; + __u16 net_fid; wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS, TASK_UNINTERRUPTIBLE); @@ -4924,28 +4925,28 @@ oplock_break_ack: * file handles but cached, then schedule deferred close immediately. * So, new open will not use cached handle. */ - spin_lock(&CIFS_I(inode)->deferred_lock); - is_deferred = cifs_is_deferred_close(cfile, &dclose); - spin_unlock(&CIFS_I(inode)->deferred_lock); - if (!CIFS_CACHE_HANDLE(cinode) && is_deferred && - cfile->deferred_close_scheduled && delayed_work_pending(&cfile->deferred)) { + if (!CIFS_CACHE_HANDLE(cinode) && !list_empty(&cinode->deferred_closes)) cifs_close_deferred_file(cinode); - } + persistent_fid = cfile->fid.persistent_fid; + volatile_fid = cfile->fid.volatile_fid; + net_fid = cfile->fid.netfid; + oplock_break_cancelled = cfile->oplock_break_cancelled; + + _cifsFileInfo_put(cfile, false /* do not wait for ourself */, false); /* * releasing stale oplock after recent reconnect of smb session using * a now incorrect file handle is not a data integrity issue but do * not bother sending an oplock release if session to server still is * disconnected since oplock already released by the server */ - if (!cfile->oplock_break_cancelled) { - rc = tcon->ses->server->ops->oplock_response(tcon, &cfile->fid, - cinode); + if (!oplock_break_cancelled) { + rc = tcon->ses->server->ops->oplock_response(tcon, persistent_fid, + volatile_fid, net_fid, cinode); cifs_dbg(FYI, "Oplock release rc = %d\n", rc); } - _cifsFileInfo_put(cfile, false /* do not wait for ourself */, false); cifs_done_oplock_break(cinode); } diff --git a/fs/cifs/fs_context.c b/fs/smb/client/fs_context.c index ace11a1a7c8a..1bda75609b64 100644 --- a/fs/cifs/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -904,6 +904,14 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, ctx->sfu_remap = false; /* disable SFU mapping */ } break; + case Opt_mapchars: + if (result.negated) + ctx->sfu_remap = false; + else { + ctx->sfu_remap = true; + ctx->remap = false; /* disable SFM (mapposix) mapping */ + } + break; case Opt_user_xattr: if (result.negated) ctx->no_xattr = 1; diff --git a/fs/cifs/fs_context.h b/fs/smb/client/fs_context.h index f4eaf8558902..f4eaf8558902 100644 --- a/fs/cifs/fs_context.h +++ b/fs/smb/client/fs_context.h diff --git a/fs/cifs/fscache.c b/fs/smb/client/fscache.c index 8f6909d633da..8f6909d633da 100644 --- a/fs/cifs/fscache.c +++ b/fs/smb/client/fscache.c diff --git a/fs/cifs/fscache.h b/fs/smb/client/fscache.h index 173999610997..173999610997 100644 --- a/fs/cifs/fscache.h +++ b/fs/smb/client/fscache.h diff --git a/fs/cifs/inode.c b/fs/smb/client/inode.c index 1087ac6104a9..1087ac6104a9 100644 --- a/fs/cifs/inode.c +++ b/fs/smb/client/inode.c diff --git a/fs/cifs/ioctl.c b/fs/smb/client/ioctl.c index cb3be58cd55e..fff092bbc7a3 100644 --- a/fs/cifs/ioctl.c +++ b/fs/smb/client/ioctl.c @@ -321,7 +321,11 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) struct tcon_link *tlink; struct cifs_sb_info *cifs_sb; __u64 ExtAttrBits = 0; +#ifdef CONFIG_CIFS_POSIX +#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY __u64 caps; +#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ +#endif /* CONFIG_CIFS_POSIX */ xid = get_xid(); @@ -331,9 +335,9 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) if (pSMBFile == NULL) break; tcon = tlink_tcon(pSMBFile->tlink); - caps = le64_to_cpu(tcon->fsUnixInfo.Capability); #ifdef CONFIG_CIFS_POSIX #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY + caps = le64_to_cpu(tcon->fsUnixInfo.Capability); if (CIFS_UNIX_EXTATTR_CAP & caps) { __u64 ExtAttrMask = 0; rc = CIFSGetExtAttr(xid, tcon, diff --git a/fs/cifs/link.c b/fs/smb/client/link.c index c66be4904e1f..c66be4904e1f 100644 --- a/fs/cifs/link.c +++ b/fs/smb/client/link.c diff --git a/fs/cifs/misc.c b/fs/smb/client/misc.c index cd914be905b2..cd914be905b2 100644 --- a/fs/cifs/misc.c +++ b/fs/smb/client/misc.c diff --git a/fs/cifs/netlink.c b/fs/smb/client/netlink.c index 147d9409252c..147d9409252c 100644 --- a/fs/cifs/netlink.c +++ b/fs/smb/client/netlink.c diff --git a/fs/cifs/netlink.h b/fs/smb/client/netlink.h index e2fa8ed24c54..e2fa8ed24c54 100644 --- a/fs/cifs/netlink.h +++ b/fs/smb/client/netlink.h diff --git a/fs/cifs/netmisc.c b/fs/smb/client/netmisc.c index 1b52e6ac431c..1b52e6ac431c 100644 --- a/fs/cifs/netmisc.c +++ b/fs/smb/client/netmisc.c diff --git a/fs/cifs/nterr.c b/fs/smb/client/nterr.c index 358a766375b4..358a766375b4 100644 --- a/fs/cifs/nterr.c +++ b/fs/smb/client/nterr.c diff --git a/fs/cifs/nterr.h b/fs/smb/client/nterr.h index edd4741cab0a..edd4741cab0a 100644 --- a/fs/cifs/nterr.h +++ b/fs/smb/client/nterr.h diff --git a/fs/cifs/ntlmssp.h b/fs/smb/client/ntlmssp.h index 2c5dde2ece58..2c5dde2ece58 100644 --- a/fs/cifs/ntlmssp.h +++ b/fs/smb/client/ntlmssp.h diff --git a/fs/cifs/readdir.c b/fs/smb/client/readdir.c index ef638086d734..ef638086d734 100644 --- a/fs/cifs/readdir.c +++ b/fs/smb/client/readdir.c diff --git a/fs/cifs/rfc1002pdu.h b/fs/smb/client/rfc1002pdu.h index ae1d025da294..ae1d025da294 100644 --- a/fs/cifs/rfc1002pdu.h +++ b/fs/smb/client/rfc1002pdu.h diff --git a/fs/cifs/sess.c b/fs/smb/client/sess.c index 335c078c42fb..335c078c42fb 100644 --- a/fs/cifs/sess.c +++ b/fs/smb/client/sess.c diff --git a/fs/cifs/smb1ops.c b/fs/smb/client/smb1ops.c index abda6148be10..7d1b3fc014d9 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/smb/client/smb1ops.c @@ -897,12 +897,11 @@ cifs_close_dir(const unsigned int xid, struct cifs_tcon *tcon, } static int -cifs_oplock_response(struct cifs_tcon *tcon, struct cifs_fid *fid, - struct cifsInodeInfo *cinode) +cifs_oplock_response(struct cifs_tcon *tcon, __u64 persistent_fid, + __u64 volatile_fid, __u16 net_fid, struct cifsInodeInfo *cinode) { - return CIFSSMBLock(0, tcon, fid->netfid, current->tgid, 0, 0, 0, 0, - LOCKING_ANDX_OPLOCK_RELEASE, false, - CIFS_CACHE_READ(cinode) ? 1 : 0); + return CIFSSMBLock(0, tcon, net_fid, current->tgid, 0, 0, 0, 0, + LOCKING_ANDX_OPLOCK_RELEASE, false, CIFS_CACHE_READ(cinode) ? 1 : 0); } static int diff --git a/fs/cifs/smb2file.c b/fs/smb/client/smb2file.c index e0ee96d69d49..e0ee96d69d49 100644 --- a/fs/cifs/smb2file.c +++ b/fs/smb/client/smb2file.c diff --git a/fs/cifs/smb2glob.h b/fs/smb/client/smb2glob.h index 82e916ad167c..82e916ad167c 100644 --- a/fs/cifs/smb2glob.h +++ b/fs/smb/client/smb2glob.h diff --git a/fs/cifs/smb2inode.c b/fs/smb/client/smb2inode.c index 163a03298430..163a03298430 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/smb/client/smb2inode.c diff --git a/fs/cifs/smb2maperror.c b/fs/smb/client/smb2maperror.c index 194799ddd382..194799ddd382 100644 --- a/fs/cifs/smb2maperror.c +++ b/fs/smb/client/smb2maperror.c diff --git a/fs/cifs/smb2misc.c b/fs/smb/client/smb2misc.c index 3935a60db5c3..3935a60db5c3 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/smb/client/smb2misc.c diff --git a/fs/cifs/smb2ops.c b/fs/smb/client/smb2ops.c index a81758225fcd..38d2265c77fd 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -618,7 +618,6 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, * Add a new one instead */ spin_lock(&ses->iface_lock); - iface = niface = NULL; list_for_each_entry_safe(iface, niface, &ses->iface_list, iface_head) { ret = iface_cmp(iface, &tmp_iface); @@ -1682,7 +1681,7 @@ smb2_copychunk_range(const unsigned int xid, pcchunk->SourceOffset = cpu_to_le64(src_off); pcchunk->TargetOffset = cpu_to_le64(dest_off); pcchunk->Length = - cpu_to_le32(min_t(u32, len, tcon->max_bytes_chunk)); + cpu_to_le32(min_t(u64, len, tcon->max_bytes_chunk)); /* Request server copy to target from src identified by key */ kfree(retbuf); @@ -2383,15 +2382,14 @@ smb2_is_network_name_deleted(char *buf, struct TCP_Server_Info *server) } static int -smb2_oplock_response(struct cifs_tcon *tcon, struct cifs_fid *fid, - struct cifsInodeInfo *cinode) +smb2_oplock_response(struct cifs_tcon *tcon, __u64 persistent_fid, + __u64 volatile_fid, __u16 net_fid, struct cifsInodeInfo *cinode) { if (tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LEASING) return SMB2_lease_break(0, tcon, cinode->lease_key, smb2_get_lease_state(cinode)); - return SMB2_oplock_break(0, tcon, fid->persistent_fid, - fid->volatile_fid, + return SMB2_oplock_break(0, tcon, persistent_fid, volatile_fid, CIFS_CACHE_READ(cinode) ? 1 : 0); } @@ -4335,8 +4333,8 @@ static void *smb2_get_aead_req(struct crypto_aead *tfm, struct smb_rqst *rqst, } sgtable.orig_nents = sgtable.nents; - rc = netfs_extract_iter_to_sg(iter, count, &sgtable, - num_sgs - sgtable.nents, 0); + rc = extract_iter_to_sg(iter, count, &sgtable, + num_sgs - sgtable.nents, 0); iov_iter_revert(iter, rc); sgtable.orig_nents = sgtable.nents; } diff --git a/fs/cifs/smb2pdu.c b/fs/smb/client/smb2pdu.c index e33ca0d33906..7063b395d22f 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -1947,6 +1947,9 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, init_copy_chunk_defaults(tcon); if (server->ops->validate_negotiate) rc = server->ops->validate_negotiate(xid, tcon); + if (rc == 0) /* See MS-SMB2 2.2.10 and 3.2.5.5 */ + if (tcon->share_flags & SMB2_SHAREFLAG_ISOLATED_TRANSPORT) + server->nosharesock = true; tcon_exit: free_rsp_buf(resp_buftype, rsp); @@ -3722,7 +3725,7 @@ SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon, if (*out_data == NULL) { rc = -ENOMEM; goto cnotify_exit; - } else + } else if (plen) *plen = le32_to_cpu(smb_rsp->OutputBufferLength); } diff --git a/fs/cifs/smb2pdu.h b/fs/smb/client/smb2pdu.h index 220994d0a0f7..220994d0a0f7 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/smb/client/smb2pdu.h diff --git a/fs/cifs/smb2proto.h b/fs/smb/client/smb2proto.h index d5d7ffb7711c..d5d7ffb7711c 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/smb/client/smb2proto.h diff --git a/fs/cifs/smb2status.h b/fs/smb/client/smb2status.h index a9e958166fc5..a9e958166fc5 100644 --- a/fs/cifs/smb2status.h +++ b/fs/smb/client/smb2status.h diff --git a/fs/cifs/smb2transport.c b/fs/smb/client/smb2transport.c index 790acf65a092..790acf65a092 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/smb/client/smb2transport.c diff --git a/fs/cifs/smbdirect.c b/fs/smb/client/smbdirect.c index 0362ebd4fa0f..223e17c16b60 100644 --- a/fs/cifs/smbdirect.c +++ b/fs/smb/client/smbdirect.c @@ -2227,7 +2227,7 @@ static int smbd_iter_to_mr(struct smbd_connection *info, memset(sgt->sgl, 0, max_sg * sizeof(struct scatterlist)); - ret = netfs_extract_iter_to_sg(iter, iov_iter_count(iter), sgt, max_sg, 0); + ret = extract_iter_to_sg(iter, iov_iter_count(iter), sgt, max_sg, 0); WARN_ON(ret < 0); if (sgt->nents > 0) sg_mark_end(&sgt->sgl[sgt->nents - 1]); diff --git a/fs/cifs/smbdirect.h b/fs/smb/client/smbdirect.h index 83f239f376f0..83f239f376f0 100644 --- a/fs/cifs/smbdirect.h +++ b/fs/smb/client/smbdirect.h diff --git a/fs/cifs/smbencrypt.c b/fs/smb/client/smbencrypt.c index 4a0487753869..f0ce26414f17 100644 --- a/fs/cifs/smbencrypt.c +++ b/fs/smb/client/smbencrypt.c @@ -24,7 +24,7 @@ #include "cifsglob.h" #include "cifs_debug.h" #include "cifsproto.h" -#include "../smbfs_common/md4.h" +#include "../common/md4.h" #ifndef false #define false 0 diff --git a/fs/cifs/smberr.h b/fs/smb/client/smberr.h index aeffdad829e2..aeffdad829e2 100644 --- a/fs/cifs/smberr.h +++ b/fs/smb/client/smberr.h diff --git a/fs/cifs/trace.c b/fs/smb/client/trace.c index 465483787193..465483787193 100644 --- a/fs/cifs/trace.c +++ b/fs/smb/client/trace.c diff --git a/fs/cifs/trace.h b/fs/smb/client/trace.h index d3053bd8ae73..d3053bd8ae73 100644 --- a/fs/cifs/trace.h +++ b/fs/smb/client/trace.h diff --git a/fs/cifs/transport.c b/fs/smb/client/transport.c index 24bdd5f4d3bc..24bdd5f4d3bc 100644 --- a/fs/cifs/transport.c +++ b/fs/smb/client/transport.c diff --git a/fs/cifs/unc.c b/fs/smb/client/unc.c index f6fc5e343ea4..f6fc5e343ea4 100644 --- a/fs/cifs/unc.c +++ b/fs/smb/client/unc.c diff --git a/fs/cifs/winucase.c b/fs/smb/client/winucase.c index 2f075b5b50df..2f075b5b50df 100644 --- a/fs/cifs/winucase.c +++ b/fs/smb/client/winucase.c diff --git a/fs/cifs/xattr.c b/fs/smb/client/xattr.c index 4ad5531686d8..4ad5531686d8 100644 --- a/fs/cifs/xattr.c +++ b/fs/smb/client/xattr.c diff --git a/fs/smbfs_common/Makefile b/fs/smb/common/Makefile index cafc61a3bfc3..c66dbbc1469c 100644 --- a/fs/smbfs_common/Makefile +++ b/fs/smb/common/Makefile @@ -3,5 +3,5 @@ # Makefile for Linux filesystem routines that are shared by client and server. # -obj-$(CONFIG_SMBFS_COMMON) += cifs_arc4.o -obj-$(CONFIG_SMBFS_COMMON) += cifs_md4.o +obj-$(CONFIG_SMBFS) += cifs_arc4.o +obj-$(CONFIG_SMBFS) += cifs_md4.o diff --git a/fs/smbfs_common/arc4.h b/fs/smb/common/arc4.h index 12e71ec033a1..12e71ec033a1 100644 --- a/fs/smbfs_common/arc4.h +++ b/fs/smb/common/arc4.h diff --git a/fs/smbfs_common/cifs_arc4.c b/fs/smb/common/cifs_arc4.c index 043e4cb839fa..043e4cb839fa 100644 --- a/fs/smbfs_common/cifs_arc4.c +++ b/fs/smb/common/cifs_arc4.c diff --git a/fs/smbfs_common/cifs_md4.c b/fs/smb/common/cifs_md4.c index 50f78cfc6ce9..50f78cfc6ce9 100644 --- a/fs/smbfs_common/cifs_md4.c +++ b/fs/smb/common/cifs_md4.c diff --git a/fs/smbfs_common/md4.h b/fs/smb/common/md4.h index 5337becc699a..5337becc699a 100644 --- a/fs/smbfs_common/md4.h +++ b/fs/smb/common/md4.h diff --git a/fs/smbfs_common/smb2pdu.h b/fs/smb/common/smb2pdu.h index bae590eec871..bae590eec871 100644 --- a/fs/smbfs_common/smb2pdu.h +++ b/fs/smb/common/smb2pdu.h diff --git a/fs/smbfs_common/smbfsctl.h b/fs/smb/common/smbfsctl.h index edd7fc2a7921..edd7fc2a7921 100644 --- a/fs/smbfs_common/smbfsctl.h +++ b/fs/smb/common/smbfsctl.h diff --git a/fs/ksmbd/Kconfig b/fs/smb/server/Kconfig index 7055cb5d2880..7055cb5d2880 100644 --- a/fs/ksmbd/Kconfig +++ b/fs/smb/server/Kconfig diff --git a/fs/ksmbd/Makefile b/fs/smb/server/Makefile index 7d6337a7dee4..7d6337a7dee4 100644 --- a/fs/ksmbd/Makefile +++ b/fs/smb/server/Makefile diff --git a/fs/ksmbd/asn1.c b/fs/smb/server/asn1.c index cc6384f79675..cc6384f79675 100644 --- a/fs/ksmbd/asn1.c +++ b/fs/smb/server/asn1.c diff --git a/fs/ksmbd/asn1.h b/fs/smb/server/asn1.h index ce105f4ce305..ce105f4ce305 100644 --- a/fs/ksmbd/asn1.h +++ b/fs/smb/server/asn1.h diff --git a/fs/ksmbd/auth.c b/fs/smb/server/auth.c index df8fb076f6f1..5e5e120edcc2 100644 --- a/fs/ksmbd/auth.c +++ b/fs/smb/server/auth.c @@ -29,7 +29,7 @@ #include "mgmt/user_config.h" #include "crypto_ctx.h" #include "transport_ipc.h" -#include "../smbfs_common/arc4.h" +#include "../common/arc4.h" /* * Fixed format data defining GSS header and fixed string diff --git a/fs/ksmbd/auth.h b/fs/smb/server/auth.h index 362b6159a6cf..362b6159a6cf 100644 --- a/fs/ksmbd/auth.h +++ b/fs/smb/server/auth.h diff --git a/fs/ksmbd/connection.c b/fs/smb/server/connection.c index 4ed379f9b1aa..4882a812ea86 100644 --- a/fs/ksmbd/connection.c +++ b/fs/smb/server/connection.c @@ -351,7 +351,8 @@ int ksmbd_conn_handler_loop(void *p) break; /* 4 for rfc1002 length field */ - size = pdu_size + 4; + /* 1 for implied bcc[0] */ + size = pdu_size + 4 + 1; conn->request_buf = kvmalloc(size, GFP_KERNEL); if (!conn->request_buf) break; diff --git a/fs/ksmbd/connection.h b/fs/smb/server/connection.h index ad8dfaa48ffb..ad8dfaa48ffb 100644 --- a/fs/ksmbd/connection.h +++ b/fs/smb/server/connection.h diff --git a/fs/ksmbd/crypto_ctx.c b/fs/smb/server/crypto_ctx.c index 81488d04199d..81488d04199d 100644 --- a/fs/ksmbd/crypto_ctx.c +++ b/fs/smb/server/crypto_ctx.c diff --git a/fs/ksmbd/crypto_ctx.h b/fs/smb/server/crypto_ctx.h index 4a367c62f653..4a367c62f653 100644 --- a/fs/ksmbd/crypto_ctx.h +++ b/fs/smb/server/crypto_ctx.h diff --git a/fs/ksmbd/glob.h b/fs/smb/server/glob.h index 5b8f3e0ebdb3..5b8f3e0ebdb3 100644 --- a/fs/ksmbd/glob.h +++ b/fs/smb/server/glob.h diff --git a/fs/ksmbd/ksmbd_netlink.h b/fs/smb/server/ksmbd_netlink.h index fb8b2d566efb..fb8b2d566efb 100644 --- a/fs/ksmbd/ksmbd_netlink.h +++ b/fs/smb/server/ksmbd_netlink.h diff --git a/fs/ksmbd/ksmbd_spnego_negtokeninit.asn1 b/fs/smb/server/ksmbd_spnego_negtokeninit.asn1 index 0065f191b54b..0065f191b54b 100644 --- a/fs/ksmbd/ksmbd_spnego_negtokeninit.asn1 +++ b/fs/smb/server/ksmbd_spnego_negtokeninit.asn1 diff --git a/fs/ksmbd/ksmbd_spnego_negtokentarg.asn1 b/fs/smb/server/ksmbd_spnego_negtokentarg.asn1 index 1151933e7b9c..1151933e7b9c 100644 --- a/fs/ksmbd/ksmbd_spnego_negtokentarg.asn1 +++ b/fs/smb/server/ksmbd_spnego_negtokentarg.asn1 diff --git a/fs/ksmbd/ksmbd_work.c b/fs/smb/server/ksmbd_work.c index 14b9caebf7a4..14b9caebf7a4 100644 --- a/fs/ksmbd/ksmbd_work.c +++ b/fs/smb/server/ksmbd_work.c diff --git a/fs/ksmbd/ksmbd_work.h b/fs/smb/server/ksmbd_work.h index f8ae6144c0ae..f8ae6144c0ae 100644 --- a/fs/ksmbd/ksmbd_work.h +++ b/fs/smb/server/ksmbd_work.h diff --git a/fs/ksmbd/mgmt/ksmbd_ida.c b/fs/smb/server/mgmt/ksmbd_ida.c index 54194d959a5e..54194d959a5e 100644 --- a/fs/ksmbd/mgmt/ksmbd_ida.c +++ b/fs/smb/server/mgmt/ksmbd_ida.c diff --git a/fs/ksmbd/mgmt/ksmbd_ida.h b/fs/smb/server/mgmt/ksmbd_ida.h index 2bc07b16cfde..2bc07b16cfde 100644 --- a/fs/ksmbd/mgmt/ksmbd_ida.h +++ b/fs/smb/server/mgmt/ksmbd_ida.h diff --git a/fs/ksmbd/mgmt/share_config.c b/fs/smb/server/mgmt/share_config.c index 328a412259dc..328a412259dc 100644 --- a/fs/ksmbd/mgmt/share_config.c +++ b/fs/smb/server/mgmt/share_config.c diff --git a/fs/ksmbd/mgmt/share_config.h b/fs/smb/server/mgmt/share_config.h index 3fd338293942..3fd338293942 100644 --- a/fs/ksmbd/mgmt/share_config.h +++ b/fs/smb/server/mgmt/share_config.h diff --git a/fs/ksmbd/mgmt/tree_connect.c b/fs/smb/server/mgmt/tree_connect.c index f07a05f37651..f07a05f37651 100644 --- a/fs/ksmbd/mgmt/tree_connect.c +++ b/fs/smb/server/mgmt/tree_connect.c diff --git a/fs/ksmbd/mgmt/tree_connect.h b/fs/smb/server/mgmt/tree_connect.h index 700df36cf3e3..700df36cf3e3 100644 --- a/fs/ksmbd/mgmt/tree_connect.h +++ b/fs/smb/server/mgmt/tree_connect.h diff --git a/fs/ksmbd/mgmt/user_config.c b/fs/smb/server/mgmt/user_config.c index 279d00feff21..279d00feff21 100644 --- a/fs/ksmbd/mgmt/user_config.c +++ b/fs/smb/server/mgmt/user_config.c diff --git a/fs/ksmbd/mgmt/user_config.h b/fs/smb/server/mgmt/user_config.h index 6a44109617f1..6a44109617f1 100644 --- a/fs/ksmbd/mgmt/user_config.h +++ b/fs/smb/server/mgmt/user_config.h diff --git a/fs/ksmbd/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c index 8a5dcab05614..8a5dcab05614 100644 --- a/fs/ksmbd/mgmt/user_session.c +++ b/fs/smb/server/mgmt/user_session.c diff --git a/fs/ksmbd/mgmt/user_session.h b/fs/smb/server/mgmt/user_session.h index f99d475b28db..f99d475b28db 100644 --- a/fs/ksmbd/mgmt/user_session.h +++ b/fs/smb/server/mgmt/user_session.h diff --git a/fs/ksmbd/misc.c b/fs/smb/server/misc.c index 9e8afaa686e3..9e8afaa686e3 100644 --- a/fs/ksmbd/misc.c +++ b/fs/smb/server/misc.c diff --git a/fs/ksmbd/misc.h b/fs/smb/server/misc.h index 1facfcd21200..1facfcd21200 100644 --- a/fs/ksmbd/misc.h +++ b/fs/smb/server/misc.h diff --git a/fs/ksmbd/ndr.c b/fs/smb/server/ndr.c index 3507d8f89074..3507d8f89074 100644 --- a/fs/ksmbd/ndr.c +++ b/fs/smb/server/ndr.c diff --git a/fs/ksmbd/ndr.h b/fs/smb/server/ndr.h index f3c108c8cf4d..f3c108c8cf4d 100644 --- a/fs/ksmbd/ndr.h +++ b/fs/smb/server/ndr.h diff --git a/fs/ksmbd/nterr.h b/fs/smb/server/nterr.h index 2f358f88a018..2f358f88a018 100644 --- a/fs/ksmbd/nterr.h +++ b/fs/smb/server/nterr.h diff --git a/fs/ksmbd/ntlmssp.h b/fs/smb/server/ntlmssp.h index f13153c18b4e..f13153c18b4e 100644 --- a/fs/ksmbd/ntlmssp.h +++ b/fs/smb/server/ntlmssp.h diff --git a/fs/ksmbd/oplock.c b/fs/smb/server/oplock.c index 2e54ded4d92c..db181bdad73a 100644 --- a/fs/ksmbd/oplock.c +++ b/fs/smb/server/oplock.c @@ -157,13 +157,42 @@ static struct oplock_info *opinfo_get_list(struct ksmbd_inode *ci) rcu_read_lock(); opinfo = list_first_or_null_rcu(&ci->m_op_list, struct oplock_info, op_entry); - if (opinfo && !atomic_inc_not_zero(&opinfo->refcount)) - opinfo = NULL; + if (opinfo) { + if (!atomic_inc_not_zero(&opinfo->refcount)) + opinfo = NULL; + else { + atomic_inc(&opinfo->conn->r_count); + if (ksmbd_conn_releasing(opinfo->conn)) { + atomic_dec(&opinfo->conn->r_count); + atomic_dec(&opinfo->refcount); + opinfo = NULL; + } + } + } + rcu_read_unlock(); return opinfo; } +static void opinfo_conn_put(struct oplock_info *opinfo) +{ + struct ksmbd_conn *conn; + + if (!opinfo) + return; + + conn = opinfo->conn; + /* + * Checking waitqueue to dropping pending requests on + * disconnection. waitqueue_active is safe because it + * uses atomic operation for condition. + */ + if (!atomic_dec_return(&conn->r_count) && waitqueue_active(&conn->r_count_q)) + wake_up(&conn->r_count_q); + opinfo_put(opinfo); +} + void opinfo_put(struct oplock_info *opinfo) { if (!atomic_dec_and_test(&opinfo->refcount)) @@ -666,13 +695,6 @@ static void __smb2_oplock_break_noti(struct work_struct *wk) out: ksmbd_free_work_struct(work); - /* - * Checking waitqueue to dropping pending requests on - * disconnection. waitqueue_active is safe because it - * uses atomic operation for condition. - */ - if (!atomic_dec_return(&conn->r_count) && waitqueue_active(&conn->r_count_q)) - wake_up(&conn->r_count_q); } /** @@ -706,7 +728,6 @@ static int smb2_oplock_break_noti(struct oplock_info *opinfo) work->conn = conn; work->sess = opinfo->sess; - atomic_inc(&conn->r_count); if (opinfo->op_state == OPLOCK_ACK_WAIT) { INIT_WORK(&work->work, __smb2_oplock_break_noti); ksmbd_queue_work(work); @@ -776,13 +797,6 @@ static void __smb2_lease_break_noti(struct work_struct *wk) out: ksmbd_free_work_struct(work); - /* - * Checking waitqueue to dropping pending requests on - * disconnection. waitqueue_active is safe because it - * uses atomic operation for condition. - */ - if (!atomic_dec_return(&conn->r_count) && waitqueue_active(&conn->r_count_q)) - wake_up(&conn->r_count_q); } /** @@ -822,7 +836,6 @@ static int smb2_lease_break_noti(struct oplock_info *opinfo) work->conn = conn; work->sess = opinfo->sess; - atomic_inc(&conn->r_count); if (opinfo->op_state == OPLOCK_ACK_WAIT) { list_for_each_safe(tmp, t, &opinfo->interim_list) { struct ksmbd_work *in_work; @@ -1144,8 +1157,10 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, } prev_opinfo = opinfo_get_list(ci); if (!prev_opinfo || - (prev_opinfo->level == SMB2_OPLOCK_LEVEL_NONE && lctx)) + (prev_opinfo->level == SMB2_OPLOCK_LEVEL_NONE && lctx)) { + opinfo_conn_put(prev_opinfo); goto set_lev; + } prev_op_has_lease = prev_opinfo->is_lease; if (prev_op_has_lease) prev_op_state = prev_opinfo->o_lease->state; @@ -1153,19 +1168,19 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, if (share_ret < 0 && prev_opinfo->level == SMB2_OPLOCK_LEVEL_EXCLUSIVE) { err = share_ret; - opinfo_put(prev_opinfo); + opinfo_conn_put(prev_opinfo); goto err_out; } if (prev_opinfo->level != SMB2_OPLOCK_LEVEL_BATCH && prev_opinfo->level != SMB2_OPLOCK_LEVEL_EXCLUSIVE) { - opinfo_put(prev_opinfo); + opinfo_conn_put(prev_opinfo); goto op_break_not_needed; } list_add(&work->interim_entry, &prev_opinfo->interim_list); err = oplock_break(prev_opinfo, SMB2_OPLOCK_LEVEL_II); - opinfo_put(prev_opinfo); + opinfo_conn_put(prev_opinfo); if (err == -ENOENT) goto set_lev; /* Check all oplock was freed by close */ @@ -1228,14 +1243,14 @@ static void smb_break_all_write_oplock(struct ksmbd_work *work, return; if (brk_opinfo->level != SMB2_OPLOCK_LEVEL_BATCH && brk_opinfo->level != SMB2_OPLOCK_LEVEL_EXCLUSIVE) { - opinfo_put(brk_opinfo); + opinfo_conn_put(brk_opinfo); return; } brk_opinfo->open_trunc = is_trunc; list_add(&work->interim_entry, &brk_opinfo->interim_list); oplock_break(brk_opinfo, SMB2_OPLOCK_LEVEL_II); - opinfo_put(brk_opinfo); + opinfo_conn_put(brk_opinfo); } /** @@ -1263,6 +1278,13 @@ void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp, list_for_each_entry_rcu(brk_op, &ci->m_op_list, op_entry) { if (!atomic_inc_not_zero(&brk_op->refcount)) continue; + + atomic_inc(&brk_op->conn->r_count); + if (ksmbd_conn_releasing(brk_op->conn)) { + atomic_dec(&brk_op->conn->r_count); + continue; + } + rcu_read_unlock(); if (brk_op->is_lease && (brk_op->o_lease->state & (~(SMB2_LEASE_READ_CACHING_LE | @@ -1292,7 +1314,7 @@ void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp, brk_op->open_trunc = is_trunc; oplock_break(brk_op, SMB2_OPLOCK_LEVEL_NONE); next: - opinfo_put(brk_op); + opinfo_conn_put(brk_op); rcu_read_lock(); } rcu_read_unlock(); @@ -1449,11 +1471,12 @@ struct lease_ctx_info *parse_lease_state(void *open_req) * smb2_find_context_vals() - find a particular context info in open request * @open_req: buffer containing smb2 file open(create) request * @tag: context name to search for + * @tag_len: the length of tag * * Return: pointer to requested context, NULL if @str context not found * or error pointer if name length is invalid. */ -struct create_context *smb2_find_context_vals(void *open_req, const char *tag) +struct create_context *smb2_find_context_vals(void *open_req, const char *tag, int tag_len) { struct create_context *cc; unsigned int next = 0; @@ -1492,7 +1515,7 @@ struct create_context *smb2_find_context_vals(void *open_req, const char *tag) return ERR_PTR(-EINVAL); name = (char *)cc + name_off; - if (memcmp(name, tag, name_len) == 0) + if (name_len == tag_len && !memcmp(name, tag, name_len)) return cc; remain_len -= next; diff --git a/fs/ksmbd/oplock.h b/fs/smb/server/oplock.h index 09753448f779..4b0fe6da7694 100644 --- a/fs/ksmbd/oplock.h +++ b/fs/smb/server/oplock.h @@ -118,7 +118,7 @@ void create_durable_v2_rsp_buf(char *cc, struct ksmbd_file *fp); void create_mxac_rsp_buf(char *cc, int maximal_access); void create_disk_id_rsp_buf(char *cc, __u64 file_id, __u64 vol_id); void create_posix_rsp_buf(char *cc, struct ksmbd_file *fp); -struct create_context *smb2_find_context_vals(void *open_req, const char *str); +struct create_context *smb2_find_context_vals(void *open_req, const char *tag, int tag_len); struct oplock_info *lookup_lease_in_table(struct ksmbd_conn *conn, char *lease_key); int find_same_lease_key(struct ksmbd_session *sess, struct ksmbd_inode *ci, diff --git a/fs/ksmbd/server.c b/fs/smb/server/server.c index f9b2e0f19b03..f9b2e0f19b03 100644 --- a/fs/ksmbd/server.c +++ b/fs/smb/server/server.c diff --git a/fs/ksmbd/server.h b/fs/smb/server/server.h index db7278181760..db7278181760 100644 --- a/fs/ksmbd/server.h +++ b/fs/smb/server/server.h diff --git a/fs/ksmbd/smb2misc.c b/fs/smb/server/smb2misc.c index fbdde426dd01..0ffe663b7590 100644 --- a/fs/ksmbd/smb2misc.c +++ b/fs/smb/server/smb2misc.c @@ -416,8 +416,11 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work) /* * Allow a message that padded to 8byte boundary. + * Linux 4.19.217 with smb 3.0.2 are sometimes + * sending messages where the cls_len is exactly + * 8 bytes less than len. */ - if (clc_len < len && (len - clc_len) < 8) + if (clc_len < len && (len - clc_len) <= 8) goto validate_credit; pr_err_ratelimited( diff --git a/fs/ksmbd/smb2ops.c b/fs/smb/server/smb2ops.c index aed7704a0672..aed7704a0672 100644 --- a/fs/ksmbd/smb2ops.c +++ b/fs/smb/server/smb2ops.c diff --git a/fs/ksmbd/smb2pdu.c b/fs/smb/server/smb2pdu.c index cb93fd231f4e..7a81541de602 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -326,13 +326,9 @@ int smb2_set_rsp_credits(struct ksmbd_work *work) if (hdr->Command == SMB2_NEGOTIATE) aux_max = 1; else - aux_max = conn->vals->max_credits - credit_charge; + aux_max = conn->vals->max_credits - conn->total_credits; credits_granted = min_t(unsigned short, credits_requested, aux_max); - if (conn->vals->max_credits - conn->total_credits < credits_granted) - credits_granted = conn->vals->max_credits - - conn->total_credits; - conn->total_credits += credits_granted; work->credits_granted += credits_granted; @@ -849,13 +845,14 @@ static void assemble_neg_contexts(struct ksmbd_conn *conn, static __le32 decode_preauth_ctxt(struct ksmbd_conn *conn, struct smb2_preauth_neg_context *pneg_ctxt, - int len_of_ctxts) + int ctxt_len) { /* * sizeof(smb2_preauth_neg_context) assumes SMB311_SALT_SIZE Salt, * which may not be present. Only check for used HashAlgorithms[1]. */ - if (len_of_ctxts < MIN_PREAUTH_CTXT_DATA_LEN) + if (ctxt_len < + sizeof(struct smb2_neg_context) + MIN_PREAUTH_CTXT_DATA_LEN) return STATUS_INVALID_PARAMETER; if (pneg_ctxt->HashAlgorithms != SMB2_PREAUTH_INTEGRITY_SHA512) @@ -867,15 +864,23 @@ static __le32 decode_preauth_ctxt(struct ksmbd_conn *conn, static void decode_encrypt_ctxt(struct ksmbd_conn *conn, struct smb2_encryption_neg_context *pneg_ctxt, - int len_of_ctxts) + int ctxt_len) { - int cph_cnt = le16_to_cpu(pneg_ctxt->CipherCount); - int i, cphs_size = cph_cnt * sizeof(__le16); + int cph_cnt; + int i, cphs_size; + + if (sizeof(struct smb2_encryption_neg_context) > ctxt_len) { + pr_err("Invalid SMB2_ENCRYPTION_CAPABILITIES context size\n"); + return; + } conn->cipher_type = 0; + cph_cnt = le16_to_cpu(pneg_ctxt->CipherCount); + cphs_size = cph_cnt * sizeof(__le16); + if (sizeof(struct smb2_encryption_neg_context) + cphs_size > - len_of_ctxts) { + ctxt_len) { pr_err("Invalid cipher count(%d)\n", cph_cnt); return; } @@ -923,15 +928,22 @@ static void decode_compress_ctxt(struct ksmbd_conn *conn, static void decode_sign_cap_ctxt(struct ksmbd_conn *conn, struct smb2_signing_capabilities *pneg_ctxt, - int len_of_ctxts) + int ctxt_len) { - int sign_algo_cnt = le16_to_cpu(pneg_ctxt->SigningAlgorithmCount); - int i, sign_alos_size = sign_algo_cnt * sizeof(__le16); + int sign_algo_cnt; + int i, sign_alos_size; + + if (sizeof(struct smb2_signing_capabilities) > ctxt_len) { + pr_err("Invalid SMB2_SIGNING_CAPABILITIES context length\n"); + return; + } conn->signing_negotiated = false; + sign_algo_cnt = le16_to_cpu(pneg_ctxt->SigningAlgorithmCount); + sign_alos_size = sign_algo_cnt * sizeof(__le16); if (sizeof(struct smb2_signing_capabilities) + sign_alos_size > - len_of_ctxts) { + ctxt_len) { pr_err("Invalid signing algorithm count(%d)\n", sign_algo_cnt); return; } @@ -969,18 +981,16 @@ static __le32 deassemble_neg_contexts(struct ksmbd_conn *conn, len_of_ctxts = len_of_smb - offset; while (i++ < neg_ctxt_cnt) { - int clen; - - /* check that offset is not beyond end of SMB */ - if (len_of_ctxts == 0) - break; + int clen, ctxt_len; if (len_of_ctxts < sizeof(struct smb2_neg_context)) break; pctx = (struct smb2_neg_context *)((char *)pctx + offset); clen = le16_to_cpu(pctx->DataLength); - if (clen + sizeof(struct smb2_neg_context) > len_of_ctxts) + ctxt_len = clen + sizeof(struct smb2_neg_context); + + if (ctxt_len > len_of_ctxts) break; if (pctx->ContextType == SMB2_PREAUTH_INTEGRITY_CAPABILITIES) { @@ -991,7 +1001,7 @@ static __le32 deassemble_neg_contexts(struct ksmbd_conn *conn, status = decode_preauth_ctxt(conn, (struct smb2_preauth_neg_context *)pctx, - len_of_ctxts); + ctxt_len); if (status != STATUS_SUCCESS) break; } else if (pctx->ContextType == SMB2_ENCRYPTION_CAPABILITIES) { @@ -1002,7 +1012,7 @@ static __le32 deassemble_neg_contexts(struct ksmbd_conn *conn, decode_encrypt_ctxt(conn, (struct smb2_encryption_neg_context *)pctx, - len_of_ctxts); + ctxt_len); } else if (pctx->ContextType == SMB2_COMPRESSION_CAPABILITIES) { ksmbd_debug(SMB, "deassemble SMB2_COMPRESSION_CAPABILITIES context\n"); @@ -1021,9 +1031,10 @@ static __le32 deassemble_neg_contexts(struct ksmbd_conn *conn, } else if (pctx->ContextType == SMB2_SIGNING_CAPABILITIES) { ksmbd_debug(SMB, "deassemble SMB2_SIGNING_CAPABILITIES context\n"); + decode_sign_cap_ctxt(conn, (struct smb2_signing_capabilities *)pctx, - len_of_ctxts); + ctxt_len); } /* offsets must be 8 byte aligned */ @@ -1057,16 +1068,16 @@ int smb2_handle_negotiate(struct ksmbd_work *work) return rc; } - if (req->DialectCount == 0) { - pr_err("malformed packet\n"); + smb2_buf_len = get_rfc1002_len(work->request_buf); + smb2_neg_size = offsetof(struct smb2_negotiate_req, Dialects); + if (smb2_neg_size > smb2_buf_len) { rsp->hdr.Status = STATUS_INVALID_PARAMETER; rc = -EINVAL; goto err_out; } - smb2_buf_len = get_rfc1002_len(work->request_buf); - smb2_neg_size = offsetof(struct smb2_negotiate_req, Dialects); - if (smb2_neg_size > smb2_buf_len) { + if (req->DialectCount == 0) { + pr_err("malformed packet\n"); rsp->hdr.Status = STATUS_INVALID_PARAMETER; rc = -EINVAL; goto err_out; @@ -1356,7 +1367,7 @@ static struct ksmbd_user *session_user(struct ksmbd_conn *conn, struct authenticate_message *authblob; struct ksmbd_user *user; char *name; - unsigned int auth_msg_len, name_off, name_len, secbuf_len; + unsigned int name_off, name_len, secbuf_len; secbuf_len = le16_to_cpu(req->SecurityBufferLength); if (secbuf_len < sizeof(struct authenticate_message)) { @@ -1366,9 +1377,8 @@ static struct ksmbd_user *session_user(struct ksmbd_conn *conn, authblob = user_authblob(conn, req); name_off = le32_to_cpu(authblob->UserName.BufferOffset); name_len = le16_to_cpu(authblob->UserName.Length); - auth_msg_len = le16_to_cpu(req->SecurityBufferOffset) + secbuf_len; - if (auth_msg_len < (u64)name_off + name_len) + if (secbuf_len < (u64)name_off + name_len) return NULL; name = smb_strndup_from_utf16((const char *)authblob + name_off, @@ -2464,7 +2474,7 @@ static int smb2_create_sd_buffer(struct ksmbd_work *work, return -ENOENT; /* Parse SD BUFFER create contexts */ - context = smb2_find_context_vals(req, SMB2_CREATE_SD_BUFFER); + context = smb2_find_context_vals(req, SMB2_CREATE_SD_BUFFER, 4); if (!context) return -ENOENT; else if (IS_ERR(context)) @@ -2666,7 +2676,7 @@ int smb2_open(struct ksmbd_work *work) if (req->CreateContextsOffset) { /* Parse non-durable handle create contexts */ - context = smb2_find_context_vals(req, SMB2_CREATE_EA_BUFFER); + context = smb2_find_context_vals(req, SMB2_CREATE_EA_BUFFER, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); goto err_out1; @@ -2686,7 +2696,7 @@ int smb2_open(struct ksmbd_work *work) } context = smb2_find_context_vals(req, - SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST); + SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); goto err_out1; @@ -2697,7 +2707,7 @@ int smb2_open(struct ksmbd_work *work) } context = smb2_find_context_vals(req, - SMB2_CREATE_TIMEWARP_REQUEST); + SMB2_CREATE_TIMEWARP_REQUEST, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); goto err_out1; @@ -2709,7 +2719,7 @@ int smb2_open(struct ksmbd_work *work) if (tcon->posix_extensions) { context = smb2_find_context_vals(req, - SMB2_CREATE_TAG_POSIX); + SMB2_CREATE_TAG_POSIX, 16); if (IS_ERR(context)) { rc = PTR_ERR(context); goto err_out1; @@ -3107,7 +3117,7 @@ int smb2_open(struct ksmbd_work *work) struct create_alloc_size_req *az_req; az_req = (struct create_alloc_size_req *)smb2_find_context_vals(req, - SMB2_CREATE_ALLOCATION_SIZE); + SMB2_CREATE_ALLOCATION_SIZE, 4); if (IS_ERR(az_req)) { rc = PTR_ERR(az_req); goto err_out; @@ -3134,7 +3144,7 @@ int smb2_open(struct ksmbd_work *work) err); } - context = smb2_find_context_vals(req, SMB2_CREATE_QUERY_ON_DISK_ID); + context = smb2_find_context_vals(req, SMB2_CREATE_QUERY_ON_DISK_ID, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); goto err_out; @@ -4359,21 +4369,6 @@ static int get_file_basic_info(struct smb2_query_info_rsp *rsp, return 0; } -static unsigned long long get_allocation_size(struct inode *inode, - struct kstat *stat) -{ - unsigned long long alloc_size = 0; - - if (!S_ISDIR(stat->mode)) { - if ((inode->i_blocks << 9) <= stat->size) - alloc_size = stat->size; - else - alloc_size = inode->i_blocks << 9; - } - - return alloc_size; -} - static void get_file_standard_info(struct smb2_query_info_rsp *rsp, struct ksmbd_file *fp, void *rsp_org) { @@ -4388,7 +4383,7 @@ static void get_file_standard_info(struct smb2_query_info_rsp *rsp, sinfo = (struct smb2_file_standard_info *)rsp->Buffer; delete_pending = ksmbd_inode_pending_delete(fp); - sinfo->AllocationSize = cpu_to_le64(get_allocation_size(inode, &stat)); + sinfo->AllocationSize = cpu_to_le64(inode->i_blocks << 9); sinfo->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size); sinfo->NumberOfLinks = cpu_to_le32(get_nlink(&stat) - delete_pending); sinfo->DeletePending = delete_pending; @@ -4453,7 +4448,7 @@ static int get_file_all_info(struct ksmbd_work *work, file_info->Attributes = fp->f_ci->m_fattr; file_info->Pad1 = 0; file_info->AllocationSize = - cpu_to_le64(get_allocation_size(inode, &stat)); + cpu_to_le64(inode->i_blocks << 9); file_info->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size); file_info->NumberOfLinks = cpu_to_le32(get_nlink(&stat) - delete_pending); @@ -4642,7 +4637,7 @@ static int get_file_network_open_info(struct smb2_query_info_rsp *rsp, file_info->ChangeTime = cpu_to_le64(time); file_info->Attributes = fp->f_ci->m_fattr; file_info->AllocationSize = - cpu_to_le64(get_allocation_size(inode, &stat)); + cpu_to_le64(inode->i_blocks << 9); file_info->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size); file_info->Reserved = cpu_to_le32(0); rsp->OutputBufferLength = @@ -5507,7 +5502,7 @@ static int smb2_create_link(struct ksmbd_work *work, { char *link_name = NULL, *target_name = NULL, *pathname = NULL; struct path path; - bool file_present = true; + bool file_present = false; int rc; if (buf_len < (u64)sizeof(struct smb2_file_link_info) + @@ -5540,8 +5535,8 @@ static int smb2_create_link(struct ksmbd_work *work, if (rc) { if (rc != -ENOENT) goto out; - file_present = false; - } + } else + file_present = true; if (file_info->ReplaceIfExists) { if (file_present) { diff --git a/fs/ksmbd/smb2pdu.h b/fs/smb/server/smb2pdu.h index 2767c08a534a..2767c08a534a 100644 --- a/fs/ksmbd/smb2pdu.h +++ b/fs/smb/server/smb2pdu.h diff --git a/fs/ksmbd/smb_common.c b/fs/smb/server/smb_common.c index af0c2a9b8529..af0c2a9b8529 100644 --- a/fs/ksmbd/smb_common.c +++ b/fs/smb/server/smb_common.c diff --git a/fs/ksmbd/smb_common.h b/fs/smb/server/smb_common.h index 9130d2e3cd78..6b0d5f1fe85c 100644 --- a/fs/ksmbd/smb_common.h +++ b/fs/smb/server/smb_common.h @@ -10,7 +10,7 @@ #include "glob.h" #include "nterr.h" -#include "../smbfs_common/smb2pdu.h" +#include "../common/smb2pdu.h" #include "smb2pdu.h" /* ksmbd's Specific ERRNO */ diff --git a/fs/ksmbd/smbacl.c b/fs/smb/server/smbacl.c index 6d6cfb6957a9..6d6cfb6957a9 100644 --- a/fs/ksmbd/smbacl.c +++ b/fs/smb/server/smbacl.c diff --git a/fs/ksmbd/smbacl.h b/fs/smb/server/smbacl.h index 49a8c292bd2e..49a8c292bd2e 100644 --- a/fs/ksmbd/smbacl.h +++ b/fs/smb/server/smbacl.h diff --git a/fs/ksmbd/smbfsctl.h b/fs/smb/server/smbfsctl.h index b98418aae20c..ecdf8f6e0df4 100644 --- a/fs/ksmbd/smbfsctl.h +++ b/fs/smb/server/smbfsctl.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: LGPL-2.1+ */ /* - * fs/cifs/smbfsctl.h: SMB, CIFS, SMB2 FSCTL definitions + * fs/smb/server/smbfsctl.h: SMB, CIFS, SMB2 FSCTL definitions * * Copyright (c) International Business Machines Corp., 2002,2009 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/ksmbd/smbstatus.h b/fs/smb/server/smbstatus.h index 108a8b6ed24a..8963deb42404 100644 --- a/fs/ksmbd/smbstatus.h +++ b/fs/smb/server/smbstatus.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: LGPL-2.1+ */ /* - * fs/cifs/smb2status.h + * fs/server/smb2status.h * * SMB2 Status code (network error) definitions * Definitions are from MS-ERREF diff --git a/fs/ksmbd/transport_ipc.c b/fs/smb/server/transport_ipc.c index 40c721f9227e..40c721f9227e 100644 --- a/fs/ksmbd/transport_ipc.c +++ b/fs/smb/server/transport_ipc.c diff --git a/fs/ksmbd/transport_ipc.h b/fs/smb/server/transport_ipc.h index 5e5b90a0c187..5e5b90a0c187 100644 --- a/fs/ksmbd/transport_ipc.h +++ b/fs/smb/server/transport_ipc.h diff --git a/fs/ksmbd/transport_rdma.c b/fs/smb/server/transport_rdma.c index c06efc020bd9..c06efc020bd9 100644 --- a/fs/ksmbd/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c diff --git a/fs/ksmbd/transport_rdma.h b/fs/smb/server/transport_rdma.h index 77aee4e5c9dc..77aee4e5c9dc 100644 --- a/fs/ksmbd/transport_rdma.h +++ b/fs/smb/server/transport_rdma.h diff --git a/fs/ksmbd/transport_tcp.c b/fs/smb/server/transport_tcp.c index eff7a1d793f0..eff7a1d793f0 100644 --- a/fs/ksmbd/transport_tcp.c +++ b/fs/smb/server/transport_tcp.c diff --git a/fs/ksmbd/transport_tcp.h b/fs/smb/server/transport_tcp.h index e338bebe322f..e338bebe322f 100644 --- a/fs/ksmbd/transport_tcp.h +++ b/fs/smb/server/transport_tcp.h diff --git a/fs/ksmbd/unicode.c b/fs/smb/server/unicode.c index 9ae676906ed3..9ae676906ed3 100644 --- a/fs/ksmbd/unicode.c +++ b/fs/smb/server/unicode.c diff --git a/fs/ksmbd/unicode.h b/fs/smb/server/unicode.h index 076f6034a789..076f6034a789 100644 --- a/fs/ksmbd/unicode.h +++ b/fs/smb/server/unicode.h diff --git a/fs/ksmbd/uniupr.h b/fs/smb/server/uniupr.h index 26583b776897..26583b776897 100644 --- a/fs/ksmbd/uniupr.h +++ b/fs/smb/server/uniupr.h diff --git a/fs/ksmbd/vfs.c b/fs/smb/server/vfs.c index 778c152708e4..6f302919e9f7 100644 --- a/fs/ksmbd/vfs.c +++ b/fs/smb/server/vfs.c @@ -86,12 +86,14 @@ static int ksmbd_vfs_path_lookup_locked(struct ksmbd_share_config *share_conf, err = vfs_path_parent_lookup(filename, flags, &parent_path, &last, &type, root_share_path); - putname(filename); - if (err) + if (err) { + putname(filename); return err; + } if (unlikely(type != LAST_NORM)) { path_put(&parent_path); + putname(filename); return -ENOENT; } @@ -108,12 +110,14 @@ static int ksmbd_vfs_path_lookup_locked(struct ksmbd_share_config *share_conf, path->dentry = d; path->mnt = share_conf->vfs_path.mnt; path_put(&parent_path); + putname(filename); return 0; err_out: inode_unlock(parent_path.dentry->d_inode); path_put(&parent_path); + putname(filename); return -ENOENT; } @@ -743,6 +747,7 @@ retry: rd.new_dir = new_path.dentry->d_inode, rd.new_dentry = new_dentry, rd.flags = flags, + rd.delegated_inode = NULL, err = vfs_rename(&rd); if (err) ksmbd_debug(VFS, "vfs_rename failed err %d\n", err); diff --git a/fs/ksmbd/vfs.h b/fs/smb/server/vfs.h index a4ae89f3230d..a4ae89f3230d 100644 --- a/fs/ksmbd/vfs.h +++ b/fs/smb/server/vfs.h diff --git a/fs/ksmbd/vfs_cache.c b/fs/smb/server/vfs_cache.c index 2d0138e72d78..2d0138e72d78 100644 --- a/fs/ksmbd/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c diff --git a/fs/ksmbd/vfs_cache.h b/fs/smb/server/vfs_cache.h index fcb13413fa8d..fcb13413fa8d 100644 --- a/fs/ksmbd/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h diff --git a/fs/ksmbd/xattr.h b/fs/smb/server/xattr.h index 16499ca5c82d..16499ca5c82d 100644 --- a/fs/ksmbd/xattr.h +++ b/fs/smb/server/xattr.h diff --git a/fs/splice.c b/fs/splice.c index 3e06611d19ae..67ddaac1f5c5 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -33,6 +33,7 @@ #include <linux/fsnotify.h> #include <linux/security.h> #include <linux/gfp.h> +#include <linux/net.h> #include <linux/socket.h> #include <linux/sched/signal.h> @@ -448,30 +449,6 @@ const struct pipe_buf_operations nosteal_pipe_buf_ops = { }; EXPORT_SYMBOL(nosteal_pipe_buf_ops); -/* - * Send 'sd->len' bytes to socket from 'sd->file' at position 'sd->pos' - * using sendpage(). Return the number of bytes sent. - */ -static int pipe_to_sendpage(struct pipe_inode_info *pipe, - struct pipe_buffer *buf, struct splice_desc *sd) -{ - struct file *file = sd->u.file; - loff_t pos = sd->pos; - int more; - - if (!likely(file->f_op->sendpage)) - return -EINVAL; - - more = (sd->flags & SPLICE_F_MORE) ? MSG_MORE : 0; - - if (sd->len < sd->total_len && - pipe_occupancy(pipe->head, pipe->tail) > 1) - more |= MSG_SENDPAGE_NOTLAST; - - return file->f_op->sendpage(file, buf->page, buf->offset, - sd->len, &pos, more); -} - static void wakeup_pipe_writers(struct pipe_inode_info *pipe) { smp_mb(); @@ -652,7 +629,7 @@ static void splice_from_pipe_end(struct pipe_inode_info *pipe, struct splice_des * Description: * This function does little more than loop over the pipe and call * @actor to do the actual moving of a single struct pipe_buffer to - * the desired destination. See pipe_to_file, pipe_to_sendpage, or + * the desired destination. See pipe_to_file, pipe_to_sendmsg, or * pipe_to_user. * */ @@ -833,8 +810,9 @@ done: EXPORT_SYMBOL(iter_file_splice_write); +#ifdef CONFIG_NET /** - * generic_splice_sendpage - splice data from a pipe to a socket + * splice_to_socket - splice data from a pipe to a socket * @pipe: pipe to splice from * @out: socket to write to * @ppos: position in @out @@ -846,13 +824,131 @@ EXPORT_SYMBOL(iter_file_splice_write); * is involved. * */ -ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, struct file *out, - loff_t *ppos, size_t len, unsigned int flags) +ssize_t splice_to_socket(struct pipe_inode_info *pipe, struct file *out, + loff_t *ppos, size_t len, unsigned int flags) { - return splice_from_pipe(pipe, out, ppos, len, flags, pipe_to_sendpage); -} + struct socket *sock = sock_from_file(out); + struct bio_vec bvec[16]; + struct msghdr msg = {}; + ssize_t ret = 0; + size_t spliced = 0; + bool need_wakeup = false; + + pipe_lock(pipe); + + while (len > 0) { + unsigned int head, tail, mask, bc = 0; + size_t remain = len; + + /* + * Check for signal early to make process killable when there + * are always buffers available + */ + ret = -ERESTARTSYS; + if (signal_pending(current)) + break; + + while (pipe_empty(pipe->head, pipe->tail)) { + ret = 0; + if (!pipe->writers) + goto out; + + if (spliced) + goto out; + + ret = -EAGAIN; + if (flags & SPLICE_F_NONBLOCK) + goto out; + + ret = -ERESTARTSYS; + if (signal_pending(current)) + goto out; + + if (need_wakeup) { + wakeup_pipe_writers(pipe); + need_wakeup = false; + } + + pipe_wait_readable(pipe); + } + + head = pipe->head; + tail = pipe->tail; + mask = pipe->ring_size - 1; + + while (!pipe_empty(head, tail)) { + struct pipe_buffer *buf = &pipe->bufs[tail & mask]; + size_t seg; + + if (!buf->len) { + tail++; + continue; + } + + seg = min_t(size_t, remain, buf->len); + seg = min_t(size_t, seg, PAGE_SIZE); + + ret = pipe_buf_confirm(pipe, buf); + if (unlikely(ret)) { + if (ret == -ENODATA) + ret = 0; + break; + } -EXPORT_SYMBOL(generic_splice_sendpage); + bvec_set_page(&bvec[bc++], buf->page, seg, buf->offset); + remain -= seg; + if (seg >= buf->len) + tail++; + if (bc >= ARRAY_SIZE(bvec)) + break; + } + + if (!bc) + break; + + msg.msg_flags = MSG_SPLICE_PAGES; + if (flags & SPLICE_F_MORE) + msg.msg_flags |= MSG_MORE; + if (remain && pipe_occupancy(pipe->head, tail) > 0) + msg.msg_flags |= MSG_MORE; + + iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, bvec, bc, + len - remain); + ret = sock_sendmsg(sock, &msg); + if (ret <= 0) + break; + + spliced += ret; + len -= ret; + tail = pipe->tail; + while (ret > 0) { + struct pipe_buffer *buf = &pipe->bufs[tail & mask]; + size_t seg = min_t(size_t, ret, buf->len); + + buf->offset += seg; + buf->len -= seg; + ret -= seg; + + if (!buf->len) { + pipe_buf_release(pipe, buf); + tail++; + } + } + + if (tail != pipe->tail) { + pipe->tail = tail; + if (pipe->files) + need_wakeup = true; + } + } + +out: + pipe_unlock(pipe); + if (need_wakeup) + wakeup_pipe_writers(pipe); + return spliced ?: ret; +} +#endif static int warn_unsupported(struct file *file, const char *op) { @@ -874,6 +970,17 @@ static long do_splice_from(struct pipe_inode_info *pipe, struct file *out, } /* + * Indicate to the caller that there was a premature EOF when reading from the + * source and the caller didn't indicate they would be sending more data after + * this. + */ +static void do_splice_eof(struct splice_desc *sd) +{ + if (sd->splice_eof) + sd->splice_eof(sd); +} + +/* * Attempt to initiate a splice from a file to a pipe. */ static long do_splice_to(struct file *in, loff_t *ppos, @@ -956,13 +1063,17 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd, */ bytes = 0; len = sd->total_len; + + /* Don't block on output, we have to drain the direct pipe. */ flags = sd->flags; + sd->flags &= ~SPLICE_F_NONBLOCK; /* - * Don't block on output, we have to drain the direct pipe. + * We signal MORE until we've read sufficient data to fulfill the + * request and we keep signalling it if the caller set it. */ - sd->flags &= ~SPLICE_F_NONBLOCK; more = sd->flags & SPLICE_F_MORE; + sd->flags |= SPLICE_F_MORE; WARN_ON_ONCE(!pipe_empty(pipe->head, pipe->tail)); @@ -972,20 +1083,18 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd, ret = do_splice_to(in, &pos, pipe, len, flags); if (unlikely(ret <= 0)) - goto out_release; + goto read_failure; read_len = ret; sd->total_len = read_len; /* - * If more data is pending, set SPLICE_F_MORE - * If this is the last data and SPLICE_F_MORE was not set - * initially, clears it. + * If we now have sufficient data to fulfill the request then + * we clear SPLICE_F_MORE if it was not set initially. */ - if (read_len < len) - sd->flags |= SPLICE_F_MORE; - else if (!more) + if (read_len >= len && !more) sd->flags &= ~SPLICE_F_MORE; + /* * NOTE: nonblocking mode only applies to the input. We * must not do the output in nonblocking mode as then we @@ -1012,6 +1121,15 @@ done: file_accessed(in); return bytes; +read_failure: + /* + * If the user did *not* set SPLICE_F_MORE *and* we didn't hit that + * "use all of len" case that cleared SPLICE_F_MORE, *and* we did a + * "->splice_in()" that returned EOF (ie zero) *and* we have sent at + * least 1 byte *then* we will also do the ->splice_eof() call. + */ + if (ret == 0 && !more && len > 0 && bytes) + do_splice_eof(sd); out_release: /* * If we did an incomplete transfer we must release @@ -1040,6 +1158,14 @@ static int direct_splice_actor(struct pipe_inode_info *pipe, sd->flags); } +static void direct_file_splice_eof(struct splice_desc *sd) +{ + struct file *file = sd->u.file; + + if (file->f_op->splice_eof) + file->f_op->splice_eof(file); +} + /** * do_splice_direct - splices data directly between two files * @in: file to splice from @@ -1065,6 +1191,7 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, .flags = flags, .pos = *ppos, .u.file = out, + .splice_eof = direct_file_splice_eof, .opos = opos, }; long ret; diff --git a/fs/statfs.c b/fs/statfs.c index 0ba34c135593..96d1c3edf289 100644 --- a/fs/statfs.c +++ b/fs/statfs.c @@ -130,6 +130,7 @@ static int do_statfs_native(struct kstatfs *st, struct statfs __user *p) if (sizeof(buf) == sizeof(*st)) memcpy(&buf, st, sizeof(*st)); else { + memset(&buf, 0, sizeof(buf)); if (sizeof buf.f_blocks == 4) { if ((st->f_blocks | st->f_bfree | st->f_bavail | st->f_bsize | st->f_frsize) & @@ -158,7 +159,6 @@ static int do_statfs_native(struct kstatfs *st, struct statfs __user *p) buf.f_namelen = st->f_namelen; buf.f_frsize = st->f_frsize; buf.f_flags = st->f_flags; - memset(buf.f_spare, 0, sizeof(buf.f_spare)); } if (copy_to_user(p, &buf, sizeof(buf))) return -EFAULT; @@ -171,6 +171,7 @@ static int do_statfs64(struct kstatfs *st, struct statfs64 __user *p) if (sizeof(buf) == sizeof(*st)) memcpy(&buf, st, sizeof(*st)); else { + memset(&buf, 0, sizeof(buf)); buf.f_type = st->f_type; buf.f_bsize = st->f_bsize; buf.f_blocks = st->f_blocks; @@ -182,7 +183,6 @@ static int do_statfs64(struct kstatfs *st, struct statfs64 __user *p) buf.f_namelen = st->f_namelen; buf.f_frsize = st->f_frsize; buf.f_flags = st->f_flags; - memset(buf.f_spare, 0, sizeof(buf.f_spare)); } if (copy_to_user(p, &buf, sizeof(buf))) return -EFAULT; diff --git a/fs/xattr.c b/fs/xattr.c index fcf67d80d7f9..e7bbb7f57557 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -985,9 +985,16 @@ int xattr_list_one(char **buffer, ssize_t *remaining_size, const char *name) return 0; } -/* +/** + * generic_listxattr - run through a dentry's xattr list() operations + * @dentry: dentry to list the xattrs + * @buffer: result buffer + * @buffer_size: size of @buffer + * * Combine the results of the list() operation from every xattr_handler in the - * list. + * xattr_handler stack. + * + * Note that this will not include the entries for POSIX ACLs. */ ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) @@ -996,10 +1003,6 @@ generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) ssize_t remaining_size = buffer_size; int err = 0; - err = posix_acl_listxattr(d_inode(dentry), &buffer, &remaining_size); - if (err) - return err; - for_each_xattr_handler(handlers, handler) { if (!handler->name || (handler->list && !handler->list(dentry))) continue; diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c index 1b078bbbf225..ee84835ebc66 100644 --- a/fs/xfs/libxfs/xfs_ag.c +++ b/fs/xfs/libxfs/xfs_ag.c @@ -495,10 +495,12 @@ xfs_freesp_init_recs( ASSERT(start >= mp->m_ag_prealloc_blocks); if (start != mp->m_ag_prealloc_blocks) { /* - * Modify first record to pad stripe align of log + * Modify first record to pad stripe align of log and + * bump the record count. */ arec->ar_blockcount = cpu_to_be32(start - mp->m_ag_prealloc_blocks); + be16_add_cpu(&block->bb_numrecs, 1); nrec = arec + 1; /* @@ -509,7 +511,6 @@ xfs_freesp_init_recs( be32_to_cpu(arec->ar_startblock) + be32_to_cpu(arec->ar_blockcount)); arec = nrec; - be16_add_cpu(&block->bb_numrecs, 1); } /* * Change record start to after the internal log @@ -518,15 +519,13 @@ xfs_freesp_init_recs( } /* - * Calculate the record block count and check for the case where - * the log might have consumed all available space in the AG. If - * so, reset the record count to 0 to avoid exposure of an invalid - * record start block. + * Calculate the block count of this record; if it is nonzero, + * increment the record count. */ arec->ar_blockcount = cpu_to_be32(id->agsize - be32_to_cpu(arec->ar_startblock)); - if (!arec->ar_blockcount) - block->bb_numrecs = 0; + if (arec->ar_blockcount) + be16_add_cpu(&block->bb_numrecs, 1); } /* @@ -538,7 +537,7 @@ xfs_bnoroot_init( struct xfs_buf *bp, struct aghdr_init_data *id) { - xfs_btree_init_block(mp, bp, XFS_BTNUM_BNO, 0, 1, id->agno); + xfs_btree_init_block(mp, bp, XFS_BTNUM_BNO, 0, 0, id->agno); xfs_freesp_init_recs(mp, bp, id); } @@ -548,7 +547,7 @@ xfs_cntroot_init( struct xfs_buf *bp, struct aghdr_init_data *id) { - xfs_btree_init_block(mp, bp, XFS_BTNUM_CNT, 0, 1, id->agno); + xfs_btree_init_block(mp, bp, XFS_BTNUM_CNT, 0, 0, id->agno); xfs_freesp_init_recs(mp, bp, id); } @@ -985,7 +984,10 @@ xfs_ag_shrink_space( if (err2 != -ENOSPC) goto resv_err; - __xfs_free_extent_later(*tpp, args.fsbno, delta, NULL, true); + err2 = __xfs_free_extent_later(*tpp, args.fsbno, delta, NULL, + true); + if (err2) + goto resv_err; /* * Roll the transaction before trying to re-init the per-ag diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index fdfa08cbf4db..c20fe99405d8 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -628,6 +628,25 @@ xfs_alloc_fixup_trees( return 0; } +/* + * We do not verify the AGFL contents against AGF-based index counters here, + * even though we may have access to the perag that contains shadow copies. We + * don't know if the AGF based counters have been checked, and if they have they + * still may be inconsistent because they haven't yet been reset on the first + * allocation after the AGF has been read in. + * + * This means we can only check that all agfl entries contain valid or null + * values because we can't reliably determine the active range to exclude + * NULLAGBNO as a valid value. + * + * However, we can't even do that for v4 format filesystems because there are + * old versions of mkfs out there that does not initialise the AGFL to known, + * verifiable values. HEnce we can't tell the difference between a AGFL block + * allocated by mkfs and a corrupted AGFL block here on v4 filesystems. + * + * As a result, we can only fully validate AGFL block numbers when we pull them + * from the freelist in xfs_alloc_get_freelist(). + */ static xfs_failaddr_t xfs_agfl_verify( struct xfs_buf *bp) @@ -637,12 +656,6 @@ xfs_agfl_verify( __be32 *agfl_bno = xfs_buf_to_agfl_bno(bp); int i; - /* - * There is no verification of non-crc AGFLs because mkfs does not - * initialise the AGFL to zero or NULL. Hence the only valid part of the - * AGFL is what the AGF says is active. We can't get to the AGF, so we - * can't verify just those entries are valid. - */ if (!xfs_has_crc(mp)) return NULL; @@ -2321,12 +2334,16 @@ xfs_free_agfl_block( } /* - * Check the agfl fields of the agf for inconsistency or corruption. The purpose - * is to detect an agfl header padding mismatch between current and early v5 - * kernels. This problem manifests as a 1-slot size difference between the - * on-disk flcount and the active [first, last] range of a wrapped agfl. This - * may also catch variants of agfl count corruption unrelated to padding. Either - * way, we'll reset the agfl and warn the user. + * Check the agfl fields of the agf for inconsistency or corruption. + * + * The original purpose was to detect an agfl header padding mismatch between + * current and early v5 kernels. This problem manifests as a 1-slot size + * difference between the on-disk flcount and the active [first, last] range of + * a wrapped agfl. + * + * However, we need to use these same checks to catch agfl count corruptions + * unrelated to padding. This could occur on any v4 or v5 filesystem, so either + * way, we need to reset the agfl and warn the user. * * Return true if a reset is required before the agfl can be used, false * otherwise. @@ -2342,10 +2359,6 @@ xfs_agfl_needs_reset( int agfl_size = xfs_agfl_size(mp); int active; - /* no agfl header on v4 supers */ - if (!xfs_has_crc(mp)) - return false; - /* * The agf read verifier catches severe corruption of these fields. * Repeat some sanity checks to cover a packed -> unpacked mismatch if @@ -2418,7 +2431,7 @@ xfs_agfl_reset( * the real allocation can proceed. Deferring the free disconnects freeing up * the AGFL slot from freeing the block. */ -STATIC void +static int xfs_defer_agfl_block( struct xfs_trans *tp, xfs_agnumber_t agno, @@ -2437,17 +2450,21 @@ xfs_defer_agfl_block( xefi->xefi_blockcount = 1; xefi->xefi_owner = oinfo->oi_owner; + if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbno(mp, xefi->xefi_startblock))) + return -EFSCORRUPTED; + trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1); xfs_extent_free_get_group(mp, xefi); xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_AGFL_FREE, &xefi->xefi_list); + return 0; } /* * Add the extent to the list of extents to be free at transaction end. * The list is maintained sorted (by block number). */ -void +int __xfs_free_extent_later( struct xfs_trans *tp, xfs_fsblock_t bno, @@ -2474,6 +2491,9 @@ __xfs_free_extent_later( #endif ASSERT(xfs_extfree_item_cache != NULL); + if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbext(mp, bno, len))) + return -EFSCORRUPTED; + xefi = kmem_cache_zalloc(xfs_extfree_item_cache, GFP_KERNEL | __GFP_NOFAIL); xefi->xefi_startblock = bno; @@ -2497,6 +2517,7 @@ __xfs_free_extent_later( xfs_extent_free_get_group(mp, xefi); xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_FREE, &xefi->xefi_list); + return 0; } #ifdef DEBUG @@ -2657,7 +2678,9 @@ xfs_alloc_fix_freelist( goto out_agbp_relse; /* defer agfl frees */ - xfs_defer_agfl_block(tp, args->agno, bno, &targs.oinfo); + error = xfs_defer_agfl_block(tp, args->agno, bno, &targs.oinfo); + if (error) + goto out_agbp_relse; } targs.tp = tp; @@ -2767,6 +2790,9 @@ xfs_alloc_get_freelist( */ agfl_bno = xfs_buf_to_agfl_bno(agflbp); bno = be32_to_cpu(agfl_bno[be32_to_cpu(agf->agf_flfirst)]); + if (XFS_IS_CORRUPT(tp->t_mountp, !xfs_verify_agbno(pag, bno))) + return -EFSCORRUPTED; + be32_add_cpu(&agf->agf_flfirst, 1); xfs_trans_brelse(tp, agflbp); if (be32_to_cpu(agf->agf_flfirst) == xfs_agfl_size(mp)) @@ -2889,6 +2915,19 @@ xfs_alloc_put_freelist( return 0; } +/* + * Verify the AGF is consistent. + * + * We do not verify the AGFL indexes in the AGF are fully consistent here + * because of issues with variable on-disk structure sizes. Instead, we check + * the agfl indexes for consistency when we initialise the perag from the AGF + * information after a read completes. + * + * If the index is inconsistent, then we mark the perag as needing an AGFL + * reset. The first AGFL update performed then resets the AGFL indexes and + * refills the AGFL with known good free blocks, allowing the filesystem to + * continue operating normally at the cost of a few leaked free space blocks. + */ static xfs_failaddr_t xfs_agf_verify( struct xfs_buf *bp) @@ -2962,7 +3001,6 @@ xfs_agf_verify( return __this_address; return NULL; - } static void @@ -3187,7 +3225,8 @@ xfs_alloc_vextent_check_args( */ static int xfs_alloc_vextent_prepare_ag( - struct xfs_alloc_arg *args) + struct xfs_alloc_arg *args, + uint32_t flags) { bool need_pag = !args->pag; int error; @@ -3196,7 +3235,7 @@ xfs_alloc_vextent_prepare_ag( args->pag = xfs_perag_get(args->mp, args->agno); args->agbp = NULL; - error = xfs_alloc_fix_freelist(args, 0); + error = xfs_alloc_fix_freelist(args, flags); if (error) { trace_xfs_alloc_vextent_nofix(args); if (need_pag) @@ -3336,7 +3375,7 @@ xfs_alloc_vextent_this_ag( return error; } - error = xfs_alloc_vextent_prepare_ag(args); + error = xfs_alloc_vextent_prepare_ag(args, 0); if (!error && args->agbp) error = xfs_alloc_ag_vextent_size(args); @@ -3380,7 +3419,7 @@ restart: for_each_perag_wrap_range(mp, start_agno, restart_agno, mp->m_sb.sb_agcount, agno, args->pag) { args->agno = agno; - error = xfs_alloc_vextent_prepare_ag(args); + error = xfs_alloc_vextent_prepare_ag(args, flags); if (error) break; if (!args->agbp) { @@ -3546,7 +3585,7 @@ xfs_alloc_vextent_exact_bno( return error; } - error = xfs_alloc_vextent_prepare_ag(args); + error = xfs_alloc_vextent_prepare_ag(args, 0); if (!error && args->agbp) error = xfs_alloc_ag_vextent_exact(args); @@ -3587,7 +3626,7 @@ xfs_alloc_vextent_near_bno( if (needs_perag) args->pag = xfs_perag_grab(mp, args->agno); - error = xfs_alloc_vextent_prepare_ag(args); + error = xfs_alloc_vextent_prepare_ag(args, 0); if (!error && args->agbp) error = xfs_alloc_ag_vextent_near(args); diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h index 5dbb25546d0b..85ac470be0da 100644 --- a/fs/xfs/libxfs/xfs_alloc.h +++ b/fs/xfs/libxfs/xfs_alloc.h @@ -230,7 +230,7 @@ xfs_buf_to_agfl_bno( return bp->b_addr; } -void __xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno, +int __xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno, xfs_filblks_t len, const struct xfs_owner_info *oinfo, bool skip_discard); @@ -254,14 +254,14 @@ void xfs_extent_free_get_group(struct xfs_mount *mp, #define XFS_EFI_ATTR_FORK (1U << 1) /* freeing attr fork block */ #define XFS_EFI_BMBT_BLOCK (1U << 2) /* freeing bmap btree block */ -static inline void +static inline int xfs_free_extent_later( struct xfs_trans *tp, xfs_fsblock_t bno, xfs_filblks_t len, const struct xfs_owner_info *oinfo) { - __xfs_free_extent_later(tp, bno, len, oinfo, false); + return __xfs_free_extent_later(tp, bno, len, oinfo, false); } diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index b512de0540d5..fef35696adb7 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -572,8 +572,12 @@ xfs_bmap_btree_to_extents( cblock = XFS_BUF_TO_BLOCK(cbp); if ((error = xfs_btree_check_block(cur, cblock, 0, cbp))) return error; + xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork); - xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo); + error = xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo); + if (error) + return error; + ip->i_nblocks--; xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L); xfs_trans_binval(tp, cbp); @@ -3494,8 +3498,10 @@ xfs_bmap_btalloc_at_eof( if (!caller_pag) args->pag = xfs_perag_get(mp, XFS_FSB_TO_AGNO(mp, ap->blkno)); error = xfs_alloc_vextent_exact_bno(args, ap->blkno); - if (!caller_pag) + if (!caller_pag) { xfs_perag_put(args->pag); + args->pag = NULL; + } if (error) return error; @@ -3505,7 +3511,6 @@ xfs_bmap_btalloc_at_eof( * Exact allocation failed. Reset to try an aligned allocation * according to the original allocation specification. */ - args->pag = NULL; args->alignment = stripe_align; args->minlen = nextminlen; args->minalignslop = 0; @@ -5229,10 +5234,12 @@ xfs_bmap_del_extent_real( if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) { xfs_refcount_decrease_extent(tp, del); } else { - __xfs_free_extent_later(tp, del->br_startblock, + error = __xfs_free_extent_later(tp, del->br_startblock, del->br_blockcount, NULL, (bflags & XFS_BMAPI_NODISCARD) || del->br_state == XFS_EXT_UNWRITTEN); + if (error) + goto done; } } diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index 1b40e5f8b1ec..36564ae3084f 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -268,11 +268,14 @@ xfs_bmbt_free_block( struct xfs_trans *tp = cur->bc_tp; xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp)); struct xfs_owner_info oinfo; + int error; xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_ino.whichfork); - xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo); - ip->i_nblocks--; + error = xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo); + if (error) + return error; + ip->i_nblocks--; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L); return 0; diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index a16d5de16933..34600f94c2f4 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -1834,7 +1834,7 @@ retry: * might be sparse and only free the regions that are allocated as part of the * chunk. */ -STATIC void +static int xfs_difree_inode_chunk( struct xfs_trans *tp, xfs_agnumber_t agno, @@ -1851,10 +1851,10 @@ xfs_difree_inode_chunk( if (!xfs_inobt_issparse(rec->ir_holemask)) { /* not sparse, calculate extent info directly */ - xfs_free_extent_later(tp, XFS_AGB_TO_FSB(mp, agno, sagbno), - M_IGEO(mp)->ialloc_blks, - &XFS_RMAP_OINFO_INODES); - return; + return xfs_free_extent_later(tp, + XFS_AGB_TO_FSB(mp, agno, sagbno), + M_IGEO(mp)->ialloc_blks, + &XFS_RMAP_OINFO_INODES); } /* holemask is only 16-bits (fits in an unsigned long) */ @@ -1871,6 +1871,8 @@ xfs_difree_inode_chunk( XFS_INOBT_HOLEMASK_BITS); nextbit = startidx + 1; while (startidx < XFS_INOBT_HOLEMASK_BITS) { + int error; + nextbit = find_next_zero_bit(holemask, XFS_INOBT_HOLEMASK_BITS, nextbit); /* @@ -1896,8 +1898,11 @@ xfs_difree_inode_chunk( ASSERT(agbno % mp->m_sb.sb_spino_align == 0); ASSERT(contigblk % mp->m_sb.sb_spino_align == 0); - xfs_free_extent_later(tp, XFS_AGB_TO_FSB(mp, agno, agbno), - contigblk, &XFS_RMAP_OINFO_INODES); + error = xfs_free_extent_later(tp, + XFS_AGB_TO_FSB(mp, agno, agbno), + contigblk, &XFS_RMAP_OINFO_INODES); + if (error) + return error; /* reset range to current bit and carry on... */ startidx = endidx = nextbit; @@ -1905,6 +1910,7 @@ xfs_difree_inode_chunk( next: nextbit++; } + return 0; } STATIC int @@ -2003,7 +2009,9 @@ xfs_difree_inobt( goto error0; } - xfs_difree_inode_chunk(tp, pag->pag_agno, &rec); + error = xfs_difree_inode_chunk(tp, pag->pag_agno, &rec); + if (error) + goto error0; } else { xic->deleted = false; diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h index f13e0809dc63..269573c82808 100644 --- a/fs/xfs/libxfs/xfs_log_format.h +++ b/fs/xfs/libxfs/xfs_log_format.h @@ -324,7 +324,6 @@ struct xfs_inode_log_format_32 { #define XFS_ILOG_DOWNER 0x200 /* change the data fork owner on replay */ #define XFS_ILOG_AOWNER 0x400 /* change the attr fork owner on replay */ - /* * The timestamps are dirty, but not necessarily anything else in the inode * core. Unlike the other fields above this one must never make it to disk @@ -333,6 +332,14 @@ struct xfs_inode_log_format_32 { */ #define XFS_ILOG_TIMESTAMP 0x4000 +/* + * The version field has been changed, but not necessarily anything else of + * interest. This must never make it to disk - it is used purely to ensure that + * the inode item ->precommit operation can update the fsync flag triggers + * in the inode item correctly. + */ +#define XFS_ILOG_IVERSION 0x8000 + #define XFS_ILOG_NONCORE (XFS_ILOG_DDATA | XFS_ILOG_DEXT | \ XFS_ILOG_DBROOT | XFS_ILOG_DEV | \ XFS_ILOG_ADATA | XFS_ILOG_AEXT | \ diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index c1c65774dcc2..b6e21433925c 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -1151,8 +1151,10 @@ xfs_refcount_adjust_extents( fsbno = XFS_AGB_TO_FSB(cur->bc_mp, cur->bc_ag.pag->pag_agno, tmp.rc_startblock); - xfs_free_extent_later(cur->bc_tp, fsbno, + error = xfs_free_extent_later(cur->bc_tp, fsbno, tmp.rc_blockcount, NULL); + if (error) + goto out_error; } (*agbno) += tmp.rc_blockcount; @@ -1210,8 +1212,10 @@ xfs_refcount_adjust_extents( fsbno = XFS_AGB_TO_FSB(cur->bc_mp, cur->bc_ag.pag->pag_agno, ext.rc_startblock); - xfs_free_extent_later(cur->bc_tp, fsbno, + error = xfs_free_extent_later(cur->bc_tp, fsbno, ext.rc_blockcount, NULL); + if (error) + goto out_error; } skip: @@ -1976,7 +1980,10 @@ xfs_refcount_recover_cow_leftovers( rr->rr_rrec.rc_blockcount); /* Free the block. */ - xfs_free_extent_later(tp, fsb, rr->rr_rrec.rc_blockcount, NULL); + error = xfs_free_extent_later(tp, fsb, + rr->rr_rrec.rc_blockcount, NULL); + if (error) + goto out_trans; error = xfs_trans_commit(tp); if (error) diff --git a/fs/xfs/libxfs/xfs_trans_inode.c b/fs/xfs/libxfs/xfs_trans_inode.c index 8b5547073379..cb4796b6e693 100644 --- a/fs/xfs/libxfs/xfs_trans_inode.c +++ b/fs/xfs/libxfs/xfs_trans_inode.c @@ -40,9 +40,8 @@ xfs_trans_ijoin( iip->ili_lock_flags = lock_flags; ASSERT(!xfs_iflags_test(ip, XFS_ISTALE)); - /* - * Get a log_item_desc to point at the new item. - */ + /* Reset the per-tx dirty context and add the item to the tx. */ + iip->ili_dirty_flags = 0; xfs_trans_add_item(tp, &iip->ili_item); } @@ -76,17 +75,10 @@ xfs_trans_ichgtime( /* * This is called to mark the fields indicated in fieldmask as needing to be * logged when the transaction is committed. The inode must already be - * associated with the given transaction. - * - * The values for fieldmask are defined in xfs_inode_item.h. We always log all - * of the core inode if any of it has changed, and we always log all of the - * inline data/extents/b-tree root if any of them has changed. - * - * Grab and pin the cluster buffer associated with this inode to avoid RMW - * cycles at inode writeback time. Avoid the need to add error handling to every - * xfs_trans_log_inode() call by shutting down on read error. This will cause - * transactions to fail and everything to error out, just like if we return a - * read error in a dirty transaction and cancel it. + * associated with the given transaction. All we do here is record where the + * inode was dirtied and mark the transaction and inode log item dirty; + * everything else is done in the ->precommit log item operation after the + * changes in the transaction have been completed. */ void xfs_trans_log_inode( @@ -96,7 +88,6 @@ xfs_trans_log_inode( { struct xfs_inode_log_item *iip = ip->i_itemp; struct inode *inode = VFS_I(ip); - uint iversion_flags = 0; ASSERT(iip); ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); @@ -105,18 +96,6 @@ xfs_trans_log_inode( tp->t_flags |= XFS_TRANS_DIRTY; /* - * Don't bother with i_lock for the I_DIRTY_TIME check here, as races - * don't matter - we either will need an extra transaction in 24 hours - * to log the timestamps, or will clear already cleared fields in the - * worst case. - */ - if (inode->i_state & I_DIRTY_TIME) { - spin_lock(&inode->i_lock); - inode->i_state &= ~I_DIRTY_TIME; - spin_unlock(&inode->i_lock); - } - - /* * First time we log the inode in a transaction, bump the inode change * counter if it is configured for this to occur. While we have the * inode locked exclusively for metadata modification, we can usually @@ -128,86 +107,10 @@ xfs_trans_log_inode( if (!test_and_set_bit(XFS_LI_DIRTY, &iip->ili_item.li_flags)) { if (IS_I_VERSION(inode) && inode_maybe_inc_iversion(inode, flags & XFS_ILOG_CORE)) - iversion_flags = XFS_ILOG_CORE; - } - - /* - * If we're updating the inode core or the timestamps and it's possible - * to upgrade this inode to bigtime format, do so now. - */ - if ((flags & (XFS_ILOG_CORE | XFS_ILOG_TIMESTAMP)) && - xfs_has_bigtime(ip->i_mount) && - !xfs_inode_has_bigtime(ip)) { - ip->i_diflags2 |= XFS_DIFLAG2_BIGTIME; - flags |= XFS_ILOG_CORE; - } - - /* - * Inode verifiers do not check that the extent size hint is an integer - * multiple of the rt extent size on a directory with both rtinherit - * and extszinherit flags set. If we're logging a directory that is - * misconfigured in this way, clear the hint. - */ - if ((ip->i_diflags & XFS_DIFLAG_RTINHERIT) && - (ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) && - (ip->i_extsize % ip->i_mount->m_sb.sb_rextsize) > 0) { - ip->i_diflags &= ~(XFS_DIFLAG_EXTSIZE | - XFS_DIFLAG_EXTSZINHERIT); - ip->i_extsize = 0; - flags |= XFS_ILOG_CORE; + flags |= XFS_ILOG_IVERSION; } - /* - * Record the specific change for fdatasync optimisation. This allows - * fdatasync to skip log forces for inodes that are only timestamp - * dirty. - */ - spin_lock(&iip->ili_lock); - iip->ili_fsync_fields |= flags; - - if (!iip->ili_item.li_buf) { - struct xfs_buf *bp; - int error; - - /* - * We hold the ILOCK here, so this inode is not going to be - * flushed while we are here. Further, because there is no - * buffer attached to the item, we know that there is no IO in - * progress, so nothing will clear the ili_fields while we read - * in the buffer. Hence we can safely drop the spin lock and - * read the buffer knowing that the state will not change from - * here. - */ - spin_unlock(&iip->ili_lock); - error = xfs_imap_to_bp(ip->i_mount, tp, &ip->i_imap, &bp); - if (error) { - xfs_force_shutdown(ip->i_mount, SHUTDOWN_META_IO_ERROR); - return; - } - - /* - * We need an explicit buffer reference for the log item but - * don't want the buffer to remain attached to the transaction. - * Hold the buffer but release the transaction reference once - * we've attached the inode log item to the buffer log item - * list. - */ - xfs_buf_hold(bp); - spin_lock(&iip->ili_lock); - iip->ili_item.li_buf = bp; - bp->b_flags |= _XBF_INODES; - list_add_tail(&iip->ili_item.li_bio_list, &bp->b_li_list); - xfs_trans_brelse(tp, bp); - } - - /* - * Always OR in the bits from the ili_last_fields field. This is to - * coordinate with the xfs_iflush() and xfs_buf_inode_iodone() routines - * in the eventual clearing of the ili_fields bits. See the big comment - * in xfs_iflush() for an explanation of this coordination mechanism. - */ - iip->ili_fields |= (flags | iip->ili_last_fields | iversion_flags); - spin_unlock(&iip->ili_lock); + iip->ili_dirty_flags |= flags; } int diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index 87ab9f95a487..5bf4326e9783 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -42,12 +42,12 @@ xchk_setup_inode_bmap( xfs_ilock(sc->ip, XFS_IOLOCK_EXCL); /* - * We don't want any ephemeral data fork updates sitting around + * We don't want any ephemeral data/cow fork updates sitting around * while we inspect block mappings, so wait for directio to finish * and flush dirty data if we have delalloc reservations. */ if (S_ISREG(VFS_I(sc->ip)->i_mode) && - sc->sm->sm_type == XFS_SCRUB_TYPE_BMBTD) { + sc->sm->sm_type != XFS_SCRUB_TYPE_BMBTA) { struct address_space *mapping = VFS_I(sc->ip)->i_mapping; sc->ilock_flags |= XFS_MMAPLOCK_EXCL; @@ -769,14 +769,14 @@ xchk_are_bmaps_contiguous( * mapping or false if there are no more mappings. Caller must ensure that * @info.icur is zeroed before the first call. */ -static int +static bool xchk_bmap_iext_iter( struct xchk_bmap_info *info, struct xfs_bmbt_irec *irec) { struct xfs_bmbt_irec got; struct xfs_ifork *ifp; - xfs_filblks_t prev_len; + unsigned int nr = 0; ifp = xfs_ifork_ptr(info->sc->ip, info->whichfork); @@ -790,12 +790,12 @@ xchk_bmap_iext_iter( irec->br_startoff); return false; } + nr++; /* * Iterate subsequent iextent records and merge them with the one * that we just read, if possible. */ - prev_len = irec->br_blockcount; while (xfs_iext_peek_next_extent(ifp, &info->icur, &got)) { if (!xchk_are_bmaps_contiguous(irec, &got)) break; @@ -805,20 +805,21 @@ xchk_bmap_iext_iter( got.br_startoff); return false; } - - /* - * Notify the user of mergeable records in the data or attr - * forks. CoW forks only exist in memory so we ignore them. - */ - if (info->whichfork != XFS_COW_FORK && - prev_len + got.br_blockcount > BMBT_BLOCKCOUNT_MASK) - xchk_ino_set_preen(info->sc, info->sc->ip->i_ino); + nr++; irec->br_blockcount += got.br_blockcount; - prev_len = got.br_blockcount; xfs_iext_next(ifp, &info->icur); } + /* + * If the merged mapping could be expressed with fewer bmbt records + * than we actually found, notify the user that this fork could be + * optimized. CoW forks only exist in memory so we ignore them. + */ + if (nr > 1 && info->whichfork != XFS_COW_FORK && + howmany_64(irec->br_blockcount, XFS_MAX_BMBT_EXTLEN) < nr) + xchk_ino_set_preen(info->sc, info->sc->ip->i_ino); + return true; } diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c index 9aa79665c608..7a20256be969 100644 --- a/fs/xfs/scrub/common.c +++ b/fs/xfs/scrub/common.c @@ -1164,32 +1164,6 @@ xchk_metadata_inode_forks( return 0; } -/* Pause background reaping of resources. */ -void -xchk_stop_reaping( - struct xfs_scrub *sc) -{ - sc->flags |= XCHK_REAPING_DISABLED; - xfs_blockgc_stop(sc->mp); - xfs_inodegc_stop(sc->mp); -} - -/* Restart background reaping of resources. */ -void -xchk_start_reaping( - struct xfs_scrub *sc) -{ - /* - * Readonly filesystems do not perform inactivation or speculative - * preallocation, so there's no need to restart the workers. - */ - if (!xfs_is_readonly(sc->mp)) { - xfs_inodegc_start(sc->mp); - xfs_blockgc_start(sc->mp); - } - sc->flags &= ~XCHK_REAPING_DISABLED; -} - /* * Enable filesystem hooks (i.e. runtime code patching) before starting a scrub * operation. Callers must not hold any locks that intersect with the CPU diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h index 18b5f2b62f13..791235cd9b00 100644 --- a/fs/xfs/scrub/common.h +++ b/fs/xfs/scrub/common.h @@ -156,8 +156,6 @@ static inline bool xchk_skip_xref(struct xfs_scrub_metadata *sm) } int xchk_metadata_inode_forks(struct xfs_scrub *sc); -void xchk_stop_reaping(struct xfs_scrub *sc); -void xchk_start_reaping(struct xfs_scrub *sc); /* * Setting up a hook to wait for intents to drain is costly -- we have to take diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c index faa315be7978..e382a35e98d8 100644 --- a/fs/xfs/scrub/fscounters.c +++ b/fs/xfs/scrub/fscounters.c @@ -150,13 +150,6 @@ xchk_setup_fscounters( if (error) return error; - /* - * Pause background reclaim while we're scrubbing to reduce the - * likelihood of background perturbations to the counters throwing off - * our calculations. - */ - xchk_stop_reaping(sc); - return xchk_trans_alloc(sc, 0); } @@ -454,6 +447,12 @@ xchk_fscounters( xchk_set_corrupt(sc); /* + * XXX: We can't quiesce percpu counter updates, so exit early. + * This can be re-enabled when we gain exclusive freeze functionality. + */ + return 0; + + /* * If ifree exceeds icount by more than the minimum variance then * something's probably wrong with the counters. */ diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index 02819bedc5b1..3d98f604765e 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -186,8 +186,6 @@ xchk_teardown( } if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) mnt_drop_write_file(sc->file); - if (sc->flags & XCHK_REAPING_DISABLED) - xchk_start_reaping(sc); if (sc->buf) { if (sc->buf_cleanup) sc->buf_cleanup(sc->buf); diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h index e71903474cd7..e113f2f5c254 100644 --- a/fs/xfs/scrub/scrub.h +++ b/fs/xfs/scrub/scrub.h @@ -105,11 +105,10 @@ struct xfs_scrub { }; /* XCHK state flags grow up from zero, XREP state flags grown down from 2^31 */ -#define XCHK_TRY_HARDER (1 << 0) /* can't get resources, try again */ -#define XCHK_REAPING_DISABLED (1 << 1) /* background block reaping paused */ -#define XCHK_FSGATES_DRAIN (1 << 2) /* defer ops draining enabled */ -#define XCHK_NEED_DRAIN (1 << 3) /* scrub needs to drain defer ops */ -#define XREP_ALREADY_FIXED (1 << 31) /* checking our repair work */ +#define XCHK_TRY_HARDER (1U << 0) /* can't get resources, try again */ +#define XCHK_FSGATES_DRAIN (1U << 2) /* defer ops draining enabled */ +#define XCHK_NEED_DRAIN (1U << 3) /* scrub needs to drain defer ops */ +#define XREP_ALREADY_FIXED (1U << 31) /* checking our repair work */ /* * The XCHK_FSGATES* flags reflect functionality in the main filesystem that diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h index 68efd6fda61c..b3894daeb86a 100644 --- a/fs/xfs/scrub/trace.h +++ b/fs/xfs/scrub/trace.h @@ -98,7 +98,6 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_FSCOUNTERS); #define XFS_SCRUB_STATE_STRINGS \ { XCHK_TRY_HARDER, "try_harder" }, \ - { XCHK_REAPING_DISABLED, "reaping_disabled" }, \ { XCHK_FSGATES_DRAIN, "fsgates_drain" }, \ { XCHK_NEED_DRAIN, "need_drain" }, \ { XREP_ALREADY_FIXED, "already_fixed" } diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index f032d3a4b727..fbb675563208 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -558,7 +558,9 @@ xfs_getbmap( if (!xfs_iext_next_extent(ifp, &icur, &got)) { xfs_fileoff_t end = XFS_B_TO_FSB(mp, XFS_ISIZE(ip)); - out[bmv->bmv_entries - 1].bmv_oflags |= BMV_OF_LAST; + if (bmv->bmv_entries > 0) + out[bmv->bmv_entries - 1].bmv_oflags |= + BMV_OF_LAST; if (whichfork != XFS_ATTR_FORK && bno < end && !xfs_getbmap_full(bmv)) { diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index df7322ed73fa..023d4e0385dd 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -452,10 +452,18 @@ xfs_buf_item_format( * This is called to pin the buffer associated with the buf log item in memory * so it cannot be written out. * - * We also always take a reference to the buffer log item here so that the bli - * is held while the item is pinned in memory. This means that we can - * unconditionally drop the reference count a transaction holds when the - * transaction is completed. + * We take a reference to the buffer log item here so that the BLI life cycle + * extends at least until the buffer is unpinned via xfs_buf_item_unpin() and + * inserted into the AIL. + * + * We also need to take a reference to the buffer itself as the BLI unpin + * processing requires accessing the buffer after the BLI has dropped the final + * BLI reference. See xfs_buf_item_unpin() for an explanation. + * If unpins race to drop the final BLI reference and only the + * BLI owns a reference to the buffer, then the loser of the race can have the + * buffer fgreed from under it (e.g. on shutdown). Taking a buffer reference per + * pin count ensures the life cycle of the buffer extends for as + * long as we hold the buffer pin reference in xfs_buf_item_unpin(). */ STATIC void xfs_buf_item_pin( @@ -470,13 +478,30 @@ xfs_buf_item_pin( trace_xfs_buf_item_pin(bip); + xfs_buf_hold(bip->bli_buf); atomic_inc(&bip->bli_refcount); atomic_inc(&bip->bli_buf->b_pin_count); } /* - * This is called to unpin the buffer associated with the buf log item which - * was previously pinned with a call to xfs_buf_item_pin(). + * This is called to unpin the buffer associated with the buf log item which was + * previously pinned with a call to xfs_buf_item_pin(). We enter this function + * with a buffer pin count, a buffer reference and a BLI reference. + * + * We must drop the BLI reference before we unpin the buffer because the AIL + * doesn't acquire a BLI reference whenever it accesses it. Therefore if the + * refcount drops to zero, the bli could still be AIL resident and the buffer + * submitted for I/O at any point before we return. This can result in IO + * completion freeing the buffer while we are still trying to access it here. + * This race condition can also occur in shutdown situations where we abort and + * unpin buffers from contexts other that journal IO completion. + * + * Hence we have to hold a buffer reference per pin count to ensure that the + * buffer cannot be freed until we have finished processing the unpin operation. + * The reference is taken in xfs_buf_item_pin(), and we must hold it until we + * are done processing the buffer state. In the case of an abort (remove = + * true) then we re-use the current pin reference as the IO reference we hand + * off to IO failure handling. */ STATIC void xfs_buf_item_unpin( @@ -493,24 +518,18 @@ xfs_buf_item_unpin( trace_xfs_buf_item_unpin(bip); - /* - * Drop the bli ref associated with the pin and grab the hold required - * for the I/O simulation failure in the abort case. We have to do this - * before the pin count drops because the AIL doesn't acquire a bli - * reference. Therefore if the refcount drops to zero, the bli could - * still be AIL resident and the buffer submitted for I/O (and freed on - * completion) at any point before we return. This can be removed once - * the AIL properly holds a reference on the bli. - */ freed = atomic_dec_and_test(&bip->bli_refcount); - if (freed && !stale && remove) - xfs_buf_hold(bp); if (atomic_dec_and_test(&bp->b_pin_count)) wake_up_all(&bp->b_waiters); - /* nothing to do but drop the pin count if the bli is active */ - if (!freed) + /* + * Nothing to do but drop the buffer pin reference if the BLI is + * still active. + */ + if (!freed) { + xfs_buf_rele(bp); return; + } if (stale) { ASSERT(bip->bli_flags & XFS_BLI_STALE); @@ -523,6 +542,15 @@ xfs_buf_item_unpin( trace_xfs_buf_item_unpin_stale(bip); /* + * The buffer has been locked and referenced since it was marked + * stale so we own both lock and reference exclusively here. We + * do not need the pin reference any more, so drop it now so + * that we only have one reference to drop once item completion + * processing is complete. + */ + xfs_buf_rele(bp); + + /* * If we get called here because of an IO error, we may or may * not have the item on the AIL. xfs_trans_ail_delete() will * take care of that situation. xfs_trans_ail_delete() drops @@ -538,16 +566,30 @@ xfs_buf_item_unpin( ASSERT(bp->b_log_item == NULL); } xfs_buf_relse(bp); - } else if (remove) { + return; + } + + if (remove) { /* - * The buffer must be locked and held by the caller to simulate - * an async I/O failure. We acquired the hold for this case - * before the buffer was unpinned. + * We need to simulate an async IO failures here to ensure that + * the correct error completion is run on this buffer. This + * requires a reference to the buffer and for the buffer to be + * locked. We can safely pass ownership of the pin reference to + * the IO to ensure that nothing can free the buffer while we + * wait for the lock and then run the IO failure completion. */ xfs_buf_lock(bp); bp->b_flags |= XBF_ASYNC; xfs_buf_ioend_fail(bp); + return; } + + /* + * BLI has no more active references - it will be moved to the AIL to + * manage the remaining BLI/buffer life cycle. There is nothing left for + * us to do here so drop the pin reference to the buffer. + */ + xfs_buf_rele(bp); } STATIC uint diff --git a/fs/xfs/xfs_filestream.c b/fs/xfs/xfs_filestream.c index 22c13933c8f8..2fc98d313708 100644 --- a/fs/xfs/xfs_filestream.c +++ b/fs/xfs/xfs_filestream.c @@ -78,7 +78,6 @@ restart: *longest = 0; err = xfs_bmap_longest_free_extent(pag, NULL, longest); if (err) { - xfs_perag_rele(pag); if (err != -EAGAIN) break; /* Couldn't lock the AGF, skip this AG. */ diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 351849fc18ff..453890942d9f 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -435,18 +435,44 @@ xfs_iget_check_free_state( } /* Make all pending inactivation work start immediately. */ -static void +static bool xfs_inodegc_queue_all( struct xfs_mount *mp) { struct xfs_inodegc *gc; int cpu; + bool ret = false; for_each_online_cpu(cpu) { gc = per_cpu_ptr(mp->m_inodegc, cpu); - if (!llist_empty(&gc->list)) + if (!llist_empty(&gc->list)) { mod_delayed_work_on(cpu, mp->m_inodegc_wq, &gc->work, 0); + ret = true; + } + } + + return ret; +} + +/* Wait for all queued work and collect errors */ +static int +xfs_inodegc_wait_all( + struct xfs_mount *mp) +{ + int cpu; + int error = 0; + + flush_workqueue(mp->m_inodegc_wq); + for_each_online_cpu(cpu) { + struct xfs_inodegc *gc; + + gc = per_cpu_ptr(mp->m_inodegc, cpu); + if (gc->error && !error) + error = gc->error; + gc->error = 0; } + + return error; } /* @@ -1486,15 +1512,14 @@ xfs_blockgc_free_space( if (error) return error; - xfs_inodegc_flush(mp); - return 0; + return xfs_inodegc_flush(mp); } /* * Reclaim all the free space that we can by scheduling the background blockgc * and inodegc workers immediately and waiting for them all to clear. */ -void +int xfs_blockgc_flush_all( struct xfs_mount *mp) { @@ -1515,7 +1540,7 @@ xfs_blockgc_flush_all( for_each_perag_tag(mp, agno, pag, XFS_ICI_BLOCKGC_TAG) flush_delayed_work(&pag->pag_blockgc_work); - xfs_inodegc_flush(mp); + return xfs_inodegc_flush(mp); } /* @@ -1837,13 +1862,17 @@ xfs_inodegc_set_reclaimable( * This is the last chance to make changes to an otherwise unreferenced file * before incore reclamation happens. */ -static void +static int xfs_inodegc_inactivate( struct xfs_inode *ip) { + int error; + trace_xfs_inode_inactivating(ip); - xfs_inactive(ip); + error = xfs_inactive(ip); xfs_inodegc_set_reclaimable(ip); + return error; + } void @@ -1856,6 +1885,8 @@ xfs_inodegc_worker( struct xfs_inode *ip, *n; unsigned int nofs_flag; + ASSERT(gc->cpu == smp_processor_id()); + WRITE_ONCE(gc->items, 0); if (!node) @@ -1873,8 +1904,12 @@ xfs_inodegc_worker( WRITE_ONCE(gc->shrinker_hits, 0); llist_for_each_entry_safe(ip, n, node, i_gclist) { + int error; + xfs_iflags_set(ip, XFS_INACTIVATING); - xfs_inodegc_inactivate(ip); + error = xfs_inodegc_inactivate(ip); + if (error && !gc->error) + gc->error = error; } memalloc_nofs_restore(nofs_flag); @@ -1898,35 +1933,52 @@ xfs_inodegc_push( * Force all currently queued inode inactivation work to run immediately and * wait for the work to finish. */ -void +int xfs_inodegc_flush( struct xfs_mount *mp) { xfs_inodegc_push(mp); trace_xfs_inodegc_flush(mp, __return_address); - flush_workqueue(mp->m_inodegc_wq); + return xfs_inodegc_wait_all(mp); } /* * Flush all the pending work and then disable the inode inactivation background - * workers and wait for them to stop. + * workers and wait for them to stop. Caller must hold sb->s_umount to + * coordinate changes in the inodegc_enabled state. */ void xfs_inodegc_stop( struct xfs_mount *mp) { + bool rerun; + if (!xfs_clear_inodegc_enabled(mp)) return; + /* + * Drain all pending inodegc work, including inodes that could be + * queued by racing xfs_inodegc_queue or xfs_inodegc_shrinker_scan + * threads that sample the inodegc state just prior to us clearing it. + * The inodegc flag state prevents new threads from queuing more + * inodes, so we queue pending work items and flush the workqueue until + * all inodegc lists are empty. IOWs, we cannot use drain_workqueue + * here because it does not allow other unserialized mechanisms to + * reschedule inodegc work while this draining is in progress. + */ xfs_inodegc_queue_all(mp); - drain_workqueue(mp->m_inodegc_wq); + do { + flush_workqueue(mp->m_inodegc_wq); + rerun = xfs_inodegc_queue_all(mp); + } while (rerun); trace_xfs_inodegc_stop(mp, __return_address); } /* * Enable the inode inactivation background workers and schedule deferred inode - * inactivation work if there is any. + * inactivation work if there is any. Caller must hold sb->s_umount to + * coordinate changes in the inodegc_enabled state. */ void xfs_inodegc_start( @@ -2069,7 +2121,8 @@ xfs_inodegc_queue( queue_delay = 0; trace_xfs_inodegc_queue(mp, __return_address); - mod_delayed_work(mp->m_inodegc_wq, &gc->work, queue_delay); + mod_delayed_work_on(current_cpu(), mp->m_inodegc_wq, &gc->work, + queue_delay); put_cpu_ptr(gc); if (xfs_inodegc_want_flush_work(ip, items, shrinker_hits)) { @@ -2113,7 +2166,8 @@ xfs_inodegc_cpu_dead( if (xfs_is_inodegc_enabled(mp)) { trace_xfs_inodegc_queue(mp, __return_address); - mod_delayed_work(mp->m_inodegc_wq, &gc->work, 0); + mod_delayed_work_on(current_cpu(), mp->m_inodegc_wq, &gc->work, + 0); } put_cpu_ptr(gc); } diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h index 87910191a9dd..1dcdcb23796e 100644 --- a/fs/xfs/xfs_icache.h +++ b/fs/xfs/xfs_icache.h @@ -62,7 +62,7 @@ int xfs_blockgc_free_dquots(struct xfs_mount *mp, struct xfs_dquot *udqp, unsigned int iwalk_flags); int xfs_blockgc_free_quota(struct xfs_inode *ip, unsigned int iwalk_flags); int xfs_blockgc_free_space(struct xfs_mount *mp, struct xfs_icwalk *icm); -void xfs_blockgc_flush_all(struct xfs_mount *mp); +int xfs_blockgc_flush_all(struct xfs_mount *mp); void xfs_inode_set_eofblocks_tag(struct xfs_inode *ip); void xfs_inode_clear_eofblocks_tag(struct xfs_inode *ip); @@ -80,7 +80,7 @@ void xfs_blockgc_start(struct xfs_mount *mp); void xfs_inodegc_worker(struct work_struct *work); void xfs_inodegc_push(struct xfs_mount *mp); -void xfs_inodegc_flush(struct xfs_mount *mp); +int xfs_inodegc_flush(struct xfs_mount *mp); void xfs_inodegc_stop(struct xfs_mount *mp); void xfs_inodegc_start(struct xfs_mount *mp); void xfs_inodegc_cpu_dead(struct xfs_mount *mp, unsigned int cpu); diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 5808abab786c..9e62cc500140 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1620,16 +1620,7 @@ xfs_inactive_ifree( */ xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_ICOUNT, -1); - /* - * Just ignore errors at this point. There is nothing we can do except - * to try to keep going. Make sure it's not a silent error. - */ - error = xfs_trans_commit(tp); - if (error) - xfs_notice(mp, "%s: xfs_trans_commit returned error %d", - __func__, error); - - return 0; + return xfs_trans_commit(tp); } /* @@ -1693,12 +1684,12 @@ xfs_inode_needs_inactive( * now be truncated. Also, we clear all of the read-ahead state * kept for the inode here since the file is now closed. */ -void +int xfs_inactive( xfs_inode_t *ip) { struct xfs_mount *mp; - int error; + int error = 0; int truncate = 0; /* @@ -1736,7 +1727,7 @@ xfs_inactive( * reference to the inode at this point anyways. */ if (xfs_can_free_eofblocks(ip, true)) - xfs_free_eofblocks(ip); + error = xfs_free_eofblocks(ip); goto out; } @@ -1773,7 +1764,7 @@ xfs_inactive( /* * Free the inode. */ - xfs_inactive_ifree(ip); + error = xfs_inactive_ifree(ip); out: /* @@ -1781,6 +1772,7 @@ out: * the attached dquots. */ xfs_qm_dqdetach(ip); + return error; } /* diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 69d21e42c10a..7547caf2f2ab 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -470,7 +470,7 @@ enum layout_break_reason { (xfs_has_grpid((pip)->i_mount) || (VFS_I(pip)->i_mode & S_ISGID)) int xfs_release(struct xfs_inode *ip); -void xfs_inactive(struct xfs_inode *ip); +int xfs_inactive(struct xfs_inode *ip); int xfs_lookup(struct xfs_inode *dp, const struct xfs_name *name, struct xfs_inode **ipp, struct xfs_name *ci_name); int xfs_create(struct mnt_idmap *idmap, diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index ca2941ab6cbc..91c847a84e10 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -29,6 +29,153 @@ static inline struct xfs_inode_log_item *INODE_ITEM(struct xfs_log_item *lip) return container_of(lip, struct xfs_inode_log_item, ili_item); } +static uint64_t +xfs_inode_item_sort( + struct xfs_log_item *lip) +{ + return INODE_ITEM(lip)->ili_inode->i_ino; +} + +/* + * Prior to finally logging the inode, we have to ensure that all the + * per-modification inode state changes are applied. This includes VFS inode + * state updates, format conversions, verifier state synchronisation and + * ensuring the inode buffer remains in memory whilst the inode is dirty. + * + * We have to be careful when we grab the inode cluster buffer due to lock + * ordering constraints. The unlinked inode modifications (xfs_iunlink_item) + * require AGI -> inode cluster buffer lock order. The inode cluster buffer is + * not locked until ->precommit, so it happens after everything else has been + * modified. + * + * Further, we have AGI -> AGF lock ordering, and with O_TMPFILE handling we + * have AGI -> AGF -> iunlink item -> inode cluster buffer lock order. Hence we + * cannot safely lock the inode cluster buffer in xfs_trans_log_inode() because + * it can be called on a inode (e.g. via bumplink/droplink) before we take the + * AGF lock modifying directory blocks. + * + * Rather than force a complete rework of all the transactions to call + * xfs_trans_log_inode() once and once only at the end of every transaction, we + * move the pinning of the inode cluster buffer to a ->precommit operation. This + * matches how the xfs_iunlink_item locks the inode cluster buffer, and it + * ensures that the inode cluster buffer locking is always done last in a + * transaction. i.e. we ensure the lock order is always AGI -> AGF -> inode + * cluster buffer. + * + * If we return the inode number as the precommit sort key then we'll also + * guarantee that the order all inode cluster buffer locking is the same all the + * inodes and unlink items in the transaction. + */ +static int +xfs_inode_item_precommit( + struct xfs_trans *tp, + struct xfs_log_item *lip) +{ + struct xfs_inode_log_item *iip = INODE_ITEM(lip); + struct xfs_inode *ip = iip->ili_inode; + struct inode *inode = VFS_I(ip); + unsigned int flags = iip->ili_dirty_flags; + + /* + * Don't bother with i_lock for the I_DIRTY_TIME check here, as races + * don't matter - we either will need an extra transaction in 24 hours + * to log the timestamps, or will clear already cleared fields in the + * worst case. + */ + if (inode->i_state & I_DIRTY_TIME) { + spin_lock(&inode->i_lock); + inode->i_state &= ~I_DIRTY_TIME; + spin_unlock(&inode->i_lock); + } + + /* + * If we're updating the inode core or the timestamps and it's possible + * to upgrade this inode to bigtime format, do so now. + */ + if ((flags & (XFS_ILOG_CORE | XFS_ILOG_TIMESTAMP)) && + xfs_has_bigtime(ip->i_mount) && + !xfs_inode_has_bigtime(ip)) { + ip->i_diflags2 |= XFS_DIFLAG2_BIGTIME; + flags |= XFS_ILOG_CORE; + } + + /* + * Inode verifiers do not check that the extent size hint is an integer + * multiple of the rt extent size on a directory with both rtinherit + * and extszinherit flags set. If we're logging a directory that is + * misconfigured in this way, clear the hint. + */ + if ((ip->i_diflags & XFS_DIFLAG_RTINHERIT) && + (ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) && + (ip->i_extsize % ip->i_mount->m_sb.sb_rextsize) > 0) { + ip->i_diflags &= ~(XFS_DIFLAG_EXTSIZE | + XFS_DIFLAG_EXTSZINHERIT); + ip->i_extsize = 0; + flags |= XFS_ILOG_CORE; + } + + /* + * Record the specific change for fdatasync optimisation. This allows + * fdatasync to skip log forces for inodes that are only timestamp + * dirty. Once we've processed the XFS_ILOG_IVERSION flag, convert it + * to XFS_ILOG_CORE so that the actual on-disk dirty tracking + * (ili_fields) correctly tracks that the version has changed. + */ + spin_lock(&iip->ili_lock); + iip->ili_fsync_fields |= (flags & ~XFS_ILOG_IVERSION); + if (flags & XFS_ILOG_IVERSION) + flags = ((flags & ~XFS_ILOG_IVERSION) | XFS_ILOG_CORE); + + if (!iip->ili_item.li_buf) { + struct xfs_buf *bp; + int error; + + /* + * We hold the ILOCK here, so this inode is not going to be + * flushed while we are here. Further, because there is no + * buffer attached to the item, we know that there is no IO in + * progress, so nothing will clear the ili_fields while we read + * in the buffer. Hence we can safely drop the spin lock and + * read the buffer knowing that the state will not change from + * here. + */ + spin_unlock(&iip->ili_lock); + error = xfs_imap_to_bp(ip->i_mount, tp, &ip->i_imap, &bp); + if (error) + return error; + + /* + * We need an explicit buffer reference for the log item but + * don't want the buffer to remain attached to the transaction. + * Hold the buffer but release the transaction reference once + * we've attached the inode log item to the buffer log item + * list. + */ + xfs_buf_hold(bp); + spin_lock(&iip->ili_lock); + iip->ili_item.li_buf = bp; + bp->b_flags |= _XBF_INODES; + list_add_tail(&iip->ili_item.li_bio_list, &bp->b_li_list); + xfs_trans_brelse(tp, bp); + } + + /* + * Always OR in the bits from the ili_last_fields field. This is to + * coordinate with the xfs_iflush() and xfs_buf_inode_iodone() routines + * in the eventual clearing of the ili_fields bits. See the big comment + * in xfs_iflush() for an explanation of this coordination mechanism. + */ + iip->ili_fields |= (flags | iip->ili_last_fields); + spin_unlock(&iip->ili_lock); + + /* + * We are done with the log item transaction dirty state, so clear it so + * that it doesn't pollute future transactions. + */ + iip->ili_dirty_flags = 0; + return 0; +} + /* * The logged size of an inode fork is always the current size of the inode * fork. This means that when an inode fork is relogged, the size of the logged @@ -662,6 +809,8 @@ xfs_inode_item_committing( } static const struct xfs_item_ops xfs_inode_item_ops = { + .iop_sort = xfs_inode_item_sort, + .iop_precommit = xfs_inode_item_precommit, .iop_size = xfs_inode_item_size, .iop_format = xfs_inode_item_format, .iop_pin = xfs_inode_item_pin, diff --git a/fs/xfs/xfs_inode_item.h b/fs/xfs/xfs_inode_item.h index bbd836a44ff0..377e06007804 100644 --- a/fs/xfs/xfs_inode_item.h +++ b/fs/xfs/xfs_inode_item.h @@ -17,6 +17,7 @@ struct xfs_inode_log_item { struct xfs_log_item ili_item; /* common portion */ struct xfs_inode *ili_inode; /* inode ptr */ unsigned short ili_lock_flags; /* inode lock flags */ + unsigned int ili_dirty_flags; /* dirty in current tx */ /* * The ili_lock protects the interactions between the dirty state and * the flush state of the inode log item. This allows us to do atomic diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 285885c308bd..18c8f168b153 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1006,8 +1006,9 @@ xfs_buffered_write_iomap_begin( if (eof) imap.br_startoff = end_fsb; /* fake hole until the end */ - /* We never need to allocate blocks for zeroing a hole. */ - if ((flags & IOMAP_ZERO) && imap.br_startoff > offset_fsb) { + /* We never need to allocate blocks for zeroing or unsharing a hole. */ + if ((flags & (IOMAP_UNSHARE | IOMAP_ZERO)) && + imap.br_startoff > offset_fsb) { xfs_hole_to_iomap(ip, iomap, offset_fsb, imap.br_startoff); goto out_unlock; } diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 322eb2ee6c55..82c81d20459d 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -2711,7 +2711,9 @@ xlog_recover_iunlink_bucket( * just to flush the inodegc queue and wait for it to * complete. */ - xfs_inodegc_flush(mp); + error = xfs_inodegc_flush(mp); + if (error) + break; } prev_agino = agino; @@ -2719,10 +2721,15 @@ xlog_recover_iunlink_bucket( } if (prev_ip) { + int error2; + ip->i_prev_unlinked = prev_agino; xfs_irele(prev_ip); + + error2 = xfs_inodegc_flush(mp); + if (error2 && !error) + return error2; } - xfs_inodegc_flush(mp); return error; } @@ -2789,7 +2796,6 @@ xlog_recover_iunlink_ag( * bucket and remaining inodes on it unreferenced and * unfreeable. */ - xfs_inodegc_flush(pag->pag_mount); xlog_recover_clear_agi_bucket(pag, bucket); } } @@ -2806,13 +2812,6 @@ xlog_recover_process_iunlinks( for_each_perag(log->l_mp, agno, pag) xlog_recover_iunlink_ag(pag); - - /* - * Flush the pending unlinked inodes to ensure that the inactivations - * are fully completed on disk and the incore inodes can be reclaimed - * before we signal that recovery is complete. - */ - xfs_inodegc_flush(log->l_mp); } STATIC void diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index f3269c0626f0..6c09f89534d3 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -62,10 +62,14 @@ struct xfs_error_cfg { struct xfs_inodegc { struct llist_head list; struct delayed_work work; + int error; /* approximate count of inodes in the list */ unsigned int items; unsigned int shrinker_hits; +#if defined(DEBUG) || defined(XFS_WARN) + unsigned int cpu; +#endif }; /* diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index f5dc46ce9803..abcc559f3c64 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -616,8 +616,10 @@ xfs_reflink_cancel_cow_blocks( xfs_refcount_free_cow_extent(*tpp, del.br_startblock, del.br_blockcount); - xfs_free_extent_later(*tpp, del.br_startblock, + error = xfs_free_extent_later(*tpp, del.br_startblock, del.br_blockcount, NULL); + if (error) + break; /* Roll the transaction */ error = xfs_defer_finish(tpp); diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 4d2e87462ac4..4120bd1cba90 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1095,8 +1095,12 @@ xfs_inodegc_init_percpu( for_each_possible_cpu(cpu) { gc = per_cpu_ptr(mp->m_inodegc, cpu); +#if defined(DEBUG) || defined(XFS_WARN) + gc->cpu = cpu; +#endif init_llist_head(&gc->list); gc->items = 0; + gc->error = 0; INIT_DELAYED_WORK(&gc->work, xfs_inodegc_worker); } return 0; diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index 8afc0c080861..8c0bfc9a33b1 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -290,7 +290,9 @@ retry: * Do not perform a synchronous scan because callers can hold * other locks. */ - xfs_blockgc_flush_all(mp); + error = xfs_blockgc_flush_all(mp); + if (error) + return error; want_retry = false; goto retry; } @@ -970,6 +972,11 @@ __xfs_trans_commit( error = xfs_defer_finish_noroll(&tp); if (error) goto out_unreserve; + + /* Run precommits from final tx in defer chain. */ + error = xfs_trans_run_precommits(tp); + if (error) + goto out_unreserve; } /* diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index d1f57e4868ed..cebdf1ca415d 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -891,9 +891,16 @@ /* * Discard .note.GNU-stack, which is emitted as PROGBITS by the compiler. * Otherwise, the type of .notes section would become PROGBITS instead of NOTES. + * + * Also, discard .note.gnu.property, otherwise it forces the notes section to + * be 8-byte aligned which causes alignment mismatches with the kernel's custom + * 4-byte aligned notes. */ #define NOTES \ - /DISCARD/ : { *(.note.GNU-stack) } \ + /DISCARD/ : { \ + *(.note.GNU-stack) \ + *(.note.gnu.property) \ + } \ .notes : AT(ADDR(.notes) - LOAD_OFFSET) { \ BOUNDED_SECTION_BY(.note.*, _notes) \ } NOTES_HEADERS \ diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h index 7e76623f9ec3..34224e77f5a2 100644 --- a/include/crypto/if_alg.h +++ b/include/crypto/if_alg.h @@ -56,9 +56,9 @@ struct af_alg_type { }; struct af_alg_sgl { - struct scatterlist sg[ALG_MAX_PAGES + 1]; - struct page *pages[ALG_MAX_PAGES]; - unsigned int npages; + struct sg_table sgt; + struct scatterlist sgl[ALG_MAX_PAGES + 1]; + bool need_unpin; }; /* TX SGL entry */ @@ -163,7 +163,6 @@ int af_alg_release(struct socket *sock); void af_alg_release_parent(struct sock *sk); int af_alg_accept(struct sock *sk, struct socket *newsock, bool kern); -int af_alg_make_sg(struct af_alg_sgl *sgl, struct iov_iter *iter, int len); void af_alg_free_sg(struct af_alg_sgl *sgl); static inline struct alg_sock *alg_sk(struct sock *sk) diff --git a/include/drm/display/drm_dp.h b/include/drm/display/drm_dp.h index 358db4a9f167..f8813c1e059b 100644 --- a/include/drm/display/drm_dp.h +++ b/include/drm/display/drm_dp.h @@ -286,9 +286,8 @@ #define DP_DSC_MAX_BITS_PER_PIXEL_HI 0x068 /* eDP 1.4 */ # define DP_DSC_MAX_BITS_PER_PIXEL_HI_MASK (0x3 << 0) -# define DP_DSC_MAX_BITS_PER_PIXEL_HI_SHIFT 8 -# define DP_DSC_MAX_BPP_DELTA_VERSION_MASK 0x06 -# define DP_DSC_MAX_BPP_DELTA_AVAILABILITY 0x08 +# define DP_DSC_MAX_BPP_DELTA_VERSION_MASK (0x3 << 5) /* eDP 1.5 & DP 2.0 */ +# define DP_DSC_MAX_BPP_DELTA_AVAILABILITY (1 << 7) /* eDP 1.5 & DP 2.0 */ #define DP_DSC_DEC_COLOR_FORMAT_CAP 0x069 # define DP_DSC_RGB (1 << 0) diff --git a/include/drm/display/drm_dp_helper.h b/include/drm/display/drm_dp_helper.h index 533d3ee7fe05..86f24a759268 100644 --- a/include/drm/display/drm_dp_helper.h +++ b/include/drm/display/drm_dp_helper.h @@ -181,9 +181,8 @@ static inline u16 drm_edp_dsc_sink_output_bpp(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE]) { return dsc_dpcd[DP_DSC_MAX_BITS_PER_PIXEL_LOW - DP_DSC_SUPPORT] | - (dsc_dpcd[DP_DSC_MAX_BITS_PER_PIXEL_HI - DP_DSC_SUPPORT] & - DP_DSC_MAX_BITS_PER_PIXEL_HI_MASK << - DP_DSC_MAX_BITS_PER_PIXEL_HI_SHIFT); + ((dsc_dpcd[DP_DSC_MAX_BITS_PER_PIXEL_HI - DP_DSC_SUPPORT] & + DP_DSC_MAX_BITS_PER_PIXEL_HI_MASK) << 8); } static inline u32 diff --git a/include/drm/drm_managed.h b/include/drm/drm_managed.h index 359883942612..ad08f834af40 100644 --- a/include/drm/drm_managed.h +++ b/include/drm/drm_managed.h @@ -105,6 +105,22 @@ char *drmm_kstrdup(struct drm_device *dev, const char *s, gfp_t gfp); void drmm_kfree(struct drm_device *dev, void *data); -int drmm_mutex_init(struct drm_device *dev, struct mutex *lock); +void __drmm_mutex_release(struct drm_device *dev, void *res); + +/** + * drmm_mutex_init - &drm_device-managed mutex_init() + * @dev: DRM device + * @lock: lock to be initialized + * + * Returns: + * 0 on success, or a negative errno code otherwise. + * + * This is a &drm_device-managed version of mutex_init(). The initialized + * lock is automatically destroyed on the final drm_dev_put(). + */ +#define drmm_mutex_init(dev, lock) ({ \ + mutex_init(lock); \ + drmm_add_action_or_reset(dev, __drmm_mutex_release, lock); \ +}) \ #endif diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index c87aeecaa9b2..583fe3b49a49 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -96,6 +96,7 @@ /* FFA Bus/Device/Driver related */ struct ffa_device { + u32 id; int vm_id; bool mode_32bit; uuid_t uuid; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index b441e633f4dd..c0ffe203a602 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1376,8 +1376,6 @@ enum blk_unique_id { BLK_UID_NAA = 3, }; -#define NFL4_UFLG_MASK 0x0000003F - struct block_device_operations { void (*submit_bio)(struct bio *bio); int (*poll_bio)(struct bio *bio, struct io_comp_batch *iob, diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e53ceee1df37..f58895830ada 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1125,7 +1125,6 @@ struct bpf_trampoline { int progs_cnt[BPF_TRAMP_MAX]; /* Executable image of trampoline */ struct bpf_tramp_image *cur_image; - u64 selector; struct module *mod; }; @@ -1197,7 +1196,7 @@ enum bpf_dynptr_type { }; int bpf_dynptr_check_size(u32 size); -u32 bpf_dynptr_get_size(const struct bpf_dynptr_kern *ptr); +u32 __bpf_dynptr_size(const struct bpf_dynptr_kern *ptr); #ifdef CONFIG_BPF_JIT int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); @@ -2078,8 +2077,8 @@ struct file *bpf_link_new_file(struct bpf_link *link, int *reserved_fd); struct bpf_link *bpf_link_get_from_fd(u32 ufd); struct bpf_link *bpf_link_get_curr_or_next(u32 *id); -int bpf_obj_pin_user(u32 ufd, const char __user *pathname); -int bpf_obj_get_user(const char __user *pathname, int flags); +int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname); +int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags); #define BPF_ITER_FUNC_PREFIX "bpf_iter_" #define DEFINE_BPF_ITER_FUNC(target, args...) \ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 3dd29a53b711..5b11a3b0fec0 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -18,8 +18,11 @@ * that converting umax_value to int cannot overflow. */ #define BPF_MAX_VAR_SIZ (1 << 29) -/* size of type_str_buf in bpf_verifier. */ -#define TYPE_STR_BUF_LEN 128 +/* size of tmp_str_buf in bpf_verifier. + * we need at least 306 bytes to fit full stack mask representation + * (in the "-8,-16,...,-512" form) + */ +#define TMP_STR_BUF_LEN 320 /* Liveness marks, used for registers and spilled-regs (in stack slots). * Read marks propagate upwards until they find a write mark; they record that @@ -238,6 +241,10 @@ enum bpf_stack_slot_type { #define BPF_REG_SIZE 8 /* size of eBPF register in bytes */ +#define BPF_REGMASK_ARGS ((1 << BPF_REG_1) | (1 << BPF_REG_2) | \ + (1 << BPF_REG_3) | (1 << BPF_REG_4) | \ + (1 << BPF_REG_5)) + #define BPF_DYNPTR_SIZE sizeof(struct bpf_dynptr_kern) #define BPF_DYNPTR_NR_SLOTS (BPF_DYNPTR_SIZE / BPF_REG_SIZE) @@ -541,6 +548,15 @@ struct bpf_subprog_info { bool is_async_cb; }; +struct bpf_verifier_env; + +struct backtrack_state { + struct bpf_verifier_env *env; + u32 frame; + u32 reg_masks[MAX_CALL_FRAMES]; + u64 stack_masks[MAX_CALL_FRAMES]; +}; + /* single container for all structs * one verifier_env per bpf_check() call */ @@ -578,6 +594,7 @@ struct bpf_verifier_env { int *insn_stack; int cur_stack; } cfg; + struct backtrack_state bt; u32 pass_cnt; /* number of times do_check() was called */ u32 subprog_cnt; /* number of instructions analyzed by the verifier */ @@ -606,8 +623,10 @@ struct bpf_verifier_env { /* Same as scratched_regs but for stack slots */ u64 scratched_stack_slots; u64 prev_log_pos, prev_insn_print_pos; - /* buffer used in reg_type_str() to generate reg_type string */ - char type_str_buf[TYPE_STR_BUF_LEN]; + /* buffer used to generate temporary string representations, + * e.g., in reg_type_str() to generate reg_type string + */ + char tmp_str_buf[TMP_STR_BUF_LEN]; }; __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index e9afbfb6d7a5..5d732f48f787 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -161,6 +161,7 @@ #define BCM_LED_SRC_OPENSHORT 0xb #define BCM_LED_SRC_OFF 0xe /* Tied high */ #define BCM_LED_SRC_ON 0xf /* Tied low */ +#define BCM_LED_SRC_MASK GENMASK(3, 0) /* * Broadcom Multicolor LED configurations (expansion register 4) @@ -206,11 +207,13 @@ #define BCM_NO_ANEG_APD_EN 0x0060 /* bits 5 & 6 */ #define BCM_APD_SINGLELP_EN 0x0100 /* Bit 8 */ -#define BCM5482_SHD_LEDS1 0x0d /* 01101: LED Selector 1 */ +#define BCM54XX_SHD_LEDS1 0x0d /* 01101: LED Selector 1 */ /* LED3 / ~LINKSPD[2] selector */ -#define BCM5482_SHD_LEDS1_LED3(src) ((src & 0xf) << 4) +#define BCM54XX_SHD_LEDS_SHIFT(led) (4 * (led)) +#define BCM54XX_SHD_LEDS1_LED3(src) ((src & 0xf) << 4) /* LED1 / ~LINKSPD[1] selector */ -#define BCM5482_SHD_LEDS1_LED1(src) ((src & 0xf) << 0) +#define BCM54XX_SHD_LEDS1_LED1(src) ((src & 0xf) << 0) +#define BCM54XX_SHD_LEDS2 0x0e /* 01110: LED Selector 2 */ #define BCM54XX_SHD_RGMII_MODE 0x0b /* 01011: RGMII Mode Selector */ #define BCM5482_SHD_SSD 0x14 /* 10100: Secondary SerDes control */ #define BCM5482_SHD_SSD_LEDM 0x0008 /* SSD LED Mode enable */ @@ -359,6 +362,8 @@ #define LPI_FEATURE_EN 0x8000 #define LPI_FEATURE_EN_DIG1000X 0x4000 +#define BRCM_CL45VEN_EEE_LPI_CNT 0x803f + /* Core register definitions*/ #define MII_BRCM_CORE_BASE12 0x12 #define MII_BRCM_CORE_BASE13 0x13 diff --git a/include/linux/btf.h b/include/linux/btf.h index 508199e38415..cac9f304e27a 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -98,10 +98,14 @@ struct btf_type; union bpf_attr; struct btf_show; struct btf_id_set; +struct bpf_prog; + +typedef int (*btf_kfunc_filter_t)(const struct bpf_prog *prog, u32 kfunc_id); struct btf_kfunc_id_set { struct module *owner; struct btf_id_set8 *set; + btf_kfunc_filter_t filter; }; struct btf_id_dtor_kfunc { @@ -479,7 +483,6 @@ static inline void *btf_id_set8_contains(const struct btf_id_set8 *set, u32 id) return bsearch(&id, set->pairs, set->cnt, sizeof(set->pairs[0]), btf_id_cmp_func); } -struct bpf_prog; struct bpf_verifier_log; #ifdef CONFIG_BPF_SYSCALL @@ -487,10 +490,10 @@ const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); const char *btf_name_by_offset(const struct btf *btf, u32 offset); struct btf *btf_parse_vmlinux(void); struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog); -u32 *btf_kfunc_id_set_contains(const struct btf *btf, - enum bpf_prog_type prog_type, - u32 kfunc_btf_id); -u32 *btf_kfunc_is_modify_return(const struct btf *btf, u32 kfunc_btf_id); +u32 *btf_kfunc_id_set_contains(const struct btf *btf, u32 kfunc_btf_id, + const struct bpf_prog *prog); +u32 *btf_kfunc_is_modify_return(const struct btf *btf, u32 kfunc_btf_id, + const struct bpf_prog *prog); int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, const struct btf_kfunc_id_set *s); int register_btf_fmodret_id_set(const struct btf_kfunc_id_set *kset); @@ -517,8 +520,9 @@ static inline const char *btf_name_by_offset(const struct btf *btf, return NULL; } static inline u32 *btf_kfunc_id_set_contains(const struct btf *btf, - enum bpf_prog_type prog_type, - u32 kfunc_btf_id) + u32 kfunc_btf_id, + struct bpf_prog *prog) + { return NULL; } diff --git a/include/linux/can/length.h b/include/linux/can/length.h index 6995092b774e..69336549d24f 100644 --- a/include/linux/can/length.h +++ b/include/linux/can/length.h @@ -6,6 +6,9 @@ #ifndef _CAN_LENGTH_H #define _CAN_LENGTH_H +#include <linux/can.h> +#include <linux/can/netlink.h> + /* * Size of a Classical CAN Standard Frame * diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 947a60b801db..d7779a18b24f 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -12,11 +12,10 @@ * Note: DISABLE_BRANCH_PROFILING can be used by special lowlevel code * to disable branch tracing on a per file basis. */ -#if defined(CONFIG_TRACE_BRANCH_PROFILING) \ - && !defined(DISABLE_BRANCH_PROFILING) && !defined(__CHECKER__) void ftrace_likely_update(struct ftrace_likely_data *f, int val, int expect, int is_constant); - +#if defined(CONFIG_TRACE_BRANCH_PROFILING) \ + && !defined(DISABLE_BRANCH_PROFILING) && !defined(__CHECKER__) #define likely_notrace(x) __builtin_expect(!!(x), 1) #define unlikely_notrace(x) __builtin_expect(!!(x), 0) diff --git a/include/linux/cper.h b/include/linux/cper.h index eacb7dd7b3af..c1a7dc325121 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -572,4 +572,10 @@ void cper_print_proc_ia(const char *pfx, int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg); int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg); +struct acpi_hest_generic_status; +void cper_estatus_print(const char *pfx, + const struct acpi_hest_generic_status *estatus); +int cper_estatus_check_header(const struct acpi_hest_generic_status *estatus); +int cper_estatus_check(const struct acpi_hest_generic_status *estatus); + #endif diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 9deeaeb457bb..abf3d3bfb6fe 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -74,6 +74,7 @@ struct class { struct class_dev_iter { struct klist_iter ki; const struct device_type *type; + struct subsys_private *sp; }; int __must_check class_register(const struct class *class); diff --git a/include/linux/efi.h b/include/linux/efi.h index 7aa62c92185f..571d1a6e1b74 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1338,4 +1338,6 @@ bool efi_config_table_is_usable(const efi_guid_t *guid, unsigned long table) return xen_efi_config_table_is_usable(guid, table); } +umode_t efi_attr_is_visible(struct kobject *kobj, struct attribute *attr, int n); + #endif /* _LINUX_EFI_H */ diff --git a/include/linux/firewire.h b/include/linux/firewire.h index 1716c01c4e54..efb6e2cf2034 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -391,7 +391,7 @@ struct fw_iso_packet { u32 tag:2; /* tx: Tag in packet header */ u32 sy:4; /* tx: Sy in packet header */ u32 header_length:8; /* Length of immediate header */ - u32 header[0]; /* tx: Top of 1394 isoch. data_block */ + u32 header[]; /* tx: Top of 1394 isoch. data_block */ }; #define FW_ISO_CONTEXT_TRANSMIT 0 diff --git a/include/linux/fs.h b/include/linux/fs.h index 21a981680856..de2cb1132f07 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1076,29 +1076,29 @@ extern int send_sigurg(struct fown_struct *fown); * sb->s_flags. Note that these mirror the equivalent MS_* flags where * represented in both. */ -#define SB_RDONLY 1 /* Mount read-only */ -#define SB_NOSUID 2 /* Ignore suid and sgid bits */ -#define SB_NODEV 4 /* Disallow access to device special files */ -#define SB_NOEXEC 8 /* Disallow program execution */ -#define SB_SYNCHRONOUS 16 /* Writes are synced at once */ -#define SB_MANDLOCK 64 /* Allow mandatory locks on an FS */ -#define SB_DIRSYNC 128 /* Directory modifications are synchronous */ -#define SB_NOATIME 1024 /* Do not update access times. */ -#define SB_NODIRATIME 2048 /* Do not update directory access times */ -#define SB_SILENT 32768 -#define SB_POSIXACL (1<<16) /* VFS does not apply the umask */ -#define SB_INLINECRYPT (1<<17) /* Use blk-crypto for encrypted files */ -#define SB_KERNMOUNT (1<<22) /* this is a kern_mount call */ -#define SB_I_VERSION (1<<23) /* Update inode I_version field */ -#define SB_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */ +#define SB_RDONLY BIT(0) /* Mount read-only */ +#define SB_NOSUID BIT(1) /* Ignore suid and sgid bits */ +#define SB_NODEV BIT(2) /* Disallow access to device special files */ +#define SB_NOEXEC BIT(3) /* Disallow program execution */ +#define SB_SYNCHRONOUS BIT(4) /* Writes are synced at once */ +#define SB_MANDLOCK BIT(6) /* Allow mandatory locks on an FS */ +#define SB_DIRSYNC BIT(7) /* Directory modifications are synchronous */ +#define SB_NOATIME BIT(10) /* Do not update access times. */ +#define SB_NODIRATIME BIT(11) /* Do not update directory access times */ +#define SB_SILENT BIT(15) +#define SB_POSIXACL BIT(16) /* VFS does not apply the umask */ +#define SB_INLINECRYPT BIT(17) /* Use blk-crypto for encrypted files */ +#define SB_KERNMOUNT BIT(22) /* this is a kern_mount call */ +#define SB_I_VERSION BIT(23) /* Update inode I_version field */ +#define SB_LAZYTIME BIT(25) /* Update the on-disk [acm]times lazily */ /* These sb flags are internal to the kernel */ -#define SB_SUBMOUNT (1<<26) -#define SB_FORCE (1<<27) -#define SB_NOSEC (1<<28) -#define SB_BORN (1<<29) -#define SB_ACTIVE (1<<30) -#define SB_NOUSER (1<<31) +#define SB_SUBMOUNT BIT(26) +#define SB_FORCE BIT(27) +#define SB_NOSEC BIT(28) +#define SB_BORN BIT(29) +#define SB_ACTIVE BIT(30) +#define SB_NOUSER BIT(31) /* These flags relate to encoding and casefolding */ #define SB_ENC_STRICT_MODE_FL (1 << 0) @@ -1796,6 +1796,7 @@ struct file_operations { int (*flock) (struct file *, int, struct file_lock *); ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); + void (*splice_eof)(struct file *file); int (*setlease)(struct file *, long, struct file_lock **, void **); long (*fallocate)(struct file *file, int mode, loff_t offset, loff_t len); @@ -2759,8 +2760,6 @@ extern ssize_t generic_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); extern ssize_t iter_file_splice_write(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); -extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, - struct file *out, loff_t *, size_t len, unsigned int flags); extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, loff_t *opos, size_t len, unsigned int flags); diff --git a/include/linux/if_team.h b/include/linux/if_team.h index fc985e5c739d..8de6b6e67829 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -208,6 +208,7 @@ struct team { bool queue_override_enabled; struct list_head *qom_lists; /* array of queue override mapping lists */ bool port_mtu_change_allowed; + bool notifier_ctx; struct { unsigned int count; unsigned int interval; /* in ms */ diff --git a/include/linux/iio/iio-gts-helper.h b/include/linux/iio/iio-gts-helper.h index dd64e544a3da..9cb6c80dea71 100644 --- a/include/linux/iio/iio-gts-helper.h +++ b/include/linux/iio/iio-gts-helper.h @@ -135,7 +135,7 @@ static inline int iio_gts_find_int_time_by_sel(struct iio_gts *gts, int sel) /** * iio_gts_find_sel_by_int_time - find selector matching integration time * @gts: Gain time scale descriptor - * @gain: HW-gain for which matching selector is searched for + * @time: Integration time for which matching selector is searched for * * Return: a selector matching given integration time or -EINVAL if * selector was not found. diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 3399d979ee1c..7fe31b2cd02f 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -36,6 +36,11 @@ struct io_uring_cmd { u8 pdu[32]; /* available inline for free use */ }; +static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe) +{ + return sqe->cmd; +} + #if defined(CONFIG_IO_URING) int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, struct iov_iter *iter, void *ioucmd); @@ -66,11 +71,6 @@ static inline void io_uring_free(struct task_struct *tsk) if (tsk->io_uring) __io_uring_free(tsk); } - -static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe) -{ - return sqe->cmd; -} #else static inline int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, struct iov_iter *iter, void *ioucmd) diff --git a/include/linux/leds.h b/include/linux/leds.h index c39bbf17a25b..8af62ff431f0 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -183,6 +183,49 @@ struct led_classdev { /* LEDs that have private triggers have this set */ struct led_hw_trigger_type *trigger_type; + + /* Unique trigger name supported by LED set in hw control mode */ + const char *hw_control_trigger; + /* + * Check if the LED driver supports the requested mode provided by the + * defined supported trigger to setup the LED to hw control mode. + * + * Return 0 on success. Return -EOPNOTSUPP when the passed flags are not + * supported and software fallback needs to be used. + * Return a negative error number on any other case for check fail due + * to various reason like device not ready or timeouts. + */ + int (*hw_control_is_supported)(struct led_classdev *led_cdev, + unsigned long flags); + /* + * Activate hardware control, LED driver will use the provided flags + * from the supported trigger and setup the LED to be driven by hardware + * following the requested mode from the trigger flags. + * Deactivate hardware blink control by setting brightness to LED_OFF via + * the brightness_set() callback. + * + * Return 0 on success, a negative error number on flags apply fail. + */ + int (*hw_control_set)(struct led_classdev *led_cdev, + unsigned long flags); + /* + * Get from the LED driver the current mode that the LED is set in hw + * control mode and put them in flags. + * Trigger can use this to get the initial state of a LED already set in + * hardware blink control. + * + * Return 0 on success, a negative error number on failing parsing the + * initial mode. Error from this function is NOT FATAL as the device + * may be in a not supported initial state by the attached LED trigger. + */ + int (*hw_control_get)(struct led_classdev *led_cdev, + unsigned long *flags); + /* + * Get the device this LED blinks in response to. + * e.g. for a PHY LED, it is the network device. If the LED is + * not yet associated to a device, return NULL. + */ + struct device *(*hw_control_get_device)(struct led_classdev *led_cdev); #endif #ifdef CONFIG_LEDS_BRIGHTNESS_HW_CHANGED @@ -509,6 +552,16 @@ static inline void *led_get_trigger_data(struct led_classdev *led_cdev) #endif /* CONFIG_LEDS_TRIGGERS */ +/* Trigger specific enum */ +enum led_trigger_netdev_modes { + TRIGGER_NETDEV_LINK = 0, + TRIGGER_NETDEV_TX, + TRIGGER_NETDEV_RX, + + /* Keep last */ + __TRIGGER_NETDEV_MAX, +}; + /* Trigger specific functions */ #ifdef CONFIG_LEDS_TRIGGER_DISK void ledtrig_disk_activity(bool write); diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index b32256e9e944..74bd269a80a2 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -344,6 +344,16 @@ extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie); #define lockdep_repin_lock(l,c) lock_repin_lock(&(l)->dep_map, (c)) #define lockdep_unpin_lock(l,c) lock_unpin_lock(&(l)->dep_map, (c)) +/* + * Must use lock_map_aquire_try() with override maps to avoid + * lockdep thinking they participate in the block chain. + */ +#define DEFINE_WAIT_OVERRIDE_MAP(_name, _wait_type) \ + struct lockdep_map _name = { \ + .name = #_name "-wait-type-override", \ + .wait_type_inner = _wait_type, \ + .lock_type = LD_LOCK_WAIT_OVERRIDE, } + #else /* !CONFIG_LOCKDEP */ static inline void lockdep_init_task(struct task_struct *task) @@ -432,6 +442,9 @@ extern int lockdep_is_held(const void *); #define lockdep_repin_lock(l, c) do { (void)(l); (void)(c); } while (0) #define lockdep_unpin_lock(l, c) do { (void)(l); (void)(c); } while (0) +#define DEFINE_WAIT_OVERRIDE_MAP(_name, _wait_type) \ + struct lockdep_map __maybe_unused _name = {} + #endif /* !LOCKDEP */ enum xhlock_context_t { @@ -556,6 +569,7 @@ do { \ #define rwsem_release(l, i) lock_release(l, i) #define lock_map_acquire(l) lock_acquire_exclusive(l, 0, 0, NULL, _THIS_IP_) +#define lock_map_acquire_try(l) lock_acquire_exclusive(l, 0, 1, NULL, _THIS_IP_) #define lock_map_acquire_read(l) lock_acquire_shared_recursive(l, 0, 0, NULL, _THIS_IP_) #define lock_map_acquire_tryread(l) lock_acquire_shared_recursive(l, 0, 1, NULL, _THIS_IP_) #define lock_map_release(l) lock_release(l, _THIS_IP_) diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h index d22430840b53..59f4fb1626ea 100644 --- a/include/linux/lockdep_types.h +++ b/include/linux/lockdep_types.h @@ -33,6 +33,7 @@ enum lockdep_wait_type { enum lockdep_lock_type { LD_LOCK_NORMAL = 0, /* normal, catch all */ LD_LOCK_PERCPU, /* percpu */ + LD_LOCK_WAIT_OVERRIDE, /* annotation */ LD_LOCK_MAX, }; diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 27013d6bf24a..c1b7008826e5 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -106,6 +106,16 @@ int mdio_driver_register(struct mdio_driver *drv); void mdio_driver_unregister(struct mdio_driver *drv); int mdio_device_bus_match(struct device *dev, struct device_driver *drv); +static inline void mdio_device_get(struct mdio_device *mdiodev) +{ + get_device(&mdiodev->dev); +} + +static inline void mdio_device_put(struct mdio_device *mdiodev) +{ + mdio_device_free(mdiodev); +} + static inline bool mdio_phy_id_is_c45(int phy_id) { return (phy_id & MDIO_PHY_ID_C45) && !(phy_id & ~MDIO_PHY_ID_C45_MASK); @@ -486,6 +496,45 @@ static inline u32 linkmode_adv_to_mii_10base_t1_t(unsigned long *adv) return result; } +/** + * mii_c73_mod_linkmode - convert a Clause 73 advertisement to linkmodes + * @adv: linkmode advertisement setting + * @lpa: array of three u16s containing the advertisement + * + * Convert an IEEE 802.3 Clause 73 advertisement to ethtool link modes. + */ +static inline void mii_c73_mod_linkmode(unsigned long *adv, u16 *lpa) +{ + linkmode_mod_bit(ETHTOOL_LINK_MODE_Pause_BIT, + adv, lpa[0] & MDIO_AN_C73_0_PAUSE); + linkmode_mod_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, + adv, lpa[0] & MDIO_AN_C73_0_ASM_DIR); + linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, + adv, lpa[1] & MDIO_AN_C73_1_1000BASE_KX); + linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, + adv, lpa[1] & MDIO_AN_C73_1_10GBASE_KX4); + linkmode_mod_bit(ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT, + adv, lpa[1] & MDIO_AN_C73_1_40GBASE_KR4); + linkmode_mod_bit(ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT, + adv, lpa[1] & MDIO_AN_C73_1_40GBASE_CR4); + /* 100GBASE_CR10 and 100GBASE_KP4 not implemented */ + linkmode_mod_bit(ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, + adv, lpa[1] & MDIO_AN_C73_1_100GBASE_KR4); + linkmode_mod_bit(ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, + adv, lpa[1] & MDIO_AN_C73_1_100GBASE_CR4); + /* 25GBASE_R_S not implemented */ + /* The 25GBASE_R bit can be used for 25Gbase KR or CR modes */ + linkmode_mod_bit(ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, + adv, lpa[1] & MDIO_AN_C73_1_25GBASE_R); + linkmode_mod_bit(ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, + adv, lpa[1] & MDIO_AN_C73_1_25GBASE_R); + linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseKR_Full_BIT, + adv, lpa[1] & MDIO_AN_C73_1_10GBASE_KR); + linkmode_mod_bit(ETHTOOL_LINK_MODE_2500baseX_Full_BIT, + adv, lpa[2] & MDIO_AN_C73_2_2500BASE_KX); + /* 5GBASE_KR not implemented */ +} + int __mdiobus_read(struct mii_bus *bus, int addr, u32 regnum); int __mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val); int __mdiobus_modify_changed(struct mii_bus *bus, int addr, u32 regnum, diff --git a/include/linux/mdio/mdio-regmap.h b/include/linux/mdio/mdio-regmap.h new file mode 100644 index 000000000000..679d9069846b --- /dev/null +++ b/include/linux/mdio/mdio-regmap.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Driver for MMIO-Mapped MDIO devices. Some IPs expose internal PHYs or PCS + * within the MMIO-mapped area + * + * Copyright (C) 2023 Maxime Chevallier <maxime.chevallier@bootlin.com> + */ +#ifndef MDIO_REGMAP_H +#define MDIO_REGMAP_H + +#include <linux/phy.h> + +struct device; +struct regmap; + +struct mdio_regmap_config { + struct device *parent; + struct regmap *regmap; + char name[MII_BUS_ID_SIZE]; + u8 valid_addr; + bool autoscan; +}; + +struct mii_bus *devm_mdio_regmap_register(struct device *dev, + const struct mdio_regmap_config *config); + +#endif diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index a4c4f737f9c1..9a744c48eec2 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1093,6 +1093,7 @@ void mlx5_cmdif_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_core_create_psv(struct mlx5_core_dev *dev, u32 pdn, int npsvs, u32 *sig_index); int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num); +__be32 mlx5_core_get_terminate_scatter_list_mkey(struct mlx5_core_dev *dev); void mlx5_core_put_rsc(struct mlx5_core_rsc_common *common); int mlx5_query_odp_caps(struct mlx5_core_dev *dev, struct mlx5_odp_caps *odp_caps); @@ -1173,7 +1174,13 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, u64 *values, int num_counters, size_t *offsets); -struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev); +struct mlx5_core_dev *mlx5_lag_get_next_peer_mdev(struct mlx5_core_dev *dev, int *i); + +#define mlx5_lag_for_each_peer_mdev(dev, peer, i) \ + for (i = 0, peer = mlx5_lag_get_next_peer_mdev(dev, &i); \ + peer; \ + peer = mlx5_lag_get_next_peer_mdev(dev, &i)) + u8 mlx5_lag_get_num_ports(struct mlx5_core_dev *dev); struct mlx5_uars_page *mlx5_get_uars_page(struct mlx5_core_dev *mdev); void mlx5_put_uars_page(struct mlx5_core_dev *mdev, struct mlx5_uars_page *up); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index dc5e2cb302a5..af3a92ad2e6b 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1705,7 +1705,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 rc[0x1]; u8 uar_4k[0x1]; - u8 reserved_at_241[0x9]; + u8 reserved_at_241[0x7]; + u8 fl_rc_qp_when_roce_disabled[0x1]; + u8 regexp_params[0x1]; u8 uar_sz[0x6]; u8 port_selection_cap[0x1]; u8 reserved_at_248[0x1]; @@ -1753,7 +1755,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_328[0x2]; u8 relaxed_ordering_read[0x1]; u8 log_max_pd[0x5]; - u8 reserved_at_330[0x9]; + u8 reserved_at_330[0x7]; + u8 vnic_env_cnt_steering_fail[0x1]; + u8 reserved_at_338[0x1]; u8 q_counter_aggregation[0x1]; u8 q_counter_other_vport[0x1]; u8 log_max_xrcd[0x5]; @@ -3671,7 +3675,13 @@ struct mlx5_ifc_vnic_diagnostic_statistics_bits { u8 eth_wqe_too_small[0x20]; - u8 reserved_at_220[0xdc0]; + u8 reserved_at_220[0xc0]; + + u8 generated_pkt_steering_fail[0x40]; + + u8 handled_pkt_steering_fail[0x40]; + + u8 reserved_at_360[0xc80]; }; struct mlx5_ifc_traffic_counter_bits { diff --git a/include/linux/msi.h b/include/linux/msi.h index cdb14a1ef268..a50ea79522f8 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -383,6 +383,13 @@ int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc); void arch_teardown_msi_irq(unsigned int irq); int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); void arch_teardown_msi_irqs(struct pci_dev *dev); +#endif /* CONFIG_PCI_MSI_ARCH_FALLBACKS */ + +/* + * Xen uses non-default msi_domain_ops and hence needs a way to populate sysfs + * entries of MSI IRQs. + */ +#if defined(CONFIG_PCI_XEN) || defined(CONFIG_PCI_MSI_ARCH_FALLBACKS) #ifdef CONFIG_SYSFS int msi_device_populate_sysfs(struct device *dev); void msi_device_destroy_sysfs(struct device *dev); @@ -390,7 +397,7 @@ void msi_device_destroy_sysfs(struct device *dev); static inline int msi_device_populate_sysfs(struct device *dev) { return 0; } static inline void msi_device_destroy_sysfs(struct device *dev) { } #endif /* !CONFIG_SYSFS */ -#endif /* CONFIG_PCI_MSI_ARCH_FALLBACKS */ +#endif /* CONFIG_PCI_XEN || CONFIG_PCI_MSI_ARCH_FALLBACKS */ /* * The restore hook is still available even for fully irq domain based diff --git a/include/linux/net.h b/include/linux/net.h index b73ad8e3c212..8defc8f1d82e 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -210,6 +210,7 @@ struct proto_ops { int offset, size_t size, int flags); ssize_t (*splice_read)(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); + void (*splice_eof)(struct socket *sock); int (*set_peek_off)(struct sock *sk, int val); int (*peek_len)(struct socket *sock); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 08fbd4622ccf..c2f0c6002a84 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -620,7 +620,7 @@ struct netdev_queue { netdevice_tracker dev_tracker; struct Qdisc __rcu *qdisc; - struct Qdisc *qdisc_sleeping; + struct Qdisc __rcu *qdisc_sleeping; #ifdef CONFIG_SYSFS struct kobject kobj; #endif @@ -768,8 +768,11 @@ static inline void rps_record_sock_flow(struct rps_sock_flow_table *table, /* We only give a hint, preemption can change CPU under us */ val |= raw_smp_processor_id(); - if (table->ents[index] != val) - table->ents[index] = val; + /* The following WRITE_ONCE() is paired with the READ_ONCE() + * here, and another one in get_rps_cpu(). + */ + if (READ_ONCE(table->ents[index]) != val) + WRITE_ONCE(table->ents[index], val); } } diff --git a/include/linux/netfs.h b/include/linux/netfs.h index a1f3522daa69..b11a84f6c32b 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -300,10 +300,6 @@ void netfs_stats_show(struct seq_file *); ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len, struct iov_iter *new, iov_iter_extraction_t extraction_flags); -struct sg_table; -ssize_t netfs_extract_iter_to_sg(struct iov_iter *iter, size_t len, - struct sg_table *sgtable, unsigned int sg_max, - iov_iter_extraction_t extraction_flags); /** * netfs_inode - Get the netfs inode context from the inode diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 1c68d67b832f..92a2063a0a23 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -617,6 +617,12 @@ PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted) * Please note that, confusingly, "page_mapping" refers to the inode * address_space which maps the page from disk; whereas "page_mapped" * refers to user virtual address space into which the page is mapped. + * + * For slab pages, since slab reuses the bits in struct page to store its + * internal states, the page->mapping does not exist as such, nor do these + * flags below. So in order to avoid testing non-existent bits, please + * make sure that PageSlab(page) actually evaluates to false before calling + * the following functions (e.g., PageAnon). See mm/slab.h. */ #define PAGE_MAPPING_ANON 0x1 #define PAGE_MAPPING_MOVABLE 0x2 diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 45c3d62e616d..95f33dadb2be 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -567,6 +567,7 @@ #define PCI_DEVICE_ID_AMD_19H_M50H_DF_F3 0x166d #define PCI_DEVICE_ID_AMD_19H_M60H_DF_F3 0x14e3 #define PCI_DEVICE_ID_AMD_19H_M70H_DF_F3 0x14f3 +#define PCI_DEVICE_ID_AMD_19H_M78H_DF_F3 0x12fb #define PCI_DEVICE_ID_AMD_CNB17H_F3 0x1703 #define PCI_DEVICE_ID_AMD_LANCE 0x2000 #define PCI_DEVICE_ID_AMD_LANCE_HOME 0x2001 diff --git a/include/linux/pcs-altera-tse.h b/include/linux/pcs-altera-tse.h deleted file mode 100644 index 92ab9f08e835..000000000000 --- a/include/linux/pcs-altera-tse.h +++ /dev/null @@ -1,17 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2022 Bootlin - * - * Maxime Chevallier <maxime.chevallier@bootlin.com> - */ - -#ifndef __LINUX_PCS_ALTERA_TSE_H -#define __LINUX_PCS_ALTERA_TSE_H - -struct phylink_pcs; -struct net_device; - -struct phylink_pcs *alt_tse_pcs_create(struct net_device *ndev, - void __iomem *pcs_base, int reg_width); - -#endif /* __LINUX_PCS_ALTERA_TSE_H */ diff --git a/include/linux/pcs-lynx.h b/include/linux/pcs-lynx.h index 5712cc2ce775..7958cccd16f2 100644 --- a/include/linux/pcs-lynx.h +++ b/include/linux/pcs-lynx.h @@ -9,9 +9,8 @@ #include <linux/mdio.h> #include <linux/phylink.h> -struct mdio_device *lynx_get_mdio_device(struct phylink_pcs *pcs); - -struct phylink_pcs *lynx_pcs_create(struct mdio_device *mdio); +struct phylink_pcs *lynx_pcs_create_mdiodev(struct mii_bus *bus, int addr); +struct phylink_pcs *lynx_pcs_create_fwnode(struct fwnode_handle *node); void lynx_pcs_destroy(struct phylink_pcs *pcs); diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index d2da1e0b4a92..ec8175b847cc 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -18,6 +18,7 @@ #define DW_AN_C37_SGMII 2 #define DW_2500BASEX 3 #define DW_AN_C37_1000BASEX 4 +#define DW_10GBASER 5 struct xpcs_id; @@ -35,8 +36,8 @@ int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, void xpcs_get_interfaces(struct dw_xpcs *xpcs, unsigned long *interfaces); int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable); -struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev, - phy_interface_t interface); +struct dw_xpcs *xpcs_create_mdiodev(struct mii_bus *bus, int addr, + phy_interface_t interface); void xpcs_destroy(struct dw_xpcs *xpcs); #endif /* __LINUX_PCS_XPCS_H */ diff --git a/include/linux/pe.h b/include/linux/pe.h index 5e1e11540870..fdf9c95709ba 100644 --- a/include/linux/pe.h +++ b/include/linux/pe.h @@ -11,25 +11,26 @@ #include <linux/types.h> /* - * Linux EFI stub v1.0 adds the following functionality: - * - Loading initrd from the LINUX_EFI_INITRD_MEDIA_GUID device path, - * - Loading/starting the kernel from firmware that targets a different - * machine type, via the entrypoint exposed in the .compat PE/COFF section. + * Starting from version v3.0, the major version field should be interpreted as + * a bit mask of features supported by the kernel's EFI stub: + * - 0x1: initrd loading from the LINUX_EFI_INITRD_MEDIA_GUID device path, + * - 0x2: initrd loading using the initrd= command line option, where the file + * may be specified using device path notation, and is not required to + * reside on the same volume as the loaded kernel image. * * The recommended way of loading and starting v1.0 or later kernels is to use * the LoadImage() and StartImage() EFI boot services, and expose the initrd * via the LINUX_EFI_INITRD_MEDIA_GUID device path. * - * Versions older than v1.0 support initrd loading via the image load options - * (using initrd=, limited to the volume from which the kernel itself was - * loaded), or via arch specific means (bootparams, DT, etc). + * Versions older than v1.0 may support initrd loading via the image load + * options (using initrd=, limited to the volume from which the kernel itself + * was loaded), or only via arch specific means (bootparams, DT, etc). * - * On x86, LoadImage() and StartImage() can be omitted if the EFI handover - * protocol is implemented, which can be inferred from the version, - * handover_offset and xloadflags fields in the bootparams structure. + * The minor version field must remain 0x0. + * (https://lore.kernel.org/all/efd6f2d4-547c-1378-1faa-53c044dbd297@gmail.com/) */ -#define LINUX_EFISTUB_MAJOR_VERSION 0x1 -#define LINUX_EFISTUB_MINOR_VERSION 0x1 +#define LINUX_EFISTUB_MAJOR_VERSION 0x3 +#define LINUX_EFISTUB_MINOR_VERSION 0x0 /* * LINUX_PE_MAGIC appears at offset 0x38 into the MS-DOS header of EFI bootable diff --git a/include/linux/phy.h b/include/linux/phy.h index e0df8b3c2bdb..11c1e91563d4 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -497,14 +497,17 @@ struct phy_device *mdiobus_scan_c22(struct mii_bus *bus, int addr); * Once complete, move to UP to restart the PHY. * - phy_stop aborts the running test and moves to @PHY_HALTED * - * @PHY_HALTED: PHY is up, but no polling or interrupts are done. Or - * PHY is in an error state. + * @PHY_HALTED: PHY is up, but no polling or interrupts are done. * - phy_start moves to @PHY_UP + * + * @PHY_ERROR: PHY is up, but is in an error state. + * - phy_stop moves to @PHY_HALTED */ enum phy_state { PHY_DOWN = 0, PHY_READY, PHY_HALTED, + PHY_ERROR, PHY_UP, PHY_RUNNING, PHY_NOLINK, @@ -1112,6 +1115,34 @@ struct phy_driver { #define PHY_ID_MATCH_MODEL(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 4) #define PHY_ID_MATCH_VENDOR(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 10) +/** + * phy_id_compare - compare @id1 with @id2 taking account of @mask + * @id1: first PHY ID + * @id2: second PHY ID + * @mask: the PHY ID mask, set bits are significant in matching + * + * Return true if the bits from @id1 and @id2 specified by @mask match. + * This uses an equivalent test to (@id & @mask) == (@phy_id & @mask). + */ +static inline bool phy_id_compare(u32 id1, u32 id2, u32 mask) +{ + return !((id1 ^ id2) & mask); +} + +/** + * phydev_id_compare - compare @id with the PHY's Clause 22 ID + * @phydev: the PHY device + * @id: the PHY ID to be matched + * + * Compare the @phydev clause 22 ID with the provided @id and return true or + * false depending whether it matches, using the bound driver mask. The + * @phydev must be bound to a driver. + */ +static inline bool phydev_id_compare(struct phy_device *phydev, u32 id) +{ + return phy_id_compare(id, phydev->phy_id, phydev->drv->phy_id_mask); +} + /* A Structure for boards to register fixups with the PHY Lib */ struct phy_fixup { struct list_head list; @@ -1175,10 +1206,12 @@ static inline int phy_read(struct phy_device *phydev, u32 regnum) #define phy_read_poll_timeout(phydev, regnum, val, cond, sleep_us, \ timeout_us, sleep_before_read) \ ({ \ - int __ret = read_poll_timeout(phy_read, val, val < 0 || (cond), \ + int __ret, __val; \ + __ret = read_poll_timeout(__val = phy_read, val, \ + __val < 0 || (cond), \ sleep_us, timeout_us, sleep_before_read, phydev, regnum); \ - if (val < 0) \ - __ret = val; \ + if (__val < 0) \ + __ret = __val; \ if (__ret) \ phydev_err(phydev, "%s failed: %d\n", __func__, __ret); \ __ret; \ @@ -1271,11 +1304,13 @@ int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); #define phy_read_mmd_poll_timeout(phydev, devaddr, regnum, val, cond, \ sleep_us, timeout_us, sleep_before_read) \ ({ \ - int __ret = read_poll_timeout(phy_read_mmd, val, (cond) || val < 0, \ + int __ret, __val; \ + __ret = read_poll_timeout(__val = phy_read_mmd, val, \ + __val < 0 || (cond), \ sleep_us, timeout_us, sleep_before_read, \ phydev, devaddr, regnum); \ - if (val < 0) \ - __ret = val; \ + if (__val < 0) \ + __ret = __val; \ if (__ret) \ phydev_err(phydev, "%s failed: %d\n", __func__, __ret); \ __ret; \ @@ -1904,10 +1939,8 @@ void phy_package_leave(struct phy_device *phydev); int devm_phy_package_join(struct device *dev, struct phy_device *phydev, int addr, size_t priv_size); -#if IS_ENABLED(CONFIG_PHYLIB) int __init mdio_bus_init(void); void mdio_bus_exit(void); -#endif int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data); int phy_ethtool_get_sset_count(struct phy_device *phydev); diff --git a/include/linux/phylink.h b/include/linux/phylink.h index bb782f05ad08..0cf07d7d11b8 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -656,6 +656,8 @@ int phylink_mii_c22_pcs_config(struct mdio_device *pcs, unsigned int mode, const unsigned long *advertising); void phylink_mii_c22_pcs_an_restart(struct mdio_device *pcs); +void phylink_resolve_c73(struct phylink_link_state *state); + void phylink_mii_c45_pcs_get_state(struct mdio_device *pcs, struct phylink_link_state *state); diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index a1aa68141d0b..7c8d65414a70 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -2,6 +2,8 @@ #ifndef __LINUX_BQ27X00_BATTERY_H__ #define __LINUX_BQ27X00_BATTERY_H__ +#include <linux/power_supply.h> + enum bq27xxx_chip { BQ27000 = 1, /* bq27000, bq27200 */ BQ27010, /* bq27010, bq27210 */ @@ -68,7 +70,9 @@ struct bq27xxx_device_info { struct bq27xxx_access_methods bus; struct bq27xxx_reg_cache cache; int charge_design_full; + bool removed; unsigned long last_update; + union power_supply_propval last_status; struct delayed_work work; struct power_supply *bat; struct list_head list; diff --git a/include/linux/ref_tracker.h b/include/linux/ref_tracker.h index 9ca353ab712b..8eac4f3d5254 100644 --- a/include/linux/ref_tracker.h +++ b/include/linux/ref_tracker.h @@ -17,12 +17,15 @@ struct ref_tracker_dir { bool dead; struct list_head list; /* List of active trackers */ struct list_head quarantine; /* List of dead trackers */ + char name[32]; #endif }; #ifdef CONFIG_REF_TRACKER + static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir, - unsigned int quarantine_count) + unsigned int quarantine_count, + const char *name) { INIT_LIST_HEAD(&dir->list); INIT_LIST_HEAD(&dir->quarantine); @@ -31,14 +34,20 @@ static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir, dir->dead = false; refcount_set(&dir->untracked, 1); refcount_set(&dir->no_tracker, 1); + strscpy(dir->name, name, sizeof(dir->name)); stack_depot_init(); } void ref_tracker_dir_exit(struct ref_tracker_dir *dir); +void ref_tracker_dir_print_locked(struct ref_tracker_dir *dir, + unsigned int display_limit); + void ref_tracker_dir_print(struct ref_tracker_dir *dir, unsigned int display_limit); +int ref_tracker_dir_snprint(struct ref_tracker_dir *dir, char *buf, size_t size); + int ref_tracker_alloc(struct ref_tracker_dir *dir, struct ref_tracker **trackerp, gfp_t gfp); @@ -48,7 +57,8 @@ int ref_tracker_free(struct ref_tracker_dir *dir, #else /* CONFIG_REF_TRACKER */ static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir, - unsigned int quarantine_count) + unsigned int quarantine_count, + const char *name) { } @@ -56,11 +66,22 @@ static inline void ref_tracker_dir_exit(struct ref_tracker_dir *dir) { } +static inline void ref_tracker_dir_print_locked(struct ref_tracker_dir *dir, + unsigned int display_limit) +{ +} + static inline void ref_tracker_dir_print(struct ref_tracker_dir *dir, unsigned int display_limit) { } +static inline int ref_tracker_dir_snprint(struct ref_tracker_dir *dir, + char *buf, size_t size) +{ + return 0; +} + static inline int ref_tracker_alloc(struct ref_tracker_dir *dir, struct ref_tracker **trackerp, gfp_t gfp) diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 537cbf9a2ade..e0f5ac90a228 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -29,7 +29,6 @@ struct kernel_clone_args { u32 io_thread:1; u32 user_worker:1; u32 no_files:1; - u32 ignore_signals:1; unsigned long stack; unsigned long stack_size; unsigned long tls; diff --git a/include/linux/sched/vhost_task.h b/include/linux/sched/vhost_task.h index 6123c10b99cf..837a23624a66 100644 --- a/include/linux/sched/vhost_task.h +++ b/include/linux/sched/vhost_task.h @@ -2,22 +2,13 @@ #ifndef _LINUX_VHOST_TASK_H #define _LINUX_VHOST_TASK_H -#include <linux/completion.h> -struct task_struct; +struct vhost_task; -struct vhost_task { - int (*fn)(void *data); - void *data; - struct completion exited; - unsigned long flags; - struct task_struct *task; -}; - -struct vhost_task *vhost_task_create(int (*fn)(void *), void *arg, +struct vhost_task *vhost_task_create(bool (*fn)(void *), void *arg, const char *name); void vhost_task_start(struct vhost_task *vtsk); void vhost_task_stop(struct vhost_task *vtsk); -bool vhost_task_should_stop(struct vhost_task *vtsk); +void vhost_task_wake(struct vhost_task *vtsk); #endif diff --git a/include/linux/sfp.h b/include/linux/sfp.h index ef06a195b3c2..9346cd44814d 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -342,6 +342,12 @@ enum { SFP_ENCODING = 11, SFP_BR_NOMINAL = 12, SFP_RATE_ID = 13, + SFF_RID_8079 = 0x01, + SFF_RID_8431_RX_ONLY = 0x02, + SFF_RID_8431_TX_ONLY = 0x04, + SFF_RID_8431 = 0x06, + SFF_RID_10G8G = 0x0e, + SFP_LINK_LEN_SM_KM = 14, SFP_LINK_LEN_SM_100M = 15, SFP_LINK_LEN_50UM_OM2_10M = 16, @@ -465,6 +471,7 @@ enum { SFP_STATUS = 110, SFP_STATUS_TX_DISABLE = BIT(7), SFP_STATUS_TX_DISABLE_FORCE = BIT(6), + SFP_STATUS_RS0_SELECT = BIT(3), SFP_STATUS_TX_FAULT = BIT(2), SFP_STATUS_RX_LOS = BIT(1), SFP_ALARM0 = 112, @@ -496,6 +503,7 @@ enum { SFP_WARN1_RXPWR_LOW = BIT(6), SFP_EXT_STATUS = 118, + SFP_EXT_STATUS_RS1_SELECT = BIT(3), SFP_EXT_STATUS_PWRLVL_SELECT = BIT(0), SFP_VSL = 120, @@ -556,6 +564,7 @@ int sfp_get_module_eeprom_by_page(struct sfp_bus *bus, struct netlink_ext_ack *extack); void sfp_upstream_start(struct sfp_bus *bus); void sfp_upstream_stop(struct sfp_bus *bus); +void sfp_upstream_set_signal_rate(struct sfp_bus *bus, unsigned int rate_kbd); void sfp_bus_put(struct sfp_bus *bus); struct sfp_bus *sfp_bus_find_fwnode(const struct fwnode_handle *fwnode); int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, @@ -615,6 +624,11 @@ static inline void sfp_upstream_stop(struct sfp_bus *bus) { } +static inline void sfp_upstream_set_signal_rate(struct sfp_bus *bus, + unsigned int rate_kbd) +{ +} + static inline void sfp_bus_put(struct sfp_bus *bus) { } diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 7bde8e1c228a..224293b2dd06 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -107,7 +107,10 @@ extern void synchronize_shrinkers(void); #ifdef CONFIG_SHRINKER_DEBUG extern int shrinker_debugfs_add(struct shrinker *shrinker); -extern struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker); +extern struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, + int *debugfs_id); +extern void shrinker_debugfs_remove(struct dentry *debugfs_entry, + int debugfs_id); extern int __printf(2, 3) shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...); #else /* CONFIG_SHRINKER_DEBUG */ @@ -115,10 +118,16 @@ static inline int shrinker_debugfs_add(struct shrinker *shrinker) { return 0; } -static inline struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker) +static inline struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, + int *debugfs_id) { + *debugfs_id = -1; return NULL; } +static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry, + int debugfs_id) +{ +} static inline __printf(2, 3) int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) { diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 00e8c435fa1a..e2f48ddb2f7c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -330,6 +330,7 @@ struct tc_skb_ext { u8 post_ct_snat:1; u8 post_ct_dnat:1; u8 act_miss:1; /* Set if act_miss_cookie is used */ + u8 l2_miss:1; /* Set by bridge upon FDB or MDB miss */ }; #endif @@ -1383,7 +1384,7 @@ static inline int skb_pad(struct sk_buff *skb, int pad) #define dev_kfree_skb(a) consume_skb(a) int skb_append_pagefrags(struct sk_buff *skb, struct page *page, - int offset, size_t size); + int offset, size_t size, size_t max_frags); struct skb_seq_state { __u32 lower_offset; @@ -1587,6 +1588,16 @@ static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) to->l4_hash = from->l4_hash; }; +static inline int skb_cmp_decrypted(const struct sk_buff *skb1, + const struct sk_buff *skb2) +{ +#ifdef CONFIG_TLS_DEVICE + return skb2->decrypted - skb1->decrypted; +#else + return 0; +#endif +} + static inline void skb_copy_decrypted(struct sk_buff *to, const struct sk_buff *from) { @@ -2426,11 +2437,6 @@ static inline void __skb_fill_page_desc_noacc(struct skb_shared_info *shinfo, { skb_frag_t *frag = &shinfo->frags[i]; - /* - * Propagate page pfmemalloc to the skb if we can. The problem is - * that not all callers have unique ownership of the page but rely - * on page_is_pfmemalloc doing the right thing(tm). - */ skb_frag_fill_page_desc(frag, page, off, size); } @@ -2463,6 +2469,11 @@ static inline void __skb_fill_page_desc(struct sk_buff *skb, int i, struct page *page, int off, int size) { __skb_fill_page_desc_noacc(skb_shinfo(skb), i, page, off, size); + + /* Propagate page pfmemalloc to the skb if we can. The problem is + * that not all callers have unique ownership of the page but rely + * on page_is_pfmemalloc doing the right thing(tm). + */ page = compound_head(page); if (page_is_pfmemalloc(page)) skb->pfmemalloc = true; @@ -4014,7 +4025,7 @@ __skb_header_pointer(const struct sk_buff *skb, int offset, int len, if (likely(hlen - offset >= len)) return (void *)data + offset; - if (!skb || unlikely(skb_copy_bits(skb, offset, buffer, len) < 0)) + if (!skb || !buffer || unlikely(skb_copy_bits(skb, offset, buffer, len) < 0)) return NULL; return buffer; @@ -5097,5 +5108,8 @@ static inline void skb_mark_for_recycle(struct sk_buff *skb) #endif } +ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter, + ssize_t maxsize, gfp_t gfp); + #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 84f787416a54..054d7911bfc9 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -71,7 +71,6 @@ struct sk_psock_link { }; struct sk_psock_work_state { - struct sk_buff *skb; u32 len; u32 off; }; @@ -105,7 +104,7 @@ struct sk_psock { struct proto *sk_proto; struct mutex work_mutex; struct sk_psock_work_state work_state; - struct work_struct work; + struct delayed_work work; struct rcu_work rwork; }; diff --git a/include/linux/socket.h b/include/linux/socket.h index 13c3a237b9c9..3fd3436bc09f 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -327,6 +327,7 @@ struct ucred { */ #define MSG_ZEROCOPY 0x4000000 /* Use user data in kernel path */ +#define MSG_SPLICE_PAGES 0x8000000 /* Splice the pages from the iterator in sendmsg() */ #define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */ #define MSG_CMSG_CLOEXEC 0x40000000 /* Set close_on_exec for file descriptor received through @@ -337,6 +338,10 @@ struct ucred { #define MSG_CMSG_COMPAT 0 /* We never have 32 bit fixups */ #endif +/* Flags to be cleared on entry by sendmsg and sendmmsg syscalls */ +#define MSG_INTERNAL_SENDMSG_FLAGS \ + (MSG_SPLICE_PAGES | MSG_SENDPAGE_NOPOLICY | MSG_SENDPAGE_NOTLAST | \ + MSG_SENDPAGE_DECRYPTED) /* Setsockoptions(2) level. Thanks to BSD these must match IPPROTO_xxx */ #define SOL_IP 0 diff --git a/include/linux/splice.h b/include/linux/splice.h index a55179fd60fc..4fab18a6e371 100644 --- a/include/linux/splice.h +++ b/include/linux/splice.h @@ -38,6 +38,7 @@ struct splice_desc { struct file *file; /* file to read/write */ void *data; /* cookie */ } u; + void (*splice_eof)(struct splice_desc *sd); /* Unexpected EOF handler */ loff_t pos; /* file position */ loff_t *opos; /* sendfile: output position */ size_t num_spliced; /* number of bytes already spliced */ @@ -84,6 +85,8 @@ extern long do_splice(struct file *in, loff_t *off_in, extern long do_tee(struct file *in, struct file *out, size_t len, unsigned int flags); +extern ssize_t splice_to_socket(struct pipe_inode_info *pipe, struct file *out, + loff_t *ppos, size_t len, unsigned int flags); /* * for dynamic pipe sizing diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 24aa159d29a7..fbc4bd423b35 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -176,7 +176,7 @@ extern struct svc_rdma_recv_ctxt * extern void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma, struct svc_rdma_recv_ctxt *ctxt); extern void svc_rdma_flush_recv_queues(struct svcxprt_rdma *rdma); -extern void svc_rdma_release_rqst(struct svc_rqst *rqstp); +extern void svc_rdma_release_ctxt(struct svc_xprt *xprt, void *ctxt); extern int svc_rdma_recvfrom(struct svc_rqst *); /* svc_rdma_rw.c */ diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 867479204840..a6b12631db21 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -23,7 +23,7 @@ struct svc_xprt_ops { int (*xpo_sendto)(struct svc_rqst *); int (*xpo_result_payload)(struct svc_rqst *, unsigned int, unsigned int); - void (*xpo_release_rqst)(struct svc_rqst *); + void (*xpo_release_ctxt)(struct svc_xprt *xprt, void *ctxt); void (*xpo_detach)(struct svc_xprt *); void (*xpo_free)(struct svc_xprt *); void (*xpo_kill_temp_xprt)(struct svc_xprt *); diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index d16ae621782c..a7116048a4d4 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -61,10 +61,9 @@ int svc_recv(struct svc_rqst *, long); void svc_send(struct svc_rqst *rqstp); void svc_drop(struct svc_rqst *); void svc_sock_update_bufs(struct svc_serv *serv); -bool svc_alien_sock(struct net *net, int fd); -int svc_addsock(struct svc_serv *serv, const int fd, - char *name_return, const size_t len, - const struct cred *cred); +int svc_addsock(struct svc_serv *serv, struct net *net, + const int fd, char *name_return, const size_t len, + const struct cred *cred); void svc_init_xprt_sock(void); void svc_cleanup_xprt_sock(void); struct svc_xprt *svc_sock_create(struct svc_serv *serv, int prot); diff --git a/include/linux/surface_aggregator/device.h b/include/linux/surface_aggregator/device.h index df81043b9e71..42b249b4c24b 100644 --- a/include/linux/surface_aggregator/device.h +++ b/include/linux/surface_aggregator/device.h @@ -243,11 +243,7 @@ static inline bool is_ssam_device(struct device *d) * Return: Returns the pointer to the &struct ssam_device_driver wrapping the * given device driver @d. */ -static inline -struct ssam_device_driver *to_ssam_device_driver(struct device_driver *d) -{ - return container_of(d, struct ssam_device_driver, driver); -} +#define to_ssam_device_driver(d) container_of_const(d, struct ssam_device_driver, driver) const struct ssam_device_id *ssam_device_id_match(const struct ssam_device_id *table, const struct ssam_device_uid uid); diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 77693389c3f9..6a1e8f157255 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -282,6 +282,7 @@ enum tpm_chip_flags { TPM_CHIP_FLAG_ALWAYS_POWERED = BIT(5), TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED = BIT(6), TPM_CHIP_FLAG_FIRMWARE_UPGRADE = BIT(7), + TPM_CHIP_FLAG_SUSPENDED = BIT(8), }; #define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 0e373222a6df..7c4a0b72334e 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -806,6 +806,7 @@ enum { FILTER_TRACE_FN, FILTER_COMM, FILTER_CPU, + FILTER_STACKTRACE, }; extern int trace_event_raw_init(struct trace_event_call *call); diff --git a/include/linux/uio.h b/include/linux/uio.h index 044c1d8c230c..0ccb983cf645 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -433,4 +433,9 @@ static inline bool iov_iter_extract_will_pin(const struct iov_iter *iter) return user_backed_iter(iter); } +struct sg_table; +ssize_t extract_iter_to_sg(struct iov_iter *iter, size_t len, + struct sg_table *sgtable, unsigned int sg_max, + iov_iter_extraction_t extraction_flags); + #endif diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index a2448e98854f..07531c4f4350 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -443,7 +443,7 @@ static inline struct usb_composite_driver *to_cdriver( * @bcd_webusb_version: 0x0100 by default, WebUSB specification version * @b_webusb_vendor_code: 0x0 by default, vendor code for WebUSB * @landing_page: empty by default, landing page to announce in WebUSB - * @use_webusb:: false by default, interested gadgets set it + * @use_webusb: false by default, interested gadgets set it * @os_desc_config: the configuration to be used with OS descriptors * @setup_pending: true when setup request is queued but not completed * @os_desc_pending: true when os_desc request is queued but not completed diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 094c77eaf455..0c7eff91adf4 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -501,6 +501,11 @@ void *hcd_buffer_alloc(struct usb_bus *bus, size_t size, void hcd_buffer_free(struct usb_bus *bus, size_t size, void *addr, dma_addr_t dma); +void *hcd_buffer_alloc_pages(struct usb_hcd *hcd, + size_t size, gfp_t mem_flags, dma_addr_t *dma); +void hcd_buffer_free_pages(struct usb_hcd *hcd, + size_t size, void *addr, dma_addr_t dma); + /* generic bus glue, needed for host controllers that don't use PCI */ extern irqreturn_t usb_hcd_irq(int irq, void *__hcd); diff --git a/include/linux/user_events.h b/include/linux/user_events.h index 2847f5a18a86..8afa8c3a0973 100644 --- a/include/linux/user_events.h +++ b/include/linux/user_events.h @@ -17,9 +17,10 @@ #ifdef CONFIG_USER_EVENTS struct user_event_mm { - struct list_head link; + struct list_head mms_link; struct list_head enablers; struct mm_struct *mm; + /* Used for one-shot lists, protected by event_mutex */ struct user_event_mm *next; refcount_t refcnt; refcount_t tasks; diff --git a/include/media/dvb_frontend.h b/include/media/dvb_frontend.h index e7c44870f20d..367d5381217b 100644 --- a/include/media/dvb_frontend.h +++ b/include/media/dvb_frontend.h @@ -686,7 +686,10 @@ struct dtv_frontend_properties { * @id: Frontend ID * @exit: Used to inform the DVB core that the frontend * thread should exit (usually, means that the hardware - * got disconnected. + * got disconnected). + * @remove_mutex: mutex that avoids a race condition between a callback + * called when the hardware is disconnected and the + * file_operations of dvb_frontend. */ struct dvb_frontend { @@ -704,6 +707,7 @@ struct dvb_frontend { int (*callback)(void *adapter_priv, int component, int cmd, int arg); int id; unsigned int exit; + struct mutex remove_mutex; }; /** diff --git a/include/media/dvb_net.h b/include/media/dvb_net.h index 9980b1dd750b..4a921ea96091 100644 --- a/include/media/dvb_net.h +++ b/include/media/dvb_net.h @@ -39,6 +39,9 @@ struct net_device; * @exit: flag to indicate when the device is being removed. * @demux: pointer to &struct dmx_demux. * @ioctl_mutex: protect access to this struct. + * @remove_mutex: mutex that avoids a race condition between a callback + * called when the hardware is disconnected and the + * file_operations of dvb_net. * * Currently, the core supports up to %DVB_NET_DEVICES_MAX (10) network * devices. @@ -51,6 +54,7 @@ struct dvb_net { unsigned int exit:1; struct dmx_demux *demux; struct mutex ioctl_mutex; + struct mutex remove_mutex; }; /** diff --git a/include/media/dvbdev.h b/include/media/dvbdev.h index 29d25c8a6f13..8958e5e2fc5b 100644 --- a/include/media/dvbdev.h +++ b/include/media/dvbdev.h @@ -194,6 +194,21 @@ struct dvb_device { }; /** + * struct dvbdevfops_node - fops nodes registered in dvbdevfops_list + * + * @fops: Dynamically allocated fops for ->owner registration + * @type: type of dvb_device + * @template: dvb_device used for registration + * @list_head: list_head for dvbdevfops_list + */ +struct dvbdevfops_node { + struct file_operations *fops; + enum dvb_device_type type; + const struct dvb_device *template; + struct list_head list_head; +}; + +/** * dvb_device_get - Increase dvb_device reference * * @dvbdev: pointer to struct dvb_device diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index cfd19e72d0fc..b325df0d54d6 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -1119,6 +1119,7 @@ struct v4l2_subdev { * @vfh: pointer to &struct v4l2_fh * @state: pointer to &struct v4l2_subdev_state * @owner: module pointer to the owner of this file handle + * @client_caps: bitmask of ``V4L2_SUBDEV_CLIENT_CAP_*`` */ struct v4l2_subdev_fh { struct v4l2_fh vfh; diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 07df96c47ef4..872dcb91a540 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -350,6 +350,7 @@ enum { enum { HCI_SETUP, HCI_CONFIG, + HCI_DEBUGFS_CREATED, HCI_AUTO_OFF, HCI_RFKILLED, HCI_MGMT, diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index a6c8aee2f256..9654567cfae3 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -515,6 +515,7 @@ struct hci_dev { struct work_struct cmd_sync_work; struct list_head cmd_sync_work_list; struct mutex cmd_sync_work_lock; + struct mutex unregister_lock; struct work_struct cmd_sync_cancel_work; struct work_struct reenable_adv_work; @@ -1201,7 +1202,8 @@ static inline struct hci_conn *hci_conn_hash_lookup_cis(struct hci_dev *hdev, if (id != BT_ISO_QOS_CIS_UNSET && id != c->iso_qos.ucast.cis) continue; - if (ba_type == c->dst_type && !bacmp(&c->dst, ba)) { + /* Match destination address if set */ + if (!ba || (ba_type == c->dst_type && !bacmp(&c->dst, ba))) { rcu_read_unlock(); return c; } @@ -1327,7 +1329,7 @@ int hci_le_create_cis(struct hci_conn *conn); struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, u8 role); -int hci_conn_del(struct hci_conn *conn); +void hci_conn_del(struct hci_conn *conn); void hci_conn_hash_flush(struct hci_dev *hdev); void hci_conn_check_pending(struct hci_dev *hdev); diff --git a/include/net/bonding.h b/include/net/bonding.h index 0efef2a952b7..b57bec6e737e 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-1.0+ */ /* * Bond several ethernet interfaces into a Cisco, running 'Etherchannel'. * @@ -7,9 +8,6 @@ * BUT, I'm the one who modified it for ethernet, so: * (c) Copyright 1999, Thomas Davis, tadavis@lbl.gov * - * This software may be used and distributed according to the terms - * of the GNU Public License, incorporated herein by reference. - * */ #ifndef _NET_BONDING_H @@ -221,6 +219,7 @@ struct bonding { struct bond_up_slave __rcu *usable_slaves; struct bond_up_slave __rcu *all_slaves; bool force_primary; + bool notifier_ctx; s32 slave_cnt; /* never change this value outside the attach/detach wrappers */ int (*recv_probe)(const struct sk_buff *, struct bonding *, struct slave *); diff --git a/include/net/devlink.h b/include/net/devlink.h index 6a942e70e451..9a3c51aa6e81 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -123,6 +123,7 @@ struct devlink_port { struct list_head list; struct list_head region_list; struct devlink *devlink; + const struct devlink_port_ops *ops; unsigned int index; spinlock_t type_lock; /* Protects type and type_eth/ib * structures consistency. @@ -1261,7 +1262,7 @@ struct devlink_ops { /** * @supported_flash_update_params: * mask of parameters supported by the driver's .flash_update - * implemementation. + * implementation. */ u32 supported_flash_update_params; unsigned long reload_actions; @@ -1273,12 +1274,6 @@ struct devlink_ops { int (*reload_up)(struct devlink *devlink, enum devlink_reload_action action, enum devlink_reload_limit limit, u32 *actions_performed, struct netlink_ext_ack *extack); - int (*port_type_set)(struct devlink_port *devlink_port, - enum devlink_port_type port_type); - int (*port_split)(struct devlink *devlink, struct devlink_port *port, - unsigned int count, struct netlink_ext_ack *extack); - int (*port_unsplit)(struct devlink *devlink, struct devlink_port *port, - struct netlink_ext_ack *extack); int (*sb_pool_get)(struct devlink *devlink, unsigned int sb_index, u16 pool_index, struct devlink_sb_pool_info *pool_info); @@ -1435,80 +1430,17 @@ struct devlink_ops { const struct devlink_trap_policer *policer, u64 *p_drops); /** - * @port_function_hw_addr_get: Port function's hardware address get function. - * - * Should be used by device drivers to report the hardware address of a function managed - * by the devlink port. Driver should return -EOPNOTSUPP if it doesn't support port - * function handling for a particular port. - * - * Note: @extack can be NULL when port notifier queries the port function. - */ - int (*port_function_hw_addr_get)(struct devlink_port *port, u8 *hw_addr, - int *hw_addr_len, - struct netlink_ext_ack *extack); - /** - * @port_function_hw_addr_set: Port function's hardware address set function. - * - * Should be used by device drivers to set the hardware address of a function managed - * by the devlink port. Driver should return -EOPNOTSUPP if it doesn't support port - * function handling for a particular port. - */ - int (*port_function_hw_addr_set)(struct devlink_port *port, - const u8 *hw_addr, int hw_addr_len, - struct netlink_ext_ack *extack); - /** - * @port_fn_roce_get: Port function's roce get function. - * - * Query RoCE state of a function managed by the devlink port. - * Return -EOPNOTSUPP if port function RoCE handling is not supported. - */ - int (*port_fn_roce_get)(struct devlink_port *devlink_port, - bool *is_enable, - struct netlink_ext_ack *extack); - /** - * @port_fn_roce_set: Port function's roce set function. - * - * Enable/Disable the RoCE state of a function managed by the devlink - * port. - * Return -EOPNOTSUPP if port function RoCE handling is not supported. - */ - int (*port_fn_roce_set)(struct devlink_port *devlink_port, - bool enable, struct netlink_ext_ack *extack); - /** - * @port_fn_migratable_get: Port function's migratable get function. - * - * Query migratable state of a function managed by the devlink port. - * Return -EOPNOTSUPP if port function migratable handling is not - * supported. - */ - int (*port_fn_migratable_get)(struct devlink_port *devlink_port, - bool *is_enable, - struct netlink_ext_ack *extack); - /** - * @port_fn_migratable_set: Port function's migratable set function. - * - * Enable/Disable migratable state of a function managed by the devlink - * port. - * Return -EOPNOTSUPP if port function migratable handling is not - * supported. - */ - int (*port_fn_migratable_set)(struct devlink_port *devlink_port, - bool enable, - struct netlink_ext_ack *extack); - /** * port_new() - Add a new port function of a specified flavor * @devlink: Devlink instance * @attrs: attributes of the new port * @extack: extack for reporting error messages - * @new_port_index: index of the new port + * @devlink_port: pointer to store new devlink port pointer * * Devlink core will call this device driver function upon user request * to create a new port function of a specified flavor and optional * attributes * * Notes: - * - Called without devlink instance lock being held. Drivers must - * implement own means of synchronization * - On success, drivers must register a port with devlink core * * Return: 0 on success, negative value otherwise. @@ -1516,56 +1448,7 @@ struct devlink_ops { int (*port_new)(struct devlink *devlink, const struct devlink_port_new_attrs *attrs, struct netlink_ext_ack *extack, - unsigned int *new_port_index); - /** - * port_del() - Delete a port function - * @devlink: Devlink instance - * @port_index: port function index to delete - * @extack: extack for reporting error messages - * - * Devlink core will call this device driver function upon user request - * to delete a previously created port function - * - * Notes: - * - Called without devlink instance lock being held. Drivers must - * implement own means of synchronization - * - On success, drivers must unregister the corresponding devlink - * port - * - * Return: 0 on success, negative value otherwise. - */ - int (*port_del)(struct devlink *devlink, unsigned int port_index, - struct netlink_ext_ack *extack); - /** - * port_fn_state_get() - Get the state of a port function - * @devlink: Devlink instance - * @port: The devlink port - * @state: Admin configured state - * @opstate: Current operational state - * @extack: extack for reporting error messages - * - * Reports the admin and operational state of a devlink port function - * - * Return: 0 on success, negative value otherwise. - */ - int (*port_fn_state_get)(struct devlink_port *port, - enum devlink_port_fn_state *state, - enum devlink_port_fn_opstate *opstate, - struct netlink_ext_ack *extack); - /** - * port_fn_state_set() - Set the admin state of a port function - * @devlink: Devlink instance - * @port: The devlink port - * @state: Admin state - * @extack: extack for reporting error messages - * - * Set the admin state of a devlink port function - * - * Return: 0 on success, negative value otherwise. - */ - int (*port_fn_state_set)(struct devlink_port *port, - enum devlink_port_fn_state state, - struct netlink_ext_ack *extack); + struct devlink_port **devlink_port); /** * Rate control callbacks. @@ -1655,15 +1538,116 @@ void devl_unregister(struct devlink *devlink); void devlink_register(struct devlink *devlink); void devlink_unregister(struct devlink *devlink); void devlink_free(struct devlink *devlink); + +/** + * struct devlink_port_ops - Port operations + * @port_split: Callback used to split the port into multiple ones. + * @port_unsplit: Callback used to unsplit the port group back into + * a single port. + * @port_type_set: Callback used to set a type of a port. + * @port_del: Callback used to delete selected port along with related function. + * Devlink core calls this upon user request to delete + * a port previously created by devlink_ops->port_new(). + * @port_fn_hw_addr_get: Callback used to set port function's hardware address. + * Should be used by device drivers to report + * the hardware address of a function managed + * by the devlink port. + * @port_fn_hw_addr_set: Callback used to set port function's hardware address. + * Should be used by device drivers to set the hardware + * address of a function managed by the devlink port. + * @port_fn_roce_get: Callback used to get port function's RoCE capability. + * Should be used by device drivers to report + * the current state of RoCE capability of a function + * managed by the devlink port. + * @port_fn_roce_set: Callback used to set port function's RoCE capability. + * Should be used by device drivers to enable/disable + * RoCE capability of a function managed + * by the devlink port. + * @port_fn_migratable_get: Callback used to get port function's migratable + * capability. Should be used by device drivers + * to report the current state of migratable capability + * of a function managed by the devlink port. + * @port_fn_migratable_set: Callback used to set port function's migratable + * capability. Should be used by device drivers + * to enable/disable migratable capability of + * a function managed by the devlink port. + * @port_fn_state_get: Callback used to get port function's state. + * Should be used by device drivers to report + * the current admin and operational state of a + * function managed by the devlink port. + * @port_fn_state_set: Callback used to get port function's state. + * Should be used by device drivers set + * the admin state of a function managed + * by the devlink port. + * + * Note: Driver should return -EOPNOTSUPP if it doesn't support + * port function (@port_fn_*) handling for a particular port. + */ +struct devlink_port_ops { + int (*port_split)(struct devlink *devlink, struct devlink_port *port, + unsigned int count, struct netlink_ext_ack *extack); + int (*port_unsplit)(struct devlink *devlink, struct devlink_port *port, + struct netlink_ext_ack *extack); + int (*port_type_set)(struct devlink_port *devlink_port, + enum devlink_port_type port_type); + int (*port_del)(struct devlink *devlink, struct devlink_port *port, + struct netlink_ext_ack *extack); + int (*port_fn_hw_addr_get)(struct devlink_port *port, u8 *hw_addr, + int *hw_addr_len, + struct netlink_ext_ack *extack); + int (*port_fn_hw_addr_set)(struct devlink_port *port, + const u8 *hw_addr, int hw_addr_len, + struct netlink_ext_ack *extack); + int (*port_fn_roce_get)(struct devlink_port *devlink_port, + bool *is_enable, + struct netlink_ext_ack *extack); + int (*port_fn_roce_set)(struct devlink_port *devlink_port, + bool enable, struct netlink_ext_ack *extack); + int (*port_fn_migratable_get)(struct devlink_port *devlink_port, + bool *is_enable, + struct netlink_ext_ack *extack); + int (*port_fn_migratable_set)(struct devlink_port *devlink_port, + bool enable, + struct netlink_ext_ack *extack); + int (*port_fn_state_get)(struct devlink_port *port, + enum devlink_port_fn_state *state, + enum devlink_port_fn_opstate *opstate, + struct netlink_ext_ack *extack); + int (*port_fn_state_set)(struct devlink_port *port, + enum devlink_port_fn_state state, + struct netlink_ext_ack *extack); +}; + void devlink_port_init(struct devlink *devlink, struct devlink_port *devlink_port); void devlink_port_fini(struct devlink_port *devlink_port); -int devl_port_register(struct devlink *devlink, - struct devlink_port *devlink_port, - unsigned int port_index); -int devlink_port_register(struct devlink *devlink, - struct devlink_port *devlink_port, - unsigned int port_index); + +int devl_port_register_with_ops(struct devlink *devlink, + struct devlink_port *devlink_port, + unsigned int port_index, + const struct devlink_port_ops *ops); + +static inline int devl_port_register(struct devlink *devlink, + struct devlink_port *devlink_port, + unsigned int port_index) +{ + return devl_port_register_with_ops(devlink, devlink_port, + port_index, NULL); +} + +int devlink_port_register_with_ops(struct devlink *devlink, + struct devlink_port *devlink_port, + unsigned int port_index, + const struct devlink_port_ops *ops); + +static inline int devlink_port_register(struct devlink *devlink, + struct devlink_port *devlink_port, + unsigned int port_index) +{ + return devlink_port_register_with_ops(devlink, devlink_port, + port_index, NULL); +} + void devl_port_unregister(struct devlink_port *devlink_port); void devlink_port_unregister(struct devlink_port *devlink_port); void devlink_port_type_eth_set(struct devlink_port *devlink_port); diff --git a/include/net/dsa.h b/include/net/dsa.h index 8903053fa5aa..75022cf771cf 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -867,9 +867,15 @@ struct dsa_switch_ops { phy_interface_t iface); int (*phylink_mac_link_state)(struct dsa_switch *ds, int port, struct phylink_link_state *state); + int (*phylink_mac_prepare)(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface); void (*phylink_mac_config)(struct dsa_switch *ds, int port, unsigned int mode, const struct phylink_link_state *state); + int (*phylink_mac_finish)(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface); void (*phylink_mac_an_restart)(struct dsa_switch *ds, int port); void (*phylink_mac_link_down)(struct dsa_switch *ds, int port, unsigned int mode, diff --git a/include/net/flow.h b/include/net/flow.h index bb8651a6eaa7..7f0adda3bf2f 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -116,11 +116,10 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif, } /* Reset some input parameters after previous lookup */ -static inline void flowi4_update_output(struct flowi4 *fl4, int oif, __u8 tos, +static inline void flowi4_update_output(struct flowi4 *fl4, int oif, __be32 daddr, __be32 saddr) { fl4->flowi4_oif = oif; - fl4->flowi4_tos = tos; fl4->daddr = daddr; fl4->saddr = saddr; } diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 85b2281576ed..8b41668c77fc 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -243,10 +243,12 @@ struct flow_dissector_key_ip { * struct flow_dissector_key_meta: * @ingress_ifindex: ingress ifindex * @ingress_iftype: ingress interface type + * @l2_miss: packet did not match an L2 entry during forwarding */ struct flow_dissector_key_meta { int ingress_ifindex; u16 ingress_iftype; + u8 l2_miss; }; /** diff --git a/include/net/gro.h b/include/net/gro.h index a4fab706240d..7b47dd6ce94f 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -11,11 +11,23 @@ #include <net/udp.h> struct napi_gro_cb { - /* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */ - void *frag0; + union { + struct { + /* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */ + void *frag0; - /* Length of frag0. */ - unsigned int frag0_len; + /* Length of frag0. */ + unsigned int frag0_len; + }; + + struct { + /* used in skb_gro_receive() slow path */ + struct sk_buff *last; + + /* jiffies when first packet was created/queued */ + unsigned long age; + }; + }; /* This indicates where we are processing relative to skb->data. */ int data_offset; @@ -32,9 +44,6 @@ struct napi_gro_cb { /* Used in ipv6_gro_receive() and foo-over-udp */ u16 proto; - /* jiffies when first packet was created/queued */ - unsigned long age; - /* Used in napi_gro_cb::free */ #define NAPI_GRO_FREE 1 #define NAPI_GRO_FREE_STOLEN_HEAD 2 @@ -77,9 +86,6 @@ struct napi_gro_cb { /* used to support CHECKSUM_COMPLETE for tunneling protocols */ __wsum csum; - - /* used in skb_gro_receive() slow path */ - struct sk_buff *last; }; #define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb) diff --git a/include/net/inet_common.h b/include/net/inet_common.h index cec453c18f1d..a75333342c4e 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -31,8 +31,11 @@ int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags); int inet_accept(struct socket *sock, struct socket *newsock, int flags, bool kern); +void __inet_accept(struct socket *sock, struct socket *newsock, + struct sock *newsk); int inet_send_prepare(struct sock *sk); int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size); +void inet_splice_eof(struct socket *sock); ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags); int inet_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 8543e740891a..325ad893f624 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -13,6 +13,7 @@ struct fqdir { /* sysctls */ long high_thresh; + long low_thresh; int timeout; int max_dist; struct inet_frags *f; diff --git a/include/net/ip.h b/include/net/ip.h index c3fffaa92d6e..50d435855ae2 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -76,6 +76,7 @@ struct ipcm_cookie { __be32 addr; int oif; struct ip_options_rcu *opt; + __u8 protocol; __u8 ttl; __s16 tos; char priority; @@ -96,6 +97,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm, ipcm->sockc.tsflags = inet->sk.sk_tsflags; ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if); ipcm->addr = inet->inet_saddr; + ipcm->protocol = inet->inet_num; } #define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb)) @@ -220,8 +222,6 @@ int ip_append_data(struct sock *sk, struct flowi4 *fl4, unsigned int flags); int ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb); -ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, - int offset, size_t size, int flags); struct sk_buff *__ip_make_skb(struct sock *sk, struct flowi4 *fl4, struct sk_buff_head *queue, struct inet_cork *cork); @@ -242,14 +242,22 @@ static inline struct sk_buff *ip_finish_skb(struct sock *sk, struct flowi4 *fl4) return __ip_make_skb(sk, fl4, &sk->sk_write_queue, &inet_sk(sk)->cork.base); } -static inline __u8 get_rttos(struct ipcm_cookie* ipc, struct inet_sock *inet) +/* Get the route scope that should be used when sending a packet. */ +static inline u8 ip_sendmsg_scope(const struct inet_sock *inet, + const struct ipcm_cookie *ipc, + const struct msghdr *msg) { - return (ipc->tos != -1) ? RT_TOS(ipc->tos) : RT_TOS(inet->tos); + if (sock_flag(&inet->sk, SOCK_LOCALROUTE) || + msg->msg_flags & MSG_DONTROUTE || + (ipc->opt && ipc->opt->opt.is_strictroute)) + return RT_SCOPE_LINK; + + return RT_SCOPE_UNIVERSE; } -static inline __u8 get_rtconn_flags(struct ipcm_cookie* ipc, struct sock* sk) +static inline __u8 get_rttos(struct ipcm_cookie* ipc, struct inet_sock *inet) { - return (ipc->tos != -1) ? RT_CONN_FLAGS_TOS(sk, ipc->tos) : RT_CONN_FLAGS(sk); + return (ipc->tos != -1) ? RT_TOS(ipc->tos) : RT_TOS(inet->tos); } /* datagram.c */ @@ -280,7 +288,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, const struct ip_options *sopt, __be32 daddr, __be32 saddr, const struct ip_reply_arg *arg, - unsigned int len, u64 transmit_time); + unsigned int len, u64 transmit_time, u32 txhash); #define IP_INC_STATS(net, field) SNMP_INC_STATS64((net)->mib.ip_statistics, field) #define __IP_INC_STATS(net, field) __SNMP_INC_STATS64((net)->mib.ip_statistics, field) diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index cd386aa7c7cc..9eef19972845 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -347,10 +347,8 @@ struct mana_tx_qp { struct mana_ethtool_stats { u64 stop_queue; u64 wake_queue; - u64 tx_cqes; u64 tx_cqe_err; u64 tx_cqe_unknown_type; - u64 rx_cqes; u64 rx_coalesced_err; u64 rx_cqe_unknown_type; }; diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 3fa5774bddac..f6a8ecc6b1fa 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -180,7 +180,7 @@ struct pneigh_entry { netdevice_tracker dev_tracker; u32 flags; u8 protocol; - u8 key[]; + u32 key[]; }; /* diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index 0855b60fba17..cf0d81be5a96 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -26,6 +26,15 @@ struct nf_conntrack_expect { struct nf_conntrack_tuple tuple; struct nf_conntrack_tuple_mask mask; + /* Usage count. */ + refcount_t use; + + /* Flags */ + unsigned int flags; + + /* Expectation class */ + unsigned int class; + /* Function to call after setup and insertion */ void (*expectfn)(struct nf_conn *new, struct nf_conntrack_expect *this); @@ -39,15 +48,6 @@ struct nf_conntrack_expect { /* Timer function; deletes the expectation. */ struct timer_list timeout; - /* Usage count. */ - refcount_t use; - - /* Flags */ - unsigned int flags; - - /* Expectation class */ - unsigned int class; - #if IS_ENABLED(CONFIG_NF_NAT) union nf_inet_addr saved_addr; /* This is the original per-proto part, used to map the diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index ebb28ec5b6fa..546fc4a9b939 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -263,8 +263,8 @@ nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table, up_write(&flow_table->flow_block_lock); } -int flow_offload_route_init(struct flow_offload *flow, - const struct nf_flow_route *route); +void flow_offload_route_init(struct flow_offload *flow, + const struct nf_flow_route *route); int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow); void flow_offload_refresh(struct nf_flowtable *flow_table, diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 3cceb3e9320b..5f2cfd84570a 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -53,7 +53,7 @@ struct netns_sysctl_ipv6 { int seg6_flowlabel; u32 ioam6_id; u64 ioam6_id_wide; - bool skip_notify_on_dev_down; + u8 skip_notify_on_dev_down; u8 fib_notify_on_flag_change; u8 icmpv6_error_anycast_as_unicast; }; diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 9fa291a04621..2b12725de9c0 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -497,29 +497,6 @@ static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh) return NULL; } -/* Variant of nexthop_fib6_nh(). - * Caller should either hold rcu_read_lock(), or RTNL. - */ -static inline struct fib6_nh *nexthop_fib6_nh_bh(struct nexthop *nh) -{ - struct nh_info *nhi; - - if (nh->is_group) { - struct nh_group *nh_grp; - - nh_grp = rcu_dereference_rtnl(nh->nh_grp); - nh = nexthop_mpath_select(nh_grp, 0); - if (!nh) - return NULL; - } - - nhi = rcu_dereference_rtnl(nh->nh_info); - if (nhi->family == AF_INET6) - return &nhi->fib6_nh; - - return NULL; -} - static inline struct net_device *fib6_info_nh_dev(struct fib6_info *f6i) { struct fib6_nh *fib6_nh; diff --git a/include/net/page_pool.h b/include/net/page_pool.h index c8ec2f34722b..126f9e294389 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -399,22 +399,4 @@ static inline void page_pool_nid_changed(struct page_pool *pool, int new_nid) page_pool_update_nid(pool, new_nid); } -static inline void page_pool_ring_lock(struct page_pool *pool) - __acquires(&pool->ring.producer_lock) -{ - if (in_softirq()) - spin_lock(&pool->ring.producer_lock); - else - spin_lock_bh(&pool->ring.producer_lock); -} - -static inline void page_pool_ring_unlock(struct page_pool *pool) - __releases(&pool->ring.producer_lock) -{ - if (in_softirq()) - spin_unlock(&pool->ring.producer_lock); - else - spin_unlock_bh(&pool->ring.producer_lock); -} - #endif /* _NET_PAGE_POOL_H */ diff --git a/include/net/ping.h b/include/net/ping.h index 9233ad3de0ad..bc7779262e60 100644 --- a/include/net/ping.h +++ b/include/net/ping.h @@ -16,11 +16,7 @@ #define PING_HTABLE_SIZE 64 #define PING_HTABLE_MASK (PING_HTABLE_SIZE-1) -/* - * gid_t is either uint or ushort. We want to pass it to - * proc_dointvec_minmax(), so it must not be larger than MAX_INT - */ -#define GID_T_MAX (((gid_t)~0U) >> 1) +#define GID_T_MAX (((gid_t)~0U) - 1) /* Compatibility glue so we can support IPv6 when it's compiled as a module */ struct pingv6_ops { diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index b3b5b0b62f16..a2ea45c7b53e 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -868,6 +868,7 @@ struct tc_htb_qopt_offload { u16 qid; u64 rate; u64 ceil; + u8 prio; }; #define TC_HTB_CLASSID_ROOT U32_MAX diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index f436688b6efc..518febb91c9f 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -127,6 +127,8 @@ static inline void qdisc_run(struct Qdisc *q) } } +extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1]; + /* Calculate maximal size of packet seen by hard_start_xmit routine of this device. */ @@ -185,6 +187,32 @@ struct tc_taprio_caps { bool broken_mqprio:1; }; +enum tc_taprio_qopt_cmd { + TAPRIO_CMD_REPLACE, + TAPRIO_CMD_DESTROY, + TAPRIO_CMD_STATS, + TAPRIO_CMD_TC_STATS, +}; + +/** + * struct tc_taprio_qopt_stats - IEEE 802.1Qbv statistics + * @window_drops: Frames that were dropped because they were too large to be + * transmitted in any of the allotted time windows (open gates) for their + * traffic class. + * @tx_overruns: Frames still being transmitted by the MAC after the + * transmission gate associated with their traffic class has closed. + * Equivalent to `12.29.1.1.2 TransmissionOverrun` from 802.1Q-2018. + */ +struct tc_taprio_qopt_stats { + u64 window_drops; + u64 tx_overruns; +}; + +struct tc_taprio_qopt_tc_stats { + int tc; + struct tc_taprio_qopt_stats stats; +}; + struct tc_taprio_sched_entry { u8 command; /* TC_TAPRIO_CMD_* */ @@ -194,16 +222,26 @@ struct tc_taprio_sched_entry { }; struct tc_taprio_qopt_offload { - struct tc_mqprio_qopt_offload mqprio; - struct netlink_ext_ack *extack; - u8 enable; - ktime_t base_time; - u64 cycle_time; - u64 cycle_time_extension; - u32 max_sdu[TC_MAX_QUEUE]; - - size_t num_entries; - struct tc_taprio_sched_entry entries[]; + enum tc_taprio_qopt_cmd cmd; + + union { + /* TAPRIO_CMD_STATS */ + struct tc_taprio_qopt_stats stats; + /* TAPRIO_CMD_TC_STATS */ + struct tc_taprio_qopt_tc_stats tc_stats; + /* TAPRIO_CMD_REPLACE */ + struct { + struct tc_mqprio_qopt_offload mqprio; + struct netlink_ext_ack *extack; + ktime_t base_time; + u64 cycle_time; + u64 cycle_time_extension; + u32 max_sdu[TC_MAX_QUEUE]; + + size_t num_entries; + struct tc_taprio_sched_entry entries[]; + }; + }; }; #if IS_ENABLED(CONFIG_NET_SCH_TAPRIO) diff --git a/include/net/route.h b/include/net/route.h index bcc367cf3aa2..5a5c726472bd 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -321,8 +321,7 @@ static inline struct rtable *ip_route_connect(struct flowi4 *fl4, __be32 dst, if (IS_ERR(rt)) return rt; ip_rt_put(rt); - flowi4_update_output(fl4, oif, fl4->flowi4_tos, fl4->daddr, - fl4->saddr); + flowi4_update_output(fl4, oif, fl4->daddr, fl4->saddr); } security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4)); return ip_route_output_flow(net, fl4, sk); @@ -337,8 +336,7 @@ static inline struct rtable *ip_route_newports(struct flowi4 *fl4, struct rtable fl4->fl4_dport = dport; fl4->fl4_sport = sport; ip_rt_put(rt); - flowi4_update_output(fl4, sk->sk_bound_dev_if, - RT_CONN_FLAGS(sk), fl4->daddr, + flowi4_update_output(fl4, sk->sk_bound_dev_if, fl4->daddr, fl4->saddr); security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4)); return ip_route_output_flow(sock_net(sk), fl4, sk); diff --git a/include/net/rpl.h b/include/net/rpl.h index 308ef0a05cae..30fe780d1e7c 100644 --- a/include/net/rpl.h +++ b/include/net/rpl.h @@ -23,9 +23,6 @@ static inline int rpl_init(void) static inline void rpl_exit(void) {} #endif -/* Worst decompression memory usage ipv6 address (16) + pad 7 */ -#define IPV6_RPL_SRH_WORST_SWAP_SIZE (sizeof(struct in6_addr) + 7) - size_t ipv6_rpl_srh_size(unsigned char n, unsigned char cmpri, unsigned char cmpre); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index fab5ba3e61b7..27271f2b37cb 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -545,7 +545,7 @@ static inline struct Qdisc *qdisc_root_bh(const struct Qdisc *qdisc) static inline struct Qdisc *qdisc_root_sleeping(const struct Qdisc *qdisc) { - return qdisc->dev_queue->qdisc_sleeping; + return rcu_dereference_rtnl(qdisc->dev_queue->qdisc_sleeping); } static inline spinlock_t *qdisc_root_sleeping_lock(const struct Qdisc *qdisc) @@ -754,7 +754,9 @@ static inline bool qdisc_tx_changing(const struct net_device *dev) for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - if (rcu_access_pointer(txq->qdisc) != txq->qdisc_sleeping) + + if (rcu_access_pointer(txq->qdisc) != + rcu_access_pointer(txq->qdisc_sleeping)) return true; } return false; diff --git a/include/net/sock.h b/include/net/sock.h index 656ea89f60ff..2790133b4b76 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -336,6 +336,7 @@ struct sk_filter; * @sk_cgrp_data: cgroup data for this cgroup * @sk_memcg: this socket's memory cgroup association * @sk_write_pending: a write to stream socket waits to start + * @sk_wait_pending: number of threads blocked on this socket * @sk_state_change: callback to indicate change in the state of the sock * @sk_data_ready: callback to indicate there is data to be processed * @sk_write_space: callback to indicate there is bf sending space available @@ -428,6 +429,7 @@ struct sock { unsigned int sk_napi_id; #endif int sk_rcvbuf; + int sk_wait_pending; struct sk_filter __rcu *sk_filter; union { @@ -1150,8 +1152,12 @@ static inline void sock_rps_record_flow(const struct sock *sk) * OR an additional socket flag * [1] : sk_state and sk_prot are in the same cache line. */ - if (sk->sk_state == TCP_ESTABLISHED) - sock_rps_record_flow_hash(sk->sk_rxhash); + if (sk->sk_state == TCP_ESTABLISHED) { + /* This READ_ONCE() is paired with the WRITE_ONCE() + * from sock_rps_save_rxhash() and sock_rps_reset_rxhash(). + */ + sock_rps_record_flow_hash(READ_ONCE(sk->sk_rxhash)); + } } #endif } @@ -1160,20 +1166,25 @@ static inline void sock_rps_save_rxhash(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_RPS - if (unlikely(sk->sk_rxhash != skb->hash)) - sk->sk_rxhash = skb->hash; + /* The following WRITE_ONCE() is paired with the READ_ONCE() + * here, and another one in sock_rps_record_flow(). + */ + if (unlikely(READ_ONCE(sk->sk_rxhash) != skb->hash)) + WRITE_ONCE(sk->sk_rxhash, skb->hash); #endif } static inline void sock_rps_reset_rxhash(struct sock *sk) { #ifdef CONFIG_RPS - sk->sk_rxhash = 0; + /* Paired with READ_ONCE() in sock_rps_record_flow() */ + WRITE_ONCE(sk->sk_rxhash, 0); #endif } #define sk_wait_event(__sk, __timeo, __condition, __wait) \ ({ int __rc; \ + __sk->sk_wait_pending++; \ release_sock(__sk); \ __rc = __condition; \ if (!__rc) { \ @@ -1183,6 +1194,7 @@ static inline void sock_rps_reset_rxhash(struct sock *sk) } \ sched_annotate_sleep(); \ lock_sock(__sk); \ + __sk->sk_wait_pending--; \ __rc = __condition; \ __rc; \ }) @@ -1267,6 +1279,7 @@ struct proto { size_t len, int flags, int *addr_len); int (*sendpage)(struct sock *sk, struct page *page, int offset, size_t size, int flags); + void (*splice_eof)(struct socket *sock); int (*bind)(struct sock *sk, struct sockaddr *addr, int addr_len); int (*bind_add)(struct sock *sk, diff --git a/include/net/tcp.h b/include/net/tcp.h index 04a31643cda3..49611af31bb7 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -161,8 +161,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); #define MAX_TCP_KEEPCNT 127 #define MAX_TCP_SYNCNT 127 -#define TCP_SYNQ_INTERVAL (HZ/5) /* Period of SYNACK timer */ - #define TCP_PAWS_24DAYS (60 * 60 * 24 * 24) #define TCP_PAWS_MSL 60 /* Per-host timestamps are invalidated * after this time. It should be equal @@ -329,12 +327,11 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied, size_t size, struct ubuf_info *uarg); +void tcp_splice_eof(struct socket *sock); int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset, size_t size, int flags); -ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, - size_t size, int flags); int tcp_send_mss(struct sock *sk, int *size_goal, int flags); void tcp_push(struct sock *sk, int flags, int mss_now, int nonagle, int size_goal); @@ -632,6 +629,7 @@ void tcp_reset(struct sock *sk, struct sk_buff *skb); void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb); void tcp_fin(struct sock *sk); void tcp_check_space(struct sock *sk); +void tcp_sack_compress_send_ack(struct sock *sk); /* tcp_timer.c */ void tcp_init_xmit_timers(struct sock *); @@ -1470,6 +1468,8 @@ static inline void tcp_adjust_rcv_ssthresh(struct sock *sk) } void tcp_cleanup_rbuf(struct sock *sk, int copied); +void __tcp_cleanup_rbuf(struct sock *sk, int copied); + /* We provision sk_rcvbuf around 200% of sk_rcvlowat. * If 87.5 % (7/8) of the space has been consumed, we want to override @@ -2043,7 +2043,7 @@ INDIRECT_CALLABLE_DECLARE(int tcp4_gro_complete(struct sk_buff *skb, int thoff)) INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb)); INDIRECT_CALLABLE_DECLARE(int tcp6_gro_complete(struct sk_buff *skb, int thoff)); INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb)); -int tcp_gro_complete(struct sk_buff *skb); +void tcp_gro_complete(struct sk_buff *skb); void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr); @@ -2326,6 +2326,14 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore); void tcp_bpf_clone(const struct sock *sk, struct sock *newsk); #endif /* CONFIG_BPF_SYSCALL */ +#ifdef CONFIG_INET +void tcp_eat_skb(struct sock *sk, struct sk_buff *skb); +#else +static inline void tcp_eat_skb(struct sock *sk, struct sk_buff *skb) +{ +} +#endif + int tcp_bpf_sendmsg_redir(struct sock *sk, bool ingress, struct sk_msg *msg, u32 bytes, int flags); #endif /* CONFIG_NET_SOCK_MSG */ diff --git a/include/net/tls.h b/include/net/tls.h index 6056ce5a2aa5..b7d0f1e3058b 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -126,6 +126,7 @@ struct tls_strparser { u32 mark : 8; u32 stopped : 1; u32 copy_mode : 1; + u32 mixed_decrypted : 1; u32 msg_ready : 1; struct strp_msg stm; @@ -258,7 +259,7 @@ struct tls_context { struct scatterlist *partially_sent_record; u16 partially_sent_offset; - bool in_tcp_sendpages; + bool splicing_pages; bool pending_open_record_frags; struct mutex tx_lock; /* protects partially_sent_* fields and diff --git a/include/net/udp.h b/include/net/udp.h index de4b528522bb..4ed0b47c5582 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -278,6 +278,7 @@ int udp_get_port(struct sock *sk, unsigned short snum, int udp_err(struct sk_buff *, u32); int udp_abort(struct sock *sk, int err); int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); +void udp_splice_eof(struct socket *sock); int udp_push_pending_frames(struct sock *sk); void udp_flush_pending_frames(struct sock *sk); int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size); @@ -437,7 +438,6 @@ struct udp_seq_afinfo { struct udp_iter_state { struct seq_net_private p; int bucket; - struct udp_seq_afinfo *bpf_seq_afinfo; }; void *udp_seq_start(struct seq_file *seq, loff_t *pos); diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index d318c769b445..a8d7b8a3688a 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -180,7 +180,7 @@ static inline bool xp_desc_crosses_non_contig_pg(struct xsk_buff_pool *pool, if (likely(!cross_pg)) return false; - return pool->dma_pages_cnt && + return pool->dma_pages && !(pool->dma_pages[addr >> PAGE_SHIFT] & XSK_NEXT_PG_CONTIG_MASK); } diff --git a/include/sound/hda-mlink.h b/include/sound/hda-mlink.h index dbc47af08135..4f44f0bd5388 100644 --- a/include/sound/hda-mlink.h +++ b/include/sound/hda-mlink.h @@ -44,6 +44,9 @@ int hdac_bus_eml_sdw_power_down_unlocked(struct hdac_bus *bus, int sublink); int hdac_bus_eml_sdw_set_lsdiid(struct hdac_bus *bus, int sublink, int dev_num); +int hdac_bus_eml_sdw_map_stream_ch(struct hdac_bus *bus, int sublink, int y, + int channel_mask, int stream_id, int dir); + void hda_bus_ml_put_all(struct hdac_bus *bus); void hda_bus_ml_reset_losidv(struct hdac_bus *bus); int hda_bus_ml_resume(struct hdac_bus *bus); @@ -51,6 +54,7 @@ int hda_bus_ml_suspend(struct hdac_bus *bus); struct hdac_ext_link *hdac_bus_eml_ssp_get_hlink(struct hdac_bus *bus); struct hdac_ext_link *hdac_bus_eml_dmic_get_hlink(struct hdac_bus *bus); +struct hdac_ext_link *hdac_bus_eml_sdw_get_hlink(struct hdac_bus *bus); struct mutex *hdac_bus_eml_get_mutex(struct hdac_bus *bus, bool alt, int elid); @@ -144,6 +148,13 @@ hdac_bus_eml_sdw_power_down_unlocked(struct hdac_bus *bus, int sublink) { return static inline int hdac_bus_eml_sdw_set_lsdiid(struct hdac_bus *bus, int sublink, int dev_num) { return 0; } +static inline int +hdac_bus_eml_sdw_map_stream_ch(struct hdac_bus *bus, int sublink, int y, + int channel_mask, int stream_id, int dir) +{ + return 0; +} + static inline void hda_bus_ml_put_all(struct hdac_bus *bus) { } static inline void hda_bus_ml_reset_losidv(struct hdac_bus *bus) { } static inline int hda_bus_ml_resume(struct hdac_bus *bus) { return 0; } @@ -155,6 +166,9 @@ hdac_bus_eml_ssp_get_hlink(struct hdac_bus *bus) { return NULL; } static inline struct hdac_ext_link * hdac_bus_eml_dmic_get_hlink(struct hdac_bus *bus) { return NULL; } +static inline struct hdac_ext_link * +hdac_bus_eml_sdw_get_hlink(struct hdac_bus *bus) { return NULL; } + static inline struct mutex * hdac_bus_eml_get_mutex(struct hdac_bus *bus, bool alt, int elid) { return NULL; } diff --git a/include/sound/soc-acpi.h b/include/sound/soc-acpi.h index b38fd25c5729..528279056b3a 100644 --- a/include/sound/soc-acpi.h +++ b/include/sound/soc-acpi.h @@ -170,6 +170,7 @@ struct snd_soc_acpi_link_adr { /* Descriptor for SST ASoC machine driver */ struct snd_soc_acpi_mach { u8 id[ACPI_ID_LEN]; + const char *uid; const struct snd_soc_acpi_codecs *comp_ids; const u32 link_mask; const struct snd_soc_acpi_link_adr *links; diff --git a/include/sound/soc-dpcm.h b/include/sound/soc-dpcm.h index 4d6ac7699833..ebd24753dd00 100644 --- a/include/sound/soc-dpcm.h +++ b/include/sound/soc-dpcm.h @@ -122,6 +122,10 @@ int snd_soc_dpcm_can_be_free_stop(struct snd_soc_pcm_runtime *fe, int snd_soc_dpcm_can_be_params(struct snd_soc_pcm_runtime *fe, struct snd_soc_pcm_runtime *be, int stream); +/* can this BE perform prepare */ +int snd_soc_dpcm_can_be_prepared(struct snd_soc_pcm_runtime *fe, + struct snd_soc_pcm_runtime *be, int stream); + /* is the current PCM operation for this FE ? */ int snd_soc_dpcm_fe_can_update(struct snd_soc_pcm_runtime *fe, int stream); diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h index 229118156a1f..4c15420e8965 100644 --- a/include/target/iscsi/iscsi_target_core.h +++ b/include/target/iscsi/iscsi_target_core.h @@ -562,12 +562,13 @@ struct iscsit_conn { #define LOGIN_FLAGS_READ_ACTIVE 2 #define LOGIN_FLAGS_WRITE_ACTIVE 3 #define LOGIN_FLAGS_CLOSED 4 +#define LOGIN_FLAGS_WORKER_RUNNING 5 unsigned long login_flags; struct delayed_work login_work; struct iscsi_login *login; struct timer_list nopin_timer; struct timer_list nopin_response_timer; - struct timer_list transport_timer; + struct timer_list login_timer; struct task_struct *login_kworker; /* Spinlock used for add/deleting cmd's from conn_cmd_list */ spinlock_t cmd_lock; @@ -576,6 +577,8 @@ struct iscsit_conn { spinlock_t nopin_timer_lock; spinlock_t response_queue_lock; spinlock_t state_lock; + spinlock_t login_timer_lock; + spinlock_t login_worker_lock; /* libcrypto RX and TX contexts for crc32c */ struct ahash_request *conn_rx_hash; struct ahash_request *conn_tx_hash; @@ -792,7 +795,6 @@ struct iscsi_np { enum np_thread_state_table np_thread_state; bool enabled; atomic_t np_reset_count; - enum iscsi_timer_flags_table np_login_timer_flags; u32 np_exports; enum np_flags_table np_flags; spinlock_t np_thread_lock; @@ -800,7 +802,6 @@ struct iscsi_np { struct socket *np_socket; struct sockaddr_storage np_sockaddr; struct task_struct *np_thread; - struct timer_list np_login_timer; void *np_context; struct iscsit_transport *np_transport; struct list_head np_list; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 1bb11a6ee667..6961a7b70028 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1035,6 +1035,7 @@ enum bpf_attach_type { BPF_TRACE_KPROBE_MULTI, BPF_LSM_CGROUP, BPF_STRUCT_OPS, + BPF_NETFILTER, __MAX_BPF_ATTACH_TYPE }; @@ -1272,6 +1273,9 @@ enum { /* Create a map that will be registered/unregesitered by the backed bpf_link */ BPF_F_LINK = (1U << 13), + +/* Get path from provided FD in BPF_OBJ_PIN/BPF_OBJ_GET commands */ + BPF_F_PATH_FD = (1U << 14), }; /* Flags for BPF_PROG_QUERY. */ @@ -1420,6 +1424,13 @@ union bpf_attr { __aligned_u64 pathname; __u32 bpf_fd; __u32 file_flags; + /* Same as dirfd in openat() syscall; see openat(2) + * manpage for details of path FD and pathname semantics; + * path_fd should accompanied by BPF_F_PATH_FD flag set in + * file_flags field, otherwise it should be set to zero; + * if BPF_F_PATH_FD flag is not set, AT_FDCWD is assumed. + */ + __s32 path_fd; }; struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */ diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index 4b7f2df66b99..e682ab628dfa 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -163,6 +163,7 @@ struct in_addr { #define IP_MULTICAST_ALL 49 #define IP_UNICAST_IF 50 #define IP_LOCAL_PORT_RANGE 51 +#define IP_PROTOCOL 52 #define MCAST_EXCLUDE 0 #define MCAST_INCLUDE 1 diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h index 256b463e47a6..b826598d1e94 100644 --- a/include/uapi/linux/mdio.h +++ b/include/uapi/linux/mdio.h @@ -231,6 +231,30 @@ #define MDIO_PMA_EXTABLE_BT1 0x0800 /* BASE-T1 ability */ #define MDIO_PMA_EXTABLE_NBT 0x4000 /* 2.5/5GBASE-T ability */ +/* AN Clause 73 linkword */ +#define MDIO_AN_C73_0_S_MASK GENMASK(4, 0) +#define MDIO_AN_C73_0_E_MASK GENMASK(9, 5) +#define MDIO_AN_C73_0_PAUSE BIT(10) +#define MDIO_AN_C73_0_ASM_DIR BIT(11) +#define MDIO_AN_C73_0_C2 BIT(12) +#define MDIO_AN_C73_0_RF BIT(13) +#define MDIO_AN_C73_0_ACK BIT(14) +#define MDIO_AN_C73_0_NP BIT(15) +#define MDIO_AN_C73_1_T_MASK GENMASK(4, 0) +#define MDIO_AN_C73_1_1000BASE_KX BIT(5) +#define MDIO_AN_C73_1_10GBASE_KX4 BIT(6) +#define MDIO_AN_C73_1_10GBASE_KR BIT(7) +#define MDIO_AN_C73_1_40GBASE_KR4 BIT(8) +#define MDIO_AN_C73_1_40GBASE_CR4 BIT(9) +#define MDIO_AN_C73_1_100GBASE_CR10 BIT(10) +#define MDIO_AN_C73_1_100GBASE_KP4 BIT(11) +#define MDIO_AN_C73_1_100GBASE_KR4 BIT(12) +#define MDIO_AN_C73_1_100GBASE_CR4 BIT(13) +#define MDIO_AN_C73_1_25GBASE_R_S BIT(14) +#define MDIO_AN_C73_1_25GBASE_R BIT(15) +#define MDIO_AN_C73_2_2500BASE_KX BIT(0) +#define MDIO_AN_C73_2_5GBASE_KR BIT(1) + /* PHY XGXS lane state register. */ #define MDIO_PHYXS_LNSTAT_SYNC0 0x0001 #define MDIO_PHYXS_LNSTAT_SYNC1 0x0002 diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index c4d4d8e42dc8..e059dc2644df 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -859,12 +859,14 @@ enum nft_exthdr_flags { * @NFT_EXTHDR_OP_TCP: match against tcp options * @NFT_EXTHDR_OP_IPV4: match against ipv4 options * @NFT_EXTHDR_OP_SCTP: match against sctp chunks + * @NFT_EXTHDR_OP_DCCP: match against dccp otions */ enum nft_exthdr_op { NFT_EXTHDR_OP_IPV6, NFT_EXTHDR_OP_TCPOPT, NFT_EXTHDR_OP_IPV4, NFT_EXTHDR_OP_SCTP, + NFT_EXTHDR_OP_DCCP, __NFT_EXTHDR_OP_MAX }; #define NFT_EXTHDR_OP_MAX (__NFT_EXTHDR_OP_MAX - 1) diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 648a82f32666..00933dda7b10 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -594,6 +594,8 @@ enum { TCA_FLOWER_KEY_L2TPV3_SID, /* be32 */ + TCA_FLOWER_L2_MISS, /* u8 */ + __TCA_FLOWER_MAX, }; diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 51a7addc56c6..00f6ff0aff1f 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -1260,6 +1260,16 @@ enum { }; enum { + TCA_TAPRIO_OFFLOAD_STATS_PAD = 1, /* u64 */ + TCA_TAPRIO_OFFLOAD_STATS_WINDOW_DROPS, /* u64 */ + TCA_TAPRIO_OFFLOAD_STATS_TX_OVERRUNS, /* u64 */ + + /* add new constants above here */ + __TCA_TAPRIO_OFFLOAD_STATS_CNT, + TCA_TAPRIO_OFFLOAD_STATS_MAX = (__TCA_TAPRIO_OFFLOAD_STATS_CNT - 1) +}; + +enum { TCA_TAPRIO_ATTR_UNSPEC, TCA_TAPRIO_ATTR_PRIOMAP, /* struct tc_mqprio_qopt */ TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST, /* nested of entry */ diff --git a/include/uapi/sound/skl-tplg-interface.h b/include/uapi/sound/skl-tplg-interface.h index f29899b179a6..4bf9c4f9add8 100644 --- a/include/uapi/sound/skl-tplg-interface.h +++ b/include/uapi/sound/skl-tplg-interface.h @@ -66,7 +66,8 @@ enum skl_ch_cfg { SKL_CH_CFG_DUAL_MONO = 9, SKL_CH_CFG_I2S_DUAL_STEREO_0 = 10, SKL_CH_CFG_I2S_DUAL_STEREO_1 = 11, - SKL_CH_CFG_4_CHANNEL = 12, + SKL_CH_CFG_7_1 = 12, + SKL_CH_CFG_4_CHANNEL = SKL_CH_CFG_7_1, SKL_CH_CFG_INVALID }; diff --git a/include/uapi/sound/sof/tokens.h b/include/uapi/sound/sof/tokens.h index bbc37877aaff..e9ec7e4eb982 100644 --- a/include/uapi/sound/sof/tokens.h +++ b/include/uapi/sound/sof/tokens.h @@ -183,7 +183,7 @@ #define SOF_TKN_CAVS_AUDIO_FORMAT_IN_INTERLEAVING_STYLE 1906 #define SOF_TKN_CAVS_AUDIO_FORMAT_IN_FMT_CFG 1907 #define SOF_TKN_CAVS_AUDIO_FORMAT_IN_SAMPLE_TYPE 1908 -#define SOF_TKN_CAVS_AUDIO_FORMAT_PIN_INDEX 1909 +#define SOF_TKN_CAVS_AUDIO_FORMAT_INPUT_PIN_INDEX 1909 /* intentional token numbering discontinuity, reserved for future use */ #define SOF_TKN_CAVS_AUDIO_FORMAT_OUT_RATE 1930 #define SOF_TKN_CAVS_AUDIO_FORMAT_OUT_BIT_DEPTH 1931 @@ -194,6 +194,7 @@ #define SOF_TKN_CAVS_AUDIO_FORMAT_OUT_INTERLEAVING_STYLE 1936 #define SOF_TKN_CAVS_AUDIO_FORMAT_OUT_FMT_CFG 1937 #define SOF_TKN_CAVS_AUDIO_FORMAT_OUT_SAMPLE_TYPE 1938 +#define SOF_TKN_CAVS_AUDIO_FORMAT_OUTPUT_PIN_INDEX 1939 /* intentional token numbering discontinuity, reserved for future use */ #define SOF_TKN_CAVS_AUDIO_FORMAT_IBS 1970 #define SOF_TKN_CAVS_AUDIO_FORMAT_OBS 1971 diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index f7553293ba98..df1d04f7a542 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -1133,7 +1133,7 @@ static inline size_t ufshcd_sg_entry_size(const struct ufs_hba *hba) ({ (void)(hba); BUILD_BUG_ON(sg_entry_size != sizeof(struct ufshcd_sg_entry)); }) #endif -static inline size_t sizeof_utp_transfer_cmd_desc(const struct ufs_hba *hba) +static inline size_t ufshcd_get_ucd_size(const struct ufs_hba *hba) { return sizeof(struct utp_transfer_cmd_desc) + SG_ALL * ufshcd_sg_entry_size(hba); } diff --git a/io_uring/epoll.c b/io_uring/epoll.c index 9aa74d2c80bc..89bff2068a19 100644 --- a/io_uring/epoll.c +++ b/io_uring/epoll.c @@ -25,10 +25,6 @@ int io_epoll_ctl_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_epoll *epoll = io_kiocb_to_cmd(req, struct io_epoll); - pr_warn_once("%s: epoll_ctl support in io_uring is deprecated and will " - "be removed in a future Linux kernel version.\n", - current->comm); - if (sqe->buf_index || sqe->splice_fd_in) return -EINVAL; diff --git a/io_uring/net.c b/io_uring/net.c index 89e839013837..f7cbb3c7a575 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -389,6 +389,7 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags) if (flags & MSG_WAITALL) min_ret = iov_iter_count(&msg.msg_iter); + flags &= ~MSG_INTERNAL_SENDMSG_FLAGS; msg.msg_flags = flags; ret = sock_sendmsg(sock, &msg); if (ret < min_ret) { @@ -1136,6 +1137,7 @@ int io_send_zc(struct io_kiocb *req, unsigned int issue_flags) msg_flags |= MSG_DONTWAIT; if (msg_flags & MSG_WAITALL) min_ret = iov_iter_count(&msg.msg_iter); + msg_flags &= ~MSG_INTERNAL_SENDMSG_FLAGS; msg.msg_flags = msg_flags; msg.msg_ubuf = &io_notif_to_data(zc->notif)->uarg; diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c index 9db4bc1f521a..5e329e3cd470 100644 --- a/io_uring/sqpoll.c +++ b/io_uring/sqpoll.c @@ -255,9 +255,13 @@ static int io_sq_thread(void *data) sqt_spin = true; if (sqt_spin || !time_after(jiffies, timeout)) { - cond_resched(); if (sqt_spin) timeout = jiffies + sqd->sq_thread_idle; + if (unlikely(need_resched())) { + mutex_unlock(&sqd->lock); + cond_resched(); + mutex_lock(&sqd->lock); + } continue; } diff --git a/kernel/bpf/bpf_lru_list.c b/kernel/bpf/bpf_lru_list.c index d99e89f113c4..3dabdd137d10 100644 --- a/kernel/bpf/bpf_lru_list.c +++ b/kernel/bpf/bpf_lru_list.c @@ -41,7 +41,12 @@ static struct list_head *local_pending_list(struct bpf_lru_locallist *loc_l) /* bpf_lru_node helpers */ static bool bpf_lru_node_is_ref(const struct bpf_lru_node *node) { - return node->ref; + return READ_ONCE(node->ref); +} + +static void bpf_lru_node_clear_ref(struct bpf_lru_node *node) +{ + WRITE_ONCE(node->ref, 0); } static void bpf_lru_list_count_inc(struct bpf_lru_list *l, @@ -89,7 +94,7 @@ static void __bpf_lru_node_move_in(struct bpf_lru_list *l, bpf_lru_list_count_inc(l, tgt_type); node->type = tgt_type; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_move(&node->list, &l->lists[tgt_type]); } @@ -110,7 +115,7 @@ static void __bpf_lru_node_move(struct bpf_lru_list *l, bpf_lru_list_count_inc(l, tgt_type); node->type = tgt_type; } - node->ref = 0; + bpf_lru_node_clear_ref(node); /* If the moving node is the next_inactive_rotation candidate, * move the next_inactive_rotation pointer also. @@ -353,7 +358,7 @@ static void __local_list_add_pending(struct bpf_lru *lru, *(u32 *)((void *)node + lru->hash_offset) = hash; node->cpu = cpu; node->type = BPF_LRU_LOCAL_LIST_T_PENDING; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_add(&node->list, local_pending_list(loc_l)); } @@ -419,7 +424,7 @@ static struct bpf_lru_node *bpf_percpu_lru_pop_free(struct bpf_lru *lru, if (!list_empty(free_list)) { node = list_first_entry(free_list, struct bpf_lru_node, list); *(u32 *)((void *)node + lru->hash_offset) = hash; - node->ref = 0; + bpf_lru_node_clear_ref(node); __bpf_lru_node_move(l, node, BPF_LRU_LIST_T_INACTIVE); } @@ -522,7 +527,7 @@ static void bpf_common_lru_push_free(struct bpf_lru *lru, } node->type = BPF_LRU_LOCAL_LIST_T_FREE; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_move(&node->list, local_free_list(loc_l)); raw_spin_unlock_irqrestore(&loc_l->lock, flags); @@ -568,7 +573,7 @@ static void bpf_common_lru_populate(struct bpf_lru *lru, void *buf, node = (struct bpf_lru_node *)(buf + node_offset); node->type = BPF_LRU_LIST_T_FREE; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]); buf += elem_size; } @@ -594,7 +599,7 @@ again: node = (struct bpf_lru_node *)(buf + node_offset); node->cpu = cpu; node->type = BPF_LRU_LIST_T_FREE; - node->ref = 0; + bpf_lru_node_clear_ref(node); list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]); i++; buf += elem_size; diff --git a/kernel/bpf/bpf_lru_list.h b/kernel/bpf/bpf_lru_list.h index 4ea227c9c1ad..8f3c8b2b4490 100644 --- a/kernel/bpf/bpf_lru_list.h +++ b/kernel/bpf/bpf_lru_list.h @@ -64,11 +64,8 @@ struct bpf_lru { static inline void bpf_lru_node_set_ref(struct bpf_lru_node *node) { - /* ref is an approximation on access frequency. It does not - * have to be very accurate. Hence, no protection is used. - */ - if (!node->ref) - node->ref = 1; + if (!READ_ONCE(node->ref)) + WRITE_ONCE(node->ref, 1); } int bpf_lru_init(struct bpf_lru *lru, bool percpu, u32 hash_offset, diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 6b682b8e4b50..947f0b83bfad 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -222,10 +222,17 @@ enum btf_kfunc_hook { enum { BTF_KFUNC_SET_MAX_CNT = 256, BTF_DTOR_KFUNC_MAX_CNT = 256, + BTF_KFUNC_FILTER_MAX_CNT = 16, +}; + +struct btf_kfunc_hook_filter { + btf_kfunc_filter_t filters[BTF_KFUNC_FILTER_MAX_CNT]; + u32 nr_filters; }; struct btf_kfunc_set_tab { struct btf_id_set8 *sets[BTF_KFUNC_HOOK_MAX]; + struct btf_kfunc_hook_filter hook_filters[BTF_KFUNC_HOOK_MAX]; }; struct btf_id_dtor_kfunc_tab { @@ -7669,9 +7676,12 @@ static int btf_check_kfunc_protos(struct btf *btf, u32 func_id, u32 func_flags) /* Kernel Function (kfunc) BTF ID set registration API */ static int btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook, - struct btf_id_set8 *add_set) + const struct btf_kfunc_id_set *kset) { + struct btf_kfunc_hook_filter *hook_filter; + struct btf_id_set8 *add_set = kset->set; bool vmlinux_set = !btf_is_module(btf); + bool add_filter = !!kset->filter; struct btf_kfunc_set_tab *tab; struct btf_id_set8 *set; u32 set_cnt; @@ -7686,6 +7696,24 @@ static int btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook, return 0; tab = btf->kfunc_set_tab; + + if (tab && add_filter) { + u32 i; + + hook_filter = &tab->hook_filters[hook]; + for (i = 0; i < hook_filter->nr_filters; i++) { + if (hook_filter->filters[i] == kset->filter) { + add_filter = false; + break; + } + } + + if (add_filter && hook_filter->nr_filters == BTF_KFUNC_FILTER_MAX_CNT) { + ret = -E2BIG; + goto end; + } + } + if (!tab) { tab = kzalloc(sizeof(*tab), GFP_KERNEL | __GFP_NOWARN); if (!tab) @@ -7708,7 +7736,7 @@ static int btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook, */ if (!vmlinux_set) { tab->sets[hook] = add_set; - return 0; + goto do_add_filter; } /* In case of vmlinux sets, there may be more than one set being @@ -7750,6 +7778,11 @@ static int btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook, sort(set->pairs, set->cnt, sizeof(set->pairs[0]), btf_id_cmp_func, NULL); +do_add_filter: + if (add_filter) { + hook_filter = &tab->hook_filters[hook]; + hook_filter->filters[hook_filter->nr_filters++] = kset->filter; + } return 0; end: btf_free_kfunc_set_tab(btf); @@ -7758,15 +7791,22 @@ end: static u32 *__btf_kfunc_id_set_contains(const struct btf *btf, enum btf_kfunc_hook hook, - u32 kfunc_btf_id) + u32 kfunc_btf_id, + const struct bpf_prog *prog) { + struct btf_kfunc_hook_filter *hook_filter; struct btf_id_set8 *set; - u32 *id; + u32 *id, i; if (hook >= BTF_KFUNC_HOOK_MAX) return NULL; if (!btf->kfunc_set_tab) return NULL; + hook_filter = &btf->kfunc_set_tab->hook_filters[hook]; + for (i = 0; i < hook_filter->nr_filters; i++) { + if (hook_filter->filters[i](prog, kfunc_btf_id)) + return NULL; + } set = btf->kfunc_set_tab->sets[hook]; if (!set) return NULL; @@ -7821,23 +7861,25 @@ static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type) * protection for looking up a well-formed btf->kfunc_set_tab. */ u32 *btf_kfunc_id_set_contains(const struct btf *btf, - enum bpf_prog_type prog_type, - u32 kfunc_btf_id) + u32 kfunc_btf_id, + const struct bpf_prog *prog) { + enum bpf_prog_type prog_type = resolve_prog_type(prog); enum btf_kfunc_hook hook; u32 *kfunc_flags; - kfunc_flags = __btf_kfunc_id_set_contains(btf, BTF_KFUNC_HOOK_COMMON, kfunc_btf_id); + kfunc_flags = __btf_kfunc_id_set_contains(btf, BTF_KFUNC_HOOK_COMMON, kfunc_btf_id, prog); if (kfunc_flags) return kfunc_flags; hook = bpf_prog_type_to_kfunc_hook(prog_type); - return __btf_kfunc_id_set_contains(btf, hook, kfunc_btf_id); + return __btf_kfunc_id_set_contains(btf, hook, kfunc_btf_id, prog); } -u32 *btf_kfunc_is_modify_return(const struct btf *btf, u32 kfunc_btf_id) +u32 *btf_kfunc_is_modify_return(const struct btf *btf, u32 kfunc_btf_id, + const struct bpf_prog *prog) { - return __btf_kfunc_id_set_contains(btf, BTF_KFUNC_HOOK_FMODRET, kfunc_btf_id); + return __btf_kfunc_id_set_contains(btf, BTF_KFUNC_HOOK_FMODRET, kfunc_btf_id, prog); } static int __register_btf_kfunc_id_set(enum btf_kfunc_hook hook, @@ -7868,7 +7910,8 @@ static int __register_btf_kfunc_id_set(enum btf_kfunc_hook hook, goto err_out; } - ret = btf_populate_kfunc_set(btf, hook, kset->set); + ret = btf_populate_kfunc_set(btf, hook, kset); + err_out: btf_put(btf); return ret; diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 517b6a5928cc..5b2741aa0d9b 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1826,6 +1826,12 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, ret = 1; } else if (ctx.optlen > max_optlen || ctx.optlen < -1) { /* optlen is out of bounds */ + if (*optlen > PAGE_SIZE && ctx.optlen >= 0) { + pr_info_once("bpf setsockopt: ignoring program buffer with optlen=%d (max_optlen=%d)\n", + ctx.optlen, max_optlen); + ret = 0; + goto out; + } ret = -EFAULT; } else { /* optlen within bounds, run kernel handler */ @@ -1881,8 +1887,10 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, .optname = optname, .current_task = current, }; + int orig_optlen; int ret; + orig_optlen = max_optlen; ctx.optlen = max_optlen; max_optlen = sockopt_alloc_buf(&ctx, max_optlen, &buf); if (max_optlen < 0) @@ -1905,6 +1913,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, ret = -EFAULT; goto out; } + orig_optlen = ctx.optlen; if (copy_from_user(ctx.optval, optval, min(ctx.optlen, max_optlen)) != 0) { @@ -1922,6 +1931,12 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, goto out; if (optval && (ctx.optlen > max_optlen || ctx.optlen < 0)) { + if (orig_optlen > PAGE_SIZE && ctx.optlen >= 0) { + pr_info_once("bpf getsockopt: ignoring program buffer with optlen=%d (max_optlen=%d)\n", + ctx.optlen, max_optlen); + ret = retval; + goto out; + } ret = -EFAULT; goto out; } diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 00c253b84bf5..9901efee4339 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -1215,7 +1215,7 @@ static long htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value ret = htab_lock_bucket(htab, b, hash, &flags); if (ret) - return ret; + goto err_lock_bucket; l_old = lookup_elem_raw(head, hash, key, key_size); @@ -1236,6 +1236,7 @@ static long htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value err: htab_unlock_bucket(htab, b, hash, flags); +err_lock_bucket: if (ret) htab_lru_push_free(htab, l_new); else if (l_old) @@ -1338,7 +1339,7 @@ static long __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, ret = htab_lock_bucket(htab, b, hash, &flags); if (ret) - return ret; + goto err_lock_bucket; l_old = lookup_elem_raw(head, hash, key, key_size); @@ -1361,6 +1362,7 @@ static long __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, ret = 0; err: htab_unlock_bucket(htab, b, hash, flags); +err_lock_bucket: if (l_new) bpf_lru_push_free(&htab->lru, &l_new->lru_node); return ret; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 8d368fa353f9..4ef4c4f8a355 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1423,7 +1423,7 @@ static const struct bpf_func_proto bpf_kptr_xchg_proto = { #define DYNPTR_SIZE_MASK 0xFFFFFF #define DYNPTR_RDONLY_BIT BIT(31) -static bool bpf_dynptr_is_rdonly(const struct bpf_dynptr_kern *ptr) +static bool __bpf_dynptr_is_rdonly(const struct bpf_dynptr_kern *ptr) { return ptr->size & DYNPTR_RDONLY_BIT; } @@ -1443,11 +1443,18 @@ static enum bpf_dynptr_type bpf_dynptr_get_type(const struct bpf_dynptr_kern *pt return (ptr->size & ~(DYNPTR_RDONLY_BIT)) >> DYNPTR_TYPE_SHIFT; } -u32 bpf_dynptr_get_size(const struct bpf_dynptr_kern *ptr) +u32 __bpf_dynptr_size(const struct bpf_dynptr_kern *ptr) { return ptr->size & DYNPTR_SIZE_MASK; } +static void bpf_dynptr_set_size(struct bpf_dynptr_kern *ptr, u32 new_size) +{ + u32 metadata = ptr->size & ~DYNPTR_SIZE_MASK; + + ptr->size = new_size | metadata; +} + int bpf_dynptr_check_size(u32 size) { return size > DYNPTR_MAX_SIZE ? -E2BIG : 0; @@ -1469,7 +1476,7 @@ void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr) static int bpf_dynptr_check_off_len(const struct bpf_dynptr_kern *ptr, u32 offset, u32 len) { - u32 size = bpf_dynptr_get_size(ptr); + u32 size = __bpf_dynptr_size(ptr); if (len > size || offset > size - len) return -E2BIG; @@ -1563,7 +1570,7 @@ BPF_CALL_5(bpf_dynptr_write, const struct bpf_dynptr_kern *, dst, u32, offset, v enum bpf_dynptr_type type; int err; - if (!dst->data || bpf_dynptr_is_rdonly(dst)) + if (!dst->data || __bpf_dynptr_is_rdonly(dst)) return -EINVAL; err = bpf_dynptr_check_off_len(dst, offset, len); @@ -1619,7 +1626,7 @@ BPF_CALL_3(bpf_dynptr_data, const struct bpf_dynptr_kern *, ptr, u32, offset, u3 if (err) return 0; - if (bpf_dynptr_is_rdonly(ptr)) + if (__bpf_dynptr_is_rdonly(ptr)) return 0; type = bpf_dynptr_get_type(ptr); @@ -2142,6 +2149,22 @@ __bpf_kfunc struct cgroup *bpf_cgroup_from_id(u64 cgid) return NULL; return cgrp; } + +/** + * bpf_task_under_cgroup - wrap task_under_cgroup_hierarchy() as a kfunc, test + * task's membership of cgroup ancestry. + * @task: the task to be tested + * @ancestor: possible ancestor of @task's cgroup + * + * Tests whether @task's default cgroup hierarchy is a descendant of @ancestor. + * It follows all the same rules as cgroup_is_descendant, and only applies + * to the default hierarchy. + */ +__bpf_kfunc long bpf_task_under_cgroup(struct task_struct *task, + struct cgroup *ancestor) +{ + return task_under_cgroup_hierarchy(task, ancestor); +} #endif /* CONFIG_CGROUPS */ /** @@ -2167,13 +2190,15 @@ __bpf_kfunc struct task_struct *bpf_task_from_pid(s32 pid) * bpf_dynptr_slice() - Obtain a read-only pointer to the dynptr data. * @ptr: The dynptr whose data slice to retrieve * @offset: Offset into the dynptr - * @buffer: User-provided buffer to copy contents into - * @buffer__szk: Size (in bytes) of the buffer. This is the length of the - * requested slice. This must be a constant. + * @buffer__opt: User-provided buffer to copy contents into. May be NULL + * @buffer__szk: Size (in bytes) of the buffer if present. This is the + * length of the requested slice. This must be a constant. * * For non-skb and non-xdp type dynptrs, there is no difference between * bpf_dynptr_slice and bpf_dynptr_data. * + * If buffer__opt is NULL, the call will fail if buffer_opt was needed. + * * If the intention is to write to the data slice, please use * bpf_dynptr_slice_rdwr. * @@ -2190,7 +2215,7 @@ __bpf_kfunc struct task_struct *bpf_task_from_pid(s32 pid) * direct pointer) */ __bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr_kern *ptr, u32 offset, - void *buffer, u32 buffer__szk) + void *buffer__opt, u32 buffer__szk) { enum bpf_dynptr_type type; u32 len = buffer__szk; @@ -2210,15 +2235,17 @@ __bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr_kern *ptr, u32 offset case BPF_DYNPTR_TYPE_RINGBUF: return ptr->data + ptr->offset + offset; case BPF_DYNPTR_TYPE_SKB: - return skb_header_pointer(ptr->data, ptr->offset + offset, len, buffer); + return skb_header_pointer(ptr->data, ptr->offset + offset, len, buffer__opt); case BPF_DYNPTR_TYPE_XDP: { void *xdp_ptr = bpf_xdp_pointer(ptr->data, ptr->offset + offset, len); if (xdp_ptr) return xdp_ptr; - bpf_xdp_copy_buf(ptr->data, ptr->offset + offset, buffer, len, false); - return buffer; + if (!buffer__opt) + return NULL; + bpf_xdp_copy_buf(ptr->data, ptr->offset + offset, buffer__opt, len, false); + return buffer__opt; } default: WARN_ONCE(true, "unknown dynptr type %d\n", type); @@ -2230,13 +2257,15 @@ __bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr_kern *ptr, u32 offset * bpf_dynptr_slice_rdwr() - Obtain a writable pointer to the dynptr data. * @ptr: The dynptr whose data slice to retrieve * @offset: Offset into the dynptr - * @buffer: User-provided buffer to copy contents into - * @buffer__szk: Size (in bytes) of the buffer. This is the length of the - * requested slice. This must be a constant. + * @buffer__opt: User-provided buffer to copy contents into. May be NULL + * @buffer__szk: Size (in bytes) of the buffer if present. This is the + * length of the requested slice. This must be a constant. * * For non-skb and non-xdp type dynptrs, there is no difference between * bpf_dynptr_slice and bpf_dynptr_data. * + * If buffer__opt is NULL, the call will fail if buffer_opt was needed. + * * The returned pointer is writable and may point to either directly the dynptr * data at the requested offset or to the buffer if unable to obtain a direct * data pointer to (example: the requested slice is to the paged area of an skb @@ -2267,9 +2296,9 @@ __bpf_kfunc void *bpf_dynptr_slice(const struct bpf_dynptr_kern *ptr, u32 offset * direct pointer) */ __bpf_kfunc void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr_kern *ptr, u32 offset, - void *buffer, u32 buffer__szk) + void *buffer__opt, u32 buffer__szk) { - if (!ptr->data || bpf_dynptr_is_rdonly(ptr)) + if (!ptr->data || __bpf_dynptr_is_rdonly(ptr)) return NULL; /* bpf_dynptr_slice_rdwr is the same logic as bpf_dynptr_slice. @@ -2294,7 +2323,59 @@ __bpf_kfunc void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr_kern *ptr, u32 o * will be copied out into the buffer and the user will need to call * bpf_dynptr_write() to commit changes. */ - return bpf_dynptr_slice(ptr, offset, buffer, buffer__szk); + return bpf_dynptr_slice(ptr, offset, buffer__opt, buffer__szk); +} + +__bpf_kfunc int bpf_dynptr_adjust(struct bpf_dynptr_kern *ptr, u32 start, u32 end) +{ + u32 size; + + if (!ptr->data || start > end) + return -EINVAL; + + size = __bpf_dynptr_size(ptr); + + if (start > size || end > size) + return -ERANGE; + + ptr->offset += start; + bpf_dynptr_set_size(ptr, end - start); + + return 0; +} + +__bpf_kfunc bool bpf_dynptr_is_null(struct bpf_dynptr_kern *ptr) +{ + return !ptr->data; +} + +__bpf_kfunc bool bpf_dynptr_is_rdonly(struct bpf_dynptr_kern *ptr) +{ + if (!ptr->data) + return false; + + return __bpf_dynptr_is_rdonly(ptr); +} + +__bpf_kfunc __u32 bpf_dynptr_size(const struct bpf_dynptr_kern *ptr) +{ + if (!ptr->data) + return -EINVAL; + + return __bpf_dynptr_size(ptr); +} + +__bpf_kfunc int bpf_dynptr_clone(struct bpf_dynptr_kern *ptr, + struct bpf_dynptr_kern *clone__uninit) +{ + if (!ptr->data) { + bpf_dynptr_set_null(clone__uninit); + return -EINVAL; + } + + *clone__uninit = *ptr; + + return 0; } __bpf_kfunc void *bpf_cast_to_kern_ctx(void *obj) @@ -2341,6 +2422,7 @@ BTF_ID_FLAGS(func, bpf_cgroup_acquire, KF_ACQUIRE | KF_RCU | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_cgroup_release, KF_RELEASE) BTF_ID_FLAGS(func, bpf_cgroup_ancestor, KF_ACQUIRE | KF_RCU | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_cgroup_from_id, KF_ACQUIRE | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_task_under_cgroup, KF_RCU) #endif BTF_ID_FLAGS(func, bpf_task_from_pid, KF_ACQUIRE | KF_RET_NULL) BTF_SET8_END(generic_btf_ids) @@ -2369,6 +2451,11 @@ BTF_ID_FLAGS(func, bpf_dynptr_slice_rdwr, KF_RET_NULL) BTF_ID_FLAGS(func, bpf_iter_num_new, KF_ITER_NEW) BTF_ID_FLAGS(func, bpf_iter_num_next, KF_ITER_NEXT | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_iter_num_destroy, KF_ITER_DESTROY) +BTF_ID_FLAGS(func, bpf_dynptr_adjust) +BTF_ID_FLAGS(func, bpf_dynptr_is_null) +BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly) +BTF_ID_FLAGS(func, bpf_dynptr_size) +BTF_ID_FLAGS(func, bpf_dynptr_clone) BTF_SET8_END(common_btf_ids) static const struct btf_kfunc_id_set common_kfunc_set = { diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 9948b542a470..4174f76133df 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -435,7 +435,7 @@ static int bpf_iter_link_pin_kernel(struct dentry *parent, return ret; } -static int bpf_obj_do_pin(const char __user *pathname, void *raw, +static int bpf_obj_do_pin(int path_fd, const char __user *pathname, void *raw, enum bpf_type type) { struct dentry *dentry; @@ -444,22 +444,21 @@ static int bpf_obj_do_pin(const char __user *pathname, void *raw, umode_t mode; int ret; - dentry = user_path_create(AT_FDCWD, pathname, &path, 0); + dentry = user_path_create(path_fd, pathname, &path, 0); if (IS_ERR(dentry)) return PTR_ERR(dentry); - mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask()); - - ret = security_path_mknod(&path, dentry, mode, 0); - if (ret) - goto out; - dir = d_inode(path.dentry); if (dir->i_op != &bpf_dir_iops) { ret = -EPERM; goto out; } + mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask()); + ret = security_path_mknod(&path, dentry, mode, 0); + if (ret) + goto out; + switch (type) { case BPF_TYPE_PROG: ret = vfs_mkobj(dentry, mode, bpf_mkprog, raw); @@ -478,7 +477,7 @@ out: return ret; } -int bpf_obj_pin_user(u32 ufd, const char __user *pathname) +int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname) { enum bpf_type type; void *raw; @@ -488,14 +487,14 @@ int bpf_obj_pin_user(u32 ufd, const char __user *pathname) if (IS_ERR(raw)) return PTR_ERR(raw); - ret = bpf_obj_do_pin(pathname, raw, type); + ret = bpf_obj_do_pin(path_fd, pathname, raw, type); if (ret != 0) bpf_any_put(raw, type); return ret; } -static void *bpf_obj_do_get(const char __user *pathname, +static void *bpf_obj_do_get(int path_fd, const char __user *pathname, enum bpf_type *type, int flags) { struct inode *inode; @@ -503,7 +502,7 @@ static void *bpf_obj_do_get(const char __user *pathname, void *raw; int ret; - ret = user_path_at(AT_FDCWD, pathname, LOOKUP_FOLLOW, &path); + ret = user_path_at(path_fd, pathname, LOOKUP_FOLLOW, &path); if (ret) return ERR_PTR(ret); @@ -527,7 +526,7 @@ out: return ERR_PTR(ret); } -int bpf_obj_get_user(const char __user *pathname, int flags) +int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags) { enum bpf_type type = BPF_TYPE_UNSPEC; int f_flags; @@ -538,7 +537,7 @@ int bpf_obj_get_user(const char __user *pathname, int flags) if (f_flags < 0) return f_flags; - raw = bpf_obj_do_get(pathname, &type, f_flags); + raw = bpf_obj_do_get(path_fd, pathname, &type, f_flags); if (IS_ERR(raw)) return PTR_ERR(raw); diff --git a/kernel/bpf/log.c b/kernel/bpf/log.c index 046ddff37a76..850494423530 100644 --- a/kernel/bpf/log.c +++ b/kernel/bpf/log.c @@ -62,9 +62,6 @@ void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, n = vscnprintf(log->kbuf, BPF_VERIFIER_TMP_LOG_SIZE, fmt, args); - WARN_ONCE(n >= BPF_VERIFIER_TMP_LOG_SIZE - 1, - "verifier log line truncated - local buffer too short\n"); - if (log->level == BPF_LOG_KERNEL) { bool newline = n > 0 && log->kbuf[n - 1] == '\n'; diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c index 2c5c64c2a53b..cd5eafaba97e 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -69,9 +69,13 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) /* Misc members not needed in bpf_map_meta_equal() check. */ inner_map_meta->ops = inner_map->ops; if (inner_map->ops == &array_map_ops) { + struct bpf_array *inner_array_meta = + container_of(inner_map_meta, struct bpf_array, map); + struct bpf_array *inner_array = container_of(inner_map, struct bpf_array, map); + + inner_array_meta->index_mask = inner_array->index_mask; + inner_array_meta->elem_size = inner_array->elem_size; inner_map_meta->bypass_spec_v1 = inner_map->bypass_spec_v1; - container_of(inner_map_meta, struct bpf_array, map)->index_mask = - container_of(inner_map, struct bpf_array, map)->index_mask; } fdput(f); diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index d9c9f45e3529..8a26cd8814c1 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -859,4 +859,4 @@ static int __init bpf_offload_init(void) return rhashtable_init(&offdevs, &offdevs_params); } -late_initcall(bpf_offload_init); +core_initcall(bpf_offload_init); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 14f39c1e573e..476ec959fab4 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1931,6 +1931,11 @@ static int map_freeze(const union bpf_attr *attr) return -ENOTSUPP; } + if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { + fdput(f); + return -EPERM; + } + mutex_lock(&map->freeze_mutex); if (bpf_map_write_active(map)) { err = -EBUSY; @@ -1940,10 +1945,6 @@ static int map_freeze(const union bpf_attr *attr) err = -EBUSY; goto err_put; } - if (!bpf_capable()) { - err = -EPERM; - goto err_put; - } WRITE_ONCE(map->frozen, true); err_put: @@ -2433,6 +2434,10 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, default: return -EINVAL; } + case BPF_PROG_TYPE_NETFILTER: + if (expected_attach_type == BPF_NETFILTER) + return 0; + return -EINVAL; case BPF_PROG_TYPE_SYSCALL: case BPF_PROG_TYPE_EXT: if (expected_attach_type) @@ -2697,23 +2702,38 @@ free_prog: return err; } -#define BPF_OBJ_LAST_FIELD file_flags +#define BPF_OBJ_LAST_FIELD path_fd static int bpf_obj_pin(const union bpf_attr *attr) { - if (CHECK_ATTR(BPF_OBJ) || attr->file_flags != 0) + int path_fd; + + if (CHECK_ATTR(BPF_OBJ) || attr->file_flags & ~BPF_F_PATH_FD) + return -EINVAL; + + /* path_fd has to be accompanied by BPF_F_PATH_FD flag */ + if (!(attr->file_flags & BPF_F_PATH_FD) && attr->path_fd) return -EINVAL; - return bpf_obj_pin_user(attr->bpf_fd, u64_to_user_ptr(attr->pathname)); + path_fd = attr->file_flags & BPF_F_PATH_FD ? attr->path_fd : AT_FDCWD; + return bpf_obj_pin_user(attr->bpf_fd, path_fd, + u64_to_user_ptr(attr->pathname)); } static int bpf_obj_get(const union bpf_attr *attr) { + int path_fd; + if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0 || - attr->file_flags & ~BPF_OBJ_FLAG_MASK) + attr->file_flags & ~(BPF_OBJ_FLAG_MASK | BPF_F_PATH_FD)) + return -EINVAL; + + /* path_fd has to be accompanied by BPF_F_PATH_FD flag */ + if (!(attr->file_flags & BPF_F_PATH_FD) && attr->path_fd) return -EINVAL; - return bpf_obj_get_user(u64_to_user_ptr(attr->pathname), + path_fd = attr->file_flags & BPF_F_PATH_FD ? attr->path_fd : AT_FDCWD; + return bpf_obj_get_user(path_fd, u64_to_user_ptr(attr->pathname), attr->file_flags); } @@ -2968,10 +2988,17 @@ static void bpf_tracing_link_show_fdinfo(const struct bpf_link *link, { struct bpf_tracing_link *tr_link = container_of(link, struct bpf_tracing_link, link.link); + u32 target_btf_id, target_obj_id; + bpf_trampoline_unpack_key(tr_link->trampoline->key, + &target_obj_id, &target_btf_id); seq_printf(seq, - "attach_type:\t%d\n", - tr_link->attach_type); + "attach_type:\t%d\n" + "target_obj_id:\t%u\n" + "target_btf_id:\t%u\n", + tr_link->attach_type, + target_obj_id, + target_btf_id); } static int bpf_tracing_link_fill_link_info(const struct bpf_link *link, @@ -4590,7 +4617,12 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) switch (prog->type) { case BPF_PROG_TYPE_EXT: + break; case BPF_PROG_TYPE_NETFILTER: + if (attr->link_create.attach_type != BPF_NETFILTER) { + ret = -EINVAL; + goto out; + } break; case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_TRACEPOINT: @@ -5380,7 +5412,8 @@ static int bpf_unpriv_handler(struct ctl_table *table, int write, *(int *)table->data = unpriv_enable; } - unpriv_ebpf_notify(unpriv_enable); + if (write) + unpriv_ebpf_notify(unpriv_enable); return ret; } diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index ac021bc43a66..78acf28d4873 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -251,11 +251,8 @@ bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total, bool *ip_a return tlinks; } -static void __bpf_tramp_image_put_deferred(struct work_struct *work) +static void bpf_tramp_image_free(struct bpf_tramp_image *im) { - struct bpf_tramp_image *im; - - im = container_of(work, struct bpf_tramp_image, work); bpf_image_ksym_del(&im->ksym); bpf_jit_free_exec(im->image); bpf_jit_uncharge_modmem(PAGE_SIZE); @@ -263,6 +260,14 @@ static void __bpf_tramp_image_put_deferred(struct work_struct *work) kfree_rcu(im, rcu); } +static void __bpf_tramp_image_put_deferred(struct work_struct *work) +{ + struct bpf_tramp_image *im; + + im = container_of(work, struct bpf_tramp_image, work); + bpf_tramp_image_free(im); +} + /* callback, fexit step 3 or fentry step 2 */ static void __bpf_tramp_image_put_rcu(struct rcu_head *rcu) { @@ -344,7 +349,7 @@ static void bpf_tramp_image_put(struct bpf_tramp_image *im) call_rcu_tasks_trace(&im->rcu, __bpf_tramp_image_put_rcu_tasks); } -static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, u32 idx) +static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key) { struct bpf_tramp_image *im; struct bpf_ksym *ksym; @@ -371,7 +376,7 @@ static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, u32 idx) ksym = &im->ksym; INIT_LIST_HEAD_RCU(&ksym->lnode); - snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu_%u", key, idx); + snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu", key); bpf_image_ksym_add(image, ksym); return im; @@ -401,11 +406,10 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut err = unregister_fentry(tr, tr->cur_image->image); bpf_tramp_image_put(tr->cur_image); tr->cur_image = NULL; - tr->selector = 0; goto out; } - im = bpf_tramp_image_alloc(tr->key, tr->selector); + im = bpf_tramp_image_alloc(tr->key); if (IS_ERR(im)) { err = PTR_ERR(im); goto out; @@ -438,12 +442,11 @@ again: &tr->func.model, tr->flags, tlinks, tr->func.addr); if (err < 0) - goto out; + goto out_free; set_memory_rox((long)im->image, 1); - WARN_ON(tr->cur_image && tr->selector == 0); - WARN_ON(!tr->cur_image && tr->selector); + WARN_ON(tr->cur_image && total == 0); if (tr->cur_image) /* progs already running at this address */ err = modify_fentry(tr, tr->cur_image->image, im->image, lock_direct_mutex); @@ -468,18 +471,21 @@ again: } #endif if (err) - goto out; + goto out_free; if (tr->cur_image) bpf_tramp_image_put(tr->cur_image); tr->cur_image = im; - tr->selector++; out: /* If any error happens, restore previous flags */ if (err) tr->flags = orig_flags; kfree(tlinks); return err; + +out_free: + bpf_tramp_image_free(im); + goto out; } static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(struct bpf_prog *prog) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index fbcf5a4e2fcd..086b2a14905b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -240,6 +240,12 @@ static void bpf_map_key_store(struct bpf_insn_aux_data *aux, u64 state) (poisoned ? BPF_MAP_KEY_POISON : 0ULL); } +static bool bpf_helper_call(const struct bpf_insn *insn) +{ + return insn->code == (BPF_JMP | BPF_CALL) && + insn->src_reg == 0; +} + static bool bpf_pseudo_call(const struct bpf_insn *insn) { return insn->code == (BPF_JMP | BPF_CALL) && @@ -273,11 +279,6 @@ struct bpf_call_arg_meta { struct btf_field *kptr_field; }; -struct btf_and_id { - struct btf *btf; - u32 btf_id; -}; - struct bpf_kfunc_call_arg_meta { /* In parameters */ struct btf *btf; @@ -296,10 +297,18 @@ struct bpf_kfunc_call_arg_meta { u64 value; bool found; } arg_constant; - union { - struct btf_and_id arg_obj_drop; - struct btf_and_id arg_refcount_acquire; - }; + + /* arg_btf and arg_btf_id are used by kfunc-specific handling, + * generally to pass info about user-defined local kptr types to later + * verification logic + * bpf_obj_drop + * Record the local kptr type to be drop'd + * bpf_refcount_acquire (via KF_ARG_PTR_TO_REFCOUNTED_KPTR arg type) + * Record the local kptr type to be refcount_incr'd + */ + struct btf *arg_btf; + u32 arg_btf_id; + struct { struct btf_field *field; } arg_list_head; @@ -309,6 +318,7 @@ struct bpf_kfunc_call_arg_meta { struct { enum bpf_dynptr_type type; u32 id; + u32 ref_obj_id; } initialized_dynptr; struct { u8 spi; @@ -468,6 +478,13 @@ static struct btf_record *reg_btf_record(const struct bpf_reg_state *reg) return rec; } +static bool subprog_is_global(const struct bpf_verifier_env *env, int subprog) +{ + struct bpf_func_info_aux *aux = env->prog->aux->func_info_aux; + + return aux && aux[subprog].linkage == BTF_FUNC_GLOBAL; +} + static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) { return btf_record_has_field(reg_btf_record(reg), BPF_SPIN_LOCK); @@ -515,6 +532,8 @@ static bool is_dynptr_ref_function(enum bpf_func_id func_id) return func_id == BPF_FUNC_dynptr_data; } +static bool is_callback_calling_kfunc(u32 btf_id); + static bool is_callback_calling_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_for_each_map_elem || @@ -524,6 +543,11 @@ static bool is_callback_calling_function(enum bpf_func_id func_id) func_id == BPF_FUNC_user_ringbuf_drain; } +static bool is_async_callback_calling_function(enum bpf_func_id func_id) +{ + return func_id == BPF_FUNC_timer_set_callback; +} + static bool is_storage_get_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_sk_storage_get || @@ -604,9 +628,9 @@ static const char *reg_type_str(struct bpf_verifier_env *env, type & PTR_TRUSTED ? "trusted_" : "" ); - snprintf(env->type_str_buf, TYPE_STR_BUF_LEN, "%s%s%s", + snprintf(env->tmp_str_buf, TMP_STR_BUF_LEN, "%s%s%s", prefix, str[base_type(type)], postfix); - return env->type_str_buf; + return env->tmp_str_buf; } static char slot_type_char[] = { @@ -847,11 +871,11 @@ static int destroy_if_dynptr_stack_slot(struct bpf_verifier_env *env, struct bpf_func_state *state, int spi); static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg, - enum bpf_arg_type arg_type, int insn_idx) + enum bpf_arg_type arg_type, int insn_idx, int clone_ref_obj_id) { struct bpf_func_state *state = func(env, reg); enum bpf_dynptr_type type; - int spi, i, id, err; + int spi, i, err; spi = dynptr_get_spi(env, reg); if (spi < 0) @@ -887,7 +911,13 @@ static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_ if (dynptr_type_refcounted(type)) { /* The id is used to track proper releasing */ - id = acquire_reference_state(env, insn_idx); + int id; + + if (clone_ref_obj_id) + id = clone_ref_obj_id; + else + id = acquire_reference_state(env, insn_idx); + if (id < 0) return id; @@ -901,24 +931,15 @@ static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_ return 0; } -static int unmark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +static void invalidate_dynptr(struct bpf_verifier_env *env, struct bpf_func_state *state, int spi) { - struct bpf_func_state *state = func(env, reg); - int spi, i; - - spi = dynptr_get_spi(env, reg); - if (spi < 0) - return spi; + int i; for (i = 0; i < BPF_REG_SIZE; i++) { state->stack[spi].slot_type[i] = STACK_INVALID; state->stack[spi - 1].slot_type[i] = STACK_INVALID; } - /* Invalidate any slices associated with this dynptr */ - if (dynptr_type_refcounted(state->stack[spi].spilled_ptr.dynptr.type)) - WARN_ON_ONCE(release_reference(env, state->stack[spi].spilled_ptr.ref_obj_id)); - __mark_reg_not_init(env, &state->stack[spi].spilled_ptr); __mark_reg_not_init(env, &state->stack[spi - 1].spilled_ptr); @@ -945,6 +966,50 @@ static int unmark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_re */ state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; state->stack[spi - 1].spilled_ptr.live |= REG_LIVE_WRITTEN; +} + +static int unmark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +{ + struct bpf_func_state *state = func(env, reg); + int spi, ref_obj_id, i; + + spi = dynptr_get_spi(env, reg); + if (spi < 0) + return spi; + + if (!dynptr_type_refcounted(state->stack[spi].spilled_ptr.dynptr.type)) { + invalidate_dynptr(env, state, spi); + return 0; + } + + ref_obj_id = state->stack[spi].spilled_ptr.ref_obj_id; + + /* If the dynptr has a ref_obj_id, then we need to invalidate + * two things: + * + * 1) Any dynptrs with a matching ref_obj_id (clones) + * 2) Any slices derived from this dynptr. + */ + + /* Invalidate any slices associated with this dynptr */ + WARN_ON_ONCE(release_reference(env, ref_obj_id)); + + /* Invalidate any dynptr clones */ + for (i = 1; i < state->allocated_stack / BPF_REG_SIZE; i++) { + if (state->stack[i].spilled_ptr.ref_obj_id != ref_obj_id) + continue; + + /* it should always be the case that if the ref obj id + * matches then the stack slot also belongs to a + * dynptr + */ + if (state->stack[i].slot_type[0] != STACK_DYNPTR) { + verbose(env, "verifier internal error: misconfigured ref_obj_id\n"); + return -EFAULT; + } + if (state->stack[i].spilled_ptr.dynptr.first_slot) + invalidate_dynptr(env, state, i); + } return 0; } @@ -1254,6 +1319,12 @@ static bool is_spilled_reg(const struct bpf_stack_state *stack) return stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL; } +static bool is_spilled_scalar_reg(const struct bpf_stack_state *stack) +{ + return stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL && + stack->spilled_ptr.type == SCALAR_VALUE; +} + static void scrub_spilled_slot(u8 *stype) { if (*stype != STACK_INVALID) @@ -3144,12 +3215,172 @@ static const char *disasm_kfunc_name(void *data, const struct bpf_insn *insn) return btf_name_by_offset(desc_btf, func->name_off); } +static inline void bt_init(struct backtrack_state *bt, u32 frame) +{ + bt->frame = frame; +} + +static inline void bt_reset(struct backtrack_state *bt) +{ + struct bpf_verifier_env *env = bt->env; + + memset(bt, 0, sizeof(*bt)); + bt->env = env; +} + +static inline u32 bt_empty(struct backtrack_state *bt) +{ + u64 mask = 0; + int i; + + for (i = 0; i <= bt->frame; i++) + mask |= bt->reg_masks[i] | bt->stack_masks[i]; + + return mask == 0; +} + +static inline int bt_subprog_enter(struct backtrack_state *bt) +{ + if (bt->frame == MAX_CALL_FRAMES - 1) { + verbose(bt->env, "BUG subprog enter from frame %d\n", bt->frame); + WARN_ONCE(1, "verifier backtracking bug"); + return -EFAULT; + } + bt->frame++; + return 0; +} + +static inline int bt_subprog_exit(struct backtrack_state *bt) +{ + if (bt->frame == 0) { + verbose(bt->env, "BUG subprog exit from frame 0\n"); + WARN_ONCE(1, "verifier backtracking bug"); + return -EFAULT; + } + bt->frame--; + return 0; +} + +static inline void bt_set_frame_reg(struct backtrack_state *bt, u32 frame, u32 reg) +{ + bt->reg_masks[frame] |= 1 << reg; +} + +static inline void bt_clear_frame_reg(struct backtrack_state *bt, u32 frame, u32 reg) +{ + bt->reg_masks[frame] &= ~(1 << reg); +} + +static inline void bt_set_reg(struct backtrack_state *bt, u32 reg) +{ + bt_set_frame_reg(bt, bt->frame, reg); +} + +static inline void bt_clear_reg(struct backtrack_state *bt, u32 reg) +{ + bt_clear_frame_reg(bt, bt->frame, reg); +} + +static inline void bt_set_frame_slot(struct backtrack_state *bt, u32 frame, u32 slot) +{ + bt->stack_masks[frame] |= 1ull << slot; +} + +static inline void bt_clear_frame_slot(struct backtrack_state *bt, u32 frame, u32 slot) +{ + bt->stack_masks[frame] &= ~(1ull << slot); +} + +static inline void bt_set_slot(struct backtrack_state *bt, u32 slot) +{ + bt_set_frame_slot(bt, bt->frame, slot); +} + +static inline void bt_clear_slot(struct backtrack_state *bt, u32 slot) +{ + bt_clear_frame_slot(bt, bt->frame, slot); +} + +static inline u32 bt_frame_reg_mask(struct backtrack_state *bt, u32 frame) +{ + return bt->reg_masks[frame]; +} + +static inline u32 bt_reg_mask(struct backtrack_state *bt) +{ + return bt->reg_masks[bt->frame]; +} + +static inline u64 bt_frame_stack_mask(struct backtrack_state *bt, u32 frame) +{ + return bt->stack_masks[frame]; +} + +static inline u64 bt_stack_mask(struct backtrack_state *bt) +{ + return bt->stack_masks[bt->frame]; +} + +static inline bool bt_is_reg_set(struct backtrack_state *bt, u32 reg) +{ + return bt->reg_masks[bt->frame] & (1 << reg); +} + +static inline bool bt_is_slot_set(struct backtrack_state *bt, u32 slot) +{ + return bt->stack_masks[bt->frame] & (1ull << slot); +} + +/* format registers bitmask, e.g., "r0,r2,r4" for 0x15 mask */ +static void fmt_reg_mask(char *buf, ssize_t buf_sz, u32 reg_mask) +{ + DECLARE_BITMAP(mask, 64); + bool first = true; + int i, n; + + buf[0] = '\0'; + + bitmap_from_u64(mask, reg_mask); + for_each_set_bit(i, mask, 32) { + n = snprintf(buf, buf_sz, "%sr%d", first ? "" : ",", i); + first = false; + buf += n; + buf_sz -= n; + if (buf_sz < 0) + break; + } +} +/* format stack slots bitmask, e.g., "-8,-24,-40" for 0x15 mask */ +static void fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask) +{ + DECLARE_BITMAP(mask, 64); + bool first = true; + int i, n; + + buf[0] = '\0'; + + bitmap_from_u64(mask, stack_mask); + for_each_set_bit(i, mask, 64) { + n = snprintf(buf, buf_sz, "%s%d", first ? "" : ",", -(i + 1) * 8); + first = false; + buf += n; + buf_sz -= n; + if (buf_sz < 0) + break; + } +} + /* For given verifier state backtrack_insn() is called from the last insn to * the first insn. Its purpose is to compute a bitmask of registers and * stack slots that needs precision in the parent verifier state. + * + * @idx is an index of the instruction we are currently processing; + * @subseq_idx is an index of the subsequent instruction that: + * - *would be* executed next, if jump history is viewed in forward order; + * - *was* processed previously during backtracking. */ -static int backtrack_insn(struct bpf_verifier_env *env, int idx, - u32 *reg_mask, u64 *stack_mask) +static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, + struct backtrack_state *bt) { const struct bpf_insn_cbs cbs = { .cb_call = disasm_kfunc_name, @@ -3160,20 +3391,24 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, u8 class = BPF_CLASS(insn->code); u8 opcode = BPF_OP(insn->code); u8 mode = BPF_MODE(insn->code); - u32 dreg = 1u << insn->dst_reg; - u32 sreg = 1u << insn->src_reg; - u32 spi; + u32 dreg = insn->dst_reg; + u32 sreg = insn->src_reg; + u32 spi, i; if (insn->code == 0) return 0; if (env->log.level & BPF_LOG_LEVEL2) { - verbose(env, "regs=%x stack=%llx before ", *reg_mask, *stack_mask); + fmt_reg_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, bt_reg_mask(bt)); + verbose(env, "mark_precise: frame%d: regs=%s ", + bt->frame, env->tmp_str_buf); + fmt_stack_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, bt_stack_mask(bt)); + verbose(env, "stack=%s before ", env->tmp_str_buf); verbose(env, "%d: ", idx); print_bpf_insn(&cbs, insn, env->allow_ptr_leaks); } if (class == BPF_ALU || class == BPF_ALU64) { - if (!(*reg_mask & dreg)) + if (!bt_is_reg_set(bt, dreg)) return 0; if (opcode == BPF_MOV) { if (BPF_SRC(insn->code) == BPF_X) { @@ -3181,8 +3416,8 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, * dreg needs precision after this insn * sreg needs precision before this insn */ - *reg_mask &= ~dreg; - *reg_mask |= sreg; + bt_clear_reg(bt, dreg); + bt_set_reg(bt, sreg); } else { /* dreg = K * dreg needs precision after this insn. @@ -3190,7 +3425,7 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, * as precise=true in this verifier state. * No further markings in parent are necessary */ - *reg_mask &= ~dreg; + bt_clear_reg(bt, dreg); } } else { if (BPF_SRC(insn->code) == BPF_X) { @@ -3198,15 +3433,15 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, * both dreg and sreg need precision * before this insn */ - *reg_mask |= sreg; + bt_set_reg(bt, sreg); } /* else dreg += K * dreg still needs precision before this insn */ } } else if (class == BPF_LDX) { - if (!(*reg_mask & dreg)) + if (!bt_is_reg_set(bt, dreg)) return 0; - *reg_mask &= ~dreg; + bt_clear_reg(bt, dreg); /* scalars can only be spilled into stack w/o losing precision. * Load from any other memory can be zero extended. @@ -3227,9 +3462,9 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } - *stack_mask |= 1ull << spi; + bt_set_slot(bt, spi); } else if (class == BPF_STX || class == BPF_ST) { - if (*reg_mask & dreg) + if (bt_is_reg_set(bt, dreg)) /* stx & st shouldn't be using _scalar_ dst_reg * to access memory. It means backtracking * encountered a case of pointer subtraction. @@ -3244,20 +3479,92 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } - if (!(*stack_mask & (1ull << spi))) + if (!bt_is_slot_set(bt, spi)) return 0; - *stack_mask &= ~(1ull << spi); + bt_clear_slot(bt, spi); if (class == BPF_STX) - *reg_mask |= sreg; + bt_set_reg(bt, sreg); } else if (class == BPF_JMP || class == BPF_JMP32) { - if (opcode == BPF_CALL) { - if (insn->src_reg == BPF_PSEUDO_CALL) - return -ENOTSUPP; - /* BPF helpers that invoke callback subprogs are - * equivalent to BPF_PSEUDO_CALL above + if (bpf_pseudo_call(insn)) { + int subprog_insn_idx, subprog; + + subprog_insn_idx = idx + insn->imm + 1; + subprog = find_subprog(env, subprog_insn_idx); + if (subprog < 0) + return -EFAULT; + + if (subprog_is_global(env, subprog)) { + /* check that jump history doesn't have any + * extra instructions from subprog; the next + * instruction after call to global subprog + * should be literally next instruction in + * caller program + */ + WARN_ONCE(idx + 1 != subseq_idx, "verifier backtracking bug"); + /* r1-r5 are invalidated after subprog call, + * so for global func call it shouldn't be set + * anymore + */ + if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) { + verbose(env, "BUG regs %x\n", bt_reg_mask(bt)); + WARN_ONCE(1, "verifier backtracking bug"); + return -EFAULT; + } + /* global subprog always sets R0 */ + bt_clear_reg(bt, BPF_REG_0); + return 0; + } else { + /* static subprog call instruction, which + * means that we are exiting current subprog, + * so only r1-r5 could be still requested as + * precise, r0 and r6-r10 or any stack slot in + * the current frame should be zero by now + */ + if (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) { + verbose(env, "BUG regs %x\n", bt_reg_mask(bt)); + WARN_ONCE(1, "verifier backtracking bug"); + return -EFAULT; + } + /* we don't track register spills perfectly, + * so fallback to force-precise instead of failing */ + if (bt_stack_mask(bt) != 0) + return -ENOTSUPP; + /* propagate r1-r5 to the caller */ + for (i = BPF_REG_1; i <= BPF_REG_5; i++) { + if (bt_is_reg_set(bt, i)) { + bt_clear_reg(bt, i); + bt_set_frame_reg(bt, bt->frame - 1, i); + } + } + if (bt_subprog_exit(bt)) + return -EFAULT; + return 0; + } + } else if ((bpf_helper_call(insn) && + is_callback_calling_function(insn->imm) && + !is_async_callback_calling_function(insn->imm)) || + (bpf_pseudo_kfunc_call(insn) && is_callback_calling_kfunc(insn->imm))) { + /* callback-calling helper or kfunc call, which means + * we are exiting from subprog, but unlike the subprog + * call handling above, we shouldn't propagate + * precision of r1-r5 (if any requested), as they are + * not actually arguments passed directly to callback + * subprogs */ - if (insn->src_reg == 0 && is_callback_calling_function(insn->imm)) + if (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) { + verbose(env, "BUG regs %x\n", bt_reg_mask(bt)); + WARN_ONCE(1, "verifier backtracking bug"); + return -EFAULT; + } + if (bt_stack_mask(bt) != 0) return -ENOTSUPP; + /* clear r1-r5 in callback subprog's mask */ + for (i = BPF_REG_1; i <= BPF_REG_5; i++) + bt_clear_reg(bt, i); + if (bt_subprog_exit(bt)) + return -EFAULT; + return 0; + } else if (opcode == BPF_CALL) { /* kfunc with imm==0 is invalid and fixup_kfunc_call will * catch this error later. Make backtracking conservative * with ENOTSUPP. @@ -3265,19 +3572,51 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL && insn->imm == 0) return -ENOTSUPP; /* regular helper call sets R0 */ - *reg_mask &= ~1; - if (*reg_mask & 0x3f) { + bt_clear_reg(bt, BPF_REG_0); + if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) { /* if backtracing was looking for registers R1-R5 * they should have been found already. */ - verbose(env, "BUG regs %x\n", *reg_mask); + verbose(env, "BUG regs %x\n", bt_reg_mask(bt)); WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } } else if (opcode == BPF_EXIT) { - return -ENOTSUPP; + bool r0_precise; + + if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) { + /* if backtracing was looking for registers R1-R5 + * they should have been found already. + */ + verbose(env, "BUG regs %x\n", bt_reg_mask(bt)); + WARN_ONCE(1, "verifier backtracking bug"); + return -EFAULT; + } + + /* BPF_EXIT in subprog or callback always returns + * right after the call instruction, so by checking + * whether the instruction at subseq_idx-1 is subprog + * call or not we can distinguish actual exit from + * *subprog* from exit from *callback*. In the former + * case, we need to propagate r0 precision, if + * necessary. In the former we never do that. + */ + r0_precise = subseq_idx - 1 >= 0 && + bpf_pseudo_call(&env->prog->insnsi[subseq_idx - 1]) && + bt_is_reg_set(bt, BPF_REG_0); + + bt_clear_reg(bt, BPF_REG_0); + if (bt_subprog_enter(bt)) + return -EFAULT; + + if (r0_precise) + bt_set_reg(bt, BPF_REG_0); + /* r6-r9 and stack slots will stay set in caller frame + * bitmasks until we return back from callee(s) + */ + return 0; } else if (BPF_SRC(insn->code) == BPF_X) { - if (!(*reg_mask & (dreg | sreg))) + if (!bt_is_reg_set(bt, dreg) && !bt_is_reg_set(bt, sreg)) return 0; /* dreg <cond> sreg * Both dreg and sreg need precision before @@ -3285,7 +3624,8 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, * before it would be equally necessary to * propagate it to dreg. */ - *reg_mask |= (sreg | dreg); + bt_set_reg(bt, dreg); + bt_set_reg(bt, sreg); /* else dreg <cond> K * Only dreg still needs precision before * this insn, so for the K-based conditional @@ -3293,9 +3633,9 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, */ } } else if (class == BPF_LD) { - if (!(*reg_mask & dreg)) + if (!bt_is_reg_set(bt, dreg)) return 0; - *reg_mask &= ~dreg; + bt_clear_reg(bt, dreg); /* It's ld_imm64 or ld_abs or ld_ind. * For ld_imm64 no further tracking of precision * into parent is necessary @@ -3366,6 +3706,11 @@ static void mark_all_scalars_precise(struct bpf_verifier_env *env, struct bpf_reg_state *reg; int i, j; + if (env->log.level & BPF_LOG_LEVEL2) { + verbose(env, "mark_precise: frame%d: falling back to forcing all scalars precise\n", + st->curframe); + } + /* big hammer: mark all scalars precise in this path. * pop_stack may still get !precise scalars. * We also skip current state and go straight to first parent state, @@ -3377,17 +3722,25 @@ static void mark_all_scalars_precise(struct bpf_verifier_env *env, func = st->frame[i]; for (j = 0; j < BPF_REG_FP; j++) { reg = &func->regs[j]; - if (reg->type != SCALAR_VALUE) + if (reg->type != SCALAR_VALUE || reg->precise) continue; reg->precise = true; + if (env->log.level & BPF_LOG_LEVEL2) { + verbose(env, "force_precise: frame%d: forcing r%d to be precise\n", + i, j); + } } for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) { if (!is_spilled_reg(&func->stack[j])) continue; reg = &func->stack[j].spilled_ptr; - if (reg->type != SCALAR_VALUE) + if (reg->type != SCALAR_VALUE || reg->precise) continue; reg->precise = true; + if (env->log.level & BPF_LOG_LEVEL2) { + verbose(env, "force_precise: frame%d: forcing fp%d to be precise\n", + i, -(j + 1) * 8); + } } } } @@ -3505,62 +3858,49 @@ static void mark_all_scalars_imprecise(struct bpf_verifier_env *env, struct bpf_ * mark_all_scalars_imprecise() to hopefully get more permissive and generic * finalized states which help in short circuiting more future states. */ -static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int regno, - int spi) +static int __mark_chain_precision(struct bpf_verifier_env *env, int regno) { + struct backtrack_state *bt = &env->bt; struct bpf_verifier_state *st = env->cur_state; int first_idx = st->first_insn_idx; int last_idx = env->insn_idx; + int subseq_idx = -1; struct bpf_func_state *func; struct bpf_reg_state *reg; - u32 reg_mask = regno >= 0 ? 1u << regno : 0; - u64 stack_mask = spi >= 0 ? 1ull << spi : 0; bool skip_first = true; - bool new_marks = false; - int i, err; + int i, fr, err; if (!env->bpf_capable) return 0; + /* set frame number from which we are starting to backtrack */ + bt_init(bt, env->cur_state->curframe); + /* Do sanity checks against current state of register and/or stack * slot, but don't set precise flag in current state, as precision * tracking in the current state is unnecessary. */ - func = st->frame[frame]; + func = st->frame[bt->frame]; if (regno >= 0) { reg = &func->regs[regno]; if (reg->type != SCALAR_VALUE) { WARN_ONCE(1, "backtracing misuse"); return -EFAULT; } - new_marks = true; - } - - while (spi >= 0) { - if (!is_spilled_reg(&func->stack[spi])) { - stack_mask = 0; - break; - } - reg = &func->stack[spi].spilled_ptr; - if (reg->type != SCALAR_VALUE) { - stack_mask = 0; - break; - } - new_marks = true; - break; + bt_set_reg(bt, regno); } - if (!new_marks) - return 0; - if (!reg_mask && !stack_mask) + if (bt_empty(bt)) return 0; for (;;) { DECLARE_BITMAP(mask, 64); u32 history = st->jmp_history_cnt; - if (env->log.level & BPF_LOG_LEVEL2) - verbose(env, "last_idx %d first_idx %d\n", last_idx, first_idx); + if (env->log.level & BPF_LOG_LEVEL2) { + verbose(env, "mark_precise: frame%d: last_idx %d first_idx %d subseq_idx %d \n", + bt->frame, last_idx, first_idx, subseq_idx); + } if (last_idx < 0) { /* we are at the entry into subprog, which @@ -3571,12 +3911,13 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r if (st->curframe == 0 && st->frame[0]->subprogno > 0 && st->frame[0]->callsite == BPF_MAIN_FUNC && - stack_mask == 0 && (reg_mask & ~0x3e) == 0) { - bitmap_from_u64(mask, reg_mask); + bt_stack_mask(bt) == 0 && + (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) == 0) { + bitmap_from_u64(mask, bt_reg_mask(bt)); for_each_set_bit(i, mask, 32) { reg = &st->frame[0]->regs[i]; if (reg->type != SCALAR_VALUE) { - reg_mask &= ~(1u << i); + bt_clear_reg(bt, i); continue; } reg->precise = true; @@ -3584,8 +3925,8 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r return 0; } - verbose(env, "BUG backtracing func entry subprog %d reg_mask %x stack_mask %llx\n", - st->frame[0]->subprogno, reg_mask, stack_mask); + verbose(env, "BUG backtracking func entry subprog %d reg_mask %x stack_mask %llx\n", + st->frame[0]->subprogno, bt_reg_mask(bt), bt_stack_mask(bt)); WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } @@ -3595,15 +3936,16 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r err = 0; skip_first = false; } else { - err = backtrack_insn(env, i, ®_mask, &stack_mask); + err = backtrack_insn(env, i, subseq_idx, bt); } if (err == -ENOTSUPP) { - mark_all_scalars_precise(env, st); + mark_all_scalars_precise(env, env->cur_state); + bt_reset(bt); return 0; } else if (err) { return err; } - if (!reg_mask && !stack_mask) + if (bt_empty(bt)) /* Found assignment(s) into tracked register in this state. * Since this state is already marked, just return. * Nothing to be tracked further in the parent state. @@ -3611,6 +3953,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r return 0; if (i == first_idx) break; + subseq_idx = i; i = get_prev_insn_idx(st, i, &history); if (i >= env->prog->len) { /* This can happen if backtracking reached insn 0 @@ -3628,84 +3971,95 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r if (!st) break; - new_marks = false; - func = st->frame[frame]; - bitmap_from_u64(mask, reg_mask); - for_each_set_bit(i, mask, 32) { - reg = &func->regs[i]; - if (reg->type != SCALAR_VALUE) { - reg_mask &= ~(1u << i); - continue; - } - if (!reg->precise) - new_marks = true; - reg->precise = true; - } - - bitmap_from_u64(mask, stack_mask); - for_each_set_bit(i, mask, 64) { - if (i >= func->allocated_stack / BPF_REG_SIZE) { - /* the sequence of instructions: - * 2: (bf) r3 = r10 - * 3: (7b) *(u64 *)(r3 -8) = r0 - * 4: (79) r4 = *(u64 *)(r10 -8) - * doesn't contain jmps. It's backtracked - * as a single block. - * During backtracking insn 3 is not recognized as - * stack access, so at the end of backtracking - * stack slot fp-8 is still marked in stack_mask. - * However the parent state may not have accessed - * fp-8 and it's "unallocated" stack space. - * In such case fallback to conservative. - */ - mark_all_scalars_precise(env, st); - return 0; + for (fr = bt->frame; fr >= 0; fr--) { + func = st->frame[fr]; + bitmap_from_u64(mask, bt_frame_reg_mask(bt, fr)); + for_each_set_bit(i, mask, 32) { + reg = &func->regs[i]; + if (reg->type != SCALAR_VALUE) { + bt_clear_frame_reg(bt, fr, i); + continue; + } + if (reg->precise) + bt_clear_frame_reg(bt, fr, i); + else + reg->precise = true; } - if (!is_spilled_reg(&func->stack[i])) { - stack_mask &= ~(1ull << i); - continue; + bitmap_from_u64(mask, bt_frame_stack_mask(bt, fr)); + for_each_set_bit(i, mask, 64) { + if (i >= func->allocated_stack / BPF_REG_SIZE) { + /* the sequence of instructions: + * 2: (bf) r3 = r10 + * 3: (7b) *(u64 *)(r3 -8) = r0 + * 4: (79) r4 = *(u64 *)(r10 -8) + * doesn't contain jmps. It's backtracked + * as a single block. + * During backtracking insn 3 is not recognized as + * stack access, so at the end of backtracking + * stack slot fp-8 is still marked in stack_mask. + * However the parent state may not have accessed + * fp-8 and it's "unallocated" stack space. + * In such case fallback to conservative. + */ + mark_all_scalars_precise(env, env->cur_state); + bt_reset(bt); + return 0; + } + + if (!is_spilled_scalar_reg(&func->stack[i])) { + bt_clear_frame_slot(bt, fr, i); + continue; + } + reg = &func->stack[i].spilled_ptr; + if (reg->precise) + bt_clear_frame_slot(bt, fr, i); + else + reg->precise = true; } - reg = &func->stack[i].spilled_ptr; - if (reg->type != SCALAR_VALUE) { - stack_mask &= ~(1ull << i); - continue; + if (env->log.level & BPF_LOG_LEVEL2) { + fmt_reg_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, + bt_frame_reg_mask(bt, fr)); + verbose(env, "mark_precise: frame%d: parent state regs=%s ", + fr, env->tmp_str_buf); + fmt_stack_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, + bt_frame_stack_mask(bt, fr)); + verbose(env, "stack=%s: ", env->tmp_str_buf); + print_verifier_state(env, func, true); } - if (!reg->precise) - new_marks = true; - reg->precise = true; - } - if (env->log.level & BPF_LOG_LEVEL2) { - verbose(env, "parent %s regs=%x stack=%llx marks:", - new_marks ? "didn't have" : "already had", - reg_mask, stack_mask); - print_verifier_state(env, func, true); } - if (!reg_mask && !stack_mask) - break; - if (!new_marks) - break; + if (bt_empty(bt)) + return 0; + subseq_idx = first_idx; last_idx = st->last_insn_idx; first_idx = st->first_insn_idx; } + + /* if we still have requested precise regs or slots, we missed + * something (e.g., stack access through non-r10 register), so + * fallback to marking all precise + */ + if (!bt_empty(bt)) { + mark_all_scalars_precise(env, env->cur_state); + bt_reset(bt); + } + return 0; } int mark_chain_precision(struct bpf_verifier_env *env, int regno) { - return __mark_chain_precision(env, env->cur_state->curframe, regno, -1); -} - -static int mark_chain_precision_frame(struct bpf_verifier_env *env, int frame, int regno) -{ - return __mark_chain_precision(env, frame, regno, -1); + return __mark_chain_precision(env, regno); } -static int mark_chain_precision_stack_frame(struct bpf_verifier_env *env, int frame, int spi) +/* mark_chain_precision_batch() assumes that env->bt is set in the caller to + * desired reg and stack masks across all relevant frames + */ +static int mark_chain_precision_batch(struct bpf_verifier_env *env) { - return __mark_chain_precision(env, frame, -1, spi); + return __mark_chain_precision(env, -1); } static bool is_spillable_regtype(enum bpf_reg_type type) @@ -4067,6 +4421,7 @@ static void mark_reg_stack_read(struct bpf_verifier_env *env, for (i = min_off; i < max_off; i++) { slot = -i - 1; spi = slot / BPF_REG_SIZE; + mark_stack_slot_scratched(env, spi); stype = ptr_state->stack[spi].slot_type; if (stype[slot % BPF_REG_SIZE] != STACK_ZERO) break; @@ -4118,6 +4473,8 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, stype = reg_state->stack[spi].slot_type; reg = ®_state->stack[spi].spilled_ptr; + mark_stack_slot_scratched(env, spi); + if (is_spilled_reg(®_state->stack[spi])) { u8 spill_size = 1; @@ -6677,7 +7034,7 @@ static int process_kptr_func(struct bpf_verifier_env *env, int regno, * type, and declare it as 'const struct bpf_dynptr *' in their prototype. */ static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn_idx, - enum bpf_arg_type arg_type) + enum bpf_arg_type arg_type, int clone_ref_obj_id) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; int err; @@ -6721,7 +7078,7 @@ static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn return err; } - err = mark_stack_slots_dynptr(env, reg, arg_type, insn_idx); + err = mark_stack_slots_dynptr(env, reg, arg_type, insn_idx, clone_ref_obj_id); } else /* MEM_RDONLY and None case from above */ { /* For the reg->type == PTR_TO_STACK case, bpf_dynptr is never const */ if (reg->type == CONST_PTR_TO_DYNPTR && !(arg_type & MEM_RDONLY)) { @@ -7143,12 +7500,16 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno, * ARG_PTR_TO_MEM + MAYBE_NULL is compatible with PTR_TO_MEM and PTR_TO_MEM + MAYBE_NULL, * but ARG_PTR_TO_MEM is compatible only with PTR_TO_MEM but NOT with PTR_TO_MEM + MAYBE_NULL * + * ARG_PTR_TO_MEM is compatible with PTR_TO_MEM that is tagged with a dynptr type. + * * Therefore we fold these flags depending on the arg_type before comparison. */ if (arg_type & MEM_RDONLY) type &= ~MEM_RDONLY; if (arg_type & PTR_MAYBE_NULL) type &= ~PTR_MAYBE_NULL; + if (base_type(arg_type) == ARG_PTR_TO_MEM) + type &= ~DYNPTR_TYPE_FLAG_MASK; if (meta->func_id == BPF_FUNC_kptr_xchg && type & MEM_ALLOC) type &= ~MEM_ALLOC; @@ -7631,7 +7992,7 @@ skip_type_check: err = check_mem_size_reg(env, reg, regno, true, meta); break; case ARG_PTR_TO_DYNPTR: - err = process_dynptr_func(env, regno, insn_idx, arg_type); + err = process_dynptr_func(env, regno, insn_idx, arg_type, 0); if (err) return err; break; @@ -8178,17 +8539,13 @@ static int set_callee_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx); -static bool is_callback_calling_kfunc(u32 btf_id); - static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx, int subprog, set_callee_state_fn set_callee_state_cb) { struct bpf_verifier_state *state = env->cur_state; - struct bpf_func_info_aux *func_info_aux; struct bpf_func_state *caller, *callee; int err; - bool is_global = false; if (state->curframe + 1 >= MAX_CALL_FRAMES) { verbose(env, "the call stack of %d frames is too deep\n", @@ -8203,13 +8560,10 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn return -EFAULT; } - func_info_aux = env->prog->aux->func_info_aux; - if (func_info_aux) - is_global = func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL; err = btf_check_subprog_call(env, subprog, caller->regs); if (err == -EFAULT) return err; - if (is_global) { + if (subprog_is_global(env, subprog)) { if (err) { verbose(env, "Caller passes invalid args into func#%d\n", subprog); @@ -9398,6 +9752,11 @@ static bool is_kfunc_arg_const_mem_size(const struct btf *btf, return __kfunc_param_match_suffix(btf, arg, "__szk"); } +static bool is_kfunc_arg_optional(const struct btf *btf, const struct btf_param *arg) +{ + return __kfunc_param_match_suffix(btf, arg, "__opt"); +} + static bool is_kfunc_arg_constant(const struct btf *btf, const struct btf_param *arg) { return __kfunc_param_match_suffix(btf, arg, "__k"); @@ -9595,6 +9954,7 @@ enum special_kfunc_type { KF_bpf_dynptr_from_xdp, KF_bpf_dynptr_slice, KF_bpf_dynptr_slice_rdwr, + KF_bpf_dynptr_clone, }; BTF_SET_START(special_kfunc_set) @@ -9614,6 +9974,7 @@ BTF_ID(func, bpf_dynptr_from_skb) BTF_ID(func, bpf_dynptr_from_xdp) BTF_ID(func, bpf_dynptr_slice) BTF_ID(func, bpf_dynptr_slice_rdwr) +BTF_ID(func, bpf_dynptr_clone) BTF_SET_END(special_kfunc_set) BTF_ID_LIST(special_kfunc_list) @@ -9635,6 +9996,7 @@ BTF_ID(func, bpf_dynptr_from_skb) BTF_ID(func, bpf_dynptr_from_xdp) BTF_ID(func, bpf_dynptr_slice) BTF_ID(func, bpf_dynptr_slice_rdwr) +BTF_ID(func, bpf_dynptr_clone) static bool is_kfunc_bpf_rcu_read_lock(struct bpf_kfunc_call_arg_meta *meta) { @@ -10323,13 +10685,14 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ } if (meta->btf == btf_vmlinux && meta->func_id == special_kfunc_list[KF_bpf_obj_drop_impl]) { - meta->arg_obj_drop.btf = reg->btf; - meta->arg_obj_drop.btf_id = reg->btf_id; + meta->arg_btf = reg->btf; + meta->arg_btf_id = reg->btf_id; } break; case KF_ARG_PTR_TO_DYNPTR: { enum bpf_arg_type dynptr_arg_type = ARG_PTR_TO_DYNPTR; + int clone_ref_obj_id = 0; if (reg->type != PTR_TO_STACK && reg->type != CONST_PTR_TO_DYNPTR) { @@ -10343,12 +10706,28 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ if (is_kfunc_arg_uninit(btf, &args[i])) dynptr_arg_type |= MEM_UNINIT; - if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_from_skb]) + if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_from_skb]) { dynptr_arg_type |= DYNPTR_TYPE_SKB; - else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_from_xdp]) + } else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_from_xdp]) { dynptr_arg_type |= DYNPTR_TYPE_XDP; + } else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_clone] && + (dynptr_arg_type & MEM_UNINIT)) { + enum bpf_dynptr_type parent_type = meta->initialized_dynptr.type; - ret = process_dynptr_func(env, regno, insn_idx, dynptr_arg_type); + if (parent_type == BPF_DYNPTR_TYPE_INVALID) { + verbose(env, "verifier internal error: no dynptr type for parent of clone\n"); + return -EFAULT; + } + + dynptr_arg_type |= (unsigned int)get_dynptr_type_flag(parent_type); + clone_ref_obj_id = meta->initialized_dynptr.ref_obj_id; + if (dynptr_type_refcounted(parent_type) && !clone_ref_obj_id) { + verbose(env, "verifier internal error: missing ref obj id for parent of clone\n"); + return -EFAULT; + } + } + + ret = process_dynptr_func(env, regno, insn_idx, dynptr_arg_type, clone_ref_obj_id); if (ret < 0) return ret; @@ -10361,6 +10740,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ } meta->initialized_dynptr.id = id; meta->initialized_dynptr.type = dynptr_get_type(env, reg); + meta->initialized_dynptr.ref_obj_id = dynptr_ref_obj_id(env, reg); } break; @@ -10464,13 +10844,17 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ break; case KF_ARG_PTR_TO_MEM_SIZE: { + struct bpf_reg_state *buff_reg = ®s[regno]; + const struct btf_param *buff_arg = &args[i]; struct bpf_reg_state *size_reg = ®s[regno + 1]; const struct btf_param *size_arg = &args[i + 1]; - ret = check_kfunc_mem_size_reg(env, size_reg, regno + 1); - if (ret < 0) { - verbose(env, "arg#%d arg#%d memory, len pair leads to invalid memory access\n", i, i + 1); - return ret; + if (!register_is_null(buff_reg) || !is_kfunc_arg_optional(meta->btf, buff_arg)) { + ret = check_kfunc_mem_size_reg(env, size_reg, regno + 1); + if (ret < 0) { + verbose(env, "arg#%d arg#%d memory, len pair leads to invalid memory access\n", i, i + 1); + return ret; + } } if (is_kfunc_arg_const_mem_size(meta->btf, size_arg, size_reg)) { @@ -10513,8 +10897,8 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ verbose(env, "bpf_refcount_acquire calls are disabled for now\n"); return -EINVAL; } - meta->arg_refcount_acquire.btf = reg->btf; - meta->arg_refcount_acquire.btf_id = reg->btf_id; + meta->arg_btf = reg->btf; + meta->arg_btf_id = reg->btf_id; break; } } @@ -10555,7 +10939,7 @@ static int fetch_kfunc_meta(struct bpf_verifier_env *env, *kfunc_name = func_name; func_proto = btf_type_by_id(desc_btf, func->type); - kfunc_flags = btf_kfunc_id_set_contains(desc_btf, resolve_prog_type(env->prog), func_id); + kfunc_flags = btf_kfunc_id_set_contains(desc_btf, func_id, env->prog); if (!kfunc_flags) { return -EACCES; } @@ -10746,12 +11130,12 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, } else if (meta.func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl]) { mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC; - regs[BPF_REG_0].btf = meta.arg_refcount_acquire.btf; - regs[BPF_REG_0].btf_id = meta.arg_refcount_acquire.btf_id; + regs[BPF_REG_0].btf = meta.arg_btf; + regs[BPF_REG_0].btf_id = meta.arg_btf_id; insn_aux->kptr_struct_meta = - btf_find_struct_meta(meta.arg_refcount_acquire.btf, - meta.arg_refcount_acquire.btf_id); + btf_find_struct_meta(meta.arg_btf, + meta.arg_btf_id); } else if (meta.func_id == special_kfunc_list[KF_bpf_list_pop_front] || meta.func_id == special_kfunc_list[KF_bpf_list_pop_back]) { struct btf_field *field = meta.arg_list_head.field; @@ -10881,8 +11265,8 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, if (meta.btf == btf_vmlinux && btf_id_set_contains(&special_kfunc_set, meta.func_id)) { if (meta.func_id == special_kfunc_list[KF_bpf_obj_drop_impl]) { insn_aux->kptr_struct_meta = - btf_find_struct_meta(meta.arg_obj_drop.btf, - meta.arg_obj_drop.btf_id); + btf_find_struct_meta(meta.arg_btf, + meta.arg_btf_id); } } } @@ -15118,20 +15502,25 @@ static int propagate_precision(struct bpf_verifier_env *env, struct bpf_reg_state *state_reg; struct bpf_func_state *state; int i, err = 0, fr; + bool first; for (fr = old->curframe; fr >= 0; fr--) { state = old->frame[fr]; state_reg = state->regs; + first = true; for (i = 0; i < BPF_REG_FP; i++, state_reg++) { if (state_reg->type != SCALAR_VALUE || !state_reg->precise || !(state_reg->live & REG_LIVE_READ)) continue; - if (env->log.level & BPF_LOG_LEVEL2) - verbose(env, "frame %d: propagating r%d\n", fr, i); - err = mark_chain_precision_frame(env, fr, i); - if (err < 0) - return err; + if (env->log.level & BPF_LOG_LEVEL2) { + if (first) + verbose(env, "frame %d: propagating r%d", fr, i); + else + verbose(env, ",r%d", i); + } + bt_set_frame_reg(&env->bt, fr, i); + first = false; } for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { @@ -15142,14 +15531,24 @@ static int propagate_precision(struct bpf_verifier_env *env, !state_reg->precise || !(state_reg->live & REG_LIVE_READ)) continue; - if (env->log.level & BPF_LOG_LEVEL2) - verbose(env, "frame %d: propagating fp%d\n", - fr, (-i - 1) * BPF_REG_SIZE); - err = mark_chain_precision_stack_frame(env, fr, i); - if (err < 0) - return err; + if (env->log.level & BPF_LOG_LEVEL2) { + if (first) + verbose(env, "frame %d: propagating fp%d", + fr, (-i - 1) * BPF_REG_SIZE); + else + verbose(env, ",fp%d", (-i - 1) * BPF_REG_SIZE); + } + bt_set_frame_slot(&env->bt, fr, i); + first = false; } + if (!first) + verbose(env, "\n"); } + + err = mark_chain_precision_batch(env); + if (err < 0) + return err; + return 0; } @@ -17033,7 +17432,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) insn_buf[cnt++] = BPF_ALU64_IMM(BPF_RSH, insn->dst_reg, shift); - insn_buf[cnt++] = BPF_ALU64_IMM(BPF_AND, insn->dst_reg, + insn_buf[cnt++] = BPF_ALU32_IMM(BPF_AND, insn->dst_reg, (1ULL << size * 8) - 1); } } @@ -18611,7 +19010,8 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, * in the fmodret id set with the KF_SLEEPABLE flag. */ else { - u32 *flags = btf_kfunc_is_modify_return(btf, btf_id); + u32 *flags = btf_kfunc_is_modify_return(btf, btf_id, + prog); if (flags && (*flags & KF_SLEEPABLE)) ret = 0; @@ -18639,7 +19039,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, return -EINVAL; } ret = -EINVAL; - if (btf_kfunc_is_modify_return(btf, btf_id) || + if (btf_kfunc_is_modify_return(btf, btf_id, prog) || !check_attach_modify_return(addr, tname)) ret = 0; if (ret) { @@ -18806,6 +19206,8 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 if (!env) return -ENOMEM; + env->bt.env = env; + len = (*prog)->len; env->insn_aux_data = vzalloc(array_size(sizeof(struct bpf_insn_aux_data), len)); diff --git a/kernel/events/core.c b/kernel/events/core.c index 68baa8194d9f..db016e418931 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10150,8 +10150,20 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, perf_trace_buf_update(record, event_type); hlist_for_each_entry_rcu(event, head, hlist_entry) { - if (perf_tp_event_match(event, &data, regs)) + if (perf_tp_event_match(event, &data, regs)) { perf_swevent_event(event, count, &data, regs); + + /* + * Here use the same on-stack perf_sample_data, + * some members in data are event-specific and + * need to be re-computed for different sweveents. + * Re-initialize data->sample_flags safely to avoid + * the problem that next event skips preparing data + * because data->sample_flags is set. + */ + perf_sample_data_init(&data, 0, 0); + perf_sample_save_raw_data(&data, &raw); + } } /* diff --git a/kernel/exit.c b/kernel/exit.c index 34b90e2e7cf7..edb50b4c9972 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -411,7 +411,10 @@ static void coredump_task_exit(struct task_struct *tsk) tsk->flags |= PF_POSTCOREDUMP; core_state = tsk->signal->core_state; spin_unlock_irq(&tsk->sighand->siglock); - if (core_state) { + + /* The vhost_worker does not particpate in coredumps */ + if (core_state && + ((tsk->flags & (PF_IO_WORKER | PF_USER_WORKER)) != PF_USER_WORKER)) { struct core_thread self; self.task = current; diff --git a/kernel/fork.c b/kernel/fork.c index ed4e01daccaa..41c964104b58 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -627,6 +627,7 @@ void free_task(struct task_struct *tsk) arch_release_task_struct(tsk); if (tsk->flags & PF_KTHREAD) free_kthread_struct(tsk); + bpf_task_storage_free(tsk); free_task_struct(tsk); } EXPORT_SYMBOL(free_task); @@ -979,7 +980,6 @@ void __put_task_struct(struct task_struct *tsk) cgroup_free(tsk); task_numa_free(tsk, true); security_task_free(tsk); - bpf_task_storage_free(tsk); exit_creds(tsk); delayacct_tsk_free(tsk); put_signal_struct(tsk->signal); @@ -2336,16 +2336,16 @@ __latent_entropy struct task_struct *copy_process( p->flags &= ~PF_KTHREAD; if (args->kthread) p->flags |= PF_KTHREAD; - if (args->user_worker) - p->flags |= PF_USER_WORKER; - if (args->io_thread) { + if (args->user_worker) { /* - * Mark us an IO worker, and block any signal that isn't + * Mark us a user worker, and block any signal that isn't * fatal or STOP */ - p->flags |= PF_IO_WORKER; + p->flags |= PF_USER_WORKER; siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP)); } + if (args->io_thread) + p->flags |= PF_IO_WORKER; if (args->name) strscpy_pad(p->comm, args->name, sizeof(p->comm)); @@ -2517,9 +2517,6 @@ __latent_entropy struct task_struct *copy_process( if (retval) goto bad_fork_cleanup_io; - if (args->ignore_signals) - ignore_signals(p); - stackleak_task_init(p); if (pid != &init_struct_pid) { diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 7a97bcb086bf..b4c31a5c1147 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -542,7 +542,7 @@ fail: return ret; } -#ifdef CONFIG_PCI_MSI_ARCH_FALLBACKS +#if defined(CONFIG_PCI_MSI_ARCH_FALLBACKS) || defined(CONFIG_PCI_XEN) /** * msi_device_populate_sysfs - Populate msi_irqs sysfs entries for a device * @dev: The device (PCI, platform etc) which will get sysfs entries @@ -574,7 +574,7 @@ void msi_device_destroy_sysfs(struct device *dev) msi_for_each_desc(desc, dev, MSI_DESC_ALL) msi_sysfs_remove_desc(dev, desc); } -#endif /* CONFIG_PCI_MSI_ARCH_FALLBACK */ +#endif /* CONFIG_PCI_MSI_ARCH_FALLBACK || CONFIG_PCI_XEN */ #else /* CONFIG_SYSFS */ static inline int msi_sysfs_create_group(struct device *dev) { return 0; } static inline int msi_sysfs_populate_desc(struct device *dev, struct msi_desc *desc) { return 0; } diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index dcd1d5bfc1e0..4dfd2f3e09b2 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -2263,6 +2263,9 @@ static inline bool usage_match(struct lock_list *entry, void *mask) static inline bool usage_skip(struct lock_list *entry, void *mask) { + if (entry->class->lock_type == LD_LOCK_NORMAL) + return false; + /* * Skip local_lock() for irq inversion detection. * @@ -2289,14 +2292,16 @@ static inline bool usage_skip(struct lock_list *entry, void *mask) * As a result, we will skip local_lock(), when we search for irq * inversion bugs. */ - if (entry->class->lock_type == LD_LOCK_PERCPU) { - if (DEBUG_LOCKS_WARN_ON(entry->class->wait_type_inner < LD_WAIT_CONFIG)) - return false; + if (entry->class->lock_type == LD_LOCK_PERCPU && + DEBUG_LOCKS_WARN_ON(entry->class->wait_type_inner < LD_WAIT_CONFIG)) + return false; - return true; - } + /* + * Skip WAIT_OVERRIDE for irq inversion detection -- it's not actually + * a lock and only used to override the wait_type. + */ - return false; + return true; } /* @@ -4768,7 +4773,8 @@ static int check_wait_context(struct task_struct *curr, struct held_lock *next) for (; depth < curr->lockdep_depth; depth++) { struct held_lock *prev = curr->held_locks + depth; - u8 prev_inner = hlock_class(prev)->wait_type_inner; + struct lock_class *class = hlock_class(prev); + u8 prev_inner = class->wait_type_inner; if (prev_inner) { /* @@ -4778,6 +4784,14 @@ static int check_wait_context(struct task_struct *curr, struct held_lock *next) * Also due to trylocks. */ curr_inner = min(curr_inner, prev_inner); + + /* + * Allow override for annotations -- this is typically + * only valid/needed for code that only exists when + * CONFIG_PREEMPT_RT=n. + */ + if (unlikely(class->lock_type == LD_LOCK_WAIT_OVERRIDE)) + curr_inner = prev_inner; } } diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index acb5a50309a1..9eabd585ce7a 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -1240,7 +1240,7 @@ static struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem) /* * lock for reading */ -static inline int __down_read_common(struct rw_semaphore *sem, int state) +static __always_inline int __down_read_common(struct rw_semaphore *sem, int state) { int ret = 0; long count; @@ -1258,17 +1258,17 @@ out: return ret; } -static inline void __down_read(struct rw_semaphore *sem) +static __always_inline void __down_read(struct rw_semaphore *sem) { __down_read_common(sem, TASK_UNINTERRUPTIBLE); } -static inline int __down_read_interruptible(struct rw_semaphore *sem) +static __always_inline int __down_read_interruptible(struct rw_semaphore *sem) { return __down_read_common(sem, TASK_INTERRUPTIBLE); } -static inline int __down_read_killable(struct rw_semaphore *sem) +static __always_inline int __down_read_killable(struct rw_semaphore *sem) { return __down_read_common(sem, TASK_KILLABLE); } diff --git a/kernel/module/decompress.c b/kernel/module/decompress.c index e97232b125eb..8a5d6d63b06c 100644 --- a/kernel/module/decompress.c +++ b/kernel/module/decompress.c @@ -257,7 +257,7 @@ static ssize_t module_zstd_decompress(struct load_info *info, do { struct page *page = module_get_next_page(info); - if (!IS_ERR(page)) { + if (IS_ERR(page)) { retval = PTR_ERR(page); goto out; } diff --git a/kernel/module/main.c b/kernel/module/main.c index 044aa2c9e3cb..4e2cf784cf8c 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1521,14 +1521,14 @@ static void __layout_sections(struct module *mod, struct load_info *info, bool i MOD_RODATA, MOD_RO_AFTER_INIT, MOD_DATA, - MOD_INVALID, /* This is needed to match the masks array */ + MOD_DATA, }; static const int init_m_to_mem_type[] = { MOD_INIT_TEXT, MOD_INIT_RODATA, MOD_INVALID, MOD_INIT_DATA, - MOD_INVALID, /* This is needed to match the masks array */ + MOD_INIT_DATA, }; for (m = 0; m < ARRAY_SIZE(masks); ++m) { diff --git a/kernel/module/stats.c b/kernel/module/stats.c index ad7b6ada29f2..6ab2c94d6bc3 100644 --- a/kernel/module/stats.c +++ b/kernel/module/stats.c @@ -276,6 +276,7 @@ static ssize_t read_file_mod_stats(struct file *file, char __user *user_buf, struct mod_fail_load *mod_fail; unsigned int len, size, count_failed = 0; char *buf; + int ret; u32 live_mod_count, fkreads, fdecompress, fbecoming, floads; unsigned long total_size, text_size, ikread_bytes, ibecoming_bytes, idecompress_bytes, imod_bytes, total_virtual_lost; @@ -390,8 +391,9 @@ static ssize_t read_file_mod_stats(struct file *file, char __user *user_buf, out_unlock: mutex_unlock(&module_mutex); out: + ret = simple_read_from_buffer(user_buf, count, ppos, buf, len); kfree(buf); - return simple_read_from_buffer(user_buf, count, ppos, buf, len); + return ret; } #undef MAX_PREAMBLE #undef MAX_FAILED_MOD_PRINT diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 944c3ae39861..a68d1276bab0 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -11492,7 +11492,7 @@ void call_trace_sched_update_nr_running(struct rq *rq, int count) #ifdef CONFIG_SCHED_MM_CID -/** +/* * @cid_lock: Guarantee forward-progress of cid allocation. * * Concurrency ID allocation within a bitmap is mostly lock-free. The cid_lock @@ -11501,7 +11501,7 @@ void call_trace_sched_update_nr_running(struct rq *rq, int count) */ DEFINE_RAW_SPINLOCK(cid_lock); -/** +/* * @use_cid_lock: Select cid allocation behavior: lock-free vs spinlock. * * When @use_cid_lock is 0, the cid allocation is lock-free. When contention is diff --git a/kernel/signal.c b/kernel/signal.c index 8f6330f0e9ca..2547fa73bde5 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1368,7 +1368,9 @@ int zap_other_threads(struct task_struct *p) while_each_thread(p, t) { task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK); - count++; + /* Don't require de_thread to wait for the vhost_worker */ + if ((t->flags & (PF_IO_WORKER | PF_USER_WORKER)) != PF_USER_WORKER) + count++; /* Don't bother with already dead threads */ if (t->exit_state) @@ -2861,11 +2863,11 @@ relock: } /* - * PF_IO_WORKER threads will catch and exit on fatal signals + * PF_USER_WORKER threads will catch and exit on fatal signals * themselves. They have cleanup that must be performed, so * we cannot call do_exit() on their behalf. */ - if (current->flags & PF_IO_WORKER) + if (current->flags & PF_USER_WORKER) goto out; /* diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 93bf2b4e47e5..771d1e040303 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -35,14 +35,15 @@ static __cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(tick_broadcast_lock); #ifdef CONFIG_TICK_ONESHOT static DEFINE_PER_CPU(struct clock_event_device *, tick_oneshot_wakeup_device); -static void tick_broadcast_setup_oneshot(struct clock_event_device *bc); +static void tick_broadcast_setup_oneshot(struct clock_event_device *bc, bool from_periodic); static void tick_broadcast_clear_oneshot(int cpu); static void tick_resume_broadcast_oneshot(struct clock_event_device *bc); # ifdef CONFIG_HOTPLUG_CPU static void tick_broadcast_oneshot_offline(unsigned int cpu); # endif #else -static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { BUG(); } +static inline void +tick_broadcast_setup_oneshot(struct clock_event_device *bc, bool from_periodic) { BUG(); } static inline void tick_broadcast_clear_oneshot(int cpu) { } static inline void tick_resume_broadcast_oneshot(struct clock_event_device *bc) { } # ifdef CONFIG_HOTPLUG_CPU @@ -264,7 +265,7 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) tick_broadcast_start_periodic(bc); else - tick_broadcast_setup_oneshot(bc); + tick_broadcast_setup_oneshot(bc, false); ret = 1; } else { /* @@ -500,7 +501,7 @@ void tick_broadcast_control(enum tick_broadcast_mode mode) if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) tick_broadcast_start_periodic(bc); else - tick_broadcast_setup_oneshot(bc); + tick_broadcast_setup_oneshot(bc, false); } } out: @@ -1020,48 +1021,101 @@ static inline ktime_t tick_get_next_period(void) /** * tick_broadcast_setup_oneshot - setup the broadcast device */ -static void tick_broadcast_setup_oneshot(struct clock_event_device *bc) +static void tick_broadcast_setup_oneshot(struct clock_event_device *bc, + bool from_periodic) { int cpu = smp_processor_id(); + ktime_t nexttick = 0; if (!bc) return; - /* Set it up only once ! */ - if (bc->event_handler != tick_handle_oneshot_broadcast) { - int was_periodic = clockevent_state_periodic(bc); - - bc->event_handler = tick_handle_oneshot_broadcast; - + /* + * When the broadcast device was switched to oneshot by the first + * CPU handling the NOHZ change, the other CPUs will reach this + * code via hrtimer_run_queues() -> tick_check_oneshot_change() + * too. Set up the broadcast device only once! + */ + if (bc->event_handler == tick_handle_oneshot_broadcast) { /* - * We must be careful here. There might be other CPUs - * waiting for periodic broadcast. We need to set the - * oneshot_mask bits for those and program the - * broadcast device to fire. + * The CPU which switched from periodic to oneshot mode + * set the broadcast oneshot bit for all other CPUs which + * are in the general (periodic) broadcast mask to ensure + * that CPUs which wait for the periodic broadcast are + * woken up. + * + * Clear the bit for the local CPU as the set bit would + * prevent the first tick_broadcast_enter() after this CPU + * switched to oneshot state to program the broadcast + * device. + * + * This code can also be reached via tick_broadcast_control(), + * but this cannot avoid the tick_broadcast_clear_oneshot() + * as that would break the periodic to oneshot transition of + * secondary CPUs. But that's harmless as the below only + * clears already cleared bits. */ + tick_broadcast_clear_oneshot(cpu); + return; + } + + + bc->event_handler = tick_handle_oneshot_broadcast; + bc->next_event = KTIME_MAX; + + /* + * When the tick mode is switched from periodic to oneshot it must + * be ensured that CPUs which are waiting for periodic broadcast + * get their wake-up at the next tick. This is achieved by ORing + * tick_broadcast_mask into tick_broadcast_oneshot_mask. + * + * For other callers, e.g. broadcast device replacement, + * tick_broadcast_oneshot_mask must not be touched as this would + * set bits for CPUs which are already NOHZ, but not idle. Their + * next tick_broadcast_enter() would observe the bit set and fail + * to update the expiry time and the broadcast event device. + */ + if (from_periodic) { cpumask_copy(tmpmask, tick_broadcast_mask); + /* Remove the local CPU as it is obviously not idle */ cpumask_clear_cpu(cpu, tmpmask); - cpumask_or(tick_broadcast_oneshot_mask, - tick_broadcast_oneshot_mask, tmpmask); + cpumask_or(tick_broadcast_oneshot_mask, tick_broadcast_oneshot_mask, tmpmask); - if (was_periodic && !cpumask_empty(tmpmask)) { - ktime_t nextevt = tick_get_next_period(); + /* + * Ensure that the oneshot broadcast handler will wake the + * CPUs which are still waiting for periodic broadcast. + */ + nexttick = tick_get_next_period(); + tick_broadcast_init_next_event(tmpmask, nexttick); - clockevents_switch_state(bc, CLOCK_EVT_STATE_ONESHOT); - tick_broadcast_init_next_event(tmpmask, nextevt); - tick_broadcast_set_event(bc, cpu, nextevt); - } else - bc->next_event = KTIME_MAX; - } else { /* - * The first cpu which switches to oneshot mode sets - * the bit for all other cpus which are in the general - * (periodic) broadcast mask. So the bit is set and - * would prevent the first broadcast enter after this - * to program the bc device. + * If the underlying broadcast clock event device is + * already in oneshot state, then there is nothing to do. + * The device was already armed for the next tick + * in tick_handle_broadcast_periodic() */ - tick_broadcast_clear_oneshot(cpu); + if (clockevent_state_oneshot(bc)) + return; } + + /* + * When switching from periodic to oneshot mode arm the broadcast + * device for the next tick. + * + * If the broadcast device has been replaced in oneshot mode and + * the oneshot broadcast mask is not empty, then arm it to expire + * immediately in order to reevaluate the next expiring timer. + * @nexttick is 0 and therefore in the past which will cause the + * clockevent code to force an event. + * + * For both cases the programming can be avoided when the oneshot + * broadcast mask is empty. + * + * tick_broadcast_set_event() implicitly switches the broadcast + * device to oneshot state. + */ + if (!cpumask_empty(tick_broadcast_oneshot_mask)) + tick_broadcast_set_event(bc, cpu, nexttick); } /* @@ -1070,14 +1124,16 @@ static void tick_broadcast_setup_oneshot(struct clock_event_device *bc) void tick_broadcast_switch_to_oneshot(void) { struct clock_event_device *bc; + enum tick_device_mode oldmode; unsigned long flags; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); + oldmode = tick_broadcast_device.mode; tick_broadcast_device.mode = TICKDEV_MODE_ONESHOT; bc = tick_broadcast_device.evtdev; if (bc) - tick_broadcast_setup_oneshot(bc); + tick_broadcast_setup_oneshot(bc, oldmode == TICKDEV_MODE_PERIODIC); raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 9a050e36dc6c..03b7f6b8e4f0 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -900,13 +900,23 @@ static const struct bpf_func_proto bpf_send_signal_thread_proto = { BPF_CALL_3(bpf_d_path, struct path *, path, char *, buf, u32, sz) { + struct path copy; long len; char *p; if (!sz) return 0; - p = d_path(path, buf, sz); + /* + * The path pointer is verified as trusted and safe to use, + * but let's double check it's valid anyway to workaround + * potentially broken verifier. + */ + len = copy_from_kernel_nofault(©, path, sizeof(*path)); + if (len < 0) + return len; + + p = d_path(©, buf, sz); if (IS_ERR(p)) { len = PTR_ERR(p); } else { @@ -1349,9 +1359,9 @@ __bpf_kfunc int bpf_verify_pkcs7_signature(struct bpf_dynptr_kern *data_ptr, } return verify_pkcs7_signature(data_ptr->data, - bpf_dynptr_get_size(data_ptr), + __bpf_dynptr_size(data_ptr), sig_ptr->data, - bpf_dynptr_get_size(sig_ptr), + __bpf_dynptr_size(sig_ptr), trusted_keyring->key, VERIFYING_UNSPECIFIED_SIGNATURE, NULL, NULL); diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 9abb3905bc8e..18d36842faf5 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -17,36 +17,30 @@ struct fprobe_rethook_node { struct rethook_node node; unsigned long entry_ip; + unsigned long entry_parent_ip; char data[]; }; -static void fprobe_handler(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops, struct ftrace_regs *fregs) +static inline void __fprobe_handler(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct ftrace_regs *fregs) { struct fprobe_rethook_node *fpr; struct rethook_node *rh = NULL; struct fprobe *fp; void *entry_data = NULL; - int bit, ret; + int ret = 0; fp = container_of(ops, struct fprobe, ops); - if (fprobe_disabled(fp)) - return; - - bit = ftrace_test_recursion_trylock(ip, parent_ip); - if (bit < 0) { - fp->nmissed++; - return; - } if (fp->exit_handler) { rh = rethook_try_get(fp->rethook); if (!rh) { fp->nmissed++; - goto out; + return; } fpr = container_of(rh, struct fprobe_rethook_node, node); fpr->entry_ip = ip; + fpr->entry_parent_ip = parent_ip; if (fp->entry_data_size) entry_data = fpr->data; } @@ -61,23 +55,60 @@ static void fprobe_handler(unsigned long ip, unsigned long parent_ip, else rethook_hook(rh, ftrace_get_regs(fregs), true); } -out: +} + +static void fprobe_handler(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct ftrace_regs *fregs) +{ + struct fprobe *fp; + int bit; + + fp = container_of(ops, struct fprobe, ops); + if (fprobe_disabled(fp)) + return; + + /* recursion detection has to go before any traceable function and + * all functions before this point should be marked as notrace + */ + bit = ftrace_test_recursion_trylock(ip, parent_ip); + if (bit < 0) { + fp->nmissed++; + return; + } + __fprobe_handler(ip, parent_ip, ops, fregs); ftrace_test_recursion_unlock(bit); + } NOKPROBE_SYMBOL(fprobe_handler); static void fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct ftrace_regs *fregs) { - struct fprobe *fp = container_of(ops, struct fprobe, ops); + struct fprobe *fp; + int bit; + + fp = container_of(ops, struct fprobe, ops); + if (fprobe_disabled(fp)) + return; + + /* recursion detection has to go before any traceable function and + * all functions called before this point should be marked as notrace + */ + bit = ftrace_test_recursion_trylock(ip, parent_ip); + if (bit < 0) { + fp->nmissed++; + return; + } if (unlikely(kprobe_running())) { fp->nmissed++; return; } + kprobe_busy_begin(); - fprobe_handler(ip, parent_ip, ops, fregs); + __fprobe_handler(ip, parent_ip, ops, fregs); kprobe_busy_end(); + ftrace_test_recursion_unlock(bit); } static void fprobe_exit_handler(struct rethook_node *rh, void *data, @@ -85,14 +116,26 @@ static void fprobe_exit_handler(struct rethook_node *rh, void *data, { struct fprobe *fp = (struct fprobe *)data; struct fprobe_rethook_node *fpr; + int bit; if (!fp || fprobe_disabled(fp)) return; fpr = container_of(rh, struct fprobe_rethook_node, node); + /* + * we need to assure no calls to traceable functions in-between the + * end of fprobe_handler and the beginning of fprobe_exit_handler. + */ + bit = ftrace_test_recursion_trylock(fpr->entry_ip, fpr->entry_parent_ip); + if (bit < 0) { + fp->nmissed++; + return; + } + fp->exit_handler(fp, fpr->entry_ip, regs, fp->entry_data_size ? (void *)fpr->data : NULL); + ftrace_test_recursion_unlock(bit); } NOKPROBE_SYMBOL(fprobe_exit_handler); diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c index 32c3dfdb4d6a..60f6cb2b486b 100644 --- a/kernel/trace/rethook.c +++ b/kernel/trace/rethook.c @@ -288,7 +288,7 @@ unsigned long rethook_trampoline_handler(struct pt_regs *regs, * These loops must be protected from rethook_free_rcu() because those * are accessing 'rhn->rethook'. */ - preempt_disable(); + preempt_disable_notrace(); /* * Run the handler on the shadow stack. Do not unlink the list here because @@ -321,7 +321,7 @@ unsigned long rethook_trampoline_handler(struct pt_regs *regs, first = first->next; rethook_recycle(rhn); } - preempt_enable(); + preempt_enable_notrace(); return correct_ret_addr; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index ebc59781456a..64a4dde073ef 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -60,6 +60,7 @@ */ bool ring_buffer_expanded; +#ifdef CONFIG_FTRACE_STARTUP_TEST /* * We need to change this state when a selftest is running. * A selftest will lurk into the ring-buffer to count the @@ -75,7 +76,6 @@ static bool __read_mostly tracing_selftest_running; */ bool __read_mostly tracing_selftest_disabled; -#ifdef CONFIG_FTRACE_STARTUP_TEST void __init disable_tracing_selftest(const char *reason) { if (!tracing_selftest_disabled) { @@ -83,6 +83,9 @@ void __init disable_tracing_selftest(const char *reason) pr_info("Ftrace startup test is disabled due to %s\n", reason); } } +#else +#define tracing_selftest_running 0 +#define tracing_selftest_disabled 0 #endif /* Pipe tracepoints to printk */ @@ -1051,7 +1054,10 @@ int __trace_array_puts(struct trace_array *tr, unsigned long ip, if (!(tr->trace_flags & TRACE_ITER_PRINTK)) return 0; - if (unlikely(tracing_selftest_running || tracing_disabled)) + if (unlikely(tracing_selftest_running && tr == &global_trace)) + return 0; + + if (unlikely(tracing_disabled)) return 0; alloc = sizeof(*entry) + size + 2; /* possible \n added */ @@ -2041,6 +2047,24 @@ static int run_tracer_selftest(struct tracer *type) return 0; } +static int do_run_tracer_selftest(struct tracer *type) +{ + int ret; + + /* + * Tests can take a long time, especially if they are run one after the + * other, as does happen during bootup when all the tracers are + * registered. This could cause the soft lockup watchdog to trigger. + */ + cond_resched(); + + tracing_selftest_running = true; + ret = run_tracer_selftest(type); + tracing_selftest_running = false; + + return ret; +} + static __init int init_trace_selftests(void) { struct trace_selftests *p, *n; @@ -2092,6 +2116,10 @@ static inline int run_tracer_selftest(struct tracer *type) { return 0; } +static inline int do_run_tracer_selftest(struct tracer *type) +{ + return 0; +} #endif /* CONFIG_FTRACE_STARTUP_TEST */ static void add_tracer_options(struct trace_array *tr, struct tracer *t); @@ -2127,8 +2155,6 @@ int __init register_tracer(struct tracer *type) mutex_lock(&trace_types_lock); - tracing_selftest_running = true; - for (t = trace_types; t; t = t->next) { if (strcmp(type->name, t->name) == 0) { /* already found */ @@ -2157,7 +2183,7 @@ int __init register_tracer(struct tracer *type) /* store the tracer for __set_tracer_option */ type->flags->trace = type; - ret = run_tracer_selftest(type); + ret = do_run_tracer_selftest(type); if (ret < 0) goto out; @@ -2166,7 +2192,6 @@ int __init register_tracer(struct tracer *type) add_tracer_options(&global_trace, type); out: - tracing_selftest_running = false; mutex_unlock(&trace_types_lock); if (ret || !default_bootup_tracer) @@ -3490,7 +3515,7 @@ __trace_array_vprintk(struct trace_buffer *buffer, unsigned int trace_ctx; char *tbuffer; - if (tracing_disabled || tracing_selftest_running) + if (tracing_disabled) return 0; /* Don't pollute graph traces with trace_vprintk internals */ @@ -3538,6 +3563,9 @@ __printf(3, 0) int trace_array_vprintk(struct trace_array *tr, unsigned long ip, const char *fmt, va_list args) { + if (tracing_selftest_running && tr == &global_trace) + return 0; + return __trace_array_vprintk(tr->array_buffer.buffer, ip, fmt, args); } @@ -5752,7 +5780,7 @@ static const char readme_msg[] = "\t table using the key(s) and value(s) named, and the value of a\n" "\t sum called 'hitcount' is incremented. Keys and values\n" "\t correspond to fields in the event's format description. Keys\n" - "\t can be any field, or the special string 'stacktrace'.\n" + "\t can be any field, or the special string 'common_stacktrace'.\n" "\t Compound keys consisting of up to two fields can be specified\n" "\t by the 'keys' keyword. Values must correspond to numeric\n" "\t fields. Sort keys consisting of up to two fields can be\n" diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 654ffa40457a..57e539d47989 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -194,6 +194,8 @@ static int trace_define_generic_fields(void) __generic_field(int, common_cpu, FILTER_CPU); __generic_field(char *, COMM, FILTER_COMM); __generic_field(char *, comm, FILTER_COMM); + __generic_field(char *, stacktrace, FILTER_STACKTRACE); + __generic_field(char *, STACKTRACE, FILTER_STACKTRACE); return ret; } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 486cca3c2b75..b97d3ad832f1 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1364,7 +1364,7 @@ static const char *hist_field_name(struct hist_field *field, if (field->field) field_name = field->field->name; else - field_name = "stacktrace"; + field_name = "common_stacktrace"; } else if (field->flags & HIST_FIELD_FL_HITCOUNT) field_name = "hitcount"; @@ -2367,7 +2367,7 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, hist_data->enable_timestamps = true; if (*flags & HIST_FIELD_FL_TIMESTAMP_USECS) hist_data->attrs->ts_in_usecs = true; - } else if (strcmp(field_name, "stacktrace") == 0) { + } else if (strcmp(field_name, "common_stacktrace") == 0) { *flags |= HIST_FIELD_FL_STACKTRACE; } else if (strcmp(field_name, "common_cpu") == 0) *flags |= HIST_FIELD_FL_CPU; @@ -2378,11 +2378,15 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, if (!field || !field->size) { /* * For backward compatibility, if field_name - * was "cpu", then we treat this the same as - * common_cpu. This also works for "CPU". + * was "cpu" or "stacktrace", then we treat this + * the same as common_cpu and common_stacktrace + * respectively. This also works for "CPU", and + * "STACKTRACE". */ if (field && field->filter_type == FILTER_CPU) { *flags |= HIST_FIELD_FL_CPU; + } else if (field && field->filter_type == FILTER_STACKTRACE) { + *flags |= HIST_FIELD_FL_STACKTRACE; } else { hist_err(tr, HIST_ERR_FIELD_NOT_FOUND, errpos(field_name)); @@ -4238,13 +4242,19 @@ static int __create_val_field(struct hist_trigger_data *hist_data, goto out; } - /* Some types cannot be a value */ - if (hist_field->flags & (HIST_FIELD_FL_GRAPH | HIST_FIELD_FL_PERCENT | - HIST_FIELD_FL_BUCKET | HIST_FIELD_FL_LOG2 | - HIST_FIELD_FL_SYM | HIST_FIELD_FL_SYM_OFFSET | - HIST_FIELD_FL_SYSCALL | HIST_FIELD_FL_STACKTRACE)) { - hist_err(file->tr, HIST_ERR_BAD_FIELD_MODIFIER, errpos(field_str)); - ret = -EINVAL; + /* values and variables should not have some modifiers */ + if (hist_field->flags & HIST_FIELD_FL_VAR) { + /* Variable */ + if (hist_field->flags & (HIST_FIELD_FL_GRAPH | HIST_FIELD_FL_PERCENT | + HIST_FIELD_FL_BUCKET | HIST_FIELD_FL_LOG2)) + goto err; + } else { + /* Value */ + if (hist_field->flags & (HIST_FIELD_FL_GRAPH | HIST_FIELD_FL_PERCENT | + HIST_FIELD_FL_BUCKET | HIST_FIELD_FL_LOG2 | + HIST_FIELD_FL_SYM | HIST_FIELD_FL_SYM_OFFSET | + HIST_FIELD_FL_SYSCALL | HIST_FIELD_FL_STACKTRACE)) + goto err; } hist_data->fields[val_idx] = hist_field; @@ -4256,6 +4266,9 @@ static int __create_val_field(struct hist_trigger_data *hist_data, ret = -EINVAL; out: return ret; + err: + hist_err(file->tr, HIST_ERR_BAD_FIELD_MODIFIER, errpos(field_str)); + return -EINVAL; } static int create_val_field(struct hist_trigger_data *hist_data, @@ -5385,7 +5398,7 @@ static void hist_trigger_print_key(struct seq_file *m, if (key_field->field) seq_printf(m, "%s.stacktrace", key_field->field->name); else - seq_puts(m, "stacktrace:\n"); + seq_puts(m, "common_stacktrace:\n"); hist_trigger_stacktrace_print(m, key + key_field->offset, HIST_STACKTRACE_DEPTH); @@ -5968,7 +5981,7 @@ static int event_hist_trigger_print(struct seq_file *m, if (field->field) seq_printf(m, "%s.stacktrace", field->field->name); else - seq_puts(m, "stacktrace"); + seq_puts(m, "common_stacktrace"); } else hist_field_print(m, field); } diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index b1ecd7677642..dbb14705d0d3 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -96,12 +96,12 @@ struct user_event { * these to track enablement sites that are tied to an event. */ struct user_event_enabler { - struct list_head link; + struct list_head mm_enablers_link; struct user_event *event; unsigned long addr; /* Track enable bit, flags, etc. Aligned for bitops. */ - unsigned int values; + unsigned long values; }; /* Bits 0-5 are for the bit to update upon enable/disable (0-63 allowed) */ @@ -116,7 +116,9 @@ struct user_event_enabler { /* Only duplicate the bit value */ #define ENABLE_VAL_DUP_MASK ENABLE_VAL_BIT_MASK -#define ENABLE_BITOPS(e) ((unsigned long *)&(e)->values) +#define ENABLE_BITOPS(e) (&(e)->values) + +#define ENABLE_BIT(e) ((int)((e)->values & ENABLE_VAL_BIT_MASK)) /* Used for asynchronous faulting in of pages */ struct user_event_enabler_fault { @@ -153,7 +155,7 @@ struct user_event_file_info { #define VALIDATOR_REL (1 << 1) struct user_event_validator { - struct list_head link; + struct list_head user_event_link; int offset; int flags; }; @@ -259,7 +261,7 @@ error: static void user_event_enabler_destroy(struct user_event_enabler *enabler) { - list_del_rcu(&enabler->link); + list_del_rcu(&enabler->mm_enablers_link); /* No longer tracking the event via the enabler */ refcount_dec(&enabler->event->refcnt); @@ -423,9 +425,9 @@ static int user_event_enabler_write(struct user_event_mm *mm, /* Update bit atomically, user tracers must be atomic as well */ if (enabler->event && enabler->event->status) - set_bit(enabler->values & ENABLE_VAL_BIT_MASK, ptr); + set_bit(ENABLE_BIT(enabler), ptr); else - clear_bit(enabler->values & ENABLE_VAL_BIT_MASK, ptr); + clear_bit(ENABLE_BIT(enabler), ptr); kunmap_local(kaddr); unpin_user_pages_dirty_lock(&page, 1, true); @@ -437,11 +439,9 @@ static bool user_event_enabler_exists(struct user_event_mm *mm, unsigned long uaddr, unsigned char bit) { struct user_event_enabler *enabler; - struct user_event_enabler *next; - list_for_each_entry_safe(enabler, next, &mm->enablers, link) { - if (enabler->addr == uaddr && - (enabler->values & ENABLE_VAL_BIT_MASK) == bit) + list_for_each_entry(enabler, &mm->enablers, mm_enablers_link) { + if (enabler->addr == uaddr && ENABLE_BIT(enabler) == bit) return true; } @@ -451,23 +451,36 @@ static bool user_event_enabler_exists(struct user_event_mm *mm, static void user_event_enabler_update(struct user_event *user) { struct user_event_enabler *enabler; - struct user_event_mm *mm = user_event_mm_get_all(user); struct user_event_mm *next; + struct user_event_mm *mm; int attempt; + lockdep_assert_held(&event_mutex); + + /* + * We need to build a one-shot list of all the mms that have an + * enabler for the user_event passed in. This list is only valid + * while holding the event_mutex. The only reason for this is due + * to the global mm list being RCU protected and we use methods + * which can wait (mmap_read_lock and pin_user_pages_remote). + * + * NOTE: user_event_mm_get_all() increments the ref count of each + * mm that is added to the list to prevent removal timing windows. + * We must always put each mm after they are used, which may wait. + */ + mm = user_event_mm_get_all(user); + while (mm) { next = mm->next; mmap_read_lock(mm->mm); - rcu_read_lock(); - list_for_each_entry_rcu(enabler, &mm->enablers, link) { + list_for_each_entry(enabler, &mm->enablers, mm_enablers_link) { if (enabler->event == user) { attempt = 0; user_event_enabler_write(mm, enabler, true, &attempt); } } - rcu_read_unlock(); mmap_read_unlock(mm->mm); user_event_mm_put(mm); mm = next; @@ -495,7 +508,9 @@ static bool user_event_enabler_dup(struct user_event_enabler *orig, enabler->values = orig->values & ENABLE_VAL_DUP_MASK; refcount_inc(&enabler->event->refcnt); - list_add_rcu(&enabler->link, &mm->enablers); + + /* Enablers not exposed yet, RCU not required */ + list_add(&enabler->mm_enablers_link, &mm->enablers); return true; } @@ -514,6 +529,14 @@ static struct user_event_mm *user_event_mm_get_all(struct user_event *user) struct user_event_mm *mm; /* + * We use the mm->next field to build a one-shot list from the global + * RCU protected list. To build this list the event_mutex must be held. + * This lets us build a list without requiring allocs that could fail + * when user based events are most wanted for diagnostics. + */ + lockdep_assert_held(&event_mutex); + + /* * We do not want to block fork/exec while enablements are being * updated, so we use RCU to walk the current tasks that have used * user_events ABI for 1 or more events. Each enabler found in each @@ -525,23 +548,24 @@ static struct user_event_mm *user_event_mm_get_all(struct user_event *user) */ rcu_read_lock(); - list_for_each_entry_rcu(mm, &user_event_mms, link) - list_for_each_entry_rcu(enabler, &mm->enablers, link) + list_for_each_entry_rcu(mm, &user_event_mms, mms_link) { + list_for_each_entry_rcu(enabler, &mm->enablers, mm_enablers_link) { if (enabler->event == user) { mm->next = found; found = user_event_mm_get(mm); break; } + } + } rcu_read_unlock(); return found; } -static struct user_event_mm *user_event_mm_create(struct task_struct *t) +static struct user_event_mm *user_event_mm_alloc(struct task_struct *t) { struct user_event_mm *user_mm; - unsigned long flags; user_mm = kzalloc(sizeof(*user_mm), GFP_KERNEL_ACCOUNT); @@ -553,12 +577,6 @@ static struct user_event_mm *user_event_mm_create(struct task_struct *t) refcount_set(&user_mm->refcnt, 1); refcount_set(&user_mm->tasks, 1); - spin_lock_irqsave(&user_event_mms_lock, flags); - list_add_rcu(&user_mm->link, &user_event_mms); - spin_unlock_irqrestore(&user_event_mms_lock, flags); - - t->user_event_mm = user_mm; - /* * The lifetime of the memory descriptor can slightly outlast * the task lifetime if a ref to the user_event_mm is taken @@ -572,6 +590,17 @@ static struct user_event_mm *user_event_mm_create(struct task_struct *t) return user_mm; } +static void user_event_mm_attach(struct user_event_mm *user_mm, struct task_struct *t) +{ + unsigned long flags; + + spin_lock_irqsave(&user_event_mms_lock, flags); + list_add_rcu(&user_mm->mms_link, &user_event_mms); + spin_unlock_irqrestore(&user_event_mms_lock, flags); + + t->user_event_mm = user_mm; +} + static struct user_event_mm *current_user_event_mm(void) { struct user_event_mm *user_mm = current->user_event_mm; @@ -579,10 +608,12 @@ static struct user_event_mm *current_user_event_mm(void) if (user_mm) goto inc; - user_mm = user_event_mm_create(current); + user_mm = user_event_mm_alloc(current); if (!user_mm) goto error; + + user_event_mm_attach(user_mm, current); inc: refcount_inc(&user_mm->refcnt); error: @@ -593,7 +624,7 @@ static void user_event_mm_destroy(struct user_event_mm *mm) { struct user_event_enabler *enabler, *next; - list_for_each_entry_safe(enabler, next, &mm->enablers, link) + list_for_each_entry_safe(enabler, next, &mm->enablers, mm_enablers_link) user_event_enabler_destroy(enabler); mmdrop(mm->mm); @@ -630,7 +661,7 @@ void user_event_mm_remove(struct task_struct *t) /* Remove the mm from the list, so it can no longer be enabled */ spin_lock_irqsave(&user_event_mms_lock, flags); - list_del_rcu(&mm->link); + list_del_rcu(&mm->mms_link); spin_unlock_irqrestore(&user_event_mms_lock, flags); /* @@ -670,7 +701,7 @@ void user_event_mm_remove(struct task_struct *t) void user_event_mm_dup(struct task_struct *t, struct user_event_mm *old_mm) { - struct user_event_mm *mm = user_event_mm_create(t); + struct user_event_mm *mm = user_event_mm_alloc(t); struct user_event_enabler *enabler; if (!mm) @@ -678,16 +709,18 @@ void user_event_mm_dup(struct task_struct *t, struct user_event_mm *old_mm) rcu_read_lock(); - list_for_each_entry_rcu(enabler, &old_mm->enablers, link) + list_for_each_entry_rcu(enabler, &old_mm->enablers, mm_enablers_link) { if (!user_event_enabler_dup(enabler, mm)) goto error; + } rcu_read_unlock(); + user_event_mm_attach(mm, t); return; error: rcu_read_unlock(); - user_event_mm_remove(t); + user_event_mm_destroy(mm); } static bool current_user_event_enabler_exists(unsigned long uaddr, @@ -748,7 +781,7 @@ retry: */ if (!*write_result) { refcount_inc(&enabler->event->refcnt); - list_add_rcu(&enabler->link, &user_mm->enablers); + list_add_rcu(&enabler->mm_enablers_link, &user_mm->enablers); } mutex_unlock(&event_mutex); @@ -904,8 +937,8 @@ static void user_event_destroy_validators(struct user_event *user) struct user_event_validator *validator, *next; struct list_head *head = &user->validators; - list_for_each_entry_safe(validator, next, head, link) { - list_del(&validator->link); + list_for_each_entry_safe(validator, next, head, user_event_link) { + list_del(&validator->user_event_link); kfree(validator); } } @@ -959,7 +992,7 @@ add_validator: validator->offset = offset; /* Want sequential access when validating */ - list_add_tail(&validator->link, &user->validators); + list_add_tail(&validator->user_event_link, &user->validators); add_field: field->type = type; @@ -1349,7 +1382,7 @@ static int user_event_validate(struct user_event *user, void *data, int len) void *pos, *end = data + len; u32 loc, offset, size; - list_for_each_entry(validator, head, link) { + list_for_each_entry(validator, head, user_event_link) { pos = data + validator->offset; /* Already done min_size check, no bounds check here */ @@ -2270,9 +2303,9 @@ static long user_events_ioctl_unreg(unsigned long uarg) */ mutex_lock(&event_mutex); - list_for_each_entry_safe(enabler, next, &mm->enablers, link) + list_for_each_entry_safe(enabler, next, &mm->enablers, mm_enablers_link) { if (enabler->addr == reg.disable_addr && - (enabler->values & ENABLE_VAL_BIT_MASK) == reg.disable_bit) { + ENABLE_BIT(enabler) == reg.disable_bit) { set_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(enabler)); if (!test_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler))) @@ -2281,6 +2314,7 @@ static long user_events_ioctl_unreg(unsigned long uarg) /* Removed at least one */ ret = 0; } + } mutex_unlock(&event_mutex); diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index efbbec2caff8..e97e3fa5cbed 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -1652,6 +1652,8 @@ static enum hrtimer_restart timerlat_irq(struct hrtimer *timer) osnoise_stop_tracing(); notify_new_max_latency(diff); + wake_up_process(tlat->kthread); + return HRTIMER_NORESTART; } } diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index ef8ed3b65d05..6a4ecfb1da43 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -308,7 +308,7 @@ trace_probe_primary_from_call(struct trace_event_call *call) { struct trace_probe_event *tpe = trace_probe_event_from_call(call); - return list_first_entry(&tpe->probes, struct trace_probe, list); + return list_first_entry_or_null(&tpe->probes, struct trace_probe, list); } static inline struct list_head *trace_probe_probe_list(struct trace_probe *tp) diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index a931d9aaea26..529590499b1f 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -848,6 +848,12 @@ trace_selftest_startup_function_graph(struct tracer *trace, } #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + /* + * These tests can take some time to run. Make sure on non PREEMPT + * kernels, we do not trigger the softlockup detector. + */ + cond_resched(); + tracing_reset_online_cpus(&tr->array_buffer); set_graph_array(tr); @@ -869,6 +875,8 @@ trace_selftest_startup_function_graph(struct tracer *trace, if (ret) goto out; + cond_resched(); + ret = register_ftrace_graph(&fgraph_ops); if (ret) { warn_failed_init_tracer(trace, ret); @@ -891,6 +899,8 @@ trace_selftest_startup_function_graph(struct tracer *trace, if (ret) goto out; + cond_resched(); + tracing_start(); if (!ret && !count) { diff --git a/kernel/vhost_task.c b/kernel/vhost_task.c index b7cbd66f889e..f80d5c51ae67 100644 --- a/kernel/vhost_task.c +++ b/kernel/vhost_task.c @@ -12,58 +12,88 @@ enum vhost_task_flags { VHOST_TASK_FLAGS_STOP, }; +struct vhost_task { + bool (*fn)(void *data); + void *data; + struct completion exited; + unsigned long flags; + struct task_struct *task; +}; + static int vhost_task_fn(void *data) { struct vhost_task *vtsk = data; - int ret; + bool dead = false; + + for (;;) { + bool did_work; + + /* mb paired w/ vhost_task_stop */ + if (test_bit(VHOST_TASK_FLAGS_STOP, &vtsk->flags)) + break; + + if (!dead && signal_pending(current)) { + struct ksignal ksig; + /* + * Calling get_signal will block in SIGSTOP, + * or clear fatal_signal_pending, but remember + * what was set. + * + * This thread won't actually exit until all + * of the file descriptors are closed, and + * the release function is called. + */ + dead = get_signal(&ksig); + if (dead) + clear_thread_flag(TIF_SIGPENDING); + } + + did_work = vtsk->fn(vtsk->data); + if (!did_work) { + set_current_state(TASK_INTERRUPTIBLE); + schedule(); + } + } - ret = vtsk->fn(vtsk->data); complete(&vtsk->exited); - do_exit(ret); + do_exit(0); +} + +/** + * vhost_task_wake - wakeup the vhost_task + * @vtsk: vhost_task to wake + * + * wake up the vhost_task worker thread + */ +void vhost_task_wake(struct vhost_task *vtsk) +{ + wake_up_process(vtsk->task); } +EXPORT_SYMBOL_GPL(vhost_task_wake); /** * vhost_task_stop - stop a vhost_task * @vtsk: vhost_task to stop * - * Callers must call vhost_task_should_stop and return from their worker - * function when it returns true; + * vhost_task_fn ensures the worker thread exits after + * VHOST_TASK_FLAGS_SOP becomes true. */ void vhost_task_stop(struct vhost_task *vtsk) { - pid_t pid = vtsk->task->pid; - set_bit(VHOST_TASK_FLAGS_STOP, &vtsk->flags); - wake_up_process(vtsk->task); + vhost_task_wake(vtsk); /* * Make sure vhost_task_fn is no longer accessing the vhost_task before - * freeing it below. If userspace crashed or exited without closing, - * then the vhost_task->task could already be marked dead so - * kernel_wait will return early. + * freeing it below. */ wait_for_completion(&vtsk->exited); - /* - * If we are just closing/removing a device and the parent process is - * not exiting then reap the task. - */ - kernel_wait4(pid, NULL, __WCLONE, NULL); kfree(vtsk); } EXPORT_SYMBOL_GPL(vhost_task_stop); /** - * vhost_task_should_stop - should the vhost task return from the work function - * @vtsk: vhost_task to stop - */ -bool vhost_task_should_stop(struct vhost_task *vtsk) -{ - return test_bit(VHOST_TASK_FLAGS_STOP, &vtsk->flags); -} -EXPORT_SYMBOL_GPL(vhost_task_should_stop); - -/** - * vhost_task_create - create a copy of a process to be used by the kernel - * @fn: thread stack + * vhost_task_create - create a copy of a task to be used by the kernel + * @fn: vhost worker function * @arg: data to be passed to fn * @name: the thread's name * @@ -71,17 +101,17 @@ EXPORT_SYMBOL_GPL(vhost_task_should_stop); * failure. The returned task is inactive, and the caller must fire it up * through vhost_task_start(). */ -struct vhost_task *vhost_task_create(int (*fn)(void *), void *arg, +struct vhost_task *vhost_task_create(bool (*fn)(void *), void *arg, const char *name) { struct kernel_clone_args args = { - .flags = CLONE_FS | CLONE_UNTRACED | CLONE_VM, + .flags = CLONE_FS | CLONE_UNTRACED | CLONE_VM | + CLONE_THREAD | CLONE_SIGHAND, .exit_signal = 0, .fn = vhost_task_fn, .name = name, .user_worker = 1, .no_files = 1, - .ignore_signals = 1, }; struct vhost_task *vtsk; struct task_struct *tsk; diff --git a/lib/cpu_rmap.c b/lib/cpu_rmap.c index 73c1636b927b..4c348670da31 100644 --- a/lib/cpu_rmap.c +++ b/lib/cpu_rmap.c @@ -280,8 +280,8 @@ static void irq_cpu_rmap_release(struct kref *ref) struct irq_glue *glue = container_of(ref, struct irq_glue, notify.kref); - cpu_rmap_put(glue->rmap); glue->rmap->obj[glue->index] = NULL; + cpu_rmap_put(glue->rmap); kfree(glue); } diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 003edc5ebd67..984985c39c9b 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -126,7 +126,7 @@ static const char *obj_states[ODEBUG_STATE_MAX] = { static void fill_pool(void) { - gfp_t gfp = GFP_ATOMIC | __GFP_NORETRY | __GFP_NOWARN; + gfp_t gfp = __GFP_HIGH | __GFP_NOWARN; struct debug_obj *obj; unsigned long flags; @@ -591,10 +591,21 @@ static void debug_objects_fill_pool(void) { /* * On RT enabled kernels the pool refill must happen in preemptible - * context: + * context -- for !RT kernels we rely on the fact that spinlock_t and + * raw_spinlock_t are basically the same type and this lock-type + * inversion works just fine. */ - if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible()) + if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible()) { + /* + * Annotate away the spinlock_t inside raw_spinlock_t warning + * by temporarily raising the wait-type to WAIT_SLEEP, matching + * the preemptible() condition above. + */ + static DEFINE_WAIT_OVERRIDE_MAP(fill_pool_map, LD_WAIT_SLEEP); + lock_map_acquire_try(&fill_pool_map); fill_pool(); + lock_map_release(&fill_pool_map); + } } static void diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 110a36479dce..8ebc43d4cc8c 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -5317,15 +5317,9 @@ int mas_empty_area(struct ma_state *mas, unsigned long min, mt = mte_node_type(mas->node); pivots = ma_pivots(mas_mn(mas), mt); - if (offset) - mas->min = pivots[offset - 1] + 1; - - if (offset < mt_pivots[mt]) - mas->max = pivots[offset]; - - if (mas->index < mas->min) - mas->index = mas->min; - + min = mas_safe_min(mas, pivots, offset); + if (mas->index < min) + mas->index = min; mas->last = mas->index + size - 1; return 0; } diff --git a/lib/net_utils.c b/lib/net_utils.c index c17201df3d08..42bb0473fb22 100644 --- a/lib/net_utils.c +++ b/lib/net_utils.c @@ -2,7 +2,8 @@ #include <linux/string.h> #include <linux/if_ether.h> #include <linux/ctype.h> -#include <linux/kernel.h> +#include <linux/export.h> +#include <linux/hex.h> bool mac_pton(const char *s, u8 *mac) { diff --git a/lib/ref_tracker.c b/lib/ref_tracker.c index dc7b14aa3431..cf5609b1ca79 100644 --- a/lib/ref_tracker.c +++ b/lib/ref_tracker.c @@ -1,11 +1,16 @@ // SPDX-License-Identifier: GPL-2.0-or-later + +#define pr_fmt(fmt) "ref_tracker: " fmt + #include <linux/export.h> +#include <linux/list_sort.h> #include <linux/ref_tracker.h> #include <linux/slab.h> #include <linux/stacktrace.h> #include <linux/stackdepot.h> #define REF_TRACKER_STACK_ENTRIES 16 +#define STACK_BUF_SIZE 1024 struct ref_tracker { struct list_head head; /* anchor into dir->list or dir->quarantine */ @@ -14,6 +19,141 @@ struct ref_tracker { depot_stack_handle_t free_stack_handle; }; +struct ref_tracker_dir_stats { + int total; + int count; + struct { + depot_stack_handle_t stack_handle; + unsigned int count; + } stacks[]; +}; + +static struct ref_tracker_dir_stats * +ref_tracker_get_stats(struct ref_tracker_dir *dir, unsigned int limit) +{ + struct ref_tracker_dir_stats *stats; + struct ref_tracker *tracker; + + stats = kmalloc(struct_size(stats, stacks, limit), + GFP_NOWAIT | __GFP_NOWARN); + if (!stats) + return ERR_PTR(-ENOMEM); + stats->total = 0; + stats->count = 0; + + list_for_each_entry(tracker, &dir->list, head) { + depot_stack_handle_t stack = tracker->alloc_stack_handle; + int i; + + ++stats->total; + for (i = 0; i < stats->count; ++i) + if (stats->stacks[i].stack_handle == stack) + break; + if (i >= limit) + continue; + if (i >= stats->count) { + stats->stacks[i].stack_handle = stack; + stats->stacks[i].count = 0; + ++stats->count; + } + ++stats->stacks[i].count; + } + + return stats; +} + +struct ostream { + char *buf; + int size, used; +}; + +#define pr_ostream(stream, fmt, args...) \ +({ \ + struct ostream *_s = (stream); \ +\ + if (!_s->buf) { \ + pr_err(fmt, ##args); \ + } else { \ + int ret, len = _s->size - _s->used; \ + ret = snprintf(_s->buf + _s->used, len, pr_fmt(fmt), ##args); \ + _s->used += min(ret, len); \ + } \ +}) + +static void +__ref_tracker_dir_pr_ostream(struct ref_tracker_dir *dir, + unsigned int display_limit, struct ostream *s) +{ + struct ref_tracker_dir_stats *stats; + unsigned int i = 0, skipped; + depot_stack_handle_t stack; + char *sbuf; + + lockdep_assert_held(&dir->lock); + + if (list_empty(&dir->list)) + return; + + stats = ref_tracker_get_stats(dir, display_limit); + if (IS_ERR(stats)) { + pr_ostream(s, "%s@%pK: couldn't get stats, error %pe\n", + dir->name, dir, stats); + return; + } + + sbuf = kmalloc(STACK_BUF_SIZE, GFP_NOWAIT | __GFP_NOWARN); + + for (i = 0, skipped = stats->total; i < stats->count; ++i) { + stack = stats->stacks[i].stack_handle; + if (sbuf && !stack_depot_snprint(stack, sbuf, STACK_BUF_SIZE, 4)) + sbuf[0] = 0; + pr_ostream(s, "%s@%pK has %d/%d users at\n%s\n", dir->name, dir, + stats->stacks[i].count, stats->total, sbuf); + skipped -= stats->stacks[i].count; + } + + if (skipped) + pr_ostream(s, "%s@%pK skipped reports about %d/%d users.\n", + dir->name, dir, skipped, stats->total); + + kfree(sbuf); + + kfree(stats); +} + +void ref_tracker_dir_print_locked(struct ref_tracker_dir *dir, + unsigned int display_limit) +{ + struct ostream os = {}; + + __ref_tracker_dir_pr_ostream(dir, display_limit, &os); +} +EXPORT_SYMBOL(ref_tracker_dir_print_locked); + +void ref_tracker_dir_print(struct ref_tracker_dir *dir, + unsigned int display_limit) +{ + unsigned long flags; + + spin_lock_irqsave(&dir->lock, flags); + ref_tracker_dir_print_locked(dir, display_limit); + spin_unlock_irqrestore(&dir->lock, flags); +} +EXPORT_SYMBOL(ref_tracker_dir_print); + +int ref_tracker_dir_snprint(struct ref_tracker_dir *dir, char *buf, size_t size) +{ + struct ostream os = { .buf = buf, .size = size }; + unsigned long flags; + + spin_lock_irqsave(&dir->lock, flags); + __ref_tracker_dir_pr_ostream(dir, 16, &os); + spin_unlock_irqrestore(&dir->lock, flags); + + return os.used; +} +EXPORT_SYMBOL(ref_tracker_dir_snprint); + void ref_tracker_dir_exit(struct ref_tracker_dir *dir) { struct ref_tracker *tracker, *n; @@ -27,13 +167,13 @@ void ref_tracker_dir_exit(struct ref_tracker_dir *dir) kfree(tracker); dir->quarantine_avail++; } - list_for_each_entry_safe(tracker, n, &dir->list, head) { - pr_err("leaked reference.\n"); - if (tracker->alloc_stack_handle) - stack_depot_print(tracker->alloc_stack_handle); + if (!list_empty(&dir->list)) { + ref_tracker_dir_print_locked(dir, 16); leak = true; - list_del(&tracker->head); - kfree(tracker); + list_for_each_entry_safe(tracker, n, &dir->list, head) { + list_del(&tracker->head); + kfree(tracker); + } } spin_unlock_irqrestore(&dir->lock, flags); WARN_ON_ONCE(leak); @@ -42,28 +182,6 @@ void ref_tracker_dir_exit(struct ref_tracker_dir *dir) } EXPORT_SYMBOL(ref_tracker_dir_exit); -void ref_tracker_dir_print(struct ref_tracker_dir *dir, - unsigned int display_limit) -{ - struct ref_tracker *tracker; - unsigned long flags; - unsigned int i = 0; - - spin_lock_irqsave(&dir->lock, flags); - list_for_each_entry(tracker, &dir->list, head) { - if (i < display_limit) { - pr_err("leaked reference.\n"); - if (tracker->alloc_stack_handle) - stack_depot_print(tracker->alloc_stack_handle); - i++; - } else { - break; - } - } - spin_unlock_irqrestore(&dir->lock, flags); -} -EXPORT_SYMBOL(ref_tracker_dir_print); - int ref_tracker_alloc(struct ref_tracker_dir *dir, struct ref_tracker **trackerp, gfp_t gfp) @@ -71,7 +189,7 @@ int ref_tracker_alloc(struct ref_tracker_dir *dir, unsigned long entries[REF_TRACKER_STACK_ENTRIES]; struct ref_tracker *tracker; unsigned int nr_entries; - gfp_t gfp_mask = gfp; + gfp_t gfp_mask = gfp | __GFP_NOWARN; unsigned long flags; WARN_ON_ONCE(dir->dead); @@ -119,7 +237,8 @@ int ref_tracker_free(struct ref_tracker_dir *dir, return -EEXIST; } nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 1); - stack_handle = stack_depot_save(entries, nr_entries, GFP_ATOMIC); + stack_handle = stack_depot_save(entries, nr_entries, + GFP_NOWAIT | __GFP_NOWARN); spin_lock_irqsave(&dir->lock, flags); if (tracker->dead) { diff --git a/lib/scatterlist.c b/lib/scatterlist.c index 8d7519a8f308..e97d7060329e 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -9,6 +9,8 @@ #include <linux/scatterlist.h> #include <linux/highmem.h> #include <linux/kmemleak.h> +#include <linux/bvec.h> +#include <linux/uio.h> /** * sg_next - return the next scatterlist entry in a list @@ -1095,3 +1097,270 @@ size_t sg_zero_buffer(struct scatterlist *sgl, unsigned int nents, return offset; } EXPORT_SYMBOL(sg_zero_buffer); + +/* + * Extract and pin a list of up to sg_max pages from UBUF- or IOVEC-class + * iterators, and add them to the scatterlist. + */ +static ssize_t extract_user_to_sg(struct iov_iter *iter, + ssize_t maxsize, + struct sg_table *sgtable, + unsigned int sg_max, + iov_iter_extraction_t extraction_flags) +{ + struct scatterlist *sg = sgtable->sgl + sgtable->nents; + struct page **pages; + unsigned int npages; + ssize_t ret = 0, res; + size_t len, off; + + /* We decant the page list into the tail of the scatterlist */ + pages = (void *)sgtable->sgl + + array_size(sg_max, sizeof(struct scatterlist)); + pages -= sg_max; + + do { + res = iov_iter_extract_pages(iter, &pages, maxsize, sg_max, + extraction_flags, &off); + if (res < 0) + goto failed; + + len = res; + maxsize -= len; + ret += len; + npages = DIV_ROUND_UP(off + len, PAGE_SIZE); + sg_max -= npages; + + for (; npages > 0; npages--) { + struct page *page = *pages; + size_t seg = min_t(size_t, PAGE_SIZE - off, len); + + *pages++ = NULL; + sg_set_page(sg, page, seg, off); + sgtable->nents++; + sg++; + len -= seg; + off = 0; + } + } while (maxsize > 0 && sg_max > 0); + + return ret; + +failed: + while (sgtable->nents > sgtable->orig_nents) + put_page(sg_page(&sgtable->sgl[--sgtable->nents])); + return res; +} + +/* + * Extract up to sg_max pages from a BVEC-type iterator and add them to the + * scatterlist. The pages are not pinned. + */ +static ssize_t extract_bvec_to_sg(struct iov_iter *iter, + ssize_t maxsize, + struct sg_table *sgtable, + unsigned int sg_max, + iov_iter_extraction_t extraction_flags) +{ + const struct bio_vec *bv = iter->bvec; + struct scatterlist *sg = sgtable->sgl + sgtable->nents; + unsigned long start = iter->iov_offset; + unsigned int i; + ssize_t ret = 0; + + for (i = 0; i < iter->nr_segs; i++) { + size_t off, len; + + len = bv[i].bv_len; + if (start >= len) { + start -= len; + continue; + } + + len = min_t(size_t, maxsize, len - start); + off = bv[i].bv_offset + start; + + sg_set_page(sg, bv[i].bv_page, len, off); + sgtable->nents++; + sg++; + sg_max--; + + ret += len; + maxsize -= len; + if (maxsize <= 0 || sg_max == 0) + break; + start = 0; + } + + if (ret > 0) + iov_iter_advance(iter, ret); + return ret; +} + +/* + * Extract up to sg_max pages from a KVEC-type iterator and add them to the + * scatterlist. This can deal with vmalloc'd buffers as well as kmalloc'd or + * static buffers. The pages are not pinned. + */ +static ssize_t extract_kvec_to_sg(struct iov_iter *iter, + ssize_t maxsize, + struct sg_table *sgtable, + unsigned int sg_max, + iov_iter_extraction_t extraction_flags) +{ + const struct kvec *kv = iter->kvec; + struct scatterlist *sg = sgtable->sgl + sgtable->nents; + unsigned long start = iter->iov_offset; + unsigned int i; + ssize_t ret = 0; + + for (i = 0; i < iter->nr_segs; i++) { + struct page *page; + unsigned long kaddr; + size_t off, len, seg; + + len = kv[i].iov_len; + if (start >= len) { + start -= len; + continue; + } + + kaddr = (unsigned long)kv[i].iov_base + start; + off = kaddr & ~PAGE_MASK; + len = min_t(size_t, maxsize, len - start); + kaddr &= PAGE_MASK; + + maxsize -= len; + ret += len; + do { + seg = min_t(size_t, len, PAGE_SIZE - off); + if (is_vmalloc_or_module_addr((void *)kaddr)) + page = vmalloc_to_page((void *)kaddr); + else + page = virt_to_page(kaddr); + + sg_set_page(sg, page, len, off); + sgtable->nents++; + sg++; + sg_max--; + + len -= seg; + kaddr += PAGE_SIZE; + off = 0; + } while (len > 0 && sg_max > 0); + + if (maxsize <= 0 || sg_max == 0) + break; + start = 0; + } + + if (ret > 0) + iov_iter_advance(iter, ret); + return ret; +} + +/* + * Extract up to sg_max folios from an XARRAY-type iterator and add them to + * the scatterlist. The pages are not pinned. + */ +static ssize_t extract_xarray_to_sg(struct iov_iter *iter, + ssize_t maxsize, + struct sg_table *sgtable, + unsigned int sg_max, + iov_iter_extraction_t extraction_flags) +{ + struct scatterlist *sg = sgtable->sgl + sgtable->nents; + struct xarray *xa = iter->xarray; + struct folio *folio; + loff_t start = iter->xarray_start + iter->iov_offset; + pgoff_t index = start / PAGE_SIZE; + ssize_t ret = 0; + size_t offset, len; + XA_STATE(xas, xa, index); + + rcu_read_lock(); + + xas_for_each(&xas, folio, ULONG_MAX) { + if (xas_retry(&xas, folio)) + continue; + if (WARN_ON(xa_is_value(folio))) + break; + if (WARN_ON(folio_test_hugetlb(folio))) + break; + + offset = offset_in_folio(folio, start); + len = min_t(size_t, maxsize, folio_size(folio) - offset); + + sg_set_page(sg, folio_page(folio, 0), len, offset); + sgtable->nents++; + sg++; + sg_max--; + + maxsize -= len; + ret += len; + if (maxsize <= 0 || sg_max == 0) + break; + } + + rcu_read_unlock(); + if (ret > 0) + iov_iter_advance(iter, ret); + return ret; +} + +/** + * extract_iter_to_sg - Extract pages from an iterator and add to an sglist + * @iter: The iterator to extract from + * @maxsize: The amount of iterator to copy + * @sgtable: The scatterlist table to fill in + * @sg_max: Maximum number of elements in @sgtable that may be filled + * @extraction_flags: Flags to qualify the request + * + * Extract the page fragments from the given amount of the source iterator and + * add them to a scatterlist that refers to all of those bits, to a maximum + * addition of @sg_max elements. + * + * The pages referred to by UBUF- and IOVEC-type iterators are extracted and + * pinned; BVEC-, KVEC- and XARRAY-type are extracted but aren't pinned; PIPE- + * and DISCARD-type are not supported. + * + * No end mark is placed on the scatterlist; that's left to the caller. + * + * @extraction_flags can have ITER_ALLOW_P2PDMA set to request peer-to-peer DMA + * be allowed on the pages extracted. + * + * If successful, @sgtable->nents is updated to include the number of elements + * added and the number of bytes added is returned. @sgtable->orig_nents is + * left unaltered. + * + * The iov_iter_extract_mode() function should be used to query how cleanup + * should be performed. + */ +ssize_t extract_iter_to_sg(struct iov_iter *iter, size_t maxsize, + struct sg_table *sgtable, unsigned int sg_max, + iov_iter_extraction_t extraction_flags) +{ + if (maxsize == 0) + return 0; + + switch (iov_iter_type(iter)) { + case ITER_UBUF: + case ITER_IOVEC: + return extract_user_to_sg(iter, maxsize, sgtable, sg_max, + extraction_flags); + case ITER_BVEC: + return extract_bvec_to_sg(iter, maxsize, sgtable, sg_max, + extraction_flags); + case ITER_KVEC: + return extract_kvec_to_sg(iter, maxsize, sgtable, sg_max, + extraction_flags); + case ITER_XARRAY: + return extract_xarray_to_sg(iter, maxsize, sgtable, sg_max, + extraction_flags); + default: + pr_err("%s(%u) unsupported\n", __func__, iov_iter_type(iter)); + WARN_ON_ONCE(1); + return -EIO; + } +} +EXPORT_SYMBOL_GPL(extract_iter_to_sg); diff --git a/lib/test_firmware.c b/lib/test_firmware.c index 05ed84c2fc4c..1d7d480b8eeb 100644 --- a/lib/test_firmware.c +++ b/lib/test_firmware.c @@ -45,6 +45,7 @@ struct test_batched_req { bool sent; const struct firmware *fw; const char *name; + const char *fw_buf; struct completion completion; struct task_struct *task; struct device *dev; @@ -175,8 +176,14 @@ static void __test_release_all_firmware(void) for (i = 0; i < test_fw_config->num_requests; i++) { req = &test_fw_config->reqs[i]; - if (req->fw) + if (req->fw) { + if (req->fw_buf) { + kfree_const(req->fw_buf); + req->fw_buf = NULL; + } release_firmware(req->fw); + req->fw = NULL; + } } vfree(test_fw_config->reqs); @@ -353,16 +360,26 @@ static ssize_t config_test_show_str(char *dst, return len; } -static int test_dev_config_update_bool(const char *buf, size_t size, +static inline int __test_dev_config_update_bool(const char *buf, size_t size, bool *cfg) { int ret; - mutex_lock(&test_fw_mutex); if (kstrtobool(buf, cfg) < 0) ret = -EINVAL; else ret = size; + + return ret; +} + +static int test_dev_config_update_bool(const char *buf, size_t size, + bool *cfg) +{ + int ret; + + mutex_lock(&test_fw_mutex); + ret = __test_dev_config_update_bool(buf, size, cfg); mutex_unlock(&test_fw_mutex); return ret; @@ -373,7 +390,8 @@ static ssize_t test_dev_config_show_bool(char *buf, bool val) return snprintf(buf, PAGE_SIZE, "%d\n", val); } -static int test_dev_config_update_size_t(const char *buf, +static int __test_dev_config_update_size_t( + const char *buf, size_t size, size_t *cfg) { @@ -384,9 +402,7 @@ static int test_dev_config_update_size_t(const char *buf, if (ret) return ret; - mutex_lock(&test_fw_mutex); *(size_t *)cfg = new; - mutex_unlock(&test_fw_mutex); /* Always return full write size even if we didn't consume all */ return size; @@ -402,7 +418,7 @@ static ssize_t test_dev_config_show_int(char *buf, int val) return snprintf(buf, PAGE_SIZE, "%d\n", val); } -static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg) +static int __test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg) { u8 val; int ret; @@ -411,14 +427,23 @@ static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg) if (ret) return ret; - mutex_lock(&test_fw_mutex); *(u8 *)cfg = val; - mutex_unlock(&test_fw_mutex); /* Always return full write size even if we didn't consume all */ return size; } +static int test_dev_config_update_u8(const char *buf, size_t size, u8 *cfg) +{ + int ret; + + mutex_lock(&test_fw_mutex); + ret = __test_dev_config_update_u8(buf, size, cfg); + mutex_unlock(&test_fw_mutex); + + return ret; +} + static ssize_t test_dev_config_show_u8(char *buf, u8 val) { return snprintf(buf, PAGE_SIZE, "%u\n", val); @@ -471,10 +496,10 @@ static ssize_t config_num_requests_store(struct device *dev, mutex_unlock(&test_fw_mutex); goto out; } - mutex_unlock(&test_fw_mutex); - rc = test_dev_config_update_u8(buf, count, - &test_fw_config->num_requests); + rc = __test_dev_config_update_u8(buf, count, + &test_fw_config->num_requests); + mutex_unlock(&test_fw_mutex); out: return rc; @@ -518,10 +543,10 @@ static ssize_t config_buf_size_store(struct device *dev, mutex_unlock(&test_fw_mutex); goto out; } - mutex_unlock(&test_fw_mutex); - rc = test_dev_config_update_size_t(buf, count, - &test_fw_config->buf_size); + rc = __test_dev_config_update_size_t(buf, count, + &test_fw_config->buf_size); + mutex_unlock(&test_fw_mutex); out: return rc; @@ -548,10 +573,10 @@ static ssize_t config_file_offset_store(struct device *dev, mutex_unlock(&test_fw_mutex); goto out; } - mutex_unlock(&test_fw_mutex); - rc = test_dev_config_update_size_t(buf, count, - &test_fw_config->file_offset); + rc = __test_dev_config_update_size_t(buf, count, + &test_fw_config->file_offset); + mutex_unlock(&test_fw_mutex); out: return rc; @@ -652,6 +677,8 @@ static ssize_t trigger_request_store(struct device *dev, mutex_lock(&test_fw_mutex); release_firmware(test_firmware); + if (test_fw_config->reqs) + __test_release_all_firmware(); test_firmware = NULL; rc = request_firmware(&test_firmware, name, dev); if (rc) { @@ -752,6 +779,8 @@ static ssize_t trigger_async_request_store(struct device *dev, mutex_lock(&test_fw_mutex); release_firmware(test_firmware); test_firmware = NULL; + if (test_fw_config->reqs) + __test_release_all_firmware(); rc = request_firmware_nowait(THIS_MODULE, 1, name, dev, GFP_KERNEL, NULL, trigger_async_request_cb); if (rc) { @@ -794,6 +823,8 @@ static ssize_t trigger_custom_fallback_store(struct device *dev, mutex_lock(&test_fw_mutex); release_firmware(test_firmware); + if (test_fw_config->reqs) + __test_release_all_firmware(); test_firmware = NULL; rc = request_firmware_nowait(THIS_MODULE, FW_ACTION_NOUEVENT, name, dev, GFP_KERNEL, NULL, @@ -856,6 +887,8 @@ static int test_fw_run_batch_request(void *data) test_fw_config->buf_size); if (!req->fw) kfree(test_buf); + else + req->fw_buf = test_buf; } else { req->rc = test_fw_config->req_firmware(&req->fw, req->name, @@ -895,6 +928,11 @@ static ssize_t trigger_batched_requests_store(struct device *dev, mutex_lock(&test_fw_mutex); + if (test_fw_config->reqs) { + rc = -EBUSY; + goto out_bail; + } + test_fw_config->reqs = vzalloc(array3_size(sizeof(struct test_batched_req), test_fw_config->num_requests, 2)); @@ -911,6 +949,7 @@ static ssize_t trigger_batched_requests_store(struct device *dev, req->fw = NULL; req->idx = i; req->name = test_fw_config->name; + req->fw_buf = NULL; req->dev = dev; init_completion(&req->completion); req->task = kthread_run(test_fw_run_batch_request, req, @@ -993,6 +1032,11 @@ ssize_t trigger_batched_requests_async_store(struct device *dev, mutex_lock(&test_fw_mutex); + if (test_fw_config->reqs) { + rc = -EBUSY; + goto out_bail; + } + test_fw_config->reqs = vzalloc(array3_size(sizeof(struct test_batched_req), test_fw_config->num_requests, 2)); @@ -1010,6 +1054,7 @@ ssize_t trigger_batched_requests_async_store(struct device *dev, for (i = 0; i < test_fw_config->num_requests; i++) { req = &test_fw_config->reqs[i]; req->name = test_fw_config->name; + req->fw_buf = NULL; req->fw = NULL; req->idx = i; init_completion(&req->completion); diff --git a/lib/test_ref_tracker.c b/lib/test_ref_tracker.c index 19d7dec70cc6..49970a7c96f3 100644 --- a/lib/test_ref_tracker.c +++ b/lib/test_ref_tracker.c @@ -64,7 +64,7 @@ static int __init test_ref_tracker_init(void) { int i; - ref_tracker_dir_init(&ref_dir, 100); + ref_tracker_dir_init(&ref_dir, 100, "selftest"); timer_setup(&test_ref_tracker_timer, test_ref_tracker_timer_func, 0); mod_timer(&test_ref_tracker_timer, jiffies + 1); diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug index a925415b4d10..018a5bd2f576 100644 --- a/mm/Kconfig.debug +++ b/mm/Kconfig.debug @@ -98,6 +98,7 @@ config PAGE_OWNER config PAGE_TABLE_CHECK bool "Check for invalid mappings in user page tables" depends on ARCH_SUPPORTS_PAGE_TABLE_CHECK + depends on EXCLUSIVE_SYSTEM_RAM select PAGE_EXTENSION help Check that anonymous page is not being mapped twice with read write diff --git a/mm/kfence/kfence.h b/mm/kfence/kfence.h index 2aafc46a4aaf..392fb273e7bd 100644 --- a/mm/kfence/kfence.h +++ b/mm/kfence/kfence.h @@ -29,7 +29,7 @@ * canary of every 8 bytes is the same. 64-bit memory can be filled and checked * at a time instead of byte by byte to improve performance. */ -#define KFENCE_CANARY_PATTERN_U64 ((u64)0xaaaaaaaaaaaaaaaa ^ (u64)(0x0706050403020100)) +#define KFENCE_CANARY_PATTERN_U64 ((u64)0xaaaaaaaaaaaaaaaa ^ (u64)(le64_to_cpu(0x0706050403020100))) /* Maximum stack depth for reports. */ #define KFENCE_STACK_DEPTH 64 diff --git a/mm/page_table_check.c b/mm/page_table_check.c index 25d8610c0042..f2baf97d5f38 100644 --- a/mm/page_table_check.c +++ b/mm/page_table_check.c @@ -71,6 +71,8 @@ static void page_table_check_clear(struct mm_struct *mm, unsigned long addr, page = pfn_to_page(pfn); page_ext = page_ext_get(page); + + BUG_ON(PageSlab(page)); anon = PageAnon(page); for (i = 0; i < pgcnt; i++) { @@ -107,6 +109,8 @@ static void page_table_check_set(struct mm_struct *mm, unsigned long addr, page = pfn_to_page(pfn); page_ext = page_ext_get(page); + + BUG_ON(PageSlab(page)); anon = PageAnon(page); for (i = 0; i < pgcnt; i++) { @@ -133,6 +137,8 @@ void __page_table_check_zero(struct page *page, unsigned int order) struct page_ext *page_ext; unsigned long i; + BUG_ON(PageSlab(page)); + page_ext = page_ext_get(page); BUG_ON(!page_ext); for (i = 0; i < (1ul << order); i++) { diff --git a/mm/shrinker_debug.c b/mm/shrinker_debug.c index 3f83b10c5031..fe10436d9911 100644 --- a/mm/shrinker_debug.c +++ b/mm/shrinker_debug.c @@ -237,7 +237,8 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) } EXPORT_SYMBOL(shrinker_debugfs_rename); -struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker) +struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, + int *debugfs_id) { struct dentry *entry = shrinker->debugfs_entry; @@ -246,14 +247,18 @@ struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker) kfree_const(shrinker->name); shrinker->name = NULL; - if (entry) { - ida_free(&shrinker_debugfs_ida, shrinker->debugfs_id); - shrinker->debugfs_entry = NULL; - } + *debugfs_id = entry ? shrinker->debugfs_id : -1; + shrinker->debugfs_entry = NULL; return entry; } +void shrinker_debugfs_remove(struct dentry *debugfs_entry, int debugfs_id) +{ + debugfs_remove_recursive(debugfs_entry); + ida_free(&shrinker_debugfs_ida, debugfs_id); +} + static int __init shrinker_debugfs_init(void) { struct shrinker *shrinker; diff --git a/mm/vmscan.c b/mm/vmscan.c index d257916f39e5..6d0cd2840cf0 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -805,6 +805,7 @@ EXPORT_SYMBOL(register_shrinker); void unregister_shrinker(struct shrinker *shrinker) { struct dentry *debugfs_entry; + int debugfs_id; if (!(shrinker->flags & SHRINKER_REGISTERED)) return; @@ -814,13 +815,13 @@ void unregister_shrinker(struct shrinker *shrinker) shrinker->flags &= ~SHRINKER_REGISTERED; if (shrinker->flags & SHRINKER_MEMCG_AWARE) unregister_memcg_shrinker(shrinker); - debugfs_entry = shrinker_debugfs_remove(shrinker); + debugfs_entry = shrinker_debugfs_detach(shrinker, &debugfs_id); mutex_unlock(&shrinker_mutex); atomic_inc(&shrinker_srcu_generation); synchronize_srcu(&shrinker_srcu); - debugfs_remove_recursive(debugfs_entry); + shrinker_debugfs_remove(debugfs_entry, debugfs_id); kfree(shrinker->nr_deferred); shrinker->nr_deferred = NULL; diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 44ddaf5d601e..02f7f414aade 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -1331,31 +1331,6 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, obj_to_location(obj, &page, &obj_idx); zspage = get_zspage(page); -#ifdef CONFIG_ZPOOL - /* - * Move the zspage to front of pool's LRU. - * - * Note that this is swap-specific, so by definition there are no ongoing - * accesses to the memory while the page is swapped out that would make - * it "hot". A new entry is hot, then ages to the tail until it gets either - * written back or swaps back in. - * - * Furthermore, map is also called during writeback. We must not put an - * isolated page on the LRU mid-reclaim. - * - * As a result, only update the LRU when the page is mapped for write - * when it's first instantiated. - * - * This is a deviation from the other backends, which perform this update - * in the allocation function (zbud_alloc, z3fold_alloc). - */ - if (mm == ZS_MM_WO) { - if (!list_empty(&zspage->lru)) - list_del(&zspage->lru); - list_add(&zspage->lru, &pool->lru); - } -#endif - /* * migration cannot move any zpages in this zspage. Here, pool->lock * is too heavy since callers would take some time until they calls @@ -1525,9 +1500,8 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) fix_fullness_group(class, zspage); record_obj(handle, obj); class_stat_inc(class, ZS_OBJS_INUSE, 1); - spin_unlock(&pool->lock); - return handle; + goto out; } spin_unlock(&pool->lock); @@ -1550,6 +1524,14 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) /* We completely set up zspage so mark them as movable */ SetZsPageMovable(pool, zspage); +out: +#ifdef CONFIG_ZPOOL + /* Add/move zspage to beginning of LRU */ + if (!list_empty(&zspage->lru)) + list_del(&zspage->lru); + list_add(&zspage->lru, &pool->lru); +#endif + spin_unlock(&pool->lock); return handle; diff --git a/mm/zswap.c b/mm/zswap.c index e1e621d0b6a0..59da2a415fbb 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1020,6 +1020,22 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) goto fail; case ZSWAP_SWAPCACHE_NEW: /* page is locked */ + /* + * Having a local reference to the zswap entry doesn't exclude + * swapping from invalidating and recycling the swap slot. Once + * the swapcache is secured against concurrent swapping to and + * from the slot, recheck that the entry is still current before + * writing. + */ + spin_lock(&tree->lock); + if (zswap_rb_search(&tree->rbroot, entry->offset) != entry) { + spin_unlock(&tree->lock); + delete_from_swap_cache(page_folio(page)); + ret = -ENOMEM; + goto fail; + } + spin_unlock(&tree->lock); + /* decompress */ acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); dlen = PAGE_SIZE; diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 870e4935d6e6..b90781b9ece6 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -109,8 +109,8 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb, * NOTE: THIS ASSUMES DIX ETHERNET, SPECIFICALLY NOT SUPPORTING * OTHER THINGS LIKE FDDI/TokenRing/802.3 SNAPs... */ - if (veth->h_vlan_proto != vlan->vlan_proto || - vlan->flags & VLAN_FLAG_REORDER_HDR) { + if (vlan->flags & VLAN_FLAG_REORDER_HDR || + veth->h_vlan_proto != vlan->vlan_proto) { u16 vlan_tci; vlan_tci = vlan->vlan_id; vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb->priority); diff --git a/net/Kconfig b/net/Kconfig index 7d39c1773eb4..2fb25b534df5 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -324,7 +324,7 @@ config CGROUP_NET_CLASSID config NET_RX_BUSY_POLL bool - default y if !PREEMPT_RT + default y if !PREEMPT_RT || (PREEMPT_RT && !NETCONSOLE) config BQL bool diff --git a/net/atm/resources.c b/net/atm/resources.c index 2b2d33eeaf20..995d29e7fb13 100644 --- a/net/atm/resources.c +++ b/net/atm/resources.c @@ -400,6 +400,7 @@ done: return error; } +#ifdef CONFIG_PROC_FS void *atm_dev_seq_start(struct seq_file *seq, loff_t *pos) { mutex_lock(&atm_dev_mutex); @@ -415,3 +416,4 @@ void *atm_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) { return seq_list_next(v, &atm_devs, pos); } +#endif diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 6968e55eb971..28a939d56090 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -101,7 +101,6 @@ static void batadv_dat_purge(struct work_struct *work); */ static void batadv_dat_start_timer(struct batadv_priv *bat_priv) { - INIT_DELAYED_WORK(&bat_priv->dat.work, batadv_dat_purge); queue_delayed_work(batadv_event_workqueue, &bat_priv->dat.work, msecs_to_jiffies(10000)); } @@ -819,6 +818,7 @@ int batadv_dat_init(struct batadv_priv *bat_priv) if (!bat_priv->dat.hash) return -ENOMEM; + INIT_DELAYED_WORK(&bat_priv->dat.work, batadv_dat_purge); batadv_dat_start_timer(bat_priv); batadv_tvlv_handler_register(bat_priv, batadv_dat_tvlv_ogm_handler_v1, diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 640b951bf40a..1ef952bda97d 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -947,8 +947,8 @@ static void find_cis(struct hci_conn *conn, void *data) { struct iso_list_data *d = data; - /* Ignore broadcast */ - if (!bacmp(&conn->dst, BDADDR_ANY)) + /* Ignore broadcast or if CIG don't match */ + if (!bacmp(&conn->dst, BDADDR_ANY) || d->cig != conn->iso_qos.ucast.cig) return; d->count++; @@ -963,12 +963,17 @@ static void cis_cleanup(struct hci_conn *conn) struct hci_dev *hdev = conn->hdev; struct iso_list_data d; + if (conn->iso_qos.ucast.cig == BT_ISO_QOS_CIG_UNSET) + return; + memset(&d, 0, sizeof(d)); d.cig = conn->iso_qos.ucast.cig; /* Check if ISO connection is a CIS and remove CIG if there are * no other connections using it. */ + hci_conn_hash_list_state(hdev, find_cis, ISO_LINK, BT_BOUND, &d); + hci_conn_hash_list_state(hdev, find_cis, ISO_LINK, BT_CONNECT, &d); hci_conn_hash_list_state(hdev, find_cis, ISO_LINK, BT_CONNECTED, &d); if (d.count) return; @@ -1083,8 +1088,28 @@ static void hci_conn_unlink(struct hci_conn *conn) if (!conn->parent) { struct hci_link *link, *t; - list_for_each_entry_safe(link, t, &conn->link_list, list) - hci_conn_unlink(link->conn); + list_for_each_entry_safe(link, t, &conn->link_list, list) { + struct hci_conn *child = link->conn; + + hci_conn_unlink(child); + + /* If hdev is down it means + * hci_dev_close_sync/hci_conn_hash_flush is in progress + * and links don't need to be cleanup as all connections + * would be cleanup. + */ + if (!test_bit(HCI_UP, &hdev->flags)) + continue; + + /* Due to race, SCO connection might be not established + * yet at this point. Delete it now, otherwise it is + * possible for it to be stuck and can't be deleted. + */ + if ((child->type == SCO_LINK || + child->type == ESCO_LINK) && + child->handle == HCI_CONN_HANDLE_UNSET) + hci_conn_del(child); + } return; } @@ -1092,35 +1117,30 @@ static void hci_conn_unlink(struct hci_conn *conn) if (!conn->link) return; - hci_conn_put(conn->parent); - conn->parent = NULL; - list_del_rcu(&conn->link->list); synchronize_rcu(); + hci_conn_drop(conn->parent); + hci_conn_put(conn->parent); + conn->parent = NULL; + kfree(conn->link); conn->link = NULL; - - /* Due to race, SCO connection might be not established - * yet at this point. Delete it now, otherwise it is - * possible for it to be stuck and can't be deleted. - */ - if (conn->handle == HCI_CONN_HANDLE_UNSET) - hci_conn_del(conn); } -int hci_conn_del(struct hci_conn *conn) +void hci_conn_del(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; BT_DBG("%s hcon %p handle %d", hdev->name, conn, conn->handle); + hci_conn_unlink(conn); + cancel_delayed_work_sync(&conn->disc_work); cancel_delayed_work_sync(&conn->auto_accept_work); cancel_delayed_work_sync(&conn->idle_work); if (conn->type == ACL_LINK) { - hci_conn_unlink(conn); /* Unacked frames */ hdev->acl_cnt += conn->sent; } else if (conn->type == LE_LINK) { @@ -1131,13 +1151,6 @@ int hci_conn_del(struct hci_conn *conn) else hdev->acl_cnt += conn->sent; } else { - struct hci_conn *acl = conn->parent; - - if (acl) { - hci_conn_unlink(conn); - hci_conn_drop(acl); - } - /* Unacked ISO frames */ if (conn->type == ISO_LINK) { if (hdev->iso_pkts) @@ -1160,8 +1173,6 @@ int hci_conn_del(struct hci_conn *conn) * rest of hci_conn_del. */ hci_conn_cleanup(conn); - - return 0; } struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src, uint8_t src_type) @@ -1760,24 +1771,23 @@ static bool hci_le_set_cig_params(struct hci_conn *conn, struct bt_iso_qos *qos) memset(&data, 0, sizeof(data)); - /* Allocate a CIG if not set */ + /* Allocate first still reconfigurable CIG if not set */ if (qos->ucast.cig == BT_ISO_QOS_CIG_UNSET) { - for (data.cig = 0x00; data.cig < 0xff; data.cig++) { + for (data.cig = 0x00; data.cig < 0xf0; data.cig++) { data.count = 0; - data.cis = 0xff; - hci_conn_hash_list_state(hdev, cis_list, ISO_LINK, - BT_BOUND, &data); + hci_conn_hash_list_state(hdev, find_cis, ISO_LINK, + BT_CONNECT, &data); if (data.count) continue; - hci_conn_hash_list_state(hdev, cis_list, ISO_LINK, + hci_conn_hash_list_state(hdev, find_cis, ISO_LINK, BT_CONNECTED, &data); if (!data.count) break; } - if (data.cig == 0xff) + if (data.cig == 0xf0) return false; /* Update CIG */ @@ -2462,22 +2472,21 @@ timer: /* Drop all connection on the device */ void hci_conn_hash_flush(struct hci_dev *hdev) { - struct hci_conn_hash *h = &hdev->conn_hash; - struct hci_conn *c, *n; + struct list_head *head = &hdev->conn_hash.list; + struct hci_conn *conn; BT_DBG("hdev %s", hdev->name); - list_for_each_entry_safe(c, n, &h->list, list) { - c->state = BT_CLOSED; - - hci_disconn_cfm(c, HCI_ERROR_LOCAL_HOST_TERM); - - /* Unlink before deleting otherwise it is possible that - * hci_conn_del removes the link which may cause the list to - * contain items already freed. - */ - hci_conn_unlink(c); - hci_conn_del(c); + /* We should not traverse the list here, because hci_conn_del + * can remove extra links, which may cause the list traversal + * to hit items that have already been released. + */ + while ((conn = list_first_entry_or_null(head, + struct hci_conn, + list)) != NULL) { + conn->state = BT_CLOSED; + hci_disconn_cfm(conn, HCI_ERROR_LOCAL_HOST_TERM); + hci_conn_del(conn); } } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index a856b1051d35..48917c68358d 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1416,10 +1416,10 @@ int hci_remove_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr) int hci_remove_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type) { - struct smp_ltk *k; + struct smp_ltk *k, *tmp; int removed = 0; - list_for_each_entry_rcu(k, &hdev->long_term_keys, list) { + list_for_each_entry_safe(k, tmp, &hdev->long_term_keys, list) { if (bacmp(bdaddr, &k->bdaddr) || k->bdaddr_type != bdaddr_type) continue; @@ -1435,9 +1435,9 @@ int hci_remove_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type) void hci_remove_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type) { - struct smp_irk *k; + struct smp_irk *k, *tmp; - list_for_each_entry_rcu(k, &hdev->identity_resolving_keys, list) { + list_for_each_entry_safe(k, tmp, &hdev->identity_resolving_keys, list) { if (bacmp(bdaddr, &k->bdaddr) || k->addr_type != addr_type) continue; @@ -2686,7 +2686,9 @@ void hci_unregister_dev(struct hci_dev *hdev) { BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus); + mutex_lock(&hdev->unregister_lock); hci_dev_set_flag(hdev, HCI_UNREGISTER); + mutex_unlock(&hdev->unregister_lock); write_lock(&hci_dev_list_lock); list_del(&hdev->list); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index d00ef6e3fc45..09ba6d8987ee 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3804,48 +3804,56 @@ static u8 hci_cc_le_set_cig_params(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct hci_rp_le_set_cig_params *rp = data; + struct hci_cp_le_set_cig_params *cp; struct hci_conn *conn; - int i = 0; + u8 status = rp->status; + int i; bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_CIG_PARAMS); + if (!cp || rp->num_handles != cp->num_cis || rp->cig_id != cp->cig_id) { + bt_dev_err(hdev, "unexpected Set CIG Parameters response data"); + status = HCI_ERROR_UNSPECIFIED; + } + hci_dev_lock(hdev); - if (rp->status) { + if (status) { while ((conn = hci_conn_hash_lookup_cig(hdev, rp->cig_id))) { conn->state = BT_CLOSED; - hci_connect_cfm(conn, rp->status); + hci_connect_cfm(conn, status); hci_conn_del(conn); } goto unlock; } - rcu_read_lock(); + /* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E page 2553 + * + * If the Status return parameter is zero, then the Controller shall + * set the Connection_Handle arrayed return parameter to the connection + * handle(s) corresponding to the CIS configurations specified in + * the CIS_IDs command parameter, in the same order. + */ + for (i = 0; i < rp->num_handles; ++i) { + conn = hci_conn_hash_lookup_cis(hdev, NULL, 0, rp->cig_id, + cp->cis[i].cis_id); + if (!conn || !bacmp(&conn->dst, BDADDR_ANY)) + continue; - list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) { - if (conn->type != ISO_LINK || - conn->iso_qos.ucast.cig != rp->cig_id || - conn->state == BT_CONNECTED) + if (conn->state != BT_BOUND && conn->state != BT_CONNECT) continue; - conn->handle = __le16_to_cpu(rp->handle[i++]); + conn->handle = __le16_to_cpu(rp->handle[i]); bt_dev_dbg(hdev, "%p handle 0x%4.4x parent %p", conn, conn->handle, conn->parent); /* Create CIS if LE is already connected */ - if (conn->parent && conn->parent->state == BT_CONNECTED) { - rcu_read_unlock(); + if (conn->parent && conn->parent->state == BT_CONNECTED) hci_le_create_cis(conn); - rcu_read_lock(); - } - - if (i == rp->num_handles) - break; } - rcu_read_unlock(); - unlock: hci_dev_unlock(hdev); diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 647a8ce54062..804cde43b4e0 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -629,6 +629,7 @@ void hci_cmd_sync_init(struct hci_dev *hdev) INIT_WORK(&hdev->cmd_sync_work, hci_cmd_sync_work); INIT_LIST_HEAD(&hdev->cmd_sync_work_list); mutex_init(&hdev->cmd_sync_work_lock); + mutex_init(&hdev->unregister_lock); INIT_WORK(&hdev->cmd_sync_cancel_work, hci_cmd_sync_cancel_work); INIT_WORK(&hdev->reenable_adv_work, reenable_adv); @@ -692,14 +693,19 @@ int hci_cmd_sync_submit(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, void *data, hci_cmd_sync_work_destroy_t destroy) { struct hci_cmd_sync_work_entry *entry; + int err = 0; - if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) - return -ENODEV; + mutex_lock(&hdev->unregister_lock); + if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) { + err = -ENODEV; + goto unlock; + } entry = kmalloc(sizeof(*entry), GFP_KERNEL); - if (!entry) - return -ENOMEM; - + if (!entry) { + err = -ENOMEM; + goto unlock; + } entry->func = func; entry->data = data; entry->destroy = destroy; @@ -710,7 +716,9 @@ int hci_cmd_sync_submit(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, queue_work(hdev->req_workqueue, &hdev->cmd_sync_work); - return 0; +unlock: + mutex_unlock(&hdev->unregister_lock); + return err; } EXPORT_SYMBOL(hci_cmd_sync_submit); @@ -4543,6 +4551,9 @@ static int hci_init_sync(struct hci_dev *hdev) !hci_dev_test_flag(hdev, HCI_CONFIG)) return 0; + if (hci_dev_test_and_set_flag(hdev, HCI_DEBUGFS_CREATED)) + return 0; + hci_debugfs_create_common(hdev); if (lmp_bredr_capable(hdev)) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 376b523c7b26..c5e8798e297c 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -4306,6 +4306,10 @@ static int l2cap_connect_create_rsp(struct l2cap_conn *conn, result = __le16_to_cpu(rsp->result); status = __le16_to_cpu(rsp->status); + if (result == L2CAP_CR_SUCCESS && (dcid < L2CAP_CID_DYN_START || + dcid > L2CAP_CID_DYN_END)) + return -EPROTO; + BT_DBG("dcid 0x%4.4x scid 0x%4.4x result 0x%2.2x status 0x%2.2x", dcid, scid, result, status); @@ -4337,6 +4341,11 @@ static int l2cap_connect_create_rsp(struct l2cap_conn *conn, switch (result) { case L2CAP_CR_SUCCESS: + if (__l2cap_get_chan_by_dcid(conn, dcid)) { + err = -EBADSLT; + break; + } + l2cap_state_change(chan, BT_CONFIG); chan->ident = 0; chan->dcid = dcid; @@ -4663,7 +4672,9 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, chan->ops->set_shutdown(chan); + l2cap_chan_unlock(chan); mutex_lock(&conn->chan_lock); + l2cap_chan_lock(chan); l2cap_chan_del(chan, ECONNRESET); mutex_unlock(&conn->chan_lock); @@ -4702,7 +4713,9 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, return 0; } + l2cap_chan_unlock(chan); mutex_lock(&conn->chan_lock); + l2cap_chan_lock(chan); l2cap_chan_del(chan, 0); mutex_unlock(&conn->chan_lock); diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 98143b86a9dd..2321bd2f9964 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -561,29 +561,6 @@ __bpf_kfunc int bpf_modify_return_test(int a, int *b) return a + *b; } -__bpf_kfunc u64 bpf_kfunc_call_test1(struct sock *sk, u32 a, u64 b, u32 c, u64 d) -{ - return a + b + c + d; -} - -__bpf_kfunc int bpf_kfunc_call_test2(struct sock *sk, u32 a, u32 b) -{ - return a + b; -} - -__bpf_kfunc struct sock *bpf_kfunc_call_test3(struct sock *sk) -{ - return sk; -} - -long noinline bpf_kfunc_call_test4(signed char a, short b, int c, long d) -{ - /* Provoke the compiler to assume that the caller has sign-extended a, - * b and c on platforms where this is required (e.g. s390x). - */ - return (long)a + (long)b + (long)c + d; -} - int noinline bpf_fentry_shadow_test(int a) { return a + 1; @@ -606,32 +583,6 @@ struct prog_test_ref_kfunc { refcount_t cnt; }; -static struct prog_test_ref_kfunc prog_test_struct = { - .a = 42, - .b = 108, - .next = &prog_test_struct, - .cnt = REFCOUNT_INIT(1), -}; - -__bpf_kfunc struct prog_test_ref_kfunc * -bpf_kfunc_call_test_acquire(unsigned long *scalar_ptr) -{ - refcount_inc(&prog_test_struct.cnt); - return &prog_test_struct; -} - -__bpf_kfunc void bpf_kfunc_call_test_offset(struct prog_test_ref_kfunc *p) -{ - WARN_ON_ONCE(1); -} - -__bpf_kfunc struct prog_test_member * -bpf_kfunc_call_memb_acquire(void) -{ - WARN_ON_ONCE(1); - return NULL; -} - __bpf_kfunc void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) { refcount_dec(&p->cnt); @@ -641,134 +592,6 @@ __bpf_kfunc void bpf_kfunc_call_memb_release(struct prog_test_member *p) { } -__bpf_kfunc void bpf_kfunc_call_memb1_release(struct prog_test_member1 *p) -{ - WARN_ON_ONCE(1); -} - -static int *__bpf_kfunc_call_test_get_mem(struct prog_test_ref_kfunc *p, const int size) -{ - if (size > 2 * sizeof(int)) - return NULL; - - return (int *)p; -} - -__bpf_kfunc int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, - const int rdwr_buf_size) -{ - return __bpf_kfunc_call_test_get_mem(p, rdwr_buf_size); -} - -__bpf_kfunc int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, - const int rdonly_buf_size) -{ - return __bpf_kfunc_call_test_get_mem(p, rdonly_buf_size); -} - -/* the next 2 ones can't be really used for testing expect to ensure - * that the verifier rejects the call. - * Acquire functions must return struct pointers, so these ones are - * failing. - */ -__bpf_kfunc int *bpf_kfunc_call_test_acq_rdonly_mem(struct prog_test_ref_kfunc *p, - const int rdonly_buf_size) -{ - return __bpf_kfunc_call_test_get_mem(p, rdonly_buf_size); -} - -__bpf_kfunc void bpf_kfunc_call_int_mem_release(int *p) -{ -} - -struct prog_test_pass1 { - int x0; - struct { - int x1; - struct { - int x2; - struct { - int x3; - }; - }; - }; -}; - -struct prog_test_pass2 { - int len; - short arr1[4]; - struct { - char arr2[4]; - unsigned long arr3[8]; - } x; -}; - -struct prog_test_fail1 { - void *p; - int x; -}; - -struct prog_test_fail2 { - int x8; - struct prog_test_pass1 x; -}; - -struct prog_test_fail3 { - int len; - char arr1[2]; - char arr2[]; -}; - -__bpf_kfunc void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb) -{ -} - -__bpf_kfunc void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p) -{ -} - -__bpf_kfunc void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p) -{ -} - -__bpf_kfunc void bpf_kfunc_call_test_fail1(struct prog_test_fail1 *p) -{ -} - -__bpf_kfunc void bpf_kfunc_call_test_fail2(struct prog_test_fail2 *p) -{ -} - -__bpf_kfunc void bpf_kfunc_call_test_fail3(struct prog_test_fail3 *p) -{ -} - -__bpf_kfunc void bpf_kfunc_call_test_mem_len_pass1(void *mem, int mem__sz) -{ -} - -__bpf_kfunc void bpf_kfunc_call_test_mem_len_fail1(void *mem, int len) -{ -} - -__bpf_kfunc void bpf_kfunc_call_test_mem_len_fail2(u64 *mem, int len) -{ -} - -__bpf_kfunc void bpf_kfunc_call_test_ref(struct prog_test_ref_kfunc *p) -{ - /* p != NULL, but p->cnt could be 0 */ -} - -__bpf_kfunc void bpf_kfunc_call_test_destructive(void) -{ -} - -__bpf_kfunc static u32 bpf_kfunc_call_test_static_unused_arg(u32 arg, u32 unused) -{ - return arg; -} - __diag_pop(); BTF_SET8_START(bpf_test_modify_return_ids) @@ -782,32 +605,8 @@ static const struct btf_kfunc_id_set bpf_test_modify_return_set = { }; BTF_SET8_START(test_sk_check_kfunc_ids) -BTF_ID_FLAGS(func, bpf_kfunc_call_test1) -BTF_ID_FLAGS(func, bpf_kfunc_call_test2) -BTF_ID_FLAGS(func, bpf_kfunc_call_test3) -BTF_ID_FLAGS(func, bpf_kfunc_call_test4) -BTF_ID_FLAGS(func, bpf_kfunc_call_test_acquire, KF_ACQUIRE | KF_RET_NULL) -BTF_ID_FLAGS(func, bpf_kfunc_call_memb_acquire, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_kfunc_call_test_release, KF_RELEASE) BTF_ID_FLAGS(func, bpf_kfunc_call_memb_release, KF_RELEASE) -BTF_ID_FLAGS(func, bpf_kfunc_call_memb1_release, KF_RELEASE) -BTF_ID_FLAGS(func, bpf_kfunc_call_test_get_rdwr_mem, KF_RET_NULL) -BTF_ID_FLAGS(func, bpf_kfunc_call_test_get_rdonly_mem, KF_RET_NULL) -BTF_ID_FLAGS(func, bpf_kfunc_call_test_acq_rdonly_mem, KF_ACQUIRE | KF_RET_NULL) -BTF_ID_FLAGS(func, bpf_kfunc_call_int_mem_release, KF_RELEASE) -BTF_ID_FLAGS(func, bpf_kfunc_call_test_pass_ctx) -BTF_ID_FLAGS(func, bpf_kfunc_call_test_pass1) -BTF_ID_FLAGS(func, bpf_kfunc_call_test_pass2) -BTF_ID_FLAGS(func, bpf_kfunc_call_test_fail1) -BTF_ID_FLAGS(func, bpf_kfunc_call_test_fail2) -BTF_ID_FLAGS(func, bpf_kfunc_call_test_fail3) -BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_pass1) -BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_fail1) -BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_fail2) -BTF_ID_FLAGS(func, bpf_kfunc_call_test_ref, KF_TRUSTED_ARGS | KF_RCU) -BTF_ID_FLAGS(func, bpf_kfunc_call_test_destructive, KF_DESTRUCTIVE) -BTF_ID_FLAGS(func, bpf_kfunc_call_test_static_unused_arg) -BTF_ID_FLAGS(func, bpf_kfunc_call_test_offset) BTF_SET8_END(test_sk_check_kfunc_ids) static void *bpf_test_init(const union bpf_attr *kattr, u32 user_size, diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 8eca8a5c80c6..9a5ea06236bd 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -39,6 +39,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) u16 vid = 0; memset(skb->cb, 0, sizeof(struct br_input_skb_cb)); + br_tc_skb_miss_set(skb, false); rcu_read_lock(); nf_ops = rcu_dereference(nf_br_ops); diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 84d6dd5e5b1a..6116eba1bd89 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -203,6 +203,8 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb, struct net_bridge_port *prev = NULL; struct net_bridge_port *p; + br_tc_skb_miss_set(skb, pkt_type != BR_PKT_BROADCAST); + list_for_each_entry_rcu(p, &br->port_list, list) { /* Do not flood unicast traffic to ports that turn it off, nor * other traffic if flood off, except for traffic we originate @@ -295,6 +297,7 @@ void br_multicast_flood(struct net_bridge_mdb_entry *mdst, allow_mode_include = false; } else { p = NULL; + br_tc_skb_miss_set(skb, true); } while (p || rp) { diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index fc17b9fd93e6..c34a0b0901b0 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -334,6 +334,7 @@ static rx_handler_result_t br_handle_frame(struct sk_buff **pskb) return RX_HANDLER_CONSUMED; memset(skb->cb, 0, sizeof(struct br_input_skb_cb)); + br_tc_skb_miss_set(skb, false); p = br_port_get_rcu(skb->dev); if (p->flags & BR_VLAN_TUNNEL) diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 2119729ded2b..a63b32c1638e 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -15,6 +15,7 @@ #include <linux/u64_stats_sync.h> #include <net/route.h> #include <net/ip6_fib.h> +#include <net/pkt_cls.h> #include <linux/if_vlan.h> #include <linux/rhashtable.h> #include <linux/refcount.h> @@ -754,6 +755,32 @@ void br_boolopt_multi_get(const struct net_bridge *br, struct br_boolopt_multi *bm); void br_opt_toggle(struct net_bridge *br, enum net_bridge_opts opt, bool on); +#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) +static inline void br_tc_skb_miss_set(struct sk_buff *skb, bool miss) +{ + struct tc_skb_ext *ext; + + if (!tc_skb_ext_tc_enabled()) + return; + + ext = skb_ext_find(skb, TC_SKB_EXT); + if (ext) { + ext->l2_miss = miss; + return; + } + if (!miss) + return; + ext = tc_skb_ext_alloc(skb); + if (!ext) + return; + ext->l2_miss = true; +} +#else +static inline void br_tc_skb_miss_set(struct sk_buff *skb, bool miss) +{ +} +#endif + /* br_device.c */ void br_dev_setup(struct net_device *dev); void br_dev_delete(struct net_device *dev, struct list_head *list); diff --git a/net/bridge/br_private_tunnel.h b/net/bridge/br_private_tunnel.h index 2b053289f016..efb096025151 100644 --- a/net/bridge/br_private_tunnel.h +++ b/net/bridge/br_private_tunnel.h @@ -27,6 +27,10 @@ int br_process_vlan_tunnel_info(const struct net_bridge *br, int br_get_vlan_tunnel_info_size(struct net_bridge_vlan_group *vg); int br_fill_vlan_tunnel_info(struct sk_buff *skb, struct net_bridge_vlan_group *vg); +bool vlan_tunid_inrange(const struct net_bridge_vlan *v_curr, + const struct net_bridge_vlan *v_last); +int br_vlan_tunnel_info(const struct net_bridge_port *p, int cmd, + u16 vid, u32 tun_id, bool *changed); #ifdef CONFIG_BRIDGE_VLAN_FILTERING /* br_vlan_tunnel.c */ @@ -43,10 +47,6 @@ void br_handle_ingress_vlan_tunnel(struct sk_buff *skb, struct net_bridge_vlan_group *vg); int br_handle_egress_vlan_tunnel(struct sk_buff *skb, struct net_bridge_vlan *vlan); -bool vlan_tunid_inrange(const struct net_bridge_vlan *v_curr, - const struct net_bridge_vlan *v_last); -int br_vlan_tunnel_info(const struct net_bridge_port *p, int cmd, - u16 vid, u32 tun_id, bool *changed); #else static inline int vlan_tunnel_init(struct net_bridge_vlan_group *vg) { diff --git a/net/can/isotp.c b/net/can/isotp.c index a750259cb79c..84f9aba02901 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -1139,7 +1139,7 @@ static int isotp_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, struct isotp_sock *so = isotp_sk(sk); int ret = 0; - if (flags & ~(MSG_DONTWAIT | MSG_TRUNC | MSG_PEEK)) + if (flags & ~(MSG_DONTWAIT | MSG_TRUNC | MSG_PEEK | MSG_CMSG_COMPAT)) return -EINVAL; if (!so->bound) diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index 821d4ff303b3..ecff1c947d68 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -126,7 +126,7 @@ static void j1939_can_recv(struct sk_buff *iskb, void *data) #define J1939_CAN_ID CAN_EFF_FLAG #define J1939_CAN_MASK (CAN_EFF_FLAG | CAN_RTR_FLAG) -static DEFINE_SPINLOCK(j1939_netdev_lock); +static DEFINE_MUTEX(j1939_netdev_lock); static struct j1939_priv *j1939_priv_create(struct net_device *ndev) { @@ -220,7 +220,7 @@ static void __j1939_rx_release(struct kref *kref) j1939_can_rx_unregister(priv); j1939_ecu_unmap_all(priv); j1939_priv_set(priv->ndev, NULL); - spin_unlock(&j1939_netdev_lock); + mutex_unlock(&j1939_netdev_lock); } /* get pointer to priv without increasing ref counter */ @@ -248,9 +248,9 @@ static struct j1939_priv *j1939_priv_get_by_ndev(struct net_device *ndev) { struct j1939_priv *priv; - spin_lock(&j1939_netdev_lock); + mutex_lock(&j1939_netdev_lock); priv = j1939_priv_get_by_ndev_locked(ndev); - spin_unlock(&j1939_netdev_lock); + mutex_unlock(&j1939_netdev_lock); return priv; } @@ -260,14 +260,14 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev) struct j1939_priv *priv, *priv_new; int ret; - spin_lock(&j1939_netdev_lock); + mutex_lock(&j1939_netdev_lock); priv = j1939_priv_get_by_ndev_locked(ndev); if (priv) { kref_get(&priv->rx_kref); - spin_unlock(&j1939_netdev_lock); + mutex_unlock(&j1939_netdev_lock); return priv; } - spin_unlock(&j1939_netdev_lock); + mutex_unlock(&j1939_netdev_lock); priv = j1939_priv_create(ndev); if (!priv) @@ -277,29 +277,31 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev) spin_lock_init(&priv->j1939_socks_lock); INIT_LIST_HEAD(&priv->j1939_socks); - spin_lock(&j1939_netdev_lock); + mutex_lock(&j1939_netdev_lock); priv_new = j1939_priv_get_by_ndev_locked(ndev); if (priv_new) { /* Someone was faster than us, use their priv and roll * back our's. */ kref_get(&priv_new->rx_kref); - spin_unlock(&j1939_netdev_lock); + mutex_unlock(&j1939_netdev_lock); dev_put(ndev); kfree(priv); return priv_new; } j1939_priv_set(ndev, priv); - spin_unlock(&j1939_netdev_lock); ret = j1939_can_rx_register(priv); if (ret < 0) goto out_priv_put; + mutex_unlock(&j1939_netdev_lock); return priv; out_priv_put: j1939_priv_set(ndev, NULL); + mutex_unlock(&j1939_netdev_lock); + dev_put(ndev); kfree(priv); @@ -308,7 +310,7 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev) void j1939_netdev_stop(struct j1939_priv *priv) { - kref_put_lock(&priv->rx_kref, __j1939_rx_release, &j1939_netdev_lock); + kref_put_mutex(&priv->rx_kref, __j1939_rx_release, &j1939_netdev_lock); j1939_priv_put(priv); } diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 7e90f9e61d9b..35970c25496a 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -798,7 +798,7 @@ static int j1939_sk_recvmsg(struct socket *sock, struct msghdr *msg, struct j1939_sk_buff_cb *skcb; int ret = 0; - if (flags & ~(MSG_DONTWAIT | MSG_ERRQUEUE)) + if (flags & ~(MSG_DONTWAIT | MSG_ERRQUEUE | MSG_CMSG_COMPAT)) return -EINVAL; if (flags & MSG_ERRQUEUE) @@ -1088,6 +1088,11 @@ void j1939_sk_errqueue(struct j1939_session *session, void j1939_sk_send_loop_abort(struct sock *sk, int err) { + struct j1939_sock *jsk = j1939_sk(sk); + + if (jsk->state & J1939_SOCK_ERRQUEUE) + return; + sk->sk_err = err; sk_error_report(sk); diff --git a/net/core/dev.c b/net/core/dev.c index b3c13e041935..6d6f8a7fe6b4 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4471,8 +4471,10 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, u32 next_cpu; u32 ident; - /* First check into global flow table if there is a match */ - ident = sock_flow_table->ents[hash & sock_flow_table->mask]; + /* First check into global flow table if there is a match. + * This READ_ONCE() pairs with WRITE_ONCE() from rps_record_sock_flow(). + */ + ident = READ_ONCE(sock_flow_table->ents[hash & sock_flow_table->mask]); if ((ident ^ hash) & ~rps_cpu_mask) goto try_rps; @@ -6197,7 +6199,8 @@ restart: if (!napi) goto out; - preempt_disable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_disable(); for (;;) { int work = 0; @@ -6239,7 +6242,8 @@ count: if (unlikely(need_resched())) { if (napi_poll) busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget); - preempt_enable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_enable(); rcu_read_unlock(); cond_resched(); if (loop_end(loop_end_arg, start_time)) @@ -6250,7 +6254,8 @@ count: } if (napi_poll) busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget); - preempt_enable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_enable(); out: rcu_read_unlock(); } @@ -10541,7 +10546,7 @@ struct netdev_queue *dev_ingress_queue_create(struct net_device *dev) return NULL; netdev_init_one_queue(dev, queue, NULL); RCU_INIT_POINTER(queue->qdisc, &noop_qdisc); - queue->qdisc_sleeping = &noop_qdisc; + RCU_INIT_POINTER(queue->qdisc_sleeping, &noop_qdisc); rcu_assign_pointer(dev->ingress_queue, queue); #endif return queue; @@ -10568,8 +10573,10 @@ void netdev_sw_irq_coalesce_default_on(struct net_device *dev) { WARN_ON(dev->reg_state == NETREG_REGISTERED); - dev->gro_flush_timeout = 20000; - dev->napi_defer_hard_irqs = 1; + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { + dev->gro_flush_timeout = 20000; + dev->napi_defer_hard_irqs = 1; + } } EXPORT_SYMBOL_GPL(netdev_sw_irq_coalesce_default_on); @@ -10630,7 +10637,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev = PTR_ALIGN(p, NETDEV_ALIGN); dev->padded = (char *)dev - (char *)p; - ref_tracker_dir_init(&dev->refcnt_tracker, 128); + ref_tracker_dir_init(&dev->refcnt_tracker, 128, name); #ifdef CONFIG_PCPU_DEV_REFCNT dev->pcpu_refcnt = alloc_percpu(int); if (!dev->pcpu_refcnt) diff --git a/net/core/filter.c b/net/core/filter.c index d9ce04ca22ce..968139f4a1ac 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -6916,6 +6916,8 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, FIELD)); \ } while (0) + BTF_TYPE_EMIT(struct bpf_tcp_sock); + switch (si->off) { case offsetof(struct bpf_tcp_sock, rtt_min): BUILD_BUG_ON(sizeof_field(struct tcp_sock, rtt_min) != @@ -11721,3 +11723,66 @@ static int __init bpf_kfunc_init(void) return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &bpf_kfunc_set_xdp); } late_initcall(bpf_kfunc_init); + +/* Disables missing prototype warnings */ +__diag_push(); +__diag_ignore_all("-Wmissing-prototypes", + "Global functions as their definitions will be in vmlinux BTF"); + +/* bpf_sock_destroy: Destroy the given socket with ECONNABORTED error code. + * + * The function expects a non-NULL pointer to a socket, and invokes the + * protocol specific socket destroy handlers. + * + * The helper can only be called from BPF contexts that have acquired the socket + * locks. + * + * Parameters: + * @sock: Pointer to socket to be destroyed + * + * Return: + * On error, may return EPROTONOSUPPORT, EINVAL. + * EPROTONOSUPPORT if protocol specific destroy handler is not supported. + * 0 otherwise + */ +__bpf_kfunc int bpf_sock_destroy(struct sock_common *sock) +{ + struct sock *sk = (struct sock *)sock; + + /* The locking semantics that allow for synchronous execution of the + * destroy handlers are only supported for TCP and UDP. + * Supporting protocols will need to acquire sock lock in the BPF context + * prior to invoking this kfunc. + */ + if (!sk->sk_prot->diag_destroy || (sk->sk_protocol != IPPROTO_TCP && + sk->sk_protocol != IPPROTO_UDP)) + return -EOPNOTSUPP; + + return sk->sk_prot->diag_destroy(sk, ECONNABORTED); +} + +__diag_pop() + +BTF_SET8_START(bpf_sk_iter_kfunc_ids) +BTF_ID_FLAGS(func, bpf_sock_destroy, KF_TRUSTED_ARGS) +BTF_SET8_END(bpf_sk_iter_kfunc_ids) + +static int tracing_iter_filter(const struct bpf_prog *prog, u32 kfunc_id) +{ + if (btf_id_set8_contains(&bpf_sk_iter_kfunc_ids, kfunc_id) && + prog->expected_attach_type != BPF_TRACE_ITER) + return -EACCES; + return 0; +} + +static const struct btf_kfunc_id_set bpf_sk_iter_kfunc_set = { + .owner = THIS_MODULE, + .set = &bpf_sk_iter_kfunc_ids, + .filter = tracing_iter_filter, +}; + +static int init_subsystem(void) +{ + return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_sk_iter_kfunc_set); +} +late_initcall(init_subsystem); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 25fb0bbc310f..481ca4080cbd 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -27,6 +27,7 @@ #include <linux/tcp.h> #include <linux/ptp_classify.h> #include <net/flow_dissector.h> +#include <net/pkt_cls.h> #include <scsi/fc/fc_fcoe.h> #include <uapi/linux/batadv_packet.h> #include <linux/bpf.h> @@ -241,6 +242,15 @@ void skb_flow_dissect_meta(const struct sk_buff *skb, FLOW_DISSECTOR_KEY_META, target_container); meta->ingress_ifindex = skb->skb_iif; +#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) + if (tc_skb_ext_tc_enabled()) { + struct tc_skb_ext *ext; + + ext = skb_ext_find(skb, TC_SKB_EXT); + if (ext) + meta->l2_miss = ext->l2_miss; + } +#endif } EXPORT_SYMBOL(skb_flow_dissect_meta); diff --git a/net/core/gro.c b/net/core/gro.c index 6783a47a6136..4d45f78e2fac 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -458,6 +458,14 @@ static void gro_pull_from_frag0(struct sk_buff *skb, int grow) } } +static void gro_try_pull_from_frag0(struct sk_buff *skb) +{ + int grow = skb_gro_offset(skb) - skb_headlen(skb); + + if (grow > 0) + gro_pull_from_frag0(skb, grow); +} + static void gro_flush_oldest(struct napi_struct *napi, struct list_head *head) { struct sk_buff *oldest; @@ -487,7 +495,6 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff struct sk_buff *pp = NULL; enum gro_result ret; int same_flow; - int grow; if (netif_elide_gro(skb->dev)) goto normal; @@ -562,17 +569,14 @@ found_ptype: else gro_list->count++; + /* Must be called before setting NAPI_GRO_CB(skb)->{age|last} */ + gro_try_pull_from_frag0(skb); NAPI_GRO_CB(skb)->age = jiffies; NAPI_GRO_CB(skb)->last = skb; if (!skb_is_gso(skb)) skb_shinfo(skb)->gso_size = skb_gro_len(skb); list_add(&skb->list, &gro_list->list); ret = GRO_HELD; - -pull: - grow = skb_gro_offset(skb) - skb_headlen(skb); - if (grow > 0) - gro_pull_from_frag0(skb, grow); ok: if (gro_list->count) { if (!test_bit(bucket, &napi->gro_bitmask)) @@ -585,7 +589,8 @@ ok: normal: ret = GRO_NORMAL; - goto pull; + gro_try_pull_from_frag0(skb); + goto ok; } struct packet_offload *gro_find_receive_by_type(__be16 type) diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 3e3598cd49f2..f4183c4c1ec8 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -308,7 +308,7 @@ EXPORT_SYMBOL_GPL(get_net_ns_by_id); /* init code that must occur even if setup_net() is not called. */ static __net_init void preinit_net(struct net *net) { - ref_tracker_dir_init(&net->notrefcnt_tracker, 128); + ref_tracker_dir_init(&net->notrefcnt_tracker, 128, "net notrefcnt"); } /* @@ -322,7 +322,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) LIST_HEAD(net_exit_list); refcount_set(&net->ns.count, 1); - ref_tracker_dir_init(&net->refcnt_tracker, 128); + ref_tracker_dir_init(&net->refcnt_tracker, 128, "net refcnt"); refcount_set(&net->passive, 1); get_random_bytes(&net->hash_mix, sizeof(u32)); diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index de17ca2f7dbf..ea9231378aa6 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -8,7 +8,7 @@ #include "netdev-genl-gen.h" -#include <linux/netdev.h> +#include <uapi/linux/netdev.h> /* NETDEV_CMD_DEV_GET - do */ static const struct nla_policy netdev_dev_get_nl_policy[NETDEV_A_DEV_IFINDEX + 1] = { diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h index 74d74fc23167..7b370c073e7d 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -9,7 +9,7 @@ #include <net/netlink.h> #include <net/genetlink.h> -#include <linux/netdev.h> +#include <uapi/linux/netdev.h> int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info); int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); diff --git a/net/core/page_pool.c b/net/core/page_pool.c index e212e9d7edcb..a3e12a61d456 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -134,6 +134,29 @@ EXPORT_SYMBOL(page_pool_ethtool_stats_get); #define recycle_stat_add(pool, __stat, val) #endif +static bool page_pool_producer_lock(struct page_pool *pool) + __acquires(&pool->ring.producer_lock) +{ + bool in_softirq = in_softirq(); + + if (in_softirq) + spin_lock(&pool->ring.producer_lock); + else + spin_lock_bh(&pool->ring.producer_lock); + + return in_softirq; +} + +static void page_pool_producer_unlock(struct page_pool *pool, + bool in_softirq) + __releases(&pool->ring.producer_lock) +{ + if (in_softirq) + spin_unlock(&pool->ring.producer_lock); + else + spin_unlock_bh(&pool->ring.producer_lock); +} + static int page_pool_init(struct page_pool *pool, const struct page_pool_params *params) { @@ -617,6 +640,7 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, int count) { int i, bulk_len = 0; + bool in_softirq; for (i = 0; i < count; i++) { struct page *page = virt_to_head_page(data[i]); @@ -635,7 +659,7 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, return; /* Bulk producer into ptr_ring page_pool cache */ - page_pool_ring_lock(pool); + in_softirq = page_pool_producer_lock(pool); for (i = 0; i < bulk_len; i++) { if (__ptr_ring_produce(&pool->ring, data[i])) { /* ring full */ @@ -644,7 +668,7 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, } } recycle_stat_add(pool, ring, i); - page_pool_ring_unlock(pool); + page_pool_producer_unlock(pool, in_softirq); /* Hopefully all pages was return into ptr_ring */ if (likely(i == bulk_len)) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 653901a1bf75..41de3a2f29e1 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2385,6 +2385,37 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[], if (tb[IFLA_BROADCAST] && nla_len(tb[IFLA_BROADCAST]) < dev->addr_len) return -EINVAL; + + if (tb[IFLA_GSO_MAX_SIZE] && + nla_get_u32(tb[IFLA_GSO_MAX_SIZE]) > dev->tso_max_size) { + NL_SET_ERR_MSG(extack, "too big gso_max_size"); + return -EINVAL; + } + + if (tb[IFLA_GSO_MAX_SEGS] && + (nla_get_u32(tb[IFLA_GSO_MAX_SEGS]) > GSO_MAX_SEGS || + nla_get_u32(tb[IFLA_GSO_MAX_SEGS]) > dev->tso_max_segs)) { + NL_SET_ERR_MSG(extack, "too big gso_max_segs"); + return -EINVAL; + } + + if (tb[IFLA_GRO_MAX_SIZE] && + nla_get_u32(tb[IFLA_GRO_MAX_SIZE]) > GRO_MAX_SIZE) { + NL_SET_ERR_MSG(extack, "too big gro_max_size"); + return -EINVAL; + } + + if (tb[IFLA_GSO_IPV4_MAX_SIZE] && + nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE]) > dev->tso_max_size) { + NL_SET_ERR_MSG(extack, "too big gso_ipv4_max_size"); + return -EINVAL; + } + + if (tb[IFLA_GRO_IPV4_MAX_SIZE] && + nla_get_u32(tb[IFLA_GRO_IPV4_MAX_SIZE]) > GRO_MAX_SIZE) { + NL_SET_ERR_MSG(extack, "too big gro_ipv4_max_size"); + return -EINVAL; + } } if (tb[IFLA_AF_SPEC]) { @@ -2858,11 +2889,6 @@ static int do_setlink(const struct sk_buff *skb, if (tb[IFLA_GSO_MAX_SIZE]) { u32 max_size = nla_get_u32(tb[IFLA_GSO_MAX_SIZE]); - if (max_size > dev->tso_max_size) { - err = -EINVAL; - goto errout; - } - if (dev->gso_max_size ^ max_size) { netif_set_gso_max_size(dev, max_size); status |= DO_SETLINK_MODIFIED; @@ -2872,11 +2898,6 @@ static int do_setlink(const struct sk_buff *skb, if (tb[IFLA_GSO_MAX_SEGS]) { u32 max_segs = nla_get_u32(tb[IFLA_GSO_MAX_SEGS]); - if (max_segs > GSO_MAX_SEGS || max_segs > dev->tso_max_segs) { - err = -EINVAL; - goto errout; - } - if (dev->gso_max_segs ^ max_segs) { netif_set_gso_max_segs(dev, max_segs); status |= DO_SETLINK_MODIFIED; @@ -2895,11 +2916,6 @@ static int do_setlink(const struct sk_buff *skb, if (tb[IFLA_GSO_IPV4_MAX_SIZE]) { u32 max_size = nla_get_u32(tb[IFLA_GSO_IPV4_MAX_SIZE]); - if (max_size > dev->tso_max_size) { - err = -EINVAL; - goto errout; - } - if (dev->gso_ipv4_max_size ^ max_size) { netif_set_gso_ipv4_max_size(dev, max_size); status |= DO_SETLINK_MODIFIED; @@ -3285,6 +3301,7 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, struct net_device *dev; unsigned int num_tx_queues = 1; unsigned int num_rx_queues = 1; + int err; if (tb[IFLA_NUM_TX_QUEUES]) num_tx_queues = nla_get_u32(tb[IFLA_NUM_TX_QUEUES]); @@ -3320,13 +3337,18 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, if (!dev) return ERR_PTR(-ENOMEM); + err = validate_linkmsg(dev, tb, extack); + if (err < 0) { + free_netdev(dev); + return ERR_PTR(err); + } + dev_net_set(dev, net); dev->rtnl_link_ops = ops; dev->rtnl_link_state = RTNL_LINK_INITIALIZING; if (tb[IFLA_MTU]) { u32 mtu = nla_get_u32(tb[IFLA_MTU]); - int err; err = dev_validate_mtu(dev, mtu, extack); if (err) { diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 6724a84ebb09..7c4338221b17 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4188,13 +4188,13 @@ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, EXPORT_SYMBOL(skb_find_text); int skb_append_pagefrags(struct sk_buff *skb, struct page *page, - int offset, size_t size) + int offset, size_t size, size_t max_frags) { int i = skb_shinfo(skb)->nr_frags; if (skb_can_coalesce(skb, i, page, offset)) { skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], size); - } else if (i < MAX_SKB_FRAGS) { + } else if (i < max_frags) { skb_zcopy_downgrade_managed(skb); get_page(page); skb_fill_page_desc_noacc(skb, i, page, offset, size); @@ -5206,8 +5206,10 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb, } else { skb = skb_clone(orig_skb, GFP_ATOMIC); - if (skb_orphan_frags_rx(skb, GFP_ATOMIC)) + if (skb_orphan_frags_rx(skb, GFP_ATOMIC)) { + kfree_skb(skb); return; + } } if (!skb) return; @@ -6892,3 +6894,91 @@ nodefer: __kfree_skb(skb); if (unlikely(kick) && !cmpxchg(&sd->defer_ipi_scheduled, 0, 1)) smp_call_function_single_async(cpu, &sd->defer_csd); } + +static void skb_splice_csum_page(struct sk_buff *skb, struct page *page, + size_t offset, size_t len) +{ + const char *kaddr; + __wsum csum; + + kaddr = kmap_local_page(page); + csum = csum_partial(kaddr + offset, len, 0); + kunmap_local(kaddr); + skb->csum = csum_block_add(skb->csum, csum, skb->len); +} + +/** + * skb_splice_from_iter - Splice (or copy) pages to skbuff + * @skb: The buffer to add pages to + * @iter: Iterator representing the pages to be added + * @maxsize: Maximum amount of pages to be added + * @gfp: Allocation flags + * + * This is a common helper function for supporting MSG_SPLICE_PAGES. It + * extracts pages from an iterator and adds them to the socket buffer if + * possible, copying them to fragments if not possible (such as if they're slab + * pages). + * + * Returns the amount of data spliced/copied or -EMSGSIZE if there's + * insufficient space in the buffer to transfer anything. + */ +ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter, + ssize_t maxsize, gfp_t gfp) +{ + size_t frag_limit = READ_ONCE(sysctl_max_skb_frags); + struct page *pages[8], **ppages = pages; + ssize_t spliced = 0, ret = 0; + unsigned int i; + + while (iter->count > 0) { + ssize_t space, nr, len; + size_t off; + + ret = -EMSGSIZE; + space = frag_limit - skb_shinfo(skb)->nr_frags; + if (space < 0) + break; + + /* We might be able to coalesce without increasing nr_frags */ + nr = clamp_t(size_t, space, 1, ARRAY_SIZE(pages)); + + len = iov_iter_extract_pages(iter, &ppages, maxsize, nr, 0, &off); + if (len <= 0) { + ret = len ?: -EIO; + break; + } + + i = 0; + do { + struct page *page = pages[i++]; + size_t part = min_t(size_t, PAGE_SIZE - off, len); + + ret = -EIO; + if (WARN_ON_ONCE(!sendpage_ok(page))) + goto out; + + ret = skb_append_pagefrags(skb, page, off, part, + frag_limit); + if (ret < 0) { + iov_iter_revert(iter, len); + goto out; + } + + if (skb->ip_summed == CHECKSUM_NONE) + skb_splice_csum_page(skb, page, off, part); + + off = 0; + spliced += part; + maxsize -= part; + len -= part; + } while (len > 0); + + if (maxsize <= 0) + break; + } + +out: + skb_len_add(skb, spliced); + return spliced ?: ret; +} +EXPORT_SYMBOL(skb_splice_from_iter); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index f81883759d38..a29508e1ff35 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -481,8 +481,6 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, msg_rx = sk_psock_peek_msg(psock); } out: - if (psock->work_state.skb && copied > 0) - schedule_work(&psock->work); return copied; } EXPORT_SYMBOL_GPL(sk_msg_recvmsg); @@ -624,42 +622,33 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, static void sk_psock_skb_state(struct sk_psock *psock, struct sk_psock_work_state *state, - struct sk_buff *skb, int len, int off) { spin_lock_bh(&psock->ingress_lock); if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { - state->skb = skb; state->len = len; state->off = off; - } else { - sock_drop(psock->sk, skb); } spin_unlock_bh(&psock->ingress_lock); } static void sk_psock_backlog(struct work_struct *work) { - struct sk_psock *psock = container_of(work, struct sk_psock, work); + struct delayed_work *dwork = to_delayed_work(work); + struct sk_psock *psock = container_of(dwork, struct sk_psock, work); struct sk_psock_work_state *state = &psock->work_state; struct sk_buff *skb = NULL; + u32 len = 0, off = 0; bool ingress; - u32 len, off; int ret; mutex_lock(&psock->work_mutex); - if (unlikely(state->skb)) { - spin_lock_bh(&psock->ingress_lock); - skb = state->skb; + if (unlikely(state->len)) { len = state->len; off = state->off; - state->skb = NULL; - spin_unlock_bh(&psock->ingress_lock); } - if (skb) - goto start; - while ((skb = skb_dequeue(&psock->ingress_skb))) { + while ((skb = skb_peek(&psock->ingress_skb))) { len = skb->len; off = 0; if (skb_bpf_strparser(skb)) { @@ -668,7 +657,6 @@ static void sk_psock_backlog(struct work_struct *work) off = stm->offset; len = stm->full_len; } -start: ingress = skb_bpf_ingress(skb); skb_bpf_redirect_clear(skb); do { @@ -678,22 +666,28 @@ start: len, ingress); if (ret <= 0) { if (ret == -EAGAIN) { - sk_psock_skb_state(psock, state, skb, - len, off); + sk_psock_skb_state(psock, state, len, off); + + /* Delay slightly to prioritize any + * other work that might be here. + */ + if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) + schedule_delayed_work(&psock->work, 1); goto end; } /* Hard errors break pipe and stop xmit. */ sk_psock_report_error(psock, ret ? -ret : EPIPE); sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED); - sock_drop(psock->sk, skb); goto end; } off += ret; len -= ret; } while (len); - if (!ingress) + skb = skb_dequeue(&psock->ingress_skb); + if (!ingress) { kfree_skb(skb); + } } end: mutex_unlock(&psock->work_mutex); @@ -734,7 +728,7 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node) INIT_LIST_HEAD(&psock->link); spin_lock_init(&psock->link_lock); - INIT_WORK(&psock->work, sk_psock_backlog); + INIT_DELAYED_WORK(&psock->work, sk_psock_backlog); mutex_init(&psock->work_mutex); INIT_LIST_HEAD(&psock->ingress_msg); spin_lock_init(&psock->ingress_lock); @@ -786,11 +780,6 @@ static void __sk_psock_zap_ingress(struct sk_psock *psock) skb_bpf_redirect_clear(skb); sock_drop(psock->sk, skb); } - kfree_skb(psock->work_state.skb); - /* We null the skb here to ensure that calls to sk_psock_backlog - * do not pick up the free'd skb. - */ - psock->work_state.skb = NULL; __sk_psock_purge_ingress_msg(psock); } @@ -809,7 +798,6 @@ void sk_psock_stop(struct sk_psock *psock) spin_lock_bh(&psock->ingress_lock); sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED); sk_psock_cork_free(psock); - __sk_psock_zap_ingress(psock); spin_unlock_bh(&psock->ingress_lock); } @@ -823,7 +811,8 @@ static void sk_psock_destroy(struct work_struct *work) sk_psock_done_strp(psock); - cancel_work_sync(&psock->work); + cancel_delayed_work_sync(&psock->work); + __sk_psock_zap_ingress(psock); mutex_destroy(&psock->work_mutex); psock_progs_drop(&psock->progs); @@ -938,7 +927,7 @@ static int sk_psock_skb_redirect(struct sk_psock *from, struct sk_buff *skb) } skb_queue_tail(&psock_other->ingress_skb, skb); - schedule_work(&psock_other->work); + schedule_delayed_work(&psock_other->work, 0); spin_unlock_bh(&psock_other->ingress_lock); return 0; } @@ -990,10 +979,8 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, err = -EIO; sk_other = psock->sk; if (sock_flag(sk_other, SOCK_DEAD) || - !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { - skb_bpf_redirect_clear(skb); + !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) goto out_free; - } skb_bpf_set_ingress(skb); @@ -1018,22 +1005,23 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, spin_lock_bh(&psock->ingress_lock); if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { skb_queue_tail(&psock->ingress_skb, skb); - schedule_work(&psock->work); + schedule_delayed_work(&psock->work, 0); err = 0; } spin_unlock_bh(&psock->ingress_lock); - if (err < 0) { - skb_bpf_redirect_clear(skb); + if (err < 0) goto out_free; - } } break; case __SK_REDIRECT: + tcp_eat_skb(psock->sk, skb); err = sk_psock_skb_redirect(psock, skb); break; case __SK_DROP: default: out_free: + skb_bpf_redirect_clear(skb); + tcp_eat_skb(psock->sk, skb); sock_drop(psock->sk, skb); } @@ -1049,7 +1037,7 @@ static void sk_psock_write_space(struct sock *sk) psock = sk_psock(sk); if (likely(psock)) { if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) - schedule_work(&psock->work); + schedule_delayed_work(&psock->work, 0); write_space = psock->saved_write_space; } rcu_read_unlock(); @@ -1078,8 +1066,7 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) skb_dst_drop(skb); skb_bpf_redirect_clear(skb); ret = bpf_prog_run_pin_on_cpu(prog, skb); - if (ret == SK_PASS) - skb_bpf_set_strparser(skb); + skb_bpf_set_strparser(skb); ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); skb->sk = NULL; } @@ -1183,12 +1170,11 @@ static int sk_psock_verdict_recv(struct sock *sk, struct sk_buff *skb) int ret = __SK_DROP; int len = skb->len; - skb_get(skb); - rcu_read_lock(); psock = sk_psock(sk); if (unlikely(!psock)) { len = 0; + tcp_eat_skb(sk, skb); sock_drop(sk, skb); goto out; } @@ -1212,12 +1198,22 @@ out: static void sk_psock_verdict_data_ready(struct sock *sk) { struct socket *sock = sk->sk_socket; + int copied; trace_sk_data_ready(sk); if (unlikely(!sock || !sock->ops || !sock->ops->read_skb)) return; - sock->ops->read_skb(sk, sk_psock_verdict_recv); + copied = sock->ops->read_skb(sk, sk_psock_verdict_recv); + if (copied >= 0) { + struct sk_psock *psock; + + rcu_read_lock(); + psock = sk_psock(sk); + if (psock) + psock->saved_data_ready(sk); + rcu_read_unlock(); + } } void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock) diff --git a/net/core/sock.c b/net/core/sock.c index 5440e67bcfe3..24f2761bdb1d 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2381,7 +2381,6 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) { u32 max_segs = 1; - sk_dst_set(sk, dst); sk->sk_route_caps = dst->dev->features; if (sk_is_tcp(sk)) sk->sk_route_caps |= NETIF_F_GSO; @@ -2400,6 +2399,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) } } sk->sk_gso_max_segs = max_segs; + sk_dst_set(sk, dst); } EXPORT_SYMBOL_GPL(sk_setup_caps); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 7c189c2e2fbf..00afb66cd095 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -1644,9 +1644,10 @@ void sock_map_close(struct sock *sk, long timeout) rcu_read_unlock(); sk_psock_stop(psock); release_sock(sk); - cancel_work_sync(&psock->work); + cancel_delayed_work_sync(&psock->work); sk_psock_put(sk, psock); } + /* Make sure we do not recurse. This is a bug. * Leak the socket instead of crashing on a stack overflow. */ diff --git a/net/devlink/core.c b/net/devlink/core.c index 777b091ef74d..c23ebabadc52 100644 --- a/net/devlink/core.c +++ b/net/devlink/core.c @@ -204,11 +204,6 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, if (ret < 0) goto err_xa_alloc; - devlink->netdevice_nb.notifier_call = devlink_port_netdevice_event; - ret = register_netdevice_notifier(&devlink->netdevice_nb); - if (ret) - goto err_register_netdevice_notifier; - devlink->dev = dev; devlink->ops = ops; xa_init_flags(&devlink->ports, XA_FLAGS_ALLOC); @@ -233,8 +228,6 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, return devlink; -err_register_netdevice_notifier: - xa_erase(&devlinks, devlink->index); err_xa_alloc: kfree(devlink); return NULL; @@ -266,8 +259,6 @@ void devlink_free(struct devlink *devlink) xa_destroy(&devlink->params); xa_destroy(&devlink->ports); - WARN_ON_ONCE(unregister_netdevice_notifier(&devlink->netdevice_nb)); - xa_erase(&devlinks, devlink->index); devlink_put(devlink); @@ -303,6 +294,10 @@ static struct pernet_operations devlink_pernet_ops __net_initdata = { .pre_exit = devlink_pernet_pre_exit, }; +static struct notifier_block devlink_port_netdevice_nb = { + .notifier_call = devlink_port_netdevice_event, +}; + static int __init devlink_init(void) { int err; @@ -311,6 +306,9 @@ static int __init devlink_init(void) if (err) goto out; err = register_pernet_subsys(&devlink_pernet_ops); + if (err) + goto out; + err = register_netdevice_notifier(&devlink_port_netdevice_nb); out: WARN_ON(err); diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h index e133f423294a..62921b2eb0d3 100644 --- a/net/devlink/devl_internal.h +++ b/net/devlink/devl_internal.h @@ -50,7 +50,6 @@ struct devlink { u8 reload_failed:1; refcount_t refcount; struct rcu_work rwork; - struct notifier_block netdevice_nb; char priv[] __aligned(NETDEV_ALIGN); }; diff --git a/net/devlink/health.c b/net/devlink/health.c index 0839706d5741..194340a8bb86 100644 --- a/net/devlink/health.c +++ b/net/devlink/health.c @@ -480,7 +480,7 @@ static void devlink_recover_notify(struct devlink_health_reporter *reporter, int err; WARN_ON(cmd != DEVLINK_CMD_HEALTH_REPORTER_RECOVER); - WARN_ON(!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)); + ASSERT_DEVLINK_REGISTERED(devlink); msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c index dffca2f9bfa7..649a9701eb6a 100644 --- a/net/devlink/leftover.c +++ b/net/devlink/leftover.c @@ -447,18 +447,18 @@ static void devlink_port_fn_cap_fill(struct nla_bitfield32 *caps, caps->value |= cap; } -static int devlink_port_fn_roce_fill(const struct devlink_ops *ops, - struct devlink_port *devlink_port, +static int devlink_port_fn_roce_fill(struct devlink_port *devlink_port, struct nla_bitfield32 *caps, struct netlink_ext_ack *extack) { bool is_enable; int err; - if (!ops->port_fn_roce_get) + if (!devlink_port->ops->port_fn_roce_get) return 0; - err = ops->port_fn_roce_get(devlink_port, &is_enable, extack); + err = devlink_port->ops->port_fn_roce_get(devlink_port, &is_enable, + extack); if (err) { if (err == -EOPNOTSUPP) return 0; @@ -469,19 +469,19 @@ static int devlink_port_fn_roce_fill(const struct devlink_ops *ops, return 0; } -static int devlink_port_fn_migratable_fill(const struct devlink_ops *ops, - struct devlink_port *devlink_port, +static int devlink_port_fn_migratable_fill(struct devlink_port *devlink_port, struct nla_bitfield32 *caps, struct netlink_ext_ack *extack) { bool is_enable; int err; - if (!ops->port_fn_migratable_get || + if (!devlink_port->ops->port_fn_migratable_get || devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) return 0; - err = ops->port_fn_migratable_get(devlink_port, &is_enable, extack); + err = devlink_port->ops->port_fn_migratable_get(devlink_port, + &is_enable, extack); if (err) { if (err == -EOPNOTSUPP) return 0; @@ -492,8 +492,7 @@ static int devlink_port_fn_migratable_fill(const struct devlink_ops *ops, return 0; } -static int devlink_port_fn_caps_fill(const struct devlink_ops *ops, - struct devlink_port *devlink_port, +static int devlink_port_fn_caps_fill(struct devlink_port *devlink_port, struct sk_buff *msg, struct netlink_ext_ack *extack, bool *msg_updated) @@ -501,11 +500,11 @@ static int devlink_port_fn_caps_fill(const struct devlink_ops *ops, struct nla_bitfield32 caps = {}; int err; - err = devlink_port_fn_roce_fill(ops, devlink_port, &caps, extack); + err = devlink_port_fn_roce_fill(devlink_port, &caps, extack); if (err) return err; - err = devlink_port_fn_migratable_fill(ops, devlink_port, &caps, extack); + err = devlink_port_fn_migratable_fill(devlink_port, &caps, extack); if (err) return err; @@ -691,8 +690,7 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg, return 0; } -static int devlink_port_fn_hw_addr_fill(const struct devlink_ops *ops, - struct devlink_port *port, +static int devlink_port_fn_hw_addr_fill(struct devlink_port *port, struct sk_buff *msg, struct netlink_ext_ack *extack, bool *msg_updated) @@ -701,10 +699,10 @@ static int devlink_port_fn_hw_addr_fill(const struct devlink_ops *ops, int hw_addr_len; int err; - if (!ops->port_function_hw_addr_get) + if (!port->ops->port_fn_hw_addr_get) return 0; - err = ops->port_function_hw_addr_get(port, hw_addr, &hw_addr_len, + err = port->ops->port_fn_hw_addr_get(port, hw_addr, &hw_addr_len, extack); if (err) { if (err == -EOPNOTSUPP) @@ -789,8 +787,7 @@ devlink_port_fn_opstate_valid(enum devlink_port_fn_opstate opstate) opstate == DEVLINK_PORT_FN_OPSTATE_ATTACHED; } -static int devlink_port_fn_state_fill(const struct devlink_ops *ops, - struct devlink_port *port, +static int devlink_port_fn_state_fill(struct devlink_port *port, struct sk_buff *msg, struct netlink_ext_ack *extack, bool *msg_updated) @@ -799,10 +796,10 @@ static int devlink_port_fn_state_fill(const struct devlink_ops *ops, enum devlink_port_fn_state state; int err; - if (!ops->port_fn_state_get) + if (!port->ops->port_fn_state_get) return 0; - err = ops->port_fn_state_get(port, &state, &opstate, extack); + err = port->ops->port_fn_state_get(port, &state, &opstate, extack); if (err) { if (err == -EOPNOTSUPP) return 0; @@ -829,18 +826,16 @@ static int devlink_port_fn_mig_set(struct devlink_port *devlink_port, bool enable, struct netlink_ext_ack *extack) { - const struct devlink_ops *ops = devlink_port->devlink->ops; - - return ops->port_fn_migratable_set(devlink_port, enable, extack); + return devlink_port->ops->port_fn_migratable_set(devlink_port, enable, + extack); } static int devlink_port_fn_roce_set(struct devlink_port *devlink_port, bool enable, struct netlink_ext_ack *extack) { - const struct devlink_ops *ops = devlink_port->devlink->ops; - - return ops->port_fn_roce_set(devlink_port, enable, extack); + return devlink_port->ops->port_fn_roce_set(devlink_port, enable, + extack); } static int devlink_port_fn_caps_set(struct devlink_port *devlink_port, @@ -874,7 +869,6 @@ static int devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *port, struct netlink_ext_ack *extack) { - const struct devlink_ops *ops; struct nlattr *function_attr; bool msg_updated = false; int err; @@ -883,16 +877,13 @@ devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *por if (!function_attr) return -EMSGSIZE; - ops = port->devlink->ops; - err = devlink_port_fn_hw_addr_fill(ops, port, msg, extack, - &msg_updated); + err = devlink_port_fn_hw_addr_fill(port, msg, extack, &msg_updated); if (err) goto out; - err = devlink_port_fn_caps_fill(ops, port, msg, extack, - &msg_updated); + err = devlink_port_fn_caps_fill(port, msg, extack, &msg_updated); if (err) goto out; - err = devlink_port_fn_state_fill(ops, port, msg, extack, &msg_updated); + err = devlink_port_fn_state_fill(port, msg, extack, &msg_updated); out: if (err || !msg_updated) nla_nest_cancel(msg, function_attr); @@ -1137,14 +1128,13 @@ static int devlink_port_type_set(struct devlink_port *devlink_port, { int err; - if (!devlink_port->devlink->ops->port_type_set) + if (!devlink_port->ops->port_type_set) return -EOPNOTSUPP; if (port_type == devlink_port->type) return 0; - err = devlink_port->devlink->ops->port_type_set(devlink_port, - port_type); + err = devlink_port->ops->port_type_set(devlink_port, port_type); if (err) return err; @@ -1157,7 +1147,6 @@ static int devlink_port_function_hw_addr_set(struct devlink_port *port, const struct nlattr *attr, struct netlink_ext_ack *extack) { - const struct devlink_ops *ops = port->devlink->ops; const u8 *hw_addr; int hw_addr_len; @@ -1178,7 +1167,7 @@ static int devlink_port_function_hw_addr_set(struct devlink_port *port, } } - return ops->port_function_hw_addr_set(port, hw_addr, hw_addr_len, + return port->ops->port_fn_hw_addr_set(port, hw_addr, hw_addr_len, extack); } @@ -1187,22 +1176,20 @@ static int devlink_port_fn_state_set(struct devlink_port *port, struct netlink_ext_ack *extack) { enum devlink_port_fn_state state; - const struct devlink_ops *ops; state = nla_get_u8(attr); - ops = port->devlink->ops; - return ops->port_fn_state_set(port, state, extack); + return port->ops->port_fn_state_set(port, state, extack); } static int devlink_port_function_validate(struct devlink_port *devlink_port, struct nlattr **tb, struct netlink_ext_ack *extack) { - const struct devlink_ops *ops = devlink_port->devlink->ops; + const struct devlink_port_ops *ops = devlink_port->ops; struct nlattr *attr; if (tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] && - !ops->port_function_hw_addr_set) { + !ops->port_fn_hw_addr_set) { NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR], "Port doesn't support function attributes"); return -EOPNOTSUPP; @@ -1320,7 +1307,7 @@ static int devlink_nl_cmd_port_split_doit(struct sk_buff *skb, if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_PORT_SPLIT_COUNT)) return -EINVAL; - if (!devlink->ops->port_split) + if (!devlink_port->ops->port_split) return -EOPNOTSUPP; count = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_SPLIT_COUNT]); @@ -1339,8 +1326,8 @@ static int devlink_nl_cmd_port_split_doit(struct sk_buff *skb, return -EINVAL; } - return devlink->ops->port_split(devlink, devlink_port, count, - info->extack); + return devlink_port->ops->port_split(devlink, devlink_port, count, + info->extack); } static int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb, @@ -1349,40 +1336,9 @@ static int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb, struct devlink_port *devlink_port = info->user_ptr[1]; struct devlink *devlink = info->user_ptr[0]; - if (!devlink->ops->port_unsplit) + if (!devlink_port->ops->port_unsplit) return -EOPNOTSUPP; - return devlink->ops->port_unsplit(devlink, devlink_port, info->extack); -} - -static int devlink_port_new_notify(struct devlink *devlink, - unsigned int port_index, - struct genl_info *info) -{ - struct devlink_port *devlink_port; - struct sk_buff *msg; - int err; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - lockdep_assert_held(&devlink->lock); - devlink_port = devlink_port_get_by_index(devlink, port_index); - if (!devlink_port) { - err = -ENODEV; - goto out; - } - - err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_NEW, - info->snd_portid, info->snd_seq, 0, NULL); - if (err) - goto out; - - return genlmsg_reply(msg, info); - -out: - nlmsg_free(msg); - return err; + return devlink_port->ops->port_unsplit(devlink, devlink_port, info->extack); } static int devlink_nl_cmd_port_new_doit(struct sk_buff *skb, @@ -1391,10 +1347,11 @@ static int devlink_nl_cmd_port_new_doit(struct sk_buff *skb, struct netlink_ext_ack *extack = info->extack; struct devlink_port_new_attrs new_attrs = {}; struct devlink *devlink = info->user_ptr[0]; - unsigned int new_port_index; + struct devlink_port *devlink_port; + struct sk_buff *msg; int err; - if (!devlink->ops->port_new || !devlink->ops->port_del) + if (!devlink->ops->port_new) return -EOPNOTSUPP; if (!info->attrs[DEVLINK_ATTR_PORT_FLAVOUR] || @@ -1423,36 +1380,43 @@ static int devlink_nl_cmd_port_new_doit(struct sk_buff *skb, new_attrs.sfnum_valid = true; } - err = devlink->ops->port_new(devlink, &new_attrs, extack, - &new_port_index); + err = devlink->ops->port_new(devlink, &new_attrs, + extack, &devlink_port); if (err) return err; - err = devlink_port_new_notify(devlink, new_port_index, info); - if (err && err != -ENODEV) { - /* Fail to send the response; destroy newly created port. */ - devlink->ops->port_del(devlink, new_port_index, extack); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) { + err = -ENOMEM; + goto err_out_port_del; } + err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_NEW, + info->snd_portid, info->snd_seq, 0, NULL); + if (WARN_ON_ONCE(err)) + goto err_out_msg_free; + err = genlmsg_reply(msg, info); + if (err) + goto err_out_port_del; + return 0; + +err_out_msg_free: + nlmsg_free(msg); +err_out_port_del: + devlink_port->ops->port_del(devlink, devlink_port, NULL); return err; } static int devlink_nl_cmd_port_del_doit(struct sk_buff *skb, struct genl_info *info) { + struct devlink_port *devlink_port = info->user_ptr[1]; struct netlink_ext_ack *extack = info->extack; struct devlink *devlink = info->user_ptr[0]; - unsigned int port_index; - if (!devlink->ops->port_del) + if (!devlink_port->ops->port_del) return -EOPNOTSUPP; - if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_PORT_INDEX)) { - NL_SET_ERR_MSG(extack, "Port index is not specified"); - return -EINVAL; - } - port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); - - return devlink->ops->port_del(devlink, port_index, extack); + return devlink_port->ops->port_del(devlink, devlink_port, extack); } static int @@ -6384,6 +6348,7 @@ const struct genl_small_ops devlink_nl_ops[56] = { .cmd = DEVLINK_CMD_PORT_DEL, .doit = devlink_nl_cmd_port_del_doit, .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, }, { .cmd = DEVLINK_CMD_LINECARD_GET, @@ -6809,7 +6774,7 @@ static void devlink_port_type_warn_cancel(struct devlink_port *devlink_port) * @devlink: devlink * @devlink_port: devlink port * - * Initialize essencial stuff that is needed for functions + * Initialize essential stuff that is needed for functions * that may be called before devlink port registration. * Call to this function is optional and not needed * in case the driver does not use such functions. @@ -6830,7 +6795,7 @@ EXPORT_SYMBOL_GPL(devlink_port_init); * * @devlink_port: devlink port * - * Deinitialize essencial stuff that is in use for functions + * Deinitialize essential stuff that is in use for functions * that may be called after devlink port unregistration. * Call to this function is optional and not needed * in case the driver does not use such functions. @@ -6841,12 +6806,15 @@ void devlink_port_fini(struct devlink_port *devlink_port) } EXPORT_SYMBOL_GPL(devlink_port_fini); +static const struct devlink_port_ops devlink_port_dummy_ops = {}; + /** - * devl_port_register() - Register devlink port + * devl_port_register_with_ops() - Register devlink port * * @devlink: devlink * @devlink_port: devlink port * @port_index: driver-specific numerical identifier of the port + * @ops: port ops * * Register devlink port with provided port index. User can use * any indexing, even hw-related one. devlink_port structure @@ -6854,9 +6822,10 @@ EXPORT_SYMBOL_GPL(devlink_port_fini); * Note that the caller should take care of zeroing the devlink_port * structure. */ -int devl_port_register(struct devlink *devlink, - struct devlink_port *devlink_port, - unsigned int port_index) +int devl_port_register_with_ops(struct devlink *devlink, + struct devlink_port *devlink_port, + unsigned int port_index, + const struct devlink_port_ops *ops) { int err; @@ -6867,6 +6836,7 @@ int devl_port_register(struct devlink *devlink, devlink_port_init(devlink, devlink_port); devlink_port->registered = true; devlink_port->index = port_index; + devlink_port->ops = ops ? ops : &devlink_port_dummy_ops; spin_lock_init(&devlink_port->type_lock); INIT_LIST_HEAD(&devlink_port->reporter_list); err = xa_insert(&devlink->ports, port_index, devlink_port, GFP_KERNEL); @@ -6878,14 +6848,15 @@ int devl_port_register(struct devlink *devlink, devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); return 0; } -EXPORT_SYMBOL_GPL(devl_port_register); +EXPORT_SYMBOL_GPL(devl_port_register_with_ops); /** - * devlink_port_register - Register devlink port + * devlink_port_register_with_ops - Register devlink port * * @devlink: devlink * @devlink_port: devlink port * @port_index: driver-specific numerical identifier of the port + * @ops: port ops * * Register devlink port with provided port index. User can use * any indexing, even hw-related one. devlink_port structure @@ -6895,18 +6866,20 @@ EXPORT_SYMBOL_GPL(devl_port_register); * * Context: Takes and release devlink->lock <mutex>. */ -int devlink_port_register(struct devlink *devlink, - struct devlink_port *devlink_port, - unsigned int port_index) +int devlink_port_register_with_ops(struct devlink *devlink, + struct devlink_port *devlink_port, + unsigned int port_index, + const struct devlink_port_ops *ops) { int err; devl_lock(devlink); - err = devl_port_register(devlink, devlink_port, port_index); + err = devl_port_register_with_ops(devlink, devlink_port, + port_index, ops); devl_unlock(devlink); return err; } -EXPORT_SYMBOL_GPL(devlink_port_register); +EXPORT_SYMBOL_GPL(devlink_port_register_with_ops); /** * devl_port_unregister() - Unregister devlink port @@ -7073,10 +7046,9 @@ int devlink_port_netdevice_event(struct notifier_block *nb, struct devlink_port *devlink_port = netdev->devlink_port; struct devlink *devlink; - devlink = container_of(nb, struct devlink, netdevice_nb); - - if (!devlink_port || devlink_port->devlink != devlink) + if (!devlink_port) return NOTIFY_OK; + devlink = devlink_port->devlink; switch (event) { case NETDEV_POST_INIT: diff --git a/net/dsa/port.c b/net/dsa/port.c index 71ba30538411..0ce8fd311c78 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -1603,6 +1603,21 @@ dsa_port_phylink_mac_select_pcs(struct phylink_config *config, return pcs; } +static int dsa_port_phylink_mac_prepare(struct phylink_config *config, + unsigned int mode, + phy_interface_t interface) +{ + struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); + struct dsa_switch *ds = dp->ds; + int err = 0; + + if (ds->ops->phylink_mac_prepare) + err = ds->ops->phylink_mac_prepare(ds, dp->index, mode, + interface); + + return err; +} + static void dsa_port_phylink_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) @@ -1616,6 +1631,21 @@ static void dsa_port_phylink_mac_config(struct phylink_config *config, ds->ops->phylink_mac_config(ds, dp->index, mode, state); } +static int dsa_port_phylink_mac_finish(struct phylink_config *config, + unsigned int mode, + phy_interface_t interface) +{ + struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); + struct dsa_switch *ds = dp->ds; + int err = 0; + + if (ds->ops->phylink_mac_finish) + err = ds->ops->phylink_mac_finish(ds, dp->index, mode, + interface); + + return err; +} + static void dsa_port_phylink_mac_an_restart(struct phylink_config *config) { struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); @@ -1671,7 +1701,9 @@ static const struct phylink_mac_ops dsa_port_phylink_mac_ops = { .validate = dsa_port_phylink_validate, .mac_select_pcs = dsa_port_phylink_mac_select_pcs, .mac_pcs_get_state = dsa_port_phylink_mac_pcs_get_state, + .mac_prepare = dsa_port_phylink_mac_prepare, .mac_config = dsa_port_phylink_mac_config, + .mac_finish = dsa_port_phylink_mac_finish, .mac_an_restart = dsa_port_phylink_mac_an_restart, .mac_link_down = dsa_port_phylink_mac_link_down, .mac_link_up = dsa_port_phylink_mac_link_up, diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 6bb778e10461..37b582225854 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1436,15 +1436,25 @@ static int ethtool_get_wol(struct net_device *dev, char __user *useraddr) static int ethtool_set_wol(struct net_device *dev, char __user *useraddr) { - struct ethtool_wolinfo wol; + struct ethtool_wolinfo wol, cur_wol; int ret; - if (!dev->ethtool_ops->set_wol) + if (!dev->ethtool_ops->get_wol || !dev->ethtool_ops->set_wol) return -EOPNOTSUPP; + memset(&cur_wol, 0, sizeof(struct ethtool_wolinfo)); + cur_wol.cmd = ETHTOOL_GWOL; + dev->ethtool_ops->get_wol(dev, &cur_wol); + if (copy_from_user(&wol, useraddr, sizeof(wol))) return -EFAULT; + if (wol.wolopts & ~cur_wol.supported) + return -EINVAL; + + if (wol.wolopts == cur_wol.wolopts) + return 0; + ret = dev->ethtool_ops->set_wol(dev, &wol); if (ret) return ret; diff --git a/net/handshake/genl.c b/net/handshake/genl.c index 9f29efb1493e..233be5cbfec9 100644 --- a/net/handshake/genl.c +++ b/net/handshake/genl.c @@ -8,7 +8,7 @@ #include "genl.h" -#include <linux/handshake.h> +#include <uapi/linux/handshake.h> /* HANDSHAKE_CMD_ACCEPT - do */ static const struct nla_policy handshake_accept_nl_policy[HANDSHAKE_A_ACCEPT_HANDLER_CLASS + 1] = { diff --git a/net/handshake/genl.h b/net/handshake/genl.h index 2c1f1aa6a02a..ae72a596f6cc 100644 --- a/net/handshake/genl.h +++ b/net/handshake/genl.h @@ -9,7 +9,7 @@ #include <net/netlink.h> #include <net/genetlink.h> -#include <linux/handshake.h> +#include <uapi/linux/handshake.h> int handshake_nl_accept_doit(struct sk_buff *skb, struct genl_info *info); int handshake_nl_done_doit(struct sk_buff *skb, struct genl_info *info); diff --git a/net/handshake/handshake-test.c b/net/handshake/handshake-test.c index e6adc5dec11a..6d37bab35c8f 100644 --- a/net/handshake/handshake-test.c +++ b/net/handshake/handshake-test.c @@ -102,7 +102,7 @@ struct handshake_req_alloc_test_param handshake_req_alloc_params[] = { { .desc = "handshake_req_alloc excessive privsize", .proto = &handshake_req_alloc_proto_6, - .gfp = GFP_KERNEL, + .gfp = GFP_KERNEL | __GFP_NOWARN, .expect_success = false, }, { @@ -209,6 +209,7 @@ static void handshake_req_submit_test4(struct kunit *test) { struct handshake_req *req, *result; struct socket *sock; + struct file *filp; int err; /* Arrange */ @@ -218,9 +219,10 @@ static void handshake_req_submit_test4(struct kunit *test) err = __sock_create(&init_net, PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock, 1); KUNIT_ASSERT_EQ(test, err, 0); - sock->file = sock_alloc_file(sock, O_NONBLOCK, NULL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, sock->file); + filp = sock_alloc_file(sock, O_NONBLOCK, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, filp); KUNIT_ASSERT_NOT_NULL(test, sock->sk); + sock->file = filp; err = handshake_req_submit(sock, req, GFP_KERNEL); KUNIT_ASSERT_EQ(test, err, 0); @@ -241,6 +243,7 @@ static void handshake_req_submit_test5(struct kunit *test) struct handshake_req *req; struct handshake_net *hn; struct socket *sock; + struct file *filp; struct net *net; int saved, err; @@ -251,9 +254,10 @@ static void handshake_req_submit_test5(struct kunit *test) err = __sock_create(&init_net, PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock, 1); KUNIT_ASSERT_EQ(test, err, 0); - sock->file = sock_alloc_file(sock, O_NONBLOCK, NULL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, sock->file); + filp = sock_alloc_file(sock, O_NONBLOCK, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, filp); KUNIT_ASSERT_NOT_NULL(test, sock->sk); + sock->file = filp; net = sock_net(sock->sk); hn = handshake_pernet(net); @@ -276,6 +280,7 @@ static void handshake_req_submit_test6(struct kunit *test) { struct handshake_req *req1, *req2; struct socket *sock; + struct file *filp; int err; /* Arrange */ @@ -287,9 +292,10 @@ static void handshake_req_submit_test6(struct kunit *test) err = __sock_create(&init_net, PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock, 1); KUNIT_ASSERT_EQ(test, err, 0); - sock->file = sock_alloc_file(sock, O_NONBLOCK, NULL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, sock->file); + filp = sock_alloc_file(sock, O_NONBLOCK, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, filp); KUNIT_ASSERT_NOT_NULL(test, sock->sk); + sock->file = filp; /* Act */ err = handshake_req_submit(sock, req1, GFP_KERNEL); @@ -307,6 +313,7 @@ static void handshake_req_cancel_test1(struct kunit *test) { struct handshake_req *req; struct socket *sock; + struct file *filp; bool result; int err; @@ -318,8 +325,9 @@ static void handshake_req_cancel_test1(struct kunit *test) &sock, 1); KUNIT_ASSERT_EQ(test, err, 0); - sock->file = sock_alloc_file(sock, O_NONBLOCK, NULL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, sock->file); + filp = sock_alloc_file(sock, O_NONBLOCK, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, filp); + sock->file = filp; err = handshake_req_submit(sock, req, GFP_KERNEL); KUNIT_ASSERT_EQ(test, err, 0); @@ -340,6 +348,7 @@ static void handshake_req_cancel_test2(struct kunit *test) struct handshake_req *req, *next; struct handshake_net *hn; struct socket *sock; + struct file *filp; struct net *net; bool result; int err; @@ -352,8 +361,9 @@ static void handshake_req_cancel_test2(struct kunit *test) &sock, 1); KUNIT_ASSERT_EQ(test, err, 0); - sock->file = sock_alloc_file(sock, O_NONBLOCK, NULL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, sock->file); + filp = sock_alloc_file(sock, O_NONBLOCK, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, filp); + sock->file = filp; err = handshake_req_submit(sock, req, GFP_KERNEL); KUNIT_ASSERT_EQ(test, err, 0); @@ -380,6 +390,7 @@ static void handshake_req_cancel_test3(struct kunit *test) struct handshake_req *req, *next; struct handshake_net *hn; struct socket *sock; + struct file *filp; struct net *net; bool result; int err; @@ -392,8 +403,9 @@ static void handshake_req_cancel_test3(struct kunit *test) &sock, 1); KUNIT_ASSERT_EQ(test, err, 0); - sock->file = sock_alloc_file(sock, O_NONBLOCK, NULL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, sock->file); + filp = sock_alloc_file(sock, O_NONBLOCK, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, filp); + sock->file = filp; err = handshake_req_submit(sock, req, GFP_KERNEL); KUNIT_ASSERT_EQ(test, err, 0); @@ -436,6 +448,7 @@ static void handshake_req_destroy_test1(struct kunit *test) { struct handshake_req *req; struct socket *sock; + struct file *filp; int err; /* Arrange */ @@ -448,8 +461,9 @@ static void handshake_req_destroy_test1(struct kunit *test) &sock, 1); KUNIT_ASSERT_EQ(test, err, 0); - sock->file = sock_alloc_file(sock, O_NONBLOCK, NULL); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, sock->file); + filp = sock_alloc_file(sock, O_NONBLOCK, NULL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, filp); + sock->file = filp; err = handshake_req_submit(sock, req, GFP_KERNEL); KUNIT_ASSERT_EQ(test, err, 0); diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index 3ba4c0f27af9..a91283d1e5bf 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -318,7 +318,7 @@ err: } #ifdef CONFIG_SYSCTL -static unsigned long lowpanfrag_low_thresh_unuesd = IPV6_FRAG_LOW_THRESH; + static struct ctl_table lowpan_frags_ns_ctl_table[] = { { .procname = "6lowpanfrag_high_thresh", @@ -374,9 +374,9 @@ static int __net_init lowpan_frags_ns_sysctl_register(struct net *net) } table[0].data = &ieee802154_lowpan->fqdir->high_thresh; - table[0].extra1 = &lowpanfrag_low_thresh_unuesd; - table[1].data = &lowpanfrag_low_thresh_unuesd; - table[1].extra2 = &ieee802154_lowpan->fqdir->high_thresh; + table[0].extra1 = &ieee802154_lowpan->fqdir->low_thresh; + table[1].data = &ieee802154_lowpan->fqdir->low_thresh; + table[1].extra2 = &ieee802154_lowpan->fqdir->high_thresh; table[2].data = &ieee802154_lowpan->fqdir->timeout; hdr = register_net_sysctl(net, "net/ieee802154/6lowpan", table); @@ -451,6 +451,7 @@ static int __net_init lowpan_frags_init_net(struct net *net) return res; ieee802154_lowpan->fqdir->high_thresh = IPV6_FRAG_HIGH_THRESH; + ieee802154_lowpan->fqdir->low_thresh = IPV6_FRAG_LOW_THRESH; ieee802154_lowpan->fqdir->timeout = IPV6_FRAG_TIMEOUT; res = lowpan_frags_ns_sysctl_register(net); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index c4aab3aacbd8..fd233c4195ac 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -586,6 +586,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) add_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending += writebias; + sk->sk_wait_pending++; /* Basic assumption: if someone sets sk->sk_err, he _must_ * change state of the socket from TCP_SYN_*. @@ -601,6 +602,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) } remove_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending -= writebias; + sk->sk_wait_pending--; return timeo; } @@ -730,6 +732,20 @@ int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, } EXPORT_SYMBOL(inet_stream_connect); +void __inet_accept(struct socket *sock, struct socket *newsock, struct sock *newsk) +{ + sock_rps_record_flow(newsk); + WARN_ON(!((1 << newsk->sk_state) & + (TCPF_ESTABLISHED | TCPF_SYN_RECV | + TCPF_CLOSE_WAIT | TCPF_CLOSE))); + + if (test_bit(SOCK_SUPPORT_ZC, &sock->flags)) + set_bit(SOCK_SUPPORT_ZC, &newsock->flags); + sock_graft(newsk, newsock); + + newsock->state = SS_CONNECTED; +} + /* * Accept a pending connection. The TCP layer now gives BSD semantics. */ @@ -743,24 +759,12 @@ int inet_accept(struct socket *sock, struct socket *newsock, int flags, /* IPV6_ADDRFORM can change sk->sk_prot under us. */ sk2 = READ_ONCE(sk1->sk_prot)->accept(sk1, flags, &err, kern); if (!sk2) - goto do_err; + return err; lock_sock(sk2); - - sock_rps_record_flow(sk2); - WARN_ON(!((1 << sk2->sk_state) & - (TCPF_ESTABLISHED | TCPF_SYN_RECV | - TCPF_CLOSE_WAIT | TCPF_CLOSE))); - - if (test_bit(SOCK_SUPPORT_ZC, &sock->flags)) - set_bit(SOCK_SUPPORT_ZC, &newsock->flags); - sock_graft(sk2, newsock); - - newsock->state = SS_CONNECTED; - err = 0; + __inet_accept(sock, newsock, sk2); release_sock(sk2); -do_err: - return err; + return 0; } EXPORT_SYMBOL(inet_accept); @@ -827,6 +831,21 @@ int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) } EXPORT_SYMBOL(inet_sendmsg); +void inet_splice_eof(struct socket *sock) +{ + const struct proto *prot; + struct sock *sk = sock->sk; + + if (unlikely(inet_send_prepare(sk))) + return; + + /* IPV6_ADDRFORM can change sk->sk_prot under us. */ + prot = READ_ONCE(sk->sk_prot); + if (prot->splice_eof) + prot->splice_eof(sock); +} +EXPORT_SYMBOL_GPL(inet_splice_eof); + ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { @@ -1046,6 +1065,7 @@ const struct proto_ops inet_stream_ops = { #ifdef CONFIG_MMU .mmap = tcp_mmap, #endif + .splice_eof = inet_splice_eof, .sendpage = inet_sendpage, .splice_read = tcp_splice_read, .read_sock = tcp_read_sock, @@ -1080,6 +1100,7 @@ const struct proto_ops inet_dgram_ops = { .read_skb = udp_read_skb, .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, + .splice_eof = inet_splice_eof, .sendpage = inet_sendpage, .set_peek_off = sk_set_peek_off, #ifdef CONFIG_COMPAT @@ -1111,6 +1132,7 @@ static const struct proto_ops inet_sockraw_ops = { .sendmsg = inet_sendmsg, .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, + .splice_eof = inet_splice_eof, .sendpage = inet_sendpage, #ifdef CONFIG_COMPAT .compat_ioctl = inet_compat_ioctl, diff --git a/net/ipv4/fou_nl.c b/net/ipv4/fou_nl.c index 6c37c4f98cca..98b90107b5ab 100644 --- a/net/ipv4/fou_nl.c +++ b/net/ipv4/fou_nl.c @@ -8,7 +8,7 @@ #include "fou_nl.h" -#include <linux/fou.h> +#include <uapi/linux/fou.h> /* Global operation policy for fou */ const struct nla_policy fou_nl_policy[FOU_ATTR_IFINDEX + 1] = { diff --git a/net/ipv4/fou_nl.h b/net/ipv4/fou_nl.h index dbd0780a5d34..63a6c4ed803d 100644 --- a/net/ipv4/fou_nl.h +++ b/net/ipv4/fou_nl.h @@ -9,7 +9,7 @@ #include <net/netlink.h> #include <net/genetlink.h> -#include <linux/fou.h> +#include <uapi/linux/fou.h> /* Global operation policy for fou */ extern const struct nla_policy fou_nl_policy[FOU_ATTR_IFINDEX + 1]; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 65ad4251f6fd..15424dec4584 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -792,7 +792,7 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk, opt = rcu_dereference(ireq->ireq_opt); flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark, - RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, + ip_sock_rt_tos(sk), ip_sock_rt_scope(sk), sk->sk_protocol, inet_sk_flowi_flags(sk), (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr, ireq->ir_loc_addr, ireq->ir_rmt_port, @@ -830,7 +830,7 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, fl4 = &newinet->cork.fl.u.ip4; flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark, - RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, + ip_sock_rt_tos(sk), ip_sock_rt_scope(sk), sk->sk_protocol, inet_sk_flowi_flags(sk), (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr, ireq->ir_loc_addr, ireq->ir_rmt_port, @@ -1142,6 +1142,7 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, if (newsk) { struct inet_connection_sock *newicsk = inet_csk(newsk); + newsk->sk_wait_pending = 0; inet_sk_set_state(newsk, TCP_SYN_RECV); newicsk->icsk_bind_hash = NULL; newicsk->icsk_bind2_hash = NULL; diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 0db5eb3dec83..69c00ffdcf3e 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -553,7 +553,7 @@ EXPORT_SYMBOL(ip_check_defrag); #ifdef CONFIG_SYSCTL static int dist_min; -static unsigned long ipfrag_low_thresh_unused; + static struct ctl_table ip4_frags_ns_ctl_table[] = { { .procname = "ipfrag_high_thresh", @@ -609,9 +609,9 @@ static int __net_init ip4_frags_ns_ctl_register(struct net *net) } table[0].data = &net->ipv4.fqdir->high_thresh; - table[0].extra1 = &ipfrag_low_thresh_unused; - table[1].data = &ipfrag_low_thresh_unused; - table[1].extra2 = &net->ipv4.fqdir->high_thresh; + table[0].extra1 = &net->ipv4.fqdir->low_thresh; + table[1].data = &net->ipv4.fqdir->low_thresh; + table[1].extra2 = &net->ipv4.fqdir->high_thresh; table[2].data = &net->ipv4.fqdir->timeout; table[3].data = &net->ipv4.fqdir->max_dist; @@ -674,9 +674,12 @@ static int __net_init ipv4_frags_init_net(struct net *net) * A 64K fragment consumes 129736 bytes (44*2944)+200 * (1500 truesize == 2944, sizeof(struct ipq) == 200) * - * We will commit 4MB at one time. Should we cross that limit. + * We will commit 4MB at one time. Should we cross that limit + * we will prune down to 3MB, making room for approx 8 big 64K + * fragments 8x128k. */ net->ipv4.fqdir->high_thresh = 4 * 1024 * 1024; + net->ipv4.fqdir->low_thresh = 3 * 1024 * 1024; /* * Important NOTE! Fragment queue must be destroyed before MSL expires. * RFC791 is wrong proposing to prolongate timer each fragment arrival diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index e55a20264960..81a1cce1a7d1 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -189,10 +189,10 @@ static int ipgre_err(struct sk_buff *skb, u32 info, } #if IS_ENABLED(CONFIG_IPV6) - if (tpi->proto == htons(ETH_P_IPV6) && - !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4 + tpi->hdr_len, - type, data_len)) - return 0; + if (tpi->proto == htons(ETH_P_IPV6) && + !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4 + tpi->hdr_len, + type, data_len)) + return 0; #endif if (t->parms.iph.daddr == 0 || diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 61892268e8a6..244fb9365d87 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -946,17 +946,6 @@ ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk } EXPORT_SYMBOL(ip_generic_getfrag); -static inline __wsum -csum_page(struct page *page, int offset, int copy) -{ - char *kaddr; - __wsum csum; - kaddr = kmap(page); - csum = csum_partial(kaddr + offset, copy, 0); - kunmap(page); - return csum; -} - static int __ip_append_data(struct sock *sk, struct flowi4 *fl4, struct sk_buff_head *queue, @@ -1048,6 +1037,14 @@ static int __ip_append_data(struct sock *sk, skb_zcopy_set(skb, uarg, &extra_uref); } } + } else if ((flags & MSG_SPLICE_PAGES) && length) { + if (inet->hdrincl) + return -EPERM; + if (rt->dst.dev->features & NETIF_F_SG) + /* We need an empty buffer to attach stuff to */ + paged = true; + else + flags &= ~MSG_SPLICE_PAGES; } cork->length += length; @@ -1207,6 +1204,15 @@ alloc_new_skb: err = -EFAULT; goto error; } + } else if (flags & MSG_SPLICE_PAGES) { + struct msghdr *msg = from; + + err = skb_splice_from_iter(skb, &msg->msg_iter, copy, + sk->sk_allocation); + if (err < 0) + goto error; + copy = err; + wmem_alloc_delta += copy; } else if (!zc) { int i = skb_shinfo(skb)->nr_frags; @@ -1310,10 +1316,10 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, } /* - * ip_append_data() and ip_append_page() can make one large IP datagram - * from many pieces of data. Each pieces will be holded on the socket - * until ip_push_pending_frames() is called. Each piece can be a page - * or non-page data. + * ip_append_data() can make one large IP datagram from many pieces of + * data. Each piece will be held on the socket until + * ip_push_pending_frames() is called. Each piece can be a page or + * non-page data. * * Not only UDP, other transport protocols - e.g. raw sockets - can use * this interface potentially. @@ -1346,134 +1352,6 @@ int ip_append_data(struct sock *sk, struct flowi4 *fl4, from, length, transhdrlen, flags); } -ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, - int offset, size_t size, int flags) -{ - struct inet_sock *inet = inet_sk(sk); - struct sk_buff *skb; - struct rtable *rt; - struct ip_options *opt = NULL; - struct inet_cork *cork; - int hh_len; - int mtu; - int len; - int err; - unsigned int maxfraglen, fragheaderlen, fraggap, maxnonfragsize; - - if (inet->hdrincl) - return -EPERM; - - if (flags&MSG_PROBE) - return 0; - - if (skb_queue_empty(&sk->sk_write_queue)) - return -EINVAL; - - cork = &inet->cork.base; - rt = (struct rtable *)cork->dst; - if (cork->flags & IPCORK_OPT) - opt = cork->opt; - - if (!(rt->dst.dev->features & NETIF_F_SG)) - return -EOPNOTSUPP; - - hh_len = LL_RESERVED_SPACE(rt->dst.dev); - mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize; - - fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); - maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; - maxnonfragsize = ip_sk_ignore_df(sk) ? 0xFFFF : mtu; - - if (cork->length + size > maxnonfragsize - fragheaderlen) { - ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, - mtu - (opt ? opt->optlen : 0)); - return -EMSGSIZE; - } - - skb = skb_peek_tail(&sk->sk_write_queue); - if (!skb) - return -EINVAL; - - cork->length += size; - - while (size > 0) { - /* Check if the remaining data fits into current packet. */ - len = mtu - skb->len; - if (len < size) - len = maxfraglen - skb->len; - - if (len <= 0) { - struct sk_buff *skb_prev; - int alloclen; - - skb_prev = skb; - fraggap = skb_prev->len - maxfraglen; - - alloclen = fragheaderlen + hh_len + fraggap + 15; - skb = sock_wmalloc(sk, alloclen, 1, sk->sk_allocation); - if (unlikely(!skb)) { - err = -ENOBUFS; - goto error; - } - - /* - * Fill in the control structures - */ - skb->ip_summed = CHECKSUM_NONE; - skb->csum = 0; - skb_reserve(skb, hh_len); - - /* - * Find where to start putting bytes. - */ - skb_put(skb, fragheaderlen + fraggap); - skb_reset_network_header(skb); - skb->transport_header = (skb->network_header + - fragheaderlen); - if (fraggap) { - skb->csum = skb_copy_and_csum_bits(skb_prev, - maxfraglen, - skb_transport_header(skb), - fraggap); - skb_prev->csum = csum_sub(skb_prev->csum, - skb->csum); - pskb_trim_unique(skb_prev, maxfraglen); - } - - /* - * Put the packet on the pending queue. - */ - __skb_queue_tail(&sk->sk_write_queue, skb); - continue; - } - - if (len > size) - len = size; - - if (skb_append_pagefrags(skb, page, offset, len)) { - err = -EMSGSIZE; - goto error; - } - - if (skb->ip_summed == CHECKSUM_NONE) { - __wsum csum; - csum = csum_page(page, offset, len); - skb->csum = csum_block_add(skb->csum, csum, skb->len); - } - - skb_len_add(skb, len); - refcount_add(len, &sk->sk_wmem_alloc); - offset += len; - size -= len; - } - return 0; - -error: - cork->length -= size; - IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS); - return err; -} - static void ip_cork_release(struct inet_cork *cork) { cork->flags &= ~IPCORK_OPT; @@ -1692,7 +1570,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, const struct ip_options *sopt, __be32 daddr, __be32 saddr, const struct ip_reply_arg *arg, - unsigned int len, u64 transmit_time) + unsigned int len, u64 transmit_time, u32 txhash) { struct ip_options_data replyopts; struct ipcm_cookie ipc; @@ -1755,6 +1633,8 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, arg->csum)); nskb->ip_summed = CHECKSUM_NONE; nskb->mono_delivery_time = !!transmit_time; + if (txhash) + skb_set_hash(nskb, txhash, PKT_HASH_TYPE_L4); ip_push_pending_frames(sk, &fl4); } out: diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index b511ff0adc0a..8e97d8d4cc9d 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -317,7 +317,14 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, ipc->tos = val; ipc->priority = rt_tos2priority(ipc->tos); break; - + case IP_PROTOCOL: + if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) + return -EINVAL; + val = *(int *)CMSG_DATA(cmsg); + if (val < 1 || val > 255) + return -EINVAL; + ipc->protocol = val; + break; default: return -EINVAL; } @@ -1761,6 +1768,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_LOCAL_PORT_RANGE: val = inet->local_port_range.hi << 16 | inet->local_port_range.lo; break; + case IP_PROTOCOL: + val = inet_sk(sk)->inet_num; + break; default: sockopt_release_sock(sk); return -ENOPROTOOPT; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 202fa1943ccd..c56b6fe6f0d7 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -173,9 +173,6 @@ static int ic_proto_have_if __initdata; /* MTU for boot device */ static int ic_dev_mtu __initdata; -/* DHCPACK can overwrite DNS if fallback was set upon first BOOTP reply */ -static int ic_nameservers_fallback __initdata; - #ifdef IPCONFIG_DYNAMIC static DEFINE_SPINLOCK(ic_recv_lock); static volatile int ic_got_reply __initdata; /* Proto(s) that replied */ @@ -668,6 +665,9 @@ static struct packet_type bootp_packet_type __initdata = { .func = ic_bootp_recv, }; +/* DHCPACK can overwrite DNS if fallback was set upon first BOOTP reply */ +static int ic_nameservers_fallback __initdata; + /* * Initialize DHCP/BOOTP extension fields in the request. */ diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 3793c81bda8a..25dd78cee179 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -705,7 +705,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct ip_options_data opt_copy; int free = 0; __be32 saddr, daddr, faddr; - u8 tos; + u8 tos, scope; int err; pr_debug("ping_v4_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num); @@ -769,11 +769,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) faddr = ipc.opt->opt.faddr; } tos = get_rttos(&ipc, inet); - if (sock_flag(sk, SOCK_LOCALROUTE) || - (msg->msg_flags & MSG_DONTROUTE) || - (ipc.opt && ipc.opt->opt.is_strictroute)) { - tos |= RTO_ONLINK; - } + scope = ip_sendmsg_scope(inet, &ipc, msg); if (ipv4_is_multicast(daddr)) { if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif)) @@ -783,10 +779,9 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } else if (!ipc.oif) ipc.oif = inet->uc_index; - flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, - RT_SCOPE_UNIVERSE, sk->sk_protocol, - inet_sk_flowi_flags(sk), faddr, saddr, 0, 0, - sk->sk_uid); + flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, scope, + sk->sk_protocol, inet_sk_flowi_flags(sk), faddr, + saddr, 0, 0, sk->sk_uid); fl4.fl4_icmp_type = user_icmph.type; fl4.fl4_icmp_code = user_icmph.code; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index ff712bf2a98d..9aacce9db7b9 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -476,10 +476,10 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct ipcm_cookie ipc; struct rtable *rt = NULL; struct flowi4 fl4; + u8 tos, scope; int free = 0; __be32 daddr; __be32 saddr; - u8 tos; int err; struct ip_options_data opt_copy; struct raw_frag_vec rfv; @@ -532,6 +532,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } ipcm_init_sk(&ipc, inet); + /* Keep backward compat */ + if (hdrincl) + ipc.protocol = IPPROTO_RAW; if (msg->msg_controllen) { err = ip_cmsg_send(sk, msg, &ipc, false); @@ -572,9 +575,8 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) daddr = ipc.opt->opt.faddr; } } - tos = get_rtconn_flags(&ipc, sk); - if (msg->msg_flags & MSG_DONTROUTE) - tos |= RTO_ONLINK; + tos = get_rttos(&ipc, inet); + scope = ip_sendmsg_scope(inet, &ipc, msg); if (ipv4_is_multicast(daddr)) { if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif)) @@ -597,9 +599,8 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } } - flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, - RT_SCOPE_UNIVERSE, - hdrincl ? IPPROTO_RAW : sk->sk_protocol, + flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, scope, + hdrincl ? ipc.protocol : sk->sk_protocol, inet_sk_flowi_flags(sk) | (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0, sk->sk_uid); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 26fb97d1d4d9..dc478a0574cb 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -418,8 +418,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) * no easy way to do this. */ flowi4_init_output(&fl4, ireq->ir_iif, ireq->ir_mark, - RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP, - inet_sk_flowi_flags(sk), + ip_sock_rt_tos(sk), ip_sock_rt_scope(sk), + IPPROTO_TCP, inet_sk_flowi_flags(sk), opt->srr ? opt->faddr : ireq->ir_rmt_addr, ireq->ir_loc_addr, th->source, th->dest, sk->sk_uid); security_req_classify_flow(req, flowi4_to_flowi_common(&fl4)); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 6ae3345a3bdf..356afe54951c 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -35,8 +35,8 @@ static int ip_ttl_max = 255; static int tcp_syn_retries_min = 1; static int tcp_syn_retries_max = MAX_TCP_SYNCNT; static int tcp_syn_linear_timeouts_max = MAX_TCP_SYNCNT; -static int ip_ping_group_range_min[] = { 0, 0 }; -static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; +static unsigned long ip_ping_group_range_min[] = { 0, 0 }; +static unsigned long ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; static u32 u32_max_div_HZ = UINT_MAX / HZ; static int one_day_secs = 24 * 3600; static u32 fib_multipath_hash_fields_all_mask __maybe_unused = @@ -166,7 +166,7 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write, { struct user_namespace *user_ns = current_user_ns(); int ret; - gid_t urange[2]; + unsigned long urange[2]; kgid_t low, high; struct ctl_table tmp = { .data = &urange, @@ -179,7 +179,7 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write, inet_get_ping_group_range_table(table, &low, &high); urange[0] = from_kgid_munged(user_ns, low); urange[1] = from_kgid_munged(user_ns, high); - ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + ret = proc_doulongvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && ret == 0) { low = make_kgid(user_ns, urange[0]); @@ -1472,13 +1472,13 @@ static struct ctl_table ipv4_net_table[] = { .extra2 = &tcp_plb_max_cong_thresh, }, { - .procname = "tcp_syn_linear_timeouts", - .data = &init_net.ipv4.sysctl_tcp_syn_linear_timeouts, - .maxlen = sizeof(u8), - .mode = 0644, - .proc_handler = proc_dou8vec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = &tcp_syn_linear_timeouts_max, + .procname = "tcp_syn_linear_timeouts", + .data = &init_net.ipv4.sysctl_tcp_syn_linear_timeouts, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &tcp_syn_linear_timeouts_max, }, { } }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 4d6392c16b7a..09f03221a6f1 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -974,175 +974,24 @@ static int tcp_wmem_schedule(struct sock *sk, int copy) return min(copy, sk->sk_forward_alloc); } -static struct sk_buff *tcp_build_frag(struct sock *sk, int size_goal, int flags, - struct page *page, int offset, size_t *size) -{ - struct sk_buff *skb = tcp_write_queue_tail(sk); - struct tcp_sock *tp = tcp_sk(sk); - bool can_coalesce; - int copy, i; - - if (!skb || (copy = size_goal - skb->len) <= 0 || - !tcp_skb_can_collapse_to(skb)) { -new_segment: - if (!sk_stream_memory_free(sk)) - return NULL; - - skb = tcp_stream_alloc_skb(sk, 0, sk->sk_allocation, - tcp_rtx_and_write_queues_empty(sk)); - if (!skb) - return NULL; - -#ifdef CONFIG_TLS_DEVICE - skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED); -#endif - tcp_skb_entail(sk, skb); - copy = size_goal; - } - - if (copy > *size) - copy = *size; - - i = skb_shinfo(skb)->nr_frags; - can_coalesce = skb_can_coalesce(skb, i, page, offset); - if (!can_coalesce && i >= READ_ONCE(sysctl_max_skb_frags)) { - tcp_mark_push(tp, skb); - goto new_segment; - } - if (tcp_downgrade_zcopy_pure(sk, skb)) - return NULL; - - copy = tcp_wmem_schedule(sk, copy); - if (!copy) - return NULL; - - if (can_coalesce) { - skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); - } else { - get_page(page); - skb_fill_page_desc_noacc(skb, i, page, offset, copy); - } - - if (!(flags & MSG_NO_SHARED_FRAGS)) - skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG; - - skb->len += copy; - skb->data_len += copy; - skb->truesize += copy; - sk_wmem_queued_add(sk, copy); - sk_mem_charge(sk, copy); - WRITE_ONCE(tp->write_seq, tp->write_seq + copy); - TCP_SKB_CB(skb)->end_seq += copy; - tcp_skb_pcount_set(skb, 0); - - *size = copy; - return skb; -} - -ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, - size_t size, int flags) -{ - struct tcp_sock *tp = tcp_sk(sk); - int mss_now, size_goal; - int err; - ssize_t copied; - long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); - - if (IS_ENABLED(CONFIG_DEBUG_VM) && - WARN_ONCE(!sendpage_ok(page), - "page must not be a Slab one and have page_count > 0")) - return -EINVAL; - - /* Wait for a connection to finish. One exception is TCP Fast Open - * (passive side) where data is allowed to be sent before a connection - * is fully established. - */ - if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) && - !tcp_passive_fastopen(sk)) { - err = sk_stream_wait_connect(sk, &timeo); - if (err != 0) - goto out_err; - } - - sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); - - mss_now = tcp_send_mss(sk, &size_goal, flags); - copied = 0; - - err = -EPIPE; - if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) - goto out_err; - - while (size > 0) { - struct sk_buff *skb; - size_t copy = size; - - skb = tcp_build_frag(sk, size_goal, flags, page, offset, ©); - if (!skb) - goto wait_for_space; - - if (!copied) - TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; - - copied += copy; - offset += copy; - size -= copy; - if (!size) - goto out; - - if (skb->len < size_goal || (flags & MSG_OOB)) - continue; - - if (forced_push(tp)) { - tcp_mark_push(tp, skb); - __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_PUSH); - } else if (skb == tcp_send_head(sk)) - tcp_push_one(sk, mss_now); - continue; - -wait_for_space: - set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); - tcp_push(sk, flags & ~MSG_MORE, mss_now, - TCP_NAGLE_PUSH, size_goal); - - err = sk_stream_wait_memory(sk, &timeo); - if (err != 0) - goto do_error; - - mss_now = tcp_send_mss(sk, &size_goal, flags); - } - -out: - if (copied) { - tcp_tx_timestamp(sk, sk->sk_tsflags); - if (!(flags & MSG_SENDPAGE_NOTLAST)) - tcp_push(sk, flags, mss_now, tp->nonagle, size_goal); - } - return copied; - -do_error: - tcp_remove_empty_skb(sk); - if (copied) - goto out; -out_err: - /* make sure we wake any epoll edge trigger waiter */ - if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { - sk->sk_write_space(sk); - tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); - } - return sk_stream_error(sk, flags, err); -} -EXPORT_SYMBOL_GPL(do_tcp_sendpages); - int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset, size_t size, int flags) { + struct bio_vec bvec; + struct msghdr msg = { .msg_flags = flags | MSG_SPLICE_PAGES, }; + if (!(sk->sk_route_caps & NETIF_F_SG)) return sock_no_sendpage_locked(sk, page, offset, size, flags); tcp_rate_check_app_limited(sk); /* is sending application-limited? */ - return do_tcp_sendpages(sk, page, offset, size, flags); + bvec_set_page(&bvec, page, size, offset); + iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); + + if (flags & MSG_SENDPAGE_NOTLAST) + msg.msg_flags |= MSG_MORE; + + return tcp_sendmsg_locked(sk, &msg, size); } EXPORT_SYMBOL_GPL(tcp_sendpage_locked); @@ -1223,28 +1072,31 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) int flags, err, copied = 0; int mss_now = 0, size_goal, copied_syn = 0; int process_backlog = 0; - bool zc = false; + int zc = 0; long timeo; flags = msg->msg_flags; if ((flags & MSG_ZEROCOPY) && size) { - skb = tcp_write_queue_tail(sk); - if (msg->msg_ubuf) { uarg = msg->msg_ubuf; - net_zcopy_get(uarg); - zc = sk->sk_route_caps & NETIF_F_SG; + if (sk->sk_route_caps & NETIF_F_SG) + zc = MSG_ZEROCOPY; } else if (sock_flag(sk, SOCK_ZEROCOPY)) { + skb = tcp_write_queue_tail(sk); uarg = msg_zerocopy_realloc(sk, size, skb_zcopy(skb)); if (!uarg) { err = -ENOBUFS; goto out_err; } - zc = sk->sk_route_caps & NETIF_F_SG; - if (!zc) + if (sk->sk_route_caps & NETIF_F_SG) + zc = MSG_ZEROCOPY; + else uarg_to_msgzc(uarg)->zerocopy = 0; } + } else if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES) && size) { + if (sk->sk_route_caps & NETIF_F_SG) + zc = MSG_SPLICE_PAGES; } if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) && @@ -1307,7 +1159,7 @@ restart: goto do_error; while (msg_data_left(msg)) { - int copy = 0; + ssize_t copy = 0; skb = tcp_write_queue_tail(sk); if (skb) @@ -1348,7 +1200,7 @@ new_segment: if (copy > msg_data_left(msg)) copy = msg_data_left(msg); - if (!zc) { + if (zc == 0) { bool merge = true; int i = skb_shinfo(skb)->nr_frags; struct page_frag *pfrag = sk_page_frag(sk); @@ -1393,7 +1245,7 @@ new_segment: page_ref_inc(pfrag->page); } pfrag->offset += copy; - } else { + } else if (zc == MSG_ZEROCOPY) { /* First append to a fragless skb builds initial * pure zerocopy skb */ @@ -1414,6 +1266,30 @@ new_segment: if (err < 0) goto do_error; copy = err; + } else if (zc == MSG_SPLICE_PAGES) { + /* Splice in data if we can; copy if we can't. */ + if (tcp_downgrade_zcopy_pure(sk, skb)) + goto wait_for_space; + copy = tcp_wmem_schedule(sk, copy); + if (!copy) + goto wait_for_space; + + err = skb_splice_from_iter(skb, &msg->msg_iter, copy, + sk->sk_allocation); + if (err < 0) { + if (err == -EMSGSIZE) { + tcp_mark_push(tp, skb); + goto new_segment; + } + goto do_error; + } + copy = err; + + if (!(flags & MSG_NO_SHARED_FRAGS)) + skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG; + + sk_wmem_queued_add(sk, copy); + sk_mem_charge(sk, copy); } if (!copied) @@ -1459,7 +1335,9 @@ out: tcp_push(sk, flags, mss_now, tp->nonagle, size_goal); } out_nopush: - net_zcopy_put(uarg); + /* msg->msg_ubuf is pinned by the caller so we don't take extra refs */ + if (uarg && !msg->msg_ubuf) + net_zcopy_put(uarg); return copied + copied_syn; do_error: @@ -1468,7 +1346,9 @@ do_error: if (copied + copied_syn) goto out; out_err: - net_zcopy_put_abort(uarg, true); + /* msg->msg_ubuf is pinned by the caller so we don't take extra refs */ + if (uarg && !msg->msg_ubuf) + net_zcopy_put_abort(uarg, true); err = sk_stream_error(sk, flags, err); /* make sure we wake any epoll edge trigger waiter */ if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { @@ -1491,6 +1371,22 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) } EXPORT_SYMBOL(tcp_sendmsg); +void tcp_splice_eof(struct socket *sock) +{ + struct sock *sk = sock->sk; + struct tcp_sock *tp = tcp_sk(sk); + int mss_now, size_goal; + + if (!tcp_write_queue_tail(sk)) + return; + + lock_sock(sk); + mss_now = tcp_send_mss(sk, &size_goal, 0); + tcp_push(sk, 0, mss_now, tp->nonagle, size_goal); + release_sock(sk); +} +EXPORT_SYMBOL_GPL(tcp_splice_eof); + /* * Handle reading urgent data. BSD has very simple semantics for * this, no blocking and very strange errors 8) @@ -1571,7 +1467,7 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len) * calculation of whether or not we must ACK for the sake of * a window update. */ -static void __tcp_cleanup_rbuf(struct sock *sk, int copied) +void __tcp_cleanup_rbuf(struct sock *sk, int copied) { struct tcp_sock *tp = tcp_sk(sk); bool time_to_ack = false; @@ -1773,7 +1669,6 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk)); tcp_flags = TCP_SKB_CB(skb)->tcp_flags; used = recv_actor(sk, skb); - consume_skb(skb); if (used < 0) { if (!copied) copied = used; @@ -1787,14 +1682,6 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) break; } } - WRITE_ONCE(tp->copied_seq, seq); - - tcp_rcv_space_adjust(sk); - - /* Clean up data we have read: This will do ACK frames. */ - if (copied > 0) - __tcp_cleanup_rbuf(sk, copied); - return copied; } EXPORT_SYMBOL(tcp_read_skb); @@ -3090,6 +2977,12 @@ int tcp_disconnect(struct sock *sk, int flags) int old_state = sk->sk_state; u32 seq; + /* Deny disconnect if other threads are blocked in sk_wait_event() + * or inet_wait_for_connect(). + */ + if (sk->sk_wait_pending) + return -EBUSY; + if (old_state != TCP_CLOSE) tcp_set_state(sk, TCP_CLOSE); @@ -4081,7 +3974,8 @@ int do_tcp_getsockopt(struct sock *sk, int level, switch (optname) { case TCP_MAXSEG: val = tp->mss_cache; - if (!val && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) + if (tp->rx_opt.user_mss && + ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) val = tp->rx_opt.user_mss; if (tp->repair) val = tp->rx_opt.mss_clamp; @@ -4682,8 +4576,10 @@ int tcp_abort(struct sock *sk, int err) return 0; } - /* Don't race with userspace socket closes such as tcp_close. */ - lock_sock(sk); + /* BPF context ensures sock locking. */ + if (!has_current_bpf_ctx()) + /* Don't race with userspace socket closes such as tcp_close. */ + lock_sock(sk); if (sk->sk_state == TCP_LISTEN) { tcp_set_state(sk, TCP_CLOSE); @@ -4707,7 +4603,8 @@ int tcp_abort(struct sock *sk, int err) bh_unlock_sock(sk); local_bh_enable(); tcp_write_queue_purge(sk); - release_sock(sk); + if (!has_current_bpf_ctx()) + release_sock(sk); return 0; } EXPORT_SYMBOL_GPL(tcp_abort); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 2e9547467edb..e75023ea052f 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -11,6 +11,24 @@ #include <net/inet_common.h> #include <net/tls.h> +void tcp_eat_skb(struct sock *sk, struct sk_buff *skb) +{ + struct tcp_sock *tcp; + int copied; + + if (!skb || !skb->len || !sk_is_tcp(sk)) + return; + + if (skb_bpf_strparser(skb)) + return; + + tcp = tcp_sk(sk); + copied = tcp->copied_seq + skb->len; + WRITE_ONCE(tcp->copied_seq, copied); + tcp_rcv_space_adjust(sk); + __tcp_cleanup_rbuf(sk, skb->len); +} + static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, struct sk_msg *msg, u32 apply_bytes, int flags) { @@ -72,11 +90,13 @@ static int tcp_bpf_push(struct sock *sk, struct sk_msg *msg, u32 apply_bytes, { bool apply = apply_bytes; struct scatterlist *sge; + struct msghdr msghdr = { .msg_flags = flags | MSG_SPLICE_PAGES, }; struct page *page; int size, ret = 0; u32 off; while (1) { + struct bio_vec bvec; bool has_tx_ulp; sge = sk_msg_elem(msg, msg->sg.start); @@ -88,16 +108,18 @@ static int tcp_bpf_push(struct sock *sk, struct sk_msg *msg, u32 apply_bytes, tcp_rate_check_app_limited(sk); retry: has_tx_ulp = tls_sw_has_ctx_tx(sk); - if (has_tx_ulp) { - flags |= MSG_SENDPAGE_NOPOLICY; - ret = kernel_sendpage_locked(sk, - page, off, size, flags); - } else { - ret = do_tcp_sendpages(sk, page, off, size, flags); - } + if (has_tx_ulp) + msghdr.msg_flags |= MSG_SENDPAGE_NOPOLICY; + + if (flags & MSG_SENDPAGE_NOTLAST) + msghdr.msg_flags |= MSG_MORE; + bvec_set_page(&bvec, page, size, off); + iov_iter_bvec(&msghdr.msg_iter, ITER_SOURCE, &bvec, 1, size); + ret = tcp_sendmsg_locked(sk, &msghdr, size); if (ret <= 0) return ret; + if (apply) apply_bytes -= ret; msg->sg.size -= ret; @@ -174,14 +196,34 @@ static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock, return ret; } +static bool is_next_msg_fin(struct sk_psock *psock) +{ + struct scatterlist *sge; + struct sk_msg *msg_rx; + int i; + + msg_rx = sk_psock_peek_msg(psock); + i = msg_rx->sg.start; + sge = sk_msg_elem(msg_rx, i); + if (!sge->length) { + struct sk_buff *skb = msg_rx->skb; + + if (skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) + return true; + } + return false; +} + static int tcp_bpf_recvmsg_parser(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { + struct tcp_sock *tcp = tcp_sk(sk); + u32 seq = tcp->copied_seq; struct sk_psock *psock; - int copied; + int copied = 0; if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); @@ -194,8 +236,43 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk, return tcp_recvmsg(sk, msg, len, flags, addr_len); lock_sock(sk); + + /* We may have received data on the sk_receive_queue pre-accept and + * then we can not use read_skb in this context because we haven't + * assigned a sk_socket yet so have no link to the ops. The work-around + * is to check the sk_receive_queue and in these cases read skbs off + * queue again. The read_skb hook is not running at this point because + * of lock_sock so we avoid having multiple runners in read_skb. + */ + if (unlikely(!skb_queue_empty(&sk->sk_receive_queue))) { + tcp_data_ready(sk); + /* This handles the ENOMEM errors if we both receive data + * pre accept and are already under memory pressure. At least + * let user know to retry. + */ + if (unlikely(!skb_queue_empty(&sk->sk_receive_queue))) { + copied = -EAGAIN; + goto out; + } + } + msg_bytes_ready: copied = sk_msg_recvmsg(sk, psock, msg, len, flags); + /* The typical case for EFAULT is the socket was gracefully + * shutdown with a FIN pkt. So check here the other case is + * some error on copy_page_to_iter which would be unexpected. + * On fin return correct return code to zero. + */ + if (copied == -EFAULT) { + bool is_fin = is_next_msg_fin(psock); + + if (is_fin) { + copied = 0; + seq++; + goto out; + } + } + seq += copied; if (!copied) { long timeo; int data; @@ -233,6 +310,10 @@ msg_bytes_ready: copied = -EAGAIN; } out: + WRITE_ONCE(tcp->copied_seq, seq); + tcp_rcv_space_adjust(sk); + if (copied > 0) + __tcp_cleanup_rbuf(sk, copied); release_sock(sk); sk_psock_put(sk, psock); return copied; @@ -404,7 +485,7 @@ static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) long timeo; int flags; - /* Don't let internal do_tcp_sendpages() flags through */ + /* Don't let internal sendpage flags through */ flags = (msg->msg_flags & ~MSG_SENDPAGE_DECRYPTED); flags |= MSG_NO_SHARED_FRAGS; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 61b6710f337a..bf8b22218dd4 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4530,7 +4530,7 @@ static void tcp_sack_maybe_coalesce(struct tcp_sock *tp) } } -static void tcp_sack_compress_send_ack(struct sock *sk) +void tcp_sack_compress_send_ack(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index db24ed8f8509..84a5d557dc1a 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -692,6 +692,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) u64 transmit_time = 0; struct sock *ctl_sk; struct net *net; + u32 txhash = 0; /* Never send a reset in response to a reset. */ if (th->rst) @@ -829,14 +830,18 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) inet_twsk(sk)->tw_priority : sk->sk_priority; transmit_time = tcp_transmit_time(sk); xfrm_sk_clone_policy(ctl_sk, sk); + txhash = (sk->sk_state == TCP_TIME_WAIT) ? + inet_twsk(sk)->tw_txhash : sk->sk_txhash; + } else { + ctl_sk->sk_mark = 0; + ctl_sk->sk_priority = 0; } ip_send_unicast_reply(ctl_sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len, - transmit_time); + transmit_time, txhash); - ctl_sk->sk_mark = 0; xfrm_sk_free_policy(ctl_sk); sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); @@ -857,7 +862,7 @@ static void tcp_v4_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, - int reply_flags, u8 tos) + int reply_flags, u8 tos, u32 txhash) { const struct tcphdr *th = tcp_hdr(skb); struct { @@ -933,9 +938,8 @@ static void tcp_v4_send_ack(const struct sock *sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len, - transmit_time); + transmit_time, txhash); - ctl_sk->sk_mark = 0; sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); local_bh_enable(); @@ -954,7 +958,8 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0, - tw->tw_tos + tw->tw_tos, + tw->tw_txhash ); inet_twsk_put(tw); @@ -987,7 +992,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, 0, tcp_md5_do_lookup(sk, l3index, addr, AF_INET), inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0, - ip_hdr(skb)->tos); + ip_hdr(skb)->tos, tcp_rsk(req)->txhash); } /* @@ -2962,7 +2967,6 @@ static int bpf_iter_tcp_seq_show(struct seq_file *seq, void *v) struct bpf_iter_meta meta; struct bpf_prog *prog; struct sock *sk = v; - bool slow; uid_t uid; int ret; @@ -2970,7 +2974,7 @@ static int bpf_iter_tcp_seq_show(struct seq_file *seq, void *v) return 0; if (sk_fullsock(sk)) - slow = lock_sock_fast(sk); + lock_sock(sk); if (unlikely(sk_unhashed(sk))) { ret = SEQ_SKIP; @@ -2994,7 +2998,7 @@ static int bpf_iter_tcp_seq_show(struct seq_file *seq, void *v) unlock: if (sk_fullsock(sk)) - unlock_sock_fast(sk, slow); + release_sock(sk); return ret; } @@ -3112,6 +3116,7 @@ struct proto tcp_prot = { .keepalive = tcp_set_keepalive, .recvmsg = tcp_recvmsg, .sendmsg = tcp_sendmsg, + .splice_eof = tcp_splice_eof, .sendpage = tcp_sendpage, .backlog_rcv = tcp_v4_do_rcv, .release_cb = tcp_release_cb, @@ -3356,7 +3361,7 @@ static struct bpf_iter_reg tcp_reg_info = { .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__tcp, sk_common), - PTR_TO_BTF_ID_OR_NULL }, + PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED }, }, .get_func_proto = bpf_iter_tcp_get_func_proto, .seq_info = &tcp_seq_info, diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index dac0d62120e6..04fc328727e6 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -303,6 +303,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) tcptw->tw_ts_offset = tp->tsoffset; tcptw->tw_last_oow_ack_time = 0; tcptw->tw_tx_delay = tp->tcp_tx_delay; + tw->tw_txhash = sk->sk_txhash; #if IS_ENABLED(CONFIG_IPV6) if (tw->tw_family == PF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); @@ -311,7 +312,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr; tw->tw_tclass = np->tclass; tw->tw_flowlabel = be32_to_cpu(np->flow_label & IPV6_FLOWLABEL_MASK); - tw->tw_txhash = sk->sk_txhash; tw->tw_ipv6only = sk->sk_ipv6only; } #endif diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 45dda7889387..05b38f58b404 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -60,12 +60,12 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, struct tcphdr *th; unsigned int thlen; unsigned int seq; - __be32 delta; unsigned int oldlen; unsigned int mss; struct sk_buff *gso_skb = skb; __sum16 newcheck; bool ooo_okay, copy_destructor; + __wsum delta; th = tcp_hdr(skb); thlen = th->doff * 4; @@ -75,7 +75,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, if (!pskb_may_pull(skb, thlen)) goto out; - oldlen = (u16)~skb->len; + oldlen = ~skb->len; __skb_pull(skb, thlen); mss = skb_shinfo(skb)->gso_size; @@ -110,7 +110,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, if (skb_is_gso(segs)) mss *= skb_shinfo(segs)->gso_segs; - delta = htonl(oldlen + (thlen + mss)); + delta = (__force __wsum)htonl(oldlen + thlen + mss); skb = segs; th = tcp_hdr(skb); @@ -119,8 +119,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, if (unlikely(skb_shinfo(gso_skb)->tx_flags & SKBTX_SW_TSTAMP)) tcp_gso_tstamp(segs, skb_shinfo(gso_skb)->tskey, seq, mss); - newcheck = ~csum_fold((__force __wsum)((__force u32)th->check + - (__force u32)delta)); + newcheck = ~csum_fold(csum_add(csum_unfold(th->check), delta)); while (skb->next) { th->fin = th->psh = 0; @@ -165,11 +164,11 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, WARN_ON_ONCE(refcount_sub_and_test(-delta, &skb->sk->sk_wmem_alloc)); } - delta = htonl(oldlen + (skb_tail_pointer(skb) - - skb_transport_header(skb)) + - skb->data_len); - th->check = ~csum_fold((__force __wsum)((__force u32)th->check + - (__force u32)delta)); + delta = (__force __wsum)htonl(oldlen + + (skb_tail_pointer(skb) - + skb_transport_header(skb)) + + skb->data_len); + th->check = ~csum_fold(csum_add(csum_unfold(th->check), delta)); if (skb->ip_summed == CHECKSUM_PARTIAL) gso_reset_checksum(skb, ~th->check); else @@ -296,7 +295,7 @@ out: return pp; } -int tcp_gro_complete(struct sk_buff *skb) +void tcp_gro_complete(struct sk_buff *skb) { struct tcphdr *th = tcp_hdr(skb); @@ -311,8 +310,6 @@ int tcp_gro_complete(struct sk_buff *skb) if (skb->encapsulation) skb->inner_transport_header = skb->transport_header; - - return 0; } EXPORT_SYMBOL(tcp_gro_complete); @@ -342,7 +339,8 @@ INDIRECT_CALLABLE_SCOPE int tcp4_gro_complete(struct sk_buff *skb, int thoff) if (NAPI_GRO_CB(skb)->is_atomic) skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_FIXEDID; - return tcp_gro_complete(skb); + tcp_gro_complete(skb); + return 0; } static const struct net_offload tcpv4_offload = { diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index cfe128b81a01..f8ce77ce7c3e 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2319,6 +2319,57 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len) return true; } +static int tcp_clone_payload(struct sock *sk, struct sk_buff *to, + int probe_size) +{ + skb_frag_t *lastfrag = NULL, *fragto = skb_shinfo(to)->frags; + int i, todo, len = 0, nr_frags = 0; + const struct sk_buff *skb; + + if (!sk_wmem_schedule(sk, to->truesize + probe_size)) + return -ENOMEM; + + skb_queue_walk(&sk->sk_write_queue, skb) { + const skb_frag_t *fragfrom = skb_shinfo(skb)->frags; + + if (skb_headlen(skb)) + return -EINVAL; + + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++, fragfrom++) { + if (len >= probe_size) + goto commit; + todo = min_t(int, skb_frag_size(fragfrom), + probe_size - len); + len += todo; + if (lastfrag && + skb_frag_page(fragfrom) == skb_frag_page(lastfrag) && + skb_frag_off(fragfrom) == skb_frag_off(lastfrag) + + skb_frag_size(lastfrag)) { + skb_frag_size_add(lastfrag, todo); + continue; + } + if (unlikely(nr_frags == MAX_SKB_FRAGS)) + return -E2BIG; + skb_frag_page_copy(fragto, fragfrom); + skb_frag_off_copy(fragto, fragfrom); + skb_frag_size_set(fragto, todo); + nr_frags++; + lastfrag = fragto++; + } + } +commit: + WARN_ON_ONCE(len != probe_size); + for (i = 0; i < nr_frags; i++) + skb_frag_ref(to, i); + + skb_shinfo(to)->nr_frags = nr_frags; + to->truesize += probe_size; + to->len += probe_size; + to->data_len += probe_size; + __skb_header_release(to); + return 0; +} + /* Create a new MTU probe if we are ready. * MTU probe is regularly attempting to increase the path MTU by * deliberately sending larger packets. This discovers routing @@ -2395,9 +2446,15 @@ static int tcp_mtu_probe(struct sock *sk) return -1; /* We're allowed to probe. Build it now. */ - nskb = tcp_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false); + nskb = tcp_stream_alloc_skb(sk, 0, GFP_ATOMIC, false); if (!nskb) return -1; + + /* build the payload, and be prepared to abort if this fails. */ + if (tcp_clone_payload(sk, nskb, probe_size)) { + consume_skb(nskb); + return -1; + } sk_wmem_queued_add(sk, nskb->truesize); sk_mem_charge(sk, nskb->truesize); @@ -2415,7 +2472,6 @@ static int tcp_mtu_probe(struct sock *sk) len = 0; tcp_for_write_queue_from_safe(skb, next, sk) { copy = min_t(int, skb->len, probe_size - len); - skb_copy_bits(skb, 0, skb_put(nskb, copy), copy); if (skb->len <= copy) { /* We've eaten all the data from this skb. diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 0d93a2573807..470f581eedd4 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -295,9 +295,19 @@ static int tcp_write_timeout(struct sock *sk) void tcp_delack_timer_handler(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); - if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || - !(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) + if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) + return; + + /* Handling the sack compression case */ + if (tp->compressed_ack) { + tcp_mstamp_refresh(tp); + tcp_sack_compress_send_ack(sk); + return; + } + + if (!(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) return; if (time_after(icsk->icsk_ack.timeout, jiffies)) { @@ -317,7 +327,7 @@ void tcp_delack_timer_handler(struct sock *sk) inet_csk_exit_pingpong_mode(sk); icsk->icsk_ack.ato = TCP_ATO_MIN; } - tcp_mstamp_refresh(tcp_sk(sk)); + tcp_mstamp_refresh(tp); tcp_send_ack(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS); } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index aa32afd871ee..df5e407286d7 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1062,8 +1062,8 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) int free = 0; int connected = 0; __be32 daddr, faddr, saddr; + u8 tos, scope; __be16 dport; - u8 tos; int err, is_udplite = IS_UDPLITE(sk); int corkreq = READ_ONCE(up->corkflag) || msg->msg_flags&MSG_MORE; int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); @@ -1183,12 +1183,9 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) connected = 0; } tos = get_rttos(&ipc, inet); - if (sock_flag(sk, SOCK_LOCALROUTE) || - (msg->msg_flags & MSG_DONTROUTE) || - (ipc.opt && ipc.opt->opt.is_strictroute)) { - tos |= RTO_ONLINK; + scope = ip_sendmsg_scope(inet, &ipc, msg); + if (scope == RT_SCOPE_LINK) connected = 0; - } if (ipv4_is_multicast(daddr)) { if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif)) @@ -1221,11 +1218,9 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl4 = &fl4_stack; - flowi4_init_output(fl4, ipc.oif, ipc.sockc.mark, tos, - RT_SCOPE_UNIVERSE, sk->sk_protocol, - flow_flags, - faddr, saddr, dport, inet->inet_sport, - sk->sk_uid); + flowi4_init_output(fl4, ipc.oif, ipc.sockc.mark, tos, scope, + sk->sk_protocol, flow_flags, faddr, saddr, + dport, inet->inet_sport, sk->sk_uid); security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4)); rt = ip_route_output_flow(net, fl4, sk); @@ -1329,57 +1324,33 @@ do_confirm: } EXPORT_SYMBOL(udp_sendmsg); -int udp_sendpage(struct sock *sk, struct page *page, int offset, - size_t size, int flags) +void udp_splice_eof(struct socket *sock) { - struct inet_sock *inet = inet_sk(sk); + struct sock *sk = sock->sk; struct udp_sock *up = udp_sk(sk); - int ret; - - if (flags & MSG_SENDPAGE_NOTLAST) - flags |= MSG_MORE; - - if (!up->pending) { - struct msghdr msg = { .msg_flags = flags|MSG_MORE }; - /* Call udp_sendmsg to specify destination address which - * sendpage interface can't pass. - * This will succeed only when the socket is connected. - */ - ret = udp_sendmsg(sk, &msg, 0); - if (ret < 0) - return ret; - } + if (!up->pending || READ_ONCE(up->corkflag)) + return; lock_sock(sk); + if (up->pending && !READ_ONCE(up->corkflag)) + udp_push_pending_frames(sk); + release_sock(sk); +} +EXPORT_SYMBOL_GPL(udp_splice_eof); - if (unlikely(!up->pending)) { - release_sock(sk); - - net_dbg_ratelimited("cork failed\n"); - return -EINVAL; - } +int udp_sendpage(struct sock *sk, struct page *page, int offset, + size_t size, int flags) +{ + struct bio_vec bvec; + struct msghdr msg = { .msg_flags = flags | MSG_SPLICE_PAGES }; - ret = ip_append_page(sk, &inet->cork.fl.u.ip4, - page, offset, size, flags); - if (ret == -EOPNOTSUPP) { - release_sock(sk); - return sock_no_sendpage(sk->sk_socket, page, offset, - size, flags); - } - if (ret < 0) { - udp_flush_pending_frames(sk); - goto out; - } + if (flags & MSG_SENDPAGE_NOTLAST) + msg.msg_flags |= MSG_MORE; - up->len += size; - if (!(READ_ONCE(up->corkflag) || (flags&MSG_MORE))) - ret = udp_push_pending_frames(sk); - if (!ret) - ret = size; -out: - release_sock(sk); - return ret; + bvec_set_page(&bvec, page, size, offset); + iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); + return udp_sendmsg(sk, &msg, size); } #define UDP_SKB_IS_STATELESS 0x80000000 @@ -1818,7 +1789,7 @@ EXPORT_SYMBOL(__skb_recv_udp); int udp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { struct sk_buff *skb; - int err, copied; + int err; try_again: skb = skb_recv_udp(sk, MSG_DONTWAIT, &err); @@ -1837,10 +1808,7 @@ try_again: } WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk)); - copied = recv_actor(sk, skb); - kfree_skb(skb); - - return copied; + return recv_actor(sk, skb); } EXPORT_SYMBOL(udp_read_skb); @@ -2930,7 +2898,8 @@ EXPORT_SYMBOL(udp_poll); int udp_abort(struct sock *sk, int err) { - lock_sock(sk); + if (!has_current_bpf_ctx()) + lock_sock(sk); /* udp{v6}_destroy_sock() sets it under the sk lock, avoid racing * with close() @@ -2943,7 +2912,8 @@ int udp_abort(struct sock *sk, int err) __udp_disconnect(sk, 0); out: - release_sock(sk); + if (!has_current_bpf_ctx()) + release_sock(sk); return 0; } @@ -2963,6 +2933,7 @@ struct proto udp_prot = { .getsockopt = udp_getsockopt, .sendmsg = udp_sendmsg, .recvmsg = udp_recvmsg, + .splice_eof = udp_splice_eof, .sendpage = udp_sendpage, .release_cb = ip4_datagram_release_cb, .hash = udp_lib_hash, @@ -2988,9 +2959,30 @@ EXPORT_SYMBOL(udp_prot); /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS -static struct udp_table *udp_get_table_afinfo(struct udp_seq_afinfo *afinfo, - struct net *net) +static unsigned short seq_file_family(const struct seq_file *seq); +static bool seq_sk_match(struct seq_file *seq, const struct sock *sk) { + unsigned short family = seq_file_family(seq); + + /* AF_UNSPEC is used as a match all */ + return ((family == AF_UNSPEC || family == sk->sk_family) && + net_eq(sock_net(sk), seq_file_net(seq))); +} + +#ifdef CONFIG_BPF_SYSCALL +static const struct seq_operations bpf_iter_udp_seq_ops; +#endif +static struct udp_table *udp_get_table_seq(struct seq_file *seq, + struct net *net) +{ + const struct udp_seq_afinfo *afinfo; + +#ifdef CONFIG_BPF_SYSCALL + if (seq->op == &bpf_iter_udp_seq_ops) + return net->ipv4.udp_table; +#endif + + afinfo = pde_data(file_inode(seq->file)); return afinfo->udp_table ? : net->ipv4.udp_table; } @@ -2998,16 +2990,10 @@ static struct sock *udp_get_first(struct seq_file *seq, int start) { struct udp_iter_state *state = seq->private; struct net *net = seq_file_net(seq); - struct udp_seq_afinfo *afinfo; struct udp_table *udptable; struct sock *sk; - if (state->bpf_seq_afinfo) - afinfo = state->bpf_seq_afinfo; - else - afinfo = pde_data(file_inode(seq->file)); - - udptable = udp_get_table_afinfo(afinfo, net); + udptable = udp_get_table_seq(seq, net); for (state->bucket = start; state->bucket <= udptable->mask; ++state->bucket) { @@ -3018,10 +3004,7 @@ static struct sock *udp_get_first(struct seq_file *seq, int start) spin_lock_bh(&hslot->lock); sk_for_each(sk, &hslot->head) { - if (!net_eq(sock_net(sk), net)) - continue; - if (afinfo->family == AF_UNSPEC || - sk->sk_family == afinfo->family) + if (seq_sk_match(seq, sk)) goto found; } spin_unlock_bh(&hslot->lock); @@ -3035,22 +3018,14 @@ static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk) { struct udp_iter_state *state = seq->private; struct net *net = seq_file_net(seq); - struct udp_seq_afinfo *afinfo; struct udp_table *udptable; - if (state->bpf_seq_afinfo) - afinfo = state->bpf_seq_afinfo; - else - afinfo = pde_data(file_inode(seq->file)); - do { sk = sk_next(sk); - } while (sk && (!net_eq(sock_net(sk), net) || - (afinfo->family != AF_UNSPEC && - sk->sk_family != afinfo->family))); + } while (sk && !seq_sk_match(seq, sk)); if (!sk) { - udptable = udp_get_table_afinfo(afinfo, net); + udptable = udp_get_table_seq(seq, net); if (state->bucket <= udptable->mask) spin_unlock_bh(&udptable->hash[state->bucket].lock); @@ -3096,15 +3071,9 @@ EXPORT_SYMBOL(udp_seq_next); void udp_seq_stop(struct seq_file *seq, void *v) { struct udp_iter_state *state = seq->private; - struct udp_seq_afinfo *afinfo; struct udp_table *udptable; - if (state->bpf_seq_afinfo) - afinfo = state->bpf_seq_afinfo; - else - afinfo = pde_data(file_inode(seq->file)); - - udptable = udp_get_table_afinfo(afinfo, seq_file_net(seq)); + udptable = udp_get_table_seq(seq, seq_file_net(seq)); if (state->bucket <= udptable->mask) spin_unlock_bh(&udptable->hash[state->bucket].lock); @@ -3157,6 +3126,143 @@ struct bpf_iter__udp { int bucket __aligned(8); }; +struct bpf_udp_iter_state { + struct udp_iter_state state; + unsigned int cur_sk; + unsigned int end_sk; + unsigned int max_sk; + int offset; + struct sock **batch; + bool st_bucket_done; +}; + +static int bpf_iter_udp_realloc_batch(struct bpf_udp_iter_state *iter, + unsigned int new_batch_sz); +static struct sock *bpf_iter_udp_batch(struct seq_file *seq) +{ + struct bpf_udp_iter_state *iter = seq->private; + struct udp_iter_state *state = &iter->state; + struct net *net = seq_file_net(seq); + struct udp_table *udptable; + unsigned int batch_sks = 0; + bool resized = false; + struct sock *sk; + + /* The current batch is done, so advance the bucket. */ + if (iter->st_bucket_done) { + state->bucket++; + iter->offset = 0; + } + + udptable = udp_get_table_seq(seq, net); + +again: + /* New batch for the next bucket. + * Iterate over the hash table to find a bucket with sockets matching + * the iterator attributes, and return the first matching socket from + * the bucket. The remaining matched sockets from the bucket are batched + * before releasing the bucket lock. This allows BPF programs that are + * called in seq_show to acquire the bucket lock if needed. + */ + iter->cur_sk = 0; + iter->end_sk = 0; + iter->st_bucket_done = false; + batch_sks = 0; + + for (; state->bucket <= udptable->mask; state->bucket++) { + struct udp_hslot *hslot2 = &udptable->hash2[state->bucket]; + + if (hlist_empty(&hslot2->head)) { + iter->offset = 0; + continue; + } + + spin_lock_bh(&hslot2->lock); + udp_portaddr_for_each_entry(sk, &hslot2->head) { + if (seq_sk_match(seq, sk)) { + /* Resume from the last iterated socket at the + * offset in the bucket before iterator was stopped. + */ + if (iter->offset) { + --iter->offset; + continue; + } + if (iter->end_sk < iter->max_sk) { + sock_hold(sk); + iter->batch[iter->end_sk++] = sk; + } + batch_sks++; + } + } + spin_unlock_bh(&hslot2->lock); + + if (iter->end_sk) + break; + + /* Reset the current bucket's offset before moving to the next bucket. */ + iter->offset = 0; + } + + /* All done: no batch made. */ + if (!iter->end_sk) + return NULL; + + if (iter->end_sk == batch_sks) { + /* Batching is done for the current bucket; return the first + * socket to be iterated from the batch. + */ + iter->st_bucket_done = true; + goto done; + } + if (!resized && !bpf_iter_udp_realloc_batch(iter, batch_sks * 3 / 2)) { + resized = true; + /* After allocating a larger batch, retry one more time to grab + * the whole bucket. + */ + state->bucket--; + goto again; + } +done: + return iter->batch[0]; +} + +static void *bpf_iter_udp_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct bpf_udp_iter_state *iter = seq->private; + struct sock *sk; + + /* Whenever seq_next() is called, the iter->cur_sk is + * done with seq_show(), so unref the iter->cur_sk. + */ + if (iter->cur_sk < iter->end_sk) { + sock_put(iter->batch[iter->cur_sk++]); + ++iter->offset; + } + + /* After updating iter->cur_sk, check if there are more sockets + * available in the current bucket batch. + */ + if (iter->cur_sk < iter->end_sk) + sk = iter->batch[iter->cur_sk]; + else + /* Prepare a new batch. */ + sk = bpf_iter_udp_batch(seq); + + ++*pos; + return sk; +} + +static void *bpf_iter_udp_seq_start(struct seq_file *seq, loff_t *pos) +{ + /* bpf iter does not support lseek, so it always + * continue from where it was stop()-ped. + */ + if (*pos) + return bpf_iter_udp_batch(seq); + + return SEQ_START_TOKEN; +} + static int udp_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, struct udp_sock *udp_sk, uid_t uid, int bucket) { @@ -3177,18 +3283,37 @@ static int bpf_iter_udp_seq_show(struct seq_file *seq, void *v) struct bpf_prog *prog; struct sock *sk = v; uid_t uid; + int ret; if (v == SEQ_START_TOKEN) return 0; + lock_sock(sk); + + if (unlikely(sk_unhashed(sk))) { + ret = SEQ_SKIP; + goto unlock; + } + uid = from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk)); meta.seq = seq; prog = bpf_iter_get_info(&meta, false); - return udp_prog_seq_show(prog, &meta, v, uid, state->bucket); + ret = udp_prog_seq_show(prog, &meta, v, uid, state->bucket); + +unlock: + release_sock(sk); + return ret; +} + +static void bpf_iter_udp_put_batch(struct bpf_udp_iter_state *iter) +{ + while (iter->cur_sk < iter->end_sk) + sock_put(iter->batch[iter->cur_sk++]); } static void bpf_iter_udp_seq_stop(struct seq_file *seq, void *v) { + struct bpf_udp_iter_state *iter = seq->private; struct bpf_iter_meta meta; struct bpf_prog *prog; @@ -3199,17 +3324,35 @@ static void bpf_iter_udp_seq_stop(struct seq_file *seq, void *v) (void)udp_prog_seq_show(prog, &meta, v, 0, 0); } - udp_seq_stop(seq, v); + if (iter->cur_sk < iter->end_sk) { + bpf_iter_udp_put_batch(iter); + iter->st_bucket_done = false; + } } static const struct seq_operations bpf_iter_udp_seq_ops = { - .start = udp_seq_start, - .next = udp_seq_next, + .start = bpf_iter_udp_seq_start, + .next = bpf_iter_udp_seq_next, .stop = bpf_iter_udp_seq_stop, .show = bpf_iter_udp_seq_show, }; #endif +static unsigned short seq_file_family(const struct seq_file *seq) +{ + const struct udp_seq_afinfo *afinfo; + +#ifdef CONFIG_BPF_SYSCALL + /* BPF iterator: bpf programs to filter sockets. */ + if (seq->op == &bpf_iter_udp_seq_ops) + return AF_UNSPEC; +#endif + + /* Proc fs iterator */ + afinfo = pde_data(file_inode(seq->file)); + return afinfo->family; +} + const struct seq_operations udp_seq_ops = { .start = udp_seq_start, .next = udp_seq_next, @@ -3418,38 +3561,55 @@ static struct pernet_operations __net_initdata udp_sysctl_ops = { DEFINE_BPF_ITER_FUNC(udp, struct bpf_iter_meta *meta, struct udp_sock *udp_sk, uid_t uid, int bucket) -static int bpf_iter_init_udp(void *priv_data, struct bpf_iter_aux_info *aux) +static int bpf_iter_udp_realloc_batch(struct bpf_udp_iter_state *iter, + unsigned int new_batch_sz) { - struct udp_iter_state *st = priv_data; - struct udp_seq_afinfo *afinfo; - int ret; + struct sock **new_batch; - afinfo = kmalloc(sizeof(*afinfo), GFP_USER | __GFP_NOWARN); - if (!afinfo) + new_batch = kvmalloc_array(new_batch_sz, sizeof(*new_batch), + GFP_USER | __GFP_NOWARN); + if (!new_batch) return -ENOMEM; - afinfo->family = AF_UNSPEC; - afinfo->udp_table = NULL; - st->bpf_seq_afinfo = afinfo; + bpf_iter_udp_put_batch(iter); + kvfree(iter->batch); + iter->batch = new_batch; + iter->max_sk = new_batch_sz; + + return 0; +} + +#define INIT_BATCH_SZ 16 + +static int bpf_iter_init_udp(void *priv_data, struct bpf_iter_aux_info *aux) +{ + struct bpf_udp_iter_state *iter = priv_data; + int ret; + ret = bpf_iter_init_seq_net(priv_data, aux); if (ret) - kfree(afinfo); + return ret; + + ret = bpf_iter_udp_realloc_batch(iter, INIT_BATCH_SZ); + if (ret) + bpf_iter_fini_seq_net(priv_data); + return ret; } static void bpf_iter_fini_udp(void *priv_data) { - struct udp_iter_state *st = priv_data; + struct bpf_udp_iter_state *iter = priv_data; - kfree(st->bpf_seq_afinfo); bpf_iter_fini_seq_net(priv_data); + kvfree(iter->batch); } static const struct bpf_iter_seq_info udp_seq_info = { .seq_ops = &bpf_iter_udp_seq_ops, .init_seq_private = bpf_iter_init_udp, .fini_seq_private = bpf_iter_fini_udp, - .seq_priv_size = sizeof(struct udp_iter_state), + .seq_priv_size = sizeof(struct bpf_udp_iter_state), }; static struct bpf_iter_reg udp_reg_info = { @@ -3457,7 +3617,7 @@ static struct bpf_iter_reg udp_reg_info = { .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__udp, udp_sk), - PTR_TO_BTF_ID_OR_NULL }, + PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED }, }, .seq_info = &udp_seq_info, }; diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index e0c9cc39b81e..56d94d23b9e0 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -64,6 +64,8 @@ struct proto udplite_prot = { .per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc, .sysctl_mem = sysctl_udp_mem, + .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min), + .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), .obj_size = sizeof(struct udp_sock), .h.udp_table = &udplite_table, }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 3797917237d0..5479da08ef40 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3633,8 +3633,8 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, idev->if_flags |= IF_READY; } - pr_info("ADDRCONF(NETDEV_CHANGE): %s: link becomes ready\n", - dev->name); + pr_debug("ADDRCONF(NETDEV_CHANGE): %s: link becomes ready\n", + dev->name); run_pending = 1; } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 2bbf13216a3d..564942bee067 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -695,6 +695,7 @@ const struct proto_ops inet6_stream_ops = { #ifdef CONFIG_MMU .mmap = tcp_mmap, #endif + .splice_eof = inet_splice_eof, .sendpage = inet_sendpage, .sendmsg_locked = tcp_sendmsg_locked, .sendpage_locked = tcp_sendpage_locked, diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index a8d961d3a477..a543df57801f 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -458,8 +458,6 @@ looped_back: ipv6_hdr(skb)->daddr = *addr; - skb_dst_drop(skb); - ip6_route_input(skb); if (skb_dst(skb)->error) { @@ -569,24 +567,6 @@ looped_back: return -1; } - if (skb_cloned(skb)) { - if (pskb_expand_head(skb, IPV6_RPL_SRH_WORST_SWAP_SIZE, 0, - GFP_ATOMIC)) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_OUTDISCARDS); - kfree_skb(skb); - return -1; - } - } else { - err = skb_cow_head(skb, IPV6_RPL_SRH_WORST_SWAP_SIZE); - if (unlikely(err)) { - kfree_skb(skb); - return -1; - } - } - - hdr = (struct ipv6_rpl_sr_hdr *)skb_transport_header(skb); - if (!pskb_may_pull(skb, ipv6_rpl_srh_size(n, hdr->cmpri, hdr->cmpre))) { kfree_skb(skb); @@ -630,6 +610,17 @@ looped_back: skb_pull(skb, ((hdr->hdrlen + 1) << 3)); skb_postpull_rcsum(skb, oldhdr, sizeof(struct ipv6hdr) + ((hdr->hdrlen + 1) << 3)); + if (unlikely(!hdr->segments_left)) { + if (pskb_expand_head(skb, sizeof(struct ipv6hdr) + ((chdr->hdrlen + 1) << 3), 0, + GFP_ATOMIC)) { + __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); + kfree_skb(skb); + kfree(buf); + return -1; + } + + oldhdr = ipv6_hdr(skb); + } skb_push(skb, ((chdr->hdrlen + 1) << 3) + sizeof(struct ipv6hdr)); skb_reset_network_header(skb); skb_mac_header_rebuild(skb); @@ -834,7 +825,6 @@ looped_back: *addr = ipv6_hdr(skb)->daddr; ipv6_hdr(skb)->daddr = daddr; - skb_dst_drop(skb); ip6_route_input(skb); if (skb_dst(skb)->error) { skb_push(skb, skb->data - skb_network_header(skb)); diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index da46c4284676..49e31e4ae7b7 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -143,6 +143,8 @@ int ipv6_find_tlv(const struct sk_buff *skb, int offset, int type) optlen = 1; break; default: + if (len < 2) + goto bad; optlen = nh[offset + 1] + 2; if (optlen > len) goto bad; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 2438da5ff6da..bac768d36cc1 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -2491,7 +2491,7 @@ static int ipv6_route_native_seq_show(struct seq_file *seq, void *v) const struct net_device *dev; if (rt->nh) - fib6_nh = nexthop_fib6_nh_bh(rt->nh); + fib6_nh = nexthop_fib6_nh(rt->nh); seq_printf(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen); @@ -2556,14 +2556,14 @@ static struct fib6_table *ipv6_route_seq_next_table(struct fib6_table *tbl, if (tbl) { h = (tbl->tb6_id & (FIB6_TABLE_HASHSZ - 1)) + 1; - node = rcu_dereference_bh(hlist_next_rcu(&tbl->tb6_hlist)); + node = rcu_dereference(hlist_next_rcu(&tbl->tb6_hlist)); } else { h = 0; node = NULL; } while (!node && h < FIB6_TABLE_HASHSZ) { - node = rcu_dereference_bh( + node = rcu_dereference( hlist_first_rcu(&net->ipv6.fib_table_hash[h++])); } return hlist_entry_safe(node, struct fib6_table, tb6_hlist); @@ -2593,7 +2593,7 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) if (!v) goto iter_table; - n = rcu_dereference_bh(((struct fib6_info *)v)->fib6_next); + n = rcu_dereference(((struct fib6_info *)v)->fib6_next); if (n) return n; @@ -2619,12 +2619,12 @@ iter_table: } static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(RCU_BH) + __acquires(RCU) { struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; - rcu_read_lock_bh(); + rcu_read_lock(); iter->tbl = ipv6_route_seq_next_table(NULL, net); iter->skip = *pos; @@ -2645,7 +2645,7 @@ static bool ipv6_route_iter_active(struct ipv6_route_iter *iter) } static void ipv6_route_native_seq_stop(struct seq_file *seq, void *v) - __releases(RCU_BH) + __releases(RCU) { struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; @@ -2653,7 +2653,7 @@ static void ipv6_route_native_seq_stop(struct seq_file *seq, void *v) if (ipv6_route_iter_active(iter)) fib6_walker_unlink(net, &iter->w); - rcu_read_unlock_bh(); + rcu_read_unlock(); } #if IS_BUILTIN(CONFIG_IPV6) && defined(CONFIG_BPF_SYSCALL) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index a4ecfc9d2593..da80974ad23a 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1015,12 +1015,14 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, ntohl(tun_id), ntohl(md->u.index), truncate, false); + proto = htons(ETH_P_ERSPAN); } else if (md->version == 2) { erspan_build_header_v2(skb, ntohl(tun_id), md->u.md2.dir, get_hwid(&md->u.md2), truncate, false); + proto = htons(ETH_P_ERSPAN2); } else { goto tx_err; } @@ -1043,24 +1045,25 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, break; } - if (t->parms.erspan_ver == 1) + if (t->parms.erspan_ver == 1) { erspan_build_header(skb, ntohl(t->parms.o_key), t->parms.index, truncate, false); - else if (t->parms.erspan_ver == 2) + proto = htons(ETH_P_ERSPAN); + } else if (t->parms.erspan_ver == 2) { erspan_build_header_v2(skb, ntohl(t->parms.o_key), t->parms.dir, t->parms.hwid, truncate, false); - else + proto = htons(ETH_P_ERSPAN2); + } else { goto tx_err; + } fl6.daddr = t->parms.raddr; } /* Push GRE header. */ - proto = (t->parms.erspan_ver == 1) ? htons(ETH_P_ERSPAN) - : htons(ETH_P_ERSPAN2); gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(atomic_fetch_inc(&t->o_seqno))); /* TooBig packet may have updated dst->dev's mtu */ diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 9554cf46ed88..c722cb881b2d 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1589,6 +1589,14 @@ emsgsize: skb_zcopy_set(skb, uarg, &extra_uref); } } + } else if ((flags & MSG_SPLICE_PAGES) && length) { + if (inet_sk(sk)->hdrincl) + return -EPERM; + if (rt->dst.dev->features & NETIF_F_SG) + /* We need an empty buffer to attach stuff to */ + paged = true; + else + flags &= ~MSG_SPLICE_PAGES; } /* @@ -1778,6 +1786,15 @@ alloc_new_skb: err = -EFAULT; goto error; } + } else if (flags & MSG_SPLICE_PAGES) { + struct msghdr *msg = from; + + err = skb_splice_from_iter(skb, &msg->msg_iter, copy, + sk->sk_allocation); + if (err < 0) + goto error; + copy = err; + wmem_alloc_delta += copy; } else if (!zc) { int i = skb_shinfo(skb)->nr_frags; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index dc8a2854e7f3..d13240f13607 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -42,7 +42,7 @@ static struct nft_ct_frag6_pernet *nf_frag_pernet(struct net *net) } #ifdef CONFIG_SYSCTL -static unsigned long nf_conntrack_frag6_low_thresh_unused = IPV6_FRAG_LOW_THRESH; + static struct ctl_table nf_ct_frag6_sysctl_table[] = { { .procname = "nf_conntrack_frag6_timeout", @@ -82,10 +82,10 @@ static int nf_ct_frag6_sysctl_register(struct net *net) nf_frag = nf_frag_pernet(net); table[0].data = &nf_frag->fqdir->timeout; - table[1].data = &nf_conntrack_frag6_low_thresh_unused; - table[1].extra2 = &nf_frag->fqdir->high_thresh; + table[1].data = &nf_frag->fqdir->low_thresh; + table[1].extra2 = &nf_frag->fqdir->high_thresh; table[2].data = &nf_frag->fqdir->high_thresh; - table[2].extra1 = &nf_conntrack_frag6_low_thresh_unused; + table[2].extra1 = &nf_frag->fqdir->low_thresh; hdr = register_net_sysctl(net, "net/netfilter", table); if (hdr == NULL) @@ -500,6 +500,7 @@ static int nf_ct_net_init(struct net *net) return res; nf_frag->fqdir->high_thresh = IPV6_FRAG_HIGH_THRESH; + nf_frag->fqdir->low_thresh = IPV6_FRAG_LOW_THRESH; nf_frag->fqdir->timeout = IPV6_FRAG_TIMEOUT; res = nf_ct_frag6_sysctl_register(net); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 7d0adb612bdd..44ee7a2e72ac 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -793,7 +793,8 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (!proto) proto = inet->inet_num; - else if (proto != inet->inet_num) + else if (proto != inet->inet_num && + inet->inet_num != IPPROTO_RAW) return -EINVAL; if (proto > 255) diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index eb8373c25675..5bc8a28e67f9 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -416,7 +416,7 @@ static const struct inet6_protocol frag_protocol = { }; #ifdef CONFIG_SYSCTL -static unsigned long ip6_frags_low_thresh_unused = IPV6_FRAG_LOW_THRESH; + static struct ctl_table ip6_frags_ns_ctl_table[] = { { .procname = "ip6frag_high_thresh", @@ -465,9 +465,9 @@ static int __net_init ip6_frags_ns_sysctl_register(struct net *net) } table[0].data = &net->ipv6.fqdir->high_thresh; - table[0].extra1 = &ip6_frags_low_thresh_unused; - table[1].data = &ip6_frags_low_thresh_unused; - table[1].extra2 = &net->ipv6.fqdir->high_thresh; + table[0].extra1 = &net->ipv6.fqdir->low_thresh; + table[1].data = &net->ipv6.fqdir->low_thresh; + table[1].extra2 = &net->ipv6.fqdir->high_thresh; table[2].data = &net->ipv6.fqdir->timeout; hdr = register_net_sysctl(net, "net/ipv6", table); @@ -536,6 +536,7 @@ static int __net_init ipv6_frags_init_net(struct net *net) return res; net->ipv6.fqdir->high_thresh = IPV6_FRAG_HIGH_THRESH; + net->ipv6.fqdir->low_thresh = IPV6_FRAG_LOW_THRESH; net->ipv6.fqdir->timeout = IPV6_FRAG_TIMEOUT; res = ip6_frags_ns_sysctl_register(net); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index e3aec46bd466..392aaa373b66 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -6412,9 +6412,9 @@ static struct ctl_table ipv6_route_table_template[] = { { .procname = "skip_notify_on_dev_down", .data = &init_net.ipv6.sysctl.skip_notify_on_dev_down, - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 34db881204d2..03b877ff4558 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -470,8 +470,6 @@ static int seg6_input_core(struct net *net, struct sock *sk, dst = dst_cache_get(&slwt->cache); preempt_enable(); - skb_dst_drop(skb); - if (!dst) { ip6_route_input(skb); dst = skb_dst(skb); @@ -482,6 +480,7 @@ static int seg6_input_core(struct net *net, struct sock *sk, preempt_enable(); } } else { + skb_dst_drop(skb); skb_dst_set(skb, dst); } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 7132eb213a7a..c17c8ff94b79 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -93,12 +93,8 @@ static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(const struct sock *sk, * This avoids a dereference and allow compiler optimizations. * It is a specialized version of inet6_sk_generic(). */ -static struct ipv6_pinfo *tcp_inet6_sk(const struct sock *sk) -{ - unsigned int offset = sizeof(struct tcp6_sock) - sizeof(struct ipv6_pinfo); - - return (struct ipv6_pinfo *)(((u8 *)sk) + offset); -} +#define tcp_inet6_sk(sk) (&container_of_const(tcp_sk(sk), \ + struct tcp6_sock, tcp)->inet6) static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) { @@ -533,7 +529,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, struct sk_buff *syn_skb) { struct inet_request_sock *ireq = inet_rsk(req); - struct ipv6_pinfo *np = tcp_inet6_sk(sk); + const struct ipv6_pinfo *np = tcp_inet6_sk(sk); struct ipv6_txoptions *opt; struct flowi6 *fl6 = &fl->u.ip6; struct sk_buff *skb; @@ -2154,6 +2150,7 @@ struct proto tcpv6_prot = { .keepalive = tcp_set_keepalive, .recvmsg = tcp_recvmsg, .sendmsg = tcp_sendmsg, + .splice_eof = tcp_splice_eof, .sendpage = tcp_sendpage, .backlog_rcv = tcp_v6_do_rcv, .release_cb = tcp_release_cb, diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index 39db5a226855..bf0c957e4b5e 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -36,7 +36,8 @@ INDIRECT_CALLABLE_SCOPE int tcp6_gro_complete(struct sk_buff *skb, int thoff) &iph->daddr, 0); skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6; - return tcp_gro_complete(skb); + tcp_gro_complete(skb); + return 0; } static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index e5a337e6b970..317b01c9bc39 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1653,6 +1653,20 @@ do_confirm: } EXPORT_SYMBOL(udpv6_sendmsg); +static void udpv6_splice_eof(struct socket *sock) +{ + struct sock *sk = sock->sk; + struct udp_sock *up = udp_sk(sk); + + if (!up->pending || READ_ONCE(up->corkflag)) + return; + + lock_sock(sk); + if (up->pending && !READ_ONCE(up->corkflag)) + udp_v6_push_pending_frames(sk); + release_sock(sk); +} + void udpv6_destroy_sock(struct sock *sk) { struct udp_sock *up = udp_sk(sk); @@ -1764,6 +1778,7 @@ struct proto udpv6_prot = { .getsockopt = udpv6_getsockopt, .sendmsg = udpv6_sendmsg, .recvmsg = udpv6_recvmsg, + .splice_eof = udpv6_splice_eof, .release_cb = ip6_datagram_release_cb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index 67eaf3ca14ce..3bab0cc13697 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -60,6 +60,8 @@ struct proto udplitev6_prot = { .per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc, .sysctl_mem = sysctl_udp_mem, + .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min), + .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), .obj_size = sizeof(struct udp6_sock), .h.udp_table = &udplite_table, }; diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index cfe828bd7fc6..7dee74430b59 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -761,149 +761,6 @@ static void kcm_push(struct kcm_sock *kcm) kcm_write_msgs(kcm); } -static ssize_t kcm_sendpage(struct socket *sock, struct page *page, - int offset, size_t size, int flags) - -{ - struct sock *sk = sock->sk; - struct kcm_sock *kcm = kcm_sk(sk); - struct sk_buff *skb = NULL, *head = NULL; - long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); - bool eor; - int err = 0; - int i; - - if (flags & MSG_SENDPAGE_NOTLAST) - flags |= MSG_MORE; - - /* No MSG_EOR from splice, only look at MSG_MORE */ - eor = !(flags & MSG_MORE); - - lock_sock(sk); - - sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); - - err = -EPIPE; - if (sk->sk_err) - goto out_error; - - if (kcm->seq_skb) { - /* Previously opened message */ - head = kcm->seq_skb; - skb = kcm_tx_msg(head)->last_skb; - i = skb_shinfo(skb)->nr_frags; - - if (skb_can_coalesce(skb, i, page, offset)) { - skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], size); - skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG; - goto coalesced; - } - - if (i >= MAX_SKB_FRAGS) { - struct sk_buff *tskb; - - tskb = alloc_skb(0, sk->sk_allocation); - while (!tskb) { - kcm_push(kcm); - err = sk_stream_wait_memory(sk, &timeo); - if (err) - goto out_error; - } - - if (head == skb) - skb_shinfo(head)->frag_list = tskb; - else - skb->next = tskb; - - skb = tskb; - skb->ip_summed = CHECKSUM_UNNECESSARY; - i = 0; - } - } else { - /* Call the sk_stream functions to manage the sndbuf mem. */ - if (!sk_stream_memory_free(sk)) { - kcm_push(kcm); - set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); - err = sk_stream_wait_memory(sk, &timeo); - if (err) - goto out_error; - } - - head = alloc_skb(0, sk->sk_allocation); - while (!head) { - kcm_push(kcm); - err = sk_stream_wait_memory(sk, &timeo); - if (err) - goto out_error; - } - - skb = head; - i = 0; - } - - get_page(page); - skb_fill_page_desc_noacc(skb, i, page, offset, size); - skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG; - -coalesced: - skb->len += size; - skb->data_len += size; - skb->truesize += size; - sk->sk_wmem_queued += size; - sk_mem_charge(sk, size); - - if (head != skb) { - head->len += size; - head->data_len += size; - head->truesize += size; - } - - if (eor) { - bool not_busy = skb_queue_empty(&sk->sk_write_queue); - - /* Message complete, queue it on send buffer */ - __skb_queue_tail(&sk->sk_write_queue, head); - kcm->seq_skb = NULL; - KCM_STATS_INCR(kcm->stats.tx_msgs); - - if (flags & MSG_BATCH) { - kcm->tx_wait_more = true; - } else if (kcm->tx_wait_more || not_busy) { - err = kcm_write_msgs(kcm); - if (err < 0) { - /* We got a hard error in write_msgs but have - * already queued this message. Report an error - * in the socket, but don't affect return value - * from sendmsg - */ - pr_warn("KCM: Hard failure on kcm_write_msgs\n"); - report_csk_error(&kcm->sk, -err); - } - } - } else { - /* Message not complete, save state */ - kcm->seq_skb = head; - kcm_tx_msg(head)->last_skb = skb; - } - - KCM_STATS_ADD(kcm->stats.tx_bytes, size); - - release_sock(sk); - return size; - -out_error: - kcm_push(kcm); - - err = sk_stream_error(sk, flags, err); - - /* make sure we wake any epoll edge trigger waiter */ - if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && err == -EAGAIN)) - sk->sk_write_space(sk); - - release_sock(sk); - return err; -} - static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; @@ -989,29 +846,52 @@ start: merge = false; } - copy = min_t(int, msg_data_left(msg), - pfrag->size - pfrag->offset); + if (msg->msg_flags & MSG_SPLICE_PAGES) { + copy = msg_data_left(msg); + if (!sk_wmem_schedule(sk, copy)) + goto wait_for_memory; - if (!sk_wmem_schedule(sk, copy)) - goto wait_for_memory; + err = skb_splice_from_iter(skb, &msg->msg_iter, copy, + sk->sk_allocation); + if (err < 0) { + if (err == -EMSGSIZE) + goto wait_for_memory; + goto out_error; + } - err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb, - pfrag->page, - pfrag->offset, - copy); - if (err) - goto out_error; + copy = err; + skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG; + sk_wmem_queued_add(sk, copy); + sk_mem_charge(sk, copy); - /* Update the skb. */ - if (merge) { - skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); + if (head != skb) + head->truesize += copy; } else { - skb_fill_page_desc(skb, i, pfrag->page, - pfrag->offset, copy); - get_page(pfrag->page); + copy = min_t(int, msg_data_left(msg), + pfrag->size - pfrag->offset); + if (!sk_wmem_schedule(sk, copy)) + goto wait_for_memory; + + err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb, + pfrag->page, + pfrag->offset, + copy); + if (err) + goto out_error; + + /* Update the skb. */ + if (merge) { + skb_frag_size_add( + &skb_shinfo(skb)->frags[i - 1], copy); + } else { + skb_fill_page_desc(skb, i, pfrag->page, + pfrag->offset, copy); + get_page(pfrag->page); + } + + pfrag->offset += copy; } - pfrag->offset += copy; copied += copy; if (head != skb) { head->len += copy; @@ -1088,6 +968,37 @@ out_error: return err; } +static void kcm_splice_eof(struct socket *sock) +{ + struct sock *sk = sock->sk; + struct kcm_sock *kcm = kcm_sk(sk); + + if (skb_queue_empty_lockless(&sk->sk_write_queue)) + return; + + lock_sock(sk); + kcm_write_msgs(kcm); + release_sock(sk); +} + +static ssize_t kcm_sendpage(struct socket *sock, struct page *page, + int offset, size_t size, int flags) + +{ + struct bio_vec bvec; + struct msghdr msg = { .msg_flags = flags | MSG_SPLICE_PAGES, }; + + if (flags & MSG_SENDPAGE_NOTLAST) + msg.msg_flags |= MSG_MORE; + + if (flags & MSG_OOB) + return -EOPNOTSUPP; + + bvec_set_page(&bvec, page, size, offset); + iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); + return kcm_sendmsg(sock, &msg, size); +} + static int kcm_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { @@ -1875,6 +1786,7 @@ static const struct proto_ops kcm_dgram_ops = { .sendmsg = kcm_sendmsg, .recvmsg = kcm_recvmsg, .mmap = sock_no_mmap, + .splice_eof = kcm_splice_eof, .sendpage = kcm_sendpage, }; @@ -1896,6 +1808,7 @@ static const struct proto_ops kcm_seqpacket_ops = { .sendmsg = kcm_sendmsg, .recvmsg = kcm_recvmsg, .mmap = sock_no_mmap, + .splice_eof = kcm_splice_eof, .sendpage = kcm_sendpage, .splice_read = kcm_splice_read, }; diff --git a/net/key/af_key.c b/net/key/af_key.c index a815f5ab4c49..31ab12fd720a 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1940,7 +1940,8 @@ static u32 gen_reqid(struct net *net) } static int -parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_ipsecrequest *rq) +parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_policy *pol, + struct sadb_x_ipsecrequest *rq) { struct net *net = xp_net(xp); struct xfrm_tmpl *t = xp->xfrm_vec + xp->xfrm_nr; @@ -1958,9 +1959,12 @@ parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_ipsecrequest *rq) if ((mode = pfkey_mode_to_xfrm(rq->sadb_x_ipsecrequest_mode)) < 0) return -EINVAL; t->mode = mode; - if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_USE) + if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_USE) { + if ((mode == XFRM_MODE_TUNNEL || mode == XFRM_MODE_BEET) && + pol->sadb_x_policy_dir == IPSEC_DIR_OUTBOUND) + return -EINVAL; t->optional = 1; - else if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_UNIQUE) { + } else if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_UNIQUE) { t->reqid = rq->sadb_x_ipsecrequest_reqid; if (t->reqid > IPSEC_MANUAL_REQID_MAX) t->reqid = 0; @@ -2002,7 +2006,7 @@ parse_ipsecrequests(struct xfrm_policy *xp, struct sadb_x_policy *pol) rq->sadb_x_ipsecrequest_len < sizeof(*rq)) return -EINVAL; - if ((err = parse_ipsecrequest(xp, rq)) < 0) + if ((err = parse_ipsecrequest(xp, pol, rq)) < 0) return err; len -= rq->sadb_x_ipsecrequest_len; rq = (void*)((u8*)rq + rq->sadb_x_ipsecrequest_len); diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index 0dac2863c6e1..a0990c365a2e 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -34,7 +34,11 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("NoDSSInWindow", MPTCP_MIB_NODSSWINDOW), SNMP_MIB_ITEM("DuplicateData", MPTCP_MIB_DUPDATA), SNMP_MIB_ITEM("AddAddr", MPTCP_MIB_ADDADDR), + SNMP_MIB_ITEM("AddAddrTx", MPTCP_MIB_ADDADDRTX), + SNMP_MIB_ITEM("AddAddrTxDrop", MPTCP_MIB_ADDADDRTXDROP), SNMP_MIB_ITEM("EchoAdd", MPTCP_MIB_ECHOADD), + SNMP_MIB_ITEM("EchoAddTx", MPTCP_MIB_ECHOADDTX), + SNMP_MIB_ITEM("EchoAddTxDrop", MPTCP_MIB_ECHOADDTXDROP), SNMP_MIB_ITEM("PortAdd", MPTCP_MIB_PORTADD), SNMP_MIB_ITEM("AddAddrDrop", MPTCP_MIB_ADDADDRDROP), SNMP_MIB_ITEM("MPJoinPortSynRx", MPTCP_MIB_JOINPORTSYNRX), @@ -44,6 +48,8 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("MismatchPortAckRx", MPTCP_MIB_MISMATCHPORTACKRX), SNMP_MIB_ITEM("RmAddr", MPTCP_MIB_RMADDR), SNMP_MIB_ITEM("RmAddrDrop", MPTCP_MIB_RMADDRDROP), + SNMP_MIB_ITEM("RmAddrTx", MPTCP_MIB_RMADDRTX), + SNMP_MIB_ITEM("RmAddrTxDrop", MPTCP_MIB_RMADDRTXDROP), SNMP_MIB_ITEM("RmSubflow", MPTCP_MIB_RMSUBFLOW), SNMP_MIB_ITEM("MPPrioTx", MPTCP_MIB_MPPRIOTX), SNMP_MIB_ITEM("MPPrioRx", MPTCP_MIB_MPPRIORX), diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index 2be3596374f4..cae71d947252 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -27,7 +27,15 @@ enum linux_mptcp_mib_field { MPTCP_MIB_NODSSWINDOW, /* Segments not in MPTCP windows */ MPTCP_MIB_DUPDATA, /* Segments discarded due to duplicate DSS */ MPTCP_MIB_ADDADDR, /* Received ADD_ADDR with echo-flag=0 */ + MPTCP_MIB_ADDADDRTX, /* Sent ADD_ADDR with echo-flag=0 */ + MPTCP_MIB_ADDADDRTXDROP, /* ADD_ADDR with echo-flag=0 not send due to + * resource exhaustion + */ MPTCP_MIB_ECHOADD, /* Received ADD_ADDR with echo-flag=1 */ + MPTCP_MIB_ECHOADDTX, /* Send ADD_ADDR with echo-flag=1 */ + MPTCP_MIB_ECHOADDTXDROP, /* ADD_ADDR with echo-flag=1 not send due + * to resource exhaustion + */ MPTCP_MIB_PORTADD, /* Received ADD_ADDR with a port-number */ MPTCP_MIB_ADDADDRDROP, /* Dropped incoming ADD_ADDR */ MPTCP_MIB_JOINPORTSYNRX, /* Received a SYN MP_JOIN with a different port-number */ @@ -37,6 +45,8 @@ enum linux_mptcp_mib_field { MPTCP_MIB_MISMATCHPORTACKRX, /* Received an ACK MP_JOIN with a mismatched port-number */ MPTCP_MIB_RMADDR, /* Received RM_ADDR */ MPTCP_MIB_RMADDRDROP, /* Dropped incoming RM_ADDR */ + MPTCP_MIB_RMADDRTX, /* Sent RM_ADDR */ + MPTCP_MIB_RMADDRTXDROP, /* RM_ADDR not sent due to resource exhaustion */ MPTCP_MIB_RMSUBFLOW, /* Remove a subflow */ MPTCP_MIB_MPPRIOTX, /* Transmit a MP_PRIO */ MPTCP_MIB_MPPRIORX, /* Received a MP_PRIO */ @@ -63,6 +73,14 @@ struct mptcp_mib { unsigned long mibs[LINUX_MIB_MPTCP_MAX]; }; +static inline void MPTCP_ADD_STATS(struct net *net, + enum linux_mptcp_mib_field field, + int val) +{ + if (likely(net->mib.mptcp_statistics)) + SNMP_ADD_STATS(net->mib.mptcp_statistics, field, val); +} + static inline void MPTCP_INC_STATS(struct net *net, enum linux_mptcp_mib_field field) { diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 19a01b6566f1..8a8083207be4 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -687,9 +687,12 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * } opts->suboptions |= OPTION_MPTCP_ADD_ADDR; if (!echo) { + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDRTX); opts->ahmac = add_addr_generate_hmac(msk->local_key, msk->remote_key, &opts->addr); + } else { + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADDTX); } pr_debug("addr_id=%d, ahmac=%llu, echo=%d, port=%d", opts->addr.id, opts->ahmac, echo, ntohs(opts->addr.port)); @@ -723,7 +726,7 @@ static bool mptcp_established_options_rm_addr(struct sock *sk, for (i = 0; i < opts->rm_list.nr; i++) pr_debug("rm_list_ids[%d]=%d", i, opts->rm_list.ids[i]); - + MPTCP_ADD_STATS(sock_net(sk), MPTCP_MIB_RMADDRTX, opts->rm_list.nr); return true; } diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 78c924506e83..92d540e527a2 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -26,7 +26,8 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk, if (add_addr & (echo ? BIT(MPTCP_ADD_ADDR_ECHO) : BIT(MPTCP_ADD_ADDR_SIGNAL))) { - pr_warn("addr_signal error, add_addr=%d, echo=%d", add_addr, echo); + MPTCP_INC_STATS(sock_net((struct sock *)msk), + echo ? MPTCP_MIB_ECHOADDTXDROP : MPTCP_MIB_ADDADDRTXDROP); return -EINVAL; } @@ -48,7 +49,8 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_ pr_debug("msk=%p, rm_list_nr=%d", msk, rm_list->nr); if (rm_addr) { - pr_warn("addr_signal error, rm_addr=%d", rm_addr); + MPTCP_ADD_STATS(sock_net((struct sock *)msk), + MPTCP_MIB_RMADDRTXDROP, rm_list->nr); return -EINVAL; } @@ -87,8 +89,15 @@ bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk) unsigned int subflows_max; int ret = 0; - if (mptcp_pm_is_userspace(msk)) - return mptcp_userspace_pm_active(msk); + if (mptcp_pm_is_userspace(msk)) { + if (mptcp_userspace_pm_active(msk)) { + spin_lock_bh(&pm->lock); + pm->subflows++; + spin_unlock_bh(&pm->lock); + return true; + } + return false; + } subflows_max = mptcp_pm_get_subflows_max(msk); @@ -181,8 +190,16 @@ void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct sock *ssk, struct mptcp_pm_data *pm = &msk->pm; bool update_subflows; - update_subflows = (subflow->request_join || subflow->mp_join) && - mptcp_pm_is_kernel(msk); + update_subflows = subflow->request_join || subflow->mp_join; + if (mptcp_pm_is_userspace(msk)) { + if (update_subflows) { + spin_lock_bh(&pm->lock); + pm->subflows--; + spin_unlock_bh(&pm->lock); + } + return; + } + if (!READ_ONCE(pm->work_pending) && !update_subflows) return; diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index bc343dab5e3f..59f8f3124855 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1558,6 +1558,24 @@ static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info) return ret; } +void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list) +{ + struct mptcp_rm_list alist = { .nr = 0 }; + struct mptcp_pm_addr_entry *entry; + + list_for_each_entry(entry, rm_list, list) { + remove_anno_list_by_saddr(msk, &entry->addr); + if (alist.nr < MPTCP_RM_IDS_MAX) + alist.ids[alist.nr++] = entry->addr.id; + } + + if (alist.nr) { + spin_lock_bh(&msk->pm.lock); + mptcp_pm_remove_addr(msk, &alist); + spin_unlock_bh(&msk->pm.lock); + } +} + void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, struct list_head *rm_list) { diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 27a275805c06..b06aa58dfcf2 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -69,6 +69,7 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, MPTCP_PM_MAX_ADDR_ID + 1, 1); list_add_tail_rcu(&e->list, &msk->pm.userspace_pm_local_addr_list); + msk->pm.local_addr_used++; ret = e->addr.id; } else if (match) { ret = entry->addr.id; @@ -79,6 +80,31 @@ append_err: return ret; } +/* If the subflow is closed from the other peer (not via a + * subflow destroy command then), we want to keep the entry + * not to assign the same ID to another address and to be + * able to send RM_ADDR after the removal of the subflow. + */ +static int mptcp_userspace_pm_delete_local_addr(struct mptcp_sock *msk, + struct mptcp_pm_addr_entry *addr) +{ + struct mptcp_pm_addr_entry *entry, *tmp; + + list_for_each_entry_safe(entry, tmp, &msk->pm.userspace_pm_local_addr_list, list) { + if (mptcp_addresses_equal(&entry->addr, &addr->addr, false)) { + /* TODO: a refcount is needed because the entry can + * be used multiple times (e.g. fullmesh mode). + */ + list_del_rcu(&entry->list); + kfree(entry); + msk->pm.local_addr_used--; + return 0; + } + } + + return -EINVAL; +} + int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id, u8 *flags, int *ifindex) @@ -171,6 +197,7 @@ int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info) spin_lock_bh(&msk->pm.lock); if (mptcp_pm_alloc_anno_list(msk, &addr_val)) { + msk->pm.add_addr_signaled++; mptcp_pm_announce_addr(msk, &addr_val.addr, false); mptcp_pm_nl_addr_send_ack(msk); } @@ -232,7 +259,7 @@ int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info) list_move(&match->list, &free_list); - mptcp_pm_remove_addrs_and_subflows(msk, &free_list); + mptcp_pm_remove_addrs(msk, &free_list); release_sock((struct sock *)msk); @@ -251,6 +278,7 @@ int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info) struct nlattr *raddr = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE]; struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; struct nlattr *laddr = info->attrs[MPTCP_PM_ATTR_ADDR]; + struct mptcp_pm_addr_entry local = { 0 }; struct mptcp_addr_info addr_r; struct mptcp_addr_info addr_l; struct mptcp_sock *msk; @@ -302,12 +330,26 @@ int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info) goto create_err; } + local.addr = addr_l; + err = mptcp_userspace_pm_append_new_local_addr(msk, &local); + if (err < 0) { + GENL_SET_ERR_MSG(info, "did not match address and id"); + goto create_err; + } + lock_sock(sk); err = __mptcp_subflow_connect(sk, &addr_l, &addr_r); release_sock(sk); + spin_lock_bh(&msk->pm.lock); + if (err) + mptcp_userspace_pm_delete_local_addr(msk, &local); + else + msk->pm.subflows++; + spin_unlock_bh(&msk->pm.lock); + create_err: sock_put((struct sock *)msk); return err; @@ -420,7 +462,11 @@ int mptcp_nl_cmd_sf_destroy(struct sk_buff *skb, struct genl_info *info) ssk = mptcp_nl_find_ssk(msk, &addr_l, &addr_r); if (ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + struct mptcp_pm_addr_entry entry = { .addr = addr_l }; + spin_lock_bh(&msk->pm.lock); + mptcp_userspace_pm_delete_local_addr(msk, &entry); + spin_unlock_bh(&msk->pm.lock); mptcp_subflow_shutdown(sk, ssk, RCV_SHUTDOWN | SEND_SHUTDOWN); mptcp_close_ssk(sk, ssk, subflow); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RMSUBFLOW); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 08dc53f56bc2..5df5cc0ffedc 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -90,8 +90,8 @@ static int __mptcp_socket_create(struct mptcp_sock *msk) if (err) return err; - msk->first = ssock->sk; - msk->subflow = ssock; + WRITE_ONCE(msk->first, ssock->sk); + WRITE_ONCE(msk->subflow, ssock); subflow = mptcp_subflow_ctx(ssock->sk); list_add(&subflow->node, &msk->conn_list); sock_hold(ssock->sk); @@ -603,7 +603,7 @@ static bool mptcp_check_data_fin(struct sock *sk) WRITE_ONCE(msk->ack_seq, msk->ack_seq + 1); WRITE_ONCE(msk->rcv_data_fin, 0); - sk->sk_shutdown |= RCV_SHUTDOWN; + WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN); smp_mb__before_atomic(); /* SHUTDOWN must be visible first */ switch (sk->sk_state) { @@ -825,6 +825,13 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) mptcp_data_unlock(sk); } +static void mptcp_subflow_joined(struct mptcp_sock *msk, struct sock *ssk) +{ + mptcp_subflow_ctx(ssk)->map_seq = READ_ONCE(msk->ack_seq); + WRITE_ONCE(msk->allow_infinite_fallback, false); + mptcp_event(MPTCP_EVENT_SUB_ESTABLISHED, msk, ssk, GFP_ATOMIC); +} + static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk) { struct sock *sk = (struct sock *)msk; @@ -839,6 +846,7 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk) mptcp_sock_graft(ssk, sk->sk_socket); mptcp_sockopt_sync_locked(msk, ssk); + mptcp_subflow_joined(msk, ssk); return true; } @@ -910,7 +918,7 @@ static void mptcp_check_for_eof(struct mptcp_sock *msk) /* hopefully temporary hack: propagate shutdown status * to msk, when all subflows agree on it */ - sk->sk_shutdown |= RCV_SHUTDOWN; + WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN); smp_mb__before_atomic(); /* SHUTDOWN must be visible first */ sk->sk_data_ready(sk); @@ -1702,7 +1710,6 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, lock_sock(ssk); msg->msg_flags |= MSG_DONTWAIT; - msk->connect_flags = O_NONBLOCK; msk->fastopening = 1; ret = tcp_sendmsg_fastopen(ssk, msg, copied_syn, len, NULL); msk->fastopening = 0; @@ -2283,7 +2290,7 @@ static void mptcp_dispose_initial_subflow(struct mptcp_sock *msk) { if (msk->subflow) { iput(SOCK_INODE(msk->subflow)); - msk->subflow = NULL; + WRITE_ONCE(msk->subflow, NULL); } } @@ -2420,7 +2427,7 @@ out_release: sock_put(ssk); if (ssk == msk->first) - msk->first = NULL; + WRITE_ONCE(msk->first, NULL); out: if (ssk == msk->last_snd) @@ -2527,7 +2534,7 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk) } inet_sk_state_store(sk, TCP_CLOSE); - sk->sk_shutdown = SHUTDOWN_MASK; + WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); smp_mb__before_atomic(); /* SHUTDOWN must be visible first */ set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags); @@ -2721,7 +2728,7 @@ static int __mptcp_init_sock(struct sock *sk) WRITE_ONCE(msk->rmem_released, 0); msk->timer_ival = TCP_RTO_MIN; - msk->first = NULL; + WRITE_ONCE(msk->first, NULL); inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss; WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk))); WRITE_ONCE(msk->allow_infinite_fallback, true); @@ -2959,7 +2966,7 @@ bool __mptcp_close(struct sock *sk, long timeout) bool do_cancel_work = false; int subflows_alive = 0; - sk->sk_shutdown = SHUTDOWN_MASK; + WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) { mptcp_listen_inuse_dec(sk); @@ -3039,7 +3046,7 @@ static void mptcp_close(struct sock *sk, long timeout) sock_put(sk); } -void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk) +static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk) { #if IS_ENABLED(CONFIG_MPTCP_IPV6) const struct ipv6_pinfo *ssk6 = inet6_sk(ssk); @@ -3102,7 +3109,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) mptcp_pm_data_reset(msk); mptcp_ca_reset(sk); - sk->sk_shutdown = 0; + WRITE_ONCE(sk->sk_shutdown, 0); sk_error_report(sk); return 0; } @@ -3116,9 +3123,10 @@ static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk) } #endif -struct sock *mptcp_sk_clone(const struct sock *sk, - const struct mptcp_options_received *mp_opt, - struct request_sock *req) +struct sock *mptcp_sk_clone_init(const struct sock *sk, + const struct mptcp_options_received *mp_opt, + struct sock *ssk, + struct request_sock *req) { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC); @@ -3137,7 +3145,7 @@ struct sock *mptcp_sk_clone(const struct sock *sk, msk = mptcp_sk(nsk); msk->local_key = subflow_req->local_key; msk->token = subflow_req->token; - msk->subflow = NULL; + WRITE_ONCE(msk->subflow, NULL); msk->in_accept_queue = 1; WRITE_ONCE(msk->fully_established, false); if (mp_opt->suboptions & OPTION_MPTCP_CSUMREQD) @@ -3150,10 +3158,30 @@ struct sock *mptcp_sk_clone(const struct sock *sk, msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq; sock_reset_flag(nsk, SOCK_RCU_FREE); - /* will be fully established after successful MPC subflow creation */ - inet_sk_state_store(nsk, TCP_SYN_RECV); - security_inet_csk_clone(nsk, req); + + /* this can't race with mptcp_close(), as the msk is + * not yet exposted to user-space + */ + inet_sk_state_store(nsk, TCP_ESTABLISHED); + + /* The msk maintain a ref to each subflow in the connections list */ + WRITE_ONCE(msk->first, ssk); + list_add(&mptcp_subflow_ctx(ssk)->node, &msk->conn_list); + sock_hold(ssk); + + /* new mpc subflow takes ownership of the newly + * created mptcp socket + */ + mptcp_token_accept(subflow_req, msk); + + /* set msk addresses early to ensure mptcp_pm_get_local_id() + * uses the correct data + */ + mptcp_copy_inaddrs(nsk, ssk); + mptcp_propagate_sndbuf(nsk, ssk); + + mptcp_rcv_space_init(msk, ssk); bh_unlock_sock(nsk); /* note: the newly allocated socket refcount is 2 now */ @@ -3185,7 +3213,7 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, struct socket *listener; struct sock *newsk; - listener = msk->subflow; + listener = READ_ONCE(msk->subflow); if (WARN_ON_ONCE(!listener)) { *err = -EINVAL; return NULL; @@ -3465,14 +3493,16 @@ bool mptcp_finish_join(struct sock *ssk) return false; } - if (!list_empty(&subflow->node)) - goto out; + /* active subflow, already present inside the conn_list */ + if (!list_empty(&subflow->node)) { + mptcp_subflow_joined(msk, ssk); + return true; + } if (!mptcp_pm_allow_new_subflow(msk)) goto err_prohibited; - /* active connections are already on conn_list. - * If we can't acquire msk socket lock here, let the release callback + /* If we can't acquire msk socket lock here, let the release callback * handle it */ mptcp_data_lock(parent); @@ -3495,11 +3525,6 @@ err_prohibited: return false; } - subflow->map_seq = READ_ONCE(msk->ack_seq); - WRITE_ONCE(msk->allow_infinite_fallback, false); - -out: - mptcp_event(MPTCP_EVENT_SUB_ESTABLISHED, msk, ssk, GFP_ATOMIC); return true; } @@ -3617,9 +3642,9 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) * acquired the subflow socket lock, too. */ if (msk->fastopening) - err = __inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags, 1); + err = __inet_stream_connect(ssock, uaddr, addr_len, O_NONBLOCK, 1); else - err = inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags); + err = inet_stream_connect(ssock, uaddr, addr_len, O_NONBLOCK); inet_sk(sk)->defer_connect = inet_sk(ssock->sk)->defer_connect; /* on successful connect, the msk state will be moved to established by @@ -3632,12 +3657,10 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) mptcp_copy_inaddrs(sk, ssock->sk); - /* unblocking connect, mptcp-level inet_stream_connect will error out - * without changing the socket state, update it here. + /* silence EINPROGRESS and let the caller inet_stream_connect + * handle the connection in progress */ - if (err == -EINPROGRESS) - sk->sk_socket->state = ssock->state; - return err; + return 0; } static struct proto mptcp_prot = { @@ -3696,18 +3719,6 @@ unlock: return err; } -static int mptcp_stream_connect(struct socket *sock, struct sockaddr *uaddr, - int addr_len, int flags) -{ - int ret; - - lock_sock(sock->sk); - mptcp_sk(sock->sk)->connect_flags = flags; - ret = __inet_stream_connect(sock, uaddr, addr_len, flags, 0); - release_sock(sock->sk); - return ret; -} - static int mptcp_listen(struct socket *sock, int backlog) { struct mptcp_sock *msk = mptcp_sk(sock->sk); @@ -3747,28 +3758,32 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, { struct mptcp_sock *msk = mptcp_sk(sock->sk); struct socket *ssock; + struct sock *newsk; int err; pr_debug("msk=%p", msk); - /* buggy applications can call accept on socket states other then LISTEN + /* Buggy applications can call accept on socket states other then LISTEN * but no need to allocate the first subflow just to error out. */ - ssock = msk->subflow; + ssock = READ_ONCE(msk->subflow); if (!ssock) return -EINVAL; - err = ssock->ops->accept(sock, newsock, flags, kern); - if (err == 0 && !mptcp_is_tcpsk(newsock->sk)) { - struct mptcp_sock *msk = mptcp_sk(newsock->sk); + newsk = mptcp_accept(sock->sk, flags, &err, kern); + if (!newsk) + return err; + + lock_sock(newsk); + + __inet_accept(sock, newsock, newsk); + if (!mptcp_is_tcpsk(newsock->sk)) { + struct mptcp_sock *msk = mptcp_sk(newsk); struct mptcp_subflow_context *subflow; - struct sock *newsk = newsock->sk; set_bit(SOCK_CUSTOM_SOCKOPT, &newsock->flags); msk->in_accept_queue = 0; - lock_sock(newsk); - /* set ssk->sk_socket of accept()ed flows to mptcp socket. * This is needed so NOSPACE flag can be set from tcp stack. */ @@ -3789,20 +3804,16 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, if (unlikely(list_empty(&msk->conn_list))) inet_sk_state_store(newsk, TCP_CLOSE); } - - release_sock(newsk); } + release_sock(newsk); - return err; + return 0; } static __poll_t mptcp_check_writeable(struct mptcp_sock *msk) { struct sock *sk = (struct sock *)msk; - if (unlikely(sk->sk_shutdown & SEND_SHUTDOWN)) - return EPOLLOUT | EPOLLWRNORM; - if (sk_stream_is_writeable(sk)) return EPOLLOUT | EPOLLWRNORM; @@ -3820,6 +3831,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk; struct mptcp_sock *msk; __poll_t mask = 0; + u8 shutdown; int state; msk = mptcp_sk(sk); @@ -3828,23 +3840,30 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock, state = inet_sk_state_load(sk); pr_debug("msk=%p state=%d flags=%lx", msk, state, msk->flags); if (state == TCP_LISTEN) { - if (WARN_ON_ONCE(!msk->subflow || !msk->subflow->sk)) + struct socket *ssock = READ_ONCE(msk->subflow); + + if (WARN_ON_ONCE(!ssock || !ssock->sk)) return 0; - return inet_csk_listen_poll(msk->subflow->sk); + return inet_csk_listen_poll(ssock->sk); } + shutdown = READ_ONCE(sk->sk_shutdown); + if (shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) + mask |= EPOLLHUP; + if (shutdown & RCV_SHUTDOWN) + mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; + if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) { mask |= mptcp_check_readable(msk); - mask |= mptcp_check_writeable(msk); + if (shutdown & SEND_SHUTDOWN) + mask |= EPOLLOUT | EPOLLWRNORM; + else + mask |= mptcp_check_writeable(msk); } else if (state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) { /* cf tcp_poll() note about TFO */ mask |= EPOLLOUT | EPOLLWRNORM; } - if (sk->sk_shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) - mask |= EPOLLHUP; - if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; /* This barrier is coupled with smp_wmb() in __mptcp_error_report() */ smp_rmb(); @@ -3859,7 +3878,7 @@ static const struct proto_ops mptcp_stream_ops = { .owner = THIS_MODULE, .release = inet_release, .bind = mptcp_bind, - .connect = mptcp_stream_connect, + .connect = inet_stream_connect, .socketpair = sock_no_socketpair, .accept = mptcp_stream_accept, .getname = inet_getname, @@ -3954,7 +3973,7 @@ static const struct proto_ops mptcp_v6_stream_ops = { .owner = THIS_MODULE, .release = inet6_release, .bind = mptcp_bind, - .connect = mptcp_stream_connect, + .connect = inet_stream_connect, .socketpair = sock_no_socketpair, .accept = mptcp_stream_accept, .getname = inet6_getname, diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 2d7b2c80a164..70c957bc56a8 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -297,7 +297,6 @@ struct mptcp_sock { nodelay:1, fastopening:1, in_accept_queue:1; - int connect_flags; struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; @@ -306,7 +305,11 @@ struct mptcp_sock { struct list_head rtx_queue; struct mptcp_data_frag *first_pending; struct list_head join_list; - struct socket *subflow; /* outgoing connect/listener/!mp_capable */ + struct socket *subflow; /* outgoing connect/listener/!mp_capable + * The mptcp ops can safely dereference, using suitable + * ONCE annotation, the subflow outside the socket + * lock as such sock is freed after close(). + */ struct sock *first; struct mptcp_pm_data pm; struct { @@ -613,7 +616,6 @@ int mptcp_is_checksum_enabled(const struct net *net); int mptcp_allow_join_id0(const struct net *net); unsigned int mptcp_stale_loss_cnt(const struct net *net); int mptcp_get_pm_type(const struct net *net); -void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk); void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, const struct mptcp_options_received *mp_opt); bool __mptcp_retransmit_pending_data(struct sock *sk); @@ -683,9 +685,10 @@ void __init mptcp_proto_init(void); int __init mptcp_proto_v6_init(void); #endif -struct sock *mptcp_sk_clone(const struct sock *sk, - const struct mptcp_options_received *mp_opt, - struct request_sock *req); +struct sock *mptcp_sk_clone_init(const struct sock *sk, + const struct mptcp_options_received *mp_opt, + struct sock *ssk, + struct request_sock *req); void mptcp_get_options(const struct sk_buff *skb, struct mptcp_options_received *mp_opt); @@ -829,6 +832,7 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk, bool echo); int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); +void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list); void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, struct list_head *rm_list); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index ba065b66551a..4688daa6b38b 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -815,38 +815,12 @@ create_child: ctx->setsockopt_seq = listener->setsockopt_seq; if (ctx->mp_capable) { - ctx->conn = mptcp_sk_clone(listener->conn, &mp_opt, req); + ctx->conn = mptcp_sk_clone_init(listener->conn, &mp_opt, child, req); if (!ctx->conn) goto fallback; owner = mptcp_sk(ctx->conn); - - /* this can't race with mptcp_close(), as the msk is - * not yet exposted to user-space - */ - inet_sk_state_store(ctx->conn, TCP_ESTABLISHED); - - /* record the newly created socket as the first msk - * subflow, but don't link it yet into conn_list - */ - WRITE_ONCE(owner->first, child); - - /* new mpc subflow takes ownership of the newly - * created mptcp socket - */ - owner->setsockopt_seq = ctx->setsockopt_seq; mptcp_pm_new_connection(owner, child, 1); - mptcp_token_accept(subflow_req, owner); - - /* set msk addresses early to ensure mptcp_pm_get_local_id() - * uses the correct data - */ - mptcp_copy_inaddrs(ctx->conn, child); - mptcp_propagate_sndbuf(ctx->conn, child); - - mptcp_rcv_space_init(owner, child); - list_add(&ctx->node, &owner->conn_list); - sock_hold(child); /* with OoO packets we can reach here without ingress * mpc option diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index 6447a09932f5..069c2659074b 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -611,14 +611,14 @@ static int ncsi_rsp_handler_snfc(struct ncsi_request *nr) return 0; } -/* Response handler for Mellanox command Get Mac Address */ -static int ncsi_rsp_handler_oem_mlx_gma(struct ncsi_request *nr) +/* Response handler for Get Mac Address command */ +static int ncsi_rsp_handler_oem_gma(struct ncsi_request *nr, int mfr_id) { struct ncsi_dev_priv *ndp = nr->ndp; struct net_device *ndev = ndp->ndev.dev; - const struct net_device_ops *ops = ndev->netdev_ops; struct ncsi_rsp_oem_pkt *rsp; struct sockaddr saddr; + u32 mac_addr_off = 0; int ret = 0; /* Get the response header */ @@ -626,11 +626,25 @@ static int ncsi_rsp_handler_oem_mlx_gma(struct ncsi_request *nr) saddr.sa_family = ndev->type; ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE; - memcpy(saddr.sa_data, &rsp->data[MLX_MAC_ADDR_OFFSET], ETH_ALEN); + if (mfr_id == NCSI_OEM_MFR_BCM_ID) + mac_addr_off = BCM_MAC_ADDR_OFFSET; + else if (mfr_id == NCSI_OEM_MFR_MLX_ID) + mac_addr_off = MLX_MAC_ADDR_OFFSET; + else if (mfr_id == NCSI_OEM_MFR_INTEL_ID) + mac_addr_off = INTEL_MAC_ADDR_OFFSET; + + memcpy(saddr.sa_data, &rsp->data[mac_addr_off], ETH_ALEN); + if (mfr_id == NCSI_OEM_MFR_BCM_ID || mfr_id == NCSI_OEM_MFR_INTEL_ID) + eth_addr_inc((u8 *)saddr.sa_data); + if (!is_valid_ether_addr((const u8 *)saddr.sa_data)) + return -ENXIO; + /* Set the flag for GMA command which should only be called once */ ndp->gma_flag = 1; - ret = ops->ndo_set_mac_address(ndev, &saddr); + rtnl_lock(); + ret = dev_set_mac_address(ndev, &saddr, NULL); + rtnl_unlock(); if (ret < 0) netdev_warn(ndev, "NCSI: 'Writing mac address to device failed\n"); @@ -649,41 +663,10 @@ static int ncsi_rsp_handler_oem_mlx(struct ncsi_request *nr) if (mlx->cmd == NCSI_OEM_MLX_CMD_GMA && mlx->param == NCSI_OEM_MLX_CMD_GMA_PARAM) - return ncsi_rsp_handler_oem_mlx_gma(nr); + return ncsi_rsp_handler_oem_gma(nr, NCSI_OEM_MFR_MLX_ID); return 0; } -/* Response handler for Broadcom command Get Mac Address */ -static int ncsi_rsp_handler_oem_bcm_gma(struct ncsi_request *nr) -{ - struct ncsi_dev_priv *ndp = nr->ndp; - struct net_device *ndev = ndp->ndev.dev; - const struct net_device_ops *ops = ndev->netdev_ops; - struct ncsi_rsp_oem_pkt *rsp; - struct sockaddr saddr; - int ret = 0; - - /* Get the response header */ - rsp = (struct ncsi_rsp_oem_pkt *)skb_network_header(nr->rsp); - - saddr.sa_family = ndev->type; - ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE; - memcpy(saddr.sa_data, &rsp->data[BCM_MAC_ADDR_OFFSET], ETH_ALEN); - /* Increase mac address by 1 for BMC's address */ - eth_addr_inc((u8 *)saddr.sa_data); - if (!is_valid_ether_addr((const u8 *)saddr.sa_data)) - return -ENXIO; - - /* Set the flag for GMA command which should only be called once */ - ndp->gma_flag = 1; - - ret = ops->ndo_set_mac_address(ndev, &saddr); - if (ret < 0) - netdev_warn(ndev, "NCSI: 'Writing mac address to device failed\n"); - - return ret; -} - /* Response handler for Broadcom card */ static int ncsi_rsp_handler_oem_bcm(struct ncsi_request *nr) { @@ -695,42 +678,10 @@ static int ncsi_rsp_handler_oem_bcm(struct ncsi_request *nr) bcm = (struct ncsi_rsp_oem_bcm_pkt *)(rsp->data); if (bcm->type == NCSI_OEM_BCM_CMD_GMA) - return ncsi_rsp_handler_oem_bcm_gma(nr); + return ncsi_rsp_handler_oem_gma(nr, NCSI_OEM_MFR_BCM_ID); return 0; } -/* Response handler for Intel command Get Mac Address */ -static int ncsi_rsp_handler_oem_intel_gma(struct ncsi_request *nr) -{ - struct ncsi_dev_priv *ndp = nr->ndp; - struct net_device *ndev = ndp->ndev.dev; - const struct net_device_ops *ops = ndev->netdev_ops; - struct ncsi_rsp_oem_pkt *rsp; - struct sockaddr saddr; - int ret = 0; - - /* Get the response header */ - rsp = (struct ncsi_rsp_oem_pkt *)skb_network_header(nr->rsp); - - saddr.sa_family = ndev->type; - ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE; - memcpy(saddr.sa_data, &rsp->data[INTEL_MAC_ADDR_OFFSET], ETH_ALEN); - /* Increase mac address by 1 for BMC's address */ - eth_addr_inc((u8 *)saddr.sa_data); - if (!is_valid_ether_addr((const u8 *)saddr.sa_data)) - return -ENXIO; - - /* Set the flag for GMA command which should only be called once */ - ndp->gma_flag = 1; - - ret = ops->ndo_set_mac_address(ndev, &saddr); - if (ret < 0) - netdev_warn(ndev, - "NCSI: 'Writing mac address to device failed\n"); - - return ret; -} - /* Response handler for Intel card */ static int ncsi_rsp_handler_oem_intel(struct ncsi_request *nr) { @@ -742,7 +693,7 @@ static int ncsi_rsp_handler_oem_intel(struct ncsi_request *nr) intel = (struct ncsi_rsp_oem_intel_pkt *)(rsp->data); if (intel->cmd == NCSI_OEM_INTEL_CMD_GMA) - return ncsi_rsp_handler_oem_intel_gma(nr); + return ncsi_rsp_handler_oem_gma(nr, NCSI_OEM_MFR_INTEL_ID); return 0; } diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 46ebee9400da..9a6b64779e64 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1694,6 +1694,14 @@ call_ad(struct net *net, struct sock *ctnl, struct sk_buff *skb, bool eexist = flags & IPSET_FLAG_EXIST, retried = false; do { + if (retried) { + __ip_set_get(set); + nfnl_unlock(NFNL_SUBSYS_IPSET); + cond_resched(); + nfnl_lock(NFNL_SUBSYS_IPSET); + __ip_set_put(set); + } + ip_set_lock(set); ret = set->variant->uadt(set, tb, adt, &lineno, flags, retried); ip_set_unlock(set); diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index feb1d7fcb09f..c7652da78c88 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -139,7 +139,7 @@ retry: if (PTR_ERR(rt) == -EINVAL && *saddr && rt_mode & IP_VS_RT_MODE_CONNECT && !loop) { *saddr = 0; - flowi4_update_output(&fl4, 0, 0, daddr, 0); + flowi4_update_output(&fl4, 0, daddr, 0); goto retry; } IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n", &daddr); @@ -147,7 +147,7 @@ retry: } else if (!*saddr && rt_mode & IP_VS_RT_MODE_CONNECT && fl4.saddr) { ip_rt_put(rt); *saddr = fl4.saddr; - flowi4_update_output(&fl4, 0, 0, daddr, fl4.saddr); + flowi4_update_output(&fl4, 0, daddr, fl4.saddr); loop = true; goto retry; } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index c4ccfec6cb98..d119f1d4c2fc 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -2260,6 +2260,9 @@ static int nf_confirm_cthelper(struct sk_buff *skb, struct nf_conn *ct, return 0; helper = rcu_dereference(help->helper); + if (!helper) + return 0; + if (!(helper->flags & NF_CT_HELPER_F_USERSPACE)) return 0; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index d40544cd61a6..69c8c8c7e9b8 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2976,7 +2976,9 @@ nla_put_failure: return -1; } +#if IS_ENABLED(CONFIG_NF_NAT) static const union nf_inet_addr any_addr; +#endif static __be32 nf_expect_get_id(const struct nf_conntrack_expect *exp) { @@ -3460,10 +3462,12 @@ ctnetlink_change_expect(struct nf_conntrack_expect *x, return 0; } +#if IS_ENABLED(CONFIG_NF_NAT) static const struct nla_policy exp_nat_nla_policy[CTA_EXPECT_NAT_MAX+1] = { [CTA_EXPECT_NAT_DIR] = { .type = NLA_U32 }, [CTA_EXPECT_NAT_TUPLE] = { .type = NLA_NESTED }, }; +#endif static int ctnetlink_parse_expect_nat(const struct nlattr *attr, diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index 728eeb0aea87..ad6f0ca40cd2 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -296,6 +296,7 @@ void nf_conntrack_gre_init_net(struct net *net) /* protocol helper struct */ const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre = { .l4proto = IPPROTO_GRE, + .allow_clash = true, #ifdef CONFIG_NF_CONNTRACK_PROCFS .print_conntrack = gre_print_conntrack, #endif diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 04bd0ed4d2ae..b46dd897f2c5 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -125,9 +125,6 @@ static int flow_offload_fill_route(struct flow_offload *flow, break; case FLOW_OFFLOAD_XMIT_XFRM: case FLOW_OFFLOAD_XMIT_NEIGH: - if (!dst_hold_safe(route->tuple[dir].dst)) - return -1; - flow_tuple->dst_cache = dst; flow_tuple->dst_cookie = flow_offload_dst_cookie(flow_tuple); break; @@ -148,27 +145,12 @@ static void nft_flow_dst_release(struct flow_offload *flow, dst_release(flow->tuplehash[dir].tuple.dst_cache); } -int flow_offload_route_init(struct flow_offload *flow, +void flow_offload_route_init(struct flow_offload *flow, const struct nf_flow_route *route) { - int err; - - err = flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_ORIGINAL); - if (err < 0) - return err; - - err = flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_REPLY); - if (err < 0) - goto err_route_reply; - + flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_ORIGINAL); + flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_REPLY); flow->type = NF_FLOW_OFFLOAD_ROUTE; - - return 0; - -err_route_reply: - nft_flow_dst_release(flow, FLOW_OFFLOAD_DIR_ORIGINAL); - - return err; } EXPORT_SYMBOL_GPL(flow_offload_route_init); diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index 19efba1e51ef..d248763917ad 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -163,38 +163,43 @@ static void nf_flow_tuple_encap(struct sk_buff *skb, } } -static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev, - struct flow_offload_tuple *tuple, u32 *hdrsize, - u32 offset) +struct nf_flowtable_ctx { + const struct net_device *in; + u32 offset; + u32 hdrsize; +}; + +static int nf_flow_tuple_ip(struct nf_flowtable_ctx *ctx, struct sk_buff *skb, + struct flow_offload_tuple *tuple) { struct flow_ports *ports; unsigned int thoff; struct iphdr *iph; u8 ipproto; - if (!pskb_may_pull(skb, sizeof(*iph) + offset)) + if (!pskb_may_pull(skb, sizeof(*iph) + ctx->offset)) return -1; - iph = (struct iphdr *)(skb_network_header(skb) + offset); + iph = (struct iphdr *)(skb_network_header(skb) + ctx->offset); thoff = (iph->ihl * 4); if (ip_is_fragment(iph) || unlikely(ip_has_options(thoff))) return -1; - thoff += offset; + thoff += ctx->offset; ipproto = iph->protocol; switch (ipproto) { case IPPROTO_TCP: - *hdrsize = sizeof(struct tcphdr); + ctx->hdrsize = sizeof(struct tcphdr); break; case IPPROTO_UDP: - *hdrsize = sizeof(struct udphdr); + ctx->hdrsize = sizeof(struct udphdr); break; #ifdef CONFIG_NF_CT_PROTO_GRE case IPPROTO_GRE: - *hdrsize = sizeof(struct gre_base_hdr); + ctx->hdrsize = sizeof(struct gre_base_hdr); break; #endif default: @@ -204,7 +209,7 @@ static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev, if (iph->ttl <= 1) return -1; - if (!pskb_may_pull(skb, thoff + *hdrsize)) + if (!pskb_may_pull(skb, thoff + ctx->hdrsize)) return -1; switch (ipproto) { @@ -224,13 +229,13 @@ static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev, } } - iph = (struct iphdr *)(skb_network_header(skb) + offset); + iph = (struct iphdr *)(skb_network_header(skb) + ctx->offset); tuple->src_v4.s_addr = iph->saddr; tuple->dst_v4.s_addr = iph->daddr; tuple->l3proto = AF_INET; tuple->l4proto = ipproto; - tuple->iifidx = dev->ifindex; + tuple->iifidx = ctx->in->ifindex; nf_flow_tuple_encap(skb, tuple); return 0; @@ -336,58 +341,56 @@ static unsigned int nf_flow_queue_xmit(struct net *net, struct sk_buff *skb, return NF_STOLEN; } -unsigned int -nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) +static struct flow_offload_tuple_rhash * +nf_flow_offload_lookup(struct nf_flowtable_ctx *ctx, + struct nf_flowtable *flow_table, struct sk_buff *skb) { - struct flow_offload_tuple_rhash *tuplehash; - struct nf_flowtable *flow_table = priv; struct flow_offload_tuple tuple = {}; - enum flow_offload_tuple_dir dir; - struct flow_offload *flow; - struct net_device *outdev; - u32 hdrsize, offset = 0; - unsigned int thoff, mtu; - struct rtable *rt; - struct iphdr *iph; - __be32 nexthop; - int ret; if (skb->protocol != htons(ETH_P_IP) && - !nf_flow_skb_encap_protocol(skb, htons(ETH_P_IP), &offset)) - return NF_ACCEPT; + !nf_flow_skb_encap_protocol(skb, htons(ETH_P_IP), &ctx->offset)) + return NULL; - if (nf_flow_tuple_ip(skb, state->in, &tuple, &hdrsize, offset) < 0) - return NF_ACCEPT; + if (nf_flow_tuple_ip(ctx, skb, &tuple) < 0) + return NULL; - tuplehash = flow_offload_lookup(flow_table, &tuple); - if (tuplehash == NULL) - return NF_ACCEPT; + return flow_offload_lookup(flow_table, &tuple); +} + +static int nf_flow_offload_forward(struct nf_flowtable_ctx *ctx, + struct nf_flowtable *flow_table, + struct flow_offload_tuple_rhash *tuplehash, + struct sk_buff *skb) +{ + enum flow_offload_tuple_dir dir; + struct flow_offload *flow; + unsigned int thoff, mtu; + struct iphdr *iph; dir = tuplehash->tuple.dir; flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); - mtu = flow->tuplehash[dir].tuple.mtu + offset; + mtu = flow->tuplehash[dir].tuple.mtu + ctx->offset; if (unlikely(nf_flow_exceeds_mtu(skb, mtu))) - return NF_ACCEPT; + return 0; - iph = (struct iphdr *)(skb_network_header(skb) + offset); - thoff = (iph->ihl * 4) + offset; + iph = (struct iphdr *)(skb_network_header(skb) + ctx->offset); + thoff = (iph->ihl * 4) + ctx->offset; if (nf_flow_state_check(flow, iph->protocol, skb, thoff)) - return NF_ACCEPT; + return 0; if (!nf_flow_dst_check(&tuplehash->tuple)) { flow_offload_teardown(flow); - return NF_ACCEPT; + return 0; } - if (skb_try_make_writable(skb, thoff + hdrsize)) - return NF_DROP; + if (skb_try_make_writable(skb, thoff + ctx->hdrsize)) + return -1; flow_offload_refresh(flow_table, flow); nf_flow_encap_pop(skb, tuplehash); - thoff -= offset; + thoff -= ctx->offset; iph = ip_hdr(skb); nf_flow_nat_ip(flow, skb, thoff, dir, iph); @@ -398,6 +401,35 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, if (flow_table->flags & NF_FLOWTABLE_COUNTER) nf_ct_acct_update(flow->ct, tuplehash->tuple.dir, skb->len); + return 1; +} + +unsigned int +nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct flow_offload_tuple_rhash *tuplehash; + struct nf_flowtable *flow_table = priv; + enum flow_offload_tuple_dir dir; + struct nf_flowtable_ctx ctx = { + .in = state->in, + }; + struct flow_offload *flow; + struct net_device *outdev; + struct rtable *rt; + __be32 nexthop; + int ret; + + tuplehash = nf_flow_offload_lookup(&ctx, flow_table, skb); + if (!tuplehash) + return NF_ACCEPT; + + ret = nf_flow_offload_forward(&ctx, flow_table, tuplehash, skb); + if (ret < 0) + return NF_DROP; + else if (ret == 0) + return NF_ACCEPT; + if (unlikely(tuplehash->tuple.xmit_type == FLOW_OFFLOAD_XMIT_XFRM)) { rt = (struct rtable *)tuplehash->tuple.dst_cache; memset(skb->cb, 0, sizeof(struct inet_skb_parm)); @@ -406,6 +438,9 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, return nf_flow_xmit_xfrm(skb, state, &rt->dst); } + dir = tuplehash->tuple.dir; + flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); + switch (tuplehash->tuple.xmit_type) { case FLOW_OFFLOAD_XMIT_NEIGH: rt = (struct rtable *)tuplehash->tuple.dst_cache; @@ -535,32 +570,31 @@ static void nf_flow_nat_ipv6(const struct flow_offload *flow, } } -static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev, - struct flow_offload_tuple *tuple, u32 *hdrsize, - u32 offset) +static int nf_flow_tuple_ipv6(struct nf_flowtable_ctx *ctx, struct sk_buff *skb, + struct flow_offload_tuple *tuple) { struct flow_ports *ports; struct ipv6hdr *ip6h; unsigned int thoff; u8 nexthdr; - thoff = sizeof(*ip6h) + offset; + thoff = sizeof(*ip6h) + ctx->offset; if (!pskb_may_pull(skb, thoff)) return -1; - ip6h = (struct ipv6hdr *)(skb_network_header(skb) + offset); + ip6h = (struct ipv6hdr *)(skb_network_header(skb) + ctx->offset); nexthdr = ip6h->nexthdr; switch (nexthdr) { case IPPROTO_TCP: - *hdrsize = sizeof(struct tcphdr); + ctx->hdrsize = sizeof(struct tcphdr); break; case IPPROTO_UDP: - *hdrsize = sizeof(struct udphdr); + ctx->hdrsize = sizeof(struct udphdr); break; #ifdef CONFIG_NF_CT_PROTO_GRE case IPPROTO_GRE: - *hdrsize = sizeof(struct gre_base_hdr); + ctx->hdrsize = sizeof(struct gre_base_hdr); break; #endif default: @@ -570,7 +604,7 @@ static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev, if (ip6h->hop_limit <= 1) return -1; - if (!pskb_may_pull(skb, thoff + *hdrsize)) + if (!pskb_may_pull(skb, thoff + ctx->hdrsize)) return -1; switch (nexthdr) { @@ -590,65 +624,47 @@ static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev, } } - ip6h = (struct ipv6hdr *)(skb_network_header(skb) + offset); + ip6h = (struct ipv6hdr *)(skb_network_header(skb) + ctx->offset); tuple->src_v6 = ip6h->saddr; tuple->dst_v6 = ip6h->daddr; tuple->l3proto = AF_INET6; tuple->l4proto = nexthdr; - tuple->iifidx = dev->ifindex; + tuple->iifidx = ctx->in->ifindex; nf_flow_tuple_encap(skb, tuple); return 0; } -unsigned int -nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) +static int nf_flow_offload_ipv6_forward(struct nf_flowtable_ctx *ctx, + struct nf_flowtable *flow_table, + struct flow_offload_tuple_rhash *tuplehash, + struct sk_buff *skb) { - struct flow_offload_tuple_rhash *tuplehash; - struct nf_flowtable *flow_table = priv; - struct flow_offload_tuple tuple = {}; enum flow_offload_tuple_dir dir; - const struct in6_addr *nexthop; struct flow_offload *flow; - struct net_device *outdev; unsigned int thoff, mtu; - u32 hdrsize, offset = 0; struct ipv6hdr *ip6h; - struct rt6_info *rt; - int ret; - - if (skb->protocol != htons(ETH_P_IPV6) && - !nf_flow_skb_encap_protocol(skb, htons(ETH_P_IPV6), &offset)) - return NF_ACCEPT; - - if (nf_flow_tuple_ipv6(skb, state->in, &tuple, &hdrsize, offset) < 0) - return NF_ACCEPT; - - tuplehash = flow_offload_lookup(flow_table, &tuple); - if (tuplehash == NULL) - return NF_ACCEPT; dir = tuplehash->tuple.dir; flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); - mtu = flow->tuplehash[dir].tuple.mtu + offset; + mtu = flow->tuplehash[dir].tuple.mtu + ctx->offset; if (unlikely(nf_flow_exceeds_mtu(skb, mtu))) - return NF_ACCEPT; + return 0; - ip6h = (struct ipv6hdr *)(skb_network_header(skb) + offset); - thoff = sizeof(*ip6h) + offset; + ip6h = (struct ipv6hdr *)(skb_network_header(skb) + ctx->offset); + thoff = sizeof(*ip6h) + ctx->offset; if (nf_flow_state_check(flow, ip6h->nexthdr, skb, thoff)) - return NF_ACCEPT; + return 0; if (!nf_flow_dst_check(&tuplehash->tuple)) { flow_offload_teardown(flow); - return NF_ACCEPT; + return 0; } - if (skb_try_make_writable(skb, thoff + hdrsize)) - return NF_DROP; + if (skb_try_make_writable(skb, thoff + ctx->hdrsize)) + return -1; flow_offload_refresh(flow_table, flow); @@ -663,6 +679,52 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, if (flow_table->flags & NF_FLOWTABLE_COUNTER) nf_ct_acct_update(flow->ct, tuplehash->tuple.dir, skb->len); + return 1; +} + +static struct flow_offload_tuple_rhash * +nf_flow_offload_ipv6_lookup(struct nf_flowtable_ctx *ctx, + struct nf_flowtable *flow_table, + struct sk_buff *skb) +{ + struct flow_offload_tuple tuple = {}; + + if (skb->protocol != htons(ETH_P_IPV6) && + !nf_flow_skb_encap_protocol(skb, htons(ETH_P_IPV6), &ctx->offset)) + return NULL; + + if (nf_flow_tuple_ipv6(ctx, skb, &tuple) < 0) + return NULL; + + return flow_offload_lookup(flow_table, &tuple); +} + +unsigned int +nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct flow_offload_tuple_rhash *tuplehash; + struct nf_flowtable *flow_table = priv; + enum flow_offload_tuple_dir dir; + struct nf_flowtable_ctx ctx = { + .in = state->in, + }; + const struct in6_addr *nexthop; + struct flow_offload *flow; + struct net_device *outdev; + struct rt6_info *rt; + int ret; + + tuplehash = nf_flow_offload_ipv6_lookup(&ctx, flow_table, skb); + if (tuplehash == NULL) + return NF_ACCEPT; + + ret = nf_flow_offload_ipv6_forward(&ctx, flow_table, tuplehash, skb); + if (ret < 0) + return NF_DROP; + else if (ret == 0) + return NF_ACCEPT; + if (unlikely(tuplehash->tuple.xmit_type == FLOW_OFFLOAD_XMIT_XFRM)) { rt = (struct rt6_info *)tuplehash->tuple.dst_cache; memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); @@ -671,6 +733,9 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, return nf_flow_xmit_xfrm(skb, state, &rt->dst); } + dir = tuplehash->tuple.dir; + flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); + switch (tuplehash->tuple.xmit_type) { case FLOW_OFFLOAD_XMIT_NEIGH: rt = (struct rt6_info *)tuplehash->tuple.dst_cache; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 59fb8320ab4d..dc58991705d7 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1600,6 +1600,8 @@ static int nft_dump_basechain_hook(struct sk_buff *skb, int family, if (nft_base_chain_netdev(family, ops->hooknum)) { nest_devs = nla_nest_start_noflag(skb, NFTA_HOOK_DEVS); + if (!nest_devs) + goto nla_put_failure; if (!hook_list) hook_list = &basechain->hook_list; @@ -3865,12 +3867,10 @@ static struct nft_rule *nft_rule_lookup_byid(const struct net *net, struct nft_trans *trans; list_for_each_entry(trans, &nft_net->commit_list, list) { - struct nft_rule *rule = nft_trans_rule(trans); - if (trans->msg_type == NFT_MSG_NEWRULE && trans->ctx.chain == chain && id == nft_trans_rule_id(trans)) - return rule; + return nft_trans_rule(trans); } return ERR_PTR(-ENOENT); } @@ -6541,10 +6541,13 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, goto err_element_clash; } - if (!(flags & NFT_SET_ELEM_CATCHALL) && set->size && - !atomic_add_unless(&set->nelems, 1, set->size + set->ndeact)) { - err = -ENFILE; - goto err_set_full; + if (!(flags & NFT_SET_ELEM_CATCHALL)) { + unsigned int max = set->size ? set->size + set->ndeact : UINT_MAX; + + if (!atomic_add_unless(&set->nelems, 1, max)) { + err = -ENFILE; + goto err_set_full; + } } nft_trans_elem(trans) = elem; @@ -9007,7 +9010,7 @@ static int nf_tables_commit_chain_prepare(struct net *net, struct nft_chain *cha continue; } - if (WARN_ON_ONCE(data + expr->ops->size > data_boundary)) + if (WARN_ON_ONCE(data + size + expr->ops->size > data_boundary)) return -ENOMEM; memcpy(data + size, expr, expr->ops->size); diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index 84eae7cabc67..2527a01486ef 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -323,7 +323,7 @@ static bool nft_bitwise_reduce(struct nft_regs_track *track, dreg = priv->dreg; regcount = DIV_ROUND_UP(priv->len, NFT_REG32_SIZE); for (i = 0; i < regcount; i++, dreg++) - track->regs[priv->dreg].bitwise = expr; + track->regs[dreg].bitwise = expr; return false; } diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index a54a7f772cec..671474e59817 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -10,6 +10,7 @@ #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> +#include <linux/dccp.h> #include <linux/sctp.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_tables.h> @@ -406,6 +407,82 @@ err: regs->verdict.code = NFT_BREAK; } +static void nft_exthdr_dccp_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_exthdr *priv = nft_expr_priv(expr); + unsigned int thoff, dataoff, optoff, optlen, i; + u32 *dest = ®s->data[priv->dreg]; + const struct dccp_hdr *dh; + struct dccp_hdr _dh; + + if (pkt->tprot != IPPROTO_DCCP || pkt->fragoff) + goto err; + + thoff = nft_thoff(pkt); + + dh = skb_header_pointer(pkt->skb, thoff, sizeof(_dh), &_dh); + if (!dh) + goto err; + + dataoff = dh->dccph_doff * sizeof(u32); + optoff = __dccp_hdr_len(dh); + if (dataoff <= optoff) + goto err; + + optlen = dataoff - optoff; + + for (i = 0; i < optlen; ) { + /* Options 0 (DCCPO_PADDING) - 31 (DCCPO_MAX_RESERVED) are 1B in + * the length; the remaining options are at least 2B long. In + * all cases, the first byte contains the option type. In + * multi-byte options, the second byte contains the option + * length, which must be at least two: 1 for the type plus 1 for + * the length plus 0-253 for any following option data. We + * aren't interested in the option data, only the type and the + * length, so we don't need to read more than two bytes at a + * time. + */ + unsigned int buflen = optlen - i; + u8 buf[2], *bufp; + u8 type, len; + + if (buflen > sizeof(buf)) + buflen = sizeof(buf); + + bufp = skb_header_pointer(pkt->skb, thoff + optoff + i, buflen, + &buf); + if (!bufp) + goto err; + + type = bufp[0]; + + if (type == priv->type) { + *dest = 1; + return; + } + + if (type <= DCCPO_MAX_RESERVED) { + i++; + continue; + } + + if (buflen < 2) + goto err; + + len = bufp[1]; + + if (len < 2) + goto err; + + i += len; + } + +err: + *dest = 0; +} + static const struct nla_policy nft_exthdr_policy[NFTA_EXTHDR_MAX + 1] = { [NFTA_EXTHDR_DREG] = { .type = NLA_U32 }, [NFTA_EXTHDR_TYPE] = { .type = NLA_U8 }, @@ -557,6 +634,22 @@ static int nft_exthdr_ipv4_init(const struct nft_ctx *ctx, return 0; } +static int nft_exthdr_dccp_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_exthdr *priv = nft_expr_priv(expr); + int err = nft_exthdr_init(ctx, expr, tb); + + if (err < 0) + return err; + + if (!(priv->flags & NFT_EXTHDR_F_PRESENT)) + return -EOPNOTSUPP; + + return 0; +} + static int nft_exthdr_dump_common(struct sk_buff *skb, const struct nft_exthdr *priv) { if (nla_put_u8(skb, NFTA_EXTHDR_TYPE, priv->type)) @@ -686,6 +779,15 @@ static const struct nft_expr_ops nft_exthdr_sctp_ops = { .reduce = nft_exthdr_reduce, }; +static const struct nft_expr_ops nft_exthdr_dccp_ops = { + .type = &nft_exthdr_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_exthdr)), + .eval = nft_exthdr_dccp_eval, + .init = nft_exthdr_dccp_init, + .dump = nft_exthdr_dump, + .reduce = nft_exthdr_reduce, +}; + static const struct nft_expr_ops * nft_exthdr_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) @@ -720,6 +822,10 @@ nft_exthdr_select_ops(const struct nft_ctx *ctx, if (tb[NFTA_EXTHDR_DREG]) return &nft_exthdr_sctp_ops; break; + case NFT_EXTHDR_OP_DCCP: + if (tb[NFTA_EXTHDR_DREG]) + return &nft_exthdr_dccp_ops; + break; } return ERR_PTR(-EOPNOTSUPP); diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index e860d8fe0e5e..5ef9146e74ad 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -250,9 +250,14 @@ static int nft_flow_route(const struct nft_pktinfo *pkt, break; } + if (!dst_hold_safe(this_dst)) + return -ENOENT; + nf_route(nft_net(pkt), &other_dst, &fl, false, nft_pf(pkt)); - if (!other_dst) + if (!other_dst) { + dst_release(this_dst); return -ENOENT; + } nft_default_forward_path(route, this_dst, dir); nft_default_forward_path(route, other_dst, !dir); @@ -349,8 +354,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, if (!flow) goto err_flow_alloc; - if (flow_offload_route_init(flow, &route) < 0) - goto err_flow_add; + flow_offload_route_init(flow, &route); if (tcph) { ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; @@ -361,12 +365,12 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, if (ret < 0) goto err_flow_add; - dst_release(route.tuple[!dir].dst); return; err_flow_add: flow_offload_free(flow); err_flow_alloc: + dst_release(route.tuple[dir].dst); dst_release(route.tuple[!dir].dst); err_flow_route: clear_bit(IPS_OFFLOAD_BIT, &ct->status); diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 03ef4fdaa460..29ac48cdd6db 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -19,6 +19,7 @@ struct nft_lookup { struct nft_set *set; u8 sreg; u8 dreg; + bool dreg_set; bool invert; struct nft_set_binding binding; }; @@ -75,7 +76,7 @@ void nft_lookup_eval(const struct nft_expr *expr, } if (ext) { - if (set->flags & NFT_SET_MAP) + if (priv->dreg_set) nft_data_copy(®s->data[priv->dreg], nft_set_ext_data(ext), set->dlen); @@ -122,11 +123,8 @@ static int nft_lookup_init(const struct nft_ctx *ctx, if (flags & ~NFT_LOOKUP_F_INV) return -EINVAL; - if (flags & NFT_LOOKUP_F_INV) { - if (set->flags & NFT_SET_MAP) - return -EINVAL; + if (flags & NFT_LOOKUP_F_INV) priv->invert = true; - } } if (tb[NFTA_LOOKUP_DREG] != NULL) { @@ -140,8 +138,17 @@ static int nft_lookup_init(const struct nft_ctx *ctx, set->dlen); if (err < 0) return err; - } else if (set->flags & NFT_SET_MAP) - return -EINVAL; + priv->dreg_set = true; + } else if (set->flags & NFT_SET_MAP) { + /* Map given, but user asks for lookup only (i.e. to + * ignore value assoicated with key). + * + * This makes no sense for anonymous maps since they are + * scoped to the rule, but for named sets this can be useful. + */ + if (set->flags & NFT_SET_ANONYMOUS) + return -EINVAL; + } priv->binding.flags = set->flags & NFT_SET_MAP; @@ -188,7 +195,7 @@ static int nft_lookup_dump(struct sk_buff *skb, goto nla_put_failure; if (nft_dump_register(skb, NFTA_LOOKUP_SREG, priv->sreg)) goto nla_put_failure; - if (priv->set->flags & NFT_SET_MAP) + if (priv->dreg_set) if (nft_dump_register(skb, NFTA_LOOKUP_DREG, priv->dreg)) goto nla_put_failure; if (nla_put_be32(skb, NFTA_LOOKUP_FLAGS, htonl(flags))) diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 06d46d182634..34c684e121d3 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1274,8 +1274,7 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old) struct nft_pipapo_match *new; int i; - new = kmalloc(sizeof(*new) + sizeof(*dst) * old->field_count, - GFP_KERNEL); + new = kmalloc(struct_size(new, f, old->field_count), GFP_KERNEL); if (!new) return ERR_PTR(-ENOMEM); @@ -2059,8 +2058,7 @@ static int nft_pipapo_init(const struct nft_set *set, if (field_count > NFT_PIPAPO_MAX_FIELDS) return -EINVAL; - m = kmalloc(sizeof(*priv->match) + sizeof(*f) * field_count, - GFP_KERNEL); + m = kmalloc(struct_size(m, f, field_count), GFP_KERNEL); if (!m) return -ENOMEM; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 19ea4d3c3553..2f114aa10f1a 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -221,7 +221,7 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, { struct nft_set *set = (struct nft_set *)__set; struct rb_node *prev = rb_prev(&rbe->node); - struct nft_rbtree_elem *rbe_prev; + struct nft_rbtree_elem *rbe_prev = NULL; struct nft_set_gc_batch *gcb; gcb = nft_set_gc_batch_check(set, NULL, GFP_ATOMIC); @@ -229,17 +229,21 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, return -ENOMEM; /* search for expired end interval coming before this element. */ - do { + while (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); if (nft_rbtree_interval_end(rbe_prev)) break; prev = rb_prev(prev); - } while (prev != NULL); + } + + if (rbe_prev) { + rb_erase(&rbe_prev->node, &priv->root); + atomic_dec(&set->nelems); + } - rb_erase(&rbe_prev->node, &priv->root); rb_erase(&rbe->node, &priv->root); - atomic_sub(2, &set->nelems); + atomic_dec(&set->nelems); nft_set_gc_batch_add(gcb, rbe); nft_set_gc_batch_complete(gcb); @@ -268,7 +272,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_set_ext **ext) { struct nft_rbtree_elem *rbe, *rbe_le = NULL, *rbe_ge = NULL; - struct rb_node *node, *parent, **p, *first = NULL; + struct rb_node *node, *next, *parent, **p, *first = NULL; struct nft_rbtree *priv = nft_set_priv(set); u8 genmask = nft_genmask_next(net); int d, err; @@ -307,7 +311,9 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, * Values stored in the tree are in reversed order, starting from * highest to lowest value. */ - for (node = first; node != NULL; node = rb_next(node)) { + for (node = first; node != NULL; node = next) { + next = rb_next(node); + rbe = rb_entry(node, struct nft_rbtree_elem, node); if (!nft_set_elem_active(&rbe->ext, genmask)) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index c87804112d0c..3a1e0fd5bf14 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1779,7 +1779,7 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, break; } } - if (put_user(ALIGN(nlk->ngroups / 8, sizeof(u32)), optlen)) + if (put_user(ALIGN(BITS_TO_BYTES(nlk->ngroups), sizeof(u32)), optlen)) err = -EFAULT; netlink_unlock_table(); return err; diff --git a/net/netrom/nr_subr.c b/net/netrom/nr_subr.c index 3f99b432ea70..e2d2af924cff 100644 --- a/net/netrom/nr_subr.c +++ b/net/netrom/nr_subr.c @@ -123,7 +123,7 @@ void nr_write_internal(struct sock *sk, int frametype) unsigned char *dptr; int len, timeout; - len = NR_NETWORK_LEN + NR_TRANSPORT_LEN; + len = NR_TRANSPORT_LEN; switch (frametype & 0x0F) { case NR_CONNREQ: @@ -141,7 +141,8 @@ void nr_write_internal(struct sock *sk, int frametype) return; } - if ((skb = alloc_skb(len, GFP_ATOMIC)) == NULL) + skb = alloc_skb(NR_NETWORK_LEN + len, GFP_ATOMIC); + if (!skb) return; /* @@ -149,7 +150,7 @@ void nr_write_internal(struct sock *sk, int frametype) */ skb_reserve(skb, NR_NETWORK_LEN); - dptr = skb_put(skb, skb_tailroom(skb)); + dptr = skb_put(skb, len); switch (frametype & 0x0F) { case NR_CONNREQ: diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index 41e3a20c8935..cdb001de0692 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -390,7 +390,8 @@ int nfc_llcp_send_connect(struct nfc_llcp_sock *sock) const u8 *service_name_tlv = NULL; const u8 *miux_tlv = NULL; const u8 *rw_tlv = NULL; - u8 service_name_tlv_length, miux_tlv_length, rw_tlv_length, rw; + u8 service_name_tlv_length = 0; + u8 miux_tlv_length, rw_tlv_length, rw; int err; u16 size = 0; __be16 miux; diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c index e9ca007718b7..0f23e5e8e03e 100644 --- a/net/nsh/nsh.c +++ b/net/nsh/nsh.c @@ -77,13 +77,12 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); + u16 mac_offset = skb->mac_header; unsigned int nsh_len, mac_len; __be16 proto; - int nhoff; skb_reset_network_header(skb); - nhoff = skb->network_header - skb->mac_header; mac_len = skb->mac_len; if (unlikely(!pskb_may_pull(skb, NSH_BASE_HDR_LEN))) @@ -108,15 +107,14 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, segs = skb_mac_gso_segment(skb, features); if (IS_ERR_OR_NULL(segs)) { skb_gso_error_unwind(skb, htons(ETH_P_NSH), nsh_len, - skb->network_header - nhoff, - mac_len); + mac_offset, mac_len); goto out; } for (skb = segs; skb; skb = skb->next) { skb->protocol = htons(ETH_P_NSH); __skb_push(skb, nsh_len); - skb_set_mac_header(skb, -nhoff); + skb->mac_header = mac_offset; skb->network_header = skb->mac_header + mac_len; skb->mac_len = mac_len; } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index fcee6012293b..58f530f60172 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -236,9 +236,6 @@ void ovs_dp_detach_port(struct vport *p) /* First drop references to device. */ hlist_del_rcu(&p->dp_hash_node); - /* Free percpu memory */ - free_percpu(p->upcall_stats); - /* Then destroy it. */ ovs_vport_del(p); } @@ -1858,12 +1855,6 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) goto err_destroy_portids; } - vport->upcall_stats = netdev_alloc_pcpu_stats(struct vport_upcall_stats_percpu); - if (!vport->upcall_stats) { - err = -ENOMEM; - goto err_destroy_vport; - } - err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid, info->snd_seq, 0, OVS_DP_CMD_NEW); BUG_ON(err < 0); @@ -1876,8 +1867,6 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) ovs_notify(&dp_datapath_genl_family, reply, info); return 0; -err_destroy_vport: - ovs_dp_detach_port(vport); err_destroy_portids: kfree(rcu_dereference_raw(dp->upcall_portids)); err_unlock_and_destroy_meters: @@ -2322,12 +2311,6 @@ restart: goto exit_unlock_free; } - vport->upcall_stats = netdev_alloc_pcpu_stats(struct vport_upcall_stats_percpu); - if (!vport->upcall_stats) { - err = -ENOMEM; - goto exit_unlock_free_vport; - } - err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), info->snd_portid, info->snd_seq, 0, OVS_VPORT_CMD_NEW, GFP_KERNEL); @@ -2345,8 +2328,6 @@ restart: ovs_notify(&dp_vport_genl_family, reply, info); return 0; -exit_unlock_free_vport: - ovs_dp_detach_port(vport); exit_unlock_free: ovs_unlock(); kfree_skb(reply); diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index f2698d2316df..c4ebf810e4b1 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -69,9 +69,7 @@ static struct dp_meter_instance *dp_meter_instance_alloc(const u32 size) { struct dp_meter_instance *ti; - ti = kvzalloc(sizeof(*ti) + - sizeof(struct dp_meter *) * size, - GFP_KERNEL); + ti = kvzalloc(struct_size(ti, dp_meters, size), GFP_KERNEL); if (!ti) return NULL; diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 7e0f5c45b512..972ae01a70f7 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -124,6 +124,7 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops, { struct vport *vport; size_t alloc_size; + int err; alloc_size = sizeof(struct vport); if (priv_size) { @@ -135,17 +136,29 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops, if (!vport) return ERR_PTR(-ENOMEM); + vport->upcall_stats = netdev_alloc_pcpu_stats(struct vport_upcall_stats_percpu); + if (!vport->upcall_stats) { + err = -ENOMEM; + goto err_kfree_vport; + } + vport->dp = parms->dp; vport->port_no = parms->port_no; vport->ops = ops; INIT_HLIST_NODE(&vport->dp_hash_node); if (ovs_vport_set_upcall_portids(vport, parms->upcall_portids)) { - kfree(vport); - return ERR_PTR(-EINVAL); + err = -EINVAL; + goto err_free_percpu; } return vport; + +err_free_percpu: + free_percpu(vport->upcall_stats); +err_kfree_vport: + kfree(vport); + return ERR_PTR(err); } EXPORT_SYMBOL_GPL(ovs_vport_alloc); @@ -165,6 +178,7 @@ void ovs_vport_free(struct vport *vport) * it is safe to use raw dereference. */ kfree(rcu_dereference_raw(vport->upcall_portids)); + free_percpu(vport->upcall_stats); kfree(vport); } EXPORT_SYMBOL_GPL(ovs_vport_free); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 94c6a1ffa459..a2dbeb264f26 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3201,6 +3201,9 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, lock_sock(sk); spin_lock(&po->bind_lock); + if (!proto) + proto = po->num; + rcu_read_lock(); if (po->fanout) { @@ -3299,7 +3302,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data_min)); name[sizeof(uaddr->sa_data_min)] = 0; - return packet_do_bind(sk, name, 0, pkt_sk(sk)->num); + return packet_do_bind(sk, name, 0, 0); } static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) @@ -3316,8 +3319,7 @@ static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len if (sll->sll_family != AF_PACKET) return -EINVAL; - return packet_do_bind(sk, NULL, sll->sll_ifindex, - sll->sll_protocol ? : pkt_sk(sk)->num); + return packet_do_bind(sk, NULL, sll->sll_ifindex, sll->sll_protocol); } static struct proto packet_proto = { diff --git a/net/packet/diag.c b/net/packet/diag.c index d0c4eda4cdc6..f6b200cb3c06 100644 --- a/net/packet/diag.c +++ b/net/packet/diag.c @@ -143,7 +143,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, rp = nlmsg_data(nlh); rp->pdiag_family = AF_PACKET; rp->pdiag_type = sk->sk_type; - rp->pdiag_num = ntohs(po->num); + rp->pdiag_num = ntohs(READ_ONCE(po->num)); rp->pdiag_ino = sk_ino; sock_diag_save_cookie(sk, rp->pdiag_cookie); diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 31f738d65f1c..da0b3b5157d5 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -980,6 +980,7 @@ static int __init af_rxrpc_init(void) BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > sizeof_field(struct sk_buff, cb)); ret = -ENOMEM; + rxrpc_gen_version_string(); rxrpc_call_jar = kmem_cache_create( "rxrpc_call_jar", sizeof(struct rxrpc_call), 0, SLAB_HWCACHE_ALIGN, NULL); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 5d44dc08f66d..e8e14c6f904d 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -1068,6 +1068,7 @@ int rxrpc_get_server_data_key(struct rxrpc_connection *, const void *, time64_t, /* * local_event.c */ +void rxrpc_gen_version_string(void); void rxrpc_send_version_request(struct rxrpc_local *local, struct rxrpc_host_header *hdr, struct sk_buff *skb); diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c index 5e69ea6b233d..993c69f97488 100644 --- a/net/rxrpc/local_event.c +++ b/net/rxrpc/local_event.c @@ -16,7 +16,16 @@ #include <generated/utsrelease.h> #include "ar-internal.h" -static const char rxrpc_version_string[65] = "linux-" UTS_RELEASE " AF_RXRPC"; +static char rxrpc_version_string[65]; // "linux-" UTS_RELEASE " AF_RXRPC"; + +/* + * Generate the VERSION packet string. + */ +void rxrpc_gen_version_string(void) +{ + snprintf(rxrpc_version_string, sizeof(rxrpc_version_string), + "linux-%.49s AF_RXRPC", UTS_RELEASE); +} /* * Reply to a version request diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 227cba58ce9f..2e9dce03d1ec 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -357,23 +357,23 @@ static int tcf_police_dump(struct sk_buff *skb, struct tc_action *a, opt.burst = PSCHED_NS2TICKS(p->tcfp_burst); if (p->rate_present) { psched_ratecfg_getrate(&opt.rate, &p->rate); - if ((police->params->rate.rate_bytes_ps >= (1ULL << 32)) && + if ((p->rate.rate_bytes_ps >= (1ULL << 32)) && nla_put_u64_64bit(skb, TCA_POLICE_RATE64, - police->params->rate.rate_bytes_ps, + p->rate.rate_bytes_ps, TCA_POLICE_PAD)) goto nla_put_failure; } if (p->peak_present) { psched_ratecfg_getrate(&opt.peakrate, &p->peak); - if ((police->params->peak.rate_bytes_ps >= (1ULL << 32)) && + if ((p->peak.rate_bytes_ps >= (1ULL << 32)) && nla_put_u64_64bit(skb, TCA_POLICE_PEAKRATE64, - police->params->peak.rate_bytes_ps, + p->peak.rate_bytes_ps, TCA_POLICE_PAD)) goto nla_put_failure; } if (p->pps_present) { if (nla_put_u64_64bit(skb, TCA_POLICE_PKTRATE64, - police->params->ppsrate.rate_pkts_ps, + p->ppsrate.rate_pkts_ps, TCA_POLICE_PAD)) goto nla_put_failure; if (nla_put_u64_64bit(skb, TCA_POLICE_PKTBURST64, diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 2621550bfddc..c877a6343fd4 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -43,8 +43,6 @@ #include <net/flow_offload.h> #include <net/tc_wrapper.h> -extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1]; - /* The list of all installed classifier types */ static LIST_HEAD(tcf_proto_base); @@ -2952,6 +2950,7 @@ static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net, return PTR_ERR(ops); if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump) { NL_SET_ERR_MSG(extack, "Chain templates are not supported with specified classifier"); + module_put(ops->owner); return -EOPNOTSUPP; } diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 9dbc43388e57..e02ecabbb75c 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -120,6 +120,7 @@ struct cls_fl_filter { u32 handle; u32 flags; u32 in_hw_count; + u8 needs_tc_skb_ext:1; struct rcu_work rwork; struct net_device *hw_dev; /* Flower classifier is unlocked, which means that its reference counter @@ -415,6 +416,8 @@ static struct cls_fl_head *fl_head_dereference(struct tcf_proto *tp) static void __fl_destroy_filter(struct cls_fl_filter *f) { + if (f->needs_tc_skb_ext) + tc_skb_ext_tc_disable(); tcf_exts_destroy(&f->exts); tcf_exts_put_net(&f->exts); kfree(f); @@ -615,7 +618,8 @@ static void *fl_get(struct tcf_proto *tp, u32 handle) } static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { - [TCA_FLOWER_UNSPEC] = { .type = NLA_UNSPEC }, + [TCA_FLOWER_UNSPEC] = { .strict_start_type = + TCA_FLOWER_L2_MISS }, [TCA_FLOWER_CLASSID] = { .type = NLA_U32 }, [TCA_FLOWER_INDEV] = { .type = NLA_STRING, .len = IFNAMSIZ }, @@ -720,7 +724,7 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_PPPOE_SID] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_PPP_PROTO] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_L2TPV3_SID] = { .type = NLA_U32 }, - + [TCA_FLOWER_L2_MISS] = NLA_POLICY_MAX(NLA_U8, 1), }; static const struct nla_policy @@ -1153,6 +1157,9 @@ static int fl_set_geneve_opt(const struct nlattr *nla, struct fl_flow_key *key, if (option_len > sizeof(struct geneve_opt)) data_len = option_len - sizeof(struct geneve_opt); + if (key->enc_opts.len > FLOW_DIS_TUN_OPTS_MAX - 4) + return -ERANGE; + opt = (struct geneve_opt *)&key->enc_opts.data[key->enc_opts.len]; memset(opt, 0xff, option_len); opt->length = data_len / 4; @@ -1668,6 +1675,10 @@ static int fl_set_key(struct net *net, struct nlattr **tb, mask->meta.ingress_ifindex = 0xffffffff; } + fl_set_key_val(tb, &key->meta.l2_miss, TCA_FLOWER_L2_MISS, + &mask->meta.l2_miss, TCA_FLOWER_UNSPEC, + sizeof(key->meta.l2_miss)); + fl_set_key_val(tb, key->eth.dst, TCA_FLOWER_KEY_ETH_DST, mask->eth.dst, TCA_FLOWER_KEY_ETH_DST_MASK, sizeof(key->eth.dst)); @@ -2085,6 +2096,11 @@ errout_cleanup: return ret; } +static bool fl_needs_tc_skb_ext(const struct fl_flow_key *mask) +{ + return mask->meta.l2_miss; +} + static int fl_set_parms(struct net *net, struct tcf_proto *tp, struct cls_fl_filter *f, struct fl_flow_mask *mask, unsigned long base, struct nlattr **tb, @@ -2121,6 +2137,14 @@ static int fl_set_parms(struct net *net, struct tcf_proto *tp, return -EINVAL; } + /* Enable tc skb extension if filter matches on data extracted from + * this extension. + */ + if (fl_needs_tc_skb_ext(&mask->key)) { + f->needs_tc_skb_ext = 1; + tc_skb_ext_tc_enable(); + } + return 0; } @@ -3074,6 +3098,11 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net, goto nla_put_failure; } + if (fl_dump_key_val(skb, &key->meta.l2_miss, + TCA_FLOWER_L2_MISS, &mask->meta.l2_miss, + TCA_FLOWER_UNSPEC, sizeof(key->meta.l2_miss))) + goto nla_put_failure; + if (fl_dump_key_val(skb, key->eth.dst, TCA_FLOWER_KEY_ETH_DST, mask->eth.dst, TCA_FLOWER_KEY_ETH_DST_MASK, sizeof(key->eth.dst)) || diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index fdb8f429333d..e4b6452318c0 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -309,7 +309,7 @@ struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle) if (dev_ingress_queue(dev)) q = qdisc_match_from_root( - dev_ingress_queue(dev)->qdisc_sleeping, + rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping), handle); out: return q; @@ -328,7 +328,8 @@ struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle) nq = dev_ingress_queue_rcu(dev); if (nq) - q = qdisc_match_from_root(nq->qdisc_sleeping, handle); + q = qdisc_match_from_root(rcu_dereference(nq->qdisc_sleeping), + handle); out: return q; } @@ -634,8 +635,13 @@ EXPORT_SYMBOL(qdisc_watchdog_init); void qdisc_watchdog_schedule_range_ns(struct qdisc_watchdog *wd, u64 expires, u64 delta_ns) { - if (test_bit(__QDISC_STATE_DEACTIVATED, - &qdisc_root_sleeping(wd->qdisc)->state)) + bool deactivated; + + rcu_read_lock(); + deactivated = test_bit(__QDISC_STATE_DEACTIVATED, + &qdisc_root_sleeping(wd->qdisc)->state); + rcu_read_unlock(); + if (deactivated) return; if (hrtimer_is_queued(&wd->timer)) { @@ -1252,7 +1258,12 @@ static struct Qdisc *qdisc_create(struct net_device *dev, sch->parent = parent; if (handle == TC_H_INGRESS) { - sch->flags |= TCQ_F_INGRESS; + if (!(sch->flags & TCQ_F_INGRESS)) { + NL_SET_ERR_MSG(extack, + "Specified parent ID is reserved for ingress and clsact Qdiscs"); + err = -EINVAL; + goto err_out3; + } handle = TC_H_MAKE(TC_H_INGRESS, 0); } else { if (handle == 0) { @@ -1473,7 +1484,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, } q = qdisc_leaf(p, clid); } else if (dev_ingress_queue(dev)) { - q = dev_ingress_queue(dev)->qdisc_sleeping; + q = rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping); } } else { q = rtnl_dereference(dev->qdisc); @@ -1559,7 +1570,7 @@ replay: } q = qdisc_leaf(p, clid); } else if (dev_ingress_queue_create(dev)) { - q = dev_ingress_queue(dev)->qdisc_sleeping; + q = rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping); } } else { q = rtnl_dereference(dev->qdisc); @@ -1591,11 +1602,20 @@ replay: NL_SET_ERR_MSG(extack, "Invalid qdisc name"); return -EINVAL; } + if (q->flags & TCQ_F_INGRESS) { + NL_SET_ERR_MSG(extack, + "Cannot regraft ingress or clsact Qdiscs"); + return -EINVAL; + } if (q == p || (p && check_loop(q, p, 0))) { NL_SET_ERR_MSG(extack, "Qdisc parent/child loop detected"); return -ELOOP; } + if (clid == TC_H_INGRESS) { + NL_SET_ERR_MSG(extack, "Ingress cannot graft directly"); + return -EINVAL; + } qdisc_refcount_inc(q); goto graft; } else { @@ -1791,8 +1811,8 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) dev_queue = dev_ingress_queue(dev); if (dev_queue && - tc_dump_qdisc_root(dev_queue->qdisc_sleeping, skb, cb, - &q_idx, s_q_idx, false, + tc_dump_qdisc_root(rtnl_dereference(dev_queue->qdisc_sleeping), + skb, cb, &q_idx, s_q_idx, false, tca[TCA_DUMP_INVISIBLE]) < 0) goto done; @@ -2235,8 +2255,8 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) dev_queue = dev_ingress_queue(dev); if (dev_queue && - tc_dump_tclass_root(dev_queue->qdisc_sleeping, skb, tcm, cb, - &t, s_t, false) < 0) + tc_dump_tclass_root(rtnl_dereference(dev_queue->qdisc_sleeping), + skb, tcm, cb, &t, s_t, false) < 0) goto done; done: @@ -2288,7 +2308,9 @@ static struct pernet_operations psched_net_ops = { .exit = psched_net_exit, }; +#if IS_ENABLED(CONFIG_RETPOLINE) DEFINE_STATIC_KEY_FALSE(tc_skip_wrapper); +#endif static int __init pktsched_init(void) { diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index 6980796d435d..591d87d5e5c0 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -201,6 +201,11 @@ out: return NET_XMIT_CN; } +static struct netlink_range_validation fq_pie_q_range = { + .min = 1, + .max = 1 << 20, +}; + static const struct nla_policy fq_pie_policy[TCA_FQ_PIE_MAX + 1] = { [TCA_FQ_PIE_LIMIT] = {.type = NLA_U32}, [TCA_FQ_PIE_FLOWS] = {.type = NLA_U32}, @@ -208,7 +213,8 @@ static const struct nla_policy fq_pie_policy[TCA_FQ_PIE_MAX + 1] = { [TCA_FQ_PIE_TUPDATE] = {.type = NLA_U32}, [TCA_FQ_PIE_ALPHA] = {.type = NLA_U32}, [TCA_FQ_PIE_BETA] = {.type = NLA_U32}, - [TCA_FQ_PIE_QUANTUM] = {.type = NLA_U32}, + [TCA_FQ_PIE_QUANTUM] = + NLA_POLICY_FULL_RANGE(NLA_U32, &fq_pie_q_range), [TCA_FQ_PIE_MEMORY_LIMIT] = {.type = NLA_U32}, [TCA_FQ_PIE_ECN_PROB] = {.type = NLA_U32}, [TCA_FQ_PIE_ECN] = {.type = NLA_U32}, @@ -373,6 +379,7 @@ static void fq_pie_timer(struct timer_list *t) spinlock_t *root_lock; /* to lock qdisc for probability calculations */ u32 idx; + rcu_read_lock(); root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); @@ -385,6 +392,7 @@ static void fq_pie_timer(struct timer_list *t) mod_timer(&q->adapt_timer, jiffies + q->p_params.tupdate); spin_unlock(root_lock); + rcu_read_unlock(); } static int fq_pie_init(struct Qdisc *sch, struct nlattr *opt, diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 37e41f972f69..3248259eba32 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -648,7 +648,7 @@ struct Qdisc_ops noop_qdisc_ops __read_mostly = { static struct netdev_queue noop_netdev_queue = { RCU_POINTER_INITIALIZER(qdisc, &noop_qdisc), - .qdisc_sleeping = &noop_qdisc, + RCU_POINTER_INITIALIZER(qdisc_sleeping, &noop_qdisc), }; struct Qdisc noop_qdisc = { @@ -1103,7 +1103,7 @@ EXPORT_SYMBOL(qdisc_put_unlocked); struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, struct Qdisc *qdisc) { - struct Qdisc *oqdisc = dev_queue->qdisc_sleeping; + struct Qdisc *oqdisc = rtnl_dereference(dev_queue->qdisc_sleeping); spinlock_t *root_lock; root_lock = qdisc_lock(oqdisc); @@ -1112,7 +1112,7 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, /* ... and graft new one */ if (qdisc == NULL) qdisc = &noop_qdisc; - dev_queue->qdisc_sleeping = qdisc; + rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc); rcu_assign_pointer(dev_queue->qdisc, &noop_qdisc); spin_unlock_bh(root_lock); @@ -1125,12 +1125,12 @@ static void shutdown_scheduler_queue(struct net_device *dev, struct netdev_queue *dev_queue, void *_qdisc_default) { - struct Qdisc *qdisc = dev_queue->qdisc_sleeping; + struct Qdisc *qdisc = rtnl_dereference(dev_queue->qdisc_sleeping); struct Qdisc *qdisc_default = _qdisc_default; if (qdisc) { rcu_assign_pointer(dev_queue->qdisc, qdisc_default); - dev_queue->qdisc_sleeping = qdisc_default; + rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc_default); qdisc_put(qdisc); } @@ -1154,7 +1154,7 @@ static void attach_one_default_qdisc(struct net_device *dev, if (!netif_is_multiqueue(dev)) qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; - dev_queue->qdisc_sleeping = qdisc; + rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc); } static void attach_default_qdiscs(struct net_device *dev) @@ -1167,7 +1167,7 @@ static void attach_default_qdiscs(struct net_device *dev) if (!netif_is_multiqueue(dev) || dev->priv_flags & IFF_NO_QUEUE) { netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL); - qdisc = txq->qdisc_sleeping; + qdisc = rtnl_dereference(txq->qdisc_sleeping); rcu_assign_pointer(dev->qdisc, qdisc); qdisc_refcount_inc(qdisc); } else { @@ -1186,7 +1186,7 @@ static void attach_default_qdiscs(struct net_device *dev) netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc); dev->priv_flags |= IFF_NO_QUEUE; netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL); - qdisc = txq->qdisc_sleeping; + qdisc = rtnl_dereference(txq->qdisc_sleeping); rcu_assign_pointer(dev->qdisc, qdisc); qdisc_refcount_inc(qdisc); dev->priv_flags ^= IFF_NO_QUEUE; @@ -1202,7 +1202,7 @@ static void transition_one_qdisc(struct net_device *dev, struct netdev_queue *dev_queue, void *_need_watchdog) { - struct Qdisc *new_qdisc = dev_queue->qdisc_sleeping; + struct Qdisc *new_qdisc = rtnl_dereference(dev_queue->qdisc_sleeping); int *need_watchdog_p = _need_watchdog; if (!(new_qdisc->flags & TCQ_F_BUILTIN)) @@ -1272,7 +1272,7 @@ static void dev_reset_queue(struct net_device *dev, struct Qdisc *qdisc; bool nolock; - qdisc = dev_queue->qdisc_sleeping; + qdisc = rtnl_dereference(dev_queue->qdisc_sleeping); if (!qdisc) return; @@ -1303,7 +1303,7 @@ static bool some_qdisc_is_busy(struct net_device *dev) int val; dev_queue = netdev_get_tx_queue(dev, i); - q = dev_queue->qdisc_sleeping; + q = rtnl_dereference(dev_queue->qdisc_sleeping); root_lock = qdisc_lock(q); spin_lock_bh(root_lock); @@ -1379,7 +1379,7 @@ EXPORT_SYMBOL(dev_deactivate); static int qdisc_change_tx_queue_len(struct net_device *dev, struct netdev_queue *dev_queue) { - struct Qdisc *qdisc = dev_queue->qdisc_sleeping; + struct Qdisc *qdisc = rtnl_dereference(dev_queue->qdisc_sleeping); const struct Qdisc_ops *ops = qdisc->ops; if (ops->change_tx_queue_len) @@ -1404,7 +1404,7 @@ void mq_change_real_num_tx(struct Qdisc *sch, unsigned int new_real_tx) unsigned int i; for (i = new_real_tx; i < dev->real_num_tx_queues; i++) { - qdisc = netdev_get_tx_queue(dev, i)->qdisc_sleeping; + qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc_sleeping); /* Only update the default qdiscs we created, * qdiscs with handles are always hashed. */ @@ -1412,7 +1412,7 @@ void mq_change_real_num_tx(struct Qdisc *sch, unsigned int new_real_tx) qdisc_hash_del(qdisc); } for (i = dev->real_num_tx_queues; i < new_real_tx; i++) { - qdisc = netdev_get_tx_queue(dev, i)->qdisc_sleeping; + qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc_sleeping); if (qdisc != &noop_qdisc && !qdisc->handle) qdisc_hash_add(qdisc, false); } @@ -1449,7 +1449,7 @@ static void dev_init_scheduler_queue(struct net_device *dev, struct Qdisc *qdisc = _qdisc; rcu_assign_pointer(dev_queue->qdisc, qdisc); - dev_queue->qdisc_sleeping = qdisc; + rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc); } void dev_init_scheduler(struct net_device *dev) diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 8aef7dd9fb88..325c29041c7d 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1814,10 +1814,6 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, NL_SET_ERR_MSG(extack, "HTB offload doesn't support the quantum parameter"); goto failure; } - if (hopt->prio) { - NL_SET_ERR_MSG(extack, "HTB offload doesn't support the prio parameter"); - goto failure; - } } /* Keeping backward compatible with rate_table based iproute2 tc */ @@ -1913,6 +1909,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, TC_HTB_CLASSID_ROOT, .rate = max_t(u64, hopt->rate.rate, rate64), .ceil = max_t(u64, hopt->ceil.rate, ceil64), + .prio = hopt->prio, .extack = extack, }; err = htb_offload(dev, &offload_opt); @@ -1933,6 +1930,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, TC_H_MIN(parent->common.classid), .rate = max_t(u64, hopt->rate.rate, rate64), .ceil = max_t(u64, hopt->ceil.rate, ceil64), + .prio = hopt->prio, .extack = extack, }; err = htb_offload(dev, &offload_opt); @@ -2018,6 +2016,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, .classid = cl->common.classid, .rate = max_t(u64, hopt->rate.rate, rate64), .ceil = max_t(u64, hopt->ceil.rate, ceil64), + .prio = hopt->prio, .extack = extack, }; err = htb_offload(dev, &offload_opt); diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index 84838128b9c5..e43a45499372 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -80,6 +80,9 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt, struct net_device *dev = qdisc_dev(sch); int err; + if (sch->parent != TC_H_INGRESS) + return -EOPNOTSUPP; + net_inc_ingress_queue(); mini_qdisc_pair_init(&q->miniqp, sch, &dev->miniq_ingress); @@ -101,6 +104,9 @@ static void ingress_destroy(struct Qdisc *sch) { struct ingress_sched_data *q = qdisc_priv(sch); + if (sch->parent != TC_H_INGRESS) + return; + tcf_block_put_ext(q->block, sch, &q->block_info); net_dec_ingress_queue(); } @@ -134,7 +140,7 @@ static struct Qdisc_ops ingress_qdisc_ops __read_mostly = { .cl_ops = &ingress_class_ops, .id = "ingress", .priv_size = sizeof(struct ingress_sched_data), - .static_flags = TCQ_F_CPUSTATS, + .static_flags = TCQ_F_INGRESS | TCQ_F_CPUSTATS, .init = ingress_init, .destroy = ingress_destroy, .dump = ingress_dump, @@ -219,6 +225,9 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt, struct net_device *dev = qdisc_dev(sch); int err; + if (sch->parent != TC_H_CLSACT) + return -EOPNOTSUPP; + net_inc_ingress_queue(); net_inc_egress_queue(); @@ -248,6 +257,9 @@ static void clsact_destroy(struct Qdisc *sch) { struct clsact_sched_data *q = qdisc_priv(sch); + if (sch->parent != TC_H_CLSACT) + return; + tcf_block_put_ext(q->egress_block, sch, &q->egress_block_info); tcf_block_put_ext(q->ingress_block, sch, &q->ingress_block_info); @@ -269,7 +281,7 @@ static struct Qdisc_ops clsact_qdisc_ops __read_mostly = { .cl_ops = &clsact_class_ops, .id = "clsact", .priv_size = sizeof(struct clsact_sched_data), - .static_flags = TCQ_F_CPUSTATS, + .static_flags = TCQ_F_INGRESS | TCQ_F_CPUSTATS, .init = clsact_init, .destroy = clsact_destroy, .dump = ingress_dump, diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index d0bc660d7401..c860119a8f09 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -141,7 +141,7 @@ static int mq_dump(struct Qdisc *sch, struct sk_buff *skb) * qdisc totals are added at end. */ for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { - qdisc = netdev_get_tx_queue(dev, ntx)->qdisc_sleeping; + qdisc = rtnl_dereference(netdev_get_tx_queue(dev, ntx)->qdisc_sleeping); spin_lock_bh(qdisc_lock(qdisc)); gnet_stats_add_basic(&sch->bstats, qdisc->cpu_bstats, @@ -202,7 +202,7 @@ static struct Qdisc *mq_leaf(struct Qdisc *sch, unsigned long cl) { struct netdev_queue *dev_queue = mq_queue_get(sch, cl); - return dev_queue->qdisc_sleeping; + return rtnl_dereference(dev_queue->qdisc_sleeping); } static unsigned long mq_find(struct Qdisc *sch, u32 classid) @@ -221,7 +221,7 @@ static int mq_dump_class(struct Qdisc *sch, unsigned long cl, tcm->tcm_parent = TC_H_ROOT; tcm->tcm_handle |= TC_H_MIN(cl); - tcm->tcm_info = dev_queue->qdisc_sleeping->handle; + tcm->tcm_info = rtnl_dereference(dev_queue->qdisc_sleeping)->handle; return 0; } @@ -230,7 +230,7 @@ static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl, { struct netdev_queue *dev_queue = mq_queue_get(sch, cl); - sch = dev_queue->qdisc_sleeping; + sch = rtnl_dereference(dev_queue->qdisc_sleeping); if (gnet_stats_copy_basic(d, sch->cpu_bstats, &sch->bstats, true) < 0 || qdisc_qstats_copy(d, sch) < 0) return -1; diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index dc5a0ff50b14..ab69ff7577fc 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -557,7 +557,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) * qdisc totals are added at end. */ for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { - qdisc = netdev_get_tx_queue(dev, ntx)->qdisc_sleeping; + qdisc = rtnl_dereference(netdev_get_tx_queue(dev, ntx)->qdisc_sleeping); spin_lock_bh(qdisc_lock(qdisc)); gnet_stats_add_basic(&sch->bstats, qdisc->cpu_bstats, @@ -604,7 +604,7 @@ static struct Qdisc *mqprio_leaf(struct Qdisc *sch, unsigned long cl) if (!dev_queue) return NULL; - return dev_queue->qdisc_sleeping; + return rtnl_dereference(dev_queue->qdisc_sleeping); } static unsigned long mqprio_find(struct Qdisc *sch, u32 classid) @@ -637,7 +637,7 @@ static int mqprio_dump_class(struct Qdisc *sch, unsigned long cl, tcm->tcm_parent = (tc < 0) ? 0 : TC_H_MAKE(TC_H_MAJ(sch->handle), TC_H_MIN(tc + TC_H_MIN_PRIORITY)); - tcm->tcm_info = dev_queue->qdisc_sleeping->handle; + tcm->tcm_info = rtnl_dereference(dev_queue->qdisc_sleeping)->handle; } else { tcm->tcm_parent = TC_H_ROOT; tcm->tcm_info = 0; @@ -693,7 +693,7 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, } else { struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); - sch = dev_queue->qdisc_sleeping; + sch = rtnl_dereference(dev_queue->qdisc_sleeping); if (gnet_stats_copy_basic(d, sch->cpu_bstats, &sch->bstats, true) < 0 || qdisc_qstats_copy(d, sch) < 0) diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index 2152a56d73f8..2da6250ec346 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -421,8 +421,10 @@ static void pie_timer(struct timer_list *t) { struct pie_sched_data *q = from_timer(q, t, adapt_timer); struct Qdisc *sch = q->sch; - spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); + spinlock_t *root_lock; + rcu_read_lock(); + root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); pie_calculate_probability(&q->params, &q->vars, sch->qstats.backlog); @@ -430,6 +432,7 @@ static void pie_timer(struct timer_list *t) if (q->params.tupdate) mod_timer(&q->adapt_timer, jiffies + q->params.tupdate); spin_unlock(root_lock); + rcu_read_unlock(); } static int pie_init(struct Qdisc *sch, struct nlattr *opt, diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 98129324e157..16277b6a0238 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -321,12 +321,15 @@ static inline void red_adaptative_timer(struct timer_list *t) { struct red_sched_data *q = from_timer(q, t, adapt_timer); struct Qdisc *sch = q->sch; - spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); + spinlock_t *root_lock; + rcu_read_lock(); + root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); red_adaptative_algo(&q->parms, &q->vars); mod_timer(&q->adapt_timer, jiffies + HZ/2); spin_unlock(root_lock); + rcu_read_unlock(); } static int red_init(struct Qdisc *sch, struct nlattr *opt, diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index abd436307d6a..66dcb18638fe 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -606,10 +606,12 @@ static void sfq_perturbation(struct timer_list *t) { struct sfq_sched_data *q = from_timer(q, t, perturb_timer); struct Qdisc *sch = q->sch; - spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); + spinlock_t *root_lock; siphash_key_t nkey; get_random_bytes(&nkey, sizeof(nkey)); + rcu_read_lock(); + root_lock = qdisc_lock(qdisc_root_sleeping(sch)); spin_lock(root_lock); q->perturbation = nkey; if (!q->filter_list && q->tail) @@ -618,6 +620,7 @@ static void sfq_perturbation(struct timer_list *t) if (q->perturb_period) mod_timer(&q->perturb_timer, jiffies + q->perturb_period); + rcu_read_unlock(); } static int sfq_change(struct Qdisc *sch, struct nlattr *opt) diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 76db9a10ef50..5076da103f63 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -27,6 +27,8 @@ #include <net/sock.h> #include <net/tcp.h> +#define TAPRIO_STAT_NOT_SET (~0ULL) + #include "sch_mqprio_lib.h" static LIST_HEAD(taprio_list); @@ -1524,7 +1526,7 @@ static int taprio_enable_offload(struct net_device *dev, "Not enough memory for enabling offload mode"); return -ENOMEM; } - offload->enable = 1; + offload->cmd = TAPRIO_CMD_REPLACE; offload->extack = extack; mqprio_qopt_reconstruct(dev, &offload->mqprio.qopt); offload->mqprio.extack = extack; @@ -1572,7 +1574,7 @@ static int taprio_disable_offload(struct net_device *dev, "Not enough memory to disable offload mode"); return -ENOMEM; } - offload->enable = 0; + offload->cmd = TAPRIO_CMD_DESTROY; err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TAPRIO, offload); if (err < 0) { @@ -2289,6 +2291,72 @@ nla_put_failure: return -EMSGSIZE; } +static int taprio_put_stat(struct sk_buff *skb, u64 val, u16 attrtype) +{ + if (val == TAPRIO_STAT_NOT_SET) + return 0; + if (nla_put_u64_64bit(skb, attrtype, val, TCA_TAPRIO_OFFLOAD_STATS_PAD)) + return -EMSGSIZE; + return 0; +} + +static int taprio_dump_xstats(struct Qdisc *sch, struct gnet_dump *d, + struct tc_taprio_qopt_offload *offload, + struct tc_taprio_qopt_stats *stats) +{ + struct net_device *dev = qdisc_dev(sch); + const struct net_device_ops *ops; + struct sk_buff *skb = d->skb; + struct nlattr *xstats; + int err; + + ops = qdisc_dev(sch)->netdev_ops; + + /* FIXME I could use qdisc_offload_dump_helper(), but that messes + * with sch->flags depending on whether the device reports taprio + * stats, and I'm not sure whether that's a good idea, considering + * that stats are optional to the offload itself + */ + if (!ops->ndo_setup_tc) + return 0; + + memset(stats, 0xff, sizeof(*stats)); + + err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TAPRIO, offload); + if (err == -EOPNOTSUPP) + return 0; + if (err) + return err; + + xstats = nla_nest_start(skb, TCA_STATS_APP); + if (!xstats) + goto err; + + if (taprio_put_stat(skb, stats->window_drops, + TCA_TAPRIO_OFFLOAD_STATS_WINDOW_DROPS) || + taprio_put_stat(skb, stats->tx_overruns, + TCA_TAPRIO_OFFLOAD_STATS_TX_OVERRUNS)) + goto err_cancel; + + nla_nest_end(skb, xstats); + + return 0; + +err_cancel: + nla_nest_cancel(skb, xstats); +err: + return -EMSGSIZE; +} + +static int taprio_dump_stats(struct Qdisc *sch, struct gnet_dump *d) +{ + struct tc_taprio_qopt_offload offload = { + .cmd = TAPRIO_CMD_STATS, + }; + + return taprio_dump_xstats(sch, d, &offload, &offload.stats); +} + static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb) { struct taprio_sched *q = qdisc_priv(sch); @@ -2358,7 +2426,7 @@ static struct Qdisc *taprio_leaf(struct Qdisc *sch, unsigned long cl) if (!dev_queue) return NULL; - return dev_queue->qdisc_sleeping; + return rtnl_dereference(dev_queue->qdisc_sleeping); } static unsigned long taprio_find(struct Qdisc *sch, u32 classid) @@ -2377,7 +2445,7 @@ static int taprio_dump_class(struct Qdisc *sch, unsigned long cl, tcm->tcm_parent = TC_H_ROOT; tcm->tcm_handle |= TC_H_MIN(cl); - tcm->tcm_info = dev_queue->qdisc_sleeping->handle; + tcm->tcm_info = rtnl_dereference(dev_queue->qdisc_sleeping)->handle; return 0; } @@ -2388,12 +2456,20 @@ static int taprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, __acquires(d->lock) { struct netdev_queue *dev_queue = taprio_queue_get(sch, cl); + struct tc_taprio_qopt_offload offload = { + .cmd = TAPRIO_CMD_TC_STATS, + .tc_stats = { + .tc = cl - 1, + }, + }; + struct Qdisc *child; - sch = dev_queue->qdisc_sleeping; - if (gnet_stats_copy_basic(d, NULL, &sch->bstats, true) < 0 || - qdisc_qstats_copy(d, sch) < 0) + child = rtnl_dereference(dev_queue->qdisc_sleeping); + if (gnet_stats_copy_basic(d, NULL, &child->bstats, true) < 0 || + qdisc_qstats_copy(d, child) < 0) return -1; - return 0; + + return taprio_dump_xstats(sch, d, &offload, &offload.tc_stats.stats); } static void taprio_walk(struct Qdisc *sch, struct qdisc_walker *arg) @@ -2440,6 +2516,7 @@ static struct Qdisc_ops taprio_qdisc_ops __read_mostly = { .dequeue = taprio_dequeue, .enqueue = taprio_enqueue, .dump = taprio_dump, + .dump_stats = taprio_dump_stats, .owner = THIS_MODULE, }; diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 16f9238aa51d..7721239c185f 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -297,7 +297,7 @@ restart: struct net_device *slave = qdisc_dev(q); struct netdev_queue *slave_txq = netdev_get_tx_queue(slave, 0); - if (slave_txq->qdisc_sleeping != q) + if (rcu_access_pointer(slave_txq->qdisc_sleeping) != q) continue; if (netif_xmit_stopped(netdev_get_tx_queue(slave, subq)) || !netif_running(slave)) { diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index c365df24ad33..664d1f2e9121 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -500,9 +500,7 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr, continue; fl4->fl4_sport = laddr->a.v4.sin_port; - flowi4_update_output(fl4, - asoc->base.sk->sk_bound_dev_if, - RT_CONN_FLAGS_TOS(asoc->base.sk, tos), + flowi4_update_output(fl4, asoc->base.sk->sk_bound_dev_if, daddr->v4.sin_addr.s_addr, laddr->a.v4.sin_addr.s_addr); diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 2f66a2006517..2abe45af98e7 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -324,9 +324,12 @@ bool sctp_transport_pl_recv(struct sctp_transport *t) t->pl.probe_size += SCTP_PL_BIG_STEP; } else if (t->pl.state == SCTP_PL_SEARCH) { if (!t->pl.probe_high) { - t->pl.probe_size = min(t->pl.probe_size + SCTP_PL_BIG_STEP, - SCTP_MAX_PLPMTU); - return false; + if (t->pl.probe_size < SCTP_MAX_PLPMTU) { + t->pl.probe_size = min(t->pl.probe_size + SCTP_PL_BIG_STEP, + SCTP_MAX_PLPMTU); + return false; + } + t->pl.probe_high = SCTP_MAX_PLPMTU; } t->pl.probe_size += SCTP_PL_MIN_STEP; if (t->pl.probe_size >= t->pl.probe_high) { @@ -341,7 +344,7 @@ bool sctp_transport_pl_recv(struct sctp_transport *t) } else if (t->pl.state == SCTP_PL_COMPLETE) { /* Raise probe_size again after 30 * interval in Search Complete */ t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */ - t->pl.probe_size += SCTP_PL_MIN_STEP; + t->pl.probe_size = min(t->pl.probe_size + SCTP_PL_MIN_STEP, SCTP_MAX_PLPMTU); } return t->pl.state == SCTP_PL_COMPLETE; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 50c38b624f77..538e9c6ec8c9 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -2000,8 +2000,10 @@ static int smc_listen_rdma_init(struct smc_sock *new_smc, return rc; /* create send buffer and rmb */ - if (smc_buf_create(new_smc, false)) + if (smc_buf_create(new_smc, false)) { + smc_conn_abort(new_smc, ini->first_contact_local); return SMC_CLC_DECL_MEM; + } return 0; } @@ -2217,8 +2219,11 @@ static void smc_find_rdma_v2_device_serv(struct smc_sock *new_smc, smcr_version = ini->smcr_version; ini->smcr_version = SMC_V2; rc = smc_listen_rdma_init(new_smc, ini); - if (!rc) + if (!rc) { rc = smc_listen_rdma_reg(new_smc, ini->first_contact_local); + if (rc) + smc_conn_abort(new_smc, ini->first_contact_local); + } if (!rc) return; ini->smcr_version = smcr_version; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 454356771cda..3f465faf2b68 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -127,6 +127,7 @@ static int smcr_lgr_conn_assign_link(struct smc_connection *conn, bool first) int i, j; /* do link balancing */ + conn->lnk = NULL; /* reset conn->lnk first */ for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { struct smc_link *lnk = &conn->lgr->lnk[i]; diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index a0840b8c935b..90f0b60b196a 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -578,7 +578,10 @@ static struct smc_buf_desc *smc_llc_get_next_rmb(struct smc_link_group *lgr, { struct smc_buf_desc *buf_next; - if (!buf_pos || list_is_last(&buf_pos->list, &lgr->rmbs[*buf_lst])) { + if (!buf_pos) + return _smc_llc_get_next_rmb(lgr, buf_lst); + + if (list_is_last(&buf_pos->list, &lgr->rmbs[*buf_lst])) { (*buf_lst)++; return _smc_llc_get_next_rmb(lgr, buf_lst); } @@ -614,6 +617,8 @@ static int smc_llc_fill_ext_v2(struct smc_llc_msg_add_link_v2_ext *ext, goto out; buf_pos = smc_llc_get_first_rmb(lgr, &buf_lst); for (i = 0; i < ext->num_rkeys; i++) { + while (buf_pos && !(buf_pos)->used) + buf_pos = smc_llc_get_next_rmb(lgr, &buf_lst, buf_pos); if (!buf_pos) break; rmb = buf_pos; @@ -623,8 +628,6 @@ static int smc_llc_fill_ext_v2(struct smc_llc_msg_add_link_v2_ext *ext, cpu_to_be64((uintptr_t)rmb->cpu_addr) : cpu_to_be64((u64)sg_dma_address(rmb->sgt[lnk_idx].sgl)); buf_pos = smc_llc_get_next_rmb(lgr, &buf_lst, buf_pos); - while (buf_pos && !(buf_pos)->used) - buf_pos = smc_llc_get_next_rmb(lgr, &buf_lst, buf_pos); } len += i * sizeof(ext->rt[0]); out: @@ -848,6 +851,8 @@ static int smc_llc_add_link_cont(struct smc_link *link, addc_llc->num_rkeys = *num_rkeys_todo; n = *num_rkeys_todo; for (i = 0; i < min_t(u8, n, SMC_LLC_RKEYS_PER_CONT_MSG); i++) { + while (*buf_pos && !(*buf_pos)->used) + *buf_pos = smc_llc_get_next_rmb(lgr, buf_lst, *buf_pos); if (!*buf_pos) { addc_llc->num_rkeys = addc_llc->num_rkeys - *num_rkeys_todo; @@ -864,8 +869,6 @@ static int smc_llc_add_link_cont(struct smc_link *link, (*num_rkeys_todo)--; *buf_pos = smc_llc_get_next_rmb(lgr, buf_lst, *buf_pos); - while (*buf_pos && !(*buf_pos)->used) - *buf_pos = smc_llc_get_next_rmb(lgr, buf_lst, *buf_pos); } addc_llc->hd.common.llc_type = SMC_LLC_ADD_LINK_CONT; addc_llc->hd.length = sizeof(struct smc_llc_msg_add_link_cont); diff --git a/net/socket.c b/net/socket.c index b7e01d0fe082..b778fc03c6e0 100644 --- a/net/socket.c +++ b/net/socket.c @@ -57,6 +57,7 @@ #include <linux/mm.h> #include <linux/socket.h> #include <linux/file.h> +#include <linux/splice.h> #include <linux/net.h> #include <linux/interrupt.h> #include <linux/thread_info.h> @@ -126,11 +127,10 @@ static long compat_sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #endif static int sock_fasync(int fd, struct file *filp, int on); -static ssize_t sock_sendpage(struct file *file, struct page *page, - int offset, size_t size, loff_t *ppos, int more); static ssize_t sock_splice_read(struct file *file, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); +static void sock_splice_eof(struct file *file); #ifdef CONFIG_PROC_FS static void sock_show_fdinfo(struct seq_file *m, struct file *f) @@ -162,9 +162,9 @@ static const struct file_operations socket_file_ops = { .mmap = sock_mmap, .release = sock_close, .fasync = sock_fasync, - .sendpage = sock_sendpage, - .splice_write = generic_splice_sendpage, + .splice_write = splice_to_socket, .splice_read = sock_splice_read, + .splice_eof = sock_splice_eof, .show_fdinfo = sock_show_fdinfo, }; @@ -1066,26 +1066,6 @@ int kernel_recvmsg(struct socket *sock, struct msghdr *msg, } EXPORT_SYMBOL(kernel_recvmsg); -static ssize_t sock_sendpage(struct file *file, struct page *page, - int offset, size_t size, loff_t *ppos, int more) -{ - struct socket *sock; - int flags; - int ret; - - sock = file->private_data; - - flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0; - /* more is a combination of MSG_MORE and MSG_SENDPAGE_NOTLAST */ - flags |= more; - - ret = kernel_sendpage(sock, page, offset, size, flags); - - if (trace_sock_send_length_enabled()) - call_trace_sock_send_length(sock->sk, ret, 0); - return ret; -} - static ssize_t sock_splice_read(struct file *file, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) @@ -1098,6 +1078,14 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos, return sock->ops->splice_read(sock, ppos, pipe, len, flags); } +static void sock_splice_eof(struct file *file) +{ + struct socket *sock = file->private_data; + + if (sock->ops->splice_eof) + sock->ops->splice_eof(sock); +} + static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; @@ -2138,6 +2126,7 @@ int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, msg.msg_name = (struct sockaddr *)&address; msg.msg_namelen = addr_len; } + flags &= ~MSG_INTERNAL_SENDMSG_FLAGS; if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; msg.msg_flags = flags; @@ -2483,6 +2472,7 @@ static int ____sys_sendmsg(struct socket *sock, struct msghdr *msg_sys, msg_sys->msg_control = ctl_buf; msg_sys->msg_control_is_user = false; } + flags &= ~MSG_INTERNAL_SENDMSG_FLAGS; msg_sys->msg_flags = flags; if (sock->file->f_flags & O_NONBLOCK) diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index 212c5d57465a..9734e1d9f991 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -639,6 +639,16 @@ gss_krb5_cts_crypt(struct crypto_sync_skcipher *cipher, struct xdr_buf *buf, ret = write_bytes_to_xdr_buf(buf, offset, data, len); +#if IS_ENABLED(CONFIG_KUNIT) + /* + * CBC-CTS does not define an output IV but RFC 3962 defines it as the + * penultimate block of ciphertext, so copy that into the IV buffer + * before returning. + */ + if (encrypt) + memcpy(iv, data, crypto_sync_skcipher_ivsize(cipher)); +#endif + out: kfree(data); return ret; diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index c8321de341ee..6debf4fd42d4 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -927,11 +927,10 @@ static void __rpc_execute(struct rpc_task *task) */ do_action = task->tk_action; /* Tasks with an RPC error status should exit */ - if (do_action != rpc_exit_task && + if (do_action && do_action != rpc_exit_task && (status = READ_ONCE(task->tk_rpc_status)) != 0) { task->tk_status = status; - if (do_action != NULL) - do_action = rpc_exit_task; + do_action = rpc_exit_task; } /* Callbacks override all actions */ if (task->tk_callback) { diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 26367cf4c17a..79967b6925bd 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1052,7 +1052,7 @@ static int __svc_register(struct net *net, const char *progname, #endif } - trace_svc_register(progname, version, protocol, port, family, error); + trace_svc_register(progname, version, family, protocol, port, error); return error; } @@ -1416,7 +1416,7 @@ err_bad_rpc: /* Only RPCv2 supported */ xdr_stream_encode_u32(xdr, RPC_VERSION); xdr_stream_encode_u32(xdr, RPC_VERSION); - goto sendit; + return 1; /* don't wrap */ err_bad_auth: dprintk("svc: authentication failed (%d)\n", @@ -1432,7 +1432,7 @@ err_bad_auth: err_bad_prog: dprintk("svc: unknown program %d\n", rqstp->rq_prog); serv->sv_stats->rpcbadfmt++; - xdr_stream_encode_u32(xdr, RPC_PROG_UNAVAIL); + *rqstp->rq_accept_statp = rpc_prog_unavail; goto sendit; err_bad_vers: @@ -1440,7 +1440,12 @@ err_bad_vers: rqstp->rq_vers, rqstp->rq_prog, progp->pg_name); serv->sv_stats->rpcbadfmt++; - xdr_stream_encode_u32(xdr, RPC_PROG_MISMATCH); + *rqstp->rq_accept_statp = rpc_prog_mismatch; + + /* + * svc_authenticate() has already added the verifier and + * advanced the stream just past rq_accept_statp. + */ xdr_stream_encode_u32(xdr, process.mismatch.lovers); xdr_stream_encode_u32(xdr, process.mismatch.hivers); goto sendit; @@ -1449,19 +1454,19 @@ err_bad_proc: svc_printk(rqstp, "unknown procedure (%d)\n", rqstp->rq_proc); serv->sv_stats->rpcbadfmt++; - xdr_stream_encode_u32(xdr, RPC_PROC_UNAVAIL); + *rqstp->rq_accept_statp = rpc_proc_unavail; goto sendit; err_garbage_args: svc_printk(rqstp, "failed to decode RPC header\n"); serv->sv_stats->rpcbadfmt++; - xdr_stream_encode_u32(xdr, RPC_GARBAGE_ARGS); + *rqstp->rq_accept_statp = rpc_garbage_args; goto sendit; err_system_err: serv->sv_stats->rpcbadfmt++; - xdr_stream_encode_u32(xdr, RPC_SYSTEM_ERR); + *rqstp->rq_accept_statp = rpc_system_err; goto sendit; } diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 84e5d7d31481..13a14897bc17 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -532,13 +532,23 @@ void svc_reserve(struct svc_rqst *rqstp, int space) } EXPORT_SYMBOL_GPL(svc_reserve); +static void free_deferred(struct svc_xprt *xprt, struct svc_deferred_req *dr) +{ + if (!dr) + return; + + xprt->xpt_ops->xpo_release_ctxt(xprt, dr->xprt_ctxt); + kfree(dr); +} + static void svc_xprt_release(struct svc_rqst *rqstp) { struct svc_xprt *xprt = rqstp->rq_xprt; - xprt->xpt_ops->xpo_release_rqst(rqstp); + xprt->xpt_ops->xpo_release_ctxt(xprt, rqstp->rq_xprt_ctxt); + rqstp->rq_xprt_ctxt = NULL; - kfree(rqstp->rq_deferred); + free_deferred(xprt, rqstp->rq_deferred); rqstp->rq_deferred = NULL; svc_rqst_release_pages(rqstp); @@ -1054,7 +1064,7 @@ static void svc_delete_xprt(struct svc_xprt *xprt) spin_unlock_bh(&serv->sv_lock); while ((dr = svc_deferred_dequeue(xprt)) != NULL) - kfree(dr); + free_deferred(xprt, dr); call_xpt_users(xprt); svc_xprt_put(xprt); @@ -1176,8 +1186,8 @@ static void svc_revisit(struct cache_deferred_req *dreq, int too_many) if (too_many || test_bit(XPT_DEAD, &xprt->xpt_flags)) { spin_unlock(&xprt->xpt_lock); trace_svc_defer_drop(dr); + free_deferred(xprt, dr); svc_xprt_put(xprt); - kfree(dr); return; } dr->xprt = NULL; @@ -1222,14 +1232,14 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req) dr->addrlen = rqstp->rq_addrlen; dr->daddr = rqstp->rq_daddr; dr->argslen = rqstp->rq_arg.len >> 2; - dr->xprt_ctxt = rqstp->rq_xprt_ctxt; - rqstp->rq_xprt_ctxt = NULL; /* back up head to the start of the buffer and copy */ skip = rqstp->rq_arg.len - rqstp->rq_arg.head[0].iov_len; memcpy(dr->args, rqstp->rq_arg.head[0].iov_base - skip, dr->argslen << 2); } + dr->xprt_ctxt = rqstp->rq_xprt_ctxt; + rqstp->rq_xprt_ctxt = NULL; trace_svc_defer(rqstp); svc_xprt_get(rqstp->rq_xprt); dr->xprt = rqstp->rq_xprt; @@ -1262,6 +1272,8 @@ static noinline int svc_deferred_recv(struct svc_rqst *rqstp) rqstp->rq_daddr = dr->daddr; rqstp->rq_respages = rqstp->rq_pages; rqstp->rq_xprt_ctxt = dr->xprt_ctxt; + + dr->xprt_ctxt = NULL; svc_xprt_received(rqstp->rq_xprt); return dr->argslen << 2; } diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index a51c9b989d58..f77cebe2c071 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -121,27 +121,27 @@ static void svc_reclassify_socket(struct socket *sock) #endif /** - * svc_tcp_release_rqst - Release transport-related resources - * @rqstp: request structure with resources to be released + * svc_tcp_release_ctxt - Release transport-related resources + * @xprt: the transport which owned the context + * @ctxt: the context from rqstp->rq_xprt_ctxt or dr->xprt_ctxt * */ -static void svc_tcp_release_rqst(struct svc_rqst *rqstp) +static void svc_tcp_release_ctxt(struct svc_xprt *xprt, void *ctxt) { } /** - * svc_udp_release_rqst - Release transport-related resources - * @rqstp: request structure with resources to be released + * svc_udp_release_ctxt - Release transport-related resources + * @xprt: the transport which owned the context + * @ctxt: the context from rqstp->rq_xprt_ctxt or dr->xprt_ctxt * */ -static void svc_udp_release_rqst(struct svc_rqst *rqstp) +static void svc_udp_release_ctxt(struct svc_xprt *xprt, void *ctxt) { - struct sk_buff *skb = rqstp->rq_xprt_ctxt; + struct sk_buff *skb = ctxt; - if (skb) { - rqstp->rq_xprt_ctxt = NULL; + if (skb) consume_skb(skb); - } } union svc_pktinfo_u { @@ -696,7 +696,8 @@ static int svc_udp_sendto(struct svc_rqst *rqstp) unsigned int sent; int err; - svc_udp_release_rqst(rqstp); + svc_udp_release_ctxt(xprt, rqstp->rq_xprt_ctxt); + rqstp->rq_xprt_ctxt = NULL; svc_set_cmsg_data(rqstp, cmh); @@ -768,7 +769,7 @@ static const struct svc_xprt_ops svc_udp_ops = { .xpo_recvfrom = svc_udp_recvfrom, .xpo_sendto = svc_udp_sendto, .xpo_result_payload = svc_sock_result_payload, - .xpo_release_rqst = svc_udp_release_rqst, + .xpo_release_ctxt = svc_udp_release_ctxt, .xpo_detach = svc_sock_detach, .xpo_free = svc_sock_free, .xpo_has_wspace = svc_udp_has_wspace, @@ -895,6 +896,9 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt) trace_svcsock_accept_err(xprt, serv->sv_name, err); return NULL; } + if (IS_ERR(sock_alloc_file(newsock, O_NONBLOCK, NULL))) + return NULL; + set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags); err = kernel_getpeername(newsock, sin); @@ -935,7 +939,7 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt) return &newsvsk->sk_xprt; failed: - sock_release(newsock); + sockfd_put(newsock); return NULL; } @@ -1298,7 +1302,8 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp) unsigned int sent; int err; - svc_tcp_release_rqst(rqstp); + svc_tcp_release_ctxt(xprt, rqstp->rq_xprt_ctxt); + rqstp->rq_xprt_ctxt = NULL; atomic_inc(&svsk->sk_sendqlen); mutex_lock(&xprt->xpt_mutex); @@ -1343,7 +1348,7 @@ static const struct svc_xprt_ops svc_tcp_ops = { .xpo_recvfrom = svc_tcp_recvfrom, .xpo_sendto = svc_tcp_sendto, .xpo_result_payload = svc_sock_result_payload, - .xpo_release_rqst = svc_tcp_release_rqst, + .xpo_release_ctxt = svc_tcp_release_ctxt, .xpo_detach = svc_tcp_sock_detach, .xpo_free = svc_sock_free, .xpo_has_wspace = svc_tcp_has_wspace, @@ -1430,7 +1435,6 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, struct socket *sock, int flags) { - struct file *filp = NULL; struct svc_sock *svsk; struct sock *inet; int pmap_register = !(flags & SVC_SOCK_ANONYMOUS); @@ -1439,14 +1443,6 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, if (!svsk) return ERR_PTR(-ENOMEM); - if (!sock->file) { - filp = sock_alloc_file(sock, O_NONBLOCK, NULL); - if (IS_ERR(filp)) { - kfree(svsk); - return ERR_CAST(filp); - } - } - inet = sock->sk; if (pmap_register) { @@ -1456,8 +1452,6 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, inet->sk_protocol, ntohs(inet_sk(inet)->inet_sport)); if (err < 0) { - if (filp) - fput(filp); kfree(svsk); return ERR_PTR(err); } @@ -1486,25 +1480,10 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, return svsk; } -bool svc_alien_sock(struct net *net, int fd) -{ - int err; - struct socket *sock = sockfd_lookup(fd, &err); - bool ret = false; - - if (!sock) - goto out; - if (sock_net(sock->sk) != net) - ret = true; - sockfd_put(sock); -out: - return ret; -} -EXPORT_SYMBOL_GPL(svc_alien_sock); - /** * svc_addsock - add a listener socket to an RPC service * @serv: pointer to RPC service to which to add a new listener + * @net: caller's network namespace * @fd: file descriptor of the new listener * @name_return: pointer to buffer to fill in with name of listener * @len: size of the buffer @@ -1514,8 +1493,8 @@ EXPORT_SYMBOL_GPL(svc_alien_sock); * Name is terminated with '\n'. On error, returns a negative errno * value. */ -int svc_addsock(struct svc_serv *serv, const int fd, char *name_return, - const size_t len, const struct cred *cred) +int svc_addsock(struct svc_serv *serv, struct net *net, const int fd, + char *name_return, const size_t len, const struct cred *cred) { int err = 0; struct socket *so = sockfd_lookup(fd, &err); @@ -1526,6 +1505,9 @@ int svc_addsock(struct svc_serv *serv, const int fd, char *name_return, if (!so) return err; + err = -EINVAL; + if (sock_net(so->sk) != net) + goto out; err = -EAFNOSUPPORT; if ((so->sk->sk_family != PF_INET) && (so->sk->sk_family != PF_INET6)) goto out; diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 1c658fa43063..a22fe7587fa6 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -239,21 +239,20 @@ void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma, } /** - * svc_rdma_release_rqst - Release transport-specific per-rqst resources - * @rqstp: svc_rqst being released + * svc_rdma_release_ctxt - Release transport-specific per-rqst resources + * @xprt: the transport which owned the context + * @vctxt: the context from rqstp->rq_xprt_ctxt or dr->xprt_ctxt * * Ensure that the recv_ctxt is released whether or not a Reply * was sent. For example, the client could close the connection, * or svc_process could drop an RPC, before the Reply is sent. */ -void svc_rdma_release_rqst(struct svc_rqst *rqstp) +void svc_rdma_release_ctxt(struct svc_xprt *xprt, void *vctxt) { - struct svc_rdma_recv_ctxt *ctxt = rqstp->rq_xprt_ctxt; - struct svc_xprt *xprt = rqstp->rq_xprt; + struct svc_rdma_recv_ctxt *ctxt = vctxt; struct svcxprt_rdma *rdma = container_of(xprt, struct svcxprt_rdma, sc_xprt); - rqstp->rq_xprt_ctxt = NULL; if (ctxt) svc_rdma_recv_ctxt_put(rdma, ctxt); } diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 416b298f74dd..ca04f7a6a085 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -80,7 +80,7 @@ static const struct svc_xprt_ops svc_rdma_ops = { .xpo_recvfrom = svc_rdma_recvfrom, .xpo_sendto = svc_rdma_sendto, .xpo_result_payload = svc_rdma_result_payload, - .xpo_release_rqst = svc_rdma_release_rqst, + .xpo_release_ctxt = svc_rdma_release_ctxt, .xpo_detach = svc_rdma_detach, .xpo_free = svc_rdma_free, .xpo_has_wspace = svc_rdma_has_wspace, diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 35cac7733fd3..1d5d3677bdaf 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -176,7 +176,7 @@ static int bearer_name_validate(const char *name, */ struct tipc_bearer *tipc_bearer_find(struct net *net, const char *name) { - struct tipc_net *tn = net_generic(net, tipc_net_id); + struct tipc_net *tn = tipc_net(net); struct tipc_bearer *b; u32 i; @@ -211,11 +211,10 @@ int tipc_bearer_get_name(struct net *net, char *name, u32 bearer_id) void tipc_bearer_add_dest(struct net *net, u32 bearer_id, u32 dest) { - struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_bearer *b; rcu_read_lock(); - b = rcu_dereference(tn->bearer_list[bearer_id]); + b = bearer_get(net, bearer_id); if (b) tipc_disc_add_dest(b->disc); rcu_read_unlock(); @@ -223,11 +222,10 @@ void tipc_bearer_add_dest(struct net *net, u32 bearer_id, u32 dest) void tipc_bearer_remove_dest(struct net *net, u32 bearer_id, u32 dest) { - struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_bearer *b; rcu_read_lock(); - b = rcu_dereference(tn->bearer_list[bearer_id]); + b = bearer_get(net, bearer_id); if (b) tipc_disc_remove_dest(b->disc); rcu_read_unlock(); @@ -431,7 +429,7 @@ int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b, dev = dev_get_by_name(net, dev_name); if (!dev) return -ENODEV; - if (tipc_mtu_bad(dev, 0)) { + if (tipc_mtu_bad(dev)) { dev_put(dev); return -EINVAL; } @@ -534,13 +532,26 @@ int tipc_bearer_mtu(struct net *net, u32 bearer_id) struct tipc_bearer *b; rcu_read_lock(); - b = rcu_dereference(tipc_net(net)->bearer_list[bearer_id]); + b = bearer_get(net, bearer_id); if (b) mtu = b->mtu; rcu_read_unlock(); return mtu; } +int tipc_bearer_min_mtu(struct net *net, u32 bearer_id) +{ + int mtu = TIPC_MIN_BEARER_MTU; + struct tipc_bearer *b; + + rcu_read_lock(); + b = bearer_get(net, bearer_id); + if (b) + mtu += b->encap_hlen; + rcu_read_unlock(); + return mtu; +} + /* tipc_bearer_xmit_skb - sends buffer to destination over bearer */ void tipc_bearer_xmit_skb(struct net *net, u32 bearer_id, @@ -695,7 +706,7 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, test_and_set_bit_lock(0, &b->up); break; case NETDEV_CHANGEMTU: - if (tipc_mtu_bad(dev, 0)) { + if (tipc_mtu_bad(dev)) { bearer_disable(net, b); break; } @@ -732,7 +743,7 @@ void tipc_bearer_cleanup(void) void tipc_bearer_stop(struct net *net) { - struct tipc_net *tn = net_generic(net, tipc_net_id); + struct tipc_net *tn = tipc_net(net); struct tipc_bearer *b; u32 i; @@ -868,7 +879,7 @@ int tipc_nl_bearer_dump(struct sk_buff *skb, struct netlink_callback *cb) struct tipc_bearer *bearer; struct tipc_nl_msg msg; struct net *net = sock_net(skb->sk); - struct tipc_net *tn = net_generic(net, tipc_net_id); + struct tipc_net *tn = tipc_net(net); if (i == MAX_BEARERS) return 0; @@ -1138,8 +1149,8 @@ int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } #ifdef CONFIG_TIPC_MEDIA_UDP - if (tipc_udp_mtu_bad(nla_get_u32 - (props[TIPC_NLA_PROP_MTU]))) { + if (nla_get_u32(props[TIPC_NLA_PROP_MTU]) < + b->encap_hlen + TIPC_MIN_BEARER_MTU) { NL_SET_ERR_MSG(info->extack, "MTU value is out-of-range"); return -EINVAL; diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 490ad6e5f7a3..1ee60649bd17 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -146,6 +146,7 @@ struct tipc_media { * @identity: array index of this bearer within TIPC bearer array * @disc: ptr to link setup request * @net_plane: network plane ('A' through 'H') currently associated with bearer + * @encap_hlen: encap headers length * @up: bearer up flag (bit 0) * @refcnt: tipc_bearer reference counter * @@ -170,6 +171,7 @@ struct tipc_bearer { u32 identity; struct tipc_discoverer *disc; char net_plane; + u16 encap_hlen; unsigned long up; refcount_t refcnt; }; @@ -232,6 +234,7 @@ int tipc_bearer_setup(void); void tipc_bearer_cleanup(void); void tipc_bearer_stop(struct net *net); int tipc_bearer_mtu(struct net *net, u32 bearer_id); +int tipc_bearer_min_mtu(struct net *net, u32 bearer_id); bool tipc_bearer_bcast_support(struct net *net, u32 bearer_id); void tipc_bearer_xmit_skb(struct net *net, u32 bearer_id, struct sk_buff *skb, @@ -254,9 +257,9 @@ static inline void tipc_loopback_trace(struct net *net, } /* check if device MTU is too low for tipc headers */ -static inline bool tipc_mtu_bad(struct net_device *dev, unsigned int reserve) +static inline bool tipc_mtu_bad(struct net_device *dev) { - if (dev->mtu >= TIPC_MIN_BEARER_MTU + reserve) + if (dev->mtu >= TIPC_MIN_BEARER_MTU) return false; netdev_warn(dev, "MTU too low for tipc bearer\n"); return true; diff --git a/net/tipc/link.c b/net/tipc/link.c index b3ce24823f50..2eff1c7949cb 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -2200,7 +2200,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, struct tipc_msg *hdr = buf_msg(skb); struct tipc_gap_ack_blks *ga = NULL; bool reply = msg_probe(hdr), retransmitted = false; - u32 dlen = msg_data_sz(hdr), glen = 0; + u32 dlen = msg_data_sz(hdr), glen = 0, msg_max; u16 peers_snd_nxt = msg_next_sent(hdr); u16 peers_tol = msg_link_tolerance(hdr); u16 peers_prio = msg_linkprio(hdr); @@ -2239,6 +2239,9 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, switch (mtyp) { case RESET_MSG: case ACTIVATE_MSG: + msg_max = msg_max_pkt(hdr); + if (msg_max < tipc_bearer_min_mtu(l->net, l->bearer_id)) + break; /* Complete own link name with peer's interface name */ if_name = strrchr(l->name, ':') + 1; if (sizeof(l->name) - (if_name - l->name) <= TIPC_MAX_IF_NAME) @@ -2283,8 +2286,8 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, l->peer_session = msg_session(hdr); l->in_session = true; l->peer_bearer_id = msg_bearer_id(hdr); - if (l->mtu > msg_max_pkt(hdr)) - l->mtu = msg_max_pkt(hdr); + if (l->mtu > msg_max) + l->mtu = msg_max; break; case STATE_MSG: diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index c2bb818704c8..926232557e77 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -738,11 +738,7 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, udp_conf.local_ip.s_addr = local.ipv4.s_addr; udp_conf.use_udp_checksums = false; ub->ifindex = dev->ifindex; - if (tipc_mtu_bad(dev, sizeof(struct iphdr) + - sizeof(struct udphdr))) { - err = -EINVAL; - goto err; - } + b->encap_hlen = sizeof(struct iphdr) + sizeof(struct udphdr); b->mtu = b->media->mtu; #if IS_ENABLED(CONFIG_IPV6) } else if (local.proto == htons(ETH_P_IPV6)) { @@ -760,6 +756,7 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, else udp_conf.local_ip6 = local.ipv6; ub->ifindex = dev->ifindex; + b->encap_hlen = sizeof(struct ipv6hdr) + sizeof(struct udphdr); b->mtu = 1280; #endif } else { diff --git a/net/tls/tls.h b/net/tls/tls.h index 804c3880d028..d002c3af1966 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -97,6 +97,7 @@ void tls_update_rx_zc_capable(struct tls_context *tls_ctx); void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx); void tls_sw_strparser_done(struct tls_context *tls_ctx); int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); +void tls_sw_splice_eof(struct socket *sock); int tls_sw_sendpage_locked(struct sock *sk, struct page *page, int offset, size_t size, int flags); int tls_sw_sendpage(struct sock *sk, struct page *page, @@ -115,6 +116,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, size_t len, unsigned int flags); int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); +void tls_device_splice_eof(struct socket *sock); int tls_device_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); int tls_tx_records(struct sock *sk, int flags); @@ -167,6 +169,11 @@ static inline bool tls_strp_msg_ready(struct tls_sw_context_rx *ctx) return ctx->strp.msg_ready; } +static inline bool tls_strp_msg_mixed_decrypted(struct tls_sw_context_rx *ctx) +{ + return ctx->strp.mixed_decrypted; +} + #ifdef CONFIG_TLS_DEVICE int tls_device_init(void); void tls_device_cleanup(void); diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index daeff54bdbfa..b4864d55900f 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -422,16 +422,10 @@ static int tls_device_copy_data(void *addr, size_t bytes, struct iov_iter *i) return 0; } -union tls_iter_offset { - struct iov_iter *msg_iter; - int offset; -}; - static int tls_push_data(struct sock *sk, - union tls_iter_offset iter_offset, + struct iov_iter *iter, size_t size, int flags, - unsigned char record_type, - struct page *zc_page) + unsigned char record_type) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_prot_info *prot = &tls_ctx->prot_info; @@ -447,7 +441,8 @@ static int tls_push_data(struct sock *sk, long timeo; if (flags & - ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_NOTLAST)) + ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_NOTLAST | + MSG_SPLICE_PAGES)) return -EOPNOTSUPP; if (unlikely(sk->sk_err)) @@ -499,21 +494,35 @@ handle_error: record = ctx->open_record; copy = min_t(size_t, size, max_open_record_len - record->len); - if (copy && zc_page) { + if (copy && (flags & MSG_SPLICE_PAGES)) { struct page_frag zc_pfrag; + struct page **pages = &zc_pfrag.page; + size_t off; + + rc = iov_iter_extract_pages(iter, &pages, + copy, 1, 0, &off); + if (rc <= 0) { + if (rc == 0) + rc = -EIO; + goto handle_error; + } + copy = rc; - zc_pfrag.page = zc_page; - zc_pfrag.offset = iter_offset.offset; + if (WARN_ON_ONCE(!sendpage_ok(zc_pfrag.page))) { + iov_iter_revert(iter, copy); + rc = -EIO; + goto handle_error; + } + + zc_pfrag.offset = off; zc_pfrag.size = copy; tls_append_frag(record, &zc_pfrag, copy); - - iter_offset.offset += copy; } else if (copy) { copy = min_t(size_t, copy, pfrag->size - pfrag->offset); rc = tls_device_copy_data(page_address(pfrag->page) + pfrag->offset, copy, - iter_offset.msg_iter); + iter); if (rc) goto handle_error; tls_append_frag(record, pfrag, copy); @@ -568,9 +577,11 @@ int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { unsigned char record_type = TLS_RECORD_TYPE_DATA; struct tls_context *tls_ctx = tls_get_ctx(sk); - union tls_iter_offset iter; int rc; + if (!tls_ctx->zerocopy_sendfile) + msg->msg_flags &= ~MSG_SPLICE_PAGES; + mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); @@ -580,8 +591,8 @@ int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) goto out; } - iter.msg_iter = &msg->msg_iter; - rc = tls_push_data(sk, iter, size, msg->msg_flags, record_type, NULL); + rc = tls_push_data(sk, &msg->msg_iter, size, msg->msg_flags, + record_type); out: release_sock(sk); @@ -589,47 +600,42 @@ out: return rc; } -int tls_device_sendpage(struct sock *sk, struct page *page, - int offset, size_t size, int flags) +void tls_device_splice_eof(struct socket *sock) { + struct sock *sk = sock->sk; struct tls_context *tls_ctx = tls_get_ctx(sk); - union tls_iter_offset iter_offset; - struct iov_iter msg_iter; - char *kaddr; - struct kvec iov; - int rc; + struct iov_iter iter = {}; - if (flags & MSG_SENDPAGE_NOTLAST) - flags |= MSG_MORE; + if (!tls_is_partially_sent_record(tls_ctx)) + return; mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); - if (flags & MSG_OOB) { - rc = -EOPNOTSUPP; - goto out; - } - - if (tls_ctx->zerocopy_sendfile) { - iter_offset.offset = offset; - rc = tls_push_data(sk, iter_offset, size, - flags, TLS_RECORD_TYPE_DATA, page); - goto out; + if (tls_is_partially_sent_record(tls_ctx)) { + iov_iter_bvec(&iter, ITER_SOURCE, NULL, 0, 0); + tls_push_data(sk, &iter, 0, 0, TLS_RECORD_TYPE_DATA); } - kaddr = kmap(page); - iov.iov_base = kaddr + offset; - iov.iov_len = size; - iov_iter_kvec(&msg_iter, ITER_SOURCE, &iov, 1, size); - iter_offset.msg_iter = &msg_iter; - rc = tls_push_data(sk, iter_offset, size, flags, TLS_RECORD_TYPE_DATA, - NULL); - kunmap(page); - -out: release_sock(sk); mutex_unlock(&tls_ctx->tx_lock); - return rc; +} + +int tls_device_sendpage(struct sock *sk, struct page *page, + int offset, size_t size, int flags) +{ + struct bio_vec bvec; + struct msghdr msg = { .msg_flags = flags | MSG_SPLICE_PAGES, }; + + if (flags & MSG_SENDPAGE_NOTLAST) + msg.msg_flags |= MSG_MORE; + + if (flags & MSG_OOB) + return -EOPNOTSUPP; + + bvec_set_page(&bvec, page, size, offset); + iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); + return tls_device_sendmsg(sk, &msg, size); } struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context, @@ -694,12 +700,10 @@ EXPORT_SYMBOL(tls_get_record); static int tls_device_push_pending_record(struct sock *sk, int flags) { - union tls_iter_offset iter; - struct iov_iter msg_iter; + struct iov_iter iter; - iov_iter_kvec(&msg_iter, ITER_SOURCE, NULL, 0, 0); - iter.msg_iter = &msg_iter; - return tls_push_data(sk, iter, 0, flags, TLS_RECORD_TYPE_DATA, NULL); + iov_iter_kvec(&iter, ITER_SOURCE, NULL, 0, 0); + return tls_push_data(sk, &iter, 0, flags, TLS_RECORD_TYPE_DATA); } void tls_device_write_space(struct sock *sk, struct tls_context *ctx) @@ -1005,20 +1009,14 @@ int tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx) struct tls_sw_context_rx *sw_ctx = tls_sw_ctx_rx(tls_ctx); struct sk_buff *skb = tls_strp_msg(sw_ctx); struct strp_msg *rxm = strp_msg(skb); - int is_decrypted = skb->decrypted; - int is_encrypted = !is_decrypted; - struct sk_buff *skb_iter; - int left; - - left = rxm->full_len - skb->len; - /* Check if all the data is decrypted already */ - skb_iter = skb_shinfo(skb)->frag_list; - while (skb_iter && left > 0) { - is_decrypted &= skb_iter->decrypted; - is_encrypted &= !skb_iter->decrypted; - - left -= skb_iter->len; - skb_iter = skb_iter->next; + int is_decrypted, is_encrypted; + + if (!tls_strp_msg_mixed_decrypted(sw_ctx)) { + is_decrypted = skb->decrypted; + is_encrypted = !is_decrypted; + } else { + is_decrypted = 0; + is_encrypted = 0; } trace_tls_device_decrypted(sk, tcp_sk(sk)->copied_seq - rxm->full_len, diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index f2e7302a4d96..7b9c83dd7de2 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -125,7 +125,10 @@ int tls_push_sg(struct sock *sk, u16 first_offset, int flags) { - int sendpage_flags = flags | MSG_SENDPAGE_NOTLAST; + struct bio_vec bvec; + struct msghdr msg = { + .msg_flags = MSG_SENDPAGE_NOTLAST | MSG_SPLICE_PAGES | flags, + }; int ret = 0; struct page *p; size_t size; @@ -134,16 +137,19 @@ int tls_push_sg(struct sock *sk, size = sg->length - offset; offset += sg->offset; - ctx->in_tcp_sendpages = true; + ctx->splicing_pages = true; while (1) { if (sg_is_last(sg)) - sendpage_flags = flags; + msg.msg_flags = flags; /* is sending application-limited? */ tcp_rate_check_app_limited(sk); p = sg_page(sg); retry: - ret = do_tcp_sendpages(sk, p, offset, size, sendpage_flags); + bvec_set_page(&bvec, p, size, offset); + iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); + + ret = tcp_sendmsg_locked(sk, &msg, size); if (ret != size) { if (ret > 0) { @@ -155,7 +161,7 @@ retry: offset -= sg->offset; ctx->partially_sent_offset = offset; ctx->partially_sent_record = (void *)sg; - ctx->in_tcp_sendpages = false; + ctx->splicing_pages = false; return ret; } @@ -169,7 +175,7 @@ retry: size = sg->length; } - ctx->in_tcp_sendpages = false; + ctx->splicing_pages = false; return 0; } @@ -247,11 +253,11 @@ static void tls_write_space(struct sock *sk) { struct tls_context *ctx = tls_get_ctx(sk); - /* If in_tcp_sendpages call lower protocol write space handler + /* If splicing_pages call lower protocol write space handler * to ensure we wake up any waiting operations there. For example - * if do_tcp_sendpages where to call sk_wait_event. + * if splicing pages where to call sk_wait_event. */ - if (ctx->in_tcp_sendpages) { + if (ctx->splicing_pages) { ctx->sk_write_space(sk); return; } @@ -352,6 +358,39 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) tls_ctx_free(sk, ctx); } +static __poll_t tls_sk_poll(struct file *file, struct socket *sock, + struct poll_table_struct *wait) +{ + struct tls_sw_context_rx *ctx; + struct tls_context *tls_ctx; + struct sock *sk = sock->sk; + struct sk_psock *psock; + __poll_t mask = 0; + u8 shutdown; + int state; + + mask = tcp_poll(file, sock, wait); + + state = inet_sk_state_load(sk); + shutdown = READ_ONCE(sk->sk_shutdown); + if (unlikely(state != TCP_ESTABLISHED || shutdown & RCV_SHUTDOWN)) + return mask; + + tls_ctx = tls_get_ctx(sk); + ctx = tls_sw_ctx_rx(tls_ctx); + psock = sk_psock_get(sk); + + if (skb_queue_empty_lockless(&ctx->rx_list) && + !tls_strp_msg_ready(ctx) && + sk_psock_queue_empty(psock)) + mask &= ~(EPOLLIN | EPOLLRDNORM); + + if (psock) + sk_psock_put(sk, psock); + + return mask; +} + static int do_tls_getsockopt_conf(struct sock *sk, char __user *optval, int __user *optlen, int tx) { @@ -918,13 +957,16 @@ static void build_proto_ops(struct proto_ops ops[TLS_NUM_CONFIG][TLS_NUM_CONFIG] ops[TLS_BASE][TLS_BASE] = *base; ops[TLS_SW ][TLS_BASE] = ops[TLS_BASE][TLS_BASE]; + ops[TLS_SW ][TLS_BASE].splice_eof = tls_sw_splice_eof; ops[TLS_SW ][TLS_BASE].sendpage_locked = tls_sw_sendpage_locked; ops[TLS_BASE][TLS_SW ] = ops[TLS_BASE][TLS_BASE]; ops[TLS_BASE][TLS_SW ].splice_read = tls_sw_splice_read; + ops[TLS_BASE][TLS_SW ].poll = tls_sk_poll; ops[TLS_SW ][TLS_SW ] = ops[TLS_SW ][TLS_BASE]; ops[TLS_SW ][TLS_SW ].splice_read = tls_sw_splice_read; + ops[TLS_SW ][TLS_SW ].poll = tls_sk_poll; #ifdef CONFIG_TLS_DEVICE ops[TLS_HW ][TLS_BASE] = ops[TLS_BASE][TLS_BASE]; @@ -986,6 +1028,7 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], prot[TLS_SW][TLS_BASE] = prot[TLS_BASE][TLS_BASE]; prot[TLS_SW][TLS_BASE].sendmsg = tls_sw_sendmsg; + prot[TLS_SW][TLS_BASE].splice_eof = tls_sw_splice_eof; prot[TLS_SW][TLS_BASE].sendpage = tls_sw_sendpage; prot[TLS_BASE][TLS_SW] = prot[TLS_BASE][TLS_BASE]; @@ -1001,10 +1044,12 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], #ifdef CONFIG_TLS_DEVICE prot[TLS_HW][TLS_BASE] = prot[TLS_BASE][TLS_BASE]; prot[TLS_HW][TLS_BASE].sendmsg = tls_device_sendmsg; + prot[TLS_HW][TLS_BASE].splice_eof = tls_device_splice_eof; prot[TLS_HW][TLS_BASE].sendpage = tls_device_sendpage; prot[TLS_HW][TLS_SW] = prot[TLS_BASE][TLS_SW]; prot[TLS_HW][TLS_SW].sendmsg = tls_device_sendmsg; + prot[TLS_HW][TLS_SW].splice_eof = tls_device_splice_eof; prot[TLS_HW][TLS_SW].sendpage = tls_device_sendpage; prot[TLS_BASE][TLS_HW] = prot[TLS_BASE][TLS_SW]; diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 955ac3e0bf4d..f37f4a0fcd3c 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -20,7 +20,9 @@ static void tls_strp_abort_strp(struct tls_strparser *strp, int err) strp->stopped = 1; /* Report an error on the lower socket */ - strp->sk->sk_err = -err; + WRITE_ONCE(strp->sk->sk_err, -err); + /* Paired with smp_rmb() in tcp_poll() */ + smp_wmb(); sk_error_report(strp->sk); } @@ -29,34 +31,50 @@ static void tls_strp_anchor_free(struct tls_strparser *strp) struct skb_shared_info *shinfo = skb_shinfo(strp->anchor); DEBUG_NET_WARN_ON_ONCE(atomic_read(&shinfo->dataref) != 1); - shinfo->frag_list = NULL; + if (!strp->copy_mode) + shinfo->frag_list = NULL; consume_skb(strp->anchor); strp->anchor = NULL; } -/* Create a new skb with the contents of input copied to its page frags */ -static struct sk_buff *tls_strp_msg_make_copy(struct tls_strparser *strp) +static struct sk_buff * +tls_strp_skb_copy(struct tls_strparser *strp, struct sk_buff *in_skb, + int offset, int len) { - struct strp_msg *rxm; struct sk_buff *skb; - int i, err, offset; + int i, err; - skb = alloc_skb_with_frags(0, strp->stm.full_len, TLS_PAGE_ORDER, + skb = alloc_skb_with_frags(0, len, TLS_PAGE_ORDER, &err, strp->sk->sk_allocation); if (!skb) return NULL; - offset = strp->stm.offset; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - WARN_ON_ONCE(skb_copy_bits(strp->anchor, offset, + WARN_ON_ONCE(skb_copy_bits(in_skb, offset, skb_frag_address(frag), skb_frag_size(frag))); offset += skb_frag_size(frag); } - skb_copy_header(skb, strp->anchor); + skb->len = len; + skb->data_len = len; + skb_copy_header(skb, in_skb); + return skb; +} + +/* Create a new skb with the contents of input copied to its page frags */ +static struct sk_buff *tls_strp_msg_make_copy(struct tls_strparser *strp) +{ + struct strp_msg *rxm; + struct sk_buff *skb; + + skb = tls_strp_skb_copy(strp, strp->anchor, strp->stm.offset, + strp->stm.full_len); + if (!skb) + return NULL; + rxm = strp_msg(skb); rxm->offset = 0; return skb; @@ -180,22 +198,22 @@ static void tls_strp_flush_anchor_copy(struct tls_strparser *strp) for (i = 0; i < shinfo->nr_frags; i++) __skb_frag_unref(&shinfo->frags[i], false); shinfo->nr_frags = 0; + if (strp->copy_mode) { + kfree_skb_list(shinfo->frag_list); + shinfo->frag_list = NULL; + } strp->copy_mode = 0; + strp->mixed_decrypted = 0; } -static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, - unsigned int offset, size_t in_len) +static int tls_strp_copyin_frag(struct tls_strparser *strp, struct sk_buff *skb, + struct sk_buff *in_skb, unsigned int offset, + size_t in_len) { - struct tls_strparser *strp = (struct tls_strparser *)desc->arg.data; - struct sk_buff *skb; - skb_frag_t *frag; size_t len, chunk; + skb_frag_t *frag; int sz; - if (strp->msg_ready) - return 0; - - skb = strp->anchor; frag = &skb_shinfo(skb)->frags[skb->len / PAGE_SIZE]; len = in_len; @@ -208,19 +226,26 @@ static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, skb_frag_size(frag), chunk)); - sz = tls_rx_msg_size(strp, strp->anchor); - if (sz < 0) { - desc->error = sz; - return 0; - } - - /* We may have over-read, sz == 0 is guaranteed under-read */ - if (sz > 0) - chunk = min_t(size_t, chunk, sz - skb->len); - skb->len += chunk; skb->data_len += chunk; skb_frag_size_add(frag, chunk); + + sz = tls_rx_msg_size(strp, skb); + if (sz < 0) + return sz; + + /* We may have over-read, sz == 0 is guaranteed under-read */ + if (unlikely(sz && sz < skb->len)) { + int over = skb->len - sz; + + WARN_ON_ONCE(over > chunk); + skb->len -= over; + skb->data_len -= over; + skb_frag_size_add(frag, -over); + + chunk -= over; + } + frag++; len -= chunk; offset += chunk; @@ -247,15 +272,99 @@ static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, offset += chunk; } - if (strp->stm.full_len == skb->len) { +read_done: + return in_len - len; +} + +static int tls_strp_copyin_skb(struct tls_strparser *strp, struct sk_buff *skb, + struct sk_buff *in_skb, unsigned int offset, + size_t in_len) +{ + struct sk_buff *nskb, *first, *last; + struct skb_shared_info *shinfo; + size_t chunk; + int sz; + + if (strp->stm.full_len) + chunk = strp->stm.full_len - skb->len; + else + chunk = TLS_MAX_PAYLOAD_SIZE + PAGE_SIZE; + chunk = min(chunk, in_len); + + nskb = tls_strp_skb_copy(strp, in_skb, offset, chunk); + if (!nskb) + return -ENOMEM; + + shinfo = skb_shinfo(skb); + if (!shinfo->frag_list) { + shinfo->frag_list = nskb; + nskb->prev = nskb; + } else { + first = shinfo->frag_list; + last = first->prev; + last->next = nskb; + first->prev = nskb; + } + + skb->len += chunk; + skb->data_len += chunk; + + if (!strp->stm.full_len) { + sz = tls_rx_msg_size(strp, skb); + if (sz < 0) + return sz; + + /* We may have over-read, sz == 0 is guaranteed under-read */ + if (unlikely(sz && sz < skb->len)) { + int over = skb->len - sz; + + WARN_ON_ONCE(over > chunk); + skb->len -= over; + skb->data_len -= over; + __pskb_trim(nskb, nskb->len - over); + + chunk -= over; + } + + strp->stm.full_len = sz; + } + + return chunk; +} + +static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, + unsigned int offset, size_t in_len) +{ + struct tls_strparser *strp = (struct tls_strparser *)desc->arg.data; + struct sk_buff *skb; + int ret; + + if (strp->msg_ready) + return 0; + + skb = strp->anchor; + if (!skb->len) + skb_copy_decrypted(skb, in_skb); + else + strp->mixed_decrypted |= !!skb_cmp_decrypted(skb, in_skb); + + if (IS_ENABLED(CONFIG_TLS_DEVICE) && strp->mixed_decrypted) + ret = tls_strp_copyin_skb(strp, skb, in_skb, offset, in_len); + else + ret = tls_strp_copyin_frag(strp, skb, in_skb, offset, in_len); + if (ret < 0) { + desc->error = ret; + ret = 0; + } + + if (strp->stm.full_len && strp->stm.full_len == skb->len) { desc->count = 0; strp->msg_ready = 1; tls_rx_msg_ready(strp); } -read_done: - return in_len - len; + return ret; } static int tls_strp_read_copyin(struct tls_strparser *strp) @@ -315,15 +424,19 @@ static int tls_strp_read_copy(struct tls_strparser *strp, bool qshort) return 0; } -static bool tls_strp_check_no_dup(struct tls_strparser *strp) +static bool tls_strp_check_queue_ok(struct tls_strparser *strp) { unsigned int len = strp->stm.offset + strp->stm.full_len; - struct sk_buff *skb; + struct sk_buff *first, *skb; u32 seq; - skb = skb_shinfo(strp->anchor)->frag_list; - seq = TCP_SKB_CB(skb)->seq; + first = skb_shinfo(strp->anchor)->frag_list; + skb = first; + seq = TCP_SKB_CB(first)->seq; + /* Make sure there's no duplicate data in the queue, + * and the decrypted status matches. + */ while (skb->len < len) { seq += skb->len; len -= skb->len; @@ -331,6 +444,8 @@ static bool tls_strp_check_no_dup(struct tls_strparser *strp) if (TCP_SKB_CB(skb)->seq != seq) return false; + if (skb_cmp_decrypted(first, skb)) + return false; } return true; @@ -411,7 +526,7 @@ static int tls_strp_read_sock(struct tls_strparser *strp) return tls_strp_read_copy(strp, true); } - if (!tls_strp_check_no_dup(strp)) + if (!tls_strp_check_queue_ok(strp)) return tls_strp_read_copy(strp, false); strp->msg_ready = 1; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 635b8bf6b937..319f61590d2c 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -70,7 +70,9 @@ noinline void tls_err_abort(struct sock *sk, int err) { WARN_ON_ONCE(err >= 0); /* sk->sk_err should contain a positive error code. */ - sk->sk_err = -err; + WRITE_ONCE(sk->sk_err, -err); + /* Paired with smp_rmb() in tcp_poll() */ + smp_wmb(); sk_error_report(sk); } @@ -929,7 +931,37 @@ static int tls_sw_push_pending_record(struct sock *sk, int flags) &copied, flags); } -int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) +static int tls_sw_sendmsg_splice(struct sock *sk, struct msghdr *msg, + struct sk_msg *msg_pl, size_t try_to_copy, + ssize_t *copied) +{ + struct page *page = NULL, **pages = &page; + + do { + ssize_t part; + size_t off; + + part = iov_iter_extract_pages(&msg->msg_iter, &pages, + try_to_copy, 1, 0, &off); + if (part <= 0) + return part ?: -EIO; + + if (WARN_ON_ONCE(!sendpage_ok(page))) { + iov_iter_revert(&msg->msg_iter, part); + return -EIO; + } + + sk_msg_page_add(msg_pl, page, part, off); + sk_mem_charge(sk, part); + *copied += part; + try_to_copy -= part; + } while (try_to_copy && !sk_msg_full(msg_pl)); + + return 0; +} + +static int tls_sw_sendmsg_locked(struct sock *sk, struct msghdr *msg, + size_t size) { long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); struct tls_context *tls_ctx = tls_get_ctx(sk); @@ -952,15 +984,6 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) int ret = 0; int pending; - if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | - MSG_CMSG_COMPAT)) - return -EOPNOTSUPP; - - ret = mutex_lock_interruptible(&tls_ctx->tx_lock); - if (ret) - return ret; - lock_sock(sk); - if (unlikely(msg->msg_controllen)) { ret = tls_process_cmsg(sk, msg, &record_type); if (ret) { @@ -1018,6 +1041,17 @@ alloc_encrypted: full_record = true; } + if (try_to_copy && (msg->msg_flags & MSG_SPLICE_PAGES)) { + ret = tls_sw_sendmsg_splice(sk, msg, msg_pl, + try_to_copy, &copied); + if (ret < 0) + goto send_end; + tls_ctx->pending_open_record_frags = true; + if (full_record || eor || sk_msg_full(msg_pl)) + goto copied; + continue; + } + if (!is_kvec && (full_record || eor) && !async_capable) { u32 first = msg_pl->sg.end; @@ -1082,6 +1116,7 @@ fallback_to_reg_send: */ tls_ctx->pending_open_record_frags = true; copied += try_to_copy; +copied: if (full_record || eor) { ret = bpf_exec_tx_verdict(msg_pl, sk, full_record, record_type, &copied, @@ -1149,157 +1184,136 @@ trim_sgl: send_end: ret = sk_stream_error(sk, msg->msg_flags, ret); + return copied > 0 ? copied : ret; +} + +int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + int ret; + + if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | + MSG_CMSG_COMPAT | MSG_SPLICE_PAGES | + MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY)) + return -EOPNOTSUPP; + ret = mutex_lock_interruptible(&tls_ctx->tx_lock); + if (ret) + return ret; + lock_sock(sk); + ret = tls_sw_sendmsg_locked(sk, msg, size); release_sock(sk); mutex_unlock(&tls_ctx->tx_lock); - return copied > 0 ? copied : ret; + return ret; } -static int tls_sw_do_sendpage(struct sock *sk, struct page *page, - int offset, size_t size, int flags) +/* + * Handle unexpected EOF during splice without SPLICE_F_MORE set. + */ +void tls_sw_splice_eof(struct socket *sock) { - long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); + struct sock *sk = sock->sk; struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); - struct tls_prot_info *prot = &tls_ctx->prot_info; - unsigned char record_type = TLS_RECORD_TYPE_DATA; - struct sk_msg *msg_pl; struct tls_rec *rec; - int num_async = 0; + struct sk_msg *msg_pl; ssize_t copied = 0; - bool full_record; - int record_room; + bool retrying = false; int ret = 0; - bool eor; - - eor = !(flags & MSG_SENDPAGE_NOTLAST); - sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); - - /* Call the sk_stream functions to manage the sndbuf mem. */ - while (size > 0) { - size_t copy, required_size; - - if (sk->sk_err) { - ret = -sk->sk_err; - goto sendpage_end; - } + int pending; - if (ctx->open_rec) - rec = ctx->open_rec; - else - rec = ctx->open_rec = tls_get_rec(sk); - if (!rec) { - ret = -ENOMEM; - goto sendpage_end; - } + if (!ctx->open_rec) + return; - msg_pl = &rec->msg_plaintext; + mutex_lock(&tls_ctx->tx_lock); + lock_sock(sk); - full_record = false; - record_room = TLS_MAX_PAYLOAD_SIZE - msg_pl->sg.size; - copy = size; - if (copy >= record_room) { - copy = record_room; - full_record = true; - } +retry: + rec = ctx->open_rec; + if (!rec) + goto unlock; - required_size = msg_pl->sg.size + copy + prot->overhead_size; + msg_pl = &rec->msg_plaintext; - if (!sk_stream_memory_free(sk)) - goto wait_for_sndbuf; -alloc_payload: - ret = tls_alloc_encrypted_msg(sk, required_size); - if (ret) { - if (ret != -ENOSPC) - goto wait_for_memory; + /* Check the BPF advisor and perform transmission. */ + ret = bpf_exec_tx_verdict(msg_pl, sk, false, TLS_RECORD_TYPE_DATA, + &copied, 0); + switch (ret) { + case 0: + case -EAGAIN: + if (retrying) + goto unlock; + retrying = true; + goto retry; + case -EINPROGRESS: + break; + default: + goto unlock; + } - /* Adjust copy according to the amount that was - * actually allocated. The difference is due - * to max sg elements limit - */ - copy -= required_size - msg_pl->sg.size; - full_record = true; - } + /* Wait for pending encryptions to get completed */ + spin_lock_bh(&ctx->encrypt_compl_lock); + ctx->async_notify = true; - sk_msg_page_add(msg_pl, page, copy, offset); - sk_mem_charge(sk, copy); + pending = atomic_read(&ctx->encrypt_pending); + spin_unlock_bh(&ctx->encrypt_compl_lock); + if (pending) + crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + else + reinit_completion(&ctx->async_wait.completion); - offset += copy; - size -= copy; - copied += copy; + /* There can be no concurrent accesses, since we have no pending + * encrypt operations + */ + WRITE_ONCE(ctx->async_notify, false); - tls_ctx->pending_open_record_frags = true; - if (full_record || eor || sk_msg_full(msg_pl)) { - ret = bpf_exec_tx_verdict(msg_pl, sk, full_record, - record_type, &copied, flags); - if (ret) { - if (ret == -EINPROGRESS) - num_async++; - else if (ret == -ENOMEM) - goto wait_for_memory; - else if (ret != -EAGAIN) { - if (ret == -ENOSPC) - ret = 0; - goto sendpage_end; - } - } - } - continue; -wait_for_sndbuf: - set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); -wait_for_memory: - ret = sk_stream_wait_memory(sk, &timeo); - if (ret) { - if (ctx->open_rec) - tls_trim_both_msgs(sk, msg_pl->sg.size); - goto sendpage_end; - } + if (ctx->async_wait.err) + goto unlock; - if (ctx->open_rec) - goto alloc_payload; + /* Transmit if any encryptions have completed */ + if (test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) { + cancel_delayed_work(&ctx->tx_work.work); + tls_tx_records(sk, 0); } - if (num_async) { - /* Transmit if any encryptions have completed */ - if (test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) { - cancel_delayed_work(&ctx->tx_work.work); - tls_tx_records(sk, flags); - } - } -sendpage_end: - ret = sk_stream_error(sk, flags, ret); - return copied > 0 ? copied : ret; +unlock: + release_sock(sk); + mutex_unlock(&tls_ctx->tx_lock); } int tls_sw_sendpage_locked(struct sock *sk, struct page *page, int offset, size_t size, int flags) { + struct bio_vec bvec; + struct msghdr msg = { .msg_flags = flags | MSG_SPLICE_PAGES, }; + if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY | MSG_NO_SHARED_FRAGS)) return -EOPNOTSUPP; + if (flags & MSG_SENDPAGE_NOTLAST) + msg.msg_flags |= MSG_MORE; - return tls_sw_do_sendpage(sk, page, offset, size, flags); + bvec_set_page(&bvec, page, size, offset); + iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); + return tls_sw_sendmsg_locked(sk, &msg, size); } int tls_sw_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) { - struct tls_context *tls_ctx = tls_get_ctx(sk); - int ret; + struct bio_vec bvec; + struct msghdr msg = { .msg_flags = flags | MSG_SPLICE_PAGES, }; if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY)) return -EOPNOTSUPP; + if (flags & MSG_SENDPAGE_NOTLAST) + msg.msg_flags |= MSG_MORE; - ret = mutex_lock_interruptible(&tls_ctx->tx_lock); - if (ret) - return ret; - lock_sock(sk); - ret = tls_sw_do_sendpage(sk, page, offset, size, flags); - release_sock(sk); - mutex_unlock(&tls_ctx->tx_lock); - return ret; + bvec_set_page(&bvec, page, size, offset); + iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); + return tls_sw_sendmsg(sk, &msg, size); } static int @@ -2304,10 +2318,14 @@ static void tls_data_ready(struct sock *sk) struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); struct sk_psock *psock; + gfp_t alloc_save; trace_sk_data_ready(sk); + alloc_save = sk->sk_allocation; + sk->sk_allocation = GFP_ATOMIC; tls_strp_data_ready(&ctx->strp); + sk->sk_allocation = alloc_save; psock = sk_psock_get(sk); if (psock) { diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index cc695c9f09ec..653136d68b32 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1839,24 +1839,6 @@ static void maybe_add_creds(struct sk_buff *skb, const struct socket *sock, } } -static int maybe_init_creds(struct scm_cookie *scm, - struct socket *socket, - const struct sock *other) -{ - int err; - struct msghdr msg = { .msg_controllen = 0 }; - - err = scm_send(socket, &msg, scm, false); - if (err) - return err; - - if (unix_passcred_enabled(socket, other)) { - scm->pid = get_pid(task_tgid(current)); - current_uid_gid(&scm->creds.uid, &scm->creds.gid); - } - return err; -} - static bool unix_skb_scm_eq(struct sk_buff *skb, struct scm_cookie *scm) { @@ -2200,19 +2182,25 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, while (sent < len) { size = len - sent; - /* Keep two messages in the pipe so it schedules better */ - size = min_t(int, size, (sk->sk_sndbuf >> 1) - 64); + if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES)) { + skb = sock_alloc_send_pskb(sk, 0, 0, + msg->msg_flags & MSG_DONTWAIT, + &err, 0); + } else { + /* Keep two messages in the pipe so it schedules better */ + size = min_t(int, size, (sk->sk_sndbuf >> 1) - 64); - /* allow fallback to order-0 allocations */ - size = min_t(int, size, SKB_MAX_HEAD(0) + UNIX_SKB_FRAGS_SZ); + /* allow fallback to order-0 allocations */ + size = min_t(int, size, SKB_MAX_HEAD(0) + UNIX_SKB_FRAGS_SZ); - data_len = max_t(int, 0, size - SKB_MAX_HEAD(0)); + data_len = max_t(int, 0, size - SKB_MAX_HEAD(0)); - data_len = min_t(size_t, size, PAGE_ALIGN(data_len)); + data_len = min_t(size_t, size, PAGE_ALIGN(data_len)); - skb = sock_alloc_send_pskb(sk, size - data_len, data_len, - msg->msg_flags & MSG_DONTWAIT, &err, - get_order(UNIX_SKB_FRAGS_SZ)); + skb = sock_alloc_send_pskb(sk, size - data_len, data_len, + msg->msg_flags & MSG_DONTWAIT, &err, + get_order(UNIX_SKB_FRAGS_SZ)); + } if (!skb) goto out_err; @@ -2224,13 +2212,24 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, } fds_sent = true; - skb_put(skb, size - data_len); - skb->data_len = data_len; - skb->len = size; - err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size); - if (err) { - kfree_skb(skb); - goto out_err; + if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES)) { + err = skb_splice_from_iter(skb, &msg->msg_iter, size, + sk->sk_allocation); + if (err < 0) { + kfree_skb(skb); + goto out_err; + } + size = err; + refcount_add(size, &sk->sk_wmem_alloc); + } else { + skb_put(skb, size - data_len); + skb->data_len = data_len; + skb->len = size; + err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size); + if (err) { + kfree_skb(skb); + goto out_err; + } } unix_state_lock(other); @@ -2275,117 +2274,15 @@ out_err: static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page, int offset, size_t size, int flags) { - int err; - bool send_sigpipe = false; - bool init_scm = true; - struct scm_cookie scm; - struct sock *other, *sk = socket->sk; - struct sk_buff *skb, *newskb = NULL, *tail = NULL; - - if (flags & MSG_OOB) - return -EOPNOTSUPP; - - other = unix_peer(sk); - if (!other || sk->sk_state != TCP_ESTABLISHED) - return -ENOTCONN; - - if (false) { -alloc_skb: - unix_state_unlock(other); - mutex_unlock(&unix_sk(other)->iolock); - newskb = sock_alloc_send_pskb(sk, 0, 0, flags & MSG_DONTWAIT, - &err, 0); - if (!newskb) - goto err; - } - - /* we must acquire iolock as we modify already present - * skbs in the sk_receive_queue and mess with skb->len - */ - err = mutex_lock_interruptible(&unix_sk(other)->iolock); - if (err) { - err = flags & MSG_DONTWAIT ? -EAGAIN : -ERESTARTSYS; - goto err; - } + struct bio_vec bvec; + struct msghdr msg = { .msg_flags = flags | MSG_SPLICE_PAGES }; - if (sk->sk_shutdown & SEND_SHUTDOWN) { - err = -EPIPE; - send_sigpipe = true; - goto err_unlock; - } + if (flags & MSG_SENDPAGE_NOTLAST) + msg.msg_flags |= MSG_MORE; - unix_state_lock(other); - - if (sock_flag(other, SOCK_DEAD) || - other->sk_shutdown & RCV_SHUTDOWN) { - err = -EPIPE; - send_sigpipe = true; - goto err_state_unlock; - } - - if (init_scm) { - err = maybe_init_creds(&scm, socket, other); - if (err) - goto err_state_unlock; - init_scm = false; - } - - skb = skb_peek_tail(&other->sk_receive_queue); - if (tail && tail == skb) { - skb = newskb; - } else if (!skb || !unix_skb_scm_eq(skb, &scm)) { - if (newskb) { - skb = newskb; - } else { - tail = skb; - goto alloc_skb; - } - } else if (newskb) { - /* this is fast path, we don't necessarily need to - * call to kfree_skb even though with newskb == NULL - * this - does no harm - */ - consume_skb(newskb); - newskb = NULL; - } - - if (skb_append_pagefrags(skb, page, offset, size)) { - tail = skb; - goto alloc_skb; - } - - skb->len += size; - skb->data_len += size; - skb->truesize += size; - refcount_add(size, &sk->sk_wmem_alloc); - - if (newskb) { - err = unix_scm_to_skb(&scm, skb, false); - if (err) - goto err_state_unlock; - spin_lock(&other->sk_receive_queue.lock); - __skb_queue_tail(&other->sk_receive_queue, newskb); - spin_unlock(&other->sk_receive_queue.lock); - } - - unix_state_unlock(other); - mutex_unlock(&unix_sk(other)->iolock); - - other->sk_data_ready(other); - scm_destroy(&scm); - return size; - -err_state_unlock: - unix_state_unlock(other); -err_unlock: - mutex_unlock(&unix_sk(other)->iolock); -err: - kfree_skb(newskb); - if (send_sigpipe && !(flags & MSG_NOSIGNAL)) - send_sig(SIGPIPE, current, 0); - if (!init_scm) - scm_destroy(&scm); - return err; + bvec_set_page(&bvec, page, size, offset); + iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); + return unix_stream_sendmsg(socket, &msg, size); } static int unix_seqpacket_sendmsg(struct socket *sock, struct msghdr *msg, @@ -2553,7 +2450,7 @@ static int unix_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { struct unix_sock *u = unix_sk(sk); struct sk_buff *skb; - int err, copied; + int err; mutex_lock(&u->iolock); skb = skb_recv_datagram(sk, MSG_DONTWAIT, &err); @@ -2561,10 +2458,7 @@ static int unix_read_skb(struct sock *sk, skb_read_actor_t recv_actor) if (!skb) return err; - copied = recv_actor(sk, skb); - kfree_skb(skb); - - return copied; + return recv_actor(sk, skb); } /* diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 413407bb646c..efb8a0937a13 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1462,7 +1462,7 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr, vsock_transport_cancel_pkt(vsk); vsock_remove_connected(vsk); goto out_wait; - } else if (timeout == 0) { + } else if ((sk->sk_state != TCP_ESTABLISHED) && (timeout == 0)) { err = -ETIMEDOUT; sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index e4878551f140..b769fc258931 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1441,7 +1441,6 @@ int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t recv_acto struct sock *sk = sk_vsock(vsk); struct sk_buff *skb; int off = 0; - int copied; int err; spin_lock_bh(&vvs->rx_lock); @@ -1454,9 +1453,7 @@ int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t recv_acto if (!skb) return err; - copied = recv_actor(sk, skb); - kfree_skb(skb); - return copied; + return recv_actor(sk, skb); } EXPORT_SYMBOL_GPL(virtio_transport_read_skb); diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index b2df1e0f8153..26f6d304451e 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -350,7 +350,7 @@ void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs) { struct xsk_dma_map *dma_map; - if (pool->dma_pages_cnt == 0) + if (!pool->dma_pages) return; dma_map = xp_find_dma_map(pool); @@ -364,6 +364,7 @@ void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs) __xp_dma_unmap(dma_map, attrs); kvfree(pool->dma_pages); + pool->dma_pages = NULL; pool->dma_pages_cnt = 0; pool->dev = NULL; } @@ -503,7 +504,7 @@ static struct xdp_buff_xsk *__xp_alloc(struct xsk_buff_pool *pool) if (pool->unaligned) { xskb = pool->free_heads[--pool->free_heads_cnt]; xp_init_xskb_addr(xskb, pool, addr); - if (pool->dma_pages_cnt) + if (pool->dma_pages) xp_init_xskb_dma(xskb, pool, pool->dma_pages, addr); } else { xskb = &pool->heads[xp_aligned_extract_idx(pool, addr)]; @@ -569,7 +570,7 @@ static u32 xp_alloc_new_from_fq(struct xsk_buff_pool *pool, struct xdp_buff **xd if (pool->unaligned) { xskb = pool->free_heads[--pool->free_heads_cnt]; xp_init_xskb_addr(xskb, pool, addr); - if (pool->dma_pages_cnt) + if (pool->dma_pages) xp_init_xskb_dma(xskb, pool, pool->dma_pages, addr); } else { xskb = &pool->heads[xp_aligned_extract_idx(pool, addr)]; diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c index 872b80188e83..3504925babdb 100644 --- a/net/xfrm/espintcp.c +++ b/net/xfrm/espintcp.c @@ -205,14 +205,16 @@ static int espintcp_sendskb_locked(struct sock *sk, struct espintcp_msg *emsg, static int espintcp_sendskmsg_locked(struct sock *sk, struct espintcp_msg *emsg, int flags) { + struct msghdr msghdr = { .msg_flags = flags | MSG_SPLICE_PAGES, }; struct sk_msg *skmsg = &emsg->skmsg; struct scatterlist *sg; int done = 0; int ret; - flags |= MSG_SENDPAGE_NOTLAST; + msghdr.msg_flags |= MSG_SENDPAGE_NOTLAST; sg = &skmsg->sg.data[skmsg->sg.start]; do { + struct bio_vec bvec; size_t size = sg->length - emsg->offset; int offset = sg->offset + emsg->offset; struct page *p; @@ -220,11 +222,13 @@ static int espintcp_sendskmsg_locked(struct sock *sk, emsg->offset = 0; if (sg_is_last(sg)) - flags &= ~MSG_SENDPAGE_NOTLAST; + msghdr.msg_flags &= ~MSG_SENDPAGE_NOTLAST; p = sg_page(sg); retry: - ret = do_tcp_sendpages(sk, p, offset, size, flags); + bvec_set_page(&bvec, p, size, offset); + iov_iter_bvec(&msghdr.msg_iter, ITER_SOURCE, &bvec, 1, size); + ret = tcp_sendmsg_locked(sk, &msghdr, size); if (ret < 0) { emsg->offset = offset - sg->offset; skmsg->sg.start += done; diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index bef28c6187eb..408f5e55744e 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -378,7 +378,7 @@ int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp, break; default: xdo->dev = NULL; - dev_put(dev); + netdev_put(dev, &xdo->dev_tracker); NL_SET_ERR_MSG(extack, "Unrecognized offload direction"); return -EINVAL; } diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index 35279c220bd7..1f99dc469027 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -310,52 +310,6 @@ static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet) skb->mark = 0; } -static int xfrmi_input(struct sk_buff *skb, int nexthdr, __be32 spi, - int encap_type, unsigned short family) -{ - struct sec_path *sp; - - sp = skb_sec_path(skb); - if (sp && (sp->len || sp->olen) && - !xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) - goto discard; - - XFRM_SPI_SKB_CB(skb)->family = family; - if (family == AF_INET) { - XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); - XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; - } else { - XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); - XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; - } - - return xfrm_input(skb, nexthdr, spi, encap_type); -discard: - kfree_skb(skb); - return 0; -} - -static int xfrmi4_rcv(struct sk_buff *skb) -{ - return xfrmi_input(skb, ip_hdr(skb)->protocol, 0, 0, AF_INET); -} - -static int xfrmi6_rcv(struct sk_buff *skb) -{ - return xfrmi_input(skb, skb_network_header(skb)[IP6CB(skb)->nhoff], - 0, 0, AF_INET6); -} - -static int xfrmi4_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) -{ - return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET); -} - -static int xfrmi6_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) -{ - return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET6); -} - static int xfrmi_rcv_cb(struct sk_buff *skb, int err) { const struct xfrm_mode *inner_mode; @@ -991,8 +945,8 @@ static struct pernet_operations xfrmi_net_ops = { }; static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = { - .handler = xfrmi6_rcv, - .input_handler = xfrmi6_input, + .handler = xfrm6_rcv, + .input_handler = xfrm_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 10, @@ -1042,8 +996,8 @@ static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = { #endif static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = { - .handler = xfrmi4_rcv, - .input_handler = xfrmi4_input, + .handler = xfrm4_rcv, + .input_handler = xfrm_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 10, diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 5c61ec04b839..6d15788b5123 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3312,7 +3312,7 @@ xfrm_secpath_reject(int idx, struct sk_buff *skb, const struct flowi *fl) static inline int xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, - unsigned short family) + unsigned short family, u32 if_id) { if (xfrm_state_kern(x)) return tmpl->optional && !xfrm_state_addr_cmp(tmpl, x, tmpl->encap_family); @@ -3323,7 +3323,8 @@ xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, (tmpl->allalgs || (tmpl->aalgos & (1<<x->props.aalgo)) || !(xfrm_id_proto_match(tmpl->id.proto, IPSEC_PROTO_ANY))) && !(x->props.mode != XFRM_MODE_TRANSPORT && - xfrm_state_addr_cmp(tmpl, x, family)); + xfrm_state_addr_cmp(tmpl, x, family)) && + (if_id == 0 || if_id == x->if_id); } /* @@ -3335,7 +3336,7 @@ xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, */ static inline int xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int start, - unsigned short family) + unsigned short family, u32 if_id) { int idx = start; @@ -3345,7 +3346,7 @@ xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int star } else start = -1; for (; idx < sp->len; idx++) { - if (xfrm_state_ok(tmpl, sp->xvec[idx], family)) + if (xfrm_state_ok(tmpl, sp->xvec[idx], family, if_id)) return ++idx; if (sp->xvec[idx]->props.mode != XFRM_MODE_TRANSPORT) { if (start == -1) @@ -3712,12 +3713,6 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, } xfrm_nr = ti; - if (net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK && - !xfrm_nr) { - XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES); - goto reject; - } - if (npols > 1) { xfrm_tmpl_sort(stp, tpp, xfrm_nr, family); tpp = stp; @@ -3730,7 +3725,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, * are implied between each two transformations. */ for (i = xfrm_nr-1, k = 0; i >= 0; i--) { - k = xfrm_policy_ok(tpp[i], sp, k, family); + k = xfrm_policy_ok(tpp[i], sp, k, family, if_id); if (k < 0) { if (k < -1) /* "-2 - errored_index" returned */ @@ -3745,9 +3740,6 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, goto reject; } - if (if_id) - secpath_reset(skb); - xfrm_pols_put(pols, npols); return 1; } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index d720e163ae6e..c34a2a06ca94 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1770,7 +1770,7 @@ static void copy_templates(struct xfrm_policy *xp, struct xfrm_user_tmpl *ut, } static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family, - struct netlink_ext_ack *extack) + int dir, struct netlink_ext_ack *extack) { u16 prev_family; int i; @@ -1796,6 +1796,10 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family, switch (ut[i].mode) { case XFRM_MODE_TUNNEL: case XFRM_MODE_BEET: + if (ut[i].optional && dir == XFRM_POLICY_OUT) { + NL_SET_ERR_MSG(extack, "Mode in optional template not allowed in outbound policy"); + return -EINVAL; + } break; default: if (ut[i].family != prev_family) { @@ -1833,7 +1837,7 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family, } static int copy_from_user_tmpl(struct xfrm_policy *pol, struct nlattr **attrs, - struct netlink_ext_ack *extack) + int dir, struct netlink_ext_ack *extack) { struct nlattr *rt = attrs[XFRMA_TMPL]; @@ -1844,7 +1848,7 @@ static int copy_from_user_tmpl(struct xfrm_policy *pol, struct nlattr **attrs, int nr = nla_len(rt) / sizeof(*utmpl); int err; - err = validate_tmpl(nr, utmpl, pol->family, extack); + err = validate_tmpl(nr, utmpl, pol->family, dir, extack); if (err) return err; @@ -1921,7 +1925,7 @@ static struct xfrm_policy *xfrm_policy_construct(struct net *net, if (err) goto error; - if (!(err = copy_from_user_tmpl(xp, attrs, extack))) + if (!(err = copy_from_user_tmpl(xp, attrs, p->dir, extack))) err = copy_from_user_sec_ctx(xp, attrs); if (err) goto error; @@ -1980,6 +1984,7 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) { xfrm_dev_policy_delete(xp); + xfrm_dev_policy_free(xp); security_xfrm_policy_free(xp->security); kfree(xp); return err; @@ -3499,7 +3504,7 @@ static struct xfrm_policy *xfrm_compile_policy(struct sock *sk, int opt, return NULL; nr = ((len - sizeof(*p)) / sizeof(*ut)); - if (validate_tmpl(nr, ut, p->sel.family, NULL)) + if (validate_tmpl(nr, ut, p->sel.family, p->dir, NULL)) return NULL; if (p->dir > XFRM_POLICY_OUT) diff --git a/samples/bpf/hbm.c b/samples/bpf/hbm.c index 6448b7826107..bf66277115e2 100644 --- a/samples/bpf/hbm.c +++ b/samples/bpf/hbm.c @@ -498,7 +498,6 @@ int main(int argc, char **argv) "Option -%c requires an argument.\n\n", optopt); case 'h': - __fallthrough; default: Usage(); return 0; diff --git a/samples/bpf/tcp_basertt_kern.c b/samples/bpf/tcp_basertt_kern.c index 8dfe09a92fec..822b0742b815 100644 --- a/samples/bpf/tcp_basertt_kern.c +++ b/samples/bpf/tcp_basertt_kern.c @@ -47,7 +47,7 @@ int bpf_basertt(struct bpf_sock_ops *skops) case BPF_SOCK_OPS_BASE_RTT: n = bpf_getsockopt(skops, SOL_TCP, TCP_CONGESTION, cong, sizeof(cong)); - if (!n && !__builtin_memcmp(cong, nv, sizeof(nv)+1)) { + if (!n && !__builtin_memcmp(cong, nv, sizeof(nv))) { /* Set base_rtt to 80us */ rv = 80; } else if (n) { diff --git a/scripts/pahole-flags.sh b/scripts/pahole-flags.sh index 1f1f1d397c39..728d55190d97 100755 --- a/scripts/pahole-flags.sh +++ b/scripts/pahole-flags.sh @@ -23,5 +23,8 @@ if [ "${pahole_ver}" -ge "124" ]; then # see PAHOLE_HAS_LANG_EXCLUDE extra_paholeopt="${extra_paholeopt} --lang_exclude=rust" fi +if [ "${pahole_ver}" -ge "125" ]; then + extra_paholeopt="${extra_paholeopt} --skip_encoding_btf_inconsistent_proto --btf_gen_optimized" +fi echo ${extra_paholeopt} diff --git a/security/selinux/Makefile b/security/selinux/Makefile index 0aecf9334ec3..8b21520bd4b9 100644 --- a/security/selinux/Makefile +++ b/security/selinux/Makefile @@ -26,5 +26,9 @@ quiet_cmd_flask = GEN $(obj)/flask.h $(obj)/av_permissions.h cmd_flask = $< $(obj)/flask.h $(obj)/av_permissions.h targets += flask.h av_permissions.h -$(obj)/flask.h $(obj)/av_permissions.h &: scripts/selinux/genheaders/genheaders FORCE +# once make >= 4.3 is required, we can use grouped targets in the rule below, +# which basically involves adding both headers and a '&' before the colon, see +# the example below: +# $(obj)/flask.h $(obj)/av_permissions.h &: scripts/selinux/... +$(obj)/flask.h: scripts/selinux/genheaders/genheaders FORCE $(call if_changed,flask) diff --git a/sound/core/oss/pcm_plugin.h b/sound/core/oss/pcm_plugin.h index 46e273bd4a78..50a6b50f5db4 100644 --- a/sound/core/oss/pcm_plugin.h +++ b/sound/core/oss/pcm_plugin.h @@ -141,6 +141,14 @@ int snd_pcm_area_copy(const struct snd_pcm_channel_area *src_channel, void *snd_pcm_plug_buf_alloc(struct snd_pcm_substream *plug, snd_pcm_uframes_t size); void snd_pcm_plug_buf_unlock(struct snd_pcm_substream *plug, void *ptr); +#else + +static inline snd_pcm_sframes_t snd_pcm_plug_client_size(struct snd_pcm_substream *handle, snd_pcm_uframes_t drv_size) { return drv_size; } +static inline snd_pcm_sframes_t snd_pcm_plug_slave_size(struct snd_pcm_substream *handle, snd_pcm_uframes_t clt_size) { return clt_size; } +static inline int snd_pcm_plug_slave_format(int format, const struct snd_mask *format_mask) { return format; } + +#endif + snd_pcm_sframes_t snd_pcm_oss_write3(struct snd_pcm_substream *substream, const char *ptr, snd_pcm_uframes_t size, int in_kernel); @@ -151,14 +159,6 @@ snd_pcm_sframes_t snd_pcm_oss_writev3(struct snd_pcm_substream *substream, snd_pcm_sframes_t snd_pcm_oss_readv3(struct snd_pcm_substream *substream, void **bufs, snd_pcm_uframes_t frames); -#else - -static inline snd_pcm_sframes_t snd_pcm_plug_client_size(struct snd_pcm_substream *handle, snd_pcm_uframes_t drv_size) { return drv_size; } -static inline snd_pcm_sframes_t snd_pcm_plug_slave_size(struct snd_pcm_substream *handle, snd_pcm_uframes_t clt_size) { return clt_size; } -static inline int snd_pcm_plug_slave_format(int format, const struct snd_mask *format_mask) { return format; } - -#endif - #ifdef PLUGIN_DEBUG #define pdprintf(fmt, args...) printk(KERN_DEBUG "plugin: " fmt, ##args) #else diff --git a/sound/firewire/digi00x/digi00x-stream.c b/sound/firewire/digi00x/digi00x-stream.c index a15f55b0dce3..295163bb8abb 100644 --- a/sound/firewire/digi00x/digi00x-stream.c +++ b/sound/firewire/digi00x/digi00x-stream.c @@ -259,8 +259,10 @@ int snd_dg00x_stream_init_duplex(struct snd_dg00x *dg00x) return err; err = init_stream(dg00x, &dg00x->tx_stream); - if (err < 0) + if (err < 0) { destroy_stream(dg00x, &dg00x->rx_stream); + return err; + } err = amdtp_domain_init(&dg00x->domain); if (err < 0) { diff --git a/sound/hda/hdac_device.c b/sound/hda/hdac_device.c index accc9d279ce5..6c043fbd606f 100644 --- a/sound/hda/hdac_device.c +++ b/sound/hda/hdac_device.c @@ -611,7 +611,7 @@ EXPORT_SYMBOL_GPL(snd_hdac_power_up_pm); int snd_hdac_keep_power_up(struct hdac_device *codec) { if (!atomic_inc_not_zero(&codec->in_pm)) { - int ret = pm_runtime_get_if_in_use(&codec->dev); + int ret = pm_runtime_get_if_active(&codec->dev, true); if (!ret) return -1; if (ret < 0) diff --git a/sound/pci/cs46xx/cs46xx_lib.c b/sound/pci/cs46xx/cs46xx_lib.c index 62f45847b351..7d882b33d45e 100644 --- a/sound/pci/cs46xx/cs46xx_lib.c +++ b/sound/pci/cs46xx/cs46xx_lib.c @@ -531,7 +531,7 @@ static int load_firmware(struct snd_cs46xx *chip) return err; } -int snd_cs46xx_download_image(struct snd_cs46xx *chip) +static __maybe_unused int snd_cs46xx_download_image(struct snd_cs46xx *chip) { int idx, err; unsigned int offset = 0; diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index fc114e522480..dbf7aa88e0e3 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -1155,8 +1155,8 @@ static bool path_has_mixer(struct hda_codec *codec, int path_idx, int ctl_type) return path && path->ctls[ctl_type]; } -static const char * const channel_name[4] = { - "Front", "Surround", "CLFE", "Side" +static const char * const channel_name[] = { + "Front", "Surround", "CLFE", "Side", "Back", }; /* give some appropriate ctl name prefix for the given line out channel */ @@ -1182,7 +1182,7 @@ static const char *get_line_out_pfx(struct hda_codec *codec, int ch, /* multi-io channels */ if (ch >= cfg->line_outs) - return channel_name[ch]; + goto fixed_name; switch (cfg->line_out_type) { case AUTO_PIN_SPEAKER_OUT: @@ -1234,6 +1234,7 @@ static const char *get_line_out_pfx(struct hda_codec *codec, int ch, if (cfg->line_outs == 1 && !spec->multi_ios) return "Line Out"; + fixed_name: if (ch >= ARRAY_SIZE(channel_name)) { snd_BUG(); return "PCM"; diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index 099722ebaed8..748a3c40966e 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -1306,6 +1306,7 @@ static const struct snd_pci_quirk ca0132_quirks[] = { SND_PCI_QUIRK(0x1458, 0xA026, "Gigabyte G1.Sniper Z97", QUIRK_R3DI), SND_PCI_QUIRK(0x1458, 0xA036, "Gigabyte GA-Z170X-Gaming 7", QUIRK_R3DI), SND_PCI_QUIRK(0x3842, 0x1038, "EVGA X99 Classified", QUIRK_R3DI), + SND_PCI_QUIRK(0x3842, 0x104b, "EVGA X299 Dark", QUIRK_R3DI), SND_PCI_QUIRK(0x3842, 0x1055, "EVGA Z390 DARK", QUIRK_R3DI), SND_PCI_QUIRK(0x1102, 0x0013, "Recon3D", QUIRK_R3D), SND_PCI_QUIRK(0x1102, 0x0018, "Recon3D", QUIRK_R3D), diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 64a944016c78..5c0b1a09fd57 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -4589,6 +4589,11 @@ HDA_CODEC_ENTRY(0x10de009d, "GPU 9d HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de009e, "GPU 9e HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de009f, "GPU 9f HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de00a0, "GPU a0 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a3, "GPU a3 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a4, "GPU a4 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a5, "GPU a5 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a6, "GPU a6 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a7, "GPU a7 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de8001, "MCP73 HDMI", patch_nvhdmi_2ch), HDA_CODEC_ENTRY(0x10de8067, "MCP67/68 HDMI", patch_nvhdmi_2ch), HDA_CODEC_ENTRY(0x67663d82, "Arise 82 HDMI/DP", patch_gf_hdmi), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 172ffc2c332b..7b5f194513c7 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -7063,6 +7063,8 @@ enum { ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, ALC295_FIXUP_DISABLE_DAC3, ALC285_FIXUP_SPEAKER2_TO_DAC1, + ALC285_FIXUP_ASUS_SPEAKER2_TO_DAC1, + ALC285_FIXUP_ASUS_HEADSET_MIC, ALC280_FIXUP_HP_HEADSET_MIC, ALC221_FIXUP_HP_FRONT_MIC, ALC292_FIXUP_TPT460, @@ -8033,6 +8035,22 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_THINKPAD_ACPI }, + [ALC285_FIXUP_ASUS_SPEAKER2_TO_DAC1] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_speaker2_to_dac1, + .chained = true, + .chain_id = ALC245_FIXUP_CS35L41_SPI_2 + }, + [ALC285_FIXUP_ASUS_HEADSET_MIC] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x03a11050 }, + { 0x1b, 0x03a11c30 }, + { } + }, + .chained = true, + .chain_id = ALC285_FIXUP_ASUS_SPEAKER2_TO_DAC1 + }, [ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -9363,7 +9381,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x802f, "HP Z240", ALC221_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x8077, "HP", ALC256_FIXUP_HP_HEADSET_MIC), SND_PCI_QUIRK(0x103c, 0x8158, "HP", ALC256_FIXUP_HP_HEADSET_MIC), - SND_PCI_QUIRK(0x103c, 0x820d, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3), + SND_PCI_QUIRK(0x103c, 0x820d, "HP Pavilion 15", ALC295_FIXUP_HP_X360), SND_PCI_QUIRK(0x103c, 0x8256, "HP", ALC221_FIXUP_HP_FRONT_MIC), SND_PCI_QUIRK(0x103c, 0x827e, "HP x360", ALC295_FIXUP_HP_X360), SND_PCI_QUIRK(0x103c, 0x827f, "HP x360", ALC269_FIXUP_HP_MUTE_LED_MIC3), @@ -9458,7 +9476,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8aa3, "HP ProBook 450 G9 (MB 8AA1)", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8aa8, "HP EliteBook 640 G9 (MB 8AA6)", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8aab, "HP EliteBook 650 G9 (MB 8AA9)", ALC236_FIXUP_HP_GPIO_LED), - SND_PCI_QUIRK(0x103c, 0x8abb, "HP ZBook Firefly 14 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8abb, "HP ZBook Firefly 14 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad1, "HP EliteBook 840 14 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad2, "HP EliteBook 860 16 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b42, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), @@ -9469,8 +9487,13 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8b47, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b5d, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b5e, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8b63, "HP Elite Dragonfly 13.5 inch G4", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b65, "HP ProBook 455 15.6 inch G10 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b66, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8b70, "HP EliteBook 835 G10", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8b72, "HP EliteBook 845 G10", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8b74, "HP EliteBook 845W G10", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8b77, "HP ElieBook 865 G10", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8b7a, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b7d, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b87, "HP", ALC236_FIXUP_HP_GPIO_LED), @@ -9480,7 +9503,9 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8b8f, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b92, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8b97, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8bf0, "HP", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c26, "HP HP EliteBook 800G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), @@ -9500,6 +9525,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1313, "Asus K42JZ", ALC269VB_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK), + SND_PCI_QUIRK(0x1043, 0x1473, "ASUS GU604V", ALC285_FIXUP_ASUS_HEADSET_MIC), + SND_PCI_QUIRK(0x1043, 0x1483, "ASUS GU603V", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A), SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK), SND_PCI_QUIRK(0x1043, 0x1683, "ASUS UM3402YAR", ALC287_FIXUP_CS35L41_I2C_2), @@ -9522,6 +9549,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1b13, "Asus U41SV", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), + SND_PCI_QUIRK(0x1043, 0x1c62, "ASUS GU603", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1c92, "ASUS ROG Strix G15", ALC285_FIXUP_ASUS_G533Z_PINS), SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x1d42, "ASUS Zephyrus G14 2022", ALC289_FIXUP_ASUS_GA401), @@ -9618,6 +9646,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0x7716, "Clevo NS50PU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x7717, "Clevo NS70PU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x7718, "Clevo L140PU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x7724, "Clevo L140AU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8228, "Clevo NR40BU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8520, "Clevo NH50D[CD]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8521, "Clevo NH77D[CD]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), @@ -11663,6 +11692,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x1632, "HP RP5800", ALC662_FIXUP_HP_RP5800), SND_PCI_QUIRK(0x103c, 0x870c, "HP", ALC897_FIXUP_HP_HSMIC_VERB), SND_PCI_QUIRK(0x103c, 0x8719, "HP", ALC897_FIXUP_HP_HSMIC_VERB), + SND_PCI_QUIRK(0x103c, 0x872b, "HP", ALC897_FIXUP_HP_HSMIC_VERB), SND_PCI_QUIRK(0x103c, 0x873e, "HP", ALC671_FIXUP_HP_HEADSET_MIC2), SND_PCI_QUIRK(0x103c, 0x877e, "HP 288 Pro G6", ALC671_FIXUP_HP_HEADSET_MIC2), SND_PCI_QUIRK(0x103c, 0x885f, "HP 288 Pro G8", ALC671_FIXUP_HP_HEADSET_MIC2), @@ -11689,6 +11719,8 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x32cb, "Lenovo ThinkCentre M70", ALC897_FIXUP_HEADSET_MIC_PIN), SND_PCI_QUIRK(0x17aa, 0x32cf, "Lenovo ThinkCentre M950", ALC897_FIXUP_HEADSET_MIC_PIN), SND_PCI_QUIRK(0x17aa, 0x32f7, "Lenovo ThinkCentre M90", ALC897_FIXUP_HEADSET_MIC_PIN), + SND_PCI_QUIRK(0x17aa, 0x3321, "Lenovo ThinkCentre M70 Gen4", ALC897_FIXUP_HEADSET_MIC_PIN), + SND_PCI_QUIRK(0x17aa, 0x331b, "Lenovo ThinkCentre M90 Gen4", ALC897_FIXUP_HEADSET_MIC_PIN), SND_PCI_QUIRK(0x17aa, 0x3742, "Lenovo TianYi510Pro-14IOB", ALC897_FIXUP_HEADSET_MIC_PIN2), SND_PCI_QUIRK(0x17aa, 0x38af, "Lenovo Ideapad Y550P", ALC662_FIXUP_IDEAPAD), SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Ideapad Y550", ALC662_FIXUP_IDEAPAD), diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 0bc6e4066d0f..4406a5def076 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -311,6 +311,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_BOARD_NAME, "8A22"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "System76"), + DMI_MATCH(DMI_PRODUCT_VERSION, "pang12"), + } + }, {} }; diff --git a/sound/soc/codecs/cs35l41-lib.c b/sound/soc/codecs/cs35l41-lib.c index 8538e2871c5f..1e4205295a0d 100644 --- a/sound/soc/codecs/cs35l41-lib.c +++ b/sound/soc/codecs/cs35l41-lib.c @@ -46,7 +46,7 @@ static const struct reg_default cs35l41_reg[] = { { CS35L41_DSP1_RX5_SRC, 0x00000020 }, { CS35L41_DSP1_RX6_SRC, 0x00000021 }, { CS35L41_DSP1_RX7_SRC, 0x0000003A }, - { CS35L41_DSP1_RX8_SRC, 0x00000001 }, + { CS35L41_DSP1_RX8_SRC, 0x0000003B }, { CS35L41_NGATE1_SRC, 0x00000008 }, { CS35L41_NGATE2_SRC, 0x00000009 }, { CS35L41_AMP_DIG_VOL_CTRL, 0x00008000 }, @@ -58,8 +58,8 @@ static const struct reg_default cs35l41_reg[] = { { CS35L41_IRQ1_MASK2, 0xFFFFFFFF }, { CS35L41_IRQ1_MASK3, 0xFFFF87FF }, { CS35L41_IRQ1_MASK4, 0xFEFFFFFF }, - { CS35L41_GPIO1_CTRL1, 0xE1000001 }, - { CS35L41_GPIO2_CTRL1, 0xE1000001 }, + { CS35L41_GPIO1_CTRL1, 0x81000001 }, + { CS35L41_GPIO2_CTRL1, 0x81000001 }, { CS35L41_MIXER_NGATE_CFG, 0x00000000 }, { CS35L41_MIXER_NGATE_CH1_CFG, 0x00000303 }, { CS35L41_MIXER_NGATE_CH2_CFG, 0x00000303 }, diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c index 46762f7f1449..d1677d76d018 100644 --- a/sound/soc/codecs/cs35l56.c +++ b/sound/soc/codecs/cs35l56.c @@ -852,10 +852,11 @@ static void cs35l56_dsp_work(struct work_struct *work) */ if (cs35l56->sdw_peripheral) { cs35l56->sdw_irq_no_unmask = true; - cancel_work_sync(&cs35l56->sdw_irq_work); + flush_work(&cs35l56->sdw_irq_work); sdw_write_no_pm(cs35l56->sdw_peripheral, CS35L56_SDW_GEN_INT_MASK_1, 0); sdw_read_no_pm(cs35l56->sdw_peripheral, CS35L56_SDW_GEN_INT_STAT_1); sdw_write_no_pm(cs35l56->sdw_peripheral, CS35L56_SDW_GEN_INT_STAT_1, 0xFF); + flush_work(&cs35l56->sdw_irq_work); } ret = cs35l56_mbox_send(cs35l56, CS35L56_MBOX_CMD_SHUTDOWN); diff --git a/sound/soc/codecs/lpass-tx-macro.c b/sound/soc/codecs/lpass-tx-macro.c index da6fcf7f0991..de978c3d70b7 100644 --- a/sound/soc/codecs/lpass-tx-macro.c +++ b/sound/soc/codecs/lpass-tx-macro.c @@ -746,6 +746,8 @@ static int tx_macro_put_dec_enum(struct snd_kcontrol *kcontrol, struct tx_macro *tx = snd_soc_component_get_drvdata(component); val = ucontrol->value.enumerated.item[0]; + if (val >= e->items) + return -EINVAL; switch (e->reg) { case CDC_TX_INP_MUX_ADC_MUX0_CFG0: @@ -772,6 +774,9 @@ static int tx_macro_put_dec_enum(struct snd_kcontrol *kcontrol, case CDC_TX_INP_MUX_ADC_MUX7_CFG0: mic_sel_reg = CDC_TX7_TX_PATH_CFG0; break; + default: + dev_err(component->dev, "Error in configuration!!\n"); + return -EINVAL; } if (val != 0) { diff --git a/sound/soc/codecs/rt5682-i2c.c b/sound/soc/codecs/rt5682-i2c.c index 2935c1bb81f3..5bc46b041786 100644 --- a/sound/soc/codecs/rt5682-i2c.c +++ b/sound/soc/codecs/rt5682-i2c.c @@ -267,7 +267,9 @@ static int rt5682_i2c_probe(struct i2c_client *i2c) ret = devm_request_threaded_irq(&i2c->dev, i2c->irq, NULL, rt5682_irq, IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING | IRQF_ONESHOT, "rt5682", rt5682); - if (ret) + if (!ret) + rt5682->irq = i2c->irq; + else dev_err(&i2c->dev, "Failed to reguest IRQ: %d\n", ret); } diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index f6c798b65c08..5d992543b791 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -2959,6 +2959,9 @@ static int rt5682_suspend(struct snd_soc_component *component) if (rt5682->is_sdw) return 0; + if (rt5682->irq) + disable_irq(rt5682->irq); + cancel_delayed_work_sync(&rt5682->jack_detect_work); cancel_delayed_work_sync(&rt5682->jd_check_work); if (rt5682->hs_jack && (rt5682->jack_type & SND_JACK_HEADSET) == SND_JACK_HEADSET) { @@ -3027,6 +3030,9 @@ static int rt5682_resume(struct snd_soc_component *component) mod_delayed_work(system_power_efficient_wq, &rt5682->jack_detect_work, msecs_to_jiffies(0)); + if (rt5682->irq) + enable_irq(rt5682->irq); + return 0; } #else diff --git a/sound/soc/codecs/rt5682.h b/sound/soc/codecs/rt5682.h index d568c6993c33..e8efd8a84a6c 100644 --- a/sound/soc/codecs/rt5682.h +++ b/sound/soc/codecs/rt5682.h @@ -1462,6 +1462,7 @@ struct rt5682_priv { int pll_out[RT5682_PLLS]; int jack_type; + int irq; int irq_work_delay_time; }; diff --git a/sound/soc/codecs/ssm2602.c b/sound/soc/codecs/ssm2602.c index 00b60369b029..c29324403e9d 100644 --- a/sound/soc/codecs/ssm2602.c +++ b/sound/soc/codecs/ssm2602.c @@ -53,6 +53,18 @@ static const struct reg_default ssm2602_reg[SSM2602_CACHEREGNUM] = { { .reg = 0x09, .def = 0x0000 } }; +/* + * ssm2602 register patch + * Workaround for playback distortions after power up: activates digital + * core, and then powers on output, DAC, and whole chip at the same time + */ + +static const struct reg_sequence ssm2602_patch[] = { + { SSM2602_ACTIVE, 0x01 }, + { SSM2602_PWR, 0x07 }, + { SSM2602_RESET, 0x00 }, +}; + /*Appending several "None"s just for OSS mixer use*/ static const char *ssm2602_input_select[] = { @@ -598,6 +610,9 @@ static int ssm260x_component_probe(struct snd_soc_component *component) return ret; } + regmap_register_patch(ssm2602->regmap, ssm2602_patch, + ARRAY_SIZE(ssm2602_patch)); + /* set the update bits */ regmap_update_bits(ssm2602->regmap, SSM2602_LINVOL, LINVOL_LRIN_BOTH, LINVOL_LRIN_BOTH); diff --git a/sound/soc/dwc/dwc-i2s.c b/sound/soc/dwc/dwc-i2s.c index acdf98b2ee9c..399a489f24f2 100644 --- a/sound/soc/dwc/dwc-i2s.c +++ b/sound/soc/dwc/dwc-i2s.c @@ -132,13 +132,13 @@ static irqreturn_t i2s_irq_handler(int irq, void *dev_id) /* Error Handling: TX */ if (isr[i] & ISR_TXFO) { - dev_err(dev->dev, "TX overrun (ch_id=%d)\n", i); + dev_err_ratelimited(dev->dev, "TX overrun (ch_id=%d)\n", i); irq_valid = true; } /* Error Handling: TX */ if (isr[i] & ISR_RXFO) { - dev_err(dev->dev, "RX overrun (ch_id=%d)\n", i); + dev_err_ratelimited(dev->dev, "RX overrun (ch_id=%d)\n", i); irq_valid = true; } } @@ -183,30 +183,6 @@ static void i2s_stop(struct dw_i2s_dev *dev, } } -static int dw_i2s_startup(struct snd_pcm_substream *substream, - struct snd_soc_dai *cpu_dai) -{ - struct dw_i2s_dev *dev = snd_soc_dai_get_drvdata(cpu_dai); - union dw_i2s_snd_dma_data *dma_data = NULL; - - if (!(dev->capability & DWC_I2S_RECORD) && - (substream->stream == SNDRV_PCM_STREAM_CAPTURE)) - return -EINVAL; - - if (!(dev->capability & DWC_I2S_PLAY) && - (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)) - return -EINVAL; - - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) - dma_data = &dev->play_dma_data; - else if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) - dma_data = &dev->capture_dma_data; - - snd_soc_dai_set_dma_data(cpu_dai, substream, (void *)dma_data); - - return 0; -} - static void dw_i2s_config(struct dw_i2s_dev *dev, int stream) { u32 ch_reg; @@ -305,12 +281,6 @@ static int dw_i2s_hw_params(struct snd_pcm_substream *substream, return 0; } -static void dw_i2s_shutdown(struct snd_pcm_substream *substream, - struct snd_soc_dai *dai) -{ - snd_soc_dai_set_dma_data(dai, substream, NULL); -} - static int dw_i2s_prepare(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { @@ -382,8 +352,6 @@ static int dw_i2s_set_fmt(struct snd_soc_dai *cpu_dai, unsigned int fmt) } static const struct snd_soc_dai_ops dw_i2s_dai_ops = { - .startup = dw_i2s_startup, - .shutdown = dw_i2s_shutdown, .hw_params = dw_i2s_hw_params, .prepare = dw_i2s_prepare, .trigger = dw_i2s_trigger, @@ -625,6 +593,14 @@ static int dw_configure_dai_by_dt(struct dw_i2s_dev *dev, } +static int dw_i2s_dai_probe(struct snd_soc_dai *dai) +{ + struct dw_i2s_dev *dev = snd_soc_dai_get_drvdata(dai); + + snd_soc_dai_init_dma_data(dai, &dev->play_dma_data, &dev->capture_dma_data); + return 0; +} + static int dw_i2s_probe(struct platform_device *pdev) { const struct i2s_platform_data *pdata = pdev->dev.platform_data; @@ -643,6 +619,7 @@ static int dw_i2s_probe(struct platform_device *pdev) return -ENOMEM; dw_i2s_dai->ops = &dw_i2s_dai_ops; + dw_i2s_dai->probe = dw_i2s_dai_probe; dev->i2s_base = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(dev->i2s_base)) diff --git a/sound/soc/fsl/fsl_micfil.c b/sound/soc/fsl/fsl_micfil.c index 94341e4352b3..3f08082a55be 100644 --- a/sound/soc/fsl/fsl_micfil.c +++ b/sound/soc/fsl/fsl_micfil.c @@ -1159,7 +1159,7 @@ static int fsl_micfil_probe(struct platform_device *pdev) ret = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0); if (ret) { dev_err(&pdev->dev, "failed to pcm register\n"); - return ret; + goto err_pm_disable; } fsl_micfil_dai.capture.formats = micfil->soc->formats; @@ -1169,9 +1169,20 @@ static int fsl_micfil_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "failed to register component %s\n", fsl_micfil_component.name); + goto err_pm_disable; } return ret; + +err_pm_disable: + pm_runtime_disable(&pdev->dev); + + return ret; +} + +static void fsl_micfil_remove(struct platform_device *pdev) +{ + pm_runtime_disable(&pdev->dev); } static int __maybe_unused fsl_micfil_runtime_suspend(struct device *dev) @@ -1232,6 +1243,7 @@ static const struct dev_pm_ops fsl_micfil_pm_ops = { static struct platform_driver fsl_micfil_driver = { .probe = fsl_micfil_probe, + .remove_new = fsl_micfil_remove, .driver = { .name = "fsl-micfil-dai", .pm = &fsl_micfil_pm_ops, diff --git a/sound/soc/intel/avs/apl.c b/sound/soc/intel/avs/apl.c index 02683dce277a..1860099c782a 100644 --- a/sound/soc/intel/avs/apl.c +++ b/sound/soc/intel/avs/apl.c @@ -169,6 +169,7 @@ static bool apl_lp_streaming(struct avs_dev *adev) { struct avs_path *path; + spin_lock(&adev->path_list_lock); /* Any gateway without buffer allocated in LP area disqualifies D0IX. */ list_for_each_entry(path, &adev->path_list, node) { struct avs_path_pipeline *ppl; @@ -188,11 +189,14 @@ static bool apl_lp_streaming(struct avs_dev *adev) if (cfg->copier.dma_type == INVALID_OBJECT_ID) continue; - if (!mod->gtw_attrs.lp_buffer_alloc) + if (!mod->gtw_attrs.lp_buffer_alloc) { + spin_unlock(&adev->path_list_lock); return false; + } } } } + spin_unlock(&adev->path_list_lock); return true; } diff --git a/sound/soc/intel/avs/avs.h b/sound/soc/intel/avs/avs.h index d7fccdcb9c16..0cf38c9e768e 100644 --- a/sound/soc/intel/avs/avs.h +++ b/sound/soc/intel/avs/avs.h @@ -283,8 +283,8 @@ void avs_release_firmwares(struct avs_dev *adev); int avs_dsp_init_module(struct avs_dev *adev, u16 module_id, u8 ppl_instance_id, u8 core_id, u8 domain, void *param, u32 param_size, - u16 *instance_id); -void avs_dsp_delete_module(struct avs_dev *adev, u16 module_id, u16 instance_id, + u8 *instance_id); +void avs_dsp_delete_module(struct avs_dev *adev, u16 module_id, u8 instance_id, u8 ppl_instance_id, u8 core_id); int avs_dsp_create_pipeline(struct avs_dev *adev, u16 req_size, u8 priority, bool lp, u16 attributes, u8 *instance_id); diff --git a/sound/soc/intel/avs/board_selection.c b/sound/soc/intel/avs/board_selection.c index b2823c2107f7..60f8fb0bff95 100644 --- a/sound/soc/intel/avs/board_selection.c +++ b/sound/soc/intel/avs/board_selection.c @@ -443,7 +443,7 @@ static int avs_register_i2s_boards(struct avs_dev *adev) } for (mach = boards->machs; mach->id[0]; mach++) { - if (!acpi_dev_present(mach->id, NULL, -1)) + if (!acpi_dev_present(mach->id, mach->uid, -1)) continue; if (mach->machine_quirk) diff --git a/sound/soc/intel/avs/control.c b/sound/soc/intel/avs/control.c index a8b14b784f8a..3dfa2e9816db 100644 --- a/sound/soc/intel/avs/control.c +++ b/sound/soc/intel/avs/control.c @@ -21,17 +21,25 @@ static struct avs_dev *avs_get_kcontrol_adev(struct snd_kcontrol *kcontrol) return to_avs_dev(w->dapm->component->dev); } -static struct avs_path_module *avs_get_kcontrol_module(struct avs_dev *adev, u32 id) +static struct avs_path_module *avs_get_volume_module(struct avs_dev *adev, u32 id) { struct avs_path *path; struct avs_path_pipeline *ppl; struct avs_path_module *mod; - list_for_each_entry(path, &adev->path_list, node) - list_for_each_entry(ppl, &path->ppl_list, node) - list_for_each_entry(mod, &ppl->mod_list, node) - if (mod->template->ctl_id && mod->template->ctl_id == id) + spin_lock(&adev->path_list_lock); + list_for_each_entry(path, &adev->path_list, node) { + list_for_each_entry(ppl, &path->ppl_list, node) { + list_for_each_entry(mod, &ppl->mod_list, node) { + if (guid_equal(&mod->template->cfg_ext->type, &AVS_PEAKVOL_MOD_UUID) + && mod->template->ctl_id == id) { + spin_unlock(&adev->path_list_lock); return mod; + } + } + } + } + spin_unlock(&adev->path_list_lock); return NULL; } @@ -49,7 +57,7 @@ int avs_control_volume_get(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_va /* prevent access to modules while path is being constructed */ mutex_lock(&adev->path_mutex); - active_module = avs_get_kcontrol_module(adev, ctl_data->id); + active_module = avs_get_volume_module(adev, ctl_data->id); if (active_module) { ret = avs_ipc_peakvol_get_volume(adev, active_module->module_id, active_module->instance_id, &dspvols, @@ -89,7 +97,7 @@ int avs_control_volume_put(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_va changed = 1; } - active_module = avs_get_kcontrol_module(adev, ctl_data->id); + active_module = avs_get_volume_module(adev, ctl_data->id); if (active_module) { dspvol.channel_id = AVS_ALL_CHANNELS_MASK; dspvol.target_volume = *volume; diff --git a/sound/soc/intel/avs/dsp.c b/sound/soc/intel/avs/dsp.c index b881100d3e02..aa03af4473e9 100644 --- a/sound/soc/intel/avs/dsp.c +++ b/sound/soc/intel/avs/dsp.c @@ -225,7 +225,7 @@ err: int avs_dsp_init_module(struct avs_dev *adev, u16 module_id, u8 ppl_instance_id, u8 core_id, u8 domain, void *param, u32 param_size, - u16 *instance_id) + u8 *instance_id) { struct avs_module_entry mentry; bool was_loaded = false; @@ -272,7 +272,7 @@ err_mod_entry: return ret; } -void avs_dsp_delete_module(struct avs_dev *adev, u16 module_id, u16 instance_id, +void avs_dsp_delete_module(struct avs_dev *adev, u16 module_id, u8 instance_id, u8 ppl_instance_id, u8 core_id) { struct avs_module_entry mentry; diff --git a/sound/soc/intel/avs/messages.h b/sound/soc/intel/avs/messages.h index d3b60ae7d743..7f23a304b4a9 100644 --- a/sound/soc/intel/avs/messages.h +++ b/sound/soc/intel/avs/messages.h @@ -619,7 +619,7 @@ enum avs_channel_config { AVS_CHANNEL_CONFIG_DUAL_MONO = 9, AVS_CHANNEL_CONFIG_I2S_DUAL_STEREO_0 = 10, AVS_CHANNEL_CONFIG_I2S_DUAL_STEREO_1 = 11, - AVS_CHANNEL_CONFIG_4_CHANNEL = 12, + AVS_CHANNEL_CONFIG_7_1 = 12, AVS_CHANNEL_CONFIG_INVALID }; diff --git a/sound/soc/intel/avs/path.h b/sound/soc/intel/avs/path.h index 197222c5e008..657f7b093e80 100644 --- a/sound/soc/intel/avs/path.h +++ b/sound/soc/intel/avs/path.h @@ -37,7 +37,7 @@ struct avs_path_pipeline { struct avs_path_module { u16 module_id; - u16 instance_id; + u8 instance_id; union avs_gtw_attributes gtw_attrs; struct avs_tplg_module *template; diff --git a/sound/soc/intel/avs/pcm.c b/sound/soc/intel/avs/pcm.c index 31c032a0f7e4..1fbb2c2fadb5 100644 --- a/sound/soc/intel/avs/pcm.c +++ b/sound/soc/intel/avs/pcm.c @@ -468,21 +468,34 @@ static int avs_dai_fe_startup(struct snd_pcm_substream *substream, struct snd_so host_stream = snd_hdac_ext_stream_assign(bus, substream, HDAC_EXT_STREAM_TYPE_HOST); if (!host_stream) { - kfree(data); - return -EBUSY; + ret = -EBUSY; + goto err; } data->host_stream = host_stream; - snd_pcm_hw_constraint_integer(runtime, SNDRV_PCM_HW_PARAM_PERIODS); + ret = snd_pcm_hw_constraint_integer(runtime, SNDRV_PCM_HW_PARAM_PERIODS); + if (ret < 0) + goto err; + /* avoid wrap-around with wall-clock */ - snd_pcm_hw_constraint_minmax(runtime, SNDRV_PCM_HW_PARAM_BUFFER_TIME, 20, 178000000); - snd_pcm_hw_constraint_list(runtime, 0, SNDRV_PCM_HW_PARAM_RATE, &hw_rates); + ret = snd_pcm_hw_constraint_minmax(runtime, SNDRV_PCM_HW_PARAM_BUFFER_TIME, 20, 178000000); + if (ret < 0) + goto err; + + ret = snd_pcm_hw_constraint_list(runtime, 0, SNDRV_PCM_HW_PARAM_RATE, &hw_rates); + if (ret < 0) + goto err; + snd_pcm_set_sync(substream); dev_dbg(dai->dev, "%s fe STARTUP tag %d str %p", __func__, hdac_stream(host_stream)->stream_tag, substream); return 0; + +err: + kfree(data); + return ret; } static void avs_dai_fe_shutdown(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) diff --git a/sound/soc/intel/avs/probes.c b/sound/soc/intel/avs/probes.c index 70a94201d6a5..275928281c6c 100644 --- a/sound/soc/intel/avs/probes.c +++ b/sound/soc/intel/avs/probes.c @@ -18,7 +18,7 @@ static int avs_dsp_init_probe(struct avs_dev *adev, union avs_connector_node_id { struct avs_probe_cfg cfg = {{0}}; struct avs_module_entry mentry; - u16 dummy; + u8 dummy; avs_get_module_entry(adev, &AVS_PROBE_MOD_UUID, &mentry); diff --git a/sound/soc/jz4740/jz4740-i2s.c b/sound/soc/jz4740/jz4740-i2s.c index 6d9cfe0a5041..d0f6c945d9ae 100644 --- a/sound/soc/jz4740/jz4740-i2s.c +++ b/sound/soc/jz4740/jz4740-i2s.c @@ -218,18 +218,48 @@ static int jz4740_i2s_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) return 0; } +static int jz4740_i2s_get_i2sdiv(unsigned long mclk, unsigned long rate, + unsigned long i2sdiv_max) +{ + unsigned long div, rate1, rate2, err1, err2; + + div = mclk / (64 * rate); + if (div == 0) + div = 1; + + rate1 = mclk / (64 * div); + rate2 = mclk / (64 * (div + 1)); + + err1 = abs(rate1 - rate); + err2 = abs(rate2 - rate); + + /* + * Choose the divider that produces the smallest error in the + * output rate and reject dividers with a 5% or higher error. + * In the event that both dividers are outside the acceptable + * error margin, reject the rate to prevent distorted audio. + * (The number 5% is arbitrary.) + */ + if (div <= i2sdiv_max && err1 <= err2 && err1 < rate/20) + return div; + if (div < i2sdiv_max && err2 < rate/20) + return div + 1; + + return -EINVAL; +} + static int jz4740_i2s_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params, struct snd_soc_dai *dai) { struct jz4740_i2s *i2s = snd_soc_dai_get_drvdata(dai); struct regmap_field *div_field; + unsigned long i2sdiv_max; unsigned int sample_size; - uint32_t ctrl; - int div; + uint32_t ctrl, conf; + int div = 1; regmap_read(i2s->regmap, JZ_REG_AIC_CTRL, &ctrl); - - div = clk_get_rate(i2s->clk_i2s) / (64 * params_rate(params)); + regmap_read(i2s->regmap, JZ_REG_AIC_CONF, &conf); switch (params_format(params)) { case SNDRV_PCM_FORMAT_S8: @@ -258,11 +288,27 @@ static int jz4740_i2s_hw_params(struct snd_pcm_substream *substream, ctrl &= ~JZ_AIC_CTRL_MONO_TO_STEREO; div_field = i2s->field_i2sdiv_playback; + i2sdiv_max = GENMASK(i2s->soc_info->field_i2sdiv_playback.msb, + i2s->soc_info->field_i2sdiv_playback.lsb); } else { ctrl &= ~JZ_AIC_CTRL_INPUT_SAMPLE_SIZE; ctrl |= FIELD_PREP(JZ_AIC_CTRL_INPUT_SAMPLE_SIZE, sample_size); div_field = i2s->field_i2sdiv_capture; + i2sdiv_max = GENMASK(i2s->soc_info->field_i2sdiv_capture.msb, + i2s->soc_info->field_i2sdiv_capture.lsb); + } + + /* + * Only calculate I2SDIV if we're supplying the bit or frame clock. + * If the codec is supplying both clocks then the divider output is + * unused, and we don't want it to limit the allowed sample rates. + */ + if (conf & (JZ_AIC_CONF_BIT_CLK_MASTER | JZ_AIC_CONF_SYNC_CLK_MASTER)) { + div = jz4740_i2s_get_i2sdiv(clk_get_rate(i2s->clk_i2s), + params_rate(params), i2sdiv_max); + if (div < 0) + return div; } regmap_write(i2s->regmap, JZ_REG_AIC_CTRL, ctrl); diff --git a/sound/soc/mediatek/mt8186/mt8186-afe-clk.c b/sound/soc/mediatek/mt8186/mt8186-afe-clk.c index a6b4f29049bb..539e3a023bc4 100644 --- a/sound/soc/mediatek/mt8186/mt8186-afe-clk.c +++ b/sound/soc/mediatek/mt8186/mt8186-afe-clk.c @@ -644,9 +644,3 @@ int mt8186_init_clock(struct mtk_base_afe *afe) return 0; } - -void mt8186_deinit_clock(void *priv) -{ - struct mtk_base_afe *afe = priv; - mt8186_audsys_clk_unregister(afe); -} diff --git a/sound/soc/mediatek/mt8186/mt8186-afe-clk.h b/sound/soc/mediatek/mt8186/mt8186-afe-clk.h index d5988717d8f2..a9d59e506d9a 100644 --- a/sound/soc/mediatek/mt8186/mt8186-afe-clk.h +++ b/sound/soc/mediatek/mt8186/mt8186-afe-clk.h @@ -81,7 +81,6 @@ enum { struct mtk_base_afe; int mt8186_set_audio_int_bus_parent(struct mtk_base_afe *afe, int clk_id); int mt8186_init_clock(struct mtk_base_afe *afe); -void mt8186_deinit_clock(void *priv); int mt8186_afe_enable_cgs(struct mtk_base_afe *afe); void mt8186_afe_disable_cgs(struct mtk_base_afe *afe); int mt8186_afe_enable_clock(struct mtk_base_afe *afe); diff --git a/sound/soc/mediatek/mt8186/mt8186-afe-pcm.c b/sound/soc/mediatek/mt8186/mt8186-afe-pcm.c index 41172a82103e..a868a04ed4e7 100644 --- a/sound/soc/mediatek/mt8186/mt8186-afe-pcm.c +++ b/sound/soc/mediatek/mt8186/mt8186-afe-pcm.c @@ -2848,10 +2848,6 @@ static int mt8186_afe_pcm_dev_probe(struct platform_device *pdev) return ret; } - ret = devm_add_action_or_reset(dev, mt8186_deinit_clock, (void *)afe); - if (ret) - return ret; - /* init memif */ afe->memif_32bit_supported = 0; afe->memif_size = MT8186_MEMIF_NUM; diff --git a/sound/soc/mediatek/mt8186/mt8186-audsys-clk.c b/sound/soc/mediatek/mt8186/mt8186-audsys-clk.c index 578969ca91c8..5666be6b1bd2 100644 --- a/sound/soc/mediatek/mt8186/mt8186-audsys-clk.c +++ b/sound/soc/mediatek/mt8186/mt8186-audsys-clk.c @@ -84,6 +84,29 @@ static const struct afe_gate aud_clks[CLK_AUD_NR_CLK] = { GATE_AUD2(CLK_AUD_ETDM_OUT1_BCLK, "aud_etdm_out1_bclk", "top_audio", 24), }; +static void mt8186_audsys_clk_unregister(void *data) +{ + struct mtk_base_afe *afe = data; + struct mt8186_afe_private *afe_priv = afe->platform_priv; + struct clk *clk; + struct clk_lookup *cl; + int i; + + if (!afe_priv) + return; + + for (i = 0; i < CLK_AUD_NR_CLK; i++) { + cl = afe_priv->lookup[i]; + if (!cl) + continue; + + clk = cl->clk; + clk_unregister_gate(clk); + + clkdev_drop(cl); + } +} + int mt8186_audsys_clk_register(struct mtk_base_afe *afe) { struct mt8186_afe_private *afe_priv = afe->platform_priv; @@ -124,27 +147,6 @@ int mt8186_audsys_clk_register(struct mtk_base_afe *afe) afe_priv->lookup[i] = cl; } - return 0; + return devm_add_action_or_reset(afe->dev, mt8186_audsys_clk_unregister, afe); } -void mt8186_audsys_clk_unregister(struct mtk_base_afe *afe) -{ - struct mt8186_afe_private *afe_priv = afe->platform_priv; - struct clk *clk; - struct clk_lookup *cl; - int i; - - if (!afe_priv) - return; - - for (i = 0; i < CLK_AUD_NR_CLK; i++) { - cl = afe_priv->lookup[i]; - if (!cl) - continue; - - clk = cl->clk; - clk_unregister_gate(clk); - - clkdev_drop(cl); - } -} diff --git a/sound/soc/mediatek/mt8186/mt8186-audsys-clk.h b/sound/soc/mediatek/mt8186/mt8186-audsys-clk.h index b8d6a06e11e8..897a2914dc19 100644 --- a/sound/soc/mediatek/mt8186/mt8186-audsys-clk.h +++ b/sound/soc/mediatek/mt8186/mt8186-audsys-clk.h @@ -10,6 +10,5 @@ #define _MT8186_AUDSYS_CLK_H_ int mt8186_audsys_clk_register(struct mtk_base_afe *afe); -void mt8186_audsys_clk_unregister(struct mtk_base_afe *afe); #endif diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index adb69d7820a8..4fb1ac8e1c4a 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -2405,6 +2405,9 @@ int dpcm_be_dai_prepare(struct snd_soc_pcm_runtime *fe, int stream) if (!snd_soc_dpcm_be_can_update(fe, be, stream)) continue; + if (!snd_soc_dpcm_can_be_prepared(fe, be, stream)) + continue; + if ((be->dpcm[stream].state != SND_SOC_DPCM_STATE_HW_PARAMS) && (be->dpcm[stream].state != SND_SOC_DPCM_STATE_STOP) && (be->dpcm[stream].state != SND_SOC_DPCM_STATE_SUSPEND) && @@ -3042,3 +3045,20 @@ int snd_soc_dpcm_can_be_params(struct snd_soc_pcm_runtime *fe, return snd_soc_dpcm_check_state(fe, be, stream, state, ARRAY_SIZE(state)); } EXPORT_SYMBOL_GPL(snd_soc_dpcm_can_be_params); + +/* + * We can only prepare a BE DAI if any of it's FE are not prepared, + * running or paused for the specified stream direction. + */ +int snd_soc_dpcm_can_be_prepared(struct snd_soc_pcm_runtime *fe, + struct snd_soc_pcm_runtime *be, int stream) +{ + const enum snd_soc_dpcm_state state[] = { + SND_SOC_DPCM_STATE_START, + SND_SOC_DPCM_STATE_PAUSED, + SND_SOC_DPCM_STATE_PREPARE, + }; + + return snd_soc_dpcm_check_state(fe, be, stream, state, ARRAY_SIZE(state)); +} +EXPORT_SYMBOL_GPL(snd_soc_dpcm_can_be_prepared); diff --git a/sound/soc/sof/amd/acp-ipc.c b/sound/soc/sof/amd/acp-ipc.c index 4e0c48a36159..749e856dc601 100644 --- a/sound/soc/sof/amd/acp-ipc.c +++ b/sound/soc/sof/amd/acp-ipc.c @@ -209,7 +209,12 @@ int acp_sof_ipc_msg_data(struct snd_sof_dev *sdev, struct snd_sof_pcm_stream *sp acp_mailbox_read(sdev, offset, p, sz); } else { struct snd_pcm_substream *substream = sps->substream; - struct acp_dsp_stream *stream = substream->runtime->private_data; + struct acp_dsp_stream *stream; + + if (!substream || !substream->runtime) + return -ESTRPIPE; + + stream = substream->runtime->private_data; if (!stream) return -ESTRPIPE; diff --git a/sound/soc/sof/debug.c b/sound/soc/sof/debug.c index b42b5982cbbc..d547318e0d32 100644 --- a/sound/soc/sof/debug.c +++ b/sound/soc/sof/debug.c @@ -438,8 +438,8 @@ void snd_sof_handle_fw_exception(struct snd_sof_dev *sdev, const char *msg) /* should we prevent DSP entering D3 ? */ if (!sdev->ipc_dump_printed) dev_info(sdev->dev, - "preventing DSP entering D3 state to preserve context\n"); - pm_runtime_get_noresume(sdev->dev); + "Attempting to prevent DSP from entering D3 state to preserve context\n"); + pm_runtime_get_if_in_use(sdev->dev); } /* dump vital information to the logs */ diff --git a/sound/soc/sof/intel/hda-mlink.c b/sound/soc/sof/intel/hda-mlink.c index 775582ab7494..b7cbf66badf5 100644 --- a/sound/soc/sof/intel/hda-mlink.c +++ b/sound/soc/sof/intel/hda-mlink.c @@ -19,6 +19,9 @@ #if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA_MLINK) +/* worst-case number of sublinks is used for sublink refcount array allocation only */ +#define HDAML_MAX_SUBLINKS (AZX_ML_LCTL_CPA_SHIFT - AZX_ML_LCTL_SPA_SHIFT) + /** * struct hdac_ext2_link - HDAudio extended+alternate link * @@ -33,6 +36,7 @@ * @leptr: extended link pointer * @eml_lock: mutual exclusion to access shared registers e.g. CPA/SPA bits * in LCTL register + * @sublink_ref_count: array of refcounts, required to power-manage sublinks independently * @base_ptr: pointer to shim/ip/shim_vs space * @instance_offset: offset between each of @slcount instances managed by link * @shim_offset: offset to SHIM register base @@ -53,6 +57,7 @@ struct hdac_ext2_link { u32 leptr; struct mutex eml_lock; /* prevent concurrent access to e.g. CPA/SPA */ + int sublink_ref_count[HDAML_MAX_SUBLINKS]; /* internal values computed from LCAP contents */ void __iomem *base_ptr; @@ -68,6 +73,7 @@ struct hdac_ext2_link { #define AZX_REG_SDW_SHIM_OFFSET 0x0 #define AZX_REG_SDW_IP_OFFSET 0x100 #define AZX_REG_SDW_VS_SHIM_OFFSET 0x6000 +#define AZX_REG_SDW_SHIM_PCMSyCM(y) (0x16 + 0x4 * (y)) /* only one instance supported */ #define AZX_REG_INTEL_DMIC_SHIM_OFFSET 0x0 @@ -91,7 +97,7 @@ struct hdac_ext2_link { */ static int hdaml_lnk_enum(struct device *dev, struct hdac_ext2_link *h2link, - void __iomem *ml_addr, int link_idx) + void __iomem *remap_addr, void __iomem *ml_addr, int link_idx) { struct hdac_ext_link *hlink = &h2link->hext_link; u32 base_offset; @@ -126,15 +132,16 @@ static int hdaml_lnk_enum(struct device *dev, struct hdac_ext2_link *h2link, link_idx, h2link->slcount); /* find IP ID and offsets */ - h2link->leptr = readl(hlink->ml_addr + AZX_REG_ML_LEPTR); + h2link->leptr = readl(ml_addr + AZX_REG_ML_LEPTR); h2link->elid = FIELD_GET(AZX_REG_ML_LEPTR_ID, h2link->leptr); base_offset = FIELD_GET(AZX_REG_ML_LEPTR_PTR, h2link->leptr); - h2link->base_ptr = hlink->ml_addr + base_offset; + h2link->base_ptr = remap_addr + base_offset; switch (h2link->elid) { case AZX_REG_ML_LEPTR_ID_SDW: + h2link->instance_offset = AZX_REG_SDW_INSTANCE_OFFSET; h2link->shim_offset = AZX_REG_SDW_SHIM_OFFSET; h2link->ip_offset = AZX_REG_SDW_IP_OFFSET; h2link->shim_vs_offset = AZX_REG_SDW_VS_SHIM_OFFSET; @@ -149,6 +156,7 @@ static int hdaml_lnk_enum(struct device *dev, struct hdac_ext2_link *h2link, link_idx, base_offset); break; case AZX_REG_ML_LEPTR_ID_INTEL_SSP: + h2link->instance_offset = AZX_REG_INTEL_SSP_INSTANCE_OFFSET; h2link->shim_offset = AZX_REG_INTEL_SSP_SHIM_OFFSET; h2link->ip_offset = AZX_REG_INTEL_SSP_IP_OFFSET; h2link->shim_vs_offset = AZX_REG_INTEL_SSP_VS_SHIM_OFFSET; @@ -333,6 +341,21 @@ static void hdaml_link_set_lsdiid(u32 __iomem *lsdiid, int dev_num) writel(val, lsdiid); } +static void hdaml_shim_map_stream_ch(u16 __iomem *pcmsycm, int lchan, int hchan, + int stream_id, int dir) +{ + u16 val; + + val = readw(pcmsycm); + + u16p_replace_bits(&val, lchan, GENMASK(3, 0)); + u16p_replace_bits(&val, hchan, GENMASK(7, 4)); + u16p_replace_bits(&val, stream_id, GENMASK(13, 8)); + u16p_replace_bits(&val, dir, BIT(15)); + + writew(val, pcmsycm); +} + static void hdaml_lctl_offload_enable(u32 __iomem *lctl, bool enable) { u32 val = readl(lctl); @@ -364,7 +387,7 @@ static int hda_ml_alloc_h2link(struct hdac_bus *bus, int index) hlink->bus = bus; hlink->ml_addr = bus->mlcap + AZX_ML_BASE + (AZX_ML_INTERVAL * index); - ret = hdaml_lnk_enum(bus->dev, h2link, hlink->ml_addr, index); + ret = hdaml_lnk_enum(bus->dev, h2link, bus->remap_addr, hlink->ml_addr, index); if (ret < 0) { kfree(h2link); return ret; @@ -641,8 +664,13 @@ static int hdac_bus_eml_power_up_base(struct hdac_bus *bus, bool alt, int elid, if (eml_lock) mutex_lock(&h2link->eml_lock); - if (++hlink->ref_count > 1) - goto skip_init; + if (!alt) { + if (++hlink->ref_count > 1) + goto skip_init; + } else { + if (++h2link->sublink_ref_count[sublink] > 1) + goto skip_init; + } ret = hdaml_link_init(hlink->ml_addr + AZX_REG_ML_LCTL, sublink); @@ -684,9 +712,13 @@ static int hdac_bus_eml_power_down_base(struct hdac_bus *bus, bool alt, int elid if (eml_lock) mutex_lock(&h2link->eml_lock); - if (--hlink->ref_count > 0) - goto skip_shutdown; - + if (!alt) { + if (--hlink->ref_count > 0) + goto skip_shutdown; + } else { + if (--h2link->sublink_ref_count[sublink] > 0) + goto skip_shutdown; + } ret = hdaml_link_shutdown(hlink->ml_addr + AZX_REG_ML_LCTL, sublink); skip_shutdown: @@ -740,6 +772,40 @@ int hdac_bus_eml_sdw_set_lsdiid(struct hdac_bus *bus, int sublink, int dev_num) return 0; } EXPORT_SYMBOL_NS(hdac_bus_eml_sdw_set_lsdiid, SND_SOC_SOF_HDA_MLINK); +/* + * the 'y' parameter comes from the PCMSyCM hardware register naming. 'y' refers to the + * PDI index, i.e. the FIFO used for RX or TX + */ +int hdac_bus_eml_sdw_map_stream_ch(struct hdac_bus *bus, int sublink, int y, + int channel_mask, int stream_id, int dir) +{ + struct hdac_ext2_link *h2link; + u16 __iomem *pcmsycm; + u16 val; + + h2link = find_ext2_link(bus, true, AZX_REG_ML_LEPTR_ID_SDW); + if (!h2link) + return -ENODEV; + + pcmsycm = h2link->base_ptr + h2link->shim_offset + + h2link->instance_offset * sublink + + AZX_REG_SDW_SHIM_PCMSyCM(y); + + mutex_lock(&h2link->eml_lock); + + hdaml_shim_map_stream_ch(pcmsycm, 0, hweight32(channel_mask), + stream_id, dir); + + mutex_unlock(&h2link->eml_lock); + + val = readw(pcmsycm); + + dev_dbg(bus->dev, "channel_mask %#x stream_id %d dir %d pcmscm %#x\n", + channel_mask, stream_id, dir, val); + + return 0; +} EXPORT_SYMBOL_NS(hdac_bus_eml_sdw_map_stream_ch, SND_SOC_SOF_HDA_MLINK); + void hda_bus_ml_put_all(struct hdac_bus *bus) { struct hdac_ext_link *hlink; @@ -836,6 +902,18 @@ struct hdac_ext_link *hdac_bus_eml_dmic_get_hlink(struct hdac_bus *bus) } EXPORT_SYMBOL_NS(hdac_bus_eml_dmic_get_hlink, SND_SOC_SOF_HDA_MLINK); +struct hdac_ext_link *hdac_bus_eml_sdw_get_hlink(struct hdac_bus *bus) +{ + struct hdac_ext2_link *h2link; + + h2link = find_ext2_link(bus, true, AZX_REG_ML_LEPTR_ID_SDW); + if (!h2link) + return NULL; + + return &h2link->hext_link; +} +EXPORT_SYMBOL_NS(hdac_bus_eml_sdw_get_hlink, SND_SOC_SOF_HDA_MLINK); + int hdac_bus_eml_enable_offload(struct hdac_bus *bus, bool alt, int elid, bool enable) { struct hdac_ext2_link *h2link; diff --git a/sound/soc/sof/ipc3-topology.c b/sound/soc/sof/ipc3-topology.c index fc1eb8e2de2c..ba4ef290b634 100644 --- a/sound/soc/sof/ipc3-topology.c +++ b/sound/soc/sof/ipc3-topology.c @@ -2103,10 +2103,13 @@ static int sof_ipc3_dai_config(struct snd_sof_dev *sdev, struct snd_sof_widget * * For the case of PAUSE/HW_FREE, since there are no quirks, flags can be used as is. */ - if (flags & SOF_DAI_CONFIG_FLAGS_HW_PARAMS) + if (flags & SOF_DAI_CONFIG_FLAGS_HW_PARAMS) { + /* Clear stale command */ + config->flags &= ~SOF_DAI_CONFIG_FLAGS_CMD_MASK; config->flags |= flags; - else + } else { config->flags = flags; + } /* only send the IPC if the widget is set up in the DSP */ if (swidget->use_count > 0) { diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c index 059eebf0a687..5abe616a2054 100644 --- a/sound/soc/sof/ipc4-topology.c +++ b/sound/soc/sof/ipc4-topology.c @@ -59,7 +59,7 @@ static const struct sof_topology_token ipc4_in_audio_format_tokens[] = { audio_fmt.interleaving_style)}, {SOF_TKN_CAVS_AUDIO_FORMAT_IN_FMT_CFG, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32, offsetof(struct sof_ipc4_pin_format, audio_fmt.fmt_cfg)}, - {SOF_TKN_CAVS_AUDIO_FORMAT_PIN_INDEX, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32, + {SOF_TKN_CAVS_AUDIO_FORMAT_INPUT_PIN_INDEX, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32, offsetof(struct sof_ipc4_pin_format, pin_index)}, {SOF_TKN_CAVS_AUDIO_FORMAT_IBS, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32, offsetof(struct sof_ipc4_pin_format, buffer_size)}, @@ -79,7 +79,7 @@ static const struct sof_topology_token ipc4_out_audio_format_tokens[] = { audio_fmt.interleaving_style)}, {SOF_TKN_CAVS_AUDIO_FORMAT_OUT_FMT_CFG, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32, offsetof(struct sof_ipc4_pin_format, audio_fmt.fmt_cfg)}, - {SOF_TKN_CAVS_AUDIO_FORMAT_PIN_INDEX, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32, + {SOF_TKN_CAVS_AUDIO_FORMAT_OUTPUT_PIN_INDEX, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32, offsetof(struct sof_ipc4_pin_format, pin_index)}, {SOF_TKN_CAVS_AUDIO_FORMAT_OBS, SND_SOC_TPLG_TUPLE_TYPE_WORD, get_token_u32, offsetof(struct sof_ipc4_pin_format, buffer_size)}, diff --git a/sound/soc/sof/pcm.c b/sound/soc/sof/pcm.c index 567db32173a8..d0ab6f390734 100644 --- a/sound/soc/sof/pcm.c +++ b/sound/soc/sof/pcm.c @@ -643,16 +643,17 @@ static int sof_pcm_probe(struct snd_soc_component *component) "%s/%s", plat_data->tplg_filename_prefix, plat_data->tplg_filename); - if (!tplg_filename) - return -ENOMEM; + if (!tplg_filename) { + ret = -ENOMEM; + goto pm_error; + } ret = snd_sof_load_topology(component, tplg_filename); - if (ret < 0) { + if (ret < 0) dev_err(component->dev, "error: failed to load DSP topology %d\n", ret); - return ret; - } +pm_error: pm_runtime_mark_last_busy(component->dev); pm_runtime_put_autosuspend(component->dev); diff --git a/sound/soc/sof/pm.c b/sound/soc/sof/pm.c index 2fdbc53ca715..2b232442e84b 100644 --- a/sound/soc/sof/pm.c +++ b/sound/soc/sof/pm.c @@ -164,7 +164,7 @@ static int sof_resume(struct device *dev, bool runtime_resume) ret = tplg_ops->set_up_all_pipelines(sdev, false); if (ret < 0) { dev_err(sdev->dev, "Failed to restore pipeline after resume %d\n", ret); - return ret; + goto setup_fail; } } @@ -178,6 +178,18 @@ static int sof_resume(struct device *dev, bool runtime_resume) dev_err(sdev->dev, "ctx_restore IPC error during resume: %d\n", ret); } +setup_fail: +#if IS_ENABLED(CONFIG_SND_SOC_SOF_DEBUG_ENABLE_DEBUGFS_CACHE) + if (ret < 0) { + /* + * Debugfs cannot be read in runtime suspend, so cache + * the contents upon failure. This allows to capture + * possible DSP coredump information. + */ + sof_cache_debugfs(sdev); + } +#endif + return ret; } diff --git a/sound/soc/sof/sof-client-probes.c b/sound/soc/sof/sof-client-probes.c index fff126808bc0..8d9e9d5f40e4 100644 --- a/sound/soc/sof/sof-client-probes.c +++ b/sound/soc/sof/sof-client-probes.c @@ -218,12 +218,7 @@ static ssize_t sof_probes_dfs_points_read(struct file *file, char __user *to, ret = ipc->points_info(cdev, &desc, &num_desc); if (ret < 0) - goto exit; - - pm_runtime_mark_last_busy(dev); - err = pm_runtime_put_autosuspend(dev); - if (err < 0) - dev_err_ratelimited(dev, "debugfs read failed to idle %d\n", err); + goto pm_error; for (i = 0; i < num_desc; i++) { offset = strlen(buf); @@ -241,6 +236,13 @@ static ssize_t sof_probes_dfs_points_read(struct file *file, char __user *to, ret = simple_read_from_buffer(to, count, ppos, buf, strlen(buf)); kfree(desc); + +pm_error: + pm_runtime_mark_last_busy(dev); + err = pm_runtime_put_autosuspend(dev); + if (err < 0) + dev_err_ratelimited(dev, "debugfs read failed to idle %d\n", err); + exit: kfree(buf); return ret; diff --git a/sound/soc/sof/topology.c b/sound/soc/sof/topology.c index d3d536b0a8f5..f160dc454b44 100644 --- a/sound/soc/sof/topology.c +++ b/sound/soc/sof/topology.c @@ -586,6 +586,10 @@ static int sof_copy_tuples(struct snd_sof_dev *sdev, struct snd_soc_tplg_vendor_ if (*num_copied_tuples == tuples_size) return 0; } + + /* stop when we've found the required token instances */ + if (found == num_tokens * token_instance_num) + return 0; } /* next array */ @@ -1261,7 +1265,7 @@ static int sof_widget_parse_tokens(struct snd_soc_component *scomp, struct snd_s if (num_sets > 1) { struct snd_sof_tuple *new_tuples; - num_tuples += token_list[object_token_list[i]].count * num_sets; + num_tuples += token_list[object_token_list[i]].count * (num_sets - 1); new_tuples = krealloc(swidget->tuples, sizeof(*new_tuples) * num_tuples, GFP_KERNEL); if (!new_tuples) { diff --git a/sound/usb/format.c b/sound/usb/format.c index 4b1c5ba121f3..ab5fed9f55b6 100644 --- a/sound/usb/format.c +++ b/sound/usb/format.c @@ -423,6 +423,7 @@ static int line6_parse_audio_format_rates_quirk(struct snd_usb_audio *chip, case USB_ID(0x0e41, 0x4248): /* Line6 Helix >= fw 2.82 */ case USB_ID(0x0e41, 0x4249): /* Line6 Helix Rack >= fw 2.82 */ case USB_ID(0x0e41, 0x424a): /* Line6 Helix LT >= fw 2.82 */ + case USB_ID(0x0e41, 0x424b): /* Line6 Pod Go */ case USB_ID(0x19f7, 0x0011): /* Rode Rodecaster Pro */ return set_fixed_rate(fp, 48000, SNDRV_PCM_RATE_48000); } diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index f8129c624b07..f7ddd73a8c0f 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -198,6 +198,15 @@ struct kvm_arm_copy_mte_tags { __u64 reserved[2]; }; +/* + * Counter/Timer offset structure. Describe the virtual/physical offset. + * To be used with KVM_ARM_SET_COUNTER_OFFSET. + */ +struct kvm_arm_counter_offset { + __u64 counter_offset; + __u64 reserved; +}; + #define KVM_ARM_TAGS_TO_GUEST 0 #define KVM_ARM_TAGS_FROM_GUEST 1 @@ -372,6 +381,10 @@ enum { #endif }; +/* Device Control API on vm fd */ +#define KVM_ARM_VM_SMCCC_CTRL 0 +#define KVM_ARM_VM_SMCCC_FILTER 0 + /* Device Control API: ARM VGIC */ #define KVM_DEV_ARM_VGIC_GRP_ADDR 0 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1 @@ -411,6 +424,8 @@ enum { #define KVM_ARM_VCPU_TIMER_CTRL 1 #define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0 #define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1 +#define KVM_ARM_VCPU_TIMER_IRQ_HVTIMER 2 +#define KVM_ARM_VCPU_TIMER_IRQ_HPTIMER 3 #define KVM_ARM_VCPU_PVTIME_CTRL 2 #define KVM_ARM_VCPU_PVTIME_IPA 0 @@ -469,6 +484,27 @@ enum { /* run->fail_entry.hardware_entry_failure_reason codes. */ #define KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED (1ULL << 0) +enum kvm_smccc_filter_action { + KVM_SMCCC_FILTER_HANDLE = 0, + KVM_SMCCC_FILTER_DENY, + KVM_SMCCC_FILTER_FWD_TO_USER, + +#ifdef __KERNEL__ + NR_SMCCC_FILTER_ACTIONS +#endif +}; + +struct kvm_smccc_filter { + __u32 base; + __u32 nr_functions; + __u8 action; + __u8 pad[15]; +}; + +/* arm64-specific KVM_EXIT_HYPERCALL flags */ +#define KVM_HYPERCALL_EXIT_SMC (1U << 0) +#define KVM_HYPERCALL_EXIT_16BIT (1U << 1) + #endif #endif /* __ARM_KVM_H__ */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index b89005819cd5..cb8ca46213be 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -97,7 +97,7 @@ #define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ #define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ #define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* AMD Last Branch Record Extension Version 2 */ -#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" LFENCE synchronizes RDTSC */ +/* FREE, was #define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) "" LFENCE synchronizes RDTSC */ #define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ #define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ #define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ @@ -226,10 +226,9 @@ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ -#define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */ -#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */ -#define X86_FEATURE_EPT ( 8*32+ 3) /* Intel Extended Page Table */ -#define X86_FEATURE_VPID ( 8*32+ 4) /* Intel Virtual Processor ID */ +#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* Intel FlexPriority */ +#define X86_FEATURE_EPT ( 8*32+ 2) /* Intel Extended Page Table */ +#define X86_FEATURE_VPID ( 8*32+ 3) /* Intel Virtual Processor ID */ #define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer VMMCALL to VMCALL */ #define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ @@ -307,14 +306,21 @@ #define X86_FEATURE_SGX_EDECCSSA (11*32+18) /* "" SGX EDECCSSA user leaf function */ #define X86_FEATURE_CALL_DEPTH (11*32+19) /* "" Call depth tracking for RSB stuffing */ #define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */ +#define X86_FEATURE_SMBA (11*32+21) /* "" Slow Memory Bandwidth Allocation */ +#define X86_FEATURE_BMEC (11*32+22) /* "" Bandwidth Monitoring Event Configuration */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ #define X86_FEATURE_CMPCCXADD (12*32+ 7) /* "" CMPccXADD instructions */ +#define X86_FEATURE_ARCH_PERFMON_EXT (12*32+ 8) /* "" Intel Architectural PerfMon Extension */ +#define X86_FEATURE_FZRM (12*32+10) /* "" Fast zero-length REP MOVSB */ +#define X86_FEATURE_FSRS (12*32+11) /* "" Fast short REP STOSB */ +#define X86_FEATURE_FSRC (12*32+12) /* "" Fast short REP {CMPSB,SCASB} */ #define X86_FEATURE_LKGS (12*32+18) /* "" Load "kernel" (userspace) GS */ #define X86_FEATURE_AMX_FP16 (12*32+21) /* "" AMX fp16 Support */ #define X86_FEATURE_AVX_IFMA (12*32+23) /* "" Support for VPMADD52[H,L]UQ */ +#define X86_FEATURE_LAM (12*32+26) /* Linear Address Masking */ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ @@ -331,6 +337,7 @@ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ #define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ #define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */ +#define X86_FEATURE_AMD_PSFD (13*32+28) /* "" Predictive Store Forwarding Disable */ #define X86_FEATURE_BTC_NO (13*32+29) /* "" Not vulnerable to Branch Type Confusion */ #define X86_FEATURE_BRS (13*32+31) /* Branch Sampling available */ @@ -363,6 +370,7 @@ #define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ #define X86_FEATURE_X2AVIC (15*32+18) /* Virtual x2apic */ #define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* Virtual SPEC_CTRL */ +#define X86_FEATURE_VNMI (15*32+25) /* Virtual NMI */ #define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* "" SVME addr check */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */ @@ -427,6 +435,13 @@ #define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* "" Virtual TSC_AUX */ #define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ +/* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */ +#define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* "" No Nested Data Breakpoints */ +#define X86_FEATURE_LFENCE_RDTSC (20*32+ 2) /* "" LFENCE always serializing / synchronizes RDTSC */ +#define X86_FEATURE_NULL_SEL_CLR_BASE (20*32+ 6) /* "" Null Selector Clears Base */ +#define X86_FEATURE_AUTOIBRS (20*32+ 8) /* "" Automatic IBRS */ +#define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* "" SMM_CTL MSR is not present */ + /* * BUG word(s) */ @@ -467,5 +482,6 @@ #define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */ #define X86_BUG_RETBLEED X86_BUG(27) /* CPU is affected by RETBleed */ #define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ +#define X86_BUG_SMT_RSB X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 5dfa4fb76f4b..fafe9be7a6f4 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -75,6 +75,12 @@ # define DISABLE_CALL_DEPTH_TRACKING (1 << (X86_FEATURE_CALL_DEPTH & 31)) #endif +#ifdef CONFIG_ADDRESS_MASKING +# define DISABLE_LAM 0 +#else +# define DISABLE_LAM (1 << (X86_FEATURE_LAM & 31)) +#endif + #ifdef CONFIG_INTEL_IOMMU_SVM # define DISABLE_ENQCMD 0 #else @@ -115,7 +121,7 @@ #define DISABLED_MASK10 0 #define DISABLED_MASK11 (DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \ DISABLE_CALL_DEPTH_TRACKING) -#define DISABLED_MASK12 0 +#define DISABLED_MASK12 (DISABLE_LAM) #define DISABLED_MASK13 0 #define DISABLED_MASK14 0 #define DISABLED_MASK15 0 diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index ad35355ee43e..3aedae61af4f 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -206,6 +206,8 @@ /* Abbreviated from Intel SDM name IA32_INTEGRITY_CAPABILITIES */ #define MSR_INTEGRITY_CAPS 0x000002d9 +#define MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT 2 +#define MSR_INTEGRITY_CAPS_ARRAY_BIST BIT(MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT) #define MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT 4 #define MSR_INTEGRITY_CAPS_PERIODIC_BIST BIT(MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT) diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 7f467fe05d42..1a6a1f987949 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -559,4 +559,7 @@ struct kvm_pmu_event_filter { #define KVM_VCPU_TSC_CTRL 0 /* control group for the timestamp counter (TSC) */ #define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */ +/* x86-specific KVM_EXIT_HYPERCALL flags. */ +#define KVM_EXIT_HYPERCALL_LONG_MODE BIT(0) + #endif /* _ASM_X86_KVM_H */ diff --git a/tools/arch/x86/include/uapi/asm/prctl.h b/tools/arch/x86/include/uapi/asm/prctl.h index 500b96e71f18..e8d7ebbca1a4 100644 --- a/tools/arch/x86/include/uapi/asm/prctl.h +++ b/tools/arch/x86/include/uapi/asm/prctl.h @@ -16,8 +16,16 @@ #define ARCH_GET_XCOMP_GUEST_PERM 0x1024 #define ARCH_REQ_XCOMP_GUEST_PERM 0x1025 +#define ARCH_XCOMP_TILECFG 17 +#define ARCH_XCOMP_TILEDATA 18 + #define ARCH_MAP_VDSO_X32 0x2001 #define ARCH_MAP_VDSO_32 0x2002 #define ARCH_MAP_VDSO_64 0x2003 +#define ARCH_GET_UNTAG_MASK 0x4001 +#define ARCH_ENABLE_TAGGED_ADDR 0x4002 +#define ARCH_GET_MAX_TAG_BITS 0x4003 +#define ARCH_FORCE_TAGGED_SVA 0x4004 + #endif /* _ASM_X86_PRCTL_H */ diff --git a/tools/arch/x86/include/uapi/asm/unistd_32.h b/tools/arch/x86/include/uapi/asm/unistd_32.h index b8ddfc4c4ab0..bc48a4dabe5d 100644 --- a/tools/arch/x86/include/uapi/asm/unistd_32.h +++ b/tools/arch/x86/include/uapi/asm/unistd_32.h @@ -2,6 +2,9 @@ #ifndef __NR_fork #define __NR_fork 2 #endif +#ifndef __NR_execve +#define __NR_execve 11 +#endif #ifndef __NR_getppid #define __NR_getppid 64 #endif diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index a91ac666f758..d055b82d22cc 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -10,13 +10,6 @@ .section .noinstr.text, "ax" /* - * We build a jump to memcpy_orig by default which gets NOPped out on - * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which - * have the enhanced REP MOVSB/STOSB feature (ERMS), change those NOPs - * to a jmp to memcpy_erms which does the REP; MOVSB mem copy. - */ - -/* * memcpy - Copy a memory block. * * Input: @@ -26,17 +19,21 @@ * * Output: * rax original destination + * + * The FSRM alternative should be done inline (avoiding the call and + * the disgusting return handling), but that would require some help + * from the compiler for better calling conventions. + * + * The 'rep movsb' itself is small enough to replace the call, but the + * two register moves blow up the code. And one of them is "needed" + * only for the return value that is the same as the source input, + * which the compiler could/should do much better anyway. */ SYM_TYPED_FUNC_START(__memcpy) - ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ - "jmp memcpy_erms", X86_FEATURE_ERMS + ALTERNATIVE "jmp memcpy_orig", "", X86_FEATURE_FSRM movq %rdi, %rax movq %rdx, %rcx - shrq $3, %rcx - andl $7, %edx - rep movsq - movl %edx, %ecx rep movsb RET SYM_FUNC_END(__memcpy) @@ -45,17 +42,6 @@ EXPORT_SYMBOL(__memcpy) SYM_FUNC_ALIAS(memcpy, __memcpy) EXPORT_SYMBOL(memcpy) -/* - * memcpy_erms() - enhanced fast string memcpy. This is faster and - * simpler than memcpy. Use memcpy_erms when possible. - */ -SYM_FUNC_START_LOCAL(memcpy_erms) - movq %rdi, %rax - movq %rdx, %rcx - rep movsb - RET -SYM_FUNC_END(memcpy_erms) - SYM_FUNC_START_LOCAL(memcpy_orig) movq %rdi, %rax diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S index 6143b1a6fa2c..7c59a704c458 100644 --- a/tools/arch/x86/lib/memset_64.S +++ b/tools/arch/x86/lib/memset_64.S @@ -18,27 +18,22 @@ * rdx count (bytes) * * rax original destination + * + * The FSRS alternative should be done inline (avoiding the call and + * the disgusting return handling), but that would require some help + * from the compiler for better calling conventions. + * + * The 'rep stosb' itself is small enough to replace the call, but all + * the register moves blow up the code. And two of them are "needed" + * only for the return value that is the same as the source input, + * which the compiler could/should do much better anyway. */ SYM_FUNC_START(__memset) - /* - * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended - * to use it when possible. If not available, use fast string instructions. - * - * Otherwise, use original memset function. - */ - ALTERNATIVE_2 "jmp memset_orig", "", X86_FEATURE_REP_GOOD, \ - "jmp memset_erms", X86_FEATURE_ERMS + ALTERNATIVE "jmp memset_orig", "", X86_FEATURE_FSRS movq %rdi,%r9 + movb %sil,%al movq %rdx,%rcx - andl $7,%edx - shrq $3,%rcx - /* expand byte value */ - movzbl %sil,%esi - movabs $0x0101010101010101,%rax - imulq %rsi,%rax - rep stosq - movl %edx,%ecx rep stosb movq %r9,%rax RET @@ -48,26 +43,6 @@ EXPORT_SYMBOL(__memset) SYM_FUNC_ALIAS(memset, __memset) EXPORT_SYMBOL(memset) -/* - * ISO C memset - set a memory block to a byte value. This function uses - * enhanced rep stosb to override the fast string function. - * The code is simpler and shorter than the fast string function as well. - * - * rdi destination - * rsi value (char) - * rdx count (bytes) - * - * rax original destination - */ -SYM_FUNC_START_LOCAL(memset_erms) - movq %rdi,%r9 - movb %sil,%al - movq %rdx,%rcx - rep stosb - movq %r9,%rax - RET -SYM_FUNC_END(memset_erms) - SYM_FUNC_START_LOCAL(memset_orig) movq %rdi,%r10 diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 11250c4734fe..3b7ba037af95 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -28,7 +28,7 @@ MAP COMMANDS | **bpftool** **map** { **show** | **list** } [*MAP*] | **bpftool** **map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE* \ | **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**inner_map** *MAP*] \ -| [**dev** *NAME*] +| [**offload_dev** *NAME*] | **bpftool** **map dump** *MAP* | **bpftool** **map update** *MAP* [**key** *DATA*] [**value** *VALUE*] [*UPDATE_FLAGS*] | **bpftool** **map lookup** *MAP* [**key** *DATA*] @@ -73,7 +73,7 @@ DESCRIPTION maps. On such kernels bpftool will automatically emit this information as well. - **bpftool map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE* **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**inner_map** *MAP*] [**dev** *NAME*] + **bpftool map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE* **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**inner_map** *MAP*] [**offload_dev** *NAME*] Create a new map with given parameters and pin it to *bpffs* as *FILE*. @@ -86,8 +86,8 @@ DESCRIPTION kernel needs it to collect metadata related to the inner maps that the new map will work with. - Keyword **dev** expects a network interface name, and is used - to request hardware offload for the map. + Keyword **offload_dev** expects a network interface name, + and is used to request hardware offload for the map. **bpftool map dump** *MAP* Dump all entries in a given *MAP*. In case of **name**, diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 9443c524bb76..dcae81bd27ed 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -31,7 +31,7 @@ PROG COMMANDS | **bpftool** **prog dump xlated** *PROG* [{ **file** *FILE* | [**opcodes**] [**linum**] [**visual**] }] | **bpftool** **prog dump jited** *PROG* [{ **file** *FILE* | [**opcodes**] [**linum**] }] | **bpftool** **prog pin** *PROG* *FILE* -| **bpftool** **prog** { **load** | **loadall** } *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] [**pinmaps** *MAP_DIR*] [**autoattach**] +| **bpftool** **prog** { **load** | **loadall** } *OBJ* *PATH* [**type** *TYPE*] [**map** { **idx** *IDX* | **name** *NAME* } *MAP*] [{ **offload_dev** | **xdpmeta_dev** } *NAME*] [**pinmaps** *MAP_DIR*] [**autoattach**] | **bpftool** **prog attach** *PROG* *ATTACH_TYPE* [*MAP*] | **bpftool** **prog detach** *PROG* *ATTACH_TYPE* [*MAP*] | **bpftool** **prog tracelog** @@ -129,7 +129,7 @@ DESCRIPTION contain a dot character ('.'), which is reserved for future extensions of *bpffs*. - **bpftool prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] [**pinmaps** *MAP_DIR*] [**autoattach**] + **bpftool prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** { **idx** *IDX* | **name** *NAME* } *MAP*] [{ **offload_dev** | **xdpmeta_dev** } *NAME*] [**pinmaps** *MAP_DIR*] [**autoattach**] Load bpf program(s) from binary *OBJ* and pin as *PATH*. **bpftool prog load** pins only the first program from the *OBJ* as *PATH*. **bpftool prog loadall** pins all programs @@ -143,8 +143,11 @@ DESCRIPTION to be replaced in the ELF file counting from 0, while *NAME* allows to replace a map by name. *MAP* specifies the map to use, referring to it by **id** or through a **pinned** file. - If **dev** *NAME* is specified program will be loaded onto - given networking device (offload). + If **offload_dev** *NAME* is specified program will be loaded + onto given networking device (offload). + If **xdpmeta_dev** *NAME* is specified program will become + device-bound without offloading, this facilitates access + to XDP metadata. Optional **pinmaps** argument can be provided to pin all maps under *MAP_DIR* directory. diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index e7234d1a5306..085bf18f3659 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -278,7 +278,7 @@ _bpftool() _bpftool_get_prog_tags return 0 ;; - dev) + dev|offload_dev|xdpmeta_dev) _sysfs_get_netdevs return 0 ;; @@ -508,7 +508,8 @@ _bpftool() ;; *) COMPREPLY=( $( compgen -W "map" -- "$cur" ) ) - _bpftool_once_attr 'type dev pinmaps autoattach' + _bpftool_once_attr 'type pinmaps autoattach' + _bpftool_one_of_list 'offload_dev xdpmeta_dev' return 0 ;; esac @@ -733,7 +734,7 @@ _bpftool() esac ;; *) - _bpftool_once_attr 'type key value entries name flags dev' + _bpftool_once_attr 'type key value entries name flags offload_dev' if _bpftool_search_list 'array_of_maps' 'hash_of_maps'; then _bpftool_once_attr 'inner_map' fi diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 1360c82ae732..cc6e6aae2447 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -68,7 +68,7 @@ void p_info(const char *fmt, ...) va_end(ap); } -static bool is_bpffs(char *path) +static bool is_bpffs(const char *path) { struct statfs st_fs; @@ -244,13 +244,16 @@ int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type) return fd; } -int mount_bpffs_for_pin(const char *name) +int mount_bpffs_for_pin(const char *name, bool is_dir) { char err_str[ERR_MAX_LEN]; char *file; char *dir; int err = 0; + if (is_dir && is_bpffs(name)) + return err; + file = malloc(strlen(name) + 1); if (!file) { p_err("mem alloc failed"); @@ -286,7 +289,7 @@ int do_pin_fd(int fd, const char *name) { int err; - err = mount_bpffs_for_pin(name); + err = mount_bpffs_for_pin(name, false); if (err) return err; diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index da16e6a27ccc..0675d6a46413 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -167,12 +167,12 @@ static int get_vendor_id(int ifindex) return strtol(buf, NULL, 0); } -static int read_procfs(const char *path) +static long read_procfs(const char *path) { char *endptr, *line = NULL; size_t len = 0; FILE *fd; - int res; + long res; fd = fopen(path, "r"); if (!fd) @@ -194,7 +194,7 @@ static int read_procfs(const char *path) static void probe_unprivileged_disabled(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -216,14 +216,14 @@ static void probe_unprivileged_disabled(void) printf("Unable to retrieve required privileges for bpf() syscall\n"); break; default: - printf("bpf() syscall restriction has unknown value %d\n", res); + printf("bpf() syscall restriction has unknown value %ld\n", res); } } } static void probe_jit_enable(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -245,7 +245,7 @@ static void probe_jit_enable(void) printf("Unable to retrieve JIT-compiler status\n"); break; default: - printf("JIT-compiler status has unknown value %d\n", + printf("JIT-compiler status has unknown value %ld\n", res); } } @@ -253,7 +253,7 @@ static void probe_jit_enable(void) static void probe_jit_harden(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -275,7 +275,7 @@ static void probe_jit_harden(void) printf("Unable to retrieve JIT hardening status\n"); break; default: - printf("JIT hardening status has unknown value %d\n", + printf("JIT hardening status has unknown value %ld\n", res); } } @@ -283,7 +283,7 @@ static void probe_jit_harden(void) static void probe_jit_kallsyms(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -302,14 +302,14 @@ static void probe_jit_kallsyms(void) printf("Unable to retrieve JIT kallsyms export status\n"); break; default: - printf("JIT kallsyms exports status has unknown value %d\n", res); + printf("JIT kallsyms exports status has unknown value %ld\n", res); } } } static void probe_jit_limit(void) { - int res; + long res; /* No support for C-style ouptut */ @@ -322,7 +322,7 @@ static void probe_jit_limit(void) printf("Unable to retrieve global memory limit for JIT compiler for unprivileged users\n"); break; default: - printf("Global memory limit for JIT compiler for unprivileged users is %d bytes\n", res); + printf("Global memory limit for JIT compiler for unprivileged users is %ld bytes\n", res); } } } diff --git a/tools/bpf/bpftool/iter.c b/tools/bpf/bpftool/iter.c index 9a1d2365a297..6b0e5202ca7a 100644 --- a/tools/bpf/bpftool/iter.c +++ b/tools/bpf/bpftool/iter.c @@ -76,7 +76,7 @@ static int do_pin(int argc, char **argv) goto close_obj; } - err = mount_bpffs_for_pin(path); + err = mount_bpffs_for_pin(path, false); if (err) goto close_link; diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c index d98dbc50cf4c..2d786072ed0d 100644 --- a/tools/bpf/bpftool/link.c +++ b/tools/bpf/bpftool/link.c @@ -195,6 +195,8 @@ static int show_link_close_json(int fd, struct bpf_link_info *info) show_link_attach_type_json(info->tracing.attach_type, json_wtr); + jsonw_uint_field(json_wtr, "target_obj_id", info->tracing.target_obj_id); + jsonw_uint_field(json_wtr, "target_btf_id", info->tracing.target_btf_id); break; case BPF_LINK_TYPE_CGROUP: jsonw_lluint_field(json_wtr, "cgroup_id", @@ -212,7 +214,10 @@ static int show_link_close_json(int fd, struct bpf_link_info *info) case BPF_LINK_TYPE_NETFILTER: netfilter_dump_json(info, json_wtr); break; - + case BPF_LINK_TYPE_STRUCT_OPS: + jsonw_uint_field(json_wtr, "map_id", + info->struct_ops.map_id); + break; default: break; } @@ -245,7 +250,10 @@ static void show_link_header_plain(struct bpf_link_info *info) else printf("type %u ", info->type); - printf("prog %u ", info->prog_id); + if (info->type == BPF_LINK_TYPE_STRUCT_OPS) + printf("map %u ", info->struct_ops.map_id); + else + printf("prog %u ", info->prog_id); } static void show_link_attach_type_plain(__u32 attach_type) @@ -369,6 +377,10 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info) printf("\n\tprog_type %u ", prog_info.type); show_link_attach_type_plain(info->tracing.attach_type); + if (info->tracing.target_obj_id || info->tracing.target_btf_id) + printf("\n\ttarget_obj_id %u target_btf_id %u ", + info->tracing.target_obj_id, + info->tracing.target_btf_id); break; case BPF_LINK_TYPE_CGROUP: printf("\n\tcgroup_id %zu ", (size_t)info->cgroup.cgroup_id); diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index a49534d7eafa..b8bb08d10dec 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -142,7 +142,7 @@ const char *get_fd_type_name(enum bpf_obj_type type); char *get_fdinfo(int fd, const char *key); int open_obj_pinned(const char *path, bool quiet); int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type); -int mount_bpffs_for_pin(const char *name); +int mount_bpffs_for_pin(const char *name, bool is_dir); int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(int *, char ***)); int do_pin_fd(int fd, const char *name); diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index aaeb8939e137..f98f7bbea2b1 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -139,6 +139,9 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key, print_hex_data_json(key, info->key_size); jsonw_name(json_wtr, "value"); print_hex_data_json(value, info->value_size); + if (map_is_map_of_maps(info->type)) + jsonw_uint_field(json_wtr, "inner_map_id", + *(unsigned int *)value); if (btf) { struct btf_dumper d = { .btf = btf, @@ -259,8 +262,13 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, } if (info->value_size) { - printf("value:%c", break_names ? '\n' : ' '); - fprint_hex(stdout, value, info->value_size, " "); + if (map_is_map_of_maps(info->type)) { + printf("inner_map_id:%c", break_names ? '\n' : ' '); + printf("%u ", *(unsigned int *)value); + } else { + printf("value:%c", break_names ? '\n' : ' '); + fprint_hex(stdout, value, info->value_size, " "); + } } printf("\n"); @@ -1279,6 +1287,11 @@ static int do_create(int argc, char **argv) "flags")) goto exit; } else if (is_prefix(*argv, "dev")) { + p_info("Warning: 'bpftool map create [...] dev <ifname>' syntax is deprecated.\n" + "Going further, please use 'offload_dev <ifname>' to request hardware offload for the map."); + goto offload_dev; + } else if (is_prefix(*argv, "offload_dev")) { +offload_dev: NEXT_ARG(); if (attr.map_ifindex) { @@ -1423,7 +1436,7 @@ static int do_help(int argc, char **argv) "Usage: %1$s %2$s { show | list } [MAP]\n" " %1$s %2$s create FILE type TYPE key KEY_SIZE value VALUE_SIZE \\\n" " entries MAX_ENTRIES name NAME [flags FLAGS] \\\n" - " [inner_map MAP] [dev NAME]\n" + " [inner_map MAP] [offload_dev NAME]\n" " %1$s %2$s dump MAP\n" " %1$s %2$s update MAP [key DATA] [value VALUE] [UPDATE_FLAGS]\n" " %1$s %2$s lookup MAP [key DATA]\n" diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 91b6075b2db3..8443a149dd17 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -1517,12 +1517,13 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) struct bpf_program *prog = NULL, *pos; unsigned int old_map_fds = 0; const char *pinmaps = NULL; + __u32 xdpmeta_ifindex = 0; + __u32 offload_ifindex = 0; bool auto_attach = false; struct bpf_object *obj; struct bpf_map *map; const char *pinfile; unsigned int i, j; - __u32 ifindex = 0; const char *file; int idx, err; @@ -1614,17 +1615,46 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) map_replace[old_map_fds].fd = fd; old_map_fds++; } else if (is_prefix(*argv, "dev")) { + p_info("Warning: 'bpftool prog load [...] dev <ifname>' syntax is deprecated.\n" + "Going further, please use 'offload_dev <ifname>' to offload program to device.\n" + "For applications using XDP hints only, use 'xdpmeta_dev <ifname>'."); + goto offload_dev; + } else if (is_prefix(*argv, "offload_dev")) { +offload_dev: NEXT_ARG(); - if (ifindex) { - p_err("offload device already specified"); + if (offload_ifindex) { + p_err("offload_dev already specified"); + goto err_free_reuse_maps; + } else if (xdpmeta_ifindex) { + p_err("xdpmeta_dev and offload_dev are mutually exclusive"); + goto err_free_reuse_maps; + } + if (!REQ_ARGS(1)) + goto err_free_reuse_maps; + + offload_ifindex = if_nametoindex(*argv); + if (!offload_ifindex) { + p_err("unrecognized netdevice '%s': %s", + *argv, strerror(errno)); + goto err_free_reuse_maps; + } + NEXT_ARG(); + } else if (is_prefix(*argv, "xdpmeta_dev")) { + NEXT_ARG(); + + if (xdpmeta_ifindex) { + p_err("xdpmeta_dev already specified"); + goto err_free_reuse_maps; + } else if (offload_ifindex) { + p_err("xdpmeta_dev and offload_dev are mutually exclusive"); goto err_free_reuse_maps; } if (!REQ_ARGS(1)) goto err_free_reuse_maps; - ifindex = if_nametoindex(*argv); - if (!ifindex) { + xdpmeta_ifindex = if_nametoindex(*argv); + if (!xdpmeta_ifindex) { p_err("unrecognized netdevice '%s': %s", *argv, strerror(errno)); goto err_free_reuse_maps; @@ -1671,7 +1701,12 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) goto err_close_obj; } - bpf_program__set_ifindex(pos, ifindex); + if (prog_type == BPF_PROG_TYPE_XDP && xdpmeta_ifindex) { + bpf_program__set_flags(pos, BPF_F_XDP_DEV_BOUND_ONLY); + bpf_program__set_ifindex(pos, xdpmeta_ifindex); + } else { + bpf_program__set_ifindex(pos, offload_ifindex); + } if (bpf_program__type(pos) != prog_type) bpf_program__set_type(pos, prog_type); bpf_program__set_expected_attach_type(pos, expected_attach_type); @@ -1709,7 +1744,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) idx = 0; bpf_object__for_each_map(map, obj) { if (bpf_map__type(map) != BPF_MAP_TYPE_PERF_EVENT_ARRAY) - bpf_map__set_ifindex(map, ifindex); + bpf_map__set_ifindex(map, offload_ifindex); if (j < old_map_fds && idx == map_replace[j].idx) { err = bpf_map__reuse_fd(map, map_replace[j++].fd); @@ -1739,7 +1774,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) goto err_close_obj; } - err = mount_bpffs_for_pin(pinfile); + err = mount_bpffs_for_pin(pinfile, !first_prog_only); if (err) goto err_close_obj; @@ -2416,7 +2451,7 @@ static int do_help(int argc, char **argv) " %1$s %2$s dump jited PROG [{ file FILE | [opcodes] [linum] }]\n" " %1$s %2$s pin PROG FILE\n" " %1$s %2$s { load | loadall } OBJ PATH \\\n" - " [type TYPE] [dev NAME] \\\n" + " [type TYPE] [{ offload_dev | xdpmeta_dev } NAME] \\\n" " [map { idx IDX | name NAME } MAP]\\\n" " [pinmaps MAP_DIR]\n" " [autoattach]\n" diff --git a/tools/bpf/bpftool/struct_ops.c b/tools/bpf/bpftool/struct_ops.c index 57c3da70aa31..3ebc9fe91e0e 100644 --- a/tools/bpf/bpftool/struct_ops.c +++ b/tools/bpf/bpftool/struct_ops.c @@ -509,7 +509,7 @@ static int do_register(int argc, char **argv) if (argc == 1) linkdir = GET_ARG(); - if (linkdir && mount_bpffs_for_pin(linkdir)) { + if (linkdir && mount_bpffs_for_pin(linkdir, true)) { p_err("can't mount bpffs for pinning"); return -1; } diff --git a/tools/gpio/lsgpio.c b/tools/gpio/lsgpio.c index c61d061247e1..52a0be45410c 100644 --- a/tools/gpio/lsgpio.c +++ b/tools/gpio/lsgpio.c @@ -94,7 +94,7 @@ static void print_attributes(struct gpio_v2_line_info *info) for (i = 0; i < info->num_attrs; i++) { if (info->attrs[i].id == GPIO_V2_LINE_ATTR_ID_DEBOUNCE) fprintf(stdout, ", debounce_period=%dusec", - info->attrs[0].debounce_period_us); + info->attrs[i].debounce_period_us); } } diff --git a/tools/include/asm/alternative.h b/tools/include/asm/alternative.h index b54bd860dff6..7ce02a223732 100644 --- a/tools/include/asm/alternative.h +++ b/tools/include/asm/alternative.h @@ -4,7 +4,6 @@ /* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */ -#define altinstruction_entry # -#define ALTERNATIVE_2 # +#define ALTERNATIVE # #endif diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h index cef3b1c25335..51ac441a37c3 100644 --- a/tools/include/linux/coresight-pmu.h +++ b/tools/include/linux/coresight-pmu.h @@ -21,19 +21,6 @@ */ #define CORESIGHT_LEGACY_CPU_TRACE_ID(cpu) (0x10 + (cpu * 2)) -/* CoreSight trace ID is currently the bottom 7 bits of the value */ -#define CORESIGHT_TRACE_ID_VAL_MASK GENMASK(6, 0) - -/* - * perf record will set the legacy meta data values as unused initially. - * This allows perf report to manage the decoders created when dynamic - * allocation in operation. - */ -#define CORESIGHT_TRACE_ID_UNUSED_FLAG BIT(31) - -/* Value to set for unused trace ID values */ -#define CORESIGHT_TRACE_ID_UNUSED_VAL 0x7F - /* * Below are the definition of bit offsets for perf option, and works as * arbitrary values for all ETM versions. diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 642808520d92..a87bbbbca2d4 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -972,6 +972,19 @@ extern "C" { #define DRM_IOCTL_GET_STATS DRM_IOR( 0x06, struct drm_stats) #define DRM_IOCTL_SET_VERSION DRM_IOWR(0x07, struct drm_set_version) #define DRM_IOCTL_MODESET_CTL DRM_IOW(0x08, struct drm_modeset_ctl) +/** + * DRM_IOCTL_GEM_CLOSE - Close a GEM handle. + * + * GEM handles are not reference-counted by the kernel. User-space is + * responsible for managing their lifetime. For example, if user-space imports + * the same memory object twice on the same DRM file description, the same GEM + * handle is returned by both imports, and user-space needs to ensure + * &DRM_IOCTL_GEM_CLOSE is performed once only. The same situation can happen + * when a memory object is allocated, then exported and imported again on the + * same DRM file description. The &DRM_IOCTL_MODE_GETFB2 IOCTL is an exception + * and always returns fresh new GEM handles even if an existing GEM handle + * already refers to the same memory object before the IOCTL is performed. + */ #define DRM_IOCTL_GEM_CLOSE DRM_IOW (0x09, struct drm_gem_close) #define DRM_IOCTL_GEM_FLINK DRM_IOWR(0x0a, struct drm_gem_flink) #define DRM_IOCTL_GEM_OPEN DRM_IOWR(0x0b, struct drm_gem_open) @@ -1012,7 +1025,37 @@ extern "C" { #define DRM_IOCTL_UNLOCK DRM_IOW( 0x2b, struct drm_lock) #define DRM_IOCTL_FINISH DRM_IOW( 0x2c, struct drm_lock) +/** + * DRM_IOCTL_PRIME_HANDLE_TO_FD - Convert a GEM handle to a DMA-BUF FD. + * + * User-space sets &drm_prime_handle.handle with the GEM handle to export and + * &drm_prime_handle.flags, and gets back a DMA-BUF file descriptor in + * &drm_prime_handle.fd. + * + * The export can fail for any driver-specific reason, e.g. because export is + * not supported for this specific GEM handle (but might be for others). + * + * Support for exporting DMA-BUFs is advertised via &DRM_PRIME_CAP_EXPORT. + */ #define DRM_IOCTL_PRIME_HANDLE_TO_FD DRM_IOWR(0x2d, struct drm_prime_handle) +/** + * DRM_IOCTL_PRIME_FD_TO_HANDLE - Convert a DMA-BUF FD to a GEM handle. + * + * User-space sets &drm_prime_handle.fd with a DMA-BUF file descriptor to + * import, and gets back a GEM handle in &drm_prime_handle.handle. + * &drm_prime_handle.flags is unused. + * + * If an existing GEM handle refers to the memory object backing the DMA-BUF, + * that GEM handle is returned. Therefore user-space which needs to handle + * arbitrary DMA-BUFs must have a user-space lookup data structure to manually + * reference-count duplicated GEM handles. For more information see + * &DRM_IOCTL_GEM_CLOSE. + * + * The import can fail for any driver-specific reason, e.g. because import is + * only supported for DMA-BUFs allocated on this DRM device. + * + * Support for importing DMA-BUFs is advertised via &DRM_PRIME_CAP_IMPORT. + */ #define DRM_IOCTL_PRIME_FD_TO_HANDLE DRM_IOWR(0x2e, struct drm_prime_handle) #define DRM_IOCTL_AGP_ACQUIRE DRM_IO( 0x30) @@ -1104,8 +1147,13 @@ extern "C" { * struct as the output. * * If the client is DRM master or has &CAP_SYS_ADMIN, &drm_mode_fb_cmd2.handles - * will be filled with GEM buffer handles. Planes are valid until one has a - * zero handle -- this can be used to compute the number of planes. + * will be filled with GEM buffer handles. Fresh new GEM handles are always + * returned, even if another GEM handle referring to the same memory object + * already exists on the DRM file description. The caller is responsible for + * removing the new handles, e.g. via the &DRM_IOCTL_GEM_CLOSE IOCTL. The same + * new handle will be returned for multiple planes in case they use the same + * memory object. Planes are valid until one has a zero handle -- this can be + * used to compute the number of planes. * * Otherwise, &drm_mode_fb_cmd2.handles will be zeroed and planes are valid * until one has a zero &drm_mode_fb_cmd2.pitches. @@ -1113,6 +1161,11 @@ extern "C" { * If the framebuffer has a format modifier, &DRM_MODE_FB_MODIFIERS will be set * in &drm_mode_fb_cmd2.flags and &drm_mode_fb_cmd2.modifier will contain the * modifier. Otherwise, user-space must ignore &drm_mode_fb_cmd2.modifier. + * + * To obtain DMA-BUF FDs for each plane without leaking GEM handles, user-space + * can export each handle via &DRM_IOCTL_PRIME_HANDLE_TO_FD, then immediately + * close each unique handle via &DRM_IOCTL_GEM_CLOSE, making sure to not + * double-close handles which are specified multiple times in the array. */ #define DRM_IOCTL_MODE_GETFB2 DRM_IOWR(0xCE, struct drm_mode_fb_cmd2) diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 8df261c5ab9b..dba7c5a5b25e 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -2491,7 +2491,7 @@ struct i915_context_param_engines { #define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */ #define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */ #define I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT 2 /* see i915_context_engines_parallel_submit */ - struct i915_engine_class_instance engines[0]; + struct i915_engine_class_instance engines[]; } __attribute__((packed)); #define I915_DEFINE_CONTEXT_PARAM_ENGINES(name__, N__) struct { \ @@ -2676,6 +2676,10 @@ enum drm_i915_oa_format { I915_OAR_FORMAT_A32u40_A4u32_B8_C8, I915_OA_FORMAT_A24u40_A14u32_B8_C8, + /* MTL OAM */ + I915_OAM_FORMAT_MPEC8u64_B8_C8, + I915_OAM_FORMAT_MPEC8u32_B8_C8, + I915_OA_FORMAT_MAX /* non-ABI */ }; @@ -2758,6 +2762,25 @@ enum drm_i915_perf_property_id { */ DRM_I915_PERF_PROP_POLL_OA_PERIOD, + /** + * Multiple engines may be mapped to the same OA unit. The OA unit is + * identified by class:instance of any engine mapped to it. + * + * This parameter specifies the engine class and must be passed along + * with DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE. + * + * This property is available in perf revision 6. + */ + DRM_I915_PERF_PROP_OA_ENGINE_CLASS, + + /** + * This parameter specifies the engine instance and must be passed along + * with DRM_I915_PERF_PROP_OA_ENGINE_CLASS. + * + * This property is available in perf revision 6. + */ + DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE, + DRM_I915_PERF_PROP_MAX /* non-ABI */ }; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 1bb11a6ee667..6961a7b70028 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1035,6 +1035,7 @@ enum bpf_attach_type { BPF_TRACE_KPROBE_MULTI, BPF_LSM_CGROUP, BPF_STRUCT_OPS, + BPF_NETFILTER, __MAX_BPF_ATTACH_TYPE }; @@ -1272,6 +1273,9 @@ enum { /* Create a map that will be registered/unregesitered by the backed bpf_link */ BPF_F_LINK = (1U << 13), + +/* Get path from provided FD in BPF_OBJ_PIN/BPF_OBJ_GET commands */ + BPF_F_PATH_FD = (1U << 14), }; /* Flags for BPF_PROG_QUERY. */ @@ -1420,6 +1424,13 @@ union bpf_attr { __aligned_u64 pathname; __u32 bpf_fd; __u32 file_flags; + /* Same as dirfd in openat() syscall; see openat(2) + * manpage for details of path FD and pathname semantics; + * path_fd should accompanied by BPF_F_PATH_FD flag set in + * file_flags field, otherwise it should be set to zero; + * if BPF_F_PATH_FD flag is not set, AT_FDCWD is assumed. + */ + __s32 path_fd; }; struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */ diff --git a/tools/include/uapi/linux/const.h b/tools/include/uapi/linux/const.h index af2a44c08683..a429381e7ca5 100644 --- a/tools/include/uapi/linux/const.h +++ b/tools/include/uapi/linux/const.h @@ -28,7 +28,7 @@ #define _BITUL(x) (_UL(1) << (x)) #define _BITULL(x) (_ULL(1) << (x)) -#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) +#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1) #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) #define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index 07a4cb149305..e682ab628dfa 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -162,6 +162,8 @@ struct in_addr { #define MCAST_MSFILTER 48 #define IP_MULTICAST_ALL 49 #define IP_UNICAST_IF 50 +#define IP_LOCAL_PORT_RANGE 51 +#define IP_PROTOCOL 52 #define MCAST_EXCLUDE 0 #define MCAST_INCLUDE 1 diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 4003a166328c..737318b1c1d9 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -341,8 +341,13 @@ struct kvm_run { __u64 nr; __u64 args[6]; __u64 ret; - __u32 longmode; - __u32 pad; + + union { +#ifndef __KERNEL__ + __u32 longmode; +#endif + __u64 flags; + }; } hypercall; /* KVM_EXIT_TPR_ACCESS */ struct { @@ -1184,6 +1189,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 224 #define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225 #define KVM_CAP_PMU_EVENT_MASKED_EVENTS 226 +#define KVM_CAP_COUNTER_OFFSET 227 #ifdef KVM_CAP_IRQ_ROUTING @@ -1543,6 +1549,8 @@ struct kvm_s390_ucas_mapping { #define KVM_SET_PMU_EVENT_FILTER _IOW(KVMIO, 0xb2, struct kvm_pmu_event_filter) #define KVM_PPC_SVM_OFF _IO(KVMIO, 0xb3) #define KVM_ARM_MTE_COPY_TAGS _IOR(KVMIO, 0xb4, struct kvm_arm_copy_mte_tags) +/* Available with KVM_CAP_COUNTER_OFFSET */ +#define KVM_ARM_SET_COUNTER_OFFSET _IOW(KVMIO, 0xb5, struct kvm_arm_counter_offset) /* ioctl for vm fd */ #define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device) diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index 759b3f53e53f..f23d9a16507f 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -290,6 +290,8 @@ struct prctl_mm_map { #define PR_SET_VMA 0x53564d41 # define PR_SET_VMA_ANON_NAME 0 +#define PR_GET_AUXV 0x41555856 + #define PR_SET_MEMORY_MERGE 67 #define PR_GET_MEMORY_MERGE 68 #endif /* _LINUX_PRCTL_H */ diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h index de6810e94abe..0aa955aa8246 100644 --- a/tools/include/uapi/sound/asound.h +++ b/tools/include/uapi/sound/asound.h @@ -429,9 +429,14 @@ struct snd_pcm_sw_params { snd_pcm_uframes_t avail_min; /* min avail frames for wakeup */ snd_pcm_uframes_t xfer_align; /* obsolete: xfer size need to be a multiple */ snd_pcm_uframes_t start_threshold; /* min hw_avail frames for automatic start */ - snd_pcm_uframes_t stop_threshold; /* min avail frames for automatic stop */ - snd_pcm_uframes_t silence_threshold; /* min distance from noise for silence filling */ - snd_pcm_uframes_t silence_size; /* silence block size */ + /* + * The following two thresholds alleviate playback buffer underruns; when + * hw_avail drops below the threshold, the respective action is triggered: + */ + snd_pcm_uframes_t stop_threshold; /* - stop playback */ + snd_pcm_uframes_t silence_threshold; /* - pre-fill buffer with silence */ + snd_pcm_uframes_t silence_size; /* max size of silence pre-fill; when >= boundary, + * fill played area with silence immediately */ snd_pcm_uframes_t boundary; /* pointers wrap point */ unsigned int proto; /* protocol version */ unsigned int tstamp_type; /* timestamp type (req. proto >= 2.0.12) */ @@ -570,7 +575,8 @@ struct __snd_pcm_mmap_status64 { struct __snd_pcm_mmap_control64 { __pad_before_uframe __pad1; snd_pcm_uframes_t appl_ptr; /* RW: appl ptr (0...boundary-1) */ - __pad_before_uframe __pad2; + __pad_before_uframe __pad2; // This should be __pad_after_uframe, but binary + // backwards compatibility constraints prevent a fix. __pad_before_uframe __pad3; snd_pcm_uframes_t avail_min; /* RW: min available frames for wakeup */ diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 128ac723c4ea..ed86b37d8024 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -572,20 +572,30 @@ int bpf_map_update_batch(int fd, const void *keys, const void *values, __u32 *co (void *)keys, (void *)values, count, opts); } -int bpf_obj_pin(int fd, const char *pathname) +int bpf_obj_pin_opts(int fd, const char *pathname, const struct bpf_obj_pin_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, file_flags); + const size_t attr_sz = offsetofend(union bpf_attr, path_fd); union bpf_attr attr; int ret; + if (!OPTS_VALID(opts, bpf_obj_pin_opts)) + return libbpf_err(-EINVAL); + memset(&attr, 0, attr_sz); + attr.path_fd = OPTS_GET(opts, path_fd, 0); attr.pathname = ptr_to_u64((void *)pathname); + attr.file_flags = OPTS_GET(opts, file_flags, 0); attr.bpf_fd = fd; ret = sys_bpf(BPF_OBJ_PIN, &attr, attr_sz); return libbpf_err_errno(ret); } +int bpf_obj_pin(int fd, const char *pathname) +{ + return bpf_obj_pin_opts(fd, pathname, NULL); +} + int bpf_obj_get(const char *pathname) { return bpf_obj_get_opts(pathname, NULL); @@ -593,7 +603,7 @@ int bpf_obj_get(const char *pathname) int bpf_obj_get_opts(const char *pathname, const struct bpf_obj_get_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, file_flags); + const size_t attr_sz = offsetofend(union bpf_attr, path_fd); union bpf_attr attr; int fd; @@ -601,6 +611,7 @@ int bpf_obj_get_opts(const char *pathname, const struct bpf_obj_get_opts *opts) return libbpf_err(-EINVAL); memset(&attr, 0, attr_sz); + attr.path_fd = OPTS_GET(opts, path_fd, 0); attr.pathname = ptr_to_u64((void *)pathname); attr.file_flags = OPTS_GET(opts, file_flags, 0); diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index a2c091389b18..9aa0ee473754 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -284,16 +284,30 @@ LIBBPF_API int bpf_map_update_batch(int fd, const void *keys, const void *values __u32 *count, const struct bpf_map_batch_opts *opts); -struct bpf_obj_get_opts { +struct bpf_obj_pin_opts { size_t sz; /* size of this struct for forward/backward compatibility */ __u32 file_flags; + int path_fd; size_t :0; }; -#define bpf_obj_get_opts__last_field file_flags +#define bpf_obj_pin_opts__last_field path_fd LIBBPF_API int bpf_obj_pin(int fd, const char *pathname); +LIBBPF_API int bpf_obj_pin_opts(int fd, const char *pathname, + const struct bpf_obj_pin_opts *opts); + +struct bpf_obj_get_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + + __u32 file_flags; + int path_fd; + + size_t :0; +}; +#define bpf_obj_get_opts__last_field path_fd + LIBBPF_API int bpf_obj_get(const char *pathname); LIBBPF_API int bpf_obj_get_opts(const char *pathname, const struct bpf_obj_get_opts *opts); diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index 929a3baca8ef..bbab9ad9dc5a 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -77,16 +77,21 @@ /* * Helper macros to manipulate data structures */ -#ifndef offsetof -#define offsetof(TYPE, MEMBER) ((unsigned long)&((TYPE *)0)->MEMBER) -#endif -#ifndef container_of + +/* offsetof() definition that uses __builtin_offset() might not preserve field + * offset CO-RE relocation properly, so force-redefine offsetof() using + * old-school approach which works with CO-RE correctly + */ +#undef offsetof +#define offsetof(type, member) ((unsigned long)&((type *)0)->member) + +/* redefined container_of() to ensure we use the above offsetof() macro */ +#undef container_of #define container_of(ptr, type, member) \ ({ \ void *__mptr = (void *)(ptr); \ ((type *)(__mptr - offsetof(type, member))); \ }) -#endif /* * Compiler (optimization) barrier. diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h index 6fb3d0f9af17..be076a4041ab 100644 --- a/tools/lib/bpf/bpf_tracing.h +++ b/tools/lib/bpf/bpf_tracing.h @@ -351,6 +351,7 @@ struct pt_regs___arm64 { * https://github.com/riscv-non-isa/riscv-elf-psabi-doc/blob/master/riscv-cc.adoc#risc-v-calling-conventions */ +/* riscv provides struct user_regs_struct instead of struct pt_regs to userspace */ #define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x)) #define __PT_PARM1_REG a0 #define __PT_PARM2_REG a1 @@ -383,7 +384,7 @@ struct pt_regs___arm64 { * https://raw.githubusercontent.com/wiki/foss-for-synopsys-dwc-arc-processors/toolchain/files/ARCv2_ABI.pdf */ -/* arc provides struct user_pt_regs instead of struct pt_regs to userspace */ +/* arc provides struct user_regs_struct instead of struct pt_regs to userspace */ #define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x)) #define __PT_PARM1_REG scratch.r0 #define __PT_PARM2_REG scratch.r1 diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 0a2c079244b6..8484b563b53d 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1064,7 +1064,7 @@ static struct btf *btf_parse_raw(const char *path, struct btf *base_btf) int err = 0; long sz; - f = fopen(path, "rb"); + f = fopen(path, "rbe"); if (!f) { err = -errno; goto err_out; diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 580985ee5545..4d9f30bf7f01 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -2250,9 +2250,25 @@ static int btf_dump_type_data_check_overflow(struct btf_dump *d, const struct btf_type *t, __u32 id, const void *data, - __u8 bits_offset) + __u8 bits_offset, + __u8 bit_sz) { - __s64 size = btf__resolve_size(d->btf, id); + __s64 size; + + if (bit_sz) { + /* bits_offset is at most 7. bit_sz is at most 128. */ + __u8 nr_bytes = (bits_offset + bit_sz + 7) / 8; + + /* When bit_sz is non zero, it is called from + * btf_dump_struct_data() where it only cares about + * negative error value. + * Return nr_bytes in success case to make it + * consistent as the regular integer case below. + */ + return data + nr_bytes > d->typed_dump->data_end ? -E2BIG : nr_bytes; + } + + size = btf__resolve_size(d->btf, id); if (size < 0 || size >= INT_MAX) { pr_warn("unexpected size [%zu] for id [%u]\n", @@ -2407,7 +2423,7 @@ static int btf_dump_dump_type_data(struct btf_dump *d, { int size, err = 0; - size = btf_dump_type_data_check_overflow(d, t, id, data, bits_offset); + size = btf_dump_type_data_check_overflow(d, t, id, data, bits_offset, bit_sz); if (size < 0) return size; err = btf_dump_type_data_check_zero(d, t, id, data, bits_offset, bit_sz); diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c index 83e8e3bfd8ff..cf3323fd47b8 100644 --- a/tools/lib/bpf/gen_loader.c +++ b/tools/lib/bpf/gen_loader.c @@ -703,17 +703,17 @@ static void emit_relo_kfunc_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo /* obtain fd in BPF_REG_9 */ emit(gen, BPF_MOV64_REG(BPF_REG_9, BPF_REG_7)); emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_9, 32)); - /* jump to fd_array store if fd denotes module BTF */ - emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0, 2)); - /* set the default value for off */ - emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), 0)); - /* skip BTF fd store for vmlinux BTF */ - emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 4)); /* load fd_array slot pointer */ emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE, 0, 0, 0, blob_fd_array_off(gen, btf_fd_idx))); - /* store BTF fd in slot */ + /* store BTF fd in slot, 0 for vmlinux */ emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_9, 0)); + /* jump to insn[insn_idx].off store if fd denotes module BTF */ + emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0, 2)); + /* set the default value for off */ + emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), 0)); + /* skip BTF fd store for vmlinux BTF */ + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 1)); /* store index into insn[insn_idx].off */ emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), btf_fd_idx)); log: diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index ad1ec893b41b..214f828ece6b 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -117,6 +117,7 @@ static const char * const attach_type_name[] = { [BPF_PERF_EVENT] = "perf_event", [BPF_TRACE_KPROBE_MULTI] = "trace_kprobe_multi", [BPF_STRUCT_OPS] = "struct_ops", + [BPF_NETFILTER] = "netfilter", }; static const char * const link_type_name[] = { @@ -1500,16 +1501,36 @@ static struct bpf_map *bpf_object__add_map(struct bpf_object *obj) return map; } -static size_t bpf_map_mmap_sz(const struct bpf_map *map) +static size_t bpf_map_mmap_sz(unsigned int value_sz, unsigned int max_entries) { - long page_sz = sysconf(_SC_PAGE_SIZE); + const long page_sz = sysconf(_SC_PAGE_SIZE); size_t map_sz; - map_sz = (size_t)roundup(map->def.value_size, 8) * map->def.max_entries; + map_sz = (size_t)roundup(value_sz, 8) * max_entries; map_sz = roundup(map_sz, page_sz); return map_sz; } +static int bpf_map_mmap_resize(struct bpf_map *map, size_t old_sz, size_t new_sz) +{ + void *mmaped; + + if (!map->mmaped) + return -EINVAL; + + if (old_sz == new_sz) + return 0; + + mmaped = mmap(NULL, new_sz, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0); + if (mmaped == MAP_FAILED) + return -errno; + + memcpy(mmaped, map->mmaped, min(old_sz, new_sz)); + munmap(map->mmaped, old_sz); + map->mmaped = mmaped; + return 0; +} + static char *internal_map_name(struct bpf_object *obj, const char *real_name) { char map_name[BPF_OBJ_NAME_LEN], *p; @@ -1608,6 +1629,7 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, { struct bpf_map_def *def; struct bpf_map *map; + size_t mmap_sz; int err; map = bpf_object__add_map(obj); @@ -1642,7 +1664,8 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, pr_debug("map '%s' (global data): at sec_idx %d, offset %zu, flags %x.\n", map->name, map->sec_idx, map->sec_offset, def->map_flags); - map->mmaped = mmap(NULL, bpf_map_mmap_sz(map), PROT_READ | PROT_WRITE, + mmap_sz = bpf_map_mmap_sz(map->def.value_size, map->def.max_entries); + map->mmaped = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0); if (map->mmaped == MAP_FAILED) { err = -errno; @@ -4329,7 +4352,7 @@ static int bpf_get_map_info_from_fdinfo(int fd, struct bpf_map_info *info) snprintf(file, sizeof(file), "/proc/%d/fdinfo/%d", getpid(), fd); memset(info, 0, sizeof(*info)); - fp = fopen(file, "r"); + fp = fopen(file, "re"); if (!fp) { err = -errno; pr_warn("failed to open %s: %d. No procfs support?\n", file, @@ -4392,18 +4415,17 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd) if (!new_name) return libbpf_err(-errno); - new_fd = open("/", O_RDONLY | O_CLOEXEC); + /* + * Like dup(), but make sure new FD is >= 3 and has O_CLOEXEC set. + * This is similar to what we do in ensure_good_fd(), but without + * closing original FD. + */ + new_fd = fcntl(fd, F_DUPFD_CLOEXEC, 3); if (new_fd < 0) { err = -errno; goto err_free_new_name; } - new_fd = dup3(fd, new_fd, O_CLOEXEC); - if (new_fd < 0) { - err = -errno; - goto err_close_new_fd; - } - err = zclose(map->fd); if (err) { err = -errno; @@ -7433,7 +7455,7 @@ int libbpf_kallsyms_parse(kallsyms_cb_t cb, void *ctx) int ret, err = 0; FILE *f; - f = fopen("/proc/kallsyms", "r"); + f = fopen("/proc/kallsyms", "re"); if (!f) { err = -errno; pr_warn("failed to open /proc/kallsyms: %d\n", err); @@ -8294,7 +8316,10 @@ static void bpf_map__destroy(struct bpf_map *map) map->init_slots_sz = 0; if (map->mmaped) { - munmap(map->mmaped, bpf_map_mmap_sz(map)); + size_t mmap_sz; + + mmap_sz = bpf_map_mmap_sz(map->def.value_size, map->def.max_entries); + munmap(map->mmaped, mmap_sz); map->mmaped = NULL; } @@ -8712,7 +8737,7 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("struct_ops+", STRUCT_OPS, 0, SEC_NONE), SEC_DEF("struct_ops.s+", STRUCT_OPS, 0, SEC_SLEEPABLE), SEC_DEF("sk_lookup", SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE), - SEC_DEF("netfilter", NETFILTER, 0, SEC_NONE), + SEC_DEF("netfilter", NETFILTER, BPF_NETFILTER, SEC_NONE), }; static size_t custom_sec_def_cnt; @@ -9412,10 +9437,103 @@ __u32 bpf_map__value_size(const struct bpf_map *map) return map->def.value_size; } +static int map_btf_datasec_resize(struct bpf_map *map, __u32 size) +{ + struct btf *btf; + struct btf_type *datasec_type, *var_type; + struct btf_var_secinfo *var; + const struct btf_type *array_type; + const struct btf_array *array; + int vlen, element_sz, new_array_id; + __u32 nr_elements; + + /* check btf existence */ + btf = bpf_object__btf(map->obj); + if (!btf) + return -ENOENT; + + /* verify map is datasec */ + datasec_type = btf_type_by_id(btf, bpf_map__btf_value_type_id(map)); + if (!btf_is_datasec(datasec_type)) { + pr_warn("map '%s': cannot be resized, map value type is not a datasec\n", + bpf_map__name(map)); + return -EINVAL; + } + + /* verify datasec has at least one var */ + vlen = btf_vlen(datasec_type); + if (vlen == 0) { + pr_warn("map '%s': cannot be resized, map value datasec is empty\n", + bpf_map__name(map)); + return -EINVAL; + } + + /* verify last var in the datasec is an array */ + var = &btf_var_secinfos(datasec_type)[vlen - 1]; + var_type = btf_type_by_id(btf, var->type); + array_type = skip_mods_and_typedefs(btf, var_type->type, NULL); + if (!btf_is_array(array_type)) { + pr_warn("map '%s': cannot be resized, last var must be an array\n", + bpf_map__name(map)); + return -EINVAL; + } + + /* verify request size aligns with array */ + array = btf_array(array_type); + element_sz = btf__resolve_size(btf, array->type); + if (element_sz <= 0 || (size - var->offset) % element_sz != 0) { + pr_warn("map '%s': cannot be resized, element size (%d) doesn't align with new total size (%u)\n", + bpf_map__name(map), element_sz, size); + return -EINVAL; + } + + /* create a new array based on the existing array, but with new length */ + nr_elements = (size - var->offset) / element_sz; + new_array_id = btf__add_array(btf, array->index_type, array->type, nr_elements); + if (new_array_id < 0) + return new_array_id; + + /* adding a new btf type invalidates existing pointers to btf objects, + * so refresh pointers before proceeding + */ + datasec_type = btf_type_by_id(btf, map->btf_value_type_id); + var = &btf_var_secinfos(datasec_type)[vlen - 1]; + var_type = btf_type_by_id(btf, var->type); + + /* finally update btf info */ + datasec_type->size = size; + var->size = size - var->offset; + var_type->type = new_array_id; + + return 0; +} + int bpf_map__set_value_size(struct bpf_map *map, __u32 size) { if (map->fd >= 0) return libbpf_err(-EBUSY); + + if (map->mmaped) { + int err; + size_t mmap_old_sz, mmap_new_sz; + + mmap_old_sz = bpf_map_mmap_sz(map->def.value_size, map->def.max_entries); + mmap_new_sz = bpf_map_mmap_sz(size, map->def.max_entries); + err = bpf_map_mmap_resize(map, mmap_old_sz, mmap_new_sz); + if (err) { + pr_warn("map '%s': failed to resize memory-mapped region: %d\n", + bpf_map__name(map), err); + return err; + } + err = map_btf_datasec_resize(map, size); + if (err && err != -ENOENT) { + pr_warn("map '%s': failed to adjust resized BTF, clearing BTF key/value info: %d\n", + bpf_map__name(map), err); + map->btf_value_type_id = 0; + map->btf_key_type_id = 0; + } + } + map->def.value_size = size; return 0; } @@ -9441,7 +9559,7 @@ int bpf_map__set_initial_value(struct bpf_map *map, return 0; } -const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize) +void *bpf_map__initial_value(struct bpf_map *map, size_t *psize) { if (!map->mmaped) return NULL; @@ -9957,7 +10075,7 @@ static int parse_uint_from_file(const char *file, const char *fmt) int err, ret; FILE *f; - f = fopen(file, "r"); + f = fopen(file, "re"); if (!f) { err = -errno; pr_debug("failed to open '%s': %s\n", file, @@ -12693,7 +12811,7 @@ int bpf_object__load_skeleton(struct bpf_object_skeleton *s) for (i = 0; i < s->map_cnt; i++) { struct bpf_map *map = *s->maps[i].map; - size_t mmap_sz = bpf_map_mmap_sz(map); + size_t mmap_sz = bpf_map_mmap_sz(map->def.value_size, map->def.max_entries); int prot, map_fd = bpf_map__fd(map); void **mmaped = s->maps[i].mmaped; @@ -12720,8 +12838,7 @@ int bpf_object__load_skeleton(struct bpf_object_skeleton *s) * as per normal clean up procedure, so we don't need to worry * about it from skeleton's clean up perspective. */ - *mmaped = mmap(map->mmaped, mmap_sz, prot, - MAP_SHARED | MAP_FIXED, map_fd, 0); + *mmaped = mmap(map->mmaped, mmap_sz, prot, MAP_SHARED | MAP_FIXED, map_fd, 0); if (*mmaped == MAP_FAILED) { err = -errno; *mmaped = NULL; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 0b7362397ea3..754da73c643b 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -869,8 +869,22 @@ LIBBPF_API int bpf_map__set_numa_node(struct bpf_map *map, __u32 numa_node); /* get/set map key size */ LIBBPF_API __u32 bpf_map__key_size(const struct bpf_map *map); LIBBPF_API int bpf_map__set_key_size(struct bpf_map *map, __u32 size); -/* get/set map value size */ +/* get map value size */ LIBBPF_API __u32 bpf_map__value_size(const struct bpf_map *map); +/** + * @brief **bpf_map__set_value_size()** sets map value size. + * @param map the BPF map instance + * @return 0, on success; negative error, otherwise + * + * There is a special case for maps with associated memory-mapped regions, like + * the global data section maps (bss, data, rodata). When this function is used + * on such a map, the mapped region is resized. Afterward, an attempt is made to + * adjust the corresponding BTF info. This attempt is best-effort and can only + * succeed if the last variable of the data section map is an array. The array + * BTF type is replaced by a new BTF array type with a different length. + * Any previously existing pointers returned from bpf_map__initial_value() or + * corresponding data section skeleton pointer must be reinitialized. + */ LIBBPF_API int bpf_map__set_value_size(struct bpf_map *map, __u32 size); /* get map key/value BTF type IDs */ LIBBPF_API __u32 bpf_map__btf_key_type_id(const struct bpf_map *map); @@ -884,7 +898,7 @@ LIBBPF_API int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra); LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map, const void *data, size_t size); -LIBBPF_API const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize); +LIBBPF_API void *bpf_map__initial_value(struct bpf_map *map, size_t *psize); /** * @brief **bpf_map__is_internal()** tells the caller whether or not the diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index a5aa3a383d69..7521a2fb7626 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -391,3 +391,8 @@ LIBBPF_1.2.0 { bpf_map_get_info_by_fd; bpf_prog_get_info_by_fd; } LIBBPF_1.1.0; + +LIBBPF_1.3.0 { + global: + bpf_obj_pin_opts; +} LIBBPF_1.2.0; diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index 6065f408a59c..9c4db90b92b6 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -38,7 +38,7 @@ static __u32 get_ubuntu_kernel_version(void) if (faccessat(AT_FDCWD, ubuntu_kver_file, R_OK, AT_EACCESS) != 0) return 0; - f = fopen(ubuntu_kver_file, "r"); + f = fopen(ubuntu_kver_file, "re"); if (!f) return 0; @@ -180,7 +180,9 @@ static int probe_prog_load(enum bpf_prog_type prog_type, case BPF_PROG_TYPE_SK_REUSEPORT: case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_CGROUP_SYSCTL: + break; case BPF_PROG_TYPE_NETFILTER: + opts.expected_attach_type = BPF_NETFILTER; break; default: return -EOPNOTSUPP; diff --git a/tools/lib/bpf/libbpf_version.h b/tools/lib/bpf/libbpf_version.h index 1fd2eeac5cfc..290411ddb39e 100644 --- a/tools/lib/bpf/libbpf_version.h +++ b/tools/lib/bpf/libbpf_version.h @@ -4,6 +4,6 @@ #define __LIBBPF_VERSION_H #define LIBBPF_MAJOR_VERSION 1 -#define LIBBPF_MINOR_VERSION 2 +#define LIBBPF_MINOR_VERSION 3 #endif /* __LIBBPF_VERSION_H */ diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c index 086eef355ab3..f1a141555f08 100644 --- a/tools/lib/bpf/usdt.c +++ b/tools/lib/bpf/usdt.c @@ -466,7 +466,7 @@ static int parse_vma_segs(int pid, const char *lib_path, struct elf_seg **segs, proceed: sprintf(line, "/proc/%d/maps", pid); - f = fopen(line, "r"); + f = fopen(line, "re"); if (!f) { err = -errno; pr_warn("usdt: failed to open '%s' to get base addr of '%s': %d\n", @@ -954,8 +954,7 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct spec_map_fd = bpf_map__fd(man->specs_map); ip_map_fd = bpf_map__fd(man->ip_to_spec_id_map); - /* TODO: perform path resolution similar to uprobe's */ - fd = open(path, O_RDONLY); + fd = open(path, O_RDONLY | O_CLOEXEC); if (fd < 0) { err = -errno; pr_warn("usdt: failed to open ELF binary '%s': %d\n", path, err); diff --git a/tools/net/ynl/Makefile b/tools/net/ynl/Makefile new file mode 100644 index 000000000000..d664b36deb5b --- /dev/null +++ b/tools/net/ynl/Makefile @@ -0,0 +1,19 @@ +# SPDX-License-Identifier: GPL-2.0 + +SUBDIRS = lib generated samples + +all: $(SUBDIRS) + +$(SUBDIRS): + @if [ -f "$@/Makefile" ] ; then \ + $(MAKE) -C $@ ; \ + fi + +clean hardclean: + @for dir in $(SUBDIRS) ; do \ + if [ -f "$$dir/Makefile" ] ; then \ + $(MAKE) -C $$dir $@; \ + fi \ + done + +.PHONY: clean all $(SUBDIRS) diff --git a/tools/net/ynl/generated/Makefile b/tools/net/ynl/generated/Makefile new file mode 100644 index 000000000000..8ce610910b8d --- /dev/null +++ b/tools/net/ynl/generated/Makefile @@ -0,0 +1,45 @@ +# SPDX-License-Identifier: GPL-2.0 + +CC=gcc +CFLAGS=-std=gnu11 -O2 -W -Wall -Wextra -Wno-unused-parameter -Wshadow \ + -I../lib/ +ifeq ("$(DEBUG)","1") + CFLAGS += -g -fsanitize=address -fsanitize=leak -static-libasan +endif + +TOOL:=../ynl-gen-c.py + +GENS:=devlink handshake fou netdev +SRCS=$(patsubst %,%-user.c,${GENS}) +HDRS=$(patsubst %,%-user.h,${GENS}) +OBJS=$(patsubst %,%-user.o,${GENS}) + +all: protos.a $(HDRS) $(SRCS) $(KHDRS) $(KSRCS) $(UAPI) regen + +protos.a: $(OBJS) + @echo -e "\tAR $@" + @ar rcs $@ $(OBJS) + +%-user.h: ../../../../Documentation/netlink/specs/%.yaml $(TOOL) + @echo -e "\tGEN $@" + @$(TOOL) --mode user --header --spec $< > $@ + +%-user.c: ../../../../Documentation/netlink/specs/%.yaml $(TOOL) + @echo -e "\tGEN $@" + @$(TOOL) --mode user --source --spec $< > $@ + +%-user.o: %-user.c %-user.h + @echo -e "\tCC $@" + @$(COMPILE.c) -c -o $@ $< + +clean: + rm -f *.o + +hardclean: clean + rm -f *.c *.h *.a + +regen: + @../ynl-regen.sh + +.PHONY: all clean hardclean regen +.DEFAULT_GOAL: all diff --git a/tools/net/ynl/generated/devlink-user.c b/tools/net/ynl/generated/devlink-user.c new file mode 100644 index 000000000000..939bd45feaca --- /dev/null +++ b/tools/net/ynl/generated/devlink-user.c @@ -0,0 +1,721 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/devlink.yaml */ +/* YNL-GEN user source */ + +#include <stdlib.h> +#include <string.h> +#include "devlink-user.h" +#include "ynl.h" +#include <linux/devlink.h> + +#include <libmnl/libmnl.h> +#include <linux/genetlink.h> + +/* Enums */ +static const char * const devlink_op_strmap[] = { + [3] = "get", + [DEVLINK_CMD_INFO_GET] = "info-get", +}; + +const char *devlink_op_str(int op) +{ + if (op < 0 || op >= (int)MNL_ARRAY_SIZE(devlink_op_strmap)) + return NULL; + return devlink_op_strmap[op]; +} + +/* Policies */ +struct ynl_policy_attr devlink_dl_info_version_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_INFO_VERSION_NAME] = { .name = "info-version-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_INFO_VERSION_VALUE] = { .name = "info-version-value", .type = YNL_PT_NUL_STR, }, +}; + +struct ynl_policy_nest devlink_dl_info_version_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_info_version_policy, +}; + +struct ynl_policy_attr devlink_dl_reload_stats_entry_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_RELOAD_STATS_LIMIT] = { .name = "reload-stats-limit", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_RELOAD_STATS_VALUE] = { .name = "reload-stats-value", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest devlink_dl_reload_stats_entry_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_reload_stats_entry_policy, +}; + +struct ynl_policy_attr devlink_dl_reload_act_stats_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_RELOAD_STATS_ENTRY] = { .name = "reload-stats-entry", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_entry_nest, }, +}; + +struct ynl_policy_nest devlink_dl_reload_act_stats_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_reload_act_stats_policy, +}; + +struct ynl_policy_attr devlink_dl_reload_act_info_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_RELOAD_ACTION] = { .name = "reload-action", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_RELOAD_ACTION_STATS] = { .name = "reload-action-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_act_stats_nest, }, +}; + +struct ynl_policy_nest devlink_dl_reload_act_info_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_reload_act_info_policy, +}; + +struct ynl_policy_attr devlink_dl_reload_stats_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_RELOAD_ACTION_INFO] = { .name = "reload-action-info", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_act_info_nest, }, +}; + +struct ynl_policy_nest devlink_dl_reload_stats_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_reload_stats_policy, +}; + +struct ynl_policy_attr devlink_dl_dev_stats_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_RELOAD_STATS] = { .name = "reload-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_nest, }, + [DEVLINK_ATTR_REMOTE_RELOAD_STATS] = { .name = "remote-reload-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_nest, }, +}; + +struct ynl_policy_nest devlink_dl_dev_stats_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_dev_stats_policy, +}; + +struct ynl_policy_attr devlink_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .name = "bus-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_DEV_NAME] = { .name = "dev-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_PORT_INDEX] = { .name = "port-index", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_INFO_DRIVER_NAME] = { .name = "info-driver-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_INFO_SERIAL_NUMBER] = { .name = "info-serial-number", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_INFO_VERSION_FIXED] = { .name = "info-version-fixed", .type = YNL_PT_NEST, .nest = &devlink_dl_info_version_nest, }, + [DEVLINK_ATTR_INFO_VERSION_RUNNING] = { .name = "info-version-running", .type = YNL_PT_NEST, .nest = &devlink_dl_info_version_nest, }, + [DEVLINK_ATTR_INFO_VERSION_STORED] = { .name = "info-version-stored", .type = YNL_PT_NEST, .nest = &devlink_dl_info_version_nest, }, + [DEVLINK_ATTR_INFO_VERSION_NAME] = { .name = "info-version-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_INFO_VERSION_VALUE] = { .name = "info-version-value", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_RELOAD_FAILED] = { .name = "reload-failed", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_RELOAD_ACTION] = { .name = "reload-action", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_DEV_STATS] = { .name = "dev-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_dev_stats_nest, }, + [DEVLINK_ATTR_RELOAD_STATS] = { .name = "reload-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_nest, }, + [DEVLINK_ATTR_RELOAD_STATS_ENTRY] = { .name = "reload-stats-entry", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_entry_nest, }, + [DEVLINK_ATTR_RELOAD_STATS_LIMIT] = { .name = "reload-stats-limit", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_RELOAD_STATS_VALUE] = { .name = "reload-stats-value", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_REMOTE_RELOAD_STATS] = { .name = "remote-reload-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_nest, }, + [DEVLINK_ATTR_RELOAD_ACTION_INFO] = { .name = "reload-action-info", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_act_info_nest, }, + [DEVLINK_ATTR_RELOAD_ACTION_STATS] = { .name = "reload-action-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_act_stats_nest, }, +}; + +struct ynl_policy_nest devlink_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_policy, +}; + +/* Common nested types */ +void devlink_dl_info_version_free(struct devlink_dl_info_version *obj) +{ + free(obj->info_version_name); + free(obj->info_version_value); +} + +int devlink_dl_info_version_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_info_version *dst = yarg->data; + const struct nlattr *attr; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_INFO_VERSION_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.info_version_name_len = len; + dst->info_version_name = malloc(len + 1); + memcpy(dst->info_version_name, mnl_attr_get_str(attr), len); + dst->info_version_name[len] = 0; + } else if (type == DEVLINK_ATTR_INFO_VERSION_VALUE) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.info_version_value_len = len; + dst->info_version_value = malloc(len + 1); + memcpy(dst->info_version_value, mnl_attr_get_str(attr), len); + dst->info_version_value[len] = 0; + } + } + + return 0; +} + +void +devlink_dl_reload_stats_entry_free(struct devlink_dl_reload_stats_entry *obj) +{ +} + +int devlink_dl_reload_stats_entry_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_reload_stats_entry *dst = yarg->data; + const struct nlattr *attr; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_RELOAD_STATS_LIMIT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.reload_stats_limit = 1; + dst->reload_stats_limit = mnl_attr_get_u8(attr); + } else if (type == DEVLINK_ATTR_RELOAD_STATS_VALUE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.reload_stats_value = 1; + dst->reload_stats_value = mnl_attr_get_u32(attr); + } + } + + return 0; +} + +void devlink_dl_reload_act_stats_free(struct devlink_dl_reload_act_stats *obj) +{ + unsigned int i; + + for (i = 0; i < obj->n_reload_stats_entry; i++) + devlink_dl_reload_stats_entry_free(&obj->reload_stats_entry[i]); + free(obj->reload_stats_entry); +} + +int devlink_dl_reload_act_stats_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_reload_act_stats *dst = yarg->data; + unsigned int n_reload_stats_entry = 0; + const struct nlattr *attr; + struct ynl_parse_arg parg; + int i; + + parg.ys = yarg->ys; + + if (dst->reload_stats_entry) + return ynl_error_parse(yarg, "attribute already present (dl-reload-act-stats.reload-stats-entry)"); + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_RELOAD_STATS_ENTRY) { + n_reload_stats_entry++; + } + } + + if (n_reload_stats_entry) { + dst->reload_stats_entry = calloc(n_reload_stats_entry, sizeof(*dst->reload_stats_entry)); + dst->n_reload_stats_entry = n_reload_stats_entry; + i = 0; + parg.rsp_policy = &devlink_dl_reload_stats_entry_nest; + mnl_attr_for_each_nested(attr, nested) { + if (mnl_attr_get_type(attr) == DEVLINK_ATTR_RELOAD_STATS_ENTRY) { + parg.data = &dst->reload_stats_entry[i]; + if (devlink_dl_reload_stats_entry_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + + return 0; +} + +void devlink_dl_reload_act_info_free(struct devlink_dl_reload_act_info *obj) +{ + unsigned int i; + + for (i = 0; i < obj->n_reload_action_stats; i++) + devlink_dl_reload_act_stats_free(&obj->reload_action_stats[i]); + free(obj->reload_action_stats); +} + +int devlink_dl_reload_act_info_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_reload_act_info *dst = yarg->data; + unsigned int n_reload_action_stats = 0; + const struct nlattr *attr; + struct ynl_parse_arg parg; + int i; + + parg.ys = yarg->ys; + + if (dst->reload_action_stats) + return ynl_error_parse(yarg, "attribute already present (dl-reload-act-info.reload-action-stats)"); + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_RELOAD_ACTION) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.reload_action = 1; + dst->reload_action = mnl_attr_get_u8(attr); + } else if (type == DEVLINK_ATTR_RELOAD_ACTION_STATS) { + n_reload_action_stats++; + } + } + + if (n_reload_action_stats) { + dst->reload_action_stats = calloc(n_reload_action_stats, sizeof(*dst->reload_action_stats)); + dst->n_reload_action_stats = n_reload_action_stats; + i = 0; + parg.rsp_policy = &devlink_dl_reload_act_stats_nest; + mnl_attr_for_each_nested(attr, nested) { + if (mnl_attr_get_type(attr) == DEVLINK_ATTR_RELOAD_ACTION_STATS) { + parg.data = &dst->reload_action_stats[i]; + if (devlink_dl_reload_act_stats_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + + return 0; +} + +void devlink_dl_reload_stats_free(struct devlink_dl_reload_stats *obj) +{ + unsigned int i; + + for (i = 0; i < obj->n_reload_action_info; i++) + devlink_dl_reload_act_info_free(&obj->reload_action_info[i]); + free(obj->reload_action_info); +} + +int devlink_dl_reload_stats_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_reload_stats *dst = yarg->data; + unsigned int n_reload_action_info = 0; + const struct nlattr *attr; + struct ynl_parse_arg parg; + int i; + + parg.ys = yarg->ys; + + if (dst->reload_action_info) + return ynl_error_parse(yarg, "attribute already present (dl-reload-stats.reload-action-info)"); + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_RELOAD_ACTION_INFO) { + n_reload_action_info++; + } + } + + if (n_reload_action_info) { + dst->reload_action_info = calloc(n_reload_action_info, sizeof(*dst->reload_action_info)); + dst->n_reload_action_info = n_reload_action_info; + i = 0; + parg.rsp_policy = &devlink_dl_reload_act_info_nest; + mnl_attr_for_each_nested(attr, nested) { + if (mnl_attr_get_type(attr) == DEVLINK_ATTR_RELOAD_ACTION_INFO) { + parg.data = &dst->reload_action_info[i]; + if (devlink_dl_reload_act_info_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + + return 0; +} + +void devlink_dl_dev_stats_free(struct devlink_dl_dev_stats *obj) +{ + devlink_dl_reload_stats_free(&obj->reload_stats); + devlink_dl_reload_stats_free(&obj->remote_reload_stats); +} + +int devlink_dl_dev_stats_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_dev_stats *dst = yarg->data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + parg.ys = yarg->ys; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_RELOAD_STATS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.reload_stats = 1; + + parg.rsp_policy = &devlink_dl_reload_stats_nest; + parg.data = &dst->reload_stats; + if (devlink_dl_reload_stats_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == DEVLINK_ATTR_REMOTE_RELOAD_STATS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.remote_reload_stats = 1; + + parg.rsp_policy = &devlink_dl_reload_stats_nest; + parg.data = &dst->remote_reload_stats; + if (devlink_dl_reload_stats_parse(&parg, attr)) + return MNL_CB_ERROR; + } + } + + return 0; +} + +/* ============== DEVLINK_CMD_GET ============== */ +/* DEVLINK_CMD_GET - do */ +void devlink_get_req_free(struct devlink_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +void devlink_get_rsp_free(struct devlink_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + devlink_dl_dev_stats_free(&rsp->dev_stats); + free(rsp); +} + +int devlink_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct devlink_get_rsp *dst; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_RELOAD_FAILED) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.reload_failed = 1; + dst->reload_failed = mnl_attr_get_u8(attr); + } else if (type == DEVLINK_ATTR_RELOAD_ACTION) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.reload_action = 1; + dst->reload_action = mnl_attr_get_u8(attr); + } else if (type == DEVLINK_ATTR_DEV_STATS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dev_stats = 1; + + parg.rsp_policy = &devlink_dl_dev_stats_nest; + parg.data = &dst->dev_stats; + if (devlink_dl_dev_stats_parse(&parg, attr)) + return MNL_CB_ERROR; + } + } + + return MNL_CB_OK; +} + +struct devlink_get_rsp * +devlink_get(struct ynl_sock *ys, struct devlink_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_get_rsp_parse; + yrs.rsp_cmd = 3; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_GET - dump */ +void devlink_get_list_free(struct devlink_get_list *rsp) +{ + struct devlink_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + devlink_dl_dev_stats_free(&rsp->obj.dev_stats); + free(rsp); + } +} + +struct devlink_get_list *devlink_get_dump(struct ynl_sock *ys) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_get_list); + yds.cb = devlink_get_rsp_parse; + yds.rsp_cmd = 3; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_GET, 1); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_get_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_INFO_GET ============== */ +/* DEVLINK_CMD_INFO_GET - do */ +void devlink_info_get_req_free(struct devlink_info_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +void devlink_info_get_rsp_free(struct devlink_info_get_rsp *rsp) +{ + unsigned int i; + + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp->info_driver_name); + free(rsp->info_serial_number); + for (i = 0; i < rsp->n_info_version_fixed; i++) + devlink_dl_info_version_free(&rsp->info_version_fixed[i]); + free(rsp->info_version_fixed); + for (i = 0; i < rsp->n_info_version_running; i++) + devlink_dl_info_version_free(&rsp->info_version_running[i]); + free(rsp->info_version_running); + for (i = 0; i < rsp->n_info_version_stored; i++) + devlink_dl_info_version_free(&rsp->info_version_stored[i]); + free(rsp->info_version_stored); + free(rsp); +} + +int devlink_info_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + unsigned int n_info_version_running = 0; + unsigned int n_info_version_stored = 0; + unsigned int n_info_version_fixed = 0; + struct ynl_parse_arg *yarg = data; + struct devlink_info_get_rsp *dst; + const struct nlattr *attr; + struct ynl_parse_arg parg; + int i; + + dst = yarg->data; + parg.ys = yarg->ys; + + if (dst->info_version_fixed) + return ynl_error_parse(yarg, "attribute already present (devlink.info-version-fixed)"); + if (dst->info_version_running) + return ynl_error_parse(yarg, "attribute already present (devlink.info-version-running)"); + if (dst->info_version_stored) + return ynl_error_parse(yarg, "attribute already present (devlink.info-version-stored)"); + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_INFO_DRIVER_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.info_driver_name_len = len; + dst->info_driver_name = malloc(len + 1); + memcpy(dst->info_driver_name, mnl_attr_get_str(attr), len); + dst->info_driver_name[len] = 0; + } else if (type == DEVLINK_ATTR_INFO_SERIAL_NUMBER) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.info_serial_number_len = len; + dst->info_serial_number = malloc(len + 1); + memcpy(dst->info_serial_number, mnl_attr_get_str(attr), len); + dst->info_serial_number[len] = 0; + } else if (type == DEVLINK_ATTR_INFO_VERSION_FIXED) { + n_info_version_fixed++; + } else if (type == DEVLINK_ATTR_INFO_VERSION_RUNNING) { + n_info_version_running++; + } else if (type == DEVLINK_ATTR_INFO_VERSION_STORED) { + n_info_version_stored++; + } + } + + if (n_info_version_fixed) { + dst->info_version_fixed = calloc(n_info_version_fixed, sizeof(*dst->info_version_fixed)); + dst->n_info_version_fixed = n_info_version_fixed; + i = 0; + parg.rsp_policy = &devlink_dl_info_version_nest; + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + if (mnl_attr_get_type(attr) == DEVLINK_ATTR_INFO_VERSION_FIXED) { + parg.data = &dst->info_version_fixed[i]; + if (devlink_dl_info_version_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + if (n_info_version_running) { + dst->info_version_running = calloc(n_info_version_running, sizeof(*dst->info_version_running)); + dst->n_info_version_running = n_info_version_running; + i = 0; + parg.rsp_policy = &devlink_dl_info_version_nest; + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + if (mnl_attr_get_type(attr) == DEVLINK_ATTR_INFO_VERSION_RUNNING) { + parg.data = &dst->info_version_running[i]; + if (devlink_dl_info_version_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + if (n_info_version_stored) { + dst->info_version_stored = calloc(n_info_version_stored, sizeof(*dst->info_version_stored)); + dst->n_info_version_stored = n_info_version_stored; + i = 0; + parg.rsp_policy = &devlink_dl_info_version_nest; + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + if (mnl_attr_get_type(attr) == DEVLINK_ATTR_INFO_VERSION_STORED) { + parg.data = &dst->info_version_stored[i]; + if (devlink_dl_info_version_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + + return MNL_CB_OK; +} + +struct devlink_info_get_rsp * +devlink_info_get(struct ynl_sock *ys, struct devlink_info_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_info_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_INFO_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_info_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_INFO_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_info_get_rsp_free(rsp); + return NULL; +} + +const struct ynl_family ynl_devlink_family = { + .name = "devlink", +}; diff --git a/tools/net/ynl/generated/devlink-user.h b/tools/net/ynl/generated/devlink-user.h new file mode 100644 index 000000000000..a008b99b6e24 --- /dev/null +++ b/tools/net/ynl/generated/devlink-user.h @@ -0,0 +1,210 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/devlink.yaml */ +/* YNL-GEN user header */ + +#ifndef _LINUX_DEVLINK_GEN_H +#define _LINUX_DEVLINK_GEN_H + +#include <stdlib.h> +#include <string.h> +#include <linux/types.h> +#include <linux/devlink.h> + +struct ynl_sock; + +extern const struct ynl_family ynl_devlink_family; + +/* Enums */ +const char *devlink_op_str(int op); + +/* Common nested types */ +struct devlink_dl_info_version { + struct { + __u32 info_version_name_len; + __u32 info_version_value_len; + } _present; + + char *info_version_name; + char *info_version_value; +}; + +struct devlink_dl_reload_stats_entry { + struct { + __u32 reload_stats_limit:1; + __u32 reload_stats_value:1; + } _present; + + __u8 reload_stats_limit; + __u32 reload_stats_value; +}; + +struct devlink_dl_reload_act_stats { + unsigned int n_reload_stats_entry; + struct devlink_dl_reload_stats_entry *reload_stats_entry; +}; + +struct devlink_dl_reload_act_info { + struct { + __u32 reload_action:1; + } _present; + + __u8 reload_action; + unsigned int n_reload_action_stats; + struct devlink_dl_reload_act_stats *reload_action_stats; +}; + +struct devlink_dl_reload_stats { + unsigned int n_reload_action_info; + struct devlink_dl_reload_act_info *reload_action_info; +}; + +struct devlink_dl_dev_stats { + struct { + __u32 reload_stats:1; + __u32 remote_reload_stats:1; + } _present; + + struct devlink_dl_reload_stats reload_stats; + struct devlink_dl_reload_stats remote_reload_stats; +}; + +/* ============== DEVLINK_CMD_GET ============== */ +/* DEVLINK_CMD_GET - do */ +struct devlink_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_get_req *devlink_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_get_req)); +} +void devlink_get_req_free(struct devlink_get_req *req); + +static inline void +devlink_get_req_set_bus_name(struct devlink_get_req *req, const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_get_req_set_dev_name(struct devlink_get_req *req, const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 reload_failed:1; + __u32 reload_action:1; + __u32 dev_stats:1; + } _present; + + char *bus_name; + char *dev_name; + __u8 reload_failed; + __u8 reload_action; + struct devlink_dl_dev_stats dev_stats; +}; + +void devlink_get_rsp_free(struct devlink_get_rsp *rsp); + +/* + * Get devlink instances. + */ +struct devlink_get_rsp * +devlink_get(struct ynl_sock *ys, struct devlink_get_req *req); + +/* DEVLINK_CMD_GET - dump */ +struct devlink_get_list { + struct devlink_get_list *next; + struct devlink_get_rsp obj __attribute__ ((aligned (8))); +}; + +void devlink_get_list_free(struct devlink_get_list *rsp); + +struct devlink_get_list *devlink_get_dump(struct ynl_sock *ys); + +/* ============== DEVLINK_CMD_INFO_GET ============== */ +/* DEVLINK_CMD_INFO_GET - do */ +struct devlink_info_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_info_get_req *devlink_info_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_info_get_req)); +} +void devlink_info_get_req_free(struct devlink_info_get_req *req); + +static inline void +devlink_info_get_req_set_bus_name(struct devlink_info_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_info_get_req_set_dev_name(struct devlink_info_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_info_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 info_driver_name_len; + __u32 info_serial_number_len; + } _present; + + char *bus_name; + char *dev_name; + char *info_driver_name; + char *info_serial_number; + unsigned int n_info_version_fixed; + struct devlink_dl_info_version *info_version_fixed; + unsigned int n_info_version_running; + struct devlink_dl_info_version *info_version_running; + unsigned int n_info_version_stored; + struct devlink_dl_info_version *info_version_stored; +}; + +void devlink_info_get_rsp_free(struct devlink_info_get_rsp *rsp); + +/* + * Get device information, like driver name, hardware and firmware versions etc. + */ +struct devlink_info_get_rsp * +devlink_info_get(struct ynl_sock *ys, struct devlink_info_get_req *req); + +#endif /* _LINUX_DEVLINK_GEN_H */ diff --git a/tools/net/ynl/generated/fou-user.c b/tools/net/ynl/generated/fou-user.c new file mode 100644 index 000000000000..4271b5d43c58 --- /dev/null +++ b/tools/net/ynl/generated/fou-user.c @@ -0,0 +1,328 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/fou.yaml */ +/* YNL-GEN user source */ + +#include <stdlib.h> +#include <string.h> +#include "fou-user.h" +#include "ynl.h" +#include <linux/fou.h> + +#include <libmnl/libmnl.h> +#include <linux/genetlink.h> + +/* Enums */ +static const char * const fou_op_strmap[] = { + [FOU_CMD_ADD] = "add", + [FOU_CMD_DEL] = "del", + [FOU_CMD_GET] = "get", +}; + +const char *fou_op_str(int op) +{ + if (op < 0 || op >= (int)MNL_ARRAY_SIZE(fou_op_strmap)) + return NULL; + return fou_op_strmap[op]; +} + +static const char * const fou_encap_type_strmap[] = { + [0] = "unspec", + [1] = "direct", + [2] = "gue", +}; + +const char *fou_encap_type_str(int value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(fou_encap_type_strmap)) + return NULL; + return fou_encap_type_strmap[value]; +} + +/* Policies */ +struct ynl_policy_attr fou_policy[FOU_ATTR_MAX + 1] = { + [FOU_ATTR_UNSPEC] = { .name = "unspec", .type = YNL_PT_REJECT, }, + [FOU_ATTR_PORT] = { .name = "port", .type = YNL_PT_U16, }, + [FOU_ATTR_AF] = { .name = "af", .type = YNL_PT_U8, }, + [FOU_ATTR_IPPROTO] = { .name = "ipproto", .type = YNL_PT_U8, }, + [FOU_ATTR_TYPE] = { .name = "type", .type = YNL_PT_U8, }, + [FOU_ATTR_REMCSUM_NOPARTIAL] = { .name = "remcsum_nopartial", .type = YNL_PT_FLAG, }, + [FOU_ATTR_LOCAL_V4] = { .name = "local_v4", .type = YNL_PT_U32, }, + [FOU_ATTR_LOCAL_V6] = { .name = "local_v6", .type = YNL_PT_BINARY,}, + [FOU_ATTR_PEER_V4] = { .name = "peer_v4", .type = YNL_PT_U32, }, + [FOU_ATTR_PEER_V6] = { .name = "peer_v6", .type = YNL_PT_BINARY,}, + [FOU_ATTR_PEER_PORT] = { .name = "peer_port", .type = YNL_PT_U16, }, + [FOU_ATTR_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest fou_nest = { + .max_attr = FOU_ATTR_MAX, + .table = fou_policy, +}; + +/* Common nested types */ +/* ============== FOU_CMD_ADD ============== */ +/* FOU_CMD_ADD - do */ +void fou_add_req_free(struct fou_add_req *req) +{ + free(req->local_v6); + free(req->peer_v6); + free(req); +} + +int fou_add(struct ynl_sock *ys, struct fou_add_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, FOU_CMD_ADD, 1); + ys->req_policy = &fou_nest; + + if (req->_present.port) + mnl_attr_put_u16(nlh, FOU_ATTR_PORT, req->port); + if (req->_present.ipproto) + mnl_attr_put_u8(nlh, FOU_ATTR_IPPROTO, req->ipproto); + if (req->_present.type) + mnl_attr_put_u8(nlh, FOU_ATTR_TYPE, req->type); + if (req->_present.remcsum_nopartial) + mnl_attr_put(nlh, FOU_ATTR_REMCSUM_NOPARTIAL, 0, NULL); + if (req->_present.local_v4) + mnl_attr_put_u32(nlh, FOU_ATTR_LOCAL_V4, req->local_v4); + if (req->_present.peer_v4) + mnl_attr_put_u32(nlh, FOU_ATTR_PEER_V4, req->peer_v4); + if (req->_present.local_v6_len) + mnl_attr_put(nlh, FOU_ATTR_LOCAL_V6, req->_present.local_v6_len, req->local_v6); + if (req->_present.peer_v6_len) + mnl_attr_put(nlh, FOU_ATTR_PEER_V6, req->_present.peer_v6_len, req->peer_v6); + if (req->_present.peer_port) + mnl_attr_put_u16(nlh, FOU_ATTR_PEER_PORT, req->peer_port); + if (req->_present.ifindex) + mnl_attr_put_u32(nlh, FOU_ATTR_IFINDEX, req->ifindex); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== FOU_CMD_DEL ============== */ +/* FOU_CMD_DEL - do */ +void fou_del_req_free(struct fou_del_req *req) +{ + free(req->local_v6); + free(req->peer_v6); + free(req); +} + +int fou_del(struct ynl_sock *ys, struct fou_del_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, FOU_CMD_DEL, 1); + ys->req_policy = &fou_nest; + + if (req->_present.af) + mnl_attr_put_u8(nlh, FOU_ATTR_AF, req->af); + if (req->_present.ifindex) + mnl_attr_put_u32(nlh, FOU_ATTR_IFINDEX, req->ifindex); + if (req->_present.port) + mnl_attr_put_u16(nlh, FOU_ATTR_PORT, req->port); + if (req->_present.peer_port) + mnl_attr_put_u16(nlh, FOU_ATTR_PEER_PORT, req->peer_port); + if (req->_present.local_v4) + mnl_attr_put_u32(nlh, FOU_ATTR_LOCAL_V4, req->local_v4); + if (req->_present.peer_v4) + mnl_attr_put_u32(nlh, FOU_ATTR_PEER_V4, req->peer_v4); + if (req->_present.local_v6_len) + mnl_attr_put(nlh, FOU_ATTR_LOCAL_V6, req->_present.local_v6_len, req->local_v6); + if (req->_present.peer_v6_len) + mnl_attr_put(nlh, FOU_ATTR_PEER_V6, req->_present.peer_v6_len, req->peer_v6); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== FOU_CMD_GET ============== */ +/* FOU_CMD_GET - do */ +void fou_get_req_free(struct fou_get_req *req) +{ + free(req->local_v6); + free(req->peer_v6); + free(req); +} + +void fou_get_rsp_free(struct fou_get_rsp *rsp) +{ + free(rsp->local_v6); + free(rsp->peer_v6); + free(rsp); +} + +int fou_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct fou_get_rsp *dst; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == FOU_ATTR_PORT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.port = 1; + dst->port = mnl_attr_get_u16(attr); + } else if (type == FOU_ATTR_IPPROTO) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.ipproto = 1; + dst->ipproto = mnl_attr_get_u8(attr); + } else if (type == FOU_ATTR_TYPE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.type = 1; + dst->type = mnl_attr_get_u8(attr); + } else if (type == FOU_ATTR_REMCSUM_NOPARTIAL) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.remcsum_nopartial = 1; + } else if (type == FOU_ATTR_LOCAL_V4) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.local_v4 = 1; + dst->local_v4 = mnl_attr_get_u32(attr); + } else if (type == FOU_ATTR_PEER_V4) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.peer_v4 = 1; + dst->peer_v4 = mnl_attr_get_u32(attr); + } else if (type == FOU_ATTR_LOCAL_V6) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = mnl_attr_get_payload_len(attr); + dst->_present.local_v6_len = len; + dst->local_v6 = malloc(len); + memcpy(dst->local_v6, mnl_attr_get_payload(attr), len); + } else if (type == FOU_ATTR_PEER_V6) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = mnl_attr_get_payload_len(attr); + dst->_present.peer_v6_len = len; + dst->peer_v6 = malloc(len); + memcpy(dst->peer_v6, mnl_attr_get_payload(attr), len); + } else if (type == FOU_ATTR_PEER_PORT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.peer_port = 1; + dst->peer_port = mnl_attr_get_u16(attr); + } else if (type == FOU_ATTR_IFINDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.ifindex = 1; + dst->ifindex = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +struct fou_get_rsp *fou_get(struct ynl_sock *ys, struct fou_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct fou_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, FOU_CMD_GET, 1); + ys->req_policy = &fou_nest; + yrs.yarg.rsp_policy = &fou_nest; + + if (req->_present.af) + mnl_attr_put_u8(nlh, FOU_ATTR_AF, req->af); + if (req->_present.ifindex) + mnl_attr_put_u32(nlh, FOU_ATTR_IFINDEX, req->ifindex); + if (req->_present.port) + mnl_attr_put_u16(nlh, FOU_ATTR_PORT, req->port); + if (req->_present.peer_port) + mnl_attr_put_u16(nlh, FOU_ATTR_PEER_PORT, req->peer_port); + if (req->_present.local_v4) + mnl_attr_put_u32(nlh, FOU_ATTR_LOCAL_V4, req->local_v4); + if (req->_present.peer_v4) + mnl_attr_put_u32(nlh, FOU_ATTR_PEER_V4, req->peer_v4); + if (req->_present.local_v6_len) + mnl_attr_put(nlh, FOU_ATTR_LOCAL_V6, req->_present.local_v6_len, req->local_v6); + if (req->_present.peer_v6_len) + mnl_attr_put(nlh, FOU_ATTR_PEER_V6, req->_present.peer_v6_len, req->peer_v6); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = fou_get_rsp_parse; + yrs.rsp_cmd = FOU_CMD_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + fou_get_rsp_free(rsp); + return NULL; +} + +/* FOU_CMD_GET - dump */ +void fou_get_list_free(struct fou_get_list *rsp) +{ + struct fou_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.local_v6); + free(rsp->obj.peer_v6); + free(rsp); + } +} + +struct fou_get_list *fou_get_dump(struct ynl_sock *ys) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct fou_get_list); + yds.cb = fou_get_rsp_parse; + yds.rsp_cmd = FOU_CMD_GET; + yds.rsp_policy = &fou_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, FOU_CMD_GET, 1); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + fou_get_list_free(yds.first); + return NULL; +} + +const struct ynl_family ynl_fou_family = { + .name = "fou", +}; diff --git a/tools/net/ynl/generated/fou-user.h b/tools/net/ynl/generated/fou-user.h new file mode 100644 index 000000000000..d8ab50579cd1 --- /dev/null +++ b/tools/net/ynl/generated/fou-user.h @@ -0,0 +1,337 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/fou.yaml */ +/* YNL-GEN user header */ + +#ifndef _LINUX_FOU_GEN_H +#define _LINUX_FOU_GEN_H + +#include <stdlib.h> +#include <string.h> +#include <linux/types.h> +#include <linux/fou.h> + +struct ynl_sock; + +extern const struct ynl_family ynl_fou_family; + +/* Enums */ +const char *fou_op_str(int op); +const char *fou_encap_type_str(int value); + +/* Common nested types */ +/* ============== FOU_CMD_ADD ============== */ +/* FOU_CMD_ADD - do */ +struct fou_add_req { + struct { + __u32 port:1; + __u32 ipproto:1; + __u32 type:1; + __u32 remcsum_nopartial:1; + __u32 local_v4:1; + __u32 peer_v4:1; + __u32 local_v6_len; + __u32 peer_v6_len; + __u32 peer_port:1; + __u32 ifindex:1; + } _present; + + __u16 port /* big-endian */; + __u8 ipproto; + __u8 type; + __u32 local_v4; + __u32 peer_v4; + void *local_v6; + void *peer_v6; + __u16 peer_port /* big-endian */; + __s32 ifindex; +}; + +static inline struct fou_add_req *fou_add_req_alloc(void) +{ + return calloc(1, sizeof(struct fou_add_req)); +} +void fou_add_req_free(struct fou_add_req *req); + +static inline void +fou_add_req_set_port(struct fou_add_req *req, __u16 port /* big-endian */) +{ + req->_present.port = 1; + req->port = port; +} +static inline void +fou_add_req_set_ipproto(struct fou_add_req *req, __u8 ipproto) +{ + req->_present.ipproto = 1; + req->ipproto = ipproto; +} +static inline void fou_add_req_set_type(struct fou_add_req *req, __u8 type) +{ + req->_present.type = 1; + req->type = type; +} +static inline void fou_add_req_set_remcsum_nopartial(struct fou_add_req *req) +{ + req->_present.remcsum_nopartial = 1; +} +static inline void +fou_add_req_set_local_v4(struct fou_add_req *req, __u32 local_v4) +{ + req->_present.local_v4 = 1; + req->local_v4 = local_v4; +} +static inline void +fou_add_req_set_peer_v4(struct fou_add_req *req, __u32 peer_v4) +{ + req->_present.peer_v4 = 1; + req->peer_v4 = peer_v4; +} +static inline void +fou_add_req_set_local_v6(struct fou_add_req *req, const void *local_v6, + size_t len) +{ + free(req->local_v6); + req->local_v6 = malloc(req->_present.local_v6_len); + memcpy(req->local_v6, local_v6, req->_present.local_v6_len); +} +static inline void +fou_add_req_set_peer_v6(struct fou_add_req *req, const void *peer_v6, + size_t len) +{ + free(req->peer_v6); + req->peer_v6 = malloc(req->_present.peer_v6_len); + memcpy(req->peer_v6, peer_v6, req->_present.peer_v6_len); +} +static inline void +fou_add_req_set_peer_port(struct fou_add_req *req, + __u16 peer_port /* big-endian */) +{ + req->_present.peer_port = 1; + req->peer_port = peer_port; +} +static inline void +fou_add_req_set_ifindex(struct fou_add_req *req, __s32 ifindex) +{ + req->_present.ifindex = 1; + req->ifindex = ifindex; +} + +/* + * Add port. + */ +int fou_add(struct ynl_sock *ys, struct fou_add_req *req); + +/* ============== FOU_CMD_DEL ============== */ +/* FOU_CMD_DEL - do */ +struct fou_del_req { + struct { + __u32 af:1; + __u32 ifindex:1; + __u32 port:1; + __u32 peer_port:1; + __u32 local_v4:1; + __u32 peer_v4:1; + __u32 local_v6_len; + __u32 peer_v6_len; + } _present; + + __u8 af; + __s32 ifindex; + __u16 port /* big-endian */; + __u16 peer_port /* big-endian */; + __u32 local_v4; + __u32 peer_v4; + void *local_v6; + void *peer_v6; +}; + +static inline struct fou_del_req *fou_del_req_alloc(void) +{ + return calloc(1, sizeof(struct fou_del_req)); +} +void fou_del_req_free(struct fou_del_req *req); + +static inline void fou_del_req_set_af(struct fou_del_req *req, __u8 af) +{ + req->_present.af = 1; + req->af = af; +} +static inline void +fou_del_req_set_ifindex(struct fou_del_req *req, __s32 ifindex) +{ + req->_present.ifindex = 1; + req->ifindex = ifindex; +} +static inline void +fou_del_req_set_port(struct fou_del_req *req, __u16 port /* big-endian */) +{ + req->_present.port = 1; + req->port = port; +} +static inline void +fou_del_req_set_peer_port(struct fou_del_req *req, + __u16 peer_port /* big-endian */) +{ + req->_present.peer_port = 1; + req->peer_port = peer_port; +} +static inline void +fou_del_req_set_local_v4(struct fou_del_req *req, __u32 local_v4) +{ + req->_present.local_v4 = 1; + req->local_v4 = local_v4; +} +static inline void +fou_del_req_set_peer_v4(struct fou_del_req *req, __u32 peer_v4) +{ + req->_present.peer_v4 = 1; + req->peer_v4 = peer_v4; +} +static inline void +fou_del_req_set_local_v6(struct fou_del_req *req, const void *local_v6, + size_t len) +{ + free(req->local_v6); + req->local_v6 = malloc(req->_present.local_v6_len); + memcpy(req->local_v6, local_v6, req->_present.local_v6_len); +} +static inline void +fou_del_req_set_peer_v6(struct fou_del_req *req, const void *peer_v6, + size_t len) +{ + free(req->peer_v6); + req->peer_v6 = malloc(req->_present.peer_v6_len); + memcpy(req->peer_v6, peer_v6, req->_present.peer_v6_len); +} + +/* + * Delete port. + */ +int fou_del(struct ynl_sock *ys, struct fou_del_req *req); + +/* ============== FOU_CMD_GET ============== */ +/* FOU_CMD_GET - do */ +struct fou_get_req { + struct { + __u32 af:1; + __u32 ifindex:1; + __u32 port:1; + __u32 peer_port:1; + __u32 local_v4:1; + __u32 peer_v4:1; + __u32 local_v6_len; + __u32 peer_v6_len; + } _present; + + __u8 af; + __s32 ifindex; + __u16 port /* big-endian */; + __u16 peer_port /* big-endian */; + __u32 local_v4; + __u32 peer_v4; + void *local_v6; + void *peer_v6; +}; + +static inline struct fou_get_req *fou_get_req_alloc(void) +{ + return calloc(1, sizeof(struct fou_get_req)); +} +void fou_get_req_free(struct fou_get_req *req); + +static inline void fou_get_req_set_af(struct fou_get_req *req, __u8 af) +{ + req->_present.af = 1; + req->af = af; +} +static inline void +fou_get_req_set_ifindex(struct fou_get_req *req, __s32 ifindex) +{ + req->_present.ifindex = 1; + req->ifindex = ifindex; +} +static inline void +fou_get_req_set_port(struct fou_get_req *req, __u16 port /* big-endian */) +{ + req->_present.port = 1; + req->port = port; +} +static inline void +fou_get_req_set_peer_port(struct fou_get_req *req, + __u16 peer_port /* big-endian */) +{ + req->_present.peer_port = 1; + req->peer_port = peer_port; +} +static inline void +fou_get_req_set_local_v4(struct fou_get_req *req, __u32 local_v4) +{ + req->_present.local_v4 = 1; + req->local_v4 = local_v4; +} +static inline void +fou_get_req_set_peer_v4(struct fou_get_req *req, __u32 peer_v4) +{ + req->_present.peer_v4 = 1; + req->peer_v4 = peer_v4; +} +static inline void +fou_get_req_set_local_v6(struct fou_get_req *req, const void *local_v6, + size_t len) +{ + free(req->local_v6); + req->local_v6 = malloc(req->_present.local_v6_len); + memcpy(req->local_v6, local_v6, req->_present.local_v6_len); +} +static inline void +fou_get_req_set_peer_v6(struct fou_get_req *req, const void *peer_v6, + size_t len) +{ + free(req->peer_v6); + req->peer_v6 = malloc(req->_present.peer_v6_len); + memcpy(req->peer_v6, peer_v6, req->_present.peer_v6_len); +} + +struct fou_get_rsp { + struct { + __u32 port:1; + __u32 ipproto:1; + __u32 type:1; + __u32 remcsum_nopartial:1; + __u32 local_v4:1; + __u32 peer_v4:1; + __u32 local_v6_len; + __u32 peer_v6_len; + __u32 peer_port:1; + __u32 ifindex:1; + } _present; + + __u16 port /* big-endian */; + __u8 ipproto; + __u8 type; + __u32 local_v4; + __u32 peer_v4; + void *local_v6; + void *peer_v6; + __u16 peer_port /* big-endian */; + __s32 ifindex; +}; + +void fou_get_rsp_free(struct fou_get_rsp *rsp); + +/* + * Get tunnel info. + */ +struct fou_get_rsp *fou_get(struct ynl_sock *ys, struct fou_get_req *req); + +/* FOU_CMD_GET - dump */ +struct fou_get_list { + struct fou_get_list *next; + struct fou_get_rsp obj __attribute__ ((aligned (8))); +}; + +void fou_get_list_free(struct fou_get_list *rsp); + +struct fou_get_list *fou_get_dump(struct ynl_sock *ys); + +#endif /* _LINUX_FOU_GEN_H */ diff --git a/tools/net/ynl/generated/handshake-user.c b/tools/net/ynl/generated/handshake-user.c new file mode 100644 index 000000000000..7c67765daf90 --- /dev/null +++ b/tools/net/ynl/generated/handshake-user.c @@ -0,0 +1,331 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/handshake.yaml */ +/* YNL-GEN user source */ + +#include <stdlib.h> +#include <string.h> +#include "handshake-user.h" +#include "ynl.h" +#include <linux/handshake.h> + +#include <libmnl/libmnl.h> +#include <linux/genetlink.h> + +/* Enums */ +static const char * const handshake_op_strmap[] = { + [HANDSHAKE_CMD_READY] = "ready", + [HANDSHAKE_CMD_ACCEPT] = "accept", + [HANDSHAKE_CMD_DONE] = "done", +}; + +const char *handshake_op_str(int op) +{ + if (op < 0 || op >= (int)MNL_ARRAY_SIZE(handshake_op_strmap)) + return NULL; + return handshake_op_strmap[op]; +} + +static const char * const handshake_handler_class_strmap[] = { + [0] = "none", + [1] = "tlshd", + [2] = "max", +}; + +const char *handshake_handler_class_str(enum handshake_handler_class value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(handshake_handler_class_strmap)) + return NULL; + return handshake_handler_class_strmap[value]; +} + +static const char * const handshake_msg_type_strmap[] = { + [0] = "unspec", + [1] = "clienthello", + [2] = "serverhello", +}; + +const char *handshake_msg_type_str(enum handshake_msg_type value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(handshake_msg_type_strmap)) + return NULL; + return handshake_msg_type_strmap[value]; +} + +static const char * const handshake_auth_strmap[] = { + [0] = "unspec", + [1] = "unauth", + [2] = "psk", + [3] = "x509", +}; + +const char *handshake_auth_str(enum handshake_auth value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(handshake_auth_strmap)) + return NULL; + return handshake_auth_strmap[value]; +} + +/* Policies */ +struct ynl_policy_attr handshake_x509_policy[HANDSHAKE_A_X509_MAX + 1] = { + [HANDSHAKE_A_X509_CERT] = { .name = "cert", .type = YNL_PT_U32, }, + [HANDSHAKE_A_X509_PRIVKEY] = { .name = "privkey", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest handshake_x509_nest = { + .max_attr = HANDSHAKE_A_X509_MAX, + .table = handshake_x509_policy, +}; + +struct ynl_policy_attr handshake_accept_policy[HANDSHAKE_A_ACCEPT_MAX + 1] = { + [HANDSHAKE_A_ACCEPT_SOCKFD] = { .name = "sockfd", .type = YNL_PT_U32, }, + [HANDSHAKE_A_ACCEPT_HANDLER_CLASS] = { .name = "handler-class", .type = YNL_PT_U32, }, + [HANDSHAKE_A_ACCEPT_MESSAGE_TYPE] = { .name = "message-type", .type = YNL_PT_U32, }, + [HANDSHAKE_A_ACCEPT_TIMEOUT] = { .name = "timeout", .type = YNL_PT_U32, }, + [HANDSHAKE_A_ACCEPT_AUTH_MODE] = { .name = "auth-mode", .type = YNL_PT_U32, }, + [HANDSHAKE_A_ACCEPT_PEER_IDENTITY] = { .name = "peer-identity", .type = YNL_PT_U32, }, + [HANDSHAKE_A_ACCEPT_CERTIFICATE] = { .name = "certificate", .type = YNL_PT_NEST, .nest = &handshake_x509_nest, }, + [HANDSHAKE_A_ACCEPT_PEERNAME] = { .name = "peername", .type = YNL_PT_NUL_STR, }, +}; + +struct ynl_policy_nest handshake_accept_nest = { + .max_attr = HANDSHAKE_A_ACCEPT_MAX, + .table = handshake_accept_policy, +}; + +struct ynl_policy_attr handshake_done_policy[HANDSHAKE_A_DONE_MAX + 1] = { + [HANDSHAKE_A_DONE_STATUS] = { .name = "status", .type = YNL_PT_U32, }, + [HANDSHAKE_A_DONE_SOCKFD] = { .name = "sockfd", .type = YNL_PT_U32, }, + [HANDSHAKE_A_DONE_REMOTE_AUTH] = { .name = "remote-auth", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest handshake_done_nest = { + .max_attr = HANDSHAKE_A_DONE_MAX, + .table = handshake_done_policy, +}; + +/* Common nested types */ +void handshake_x509_free(struct handshake_x509 *obj) +{ +} + +int handshake_x509_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct handshake_x509 *dst = yarg->data; + const struct nlattr *attr; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == HANDSHAKE_A_X509_CERT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.cert = 1; + dst->cert = mnl_attr_get_u32(attr); + } else if (type == HANDSHAKE_A_X509_PRIVKEY) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.privkey = 1; + dst->privkey = mnl_attr_get_u32(attr); + } + } + + return 0; +} + +/* ============== HANDSHAKE_CMD_ACCEPT ============== */ +/* HANDSHAKE_CMD_ACCEPT - do */ +void handshake_accept_req_free(struct handshake_accept_req *req) +{ + free(req); +} + +void handshake_accept_rsp_free(struct handshake_accept_rsp *rsp) +{ + unsigned int i; + + free(rsp->peer_identity); + for (i = 0; i < rsp->n_certificate; i++) + handshake_x509_free(&rsp->certificate[i]); + free(rsp->certificate); + free(rsp->peername); + free(rsp); +} + +int handshake_accept_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct handshake_accept_rsp *dst; + unsigned int n_peer_identity = 0; + unsigned int n_certificate = 0; + const struct nlattr *attr; + struct ynl_parse_arg parg; + int i; + + dst = yarg->data; + parg.ys = yarg->ys; + + if (dst->certificate) + return ynl_error_parse(yarg, "attribute already present (accept.certificate)"); + if (dst->peer_identity) + return ynl_error_parse(yarg, "attribute already present (accept.peer-identity)"); + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == HANDSHAKE_A_ACCEPT_SOCKFD) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.sockfd = 1; + dst->sockfd = mnl_attr_get_u32(attr); + } else if (type == HANDSHAKE_A_ACCEPT_MESSAGE_TYPE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.message_type = 1; + dst->message_type = mnl_attr_get_u32(attr); + } else if (type == HANDSHAKE_A_ACCEPT_TIMEOUT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.timeout = 1; + dst->timeout = mnl_attr_get_u32(attr); + } else if (type == HANDSHAKE_A_ACCEPT_AUTH_MODE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.auth_mode = 1; + dst->auth_mode = mnl_attr_get_u32(attr); + } else if (type == HANDSHAKE_A_ACCEPT_PEER_IDENTITY) { + n_peer_identity++; + } else if (type == HANDSHAKE_A_ACCEPT_CERTIFICATE) { + n_certificate++; + } else if (type == HANDSHAKE_A_ACCEPT_PEERNAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.peername_len = len; + dst->peername = malloc(len + 1); + memcpy(dst->peername, mnl_attr_get_str(attr), len); + dst->peername[len] = 0; + } + } + + if (n_certificate) { + dst->certificate = calloc(n_certificate, sizeof(*dst->certificate)); + dst->n_certificate = n_certificate; + i = 0; + parg.rsp_policy = &handshake_x509_nest; + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + if (mnl_attr_get_type(attr) == HANDSHAKE_A_ACCEPT_CERTIFICATE) { + parg.data = &dst->certificate[i]; + if (handshake_x509_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + if (n_peer_identity) { + dst->peer_identity = calloc(n_peer_identity, sizeof(*dst->peer_identity)); + dst->n_peer_identity = n_peer_identity; + i = 0; + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + if (mnl_attr_get_type(attr) == HANDSHAKE_A_ACCEPT_PEER_IDENTITY) { + dst->peer_identity[i] = mnl_attr_get_u32(attr); + i++; + } + } + } + + return MNL_CB_OK; +} + +struct handshake_accept_rsp * +handshake_accept(struct ynl_sock *ys, struct handshake_accept_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct handshake_accept_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, HANDSHAKE_CMD_ACCEPT, 1); + ys->req_policy = &handshake_accept_nest; + yrs.yarg.rsp_policy = &handshake_accept_nest; + + if (req->_present.handler_class) + mnl_attr_put_u32(nlh, HANDSHAKE_A_ACCEPT_HANDLER_CLASS, req->handler_class); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = handshake_accept_rsp_parse; + yrs.rsp_cmd = HANDSHAKE_CMD_ACCEPT; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + handshake_accept_rsp_free(rsp); + return NULL; +} + +/* HANDSHAKE_CMD_ACCEPT - notify */ +void handshake_accept_ntf_free(struct handshake_accept_ntf *rsp) +{ + unsigned int i; + + free(rsp->obj.peer_identity); + for (i = 0; i < rsp->obj.n_certificate; i++) + handshake_x509_free(&rsp->obj.certificate[i]); + free(rsp->obj.certificate); + free(rsp->obj.peername); + free(rsp); +} + +/* ============== HANDSHAKE_CMD_DONE ============== */ +/* HANDSHAKE_CMD_DONE - do */ +void handshake_done_req_free(struct handshake_done_req *req) +{ + free(req->remote_auth); + free(req); +} + +int handshake_done(struct ynl_sock *ys, struct handshake_done_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, HANDSHAKE_CMD_DONE, 1); + ys->req_policy = &handshake_done_nest; + + if (req->_present.status) + mnl_attr_put_u32(nlh, HANDSHAKE_A_DONE_STATUS, req->status); + if (req->_present.sockfd) + mnl_attr_put_u32(nlh, HANDSHAKE_A_DONE_SOCKFD, req->sockfd); + for (unsigned int i = 0; i < req->n_remote_auth; i++) + mnl_attr_put_u32(nlh, HANDSHAKE_A_DONE_REMOTE_AUTH, req->remote_auth[i]); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +static const struct ynl_ntf_info handshake_ntf_info[] = { + [HANDSHAKE_CMD_READY] = { + .alloc_sz = sizeof(struct handshake_accept_ntf), + .cb = handshake_accept_rsp_parse, + .policy = &handshake_accept_nest, + .free = (void *)handshake_accept_ntf_free, + }, +}; + +const struct ynl_family ynl_handshake_family = { + .name = "handshake", + .ntf_info = handshake_ntf_info, + .ntf_info_size = MNL_ARRAY_SIZE(handshake_ntf_info), +}; diff --git a/tools/net/ynl/generated/handshake-user.h b/tools/net/ynl/generated/handshake-user.h new file mode 100644 index 000000000000..47646bb91cea --- /dev/null +++ b/tools/net/ynl/generated/handshake-user.h @@ -0,0 +1,145 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/handshake.yaml */ +/* YNL-GEN user header */ + +#ifndef _LINUX_HANDSHAKE_GEN_H +#define _LINUX_HANDSHAKE_GEN_H + +#include <stdlib.h> +#include <string.h> +#include <linux/types.h> +#include <linux/handshake.h> + +struct ynl_sock; + +extern const struct ynl_family ynl_handshake_family; + +/* Enums */ +const char *handshake_op_str(int op); +const char *handshake_handler_class_str(enum handshake_handler_class value); +const char *handshake_msg_type_str(enum handshake_msg_type value); +const char *handshake_auth_str(enum handshake_auth value); + +/* Common nested types */ +struct handshake_x509 { + struct { + __u32 cert:1; + __u32 privkey:1; + } _present; + + __u32 cert; + __u32 privkey; +}; + +/* ============== HANDSHAKE_CMD_ACCEPT ============== */ +/* HANDSHAKE_CMD_ACCEPT - do */ +struct handshake_accept_req { + struct { + __u32 handler_class:1; + } _present; + + enum handshake_handler_class handler_class; +}; + +static inline struct handshake_accept_req *handshake_accept_req_alloc(void) +{ + return calloc(1, sizeof(struct handshake_accept_req)); +} +void handshake_accept_req_free(struct handshake_accept_req *req); + +static inline void +handshake_accept_req_set_handler_class(struct handshake_accept_req *req, + enum handshake_handler_class handler_class) +{ + req->_present.handler_class = 1; + req->handler_class = handler_class; +} + +struct handshake_accept_rsp { + struct { + __u32 sockfd:1; + __u32 message_type:1; + __u32 timeout:1; + __u32 auth_mode:1; + __u32 peername_len; + } _present; + + __u32 sockfd; + enum handshake_msg_type message_type; + __u32 timeout; + enum handshake_auth auth_mode; + unsigned int n_peer_identity; + __u32 *peer_identity; + unsigned int n_certificate; + struct handshake_x509 *certificate; + char *peername; +}; + +void handshake_accept_rsp_free(struct handshake_accept_rsp *rsp); + +/* + * Handler retrieves next queued handshake request + */ +struct handshake_accept_rsp * +handshake_accept(struct ynl_sock *ys, struct handshake_accept_req *req); + +/* HANDSHAKE_CMD_ACCEPT - notify */ +struct handshake_accept_ntf { + __u16 family; + __u8 cmd; + struct ynl_ntf_base_type *next; + void (*free)(struct handshake_accept_ntf *ntf); + struct handshake_accept_rsp obj __attribute__ ((aligned (8))); +}; + +void handshake_accept_ntf_free(struct handshake_accept_ntf *rsp); + +/* ============== HANDSHAKE_CMD_DONE ============== */ +/* HANDSHAKE_CMD_DONE - do */ +struct handshake_done_req { + struct { + __u32 status:1; + __u32 sockfd:1; + } _present; + + __u32 status; + __u32 sockfd; + unsigned int n_remote_auth; + __u32 *remote_auth; +}; + +static inline struct handshake_done_req *handshake_done_req_alloc(void) +{ + return calloc(1, sizeof(struct handshake_done_req)); +} +void handshake_done_req_free(struct handshake_done_req *req); + +static inline void +handshake_done_req_set_status(struct handshake_done_req *req, __u32 status) +{ + req->_present.status = 1; + req->status = status; +} +static inline void +handshake_done_req_set_sockfd(struct handshake_done_req *req, __u32 sockfd) +{ + req->_present.sockfd = 1; + req->sockfd = sockfd; +} +static inline void +__handshake_done_req_set_remote_auth(struct handshake_done_req *req, + __u32 *remote_auth, + unsigned int n_remote_auth) +{ + free(req->remote_auth); + req->remote_auth = remote_auth; + req->n_remote_auth = n_remote_auth; +} + +/* + * Handler reports handshake completion + */ +int handshake_done(struct ynl_sock *ys, struct handshake_done_req *req); + +#endif /* _LINUX_HANDSHAKE_GEN_H */ diff --git a/tools/net/ynl/generated/netdev-user.c b/tools/net/ynl/generated/netdev-user.c new file mode 100644 index 000000000000..4eb8aefef0cd --- /dev/null +++ b/tools/net/ynl/generated/netdev-user.c @@ -0,0 +1,200 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/netdev.yaml */ +/* YNL-GEN user source */ + +#include <stdlib.h> +#include <string.h> +#include "netdev-user.h" +#include "ynl.h" +#include <linux/netdev.h> + +#include <libmnl/libmnl.h> +#include <linux/genetlink.h> + +/* Enums */ +static const char * const netdev_op_strmap[] = { + [NETDEV_CMD_DEV_GET] = "dev-get", + [NETDEV_CMD_DEV_ADD_NTF] = "dev-add-ntf", + [NETDEV_CMD_DEV_DEL_NTF] = "dev-del-ntf", + [NETDEV_CMD_DEV_CHANGE_NTF] = "dev-change-ntf", +}; + +const char *netdev_op_str(int op) +{ + if (op < 0 || op >= (int)MNL_ARRAY_SIZE(netdev_op_strmap)) + return NULL; + return netdev_op_strmap[op]; +} + +static const char * const netdev_xdp_act_strmap[] = { + [0] = "basic", + [1] = "redirect", + [2] = "ndo-xmit", + [3] = "xsk-zerocopy", + [4] = "hw-offload", + [5] = "rx-sg", + [6] = "ndo-xmit-sg", +}; + +const char *netdev_xdp_act_str(enum netdev_xdp_act value) +{ + value = ffs(value) - 1; + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(netdev_xdp_act_strmap)) + return NULL; + return netdev_xdp_act_strmap[value]; +} + +/* Policies */ +struct ynl_policy_attr netdev_dev_policy[NETDEV_A_DEV_MAX + 1] = { + [NETDEV_A_DEV_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, }, + [NETDEV_A_DEV_PAD] = { .name = "pad", .type = YNL_PT_IGNORE, }, + [NETDEV_A_DEV_XDP_FEATURES] = { .name = "xdp-features", .type = YNL_PT_U64, }, +}; + +struct ynl_policy_nest netdev_dev_nest = { + .max_attr = NETDEV_A_DEV_MAX, + .table = netdev_dev_policy, +}; + +/* Common nested types */ +/* ============== NETDEV_CMD_DEV_GET ============== */ +/* NETDEV_CMD_DEV_GET - do */ +void netdev_dev_get_req_free(struct netdev_dev_get_req *req) +{ + free(req); +} + +void netdev_dev_get_rsp_free(struct netdev_dev_get_rsp *rsp) +{ + free(rsp); +} + +int netdev_dev_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct netdev_dev_get_rsp *dst; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == NETDEV_A_DEV_IFINDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.ifindex = 1; + dst->ifindex = mnl_attr_get_u32(attr); + } else if (type == NETDEV_A_DEV_XDP_FEATURES) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.xdp_features = 1; + dst->xdp_features = mnl_attr_get_u64(attr); + } + } + + return MNL_CB_OK; +} + +struct netdev_dev_get_rsp * +netdev_dev_get(struct ynl_sock *ys, struct netdev_dev_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct netdev_dev_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, NETDEV_CMD_DEV_GET, 1); + ys->req_policy = &netdev_dev_nest; + yrs.yarg.rsp_policy = &netdev_dev_nest; + + if (req->_present.ifindex) + mnl_attr_put_u32(nlh, NETDEV_A_DEV_IFINDEX, req->ifindex); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = netdev_dev_get_rsp_parse; + yrs.rsp_cmd = NETDEV_CMD_DEV_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + netdev_dev_get_rsp_free(rsp); + return NULL; +} + +/* NETDEV_CMD_DEV_GET - dump */ +void netdev_dev_get_list_free(struct netdev_dev_get_list *rsp) +{ + struct netdev_dev_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp); + } +} + +struct netdev_dev_get_list *netdev_dev_get_dump(struct ynl_sock *ys) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct netdev_dev_get_list); + yds.cb = netdev_dev_get_rsp_parse; + yds.rsp_cmd = NETDEV_CMD_DEV_GET; + yds.rsp_policy = &netdev_dev_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, NETDEV_CMD_DEV_GET, 1); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + netdev_dev_get_list_free(yds.first); + return NULL; +} + +/* NETDEV_CMD_DEV_GET - notify */ +void netdev_dev_get_ntf_free(struct netdev_dev_get_ntf *rsp) +{ + free(rsp); +} + +static const struct ynl_ntf_info netdev_ntf_info[] = { + [NETDEV_CMD_DEV_ADD_NTF] = { + .alloc_sz = sizeof(struct netdev_dev_get_ntf), + .cb = netdev_dev_get_rsp_parse, + .policy = &netdev_dev_nest, + .free = (void *)netdev_dev_get_ntf_free, + }, + [NETDEV_CMD_DEV_DEL_NTF] = { + .alloc_sz = sizeof(struct netdev_dev_get_ntf), + .cb = netdev_dev_get_rsp_parse, + .policy = &netdev_dev_nest, + .free = (void *)netdev_dev_get_ntf_free, + }, + [NETDEV_CMD_DEV_CHANGE_NTF] = { + .alloc_sz = sizeof(struct netdev_dev_get_ntf), + .cb = netdev_dev_get_rsp_parse, + .policy = &netdev_dev_nest, + .free = (void *)netdev_dev_get_ntf_free, + }, +}; + +const struct ynl_family ynl_netdev_family = { + .name = "netdev", + .ntf_info = netdev_ntf_info, + .ntf_info_size = MNL_ARRAY_SIZE(netdev_ntf_info), +}; diff --git a/tools/net/ynl/generated/netdev-user.h b/tools/net/ynl/generated/netdev-user.h new file mode 100644 index 000000000000..5554dc69bb9c --- /dev/null +++ b/tools/net/ynl/generated/netdev-user.h @@ -0,0 +1,85 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/netdev.yaml */ +/* YNL-GEN user header */ + +#ifndef _LINUX_NETDEV_GEN_H +#define _LINUX_NETDEV_GEN_H + +#include <stdlib.h> +#include <string.h> +#include <linux/types.h> +#include <linux/netdev.h> + +struct ynl_sock; + +extern const struct ynl_family ynl_netdev_family; + +/* Enums */ +const char *netdev_op_str(int op); +const char *netdev_xdp_act_str(enum netdev_xdp_act value); + +/* Common nested types */ +/* ============== NETDEV_CMD_DEV_GET ============== */ +/* NETDEV_CMD_DEV_GET - do */ +struct netdev_dev_get_req { + struct { + __u32 ifindex:1; + } _present; + + __u32 ifindex; +}; + +static inline struct netdev_dev_get_req *netdev_dev_get_req_alloc(void) +{ + return calloc(1, sizeof(struct netdev_dev_get_req)); +} +void netdev_dev_get_req_free(struct netdev_dev_get_req *req); + +static inline void +netdev_dev_get_req_set_ifindex(struct netdev_dev_get_req *req, __u32 ifindex) +{ + req->_present.ifindex = 1; + req->ifindex = ifindex; +} + +struct netdev_dev_get_rsp { + struct { + __u32 ifindex:1; + __u32 xdp_features:1; + } _present; + + __u32 ifindex; + __u64 xdp_features; +}; + +void netdev_dev_get_rsp_free(struct netdev_dev_get_rsp *rsp); + +/* + * Get / dump information about a netdev. + */ +struct netdev_dev_get_rsp * +netdev_dev_get(struct ynl_sock *ys, struct netdev_dev_get_req *req); + +/* NETDEV_CMD_DEV_GET - dump */ +struct netdev_dev_get_list { + struct netdev_dev_get_list *next; + struct netdev_dev_get_rsp obj __attribute__ ((aligned (8))); +}; + +void netdev_dev_get_list_free(struct netdev_dev_get_list *rsp); + +struct netdev_dev_get_list *netdev_dev_get_dump(struct ynl_sock *ys); + +/* NETDEV_CMD_DEV_GET - notify */ +struct netdev_dev_get_ntf { + __u16 family; + __u8 cmd; + struct ynl_ntf_base_type *next; + void (*free)(struct netdev_dev_get_ntf *ntf); + struct netdev_dev_get_rsp obj __attribute__ ((aligned (8))); +}; + +void netdev_dev_get_ntf_free(struct netdev_dev_get_ntf *rsp); + +#endif /* _LINUX_NETDEV_GEN_H */ diff --git a/tools/net/ynl/lib/Makefile b/tools/net/ynl/lib/Makefile new file mode 100644 index 000000000000..d2e50fd0a52d --- /dev/null +++ b/tools/net/ynl/lib/Makefile @@ -0,0 +1,28 @@ +# SPDX-License-Identifier: GPL-2.0 + +CC=gcc +CFLAGS=-std=gnu11 -O2 -W -Wall -Wextra -Wno-unused-parameter -Wshadow +ifeq ("$(DEBUG)","1") + CFLAGS += -g -fsanitize=address -fsanitize=leak -static-libasan +endif + +SRCS=$(wildcard *.c) +OBJS=$(patsubst %.c,%.o,${SRCS}) + +include $(wildcard *.d) + +all: ynl.a + +ynl.a: $(OBJS) + ar rcs $@ $(OBJS) +clean: + rm -f *.o *.d *~ + +hardclean: clean + rm -f *.a + +%.o: %.c + $(COMPILE.c) -MMD -c -o $@ $< + +.PHONY: all clean +.DEFAULT_GOAL=all diff --git a/tools/net/ynl/lib/nlspec.py b/tools/net/ynl/lib/nlspec.py index a0241add3839..c5d4a6d476a0 100644 --- a/tools/net/ynl/lib/nlspec.py +++ b/tools/net/ynl/lib/nlspec.py @@ -226,11 +226,15 @@ class SpecStructMember(SpecElement): Represents a single struct member attribute. Attributes: - type string, type of the member attribute + type string, type of the member attribute + byte_order string or None for native byte order + enum string, name of the enum definition """ def __init__(self, family, yaml): super().__init__(family, yaml) self.type = yaml['type'] + self.byte_order = yaml.get('byte-order') + self.enum = yaml.get('enum') class SpecStruct(SpecElement): @@ -320,12 +324,13 @@ class SpecFamily(SpecElement): Attributes: proto protocol type (e.g. genetlink) + msg_id_model enum-model for operations (unified, directional etc.) license spec license (loaded from an SPDX tag on the spec) attr_sets dict of attribute sets msgs dict of all messages (index by name) - msgs_by_value dict of all messages (indexed by name) ops dict of all valid requests / responses + ntfs dict of all async events consts dict of all constants/enums fixed_header string, optional name of family default fixed header struct """ @@ -345,6 +350,7 @@ class SpecFamily(SpecElement): super().__init__(self, spec) self.proto = self.yaml.get('protocol', 'genetlink') + self.msg_id_model = self.yaml['operations'].get('enum-model', 'unified') if schema_path is None: schema_path = os.path.dirname(os.path.dirname(spec_path)) + f'/{self.proto}.yaml' @@ -364,6 +370,7 @@ class SpecFamily(SpecElement): self.req_by_value = collections.OrderedDict() self.rsp_by_value = collections.OrderedDict() self.ops = collections.OrderedDict() + self.ntfs = collections.OrderedDict() self.consts = collections.OrderedDict() last_exception = None @@ -416,7 +423,7 @@ class SpecFamily(SpecElement): self.fixed_header = self.yaml['operations'].get('fixed-header') req_val = rsp_val = 1 for elem in self.yaml['operations']['list']: - if 'notify' in elem: + if 'notify' in elem or 'event' in elem: if 'value' in elem: rsp_val = elem['value'] req_val_next = req_val @@ -438,6 +445,10 @@ class SpecFamily(SpecElement): else: raise Exception("Can't parse directional ops") + if req_val == req_val_next: + req_val = None + if rsp_val == rsp_val_next: + rsp_val = None op = self.new_operation(elem, req_val, rsp_val) req_val = req_val_next rsp_val = rsp_val_next @@ -469,10 +480,9 @@ class SpecFamily(SpecElement): attr_set = self.new_attr_set(elem) self.attr_sets[elem['name']] = attr_set - msg_id_model = self.yaml['operations'].get('enum-model', 'unified') - if msg_id_model == 'unified': + if self.msg_id_model == 'unified': self._dictify_ops_unified() - elif msg_id_model == 'directional': + elif self.msg_id_model == 'directional': self._dictify_ops_directional() for op in self.msgs.values(): @@ -482,3 +492,5 @@ class SpecFamily(SpecElement): self.rsp_by_value[op.rsp_value] = op if not op.is_async and 'attribute-set' in op: self.ops[op.name] = op + elif op.is_async: + self.ntfs[op.name] = op diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c new file mode 100644 index 000000000000..514e0d69e731 --- /dev/null +++ b/tools/net/ynl/lib/ynl.c @@ -0,0 +1,901 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +#include <errno.h> +#include <poll.h> +#include <string.h> +#include <stdlib.h> +#include <linux/types.h> + +#include <libmnl/libmnl.h> +#include <linux/genetlink.h> + +#include "ynl.h" + +#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof(*arr)) + +#define __yerr_msg(yse, _msg...) \ + ({ \ + struct ynl_error *_yse = (yse); \ + \ + if (_yse) { \ + snprintf(_yse->msg, sizeof(_yse->msg) - 1, _msg); \ + _yse->msg[sizeof(_yse->msg) - 1] = 0; \ + } \ + }) + +#define __yerr_code(yse, _code...) \ + ({ \ + struct ynl_error *_yse = (yse); \ + \ + if (_yse) { \ + _yse->code = _code; \ + } \ + }) + +#define __yerr(yse, _code, _msg...) \ + ({ \ + __yerr_msg(yse, _msg); \ + __yerr_code(yse, _code); \ + }) + +#define __perr(yse, _msg) __yerr(yse, errno, _msg) + +#define yerr_msg(_ys, _msg...) __yerr_msg(&(_ys)->err, _msg) +#define yerr(_ys, _code, _msg...) __yerr(&(_ys)->err, _code, _msg) +#define perr(_ys, _msg) __yerr(&(_ys)->err, errno, _msg) + +/* -- Netlink boiler plate */ +static int +ynl_err_walk_report_one(struct ynl_policy_nest *policy, unsigned int type, + char *str, int str_sz, int *n) +{ + if (!policy) { + if (*n < str_sz) + *n += snprintf(str, str_sz, "!policy"); + return 1; + } + + if (type > policy->max_attr) { + if (*n < str_sz) + *n += snprintf(str, str_sz, "!oob"); + return 1; + } + + if (!policy->table[type].name) { + if (*n < str_sz) + *n += snprintf(str, str_sz, "!name"); + return 1; + } + + if (*n < str_sz) + *n += snprintf(str, str_sz - *n, + ".%s", policy->table[type].name); + return 0; +} + +static int +ynl_err_walk(struct ynl_sock *ys, void *start, void *end, unsigned int off, + struct ynl_policy_nest *policy, char *str, int str_sz, + struct ynl_policy_nest **nest_pol) +{ + unsigned int astart_off, aend_off; + const struct nlattr *attr; + unsigned int data_len; + unsigned int type; + bool found = false; + int n = 0; + + if (!policy) { + if (n < str_sz) + n += snprintf(str, str_sz, "!policy"); + return n; + } + + data_len = end - start; + + mnl_attr_for_each_payload(start, data_len) { + astart_off = (char *)attr - (char *)start; + aend_off = astart_off + mnl_attr_get_payload_len(attr); + if (aend_off <= off) + continue; + + found = true; + break; + } + if (!found) + return 0; + + off -= astart_off; + + type = mnl_attr_get_type(attr); + + if (ynl_err_walk_report_one(policy, type, str, str_sz, &n)) + return n; + + if (!off) { + if (nest_pol) + *nest_pol = policy->table[type].nest; + return n; + } + + if (!policy->table[type].nest) { + if (n < str_sz) + n += snprintf(str, str_sz, "!nest"); + return n; + } + + off -= sizeof(struct nlattr); + start = mnl_attr_get_payload(attr); + end = start + mnl_attr_get_payload_len(attr); + + return n + ynl_err_walk(ys, start, end, off, policy->table[type].nest, + &str[n], str_sz - n, nest_pol); +} + +#define NLMSGERR_ATTR_MISS_TYPE (NLMSGERR_ATTR_POLICY + 1) +#define NLMSGERR_ATTR_MISS_NEST (NLMSGERR_ATTR_POLICY + 2) +#define NLMSGERR_ATTR_MAX (NLMSGERR_ATTR_MAX + 2) + +static int +ynl_ext_ack_check(struct ynl_sock *ys, const struct nlmsghdr *nlh, + unsigned int hlen) +{ + const struct nlattr *tb[NLMSGERR_ATTR_MAX + 1] = {}; + char miss_attr[sizeof(ys->err.msg)]; + char bad_attr[sizeof(ys->err.msg)]; + const struct nlattr *attr; + const char *str = NULL; + + if (!(nlh->nlmsg_flags & NLM_F_ACK_TLVS)) + return MNL_CB_OK; + + mnl_attr_for_each(attr, nlh, hlen) { + unsigned int len, type; + + len = mnl_attr_get_payload_len(attr); + type = mnl_attr_get_type(attr); + + if (type > NLMSGERR_ATTR_MAX) + continue; + + tb[type] = attr; + + switch (type) { + case NLMSGERR_ATTR_OFFS: + case NLMSGERR_ATTR_MISS_TYPE: + case NLMSGERR_ATTR_MISS_NEST: + if (len != sizeof(__u32)) + return MNL_CB_ERROR; + break; + case NLMSGERR_ATTR_MSG: + str = mnl_attr_get_payload(attr); + if (str[len - 1]) + return MNL_CB_ERROR; + break; + default: + break; + } + } + + bad_attr[0] = '\0'; + miss_attr[0] = '\0'; + + if (tb[NLMSGERR_ATTR_OFFS]) { + unsigned int n, off; + void *start, *end; + + ys->err.attr_offs = mnl_attr_get_u32(tb[NLMSGERR_ATTR_OFFS]); + + n = snprintf(bad_attr, sizeof(bad_attr), "%sbad attribute: ", + str ? " (" : ""); + + start = mnl_nlmsg_get_payload_offset(ys->nlh, + sizeof(struct genlmsghdr)); + end = mnl_nlmsg_get_payload_tail(ys->nlh); + + off = ys->err.attr_offs; + off -= sizeof(struct nlmsghdr); + off -= sizeof(struct genlmsghdr); + + n += ynl_err_walk(ys, start, end, off, ys->req_policy, + &bad_attr[n], sizeof(bad_attr) - n, NULL); + + if (n >= sizeof(bad_attr)) + n = sizeof(bad_attr) - 1; + bad_attr[n] = '\0'; + } + if (tb[NLMSGERR_ATTR_MISS_TYPE]) { + struct ynl_policy_nest *nest_pol = NULL; + unsigned int n, off, type; + void *start, *end; + int n2; + + type = mnl_attr_get_u32(tb[NLMSGERR_ATTR_MISS_TYPE]); + + n = snprintf(miss_attr, sizeof(miss_attr), "%smissing attribute: ", + bad_attr[0] ? ", " : (str ? " (" : "")); + + start = mnl_nlmsg_get_payload_offset(ys->nlh, + sizeof(struct genlmsghdr)); + end = mnl_nlmsg_get_payload_tail(ys->nlh); + + nest_pol = ys->req_policy; + if (tb[NLMSGERR_ATTR_MISS_NEST]) { + off = mnl_attr_get_u32(tb[NLMSGERR_ATTR_MISS_NEST]); + off -= sizeof(struct nlmsghdr); + off -= sizeof(struct genlmsghdr); + + n += ynl_err_walk(ys, start, end, off, ys->req_policy, + &miss_attr[n], sizeof(miss_attr) - n, + &nest_pol); + } + + n2 = 0; + ynl_err_walk_report_one(nest_pol, type, &miss_attr[n], + sizeof(miss_attr) - n, &n2); + n += n2; + + if (n >= sizeof(miss_attr)) + n = sizeof(miss_attr) - 1; + miss_attr[n] = '\0'; + } + + /* Implicitly depend on ys->err.code already set */ + if (str) + yerr_msg(ys, "Kernel %s: '%s'%s%s%s", + ys->err.code ? "error" : "warning", + str, bad_attr, miss_attr, + bad_attr[0] || miss_attr[0] ? ")" : ""); + else if (bad_attr[0] || miss_attr[0]) + yerr_msg(ys, "Kernel %s: %s%s", + ys->err.code ? "error" : "warning", + bad_attr, miss_attr); + + return MNL_CB_OK; +} + +static int ynl_cb_error(const struct nlmsghdr *nlh, void *data) +{ + const struct nlmsgerr *err = mnl_nlmsg_get_payload(nlh); + struct ynl_parse_arg *yarg = data; + unsigned int hlen; + int code; + + code = err->error >= 0 ? err->error : -err->error; + yarg->ys->err.code = code; + errno = code; + + hlen = sizeof(*err); + if (!(nlh->nlmsg_flags & NLM_F_CAPPED)) + hlen += mnl_nlmsg_get_payload_len(&err->msg); + + ynl_ext_ack_check(yarg->ys, nlh, hlen); + + return code ? MNL_CB_ERROR : MNL_CB_STOP; +} + +static int ynl_cb_done(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + int err; + + err = *(int *)NLMSG_DATA(nlh); + if (err < 0) { + yarg->ys->err.code = -err; + errno = -err; + + ynl_ext_ack_check(yarg->ys, nlh, sizeof(int)); + + return MNL_CB_ERROR; + } + return MNL_CB_STOP; +} + +static int ynl_cb_noop(const struct nlmsghdr *nlh, void *data) +{ + return MNL_CB_OK; +} + +mnl_cb_t ynl_cb_array[NLMSG_MIN_TYPE] = { + [NLMSG_NOOP] = ynl_cb_noop, + [NLMSG_ERROR] = ynl_cb_error, + [NLMSG_DONE] = ynl_cb_done, + [NLMSG_OVERRUN] = ynl_cb_noop, +}; + +/* Attribute validation */ + +int ynl_attr_validate(struct ynl_parse_arg *yarg, const struct nlattr *attr) +{ + struct ynl_policy_attr *policy; + unsigned int type, len; + unsigned char *data; + + data = mnl_attr_get_payload(attr); + len = mnl_attr_get_payload_len(attr); + type = mnl_attr_get_type(attr); + if (type > yarg->rsp_policy->max_attr) { + yerr(yarg->ys, YNL_ERROR_INTERNAL, + "Internal error, validating unknown attribute"); + return -1; + } + + policy = &yarg->rsp_policy->table[type]; + + switch (policy->type) { + case YNL_PT_REJECT: + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Rejected attribute (%s)", policy->name); + return -1; + case YNL_PT_IGNORE: + break; + case YNL_PT_U8: + if (len == sizeof(__u8)) + break; + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Invalid attribute (u8 %s)", policy->name); + return -1; + case YNL_PT_U16: + if (len == sizeof(__u16)) + break; + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Invalid attribute (u16 %s)", policy->name); + return -1; + case YNL_PT_U32: + if (len == sizeof(__u32)) + break; + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Invalid attribute (u32 %s)", policy->name); + return -1; + case YNL_PT_U64: + if (len == sizeof(__u64)) + break; + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Invalid attribute (u64 %s)", policy->name); + return -1; + case YNL_PT_FLAG: + /* Let flags grow into real attrs, why not.. */ + break; + case YNL_PT_NEST: + if (!len || len >= sizeof(*attr)) + break; + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Invalid attribute (nest %s)", policy->name); + return -1; + case YNL_PT_BINARY: + if (!policy->len || len == policy->len) + break; + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Invalid attribute (binary %s)", policy->name); + return -1; + case YNL_PT_NUL_STR: + if ((!policy->len || len <= policy->len) && !data[len - 1]) + break; + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Invalid attribute (string %s)", policy->name); + return -1; + default: + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Invalid attribute (unknown %s)", policy->name); + return -1; + } + + return 0; +} + +/* Generic code */ + +static void ynl_err_reset(struct ynl_sock *ys) +{ + ys->err.code = 0; + ys->err.attr_offs = 0; + ys->err.msg[0] = 0; +} + +struct nlmsghdr *ynl_msg_start(struct ynl_sock *ys, __u32 id, __u16 flags) +{ + struct nlmsghdr *nlh; + + ynl_err_reset(ys); + + nlh = ys->nlh = mnl_nlmsg_put_header(ys->tx_buf); + nlh->nlmsg_type = id; + nlh->nlmsg_flags = flags; + nlh->nlmsg_seq = ++ys->seq; + + return nlh; +} + +struct nlmsghdr * +ynl_gemsg_start(struct ynl_sock *ys, __u32 id, __u16 flags, + __u8 cmd, __u8 version) +{ + struct genlmsghdr gehdr; + struct nlmsghdr *nlh; + void *data; + + nlh = ynl_msg_start(ys, id, flags); + + memset(&gehdr, 0, sizeof(gehdr)); + gehdr.cmd = cmd; + gehdr.version = version; + + data = mnl_nlmsg_put_extra_header(nlh, sizeof(gehdr)); + memcpy(data, &gehdr, sizeof(gehdr)); + + return nlh; +} + +void ynl_msg_start_req(struct ynl_sock *ys, __u32 id) +{ + ynl_msg_start(ys, id, NLM_F_REQUEST | NLM_F_ACK); +} + +void ynl_msg_start_dump(struct ynl_sock *ys, __u32 id) +{ + ynl_msg_start(ys, id, NLM_F_REQUEST | NLM_F_ACK | NLM_F_DUMP); +} + +struct nlmsghdr * +ynl_gemsg_start_req(struct ynl_sock *ys, __u32 id, __u8 cmd, __u8 version) +{ + return ynl_gemsg_start(ys, id, NLM_F_REQUEST | NLM_F_ACK, cmd, version); +} + +struct nlmsghdr * +ynl_gemsg_start_dump(struct ynl_sock *ys, __u32 id, __u8 cmd, __u8 version) +{ + return ynl_gemsg_start(ys, id, NLM_F_REQUEST | NLM_F_ACK | NLM_F_DUMP, + cmd, version); +} + +int ynl_recv_ack(struct ynl_sock *ys, int ret) +{ + if (!ret) { + yerr(ys, YNL_ERROR_EXPECT_ACK, + "Expecting an ACK but nothing received"); + return -1; + } + + ret = mnl_socket_recvfrom(ys->sock, ys->rx_buf, MNL_SOCKET_BUFFER_SIZE); + if (ret < 0) { + perr(ys, "Socket receive failed"); + return ret; + } + return mnl_cb_run(ys->rx_buf, ret, ys->seq, ys->portid, + ynl_cb_null, ys); +} + +int ynl_cb_null(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + + yerr(yarg->ys, YNL_ERROR_UNEXPECT_MSG, + "Received a message when none were expected"); + + return MNL_CB_ERROR; +} + +/* Init/fini and genetlink boiler plate */ +static int +ynl_get_family_info_mcast(struct ynl_sock *ys, const struct nlattr *mcasts) +{ + const struct nlattr *entry, *attr; + unsigned int i; + + mnl_attr_for_each_nested(attr, mcasts) + ys->n_mcast_groups++; + + if (!ys->n_mcast_groups) + return 0; + + ys->mcast_groups = calloc(ys->n_mcast_groups, + sizeof(*ys->mcast_groups)); + if (!ys->mcast_groups) + return MNL_CB_ERROR; + + i = 0; + mnl_attr_for_each_nested(entry, mcasts) { + mnl_attr_for_each_nested(attr, entry) { + if (mnl_attr_get_type(attr) == CTRL_ATTR_MCAST_GRP_ID) + ys->mcast_groups[i].id = mnl_attr_get_u32(attr); + if (mnl_attr_get_type(attr) == CTRL_ATTR_MCAST_GRP_NAME) { + strncpy(ys->mcast_groups[i].name, + mnl_attr_get_str(attr), + GENL_NAMSIZ - 1); + ys->mcast_groups[i].name[GENL_NAMSIZ - 1] = 0; + } + } + } + + return 0; +} + +static int ynl_get_family_info_cb(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct ynl_sock *ys = yarg->ys; + const struct nlattr *attr; + bool found_id = true; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + if (mnl_attr_get_type(attr) == CTRL_ATTR_MCAST_GROUPS) + if (ynl_get_family_info_mcast(ys, attr)) + return MNL_CB_ERROR; + + if (mnl_attr_get_type(attr) != CTRL_ATTR_FAMILY_ID) + continue; + + if (mnl_attr_get_payload_len(attr) != sizeof(__u16)) { + yerr(ys, YNL_ERROR_ATTR_INVALID, "Invalid family ID"); + return MNL_CB_ERROR; + } + + ys->family_id = mnl_attr_get_u16(attr); + found_id = true; + } + + if (!found_id) { + yerr(ys, YNL_ERROR_ATTR_MISSING, "Family ID missing"); + return MNL_CB_ERROR; + } + return MNL_CB_OK; +} + +static int ynl_sock_read_family(struct ynl_sock *ys, const char *family_name) +{ + struct ynl_parse_arg yarg = { .ys = ys, }; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, GENL_ID_CTRL, CTRL_CMD_GETFAMILY, 1); + mnl_attr_put_strz(nlh, CTRL_ATTR_FAMILY_NAME, family_name); + + err = mnl_socket_sendto(ys->sock, nlh, nlh->nlmsg_len); + if (err < 0) { + perr(ys, "failed to request socket family info"); + return err; + } + + err = mnl_socket_recvfrom(ys->sock, ys->rx_buf, MNL_SOCKET_BUFFER_SIZE); + if (err <= 0) { + perr(ys, "failed to receive the socket family info"); + return err; + } + err = mnl_cb_run2(ys->rx_buf, err, ys->seq, ys->portid, + ynl_get_family_info_cb, &yarg, + ynl_cb_array, ARRAY_SIZE(ynl_cb_array)); + if (err < 0) { + free(ys->mcast_groups); + perr(ys, "failed to receive the socket family info - no such family?"); + return err; + } + + return ynl_recv_ack(ys, err); +} + +struct ynl_sock * +ynl_sock_create(const struct ynl_family *yf, struct ynl_error *yse) +{ + struct ynl_sock *ys; + int one = 1; + + ys = malloc(sizeof(*ys) + 2 * MNL_SOCKET_BUFFER_SIZE); + if (!ys) + return NULL; + memset(ys, 0, sizeof(*ys)); + + ys->family = yf; + ys->tx_buf = &ys->raw_buf[0]; + ys->rx_buf = &ys->raw_buf[MNL_SOCKET_BUFFER_SIZE]; + ys->ntf_last_next = &ys->ntf_first; + + ys->sock = mnl_socket_open(NETLINK_GENERIC); + if (!ys->sock) { + __perr(yse, "failed to create a netlink socket"); + goto err_free_sock; + } + + if (mnl_socket_setsockopt(ys->sock, NETLINK_CAP_ACK, + &one, sizeof(one))) { + __perr(yse, "failed to enable netlink ACK"); + goto err_close_sock; + } + if (mnl_socket_setsockopt(ys->sock, NETLINK_EXT_ACK, + &one, sizeof(one))) { + __perr(yse, "failed to enable netlink ext ACK"); + goto err_close_sock; + } + + ys->seq = random(); + ys->portid = mnl_socket_get_portid(ys->sock); + + if (ynl_sock_read_family(ys, yf->name)) { + if (yse) + memcpy(yse, &ys->err, sizeof(*yse)); + goto err_close_sock; + } + + return ys; + +err_close_sock: + mnl_socket_close(ys->sock); +err_free_sock: + free(ys); + return NULL; +} + +void ynl_sock_destroy(struct ynl_sock *ys) +{ + struct ynl_ntf_base_type *ntf; + + mnl_socket_close(ys->sock); + while ((ntf = ynl_ntf_dequeue(ys))) + ynl_ntf_free(ntf); + free(ys->mcast_groups); + free(ys); +} + +/* YNL multicast handling */ + +void ynl_ntf_free(struct ynl_ntf_base_type *ntf) +{ + ntf->free(ntf); +} + +int ynl_subscribe(struct ynl_sock *ys, const char *grp_name) +{ + unsigned int i; + int err; + + for (i = 0; i < ys->n_mcast_groups; i++) + if (!strcmp(ys->mcast_groups[i].name, grp_name)) + break; + if (i == ys->n_mcast_groups) { + yerr(ys, ENOENT, "Multicast group '%s' not found", grp_name); + return -1; + } + + err = mnl_socket_setsockopt(ys->sock, NETLINK_ADD_MEMBERSHIP, + &ys->mcast_groups[i].id, + sizeof(ys->mcast_groups[i].id)); + if (err < 0) { + perr(ys, "Subscribing to multicast group failed"); + return -1; + } + + return 0; +} + +int ynl_socket_get_fd(struct ynl_sock *ys) +{ + return mnl_socket_get_fd(ys->sock); +} + +struct ynl_ntf_base_type *ynl_ntf_dequeue(struct ynl_sock *ys) +{ + struct ynl_ntf_base_type *ntf; + + if (!ynl_has_ntf(ys)) + return NULL; + + ntf = ys->ntf_first; + ys->ntf_first = ntf->next; + if (ys->ntf_last_next == &ntf->next) + ys->ntf_last_next = &ys->ntf_first; + + return ntf; +} + +static int ynl_ntf_parse(struct ynl_sock *ys, const struct nlmsghdr *nlh) +{ + struct ynl_parse_arg yarg = { .ys = ys, }; + const struct ynl_ntf_info *info; + struct ynl_ntf_base_type *rsp; + struct genlmsghdr *gehdr; + int ret; + + gehdr = mnl_nlmsg_get_payload(nlh); + if (gehdr->cmd >= ys->family->ntf_info_size) + return MNL_CB_ERROR; + info = &ys->family->ntf_info[gehdr->cmd]; + if (!info->cb) + return MNL_CB_ERROR; + + rsp = calloc(1, info->alloc_sz); + rsp->free = info->free; + yarg.data = rsp->data; + yarg.rsp_policy = info->policy; + + ret = info->cb(nlh, &yarg); + if (ret <= MNL_CB_STOP) + goto err_free; + + rsp->family = nlh->nlmsg_type; + rsp->cmd = gehdr->cmd; + + *ys->ntf_last_next = rsp; + ys->ntf_last_next = &rsp->next; + + return MNL_CB_OK; + +err_free: + info->free(rsp); + return MNL_CB_ERROR; +} + +static int ynl_ntf_trampoline(const struct nlmsghdr *nlh, void *data) +{ + return ynl_ntf_parse((struct ynl_sock *)data, nlh); +} + +int ynl_ntf_check(struct ynl_sock *ys) +{ + ssize_t len; + int err; + + do { + /* libmnl doesn't let us pass flags to the recv to make + * it non-blocking so we need to poll() or peek() :| + */ + struct pollfd pfd = { }; + + pfd.fd = mnl_socket_get_fd(ys->sock); + pfd.events = POLLIN; + err = poll(&pfd, 1, 1); + if (err < 1) + return err; + + len = mnl_socket_recvfrom(ys->sock, ys->rx_buf, + MNL_SOCKET_BUFFER_SIZE); + if (len < 0) + return len; + + err = mnl_cb_run2(ys->rx_buf, len, ys->seq, ys->portid, + ynl_ntf_trampoline, ys, + ynl_cb_array, NLMSG_MIN_TYPE); + if (err < 0) + return err; + } while (err > 0); + + return 0; +} + +/* YNL specific helpers used by the auto-generated code */ + +struct ynl_dump_list_type *YNL_LIST_END = (void *)(0xb4d123); + +void ynl_error_unknown_notification(struct ynl_sock *ys, __u8 cmd) +{ + yerr(ys, YNL_ERROR_UNKNOWN_NTF, + "Unknown notification message type '%d'", cmd); +} + +int ynl_error_parse(struct ynl_parse_arg *yarg, const char *msg) +{ + yerr(yarg->ys, YNL_ERROR_INV_RESP, "Error parsing response: %s", msg); + return MNL_CB_ERROR; +} + +static int +ynl_check_alien(struct ynl_sock *ys, const struct nlmsghdr *nlh, __u32 rsp_cmd) +{ + struct genlmsghdr *gehdr; + + if (mnl_nlmsg_get_payload_len(nlh) < sizeof(*gehdr)) { + yerr(ys, YNL_ERROR_INV_RESP, + "Kernel responded with truncated message"); + return -1; + } + + gehdr = mnl_nlmsg_get_payload(nlh); + if (gehdr->cmd != rsp_cmd) + return ynl_ntf_parse(ys, nlh); + + return 0; +} + +static int ynl_req_trampoline(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_req_state *yrs = data; + int ret; + + ret = ynl_check_alien(yrs->yarg.ys, nlh, yrs->rsp_cmd); + if (ret) + return ret < 0 ? MNL_CB_ERROR : MNL_CB_OK; + + return yrs->cb(nlh, &yrs->yarg); +} + +int ynl_exec(struct ynl_sock *ys, struct nlmsghdr *req_nlh, + struct ynl_req_state *yrs) +{ + ssize_t len; + int err; + + err = mnl_socket_sendto(ys->sock, req_nlh, req_nlh->nlmsg_len); + if (err < 0) + return err; + + do { + len = mnl_socket_recvfrom(ys->sock, ys->rx_buf, + MNL_SOCKET_BUFFER_SIZE); + if (len < 0) + return len; + + err = mnl_cb_run2(ys->rx_buf, len, ys->seq, ys->portid, + ynl_req_trampoline, yrs, + ynl_cb_array, NLMSG_MIN_TYPE); + if (err < 0) + return err; + } while (err > 0); + + return 0; +} + +static int ynl_dump_trampoline(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_dump_state *ds = data; + struct ynl_dump_list_type *obj; + struct ynl_parse_arg yarg = {}; + int ret; + + ret = ynl_check_alien(ds->ys, nlh, ds->rsp_cmd); + if (ret) + return ret < 0 ? MNL_CB_ERROR : MNL_CB_OK; + + obj = calloc(1, ds->alloc_sz); + if (!obj) + return MNL_CB_ERROR; + + if (!ds->first) + ds->first = obj; + if (ds->last) + ds->last->next = obj; + ds->last = obj; + + yarg.ys = ds->ys; + yarg.rsp_policy = ds->rsp_policy; + yarg.data = &obj->data; + + return ds->cb(nlh, &yarg); +} + +static void *ynl_dump_end(struct ynl_dump_state *ds) +{ + if (!ds->first) + return YNL_LIST_END; + + ds->last->next = YNL_LIST_END; + return ds->first; +} + +int ynl_exec_dump(struct ynl_sock *ys, struct nlmsghdr *req_nlh, + struct ynl_dump_state *yds) +{ + ssize_t len; + int err; + + err = mnl_socket_sendto(ys->sock, req_nlh, req_nlh->nlmsg_len); + if (err < 0) + return err; + + do { + len = mnl_socket_recvfrom(ys->sock, ys->rx_buf, + MNL_SOCKET_BUFFER_SIZE); + if (len < 0) + goto err_close_list; + + err = mnl_cb_run2(ys->rx_buf, len, ys->seq, ys->portid, + ynl_dump_trampoline, yds, + ynl_cb_array, NLMSG_MIN_TYPE); + if (err < 0) + goto err_close_list; + } while (err > 0); + + yds->first = ynl_dump_end(yds); + return 0; + +err_close_list: + yds->first = ynl_dump_end(yds); + return -1; +} diff --git a/tools/net/ynl/lib/ynl.h b/tools/net/ynl/lib/ynl.h new file mode 100644 index 000000000000..9eafa3552c16 --- /dev/null +++ b/tools/net/ynl/lib/ynl.h @@ -0,0 +1,237 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +#ifndef __YNL_C_H +#define __YNL_C_H 1 + +#include <stddef.h> +#include <libmnl/libmnl.h> +#include <linux/genetlink.h> +#include <linux/types.h> + +struct mnl_socket; +struct nlmsghdr; + +/* + * User facing code + */ + +struct ynl_ntf_base_type; +struct ynl_ntf_info; +struct ynl_sock; + +enum ynl_error_code { + YNL_ERROR_NONE = 0, + __YNL_ERRNO_END = 4096, + YNL_ERROR_INTERNAL, + YNL_ERROR_EXPECT_ACK, + YNL_ERROR_EXPECT_MSG, + YNL_ERROR_UNEXPECT_MSG, + YNL_ERROR_ATTR_MISSING, + YNL_ERROR_ATTR_INVALID, + YNL_ERROR_UNKNOWN_NTF, + YNL_ERROR_INV_RESP, +}; + +/** + * struct ynl_error - error encountered by YNL + * @code: errno (low values) or YNL error code (enum ynl_error_code) + * @attr_offs: offset of bad attribute (for very advanced users) + * @msg: error message + * + * Error information for when YNL operations fail. + * Users should interact with the err member of struct ynl_sock directly. + * The main exception to that rule is ynl_sock_create(). + */ +struct ynl_error { + enum ynl_error_code code; + unsigned int attr_offs; + char msg[512]; +}; + +/** + * struct ynl_family - YNL family info + * Family description generated by codegen. Pass to ynl_sock_create(). + */ +struct ynl_family { +/* private: */ + const char *name; + const struct ynl_ntf_info *ntf_info; + unsigned int ntf_info_size; +}; + +/** + * struct ynl_sock - YNL wrapped netlink socket + * @err: YNL error descriptor, cleared on every request. + */ +struct ynl_sock { + struct ynl_error err; + +/* private: */ + const struct ynl_family *family; + struct mnl_socket *sock; + __u32 seq; + __u32 portid; + __u16 family_id; + + unsigned int n_mcast_groups; + struct { + unsigned int id; + char name[GENL_NAMSIZ]; + } *mcast_groups; + + struct ynl_ntf_base_type *ntf_first; + struct ynl_ntf_base_type **ntf_last_next; + + struct nlmsghdr *nlh; + struct ynl_policy_nest *req_policy; + unsigned char *tx_buf; + unsigned char *rx_buf; + unsigned char raw_buf[]; +}; + +struct ynl_sock * +ynl_sock_create(const struct ynl_family *yf, struct ynl_error *e); +void ynl_sock_destroy(struct ynl_sock *ys); + +#define ynl_dump_foreach(dump, iter) \ + for (typeof(dump->obj) *iter = &dump->obj; \ + !ynl_dump_obj_is_last(iter); \ + iter = ynl_dump_obj_next(iter)) + +int ynl_subscribe(struct ynl_sock *ys, const char *grp_name); +int ynl_socket_get_fd(struct ynl_sock *ys); +int ynl_ntf_check(struct ynl_sock *ys); + +/** + * ynl_has_ntf() - check if socket has *parsed* notifications + * @ys: active YNL socket + * + * Note that this does not take into account notifications sitting + * in netlink socket, just the notifications which have already been + * read and parsed (e.g. during a ynl_ntf_check() call). + */ +static inline bool ynl_has_ntf(struct ynl_sock *ys) +{ + return ys->ntf_last_next != &ys->ntf_first; +} +struct ynl_ntf_base_type *ynl_ntf_dequeue(struct ynl_sock *ys); + +void ynl_ntf_free(struct ynl_ntf_base_type *ntf); + +/* + * YNL internals / low level stuff + */ + +/* Generic mnl helper code */ + +enum ynl_policy_type { + YNL_PT_REJECT = 1, + YNL_PT_IGNORE, + YNL_PT_NEST, + YNL_PT_FLAG, + YNL_PT_BINARY, + YNL_PT_U8, + YNL_PT_U16, + YNL_PT_U32, + YNL_PT_U64, + YNL_PT_NUL_STR, +}; + +struct ynl_policy_attr { + enum ynl_policy_type type; + unsigned int len; + const char *name; + struct ynl_policy_nest *nest; +}; + +struct ynl_policy_nest { + unsigned int max_attr; + struct ynl_policy_attr *table; +}; + +struct ynl_parse_arg { + struct ynl_sock *ys; + struct ynl_policy_nest *rsp_policy; + void *data; +}; + +struct ynl_dump_list_type { + struct ynl_dump_list_type *next; + unsigned char data[] __attribute__ ((aligned (8))); +}; +extern struct ynl_dump_list_type *YNL_LIST_END; + +static inline bool ynl_dump_obj_is_last(void *obj) +{ + unsigned long uptr = (unsigned long)obj; + + uptr -= offsetof(struct ynl_dump_list_type, data); + return uptr == (unsigned long)YNL_LIST_END; +} + +static inline void *ynl_dump_obj_next(void *obj) +{ + unsigned long uptr = (unsigned long)obj; + struct ynl_dump_list_type *list; + + uptr -= offsetof(struct ynl_dump_list_type, data); + list = (void *)uptr; + uptr = (unsigned long)list->next; + uptr += offsetof(struct ynl_dump_list_type, data); + + return (void *)uptr; +} + +struct ynl_ntf_base_type { + __u16 family; + __u8 cmd; + struct ynl_ntf_base_type *next; + void (*free)(struct ynl_ntf_base_type *ntf); + unsigned char data[] __attribute__ ((aligned (8))); +}; + +extern mnl_cb_t ynl_cb_array[NLMSG_MIN_TYPE]; + +struct nlmsghdr * +ynl_gemsg_start_req(struct ynl_sock *ys, __u32 id, __u8 cmd, __u8 version); +struct nlmsghdr * +ynl_gemsg_start_dump(struct ynl_sock *ys, __u32 id, __u8 cmd, __u8 version); + +int ynl_attr_validate(struct ynl_parse_arg *yarg, const struct nlattr *attr); + +int ynl_recv_ack(struct ynl_sock *ys, int ret); +int ynl_cb_null(const struct nlmsghdr *nlh, void *data); + +/* YNL specific helpers used by the auto-generated code */ + +struct ynl_req_state { + struct ynl_parse_arg yarg; + mnl_cb_t cb; + __u32 rsp_cmd; +}; + +struct ynl_dump_state { + struct ynl_sock *ys; + struct ynl_policy_nest *rsp_policy; + void *first; + struct ynl_dump_list_type *last; + size_t alloc_sz; + mnl_cb_t cb; + __u32 rsp_cmd; +}; + +struct ynl_ntf_info { + struct ynl_policy_nest *policy; + mnl_cb_t cb; + size_t alloc_sz; + void (*free)(struct ynl_ntf_base_type *ntf); +}; + +int ynl_exec(struct ynl_sock *ys, struct nlmsghdr *req_nlh, + struct ynl_req_state *yrs); +int ynl_exec_dump(struct ynl_sock *ys, struct nlmsghdr *req_nlh, + struct ynl_dump_state *yds); + +void ynl_error_unknown_notification(struct ynl_sock *ys, __u8 cmd); +int ynl_error_parse(struct ynl_parse_arg *yarg, const char *msg); + +#endif diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py index aa77bcae4807..3b343d6cbbc0 100644 --- a/tools/net/ynl/lib/ynl.py +++ b/tools/net/ynl/lib/ynl.py @@ -1,10 +1,12 @@ # SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +from collections import namedtuple import functools import os import random import socket import struct +from struct import Struct import yaml from .nlspec import SpecFamily @@ -76,10 +78,17 @@ class NlError(Exception): class NlAttr: - type_formats = { 'u8' : ('B', 1), 's8' : ('b', 1), - 'u16': ('H', 2), 's16': ('h', 2), - 'u32': ('I', 4), 's32': ('i', 4), - 'u64': ('Q', 8), 's64': ('q', 8) } + ScalarFormat = namedtuple('ScalarFormat', ['native', 'big', 'little']) + type_formats = { + 'u8' : ScalarFormat(Struct('B'), Struct("B"), Struct("B")), + 's8' : ScalarFormat(Struct('b'), Struct("b"), Struct("b")), + 'u16': ScalarFormat(Struct('H'), Struct(">H"), Struct("<H")), + 's16': ScalarFormat(Struct('h'), Struct(">h"), Struct("<h")), + 'u32': ScalarFormat(Struct('I'), Struct(">I"), Struct("<I")), + 's32': ScalarFormat(Struct('i'), Struct(">i"), Struct("<i")), + 'u64': ScalarFormat(Struct('Q'), Struct(">Q"), Struct("<Q")), + 's64': ScalarFormat(Struct('q'), Struct(">q"), Struct("<q")) + } def __init__(self, raw, offset): self._len, self._type = struct.unpack("HH", raw[offset:offset + 4]) @@ -88,25 +97,17 @@ class NlAttr: self.full_len = (self.payload_len + 3) & ~3 self.raw = raw[offset + 4:offset + self.payload_len] - def format_byte_order(byte_order): + @classmethod + def get_format(cls, attr_type, byte_order=None): + format = cls.type_formats[attr_type] if byte_order: - return ">" if byte_order == "big-endian" else "<" - return "" + return format.big if byte_order == "big-endian" \ + else format.little + return format.native - def as_u8(self): - return struct.unpack("B", self.raw)[0] - - def as_u16(self, byte_order=None): - endian = NlAttr.format_byte_order(byte_order) - return struct.unpack(f"{endian}H", self.raw)[0] - - def as_u32(self, byte_order=None): - endian = NlAttr.format_byte_order(byte_order) - return struct.unpack(f"{endian}I", self.raw)[0] - - def as_u64(self, byte_order=None): - endian = NlAttr.format_byte_order(byte_order) - return struct.unpack(f"{endian}Q", self.raw)[0] + def as_scalar(self, attr_type, byte_order=None): + format = self.get_format(attr_type, byte_order) + return format.unpack(self.raw)[0] def as_strz(self): return self.raw.decode('ascii')[:-1] @@ -115,17 +116,17 @@ class NlAttr: return self.raw def as_c_array(self, type): - format, _ = self.type_formats[type] - return list({ x[0] for x in struct.iter_unpack(format, self.raw) }) + format = self.get_format(type) + return [ x[0] for x in format.iter_unpack(self.raw) ] def as_struct(self, members): value = dict() offset = 0 for m in members: # TODO: handle non-scalar members - format, size = self.type_formats[m.type] - decoded = struct.unpack_from(format, self.raw, offset) - offset += size + format = self.get_format(m.type, m.byte_order) + decoded = format.unpack_from(self.raw, offset) + offset += format.size value[m.name] = decoded[0] return value @@ -184,11 +185,11 @@ class NlMsg: if extack.type == Netlink.NLMSGERR_ATTR_MSG: self.extack['msg'] = extack.as_strz() elif extack.type == Netlink.NLMSGERR_ATTR_MISS_TYPE: - self.extack['miss-type'] = extack.as_u32() + self.extack['miss-type'] = extack.as_scalar('u32') elif extack.type == Netlink.NLMSGERR_ATTR_MISS_NEST: - self.extack['miss-nest'] = extack.as_u32() + self.extack['miss-nest'] = extack.as_scalar('u32') elif extack.type == Netlink.NLMSGERR_ATTR_OFFS: - self.extack['bad-attr-offs'] = extack.as_u32() + self.extack['bad-attr-offs'] = extack.as_scalar('u32') else: if 'unknown' not in self.extack: self.extack['unknown'] = [] @@ -272,11 +273,11 @@ def _genl_load_families(): fam = dict() for attr in gm.raw_attrs: if attr.type == Netlink.CTRL_ATTR_FAMILY_ID: - fam['id'] = attr.as_u16() + fam['id'] = attr.as_scalar('u16') elif attr.type == Netlink.CTRL_ATTR_FAMILY_NAME: fam['name'] = attr.as_strz() elif attr.type == Netlink.CTRL_ATTR_MAXATTR: - fam['maxattr'] = attr.as_u32() + fam['maxattr'] = attr.as_scalar('u32') elif attr.type == Netlink.CTRL_ATTR_MCAST_GROUPS: fam['mcast'] = dict() for entry in NlAttrs(attr.raw): @@ -286,7 +287,7 @@ def _genl_load_families(): if entry_attr.type == Netlink.CTRL_ATTR_MCAST_GRP_NAME: mcast_name = entry_attr.as_strz() elif entry_attr.type == Netlink.CTRL_ATTR_MCAST_GRP_ID: - mcast_id = entry_attr.as_u32() + mcast_id = entry_attr.as_scalar('u32') if mcast_name and mcast_id is not None: fam['mcast'][mcast_name] = mcast_id if 'name' in fam and 'id' in fam: @@ -304,9 +305,9 @@ class GenlMsg: self.fixed_header_attrs = dict() for m in fixed_header_members: - format, size = NlAttr.type_formats[m.type] - decoded = struct.unpack_from(format, nl_msg.raw, offset) - offset += size + format = NlAttr.get_format(m.type, m.byte_order) + decoded = format.unpack_from(nl_msg.raw, offset) + offset += format.size self.fixed_header_attrs[m.name] = decoded[0] self.raw = nl_msg.raw[offset:] @@ -381,21 +382,13 @@ class YnlFamily(SpecFamily): attr_payload += self._add_attr(attr['nested-attributes'], subname, subvalue) elif attr["type"] == 'flag': attr_payload = b'' - elif attr["type"] == 'u8': - attr_payload = struct.pack("B", int(value)) - elif attr["type"] == 'u16': - endian = NlAttr.format_byte_order(attr.byte_order) - attr_payload = struct.pack(f"{endian}H", int(value)) - elif attr["type"] == 'u32': - endian = NlAttr.format_byte_order(attr.byte_order) - attr_payload = struct.pack(f"{endian}I", int(value)) - elif attr["type"] == 'u64': - endian = NlAttr.format_byte_order(attr.byte_order) - attr_payload = struct.pack(f"{endian}Q", int(value)) elif attr["type"] == 'string': attr_payload = str(value).encode('ascii') + b'\x00' elif attr["type"] == 'binary': attr_payload = value + elif attr['type'] in NlAttr.type_formats: + format = NlAttr.get_format(attr['type'], attr.byte_order) + attr_payload = format.pack(int(value)) else: raise Exception(f'Unknown type at {space} {name} {value} {attr["type"]}') @@ -419,7 +412,11 @@ class YnlFamily(SpecFamily): def _decode_binary(self, attr, attr_spec): if attr_spec.struct_name: - decoded = attr.as_struct(self.consts[attr_spec.struct_name]) + members = self.consts[attr_spec.struct_name] + decoded = attr.as_struct(members) + for m in members: + if m.enum: + self._decode_enum(decoded, m) elif attr_spec.sub_type: decoded = attr.as_c_array(attr_spec.sub_type) else: @@ -434,22 +431,16 @@ class YnlFamily(SpecFamily): if attr_spec["type"] == 'nest': subdict = self._decode(NlAttrs(attr.raw), attr_spec['nested-attributes']) decoded = subdict - elif attr_spec['type'] == 'u8': - decoded = attr.as_u8() - elif attr_spec['type'] == 'u16': - decoded = attr.as_u16(attr_spec.byte_order) - elif attr_spec['type'] == 'u32': - decoded = attr.as_u32(attr_spec.byte_order) - elif attr_spec['type'] == 'u64': - decoded = attr.as_u64(attr_spec.byte_order) elif attr_spec["type"] == 'string': decoded = attr.as_strz() elif attr_spec["type"] == 'binary': decoded = self._decode_binary(attr, attr_spec) elif attr_spec["type"] == 'flag': decoded = True + elif attr_spec["type"] in NlAttr.type_formats: + decoded = attr.as_scalar(attr_spec['type'], attr_spec.byte_order) else: - raise Exception(f'Unknown {attr.type} {attr_spec["name"]} {attr_spec["type"]}') + raise Exception(f'Unknown {attr_spec["type"]} with name {attr_spec["name"]}') if not attr_spec.is_multi: rsp[attr_spec['name']] = decoded @@ -554,9 +545,9 @@ class YnlFamily(SpecFamily): if op.fixed_header: fixed_header_members = self.consts[op.fixed_header].members for m in fixed_header_members: - value = vals.pop(m.name) - format, _ = NlAttr.type_formats[m.type] - msg += struct.pack(format, value) + value = vals.pop(m.name) if m.name in vals else 0 + format = NlAttr.get_format(m.type, m.byte_order) + msg += format.pack(value) for name, value in vals.items(): msg += self._add_attr(op.attr_set.name, name, value) msg = _genl_msg_finalize(msg) @@ -591,8 +582,9 @@ class YnlFamily(SpecFamily): print('Unexpected message: ' + repr(gm)) continue - rsp.append(self._decode(gm.raw_attrs, op.attr_set.name) - | gm.fixed_header_attrs) + rsp_msg = self._decode(gm.raw_attrs, op.attr_set.name) + rsp_msg.update(gm.fixed_header_attrs) + rsp.append(rsp_msg) if not rsp: return None diff --git a/tools/net/ynl/samples/.gitignore b/tools/net/ynl/samples/.gitignore new file mode 100644 index 000000000000..a24678b67557 --- /dev/null +++ b/tools/net/ynl/samples/.gitignore @@ -0,0 +1,2 @@ +devlink +netdev diff --git a/tools/net/ynl/samples/Makefile b/tools/net/ynl/samples/Makefile new file mode 100644 index 000000000000..714316cad45f --- /dev/null +++ b/tools/net/ynl/samples/Makefile @@ -0,0 +1,28 @@ +# SPDX-License-Identifier: GPL-2.0 + +CC=gcc +CFLAGS=-std=gnu11 -O2 -W -Wall -Wextra -Wno-unused-parameter -Wshadow \ + -I../lib/ -I../generated/ +ifeq ("$(DEBUG)","1") + CFLAGS += -g -fsanitize=address -fsanitize=leak -static-libasan +endif + +LDLIBS=-lmnl ../lib/ynl.a ../generated/protos.a + +SRCS=$(wildcard *.c) +BINS=$(patsubst %.c,%,${SRCS}) + +include $(wildcard *.d) + +all: $(BINS) + +$(BINS): ../lib/ynl.a ../generated/protos.a + +clean: + rm -f *.o *.d *~ + +hardclean: clean + rm -f $(BINS) + +.PHONY: all clean +.DEFAULT_GOAL=all diff --git a/tools/net/ynl/samples/devlink.c b/tools/net/ynl/samples/devlink.c new file mode 100644 index 000000000000..d2611d7ebab4 --- /dev/null +++ b/tools/net/ynl/samples/devlink.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <string.h> + +#include <ynl.h> + +#include "devlink-user.h" + +int main(int argc, char **argv) +{ + struct devlink_get_list *devs; + struct ynl_sock *ys; + + ys = ynl_sock_create(&ynl_devlink_family, NULL); + if (!ys) + return 1; + + devs = devlink_get_dump(ys); + if (!devs) + goto err_close; + + ynl_dump_foreach(devs, d) { + struct devlink_info_get_req *info_req; + struct devlink_info_get_rsp *info_rsp; + + printf("%s/%s:\n", d->bus_name, d->dev_name); + + info_req = devlink_info_get_req_alloc(); + devlink_info_get_req_set_bus_name(info_req, d->bus_name); + devlink_info_get_req_set_dev_name(info_req, d->dev_name); + + info_rsp = devlink_info_get(ys, info_req); + devlink_info_get_req_free(info_req); + if (!info_rsp) + goto err_free_devs; + + if (info_rsp->_present.info_driver_name_len) + printf(" driver: %s\n", info_rsp->info_driver_name); + if (info_rsp->n_info_version_running) + printf(" running fw:\n"); + for (unsigned i = 0; i < info_rsp->n_info_version_running; i++) + printf(" %s: %s\n", + info_rsp->info_version_running[i].info_version_name, + info_rsp->info_version_running[i].info_version_value); + printf(" ...\n"); + devlink_info_get_rsp_free(info_rsp); + } + devlink_get_list_free(devs); + + ynl_sock_destroy(ys); + + return 0; + +err_free_devs: + devlink_get_list_free(devs); +err_close: + fprintf(stderr, "YNL: %s\n", ys->err.msg); + ynl_sock_destroy(ys); + return 2; +} diff --git a/tools/net/ynl/samples/netdev.c b/tools/net/ynl/samples/netdev.c new file mode 100644 index 000000000000..d31268aa47c5 --- /dev/null +++ b/tools/net/ynl/samples/netdev.c @@ -0,0 +1,108 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <string.h> + +#include <ynl.h> + +#include <net/if.h> + +#include "netdev-user.h" + +/* netdev genetlink family code sample + * This sample shows off basics of the netdev family but also notification + * handling, hence the somewhat odd UI. We subscribe to notifications first + * then wait for ifc selection, so the socket may already accumulate + * notifications as we wait. This allows us to test that YNL can handle + * requests and notifications getting interleaved. + */ + +static void netdev_print_device(struct netdev_dev_get_rsp *d, unsigned int op) +{ + char ifname[IF_NAMESIZE]; + const char *name; + + if (!d->_present.ifindex) + return; + + name = if_indextoname(d->ifindex, ifname); + if (name) + printf("%8s", name); + printf("[%d]\t", d->ifindex); + + if (!d->_present.xdp_features) + return; + + printf("%llx:", d->xdp_features); + for (int i = 0; d->xdp_features > 1U << i; i++) { + if (d->xdp_features & (1U << i)) + printf(" %s", netdev_xdp_act_str(1 << i)); + } + + name = netdev_op_str(op); + if (name) + printf(" (ntf: %s)", name); + printf("\n"); +} + +int main(int argc, char **argv) +{ + struct netdev_dev_get_list *devs; + struct ynl_ntf_base_type *ntf; + struct ynl_error yerr; + struct ynl_sock *ys; + int ifindex = 0; + + if (argc > 1) + ifindex = strtol(argv[1], NULL, 0); + + ys = ynl_sock_create(&ynl_netdev_family, &yerr); + if (!ys) { + fprintf(stderr, "YNL: %s\n", yerr.msg); + return 1; + } + + if (ynl_subscribe(ys, "mgmt")) + goto err_close; + + printf("Select ifc ($ifindex; or 0 = dump; or -2 ntf check): "); + scanf("%d", &ifindex); + + if (ifindex > 0) { + struct netdev_dev_get_req *req; + struct netdev_dev_get_rsp *d; + + req = netdev_dev_get_req_alloc(); + netdev_dev_get_req_set_ifindex(req, ifindex); + + d = netdev_dev_get(ys, req); + netdev_dev_get_req_free(req); + if (!d) + goto err_close; + + netdev_print_device(d, 0); + netdev_dev_get_rsp_free(d); + } else if (!ifindex) { + devs = netdev_dev_get_dump(ys); + if (!devs) + goto err_close; + + ynl_dump_foreach(devs, d) + netdev_print_device(d, 0); + netdev_dev_get_list_free(devs); + } else if (ifindex == -2) { + ynl_ntf_check(ys); + } + while ((ntf = ynl_ntf_dequeue(ys))) { + netdev_print_device((struct netdev_dev_get_rsp *)&ntf->data, + ntf->cmd); + ynl_ntf_free(ntf); + } + + ynl_sock_destroy(ys); + return 0; + +err_close: + fprintf(stderr, "YNL: %s\n", ys->err.msg); + ynl_sock_destroy(ys); + return 2; +} diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py index cc2f8c945340..7b051c00cfc3 100755 --- a/tools/net/ynl/ynl-gen-c.py +++ b/tools/net/ynl/ynl-gen-c.py @@ -94,7 +94,10 @@ class Type(SpecAttr): def arg_member(self, ri): member = self._complex_member_type(ri) if member: - return [member + ' *' + self.c_name] + arg = [member + ' *' + self.c_name] + if self.presence_type() == 'count': + arg += ['unsigned int n_' + self.c_name] + return arg raise Exception(f"Struct member not implemented for class type {self.type}") def struct_member(self, ri): @@ -150,7 +153,7 @@ class Type(SpecAttr): init_lines = [init_lines] kw = 'if' if first else 'else if' - ri.cw.block_start(line=f"{kw} (mnl_attr_get_type(attr) == {self.enum_name})") + ri.cw.block_start(line=f"{kw} (type == {self.enum_name})") if local_vars: for local in local_vars: ri.cw.p(local) @@ -170,6 +173,7 @@ class Type(SpecAttr): for line in lines: ri.cw.p(line) ri.cw.block_end() + return True def _setter_lines(self, ri, member, presence): raise Exception(f"Setter not implemented for class type {self.type}") @@ -187,9 +191,12 @@ class Type(SpecAttr): code.append(presence + ' = 1;') code += self._setter_lines(ri, member, presence) - ri.cw.write_func('static inline void', - f"{op_prefix(ri, direction, deref=deref)}_set_{'_'.join(ref)}", - body=code, + func_name = f"{op_prefix(ri, direction, deref=deref)}_set_{'_'.join(ref)}" + free = bool([x for x in code if 'free(' in x]) + alloc = bool([x for x in code if 'alloc(' in x]) + if free and not alloc: + func_name = '__' + func_name + ri.cw.write_func('static inline void', func_name, body=code, args=[f'{type_name(ri, direction, deref=deref)} *{var}'] + self.arg_member(ri)) @@ -197,6 +204,12 @@ class TypeUnused(Type): def presence_type(self): return '' + def arg_member(self, ri): + return [] + + def _attr_get(self, ri, var): + return ['return MNL_CB_ERROR;'], None, None + def _attr_typol(self): return '.type = YNL_PT_REJECT, ' @@ -208,12 +221,24 @@ class TypePad(Type): def presence_type(self): return '' + def arg_member(self, ri): + return [] + def _attr_typol(self): - return '.type = YNL_PT_REJECT, ' + return '.type = YNL_PT_IGNORE, ' + + def attr_put(self, ri, var): + pass + + def attr_get(self, ri, var, first): + pass def attr_policy(self, cw): pass + def setter(self, ri, space, direction, deref=False, ref=None): + pass + class TypeScalar(Type): def __init__(self, family, attr_set, attr, value): @@ -411,7 +436,8 @@ class TypeNest(Type): f"{self.enum_name}, &{var}->{self.c_name})") def _attr_get(self, ri, var): - get_lines = [f"{self.nested_render_name}_parse(&parg, attr);"] + get_lines = [f"if ({self.nested_render_name}_parse(&parg, attr))", + "return MNL_CB_ERROR;"] init_lines = [f"parg.rsp_policy = &{self.nested_render_name}_nest;", f"parg.data = &{var}->{self.c_name};"] return get_lines, init_lines, None @@ -430,6 +456,13 @@ class TypeMultiAttr(Type): def presence_type(self): return 'count' + def _mnl_type(self): + t = self.type + # mnl does not have a helper for signed types + if t[0] == 's': + t = 'u' + t[1:] + return t + def _complex_member_type(self, ri): if 'type' not in self.attr or self.attr['type'] == 'nest': return f"struct {self.nested_render_name}" @@ -443,9 +476,14 @@ class TypeMultiAttr(Type): return 'type' not in self.attr or self.attr['type'] == 'nest' def free(self, ri, var, ref): - if 'type' not in self.attr or self.attr['type'] == 'nest': + if self.attr['type'] in scalars: + ri.cw.p(f"free({var}->{ref}{self.c_name});") + elif 'type' not in self.attr or self.attr['type'] == 'nest': ri.cw.p(f"for (i = 0; i < {var}->{ref}n_{self.c_name}; i++)") ri.cw.p(f'{self.nested_render_name}_free(&{var}->{ref}{self.c_name}[i]);') + ri.cw.p(f"free({var}->{ref}{self.c_name});") + else: + raise Exception(f"Free of MultiAttr sub-type {self.attr['type']} not supported yet") def _attr_typol(self): if 'type' not in self.attr or self.attr['type'] == 'nest': @@ -456,7 +494,26 @@ class TypeMultiAttr(Type): raise Exception(f"Sub-type {self.attr['type']} not supported yet") def _attr_get(self, ri, var): - return f'{var}->n_{self.c_name}++;', None, None + return f'n_{self.c_name}++;', None, None + + def attr_put(self, ri, var): + if self.attr['type'] in scalars: + put_type = self._mnl_type() + ri.cw.p(f"for (unsigned int i = 0; i < {var}->n_{self.c_name}; i++)") + ri.cw.p(f"mnl_attr_put_{put_type}(nlh, {self.enum_name}, {var}->{self.c_name}[i]);") + elif 'type' not in self.attr or self.attr['type'] == 'nest': + ri.cw.p(f"for (unsigned int i = 0; i < {var}->n_{self.c_name}; i++)") + self._attr_put_line(ri, var, f"{self.nested_render_name}_put(nlh, " + + f"{self.enum_name}, &{var}->{self.c_name}[i])") + else: + raise Exception(f"Put of MultiAttr sub-type {self.attr['type']} not supported yet") + + def _setter_lines(self, ri, member, presence): + # For multi-attr we have a count, not presence, hack up the presence + presence = presence[:-(len('_present.') + len(self.c_name))] + "n_" + self.c_name + return [f"free({member});", + f"{member} = {self.c_name};", + f"{presence} = n_{self.c_name};"] class TypeArrayNest(Type): @@ -658,14 +715,13 @@ class Operation(SpecOperation): def __init__(self, family, yaml, req_value, rsp_value): super().__init__(family, yaml, req_value, rsp_value) - if req_value != rsp_value: - raise Exception("Directional messages not supported by codegen") - self.render_name = family.name + '_' + c_lower(self.name) self.dual_policy = ('do' in yaml and 'request' in yaml['do']) and \ ('dump' in yaml and 'request' in yaml['dump']) + self.has_ntf = False + # Added by resolve: self.enum_name = None delattr(self, "enum_name") @@ -678,12 +734,8 @@ class Operation(SpecOperation): else: self.enum_name = self.family.async_op_prefix + c_upper(self.name) - def add_notification(self, op): - if 'notify' not in self.yaml: - self.yaml['notify'] = dict() - self.yaml['notify']['reply'] = self.yaml['do']['reply'] - self.yaml['notify']['cmds'] = [] - self.yaml['notify']['cmds'].append(op) + def mark_has_ntf(self): + self.has_ntf = True class Family(SpecFamily): @@ -745,14 +797,12 @@ class Family(SpecFamily): self.root_sets = dict() # dict space-name -> set('request', 'reply') self.pure_nested_structs = dict() - self.all_notify = dict() + self._mark_notify() self._mock_up_events() - self._dictify() self._load_root_sets() self._load_nested_sets() - self._load_all_notify() self._load_hooks() self.kernel_policy = self.yaml.get('kernel-policy', 'split') @@ -768,6 +818,11 @@ class Family(SpecFamily): def new_operation(self, elem, req_value, rsp_value): return Operation(self, elem, req_value, rsp_value) + def _mark_notify(self): + for op in self.msgs.values(): + if 'notify' in op: + self.ops[op['notify']].mark_has_ntf() + # Fake a 'do' equivalent of all events, so that we can render their response parsing def _mock_up_events(self): for op in self.yaml['operations']['list']: @@ -778,16 +833,8 @@ class Family(SpecFamily): } } - def _dictify(self): - ntf = [] - for msg in self.msgs.values(): - if 'notify' in msg: - ntf.append(msg) - for n in ntf: - self.ops[n['notify']].add_notification(n) - def _load_root_sets(self): - for op_name, op in self.ops.items(): + for op_name, op in self.msgs.items(): if 'attribute-set' not in op: continue @@ -798,6 +845,8 @@ class Family(SpecFamily): req_attrs.update(set(op[op_mode]['request']['attributes'])) if op_mode in op and 'reply' in op[op_mode]: rsp_attrs.update(set(op[op_mode]['reply']['attributes'])) + if 'event' in op: + rsp_attrs.update(set(op['event']['attributes'])) if op['attribute-set'] not in self.root_sets: self.root_sets[op['attribute-set']] = {'request': req_attrs, 'reply': rsp_attrs} @@ -806,33 +855,73 @@ class Family(SpecFamily): self.root_sets[op['attribute-set']]['reply'].update(rsp_attrs) def _load_nested_sets(self): + attr_set_queue = list(self.root_sets.keys()) + attr_set_seen = set(self.root_sets.keys()) + + while len(attr_set_queue): + a_set = attr_set_queue.pop(0) + for attr, spec in self.attr_sets[a_set].items(): + if 'nested-attributes' not in spec: + continue + + nested = spec['nested-attributes'] + if nested not in attr_set_seen: + attr_set_queue.append(nested) + attr_set_seen.add(nested) + + inherit = set() + if nested not in self.root_sets: + if nested not in self.pure_nested_structs: + self.pure_nested_structs[nested] = Struct(self, nested, inherited=inherit) + else: + raise Exception(f'Using attr set as root and nested not supported - {nested}') + + if 'type-value' in spec: + if nested in self.root_sets: + raise Exception("Inheriting members to a space used as root not supported") + inherit.update(set(spec['type-value'])) + elif spec['type'] == 'array-nest': + inherit.add('idx') + self.pure_nested_structs[nested].set_inherited(inherit) + for root_set, rs_members in self.root_sets.items(): for attr, spec in self.attr_sets[root_set].items(): if 'nested-attributes' in spec: - inherit = set() nested = spec['nested-attributes'] - if nested not in self.root_sets: - self.pure_nested_structs[nested] = Struct(self, nested, inherited=inherit) if attr in rs_members['request']: self.pure_nested_structs[nested].request = True if attr in rs_members['reply']: self.pure_nested_structs[nested].reply = True - if 'type-value' in spec: - if nested in self.root_sets: - raise Exception("Inheriting members to a space used as root not supported") - inherit.update(set(spec['type-value'])) - elif spec['type'] == 'array-nest': - inherit.add('idx') - self.pure_nested_structs[nested].set_inherited(inherit) - - def _load_all_notify(self): - for op_name, op in self.ops.items(): - if not op: - continue - - if 'notify' in op: - self.all_notify[op_name] = op['notify']['cmds'] + # Try to reorder according to dependencies + pns_key_list = list(self.pure_nested_structs.keys()) + pns_key_seen = set() + rounds = len(pns_key_list)**2 # it's basically bubble sort + for _ in range(rounds): + if len(pns_key_list) == 0: + break + name = pns_key_list.pop(0) + finished = True + for _, spec in self.attr_sets[name].items(): + if 'nested-attributes' in spec: + if spec['nested-attributes'] not in pns_key_seen: + # Dicts are sorted, this will make struct last + struct = self.pure_nested_structs.pop(name) + self.pure_nested_structs[name] = struct + finished = False + break + if finished: + pns_key_seen.add(name) + else: + pns_key_list.append(name) + # Propagate the request / reply + for attr_set, struct in reversed(self.pure_nested_structs.items()): + for _, spec in self.attr_sets[attr_set].items(): + if 'nested-attributes' in spec: + child = self.pure_nested_structs.get(spec['nested-attributes']) + if child: + child.request |= struct.request + child.reply |= struct.reply def _load_global_policy(self): global_set = set() @@ -874,33 +963,35 @@ class Family(SpecFamily): class RenderInfo: - def __init__(self, cw, family, ku_space, op, op_name, op_mode, attr_set=None): + def __init__(self, cw, family, ku_space, op, op_mode, attr_set=None): self.family = family self.nl = cw.nlib self.ku_space = ku_space - self.op = op - self.op_name = op_name self.op_mode = op_mode + self.op = op # 'do' and 'dump' response parsing is identical - if op_mode != 'do' and 'dump' in op and 'do' in op and 'reply' in op['do'] and \ - op["do"]["reply"] == op["dump"]["reply"]: - self.type_consistent = True - else: - self.type_consistent = op_mode == 'event' + self.type_consistent = True + if op_mode != 'do' and 'dump' in op and 'do' in op: + if ('reply' in op['do']) != ('reply' in op["dump"]): + self.type_consistent = False + elif 'reply' in op['do'] and op["do"]["reply"] != op["dump"]["reply"]: + self.type_consistent = False self.attr_set = attr_set if not self.attr_set: self.attr_set = op['attribute-set'] if op: - self.type_name = c_lower(op_name) + self.type_name = c_lower(op.name) else: self.type_name = c_lower(attr_set) self.cw = cw self.struct = dict() + if op_mode == 'notify': + op_mode = 'do' for op_dir in ['request', 'reply']: if op and op_dir in op[op_mode]: self.struct[op_dir] = Struct(family, self.attr_set, @@ -914,6 +1005,7 @@ class CodeWriter: self.nlib = nlib self._nl = False + self._block_end = False self._silent_block = False self._ind = 0 self._out = out_file @@ -923,9 +1015,17 @@ class CodeWriter: return line.startswith('if') or line.startswith('while') or line.startswith('for') def p(self, line, add_ind=0): + if self._block_end: + self._block_end = False + if line.startswith('else'): + line = '} ' + line + else: + self._out.write('\t' * self._ind + '}\n') + if self._nl: self._out.write('\n') self._nl = False + ind = self._ind if line[-1] == ':': ind -= 1 @@ -949,7 +1049,14 @@ class CodeWriter: if line and line[0] not in {';', ','}: line = ' ' + line self._ind -= 1 - self.p('}' + line) + self._nl = False + if not line: + # Delay printing closing bracket in case "else" comes next + if self._block_end: + self._out.write('\t' * (self._ind + 1) + '}\n') + self._block_end = True + else: + self.p('}' + line) def write_doc_line(self, doc, indent=True): words = doc.split() @@ -1068,7 +1175,40 @@ op_mode_to_wrapper = { } _C_KW = { - 'do' + 'auto', + 'bool', + 'break', + 'case', + 'char', + 'const', + 'continue', + 'default', + 'do', + 'double', + 'else', + 'enum', + 'extern', + 'float', + 'for', + 'goto', + 'if', + 'inline', + 'int', + 'long', + 'register', + 'return', + 'short', + 'signed', + 'sizeof', + 'static', + 'struct', + 'switch', + 'typedef', + 'union', + 'unsigned', + 'void', + 'volatile', + 'while' } @@ -1131,10 +1271,6 @@ def print_dump_prototype(ri): print_prototype(ri, "request") -def put_typol_fwd(cw, struct): - cw.p(f'extern struct ynl_policy_nest {struct.render_name}_nest;') - - def put_typol(cw, struct): type_max = struct.attr_set.max_name cw.block_start(line=f'struct ynl_policy_attr {struct.render_name}_policy[{type_max} + 1] =') @@ -1152,6 +1288,58 @@ def put_typol(cw, struct): cw.nl() +def _put_enum_to_str_helper(cw, render_name, map_name, arg_name, enum=None): + args = [f'int {arg_name}'] + if enum and not ('enum-name' in enum and not enum['enum-name']): + args = [f'enum {render_name} {arg_name}'] + cw.write_func_prot('const char *', f'{render_name}_str', args) + cw.block_start() + if enum and enum.type == 'flags': + cw.p(f'{arg_name} = ffs({arg_name}) - 1;') + cw.p(f'if ({arg_name} < 0 || {arg_name} >= (int)MNL_ARRAY_SIZE({map_name}))') + cw.p('return NULL;') + cw.p(f'return {map_name}[{arg_name}];') + cw.block_end() + cw.nl() + + +def put_op_name_fwd(family, cw): + cw.write_func_prot('const char *', f'{family.name}_op_str', ['int op'], suffix=';') + + +def put_op_name(family, cw): + map_name = f'{family.name}_op_strmap' + cw.block_start(line=f"static const char * const {map_name}[] =") + for op_name, op in family.msgs.items(): + if op.rsp_value: + if op.req_value == op.rsp_value: + cw.p(f'[{op.enum_name}] = "{op_name}",') + else: + cw.p(f'[{op.rsp_value}] = "{op_name}",') + cw.block_end(line=';') + cw.nl() + + _put_enum_to_str_helper(cw, family.name + '_op', map_name, 'op') + + +def put_enum_to_str_fwd(family, cw, enum): + args = [f'enum {enum.render_name} value'] + if 'enum-name' in enum and not enum['enum-name']: + args = ['int value'] + cw.write_func_prot('const char *', f'{enum.render_name}_str', args, suffix=';') + + +def put_enum_to_str(family, cw, enum): + map_name = f'{enum.render_name}_strmap' + cw.block_start(line=f"static const char * const {map_name}[] =") + for entry in enum.entries.values(): + cw.p(f'[{entry.value}] = "{entry.name}",') + cw.block_end(line=';') + cw.nl() + + _put_enum_to_str_helper(cw, enum.render_name, map_name, 'value', enum=enum) + + def put_req_nested(ri, struct): func_args = ['struct nlmsghdr *nlh', 'unsigned int attr_type', @@ -1196,6 +1384,11 @@ def _multi_parse(ri, struct, init_lines, local_vars): local_vars.append('struct ynl_parse_arg parg;') init_lines.append('parg.ys = yarg->ys;') + all_multi = array_nests | multi_attrs + + for anest in sorted(all_multi): + local_vars.append(f"unsigned int n_{struct[anest].c_name} = 0;") + ri.cw.block_start() ri.cw.write_func_lvar(local_vars) @@ -1206,13 +1399,21 @@ def _multi_parse(ri, struct, init_lines, local_vars): for arg in struct.inherited: ri.cw.p(f'dst->{arg} = {arg};') + for anest in sorted(all_multi): + aspec = struct[anest] + ri.cw.p(f"if (dst->{aspec.c_name})") + ri.cw.p(f'return ynl_error_parse(yarg, "attribute already present ({struct.attr_set.name}.{aspec.name})");') + ri.cw.nl() ri.cw.block_start(line=iter_line) + ri.cw.p('unsigned int type = mnl_attr_get_type(attr);') + ri.cw.nl() first = True for _, arg in struct.member_list(): - arg.attr_get(ri, 'dst', first=first) - first = False + good = arg.attr_get(ri, 'dst', first=first) + # First may be 'unused' or 'pad', ignore those + first &= not good ri.cw.block_end() ri.cw.nl() @@ -1220,8 +1421,9 @@ def _multi_parse(ri, struct, init_lines, local_vars): for anest in sorted(array_nests): aspec = struct[anest] - ri.cw.block_start(line=f"if (dst->n_{aspec.c_name})") - ri.cw.p(f"dst->{aspec.c_name} = calloc(dst->n_{aspec.c_name}, sizeof(*dst->{aspec.c_name}));") + ri.cw.block_start(line=f"if (n_{aspec.c_name})") + ri.cw.p(f"dst->{aspec.c_name} = calloc({aspec.c_name}, sizeof(*dst->{aspec.c_name}));") + ri.cw.p(f"dst->n_{aspec.c_name} = n_{aspec.c_name};") ri.cw.p('i = 0;') ri.cw.p(f"parg.rsp_policy = &{aspec.nested_render_name}_nest;") ri.cw.block_start(line=f"mnl_attr_for_each_nested(attr, attr_{aspec.c_name})") @@ -1235,8 +1437,9 @@ def _multi_parse(ri, struct, init_lines, local_vars): for anest in sorted(multi_attrs): aspec = struct[anest] - ri.cw.block_start(line=f"if (dst->n_{aspec.c_name})") - ri.cw.p(f"dst->{aspec.c_name} = calloc(dst->n_{aspec.c_name}, sizeof(*dst->{aspec.c_name}));") + ri.cw.block_start(line=f"if (n_{aspec.c_name})") + ri.cw.p(f"dst->{aspec.c_name} = calloc(n_{aspec.c_name}, sizeof(*dst->{aspec.c_name}));") + ri.cw.p(f"dst->n_{aspec.c_name} = n_{aspec.c_name};") ri.cw.p('i = 0;') if 'nested-attributes' in aspec: ri.cw.p(f"parg.rsp_policy = &{aspec.nested_render_name}_nest;") @@ -1304,13 +1507,13 @@ def print_req(ri): ret_err = '-1' direction = "request" local_vars = ['struct nlmsghdr *nlh;', - 'int len, err;'] + 'int err;'] if 'reply' in ri.op[ri.op_mode]: ret_ok = 'rsp' ret_err = 'NULL' local_vars += [f'{type_name(ri, rdir(direction))} *rsp;', - 'struct ynl_parse_arg yarg = { .ys = ys, };'] + 'struct ynl_req_state yrs = { .yarg = { .ys = ys, }, };'] print_prototype(ri, direction, terminate=False) ri.cw.block_start() @@ -1320,41 +1523,39 @@ def print_req(ri): ri.cw.p(f"ys->req_policy = &{ri.struct['request'].render_name}_nest;") if 'reply' in ri.op[ri.op_mode]: - ri.cw.p(f"yarg.rsp_policy = &{ri.struct['reply'].render_name}_nest;") + ri.cw.p(f"yrs.yarg.rsp_policy = &{ri.struct['reply'].render_name}_nest;") ri.cw.nl() for _, attr in ri.struct["request"].member_list(): attr.attr_put(ri, "req") ri.cw.nl() - ri.cw.p('err = mnl_socket_sendto(ys->sock, nlh, nlh->nlmsg_len);') - ri.cw.p('if (err < 0)') - ri.cw.p(f"return {ret_err};") - ri.cw.nl() - ri.cw.p('len = mnl_socket_recvfrom(ys->sock, ys->rx_buf, MNL_SOCKET_BUFFER_SIZE);') - ri.cw.p('if (len < 0)') - ri.cw.p(f"return {ret_err};") - ri.cw.nl() - + parse_arg = "NULL" if 'reply' in ri.op[ri.op_mode]: ri.cw.p('rsp = calloc(1, sizeof(*rsp));') - ri.cw.p('yarg.data = rsp;') + ri.cw.p('yrs.yarg.data = rsp;') + ri.cw.p(f"yrs.cb = {op_prefix(ri, 'reply')}_parse;") + if ri.op.value is not None: + ri.cw.p(f'yrs.rsp_cmd = {ri.op.enum_name};') + else: + ri.cw.p(f'yrs.rsp_cmd = {ri.op.rsp_value};') ri.cw.nl() - ri.cw.p(f"err = {ri.nl.parse_cb_run(op_prefix(ri, 'reply') + '_parse', '&yarg', False)};") - ri.cw.p('if (err < 0)') + parse_arg = '&yrs' + ri.cw.p(f"err = ynl_exec(ys, nlh, {parse_arg});") + ri.cw.p('if (err < 0)') + if 'reply' in ri.op[ri.op_mode]: ri.cw.p('goto err_free;') - ri.cw.nl() - - ri.cw.p('err = ynl_recv_ack(ys, err);') - ri.cw.p('if (err)') - ri.cw.p('goto err_free;') + else: + ri.cw.p('return -1;') ri.cw.nl() + ri.cw.p(f"return {ret_ok};") ri.cw.nl() - ri.cw.p('err_free:') if 'reply' in ri.op[ri.op_mode]: + ri.cw.p('err_free:') ri.cw.p(f"{call_free(ri, rdir(direction), 'rsp')}") - ri.cw.p(f"return {ret_err};") + ri.cw.p(f"return {ret_err};") + ri.cw.block_end() @@ -1364,7 +1565,7 @@ def print_dump(ri): ri.cw.block_start() local_vars = ['struct ynl_dump_state yds = {};', 'struct nlmsghdr *nlh;', - 'int len, err;'] + 'int err;'] for var in local_vars: ri.cw.p(f'{var}') @@ -1373,6 +1574,10 @@ def print_dump(ri): ri.cw.p('yds.ys = ys;') ri.cw.p(f"yds.alloc_sz = sizeof({type_name(ri, rdir(direction))});") ri.cw.p(f"yds.cb = {op_prefix(ri, 'reply', deref=True)}_parse;") + if ri.op.value is not None: + ri.cw.p(f'yds.rsp_cmd = {ri.op.enum_name};') + else: + ri.cw.p(f'yds.rsp_cmd = {ri.op.rsp_value};') ri.cw.p(f"yds.rsp_policy = &{ri.struct['reply'].render_name}_nest;") ri.cw.nl() ri.cw.p(f"nlh = ynl_gemsg_start_dump(ys, {ri.nl.get_family_id()}, {ri.op.enum_name}, 1);") @@ -1384,20 +1589,9 @@ def print_dump(ri): attr.attr_put(ri, "req") ri.cw.nl() - ri.cw.p('err = mnl_socket_sendto(ys->sock, nlh, nlh->nlmsg_len);') - ri.cw.p('if (err < 0)') - ri.cw.p('return NULL;') - ri.cw.nl() - - ri.cw.block_start(line='do') - ri.cw.p('len = mnl_socket_recvfrom(ys->sock, ys->rx_buf, MNL_SOCKET_BUFFER_SIZE);') - ri.cw.p('if (len < 0)') - ri.cw.p('goto free_list;') - ri.cw.nl() - ri.cw.p(f"err = {ri.nl.parse_cb_run('ynl_dump_trampoline', '&yds', False, indent=2)};") + ri.cw.p('err = ynl_exec_dump(ys, nlh, &yds);') ri.cw.p('if (err < 0)') ri.cw.p('goto free_list;') - ri.cw.block_end(line='while (err > 0);') ri.cw.nl() ri.cw.p('return yds.first;') @@ -1418,6 +1612,14 @@ def free_arg_name(direction): return 'obj' +def print_alloc_wrapper(ri, direction): + name = op_prefix(ri, direction) + ri.cw.write_func_prot(f'static inline struct {name} *', f"{name}_alloc", [f"void"]) + ri.cw.block_start() + ri.cw.p(f'return calloc(1, sizeof(struct {name}));') + ri.cw.block_end() + + def print_free_prototype(ri, direction, suffix=';'): name = op_prefix(ri, direction) arg = free_arg_name(direction) @@ -1465,6 +1667,7 @@ def print_type_full(ri, struct): def print_type_helpers(ri, direction, deref=False): print_free_prototype(ri, direction) + ri.cw.nl() if ri.ku_space == 'user' and direction == 'request': for _, attr in ri.struct[direction].member_list(): @@ -1473,6 +1676,7 @@ def print_type_helpers(ri, direction, deref=False): def print_req_type_helpers(ri): + print_alloc_wrapper(ri, "request") print_type_helpers(ri, "request") @@ -1496,6 +1700,12 @@ def print_req_type(ri): print_type(ri, "request") +def print_req_free(ri): + if 'request' not in ri.op[ri.op_mode]: + return + _free_type(ri, 'request', ri.struct['request']) + + def print_rsp_type(ri): if (ri.op_mode == 'do' or ri.op_mode == 'dump') and 'reply' in ri.op[ri.op_mode]: direction = 'reply' @@ -1513,6 +1723,7 @@ def print_wrapped_type(ri): elif ri.op_mode == 'notify' or ri.op_mode == 'event': ri.cw.p('__u16 family;') ri.cw.p('__u8 cmd;') + ri.cw.p('struct ynl_ntf_base_type *next;') ri.cw.p(f"void (*free)({type_name(ri, 'reply')} *ntf);") ri.cw.p(f"{type_name(ri, 'reply', deref=True)} obj __attribute__ ((aligned (8)));") ri.cw.block_end(line=';') @@ -1564,7 +1775,7 @@ def print_dump_type_free(ri): ri.cw.block_start() ri.cw.p(f"{sub_type} *next = rsp;") ri.cw.nl() - ri.cw.block_start(line='while (next)') + ri.cw.block_start(line='while ((void *)next != YNL_LIST_END)') _free_type_members_iter(ri, ri.struct['reply']) ri.cw.p('rsp = next;') ri.cw.p('next = rsp->next;') @@ -1587,70 +1798,6 @@ def print_ntf_type_free(ri): ri.cw.nl() -def print_ntf_parse_prototype(family, cw, suffix=';'): - cw.write_func_prot('struct ynl_ntf_base_type *', f"{family['name']}_ntf_parse", - ['struct ynl_sock *ys'], suffix=suffix) - - -def print_ntf_type_parse(family, cw, ku_mode): - print_ntf_parse_prototype(family, cw, suffix='') - cw.block_start() - cw.write_func_lvar(['struct genlmsghdr *genlh;', - 'struct nlmsghdr *nlh;', - 'struct ynl_parse_arg yarg = { .ys = ys, };', - 'struct ynl_ntf_base_type *rsp;', - 'int len, err;', - 'mnl_cb_t parse;']) - cw.p('len = mnl_socket_recvfrom(ys->sock, ys->rx_buf, MNL_SOCKET_BUFFER_SIZE);') - cw.p('if (len < (ssize_t)(sizeof(*nlh) + sizeof(*genlh)))') - cw.p('return NULL;') - cw.nl() - cw.p('nlh = (struct nlmsghdr *)ys->rx_buf;') - cw.p('genlh = mnl_nlmsg_get_payload(nlh);') - cw.nl() - cw.block_start(line='switch (genlh->cmd)') - for ntf_op in sorted(family.all_notify.keys()): - op = family.ops[ntf_op] - ri = RenderInfo(cw, family, ku_mode, op, ntf_op, "notify") - for ntf in op['notify']['cmds']: - cw.p(f"case {ntf.enum_name}:") - cw.p(f"rsp = calloc(1, sizeof({type_name(ri, 'notify')}));") - cw.p(f"parse = {op_prefix(ri, 'reply', deref=True)}_parse;") - cw.p(f"yarg.rsp_policy = &{ri.struct['reply'].render_name}_nest;") - cw.p(f"rsp->free = (void *){op_prefix(ri, 'notify')}_free;") - cw.p('break;') - for op_name, op in family.ops.items(): - if 'event' not in op: - continue - ri = RenderInfo(cw, family, ku_mode, op, op_name, "event") - cw.p(f"case {op.enum_name}:") - cw.p(f"rsp = calloc(1, sizeof({type_name(ri, 'event')}));") - cw.p(f"parse = {op_prefix(ri, 'reply', deref=True)}_parse;") - cw.p(f"yarg.rsp_policy = &{ri.struct['reply'].render_name}_nest;") - cw.p(f"rsp->free = (void *){op_prefix(ri, 'notify')}_free;") - cw.p('break;') - cw.p('default:') - cw.p('ynl_error_unknown_notification(ys, genlh->cmd);') - cw.p('return NULL;') - cw.block_end() - cw.nl() - cw.p('yarg.data = rsp->data;') - cw.nl() - cw.p(f"err = {cw.nlib.parse_cb_run('parse', '&yarg', True)};") - cw.p('if (err < 0)') - cw.p('goto err_free;') - cw.nl() - cw.p('rsp->family = nlh->nlmsg_type;') - cw.p('rsp->cmd = genlh->cmd;') - cw.p('return rsp;') - cw.nl() - cw.p('err_free:') - cw.p('free(rsp);') - cw.p('return NULL;') - cw.block_end() - cw.nl() - - def print_req_policy_fwd(cw, struct, ri=None, terminate=True): if terminate and ri and kernel_can_gen_family_struct(struct.family): return @@ -2035,6 +2182,48 @@ def render_uapi(family, cw): cw.p(f'#endif /* {hdr_prot} */') +def _render_user_ntf_entry(ri, op): + ri.cw.block_start(line=f"[{op.enum_name}] = ") + ri.cw.p(f".alloc_sz\t= sizeof({type_name(ri, 'event')}),") + ri.cw.p(f".cb\t\t= {op_prefix(ri, 'reply', deref=True)}_parse,") + ri.cw.p(f".policy\t\t= &{ri.struct['reply'].render_name}_nest,") + ri.cw.p(f".free\t\t= (void *){op_prefix(ri, 'notify')}_free,") + ri.cw.block_end(line=',') + + +def render_user_family(family, cw, prototype): + symbol = f'const struct ynl_family ynl_{family.c_name}_family' + if prototype: + cw.p(f'extern {symbol};') + return + + if family.ntfs: + cw.block_start(line=f"static const struct ynl_ntf_info {family['name']}_ntf_info[] = ") + for ntf_op_name, ntf_op in family.ntfs.items(): + if 'notify' in ntf_op: + op = family.ops[ntf_op['notify']] + ri = RenderInfo(cw, family, "user", op, "notify") + elif 'event' in ntf_op: + ri = RenderInfo(cw, family, "user", ntf_op, "event") + else: + raise Exception('Invalid notification ' + ntf_op_name) + _render_user_ntf_entry(ri, ntf_op) + for op_name, op in family.ops.items(): + if 'event' not in op: + continue + ri = RenderInfo(cw, family, "user", op, "event") + _render_user_ntf_entry(ri, op) + cw.block_end(line=";") + cw.nl() + + cw.block_start(f'{symbol} = ') + cw.p(f'.name\t\t= "{family.name}",') + if family.ntfs: + cw.p(f".ntf_info\t= {family['name']}_ntf_info,") + cw.p(f".ntf_info_size\t= MNL_ARRAY_SIZE({family['name']}_ntf_info),") + cw.block_end(line=';') + + def find_kernel_root(full_path): sub_path = '' while True: @@ -2071,6 +2260,13 @@ def main(): os.sys.exit(1) return + supported_models = ['unified'] + if args.mode == 'user': + supported_models += ['directional'] + if parsed.msg_id_model not in supported_models: + print(f'Message enum-model {parsed.msg_id_model} not supported for {args.mode} generation') + os.sys.exit(1) + cw = CodeWriter(BaseNlLib(), out_file) _, spec_kernel = find_kernel_root(args.spec) @@ -2101,7 +2297,16 @@ def main(): if args.out_file: cw.p(f'#include "{os.path.basename(args.out_file[:-2])}.h"') cw.nl() - headers = [parsed.uapi_header] + headers = ['uapi/' + parsed.uapi_header] + else: + cw.p('#include <stdlib.h>') + cw.p('#include <string.h>') + if args.header: + cw.p('#include <linux/types.h>') + else: + cw.p(f'#include "{parsed.name}-user.h"') + cw.p('#include "ynl.h"') + headers = [parsed.uapi_header] for definition in parsed['definitions']: if 'header' in definition: headers.append(definition['header']) @@ -2111,9 +2316,6 @@ def main(): if args.mode == "user": if not args.header: - cw.p("#include <stdlib.h>") - cw.p("#include <stdio.h>") - cw.p("#include <string.h>") cw.p("#include <libmnl/libmnl.h>") cw.p("#include <linux/genetlink.h>") cw.nl() @@ -2121,6 +2323,8 @@ def main(): cw.p(f'#include "{one}"') else: cw.p('struct ynl_sock;') + cw.nl() + render_user_family(parsed, cw, True) cw.nl() if args.mode == "kernel": @@ -2144,7 +2348,7 @@ def main(): if parsed.kernel_policy in {'per-op', 'split'}: for op_name, op in parsed.ops.items(): if 'do' in op and 'event' not in op: - ri = RenderInfo(cw, parsed, args.mode, op, op_name, "do") + ri = RenderInfo(cw, parsed, args.mode, op, "do") print_req_policy_fwd(cw, ri.struct['request'], ri=ri) cw.nl() @@ -2173,7 +2377,7 @@ def main(): for op_mode in ['do', 'dump']: if op_mode in op and 'request' in op[op_mode]: cw.p(f"/* {op.enum_name} - {op_mode} */") - ri = RenderInfo(cw, parsed, args.mode, op, op_name, op_mode) + ri = RenderInfo(cw, parsed, args.mode, op, op_mode) print_req_policy(cw, ri.struct['request'], ri=ri) cw.nl() @@ -2182,11 +2386,18 @@ def main(): print_kernel_family_struct_src(parsed, cw) if args.mode == "user": - has_ntf = False if args.header: + cw.p('/* Enums */') + put_op_name_fwd(parsed, cw) + + for name, const in parsed.consts.items(): + if isinstance(const, EnumSet): + put_enum_to_str_fwd(parsed, cw, const) + cw.nl() + cw.p('/* Common nested types */') - for attr_set, struct in sorted(parsed.pure_nested_structs.items()): - ri = RenderInfo(cw, parsed, args.mode, "", "", "", attr_set) + for attr_set, struct in parsed.pure_nested_structs.items(): + ri = RenderInfo(cw, parsed, args.mode, "", "", attr_set) print_type_full(ri, struct) for op_name, op in parsed.ops.items(): @@ -2194,7 +2405,7 @@ def main(): if 'do' in op and 'event' not in op: cw.p(f"/* {op.enum_name} - do */") - ri = RenderInfo(cw, parsed, args.mode, op, op_name, "do") + ri = RenderInfo(cw, parsed, args.mode, op, "do") print_req_type(ri) print_req_type_helpers(ri) cw.nl() @@ -2206,7 +2417,7 @@ def main(): if 'dump' in op: cw.p(f"/* {op.enum_name} - dump */") - ri = RenderInfo(cw, parsed, args.mode, op, op_name, 'dump') + ri = RenderInfo(cw, parsed, args.mode, op, 'dump') if 'request' in op['dump']: print_req_type(ri) print_req_type_helpers(ri) @@ -2216,39 +2427,41 @@ def main(): print_dump_prototype(ri) cw.nl() - if 'notify' in op: + if op.has_ntf: cw.p(f"/* {op.enum_name} - notify */") - ri = RenderInfo(cw, parsed, args.mode, op, op_name, 'notify') - has_ntf = True + ri = RenderInfo(cw, parsed, args.mode, op, 'notify') if not ri.type_consistent: - raise Exception('Only notifications with consistent types supported') + raise Exception(f'Only notifications with consistent types supported ({op.name})') print_wrapped_type(ri) + for op_name, op in parsed.ntfs.items(): if 'event' in op: - ri = RenderInfo(cw, parsed, args.mode, op, op_name, 'event') + ri = RenderInfo(cw, parsed, args.mode, op, 'event') cw.p(f"/* {op.enum_name} - event */") print_rsp_type(ri) cw.nl() print_wrapped_type(ri) - - if has_ntf: - cw.p('/* --------------- Common notification parsing --------------- */') - print_ntf_parse_prototype(parsed, cw) cw.nl() else: - cw.p('/* Policies */') - for name, _ in parsed.attr_sets.items(): - struct = Struct(parsed, name) - put_typol_fwd(cw, struct) + cw.p('/* Enums */') + put_op_name(parsed, cw) + + for name, const in parsed.consts.items(): + if isinstance(const, EnumSet): + put_enum_to_str(parsed, cw, const) cw.nl() - for name, _ in parsed.attr_sets.items(): + cw.p('/* Policies */') + for name in parsed.pure_nested_structs: + struct = Struct(parsed, name) + put_typol(cw, struct) + for name in parsed.root_sets: struct = Struct(parsed, name) put_typol(cw, struct) cw.p('/* Common nested types */') - for attr_set, struct in sorted(parsed.pure_nested_structs.items()): - ri = RenderInfo(cw, parsed, args.mode, "", "", "", attr_set) + for attr_set, struct in parsed.pure_nested_structs.items(): + ri = RenderInfo(cw, parsed, args.mode, "", "", attr_set) free_rsp_nested(ri, struct) if struct.request: @@ -2260,7 +2473,8 @@ def main(): cw.p(f"/* ============== {op.enum_name} ============== */") if 'do' in op and 'event' not in op: cw.p(f"/* {op.enum_name} - do */") - ri = RenderInfo(cw, parsed, args.mode, op, op_name, "do") + ri = RenderInfo(cw, parsed, args.mode, op, "do") + print_req_free(ri) print_rsp_free(ri) parse_rsp_msg(ri) print_req(ri) @@ -2268,34 +2482,31 @@ def main(): if 'dump' in op: cw.p(f"/* {op.enum_name} - dump */") - ri = RenderInfo(cw, parsed, args.mode, op, op_name, "dump") + ri = RenderInfo(cw, parsed, args.mode, op, "dump") if not ri.type_consistent: parse_rsp_msg(ri, deref=True) print_dump_type_free(ri) print_dump(ri) cw.nl() - if 'notify' in op: + if op.has_ntf: cw.p(f"/* {op.enum_name} - notify */") - ri = RenderInfo(cw, parsed, args.mode, op, op_name, 'notify') - has_ntf = True + ri = RenderInfo(cw, parsed, args.mode, op, 'notify') if not ri.type_consistent: - raise Exception('Only notifications with consistent types supported') + raise Exception(f'Only notifications with consistent types supported ({op.name})') print_ntf_type_free(ri) + for op_name, op in parsed.ntfs.items(): if 'event' in op: cw.p(f"/* {op.enum_name} - event */") - has_ntf = True - ri = RenderInfo(cw, parsed, args.mode, op, op_name, "do") + ri = RenderInfo(cw, parsed, args.mode, op, "do") parse_rsp_msg(ri) - ri = RenderInfo(cw, parsed, args.mode, op, op_name, "event") + ri = RenderInfo(cw, parsed, args.mode, op, "event") print_ntf_type_free(ri) - - if has_ntf: - cw.p('/* --------------- Common notification parsing --------------- */') - print_ntf_type_parse(parsed, cw, args.mode) + cw.nl() + render_user_family(parsed, cw, False) if args.header: cw.p(f'#endif /* {hdr_prot} */') diff --git a/tools/net/ynl/ynl-regen.sh b/tools/net/ynl/ynl-regen.sh index 74f5de1c2399..2a4525e2aa17 100755 --- a/tools/net/ynl/ynl-regen.sh +++ b/tools/net/ynl/ynl-regen.sh @@ -14,7 +14,7 @@ done KDIR=$(dirname $(dirname $(dirname $(dirname $(realpath $0))))) -files=$(git grep --files-with-matches '^/\* YNL-GEN \(kernel\|uapi\)') +files=$(git grep --files-with-matches '^/\* YNL-GEN \(kernel\|uapi\|user\)') for f in $files; do # params: 0 1 2 3 # $YAML YNL-GEN kernel $mode diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 4884520f954f..a794d9eca93d 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -216,6 +216,12 @@ ifeq ($(call get-executable,$(BISON)),) dummy := $(error Error: $(BISON) is missing on this system, please install it) endif +ifeq ($(BUILD_BPF_SKEL),1) + ifeq ($(call get-executable,$(CLANG)),) + dummy := $(error $(CLANG) is missing on this system, please install it to be able to build with BUILD_BPF_SKEL=1) + endif +endif + ifneq ($(OUTPUT),) ifeq ($(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\).\([0-9]\+\)/\1\2\3/g') \>\= 371), 1) BISON_FILE_PREFIX_MAP := --file-prefix-map=$(OUTPUT)= @@ -921,6 +927,7 @@ ifndef NO_DEMANGLE EXTLIBS += -lstdc++ CFLAGS += -DHAVE_CXA_DEMANGLE_SUPPORT CXXFLAGS += -DHAVE_CXA_DEMANGLE_SUPPORT + $(call detected,CONFIG_CXX_DEMANGLE) endif ifdef BUILD_NONDISTRO ifeq ($(filter -liberty,$(EXTLIBS)),) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index a42a6a99c2bc..f48794816d82 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -181,7 +181,6 @@ HOSTCC ?= gcc HOSTLD ?= ld HOSTAR ?= ar CLANG ?= clang -LLVM_STRIP ?= llvm-strip PKG_CONFIG = $(CROSS_COMPILE)pkg-config @@ -1057,15 +1056,33 @@ $(SKEL_TMP_OUT) $(LIBAPI_OUTPUT) $(LIBBPF_OUTPUT) $(LIBPERF_OUTPUT) $(LIBSUBCMD_ ifdef BUILD_BPF_SKEL BPFTOOL := $(SKEL_TMP_OUT)/bootstrap/bpftool -BPF_INCLUDE := -I$(SKEL_TMP_OUT)/.. -I$(LIBBPF_INCLUDE) +# Get Clang's default includes on this system, as opposed to those seen by +# '-target bpf'. This fixes "missing" files on some architectures/distros, +# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc. +# +# Use '-idirafter': Don't interfere with include mechanics except where the +# build would have failed anyways. +define get_sys_includes +$(shell $(1) $(2) -v -E - </dev/null 2>&1 \ + | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \ +$(shell $(1) $(2) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}') +endef + +ifneq ($(CROSS_COMPILE),) +CLANG_TARGET_ARCH = --target=$(notdir $(CROSS_COMPILE:%-=%)) +endif + +CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH)) +BPF_INCLUDE := -I$(SKEL_TMP_OUT)/.. -I$(LIBBPF_INCLUDE) $(CLANG_SYS_INCLUDES) +TOOLS_UAPI_INCLUDE := -I$(srctree)/tools/include/uapi $(BPFTOOL): | $(SKEL_TMP_OUT) $(Q)CFLAGS= $(MAKE) -C ../bpf/bpftool \ OUTPUT=$(SKEL_TMP_OUT)/ bootstrap $(SKEL_TMP_OUT)/%.bpf.o: util/bpf_skel/%.bpf.c $(LIBBPF) | $(SKEL_TMP_OUT) - $(QUIET_CLANG)$(CLANG) -g -O2 -target bpf -Wall -Werror $(BPF_INCLUDE) \ - -c $(filter util/bpf_skel/%.bpf.c,$^) -o $@ && $(LLVM_STRIP) -g $@ + $(QUIET_CLANG)$(CLANG) -g -O2 -target bpf -Wall -Werror $(BPF_INCLUDE) $(TOOLS_UAPI_INCLUDE) \ + -c $(filter util/bpf_skel/%.bpf.c,$^) -o $@ $(SKEL_OUT)/%.skel.h: $(SKEL_TMP_OUT)/%.bpf.o | $(BPFTOOL) $(QUIET_GENSKEL)$(BPFTOOL) gen skeleton $< > $@ diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 77cb03e6ff87..9ca040bfb1aa 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -78,9 +78,9 @@ static int cs_etm_validate_context_id(struct auxtrace_record *itr, char path[PATH_MAX]; int err; u32 val; - u64 contextid = - evsel->core.attr.config & - (perf_pmu__format_bits(&cs_etm_pmu->format, "contextid1") | + u64 contextid = evsel->core.attr.config & + (perf_pmu__format_bits(&cs_etm_pmu->format, "contextid") | + perf_pmu__format_bits(&cs_etm_pmu->format, "contextid1") | perf_pmu__format_bits(&cs_etm_pmu->format, "contextid2")); if (!contextid) @@ -114,8 +114,7 @@ static int cs_etm_validate_context_id(struct auxtrace_record *itr, * 0b00100 Maximum of 32-bit Context ID size. * All other values are reserved. */ - val = BMVAL(val, 5, 9); - if (!val || val != 0x4) { + if (BMVAL(val, 5, 9) != 0x4) { pr_err("%s: CONTEXTIDR_EL1 isn't supported, disable with %s/contextid1=0/\n", CORESIGHT_ETM_PMU_NAME, CORESIGHT_ETM_PMU_NAME); return -EINVAL; diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c index 860a8b42b4b5..a9623b128ece 100644 --- a/tools/perf/arch/arm/util/pmu.c +++ b/tools/perf/arch/arm/util/pmu.c @@ -12,7 +12,7 @@ #include "arm-spe.h" #include "hisi-ptt.h" #include "../../../util/pmu.h" -#include "../cs-etm.h" +#include "../../../util/cs-etm.h" struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c index d730666ab95d..80b9f6287fe2 100644 --- a/tools/perf/arch/arm64/util/header.c +++ b/tools/perf/arch/arm64/util/header.c @@ -29,8 +29,8 @@ static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus) char path[PATH_MAX]; FILE *file; - scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d"MIDR, - sysfs, cpus->map[cpu]); + scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d" MIDR, + sysfs, RC_CHK_ACCESS(cpus)->map[cpu].cpu); file = fopen(path, "r"); if (!file) { diff --git a/tools/perf/arch/arm64/util/pmu.c b/tools/perf/arch/arm64/util/pmu.c index fa143acb4c8d..ef1ed645097c 100644 --- a/tools/perf/arch/arm64/util/pmu.c +++ b/tools/perf/arch/arm64/util/pmu.c @@ -18,7 +18,7 @@ static struct perf_pmu *pmu__find_core_pmu(void) * The cpumap should cover all CPUs. Otherwise, some CPUs may * not support some events or have different event IDs. */ - if (pmu->cpus->nr != cpu__max_cpu().cpu) + if (RC_CHK_ACCESS(pmu->cpus)->nr != cpu__max_cpu().cpu) return NULL; return pmu; diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index 799147658dee..b68f47541169 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -449,7 +449,7 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self -# 447 reserved for memfd_secret +447 common memfd_secret sys_memfd_secret sys_memfd_secret 448 common process_mrelease sys_process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h index 50ae8bd58296..6188e19d3129 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h +++ b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h @@ -7,7 +7,3 @@ MEMCPY_FN(memcpy_orig, MEMCPY_FN(__memcpy, "x86-64-movsq", "movsq-based memcpy() in arch/x86/lib/memcpy_64.S") - -MEMCPY_FN(memcpy_erms, - "x86-64-movsb", - "movsb-based memcpy() in arch/x86/lib/memcpy_64.S") diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S index 6eb45a2aa8db..1b9fef7efcdc 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm.S +++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S @@ -2,7 +2,7 @@ /* Various wrappers to make the kernel .S file build in user-space: */ -// memcpy_orig and memcpy_erms are being defined as SYM_L_LOCAL but we need it +// memcpy_orig is being defined as SYM_L_LOCAL but we need it #define SYM_FUNC_START_LOCAL(name) \ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #define memcpy MEMCPY /* don't hide glibc's memcpy() */ diff --git a/tools/perf/bench/mem-memset-x86-64-asm-def.h b/tools/perf/bench/mem-memset-x86-64-asm-def.h index dac6d2b7c39b..247c72fdfb9d 100644 --- a/tools/perf/bench/mem-memset-x86-64-asm-def.h +++ b/tools/perf/bench/mem-memset-x86-64-asm-def.h @@ -7,7 +7,3 @@ MEMSET_FN(memset_orig, MEMSET_FN(__memset, "x86-64-stosq", "movsq-based memset() in arch/x86/lib/memset_64.S") - -MEMSET_FN(memset_erms, - "x86-64-stosb", - "movsb-based memset() in arch/x86/lib/memset_64.S") diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S index 6f093c483842..abd26c95f1aa 100644 --- a/tools/perf/bench/mem-memset-x86-64-asm.S +++ b/tools/perf/bench/mem-memset-x86-64-asm.S @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -// memset_orig and memset_erms are being defined as SYM_L_LOCAL but we need it +// memset_orig is being defined as SYM_L_LOCAL but we need it #define SYM_FUNC_START_LOCAL(name) \ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #define memset MEMSET /* don't hide glibc's memset() */ diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index 810e3376c7d6..f9906f52e4fa 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -1175,7 +1175,7 @@ int cmd_ftrace(int argc, const char **argv) OPT_BOOLEAN('b', "use-bpf", &ftrace.target.use_bpf, "Use BPF to measure function latency"), #endif - OPT_BOOLEAN('n', "--use-nsec", &ftrace.use_nsec, + OPT_BOOLEAN('n', "use-nsec", &ftrace.use_nsec, "Use nano-second histogram"), OPT_PARENT(common_options), }; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 006f522d0e7f..c57be48d65bb 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -3647,6 +3647,13 @@ static int process_stat_config_event(struct perf_session *session __maybe_unused union perf_event *event) { perf_event__read_stat_config(&stat_config, &event->stat_config); + + /* + * Aggregation modes are not used since post-processing scripts are + * supposed to take care of such requirements + */ + stat_config.aggr_mode = AGGR_NONE; + return 0; } diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index cc9fa48d636f..b9ad32f21e57 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -667,6 +667,13 @@ static enum counter_recovery stat_handle_error(struct evsel *counter) evsel_list->core.threads->err_thread = -1; return COUNTER_RETRY; } + } else if (counter->skippable) { + if (verbose > 0) + ui__warning("skipping event %s that kernel failed to open .\n", + evsel__name(counter)); + counter->supported = false; + counter->errored = true; + return COUNTER_SKIP; } evsel__open_strerror(counter, &target, errno, msg, sizeof(msg)); @@ -1890,15 +1897,28 @@ static int add_default_attributes(void) * caused by exposing latent bugs. This is fixed properly in: * https://lore.kernel.org/lkml/bff481ba-e60a-763f-0aa0-3ee53302c480@linux.intel.com/ */ - if (metricgroup__has_metric("TopdownL1") && !perf_pmu__has_hybrid() && - metricgroup__parse_groups(evsel_list, "TopdownL1", - /*metric_no_group=*/false, - /*metric_no_merge=*/false, - /*metric_no_threshold=*/true, - stat_config.user_requested_cpu_list, - stat_config.system_wide, - &stat_config.metric_events) < 0) - return -1; + if (metricgroup__has_metric("TopdownL1") && !perf_pmu__has_hybrid()) { + struct evlist *metric_evlist = evlist__new(); + struct evsel *metric_evsel; + + if (!metric_evlist) + return -1; + + if (metricgroup__parse_groups(metric_evlist, "TopdownL1", + /*metric_no_group=*/false, + /*metric_no_merge=*/false, + /*metric_no_threshold=*/true, + stat_config.user_requested_cpu_list, + stat_config.system_wide, + &stat_config.metric_events) < 0) + return -1; + + evlist__for_each_entry(metric_evlist, metric_evsel) { + metric_evsel->skippable = true; + } + evlist__splice_list_tail(evsel_list, &metric_evlist->core.entries); + evlist__delete(metric_evlist); + } /* Platform specific attrs */ if (evlist__add_default_attrs(evsel_list, default_null_attrs) < 0) diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json index 75d80e70e5cd..1f9047553942 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json @@ -133,6 +133,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. The rest of these subevents count backend stalls, in cycles, due to an outstanding request which is memory bound vs core bound. The subevents are not slot based events and therefore can not be precisely added or subtracted from the Backend_Bound_Aux subevents which are slot based.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -143,6 +144,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound_aux", "MetricThreshold": "tma_backend_bound_aux > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that UOPS must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. All of these subevents count backend stalls, in slots, due to a resource limitation. These are not cycle based events and therefore can not be precisely added or subtracted from the Backend_Bound subevents which are cycle based. These subevents are supplementary to Backend_Bound and can be used to analyze results from a resource perspective at allocation.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -153,6 +155,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -163,6 +166,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_base", "MetricThreshold": "tma_base > 0.6", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -182,6 +186,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -209,6 +214,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -255,6 +261,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -264,6 +271,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.15", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -291,6 +299,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -593,6 +602,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -611,6 +621,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -629,6 +640,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_ms_uops", "MetricThreshold": "tma_ms_uops > 0.05", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -729,6 +741,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_aux_group", "MetricName": "tma_resource_bound", "MetricThreshold": "tma_resource_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -739,6 +752,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.75", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -848,6 +862,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -858,6 +873,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -868,6 +884,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -919,6 +936,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1031,6 +1049,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1041,6 +1060,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1121,6 +1141,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1141,6 +1162,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. Sample with: UOPS_RETIRED.HEAVY", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2023,6 +2045,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2082,6 +2105,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2112,6 +2136,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2310,6 +2335,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json index 1a85d935c733..0402adbf7d92 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json @@ -98,6 +98,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. The rest of these subevents count backend stalls, in cycles, due to an outstanding request which is memory bound vs core bound. The subevents are not slot based events and therefore can not be precisely added or subtracted from the Backend_Bound_Aux subevents which are slot based.", "ScaleUnit": "100%" }, @@ -107,6 +108,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound_aux", "MetricThreshold": "tma_backend_bound_aux > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that UOPS must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. All of these subevents count backend stalls, in slots, due to a resource limitation. These are not cycle based events and therefore can not be precisely added or subtracted from the Backend_Bound subevents which are cycle based. These subevents are supplementary to Backend_Bound and can be used to analyze results from a resource perspective at allocation.", "ScaleUnit": "100%" }, @@ -116,6 +118,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "ScaleUnit": "100%" }, @@ -125,6 +128,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_base", "MetricThreshold": "tma_base > 0.6", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -142,6 +146,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -166,6 +171,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -207,6 +213,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -215,6 +222,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.15", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -239,6 +247,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%" }, { @@ -499,6 +508,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -515,6 +525,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -531,6 +542,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_ms_uops", "MetricThreshold": "tma_ms_uops > 0.05", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", "ScaleUnit": "100%" }, @@ -620,6 +632,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_aux_group", "MetricName": "tma_resource_bound", "MetricThreshold": "tma_resource_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count.", "ScaleUnit": "100%" }, @@ -629,6 +642,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.75", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json index 51cf8560a8d3..f9e2316601e1 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -170,6 +173,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -263,6 +267,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -272,6 +277,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -326,6 +332,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -335,6 +342,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -828,6 +836,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -858,6 +867,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -886,6 +896,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1048,6 +1059,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json index fb57c7382408..e9c46d336a8e 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json @@ -97,6 +97,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -106,6 +107,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -116,6 +118,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -164,6 +167,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -248,6 +252,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -257,6 +262,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -311,6 +317,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -320,6 +327,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -795,6 +803,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -825,6 +834,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -853,6 +863,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1013,6 +1024,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json index 65ec0c9e55d1..437b9867acb9 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -170,6 +173,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -263,6 +267,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -272,6 +277,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -326,6 +332,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -335,6 +342,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -829,6 +837,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -869,6 +878,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -897,6 +907,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1079,6 +1090,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json index 8f7dc72accd0..875c766222e3 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json @@ -101,6 +101,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -110,6 +111,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -120,6 +122,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -167,6 +170,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -271,6 +275,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -280,6 +285,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -354,6 +360,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -372,6 +379,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1142,6 +1150,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1196,6 +1205,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1224,6 +1234,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1458,6 +1469,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json index 2528418200bb..9570a88d6d1c 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -272,6 +278,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -281,6 +288,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -663,6 +671,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -693,6 +702,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -721,6 +731,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -874,6 +885,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json index 11f152c346eb..a522202cf684 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -272,6 +278,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -281,6 +288,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -664,6 +672,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -704,6 +713,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -732,6 +742,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -905,6 +916,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json index f45ae3483df4..1a2154f28b7b 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json @@ -115,6 +115,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -124,6 +125,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -141,6 +143,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -187,6 +190,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -288,6 +292,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -297,6 +302,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -369,6 +375,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -378,6 +385,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1111,6 +1119,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1164,6 +1173,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1191,6 +1201,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1360,6 +1371,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json index 0f9b174dfc22..1ef772b40e04 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json @@ -80,6 +80,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -89,6 +90,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -106,6 +108,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -152,6 +155,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -253,6 +257,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -262,6 +267,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -334,6 +340,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -343,6 +350,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1134,6 +1142,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1187,6 +1196,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1214,6 +1224,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1410,6 +1421,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json index 5247f69c13b6..11080ccffd51 100644 --- a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -299,6 +305,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -308,6 +315,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -724,6 +732,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -754,6 +763,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -782,6 +792,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -917,6 +928,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json index 89469b10fa30..65a46d659c0a 100644 --- a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -299,6 +305,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -308,6 +315,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -725,6 +733,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -765,6 +774,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -793,6 +803,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -948,6 +959,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json index e8f4e5c01c9f..66a6f657bd6f 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json @@ -76,6 +76,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -85,6 +86,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -95,6 +97,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -114,6 +117,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -160,6 +164,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_lcp", "ScaleUnit": "100%" }, @@ -169,6 +174,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -205,6 +211,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -214,6 +221,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -412,6 +420,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -422,6 +431,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -450,6 +460,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -487,6 +498,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json index 4a99fe515f4b..4b8bc19392a4 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json @@ -76,6 +76,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -85,6 +86,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -95,6 +97,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -114,6 +117,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -160,6 +164,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_lcp", "ScaleUnit": "100%" }, @@ -169,6 +174,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -205,6 +211,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -214,6 +221,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -411,6 +419,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -421,6 +430,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -449,6 +459,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -486,6 +497,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json index 126300b7ae77..620fc5bd2217 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json @@ -87,6 +87,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -96,6 +97,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -105,6 +107,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -151,6 +154,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -252,6 +256,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -261,6 +266,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -351,6 +357,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -369,6 +376,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. Sample with: UOPS_RETIRED.HEAVY", "ScaleUnit": "100%" }, @@ -1216,6 +1224,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1269,6 +1278,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1304,6 +1314,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1509,6 +1520,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json index a6d212b349f5..21ef6c9be816 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json @@ -101,6 +101,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -110,6 +111,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -120,6 +122,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -167,6 +170,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -271,6 +275,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -280,6 +285,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -345,6 +351,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -363,6 +370,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1065,6 +1073,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1110,6 +1119,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1138,6 +1148,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1343,6 +1354,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json index fa2f7f126a30..eb6f12c0343d 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json @@ -101,6 +101,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -110,6 +111,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -120,6 +122,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -167,6 +170,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -271,6 +275,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -280,6 +285,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -354,6 +360,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -372,6 +379,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1123,6 +1131,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1177,6 +1186,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1205,6 +1215,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1429,6 +1440,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json index 4c80d6be6cf1..b442ed4acfbb 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json @@ -109,6 +109,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -118,6 +119,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -135,6 +137,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -181,6 +184,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -282,6 +286,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -291,6 +296,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -363,6 +369,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -372,6 +379,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1125,6 +1133,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1178,6 +1187,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1205,6 +1215,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1374,6 +1385,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index ca99b9cfe4ad..f57a8f274025 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -52,7 +52,8 @@ _json_event_attributes = [ # Attributes that are in pmu_metric rather than pmu_event. _json_metric_attributes = [ 'metric_name', 'metric_group', 'metric_expr', 'metric_threshold', 'desc', - 'long_desc', 'unit', 'compat', 'aggr_mode', 'event_grouping' + 'long_desc', 'unit', 'compat', 'metricgroup_no_group', 'aggr_mode', + 'event_grouping' ] # Attributes that are bools or enum int values, encoded as '0', '1',... _json_enum_attributes = ['aggr_mode', 'deprecated', 'event_grouping', 'perpkg'] @@ -303,6 +304,7 @@ class JsonEvent: self.deprecated = jd.get('Deprecated') self.metric_name = jd.get('MetricName') self.metric_group = jd.get('MetricGroup') + self.metricgroup_no_group = jd.get('MetricgroupNoGroup') self.event_grouping = convert_metric_constraint(jd.get('MetricConstraint')) self.metric_expr = None if 'MetricExpr' in jd: diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h index b7dff8f1021f..80349685cf4d 100644 --- a/tools/perf/pmu-events/pmu-events.h +++ b/tools/perf/pmu-events/pmu-events.h @@ -59,6 +59,7 @@ struct pmu_metric { const char *compat; const char *desc; const char *long_desc; + const char *metricgroup_no_group; enum aggr_mode_class aggr_mode; enum metric_event_groups event_grouping; }; diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py index ccfef861e931..e890c261ad26 100644 --- a/tools/perf/tests/attr.py +++ b/tools/perf/tests/attr.py @@ -152,7 +152,7 @@ def parse_version(version): # - expected values assignments class Test(object): def __init__(self, path, options): - parser = configparser.SafeConfigParser() + parser = configparser.ConfigParser() parser.read(path) log.warning("running '%s'" % path) @@ -247,7 +247,7 @@ class Test(object): return True def load_events(self, path, events): - parser_event = configparser.SafeConfigParser() + parser_event = configparser.ConfigParser() parser_event.read(path) # The event record section header contains 'event' word, @@ -261,7 +261,7 @@ class Test(object): # Read parent event if there's any if (':' in section): base = section[section.index(':') + 1:] - parser_base = configparser.SafeConfigParser() + parser_base = configparser.ConfigParser() parser_base.read(self.test_dir + '/' + base) base_items = parser_base.items('event') diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat index a21fb65bc012..fccd8ec4d1b0 100644 --- a/tools/perf/tests/attr/base-stat +++ b/tools/perf/tests/attr/base-stat @@ -16,7 +16,7 @@ pinned=0 exclusive=0 exclude_user=0 exclude_kernel=0|1 -exclude_hv=0 +exclude_hv=0|1 exclude_idle=0 mmap=0 comm=0 diff --git a/tools/perf/tests/attr/test-stat-default b/tools/perf/tests/attr/test-stat-default index d8ea6a88163f..a1e2da0a9a6d 100644 --- a/tools/perf/tests/attr/test-stat-default +++ b/tools/perf/tests/attr/test-stat-default @@ -40,7 +40,6 @@ fd=6 type=0 config=7 optional=1 - # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND [event7:base-stat] fd=7 @@ -89,79 +88,98 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 +config=33280 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +# PERF_TYPE_RAW / topdown-be-bound (0x8300) [event14:base-stat] fd=14 group_fd=11 type=4 -config=33280 +config=33536 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-be-bound (0x8300) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) [event15:base-stat] fd=15 group_fd=11 type=4 -config=33536 +config=33024 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-1 b/tools/perf/tests/attr/test-stat-detailed-1 index b656ab93c5bf..1c52cb05c900 100644 --- a/tools/perf/tests/attr/test-stat-detailed-1 +++ b/tools/perf/tests/attr/test-stat-detailed-1 @@ -90,89 +90,108 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 +config=33280 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +# PERF_TYPE_RAW / topdown-be-bound (0x8300) [event14:base-stat] fd=14 group_fd=11 type=4 -config=33280 +config=33536 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-be-bound (0x8300) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) [event15:base-stat] fd=15 group_fd=11 type=4 -config=33536 +config=33024 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event20:base-stat] -fd=20 +[event25:base-stat] +fd=25 type=3 config=0 optional=1 @@ -181,8 +200,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event21:base-stat] -fd=21 +[event26:base-stat] +fd=26 type=3 config=65536 optional=1 @@ -191,8 +210,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event22:base-stat] -fd=22 +[event27:base-stat] +fd=27 type=3 config=2 optional=1 @@ -201,8 +220,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event23:base-stat] -fd=23 +[event28:base-stat] +fd=28 type=3 config=65538 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-2 b/tools/perf/tests/attr/test-stat-detailed-2 index 97625090a1c4..7e961d24a885 100644 --- a/tools/perf/tests/attr/test-stat-detailed-2 +++ b/tools/perf/tests/attr/test-stat-detailed-2 @@ -90,89 +90,108 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 +config=33280 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +# PERF_TYPE_RAW / topdown-be-bound (0x8300) [event14:base-stat] fd=14 group_fd=11 type=4 -config=33280 +config=33536 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-be-bound (0x8300) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) [event15:base-stat] fd=15 group_fd=11 type=4 -config=33536 +config=33024 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event20:base-stat] -fd=20 +[event25:base-stat] +fd=25 type=3 config=0 optional=1 @@ -181,8 +200,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event21:base-stat] -fd=21 +[event26:base-stat] +fd=26 type=3 config=65536 optional=1 @@ -191,8 +210,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event22:base-stat] -fd=22 +[event27:base-stat] +fd=27 type=3 config=2 optional=1 @@ -201,8 +220,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event23:base-stat] -fd=23 +[event28:base-stat] +fd=28 type=3 config=65538 optional=1 @@ -211,8 +230,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event24:base-stat] -fd=24 +[event29:base-stat] +fd=29 type=3 config=1 optional=1 @@ -221,8 +240,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event25:base-stat] -fd=25 +[event30:base-stat] +fd=30 type=3 config=65537 optional=1 @@ -231,8 +250,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event26:base-stat] -fd=26 +[event31:base-stat] +fd=31 type=3 config=3 optional=1 @@ -241,8 +260,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event27:base-stat] -fd=27 +[event32:base-stat] +fd=32 type=3 config=65539 optional=1 @@ -251,8 +270,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event28:base-stat] -fd=28 +[event33:base-stat] +fd=33 type=3 config=4 optional=1 @@ -261,8 +280,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event29:base-stat] -fd=29 +[event34:base-stat] +fd=34 type=3 config=65540 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-3 b/tools/perf/tests/attr/test-stat-detailed-3 index d555042e3fbf..e50535f45977 100644 --- a/tools/perf/tests/attr/test-stat-detailed-3 +++ b/tools/perf/tests/attr/test-stat-detailed-3 @@ -90,89 +90,108 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 +config=33280 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +# PERF_TYPE_RAW / topdown-be-bound (0x8300) [event14:base-stat] fd=14 group_fd=11 type=4 -config=33280 +config=33536 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-be-bound (0x8300) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) [event15:base-stat] fd=15 group_fd=11 type=4 -config=33536 +config=33024 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event20:base-stat] -fd=20 +[event25:base-stat] +fd=25 type=3 config=0 optional=1 @@ -181,8 +200,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event21:base-stat] -fd=21 +[event26:base-stat] +fd=26 type=3 config=65536 optional=1 @@ -191,8 +210,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event22:base-stat] -fd=22 +[event27:base-stat] +fd=27 type=3 config=2 optional=1 @@ -201,8 +220,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event23:base-stat] -fd=23 +[event28:base-stat] +fd=28 type=3 config=65538 optional=1 @@ -211,8 +230,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event24:base-stat] -fd=24 +[event29:base-stat] +fd=29 type=3 config=1 optional=1 @@ -221,8 +240,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event25:base-stat] -fd=25 +[event30:base-stat] +fd=30 type=3 config=65537 optional=1 @@ -231,8 +250,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event26:base-stat] -fd=26 +[event31:base-stat] +fd=31 type=3 config=3 optional=1 @@ -241,8 +260,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event27:base-stat] -fd=27 +[event32:base-stat] +fd=32 type=3 config=65539 optional=1 @@ -251,8 +270,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event28:base-stat] -fd=28 +[event33:base-stat] +fd=33 type=3 config=4 optional=1 @@ -261,8 +280,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event29:base-stat] -fd=29 +[event34:base-stat] +fd=34 type=3 config=65540 optional=1 @@ -271,8 +290,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event30:base-stat] -fd=30 +[event35:base-stat] +fd=35 type=3 config=512 optional=1 @@ -281,8 +300,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event31:base-stat] -fd=31 +[event36:base-stat] +fd=36 type=3 config=66048 optional=1 diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index cbf0e0c74906..733ead151c63 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -120,7 +120,8 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u p = "FOO/0"; ret = expr__parse(&val, ctx, p); - TEST_ASSERT_VAL("division by zero", ret == -1); + TEST_ASSERT_VAL("division by zero", ret == 0); + TEST_ASSERT_VAL("division by zero", isnan(val)); p = "BAR/"; ret = expr__parse(&val, ctx, p); diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index 1185b79e6274..c05148ea400c 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -38,6 +38,7 @@ static void load_runtime_stat(struct evlist *evlist, struct value *vals) evlist__alloc_aggr_stats(evlist, 1); evlist__for_each_entry(evlist, evsel) { count = find_value(evsel->name, vals); + evsel->supported = true; evsel->stats->aggr->counts.val = count; if (evsel__name_is(evsel, "duration_time")) update_stats(&walltime_nsecs_stats, count); diff --git a/tools/perf/tests/shell/stat.sh b/tools/perf/tests/shell/stat.sh index 2c1d3f704995..b154fbb15d54 100755 --- a/tools/perf/tests/shell/stat.sh +++ b/tools/perf/tests/shell/stat.sh @@ -28,6 +28,18 @@ test_stat_record_report() { echo "stat record and report test [Success]" } +test_stat_record_script() { + echo "stat record and script test" + if ! perf stat record -o - true | perf script -i - 2>&1 | \ + grep -E -q "CPU[[:space:]]+THREAD[[:space:]]+VAL[[:space:]]+ENA[[:space:]]+RUN[[:space:]]+TIME[[:space:]]+EVENT" + then + echo "stat record and script test [Failed]" + err=1 + return + fi + echo "stat record and script test [Success]" +} + test_stat_repeat_weak_groups() { echo "stat repeat weak groups test" if ! perf stat -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}' \ @@ -93,6 +105,7 @@ test_topdown_weak_groups() { test_default_stat test_stat_record_report +test_stat_record_script test_stat_repeat_weak_groups test_topdown_groups test_topdown_weak_groups diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh index 4ddb17cb83c5..3a8b9bffa022 100755 --- a/tools/perf/tests/shell/test_intel_pt.sh +++ b/tools/perf/tests/shell/test_intel_pt.sh @@ -506,6 +506,13 @@ test_sample() echo "perf record failed with --aux-sample" return 1 fi + # Check with event with PMU name + if perf_record_no_decode -o "${perfdatafile}" -e br_misp_retired.all_branches:u uname ; then + if ! perf_record_no_decode -o "${perfdatafile}" -e '{intel_pt//,br_misp_retired.all_branches/aux-sample-size=8192/}:u' uname ; then + echo "perf record failed with --aux-sample-size" + return 1 + fi + fi echo OK return 0 } diff --git a/tools/perf/tests/shell/test_java_symbol.sh b/tools/perf/tests/shell/test_java_symbol.sh index 90cea8811926..499539d1c479 100755 --- a/tools/perf/tests/shell/test_java_symbol.sh +++ b/tools/perf/tests/shell/test_java_symbol.sh @@ -56,7 +56,7 @@ if [ $? -ne 0 ]; then exit 1 fi -if ! perf inject -i $PERF_DATA -o $PERF_INJ_DATA -j; then +if ! DEBUGINFOD_URLS='' perf inject -i $PERF_DATA -o $PERF_INJ_DATA -j; then echo "Fail to inject samples" exit 1 fi diff --git a/tools/perf/trace/beauty/arch_prctl.c b/tools/perf/trace/beauty/arch_prctl.c index fe022ca67e60..a211348d3204 100644 --- a/tools/perf/trace/beauty/arch_prctl.c +++ b/tools/perf/trace/beauty/arch_prctl.c @@ -12,10 +12,12 @@ static DEFINE_STRARRAY_OFFSET(x86_arch_prctl_codes_1, "ARCH_", x86_arch_prctl_codes_1_offset); static DEFINE_STRARRAY_OFFSET(x86_arch_prctl_codes_2, "ARCH_", x86_arch_prctl_codes_2_offset); +static DEFINE_STRARRAY_OFFSET(x86_arch_prctl_codes_3, "ARCH_", x86_arch_prctl_codes_3_offset); static struct strarray *x86_arch_prctl_codes[] = { &strarray__x86_arch_prctl_codes_1, &strarray__x86_arch_prctl_codes_2, + &strarray__x86_arch_prctl_codes_3, }; static DEFINE_STRARRAYS(x86_arch_prctl_codes); diff --git a/tools/perf/trace/beauty/x86_arch_prctl.sh b/tools/perf/trace/beauty/x86_arch_prctl.sh index 57fa6aaffe70..fd5c740512c5 100755 --- a/tools/perf/trace/beauty/x86_arch_prctl.sh +++ b/tools/perf/trace/beauty/x86_arch_prctl.sh @@ -24,3 +24,4 @@ print_range () { print_range 1 0x1 0x1001 print_range 2 0x2 0x2001 +print_range 3 0x4 0x4001 diff --git a/tools/perf/util/Build b/tools/perf/util/Build index bd18fe5f2719..f9df1df1eec0 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -214,7 +214,7 @@ perf-$(CONFIG_ZSTD) += zstd.o perf-$(CONFIG_LIBCAP) += cap.o -perf-y += demangle-cxx.o +perf-$(CONFIG_CXX_DEMANGLE) += demangle-cxx.o perf-y += demangle-ocaml.o perf-y += demangle-java.o perf-y += demangle-rust.o diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index 8d3cfbb3cc65..1d48226ae75d 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -416,6 +416,8 @@ int contention_end(u64 *ctx) return 0; } +struct rq {}; + extern struct rq runqueues __ksym; struct rq___old { diff --git a/tools/perf/util/bpf_skel/sample_filter.bpf.c b/tools/perf/util/bpf_skel/sample_filter.bpf.c index cffe493af1ed..fb94f5280626 100644 --- a/tools/perf/util/bpf_skel/sample_filter.bpf.c +++ b/tools/perf/util/bpf_skel/sample_filter.bpf.c @@ -25,7 +25,7 @@ struct perf_sample_data___new { } __attribute__((preserve_access_index)); /* new kernel perf_mem_data_src definition */ -union perf_mem_data_src__new { +union perf_mem_data_src___new { __u64 val; struct { __u64 mem_op:5, /* type of opcode */ @@ -108,7 +108,7 @@ static inline __u64 perf_get_sample(struct bpf_perf_event_data_kern *kctx, if (entry->part == 7) return kctx->data->data_src.mem_blk; if (entry->part == 8) { - union perf_mem_data_src__new *data = (void *)&kctx->data->data_src; + union perf_mem_data_src___new *data = (void *)&kctx->data->data_src; if (bpf_core_field_exists(data->mem_hops)) return data->mem_hops; diff --git a/tools/perf/util/bpf_skel/vmlinux.h b/tools/perf/util/bpf_skel/vmlinux.h index 449b1ea91fc4..c7ed51b0c1ef 100644 --- a/tools/perf/util/bpf_skel/vmlinux.h +++ b/tools/perf/util/bpf_skel/vmlinux.h @@ -1,6 +1,7 @@ #ifndef __VMLINUX_H #define __VMLINUX_H +#include <linux/stddef.h> // for define __always_inline #include <linux/bpf.h> #include <linux/types.h> #include <linux/perf_event.h> diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h index 70cac0375b34..ecca40787ac9 100644 --- a/tools/perf/util/cs-etm.h +++ b/tools/perf/util/cs-etm.h @@ -227,6 +227,19 @@ struct cs_etm_packet_queue { #define INFO_HEADER_SIZE (sizeof(((struct perf_record_auxtrace_info *)0)->type) + \ sizeof(((struct perf_record_auxtrace_info *)0)->reserved__)) +/* CoreSight trace ID is currently the bottom 7 bits of the value */ +#define CORESIGHT_TRACE_ID_VAL_MASK GENMASK(6, 0) + +/* + * perf record will set the legacy meta data values as unused initially. + * This allows perf report to manage the decoders created when dynamic + * allocation in operation. + */ +#define CORESIGHT_TRACE_ID_UNUSED_FLAG BIT(31) + +/* Value to set for unused trace ID values */ +#define CORESIGHT_TRACE_ID_UNUSED_VAL 0x7F + int cs_etm__process_auxtrace_info(union perf_event *event, struct perf_session *session); struct perf_event_attr *cs_etm_get_default_config(struct perf_pmu *pmu); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 356c07f03be6..c2dbb5647e75 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -282,6 +282,7 @@ void evsel__init(struct evsel *evsel, evsel->bpf_fd = -1; INIT_LIST_HEAD(&evsel->config_terms); INIT_LIST_HEAD(&evsel->bpf_counter_list); + INIT_LIST_HEAD(&evsel->bpf_filters); perf_evsel__object.init(evsel); evsel->sample_size = __evsel__sample_size(attr->sample_type); evsel__calc_id_pos(evsel); @@ -290,6 +291,7 @@ void evsel__init(struct evsel *evsel, evsel->per_pkg_mask = NULL; evsel->collect_stat = false; evsel->pmu_name = NULL; + evsel->skippable = false; } struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx) @@ -828,26 +830,26 @@ bool evsel__name_is(struct evsel *evsel, const char *name) const char *evsel__group_pmu_name(const struct evsel *evsel) { - const struct evsel *leader; + struct evsel *leader = evsel__leader(evsel); + struct evsel *pos; - /* If the pmu_name is set use it. pmu_name isn't set for CPU and software events. */ - if (evsel->pmu_name) - return evsel->pmu_name; /* * Software events may be in a group with other uncore PMU events. Use - * the pmu_name of the group leader to avoid breaking the software event - * out of the group. + * the pmu_name of the first non-software event to avoid breaking the + * software event out of the group. * * Aux event leaders, like intel_pt, expect a group with events from * other PMUs, so substitute the AUX event's PMU in this case. */ - leader = evsel__leader(evsel); - if ((evsel->core.attr.type == PERF_TYPE_SOFTWARE || evsel__is_aux_event(leader)) && - leader->pmu_name) { - return leader->pmu_name; + if (evsel->core.attr.type == PERF_TYPE_SOFTWARE || evsel__is_aux_event(leader)) { + /* Starting with the leader, find the first event with a named PMU. */ + for_each_group_evsel(pos, leader) { + if (pos->pmu_name) + return pos->pmu_name; + } } - return "cpu"; + return evsel->pmu_name ?: "cpu"; } const char *evsel__metric_id(const struct evsel *evsel) @@ -1725,9 +1727,13 @@ static int get_group_fd(struct evsel *evsel, int cpu_map_idx, int thread) return -1; fd = FD(leader, cpu_map_idx, thread); - BUG_ON(fd == -1); + BUG_ON(fd == -1 && !leader->skippable); - return fd; + /* + * When the leader has been skipped, return -2 to distinguish from no + * group leader case. + */ + return fd == -1 ? -2 : fd; } static void evsel__remove_fd(struct evsel *pos, int nr_cpus, int nr_threads, int thread_idx) @@ -2109,6 +2115,12 @@ retry_open: group_fd = get_group_fd(evsel, idx, thread); + if (group_fd == -2) { + pr_debug("broken group leader for %s\n", evsel->name); + err = -EINVAL; + goto out_close; + } + test_attr__ready(); /* Debug message used by test scripts */ diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index d575390d80bc..0f54f28a69c2 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -95,6 +95,7 @@ struct evsel { bool weak_group; bool bpf_counter; bool use_config_name; + bool skippable; int bpf_fd; struct bpf_object *bpf_obj; struct list_head config_terms; @@ -150,10 +151,8 @@ struct evsel { */ struct bpf_counter_ops *bpf_counter_ops; - union { - struct list_head bpf_counter_list; /* for perf-stat -b */ - struct list_head bpf_filters; /* for perf-record --filter */ - }; + struct list_head bpf_counter_list; /* for perf-stat -b */ + struct list_head bpf_filters; /* for perf-record --filter */ /* for perf-stat --use-bpf */ int bperf_leader_prog_fd; diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index 250e444bf032..4ce931cccb63 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -225,7 +225,11 @@ expr: NUMBER { if (fpclassify($3.val) == FP_ZERO) { pr_debug("division by zero\n"); - YYABORT; + assert($3.ids == NULL); + if (compute_ids) + ids__free($1.ids); + $$.val = NAN; + $$.ids = NULL; } else if (!compute_ids || (is_const($1.val) && is_const($3.val))) { assert($1.ids == NULL); assert($3.ids == NULL); diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index c566c6859302..5e9c657dd3f7 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -1144,12 +1144,12 @@ static int metricgroup__add_metric_callback(const struct pmu_metric *pm, struct metricgroup__add_metric_data *data = vdata; int ret = 0; - if (pm->metric_expr && - (match_metric(pm->metric_group, data->metric_name) || - match_metric(pm->metric_name, data->metric_name))) { + if (pm->metric_expr && match_pm_metric(pm, data->metric_name)) { + bool metric_no_group = data->metric_no_group || + match_metric(data->metric_name, pm->metricgroup_no_group); data->has_match = true; - ret = add_metric(data->list, pm, data->modifier, data->metric_no_group, + ret = add_metric(data->list, pm, data->modifier, metric_no_group, data->metric_no_threshold, data->user_requested_cpu_list, data->system_wide, /*root_metric=*/NULL, /*visited_metrics=*/NULL, table); @@ -1672,7 +1672,7 @@ static int metricgroup__topdown_max_level_callback(const struct pmu_metric *pm, { unsigned int *max_level = data; unsigned int level; - const char *p = strstr(pm->metric_group, "TopdownL"); + const char *p = strstr(pm->metric_group ?: "", "TopdownL"); if (!p || p[8] == '\0') return 0; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index d71019dcd614..34ba840ae19a 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -2140,25 +2140,32 @@ static int evlist__cmp(void *state, const struct list_head *l, const struct list int *leader_idx = state; int lhs_leader_idx = *leader_idx, rhs_leader_idx = *leader_idx, ret; const char *lhs_pmu_name, *rhs_pmu_name; + bool lhs_has_group = false, rhs_has_group = false; /* * First sort by grouping/leader. Read the leader idx only if the evsel * is part of a group, as -1 indicates no group. */ - if (lhs_core->leader != lhs_core || lhs_core->nr_members > 1) + if (lhs_core->leader != lhs_core || lhs_core->nr_members > 1) { + lhs_has_group = true; lhs_leader_idx = lhs_core->leader->idx; - if (rhs_core->leader != rhs_core || rhs_core->nr_members > 1) + } + if (rhs_core->leader != rhs_core || rhs_core->nr_members > 1) { + rhs_has_group = true; rhs_leader_idx = rhs_core->leader->idx; + } if (lhs_leader_idx != rhs_leader_idx) return lhs_leader_idx - rhs_leader_idx; - /* Group by PMU. Groups can't span PMUs. */ - lhs_pmu_name = evsel__group_pmu_name(lhs); - rhs_pmu_name = evsel__group_pmu_name(rhs); - ret = strcmp(lhs_pmu_name, rhs_pmu_name); - if (ret) - return ret; + /* Group by PMU if there is a group. Groups can't span PMUs. */ + if (lhs_has_group && rhs_has_group) { + lhs_pmu_name = evsel__group_pmu_name(lhs); + rhs_pmu_name = evsel__group_pmu_name(rhs); + ret = strcmp(lhs_pmu_name, rhs_pmu_name); + if (ret) + return ret; + } /* Architecture specific sorting. */ return arch_evlist__cmp(lhs, rhs); diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 73b2ff2ddf29..bf5a6c14dfcd 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -431,7 +431,7 @@ static void print_metric_json(struct perf_stat_config *config __maybe_unused, struct outstate *os = ctx; FILE *out = os->fh; - fprintf(out, "\"metric-value\" : %f, ", val); + fprintf(out, "\"metric-value\" : \"%f\", ", val); fprintf(out, "\"metric-unit\" : \"%s\"", unit); if (!config->metric_only) fprintf(out, "}"); diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index eeccab6751d7..1566a206ba42 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -403,12 +403,25 @@ static int prepare_metric(struct evsel **metric_events, if (!aggr) break; - /* - * If an event was scaled during stat gathering, reverse - * the scale before computing the metric. - */ - val = aggr->counts.val * (1.0 / metric_events[i]->scale); - source_count = evsel__source_count(metric_events[i]); + if (!metric_events[i]->supported) { + /* + * Not supported events will have a count of 0, + * which can be confusing in a + * metric. Explicitly set the value to NAN. Not + * counted events (enable time of 0) are read as + * 0. + */ + val = NAN; + source_count = 0; + } else { + /* + * If an event was scaled during stat gathering, + * reverse the scale before computing the + * metric. + */ + val = aggr->counts.val * (1.0 / metric_events[i]->scale); + source_count = evsel__source_count(metric_events[i]); + } } n = strdup(evsel__metric_id(metric_events[i])); if (!n) diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index b2ed9cc52265..63882a4db5c7 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -31,6 +31,13 @@ #include <bfd.h> #endif +#if defined(HAVE_LIBBFD_SUPPORT) || defined(HAVE_CPLUS_DEMANGLE_SUPPORT) +#ifndef DMGL_PARAMS +#define DMGL_PARAMS (1 << 0) /* Include function args */ +#define DMGL_ANSI (1 << 1) /* Include const, volatile, etc */ +#endif +#endif + #ifndef EM_AARCH64 #define EM_AARCH64 183 /* ARM 64 bit */ #endif @@ -271,6 +278,26 @@ static bool want_demangle(bool is_kernel_sym) return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle; } +/* + * Demangle C++ function signature, typically replaced by demangle-cxx.cpp + * version. + */ +__weak char *cxx_demangle_sym(const char *str __maybe_unused, bool params __maybe_unused, + bool modifiers __maybe_unused) +{ +#ifdef HAVE_LIBBFD_SUPPORT + int flags = (params ? DMGL_PARAMS : 0) | (modifiers ? DMGL_ANSI : 0); + + return bfd_demangle(NULL, str, flags); +#elif defined(HAVE_CPLUS_DEMANGLE_SUPPORT) + int flags = (params ? DMGL_PARAMS : 0) | (modifiers ? DMGL_ANSI : 0); + + return cplus_demangle(str, flags); +#else + return NULL; +#endif +} + static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name) { char *demangled = NULL; diff --git a/tools/power/cpupower/lib/powercap.c b/tools/power/cpupower/lib/powercap.c index 0ce29ee4c2e4..a7a59c6bacda 100644 --- a/tools/power/cpupower/lib/powercap.c +++ b/tools/power/cpupower/lib/powercap.c @@ -40,25 +40,34 @@ static int sysfs_get_enabled(char *path, int *mode) { int fd; char yes_no; + int ret = 0; *mode = 0; fd = open(path, O_RDONLY); - if (fd == -1) - return -1; + if (fd == -1) { + ret = -1; + goto out; + } if (read(fd, &yes_no, 1) != 1) { - close(fd); - return -1; + ret = -1; + goto out_close; } if (yes_no == '1') { *mode = 1; - return 0; + goto out_close; } else if (yes_no == '0') { - return 0; + goto out_close; + } else { + ret = -1; + goto out_close; } - return -1; +out_close: + close(fd); +out: + return ret; } int powercap_get_enabled(int *mode) diff --git a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c index e7d48cb563c0..ae6af354a81d 100644 --- a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c +++ b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c @@ -70,8 +70,8 @@ static int max_freq_mode; */ static unsigned long max_frequency; -static unsigned long long tsc_at_measure_start; -static unsigned long long tsc_at_measure_end; +static unsigned long long *tsc_at_measure_start; +static unsigned long long *tsc_at_measure_end; static unsigned long long *mperf_previous_count; static unsigned long long *aperf_previous_count; static unsigned long long *mperf_current_count; @@ -169,7 +169,7 @@ static int mperf_get_count_percent(unsigned int id, double *percent, aperf_diff = aperf_current_count[cpu] - aperf_previous_count[cpu]; if (max_freq_mode == MAX_FREQ_TSC_REF) { - tsc_diff = tsc_at_measure_end - tsc_at_measure_start; + tsc_diff = tsc_at_measure_end[cpu] - tsc_at_measure_start[cpu]; *percent = 100.0 * mperf_diff / tsc_diff; dprint("%s: TSC Ref - mperf_diff: %llu, tsc_diff: %llu\n", mperf_cstates[id].name, mperf_diff, tsc_diff); @@ -206,7 +206,7 @@ static int mperf_get_count_freq(unsigned int id, unsigned long long *count, if (max_freq_mode == MAX_FREQ_TSC_REF) { /* Calculate max_freq from TSC count */ - tsc_diff = tsc_at_measure_end - tsc_at_measure_start; + tsc_diff = tsc_at_measure_end[cpu] - tsc_at_measure_start[cpu]; time_diff = timespec_diff_us(time_start, time_end); max_frequency = tsc_diff / time_diff; } @@ -225,33 +225,27 @@ static int mperf_get_count_freq(unsigned int id, unsigned long long *count, static int mperf_start(void) { int cpu; - unsigned long long dbg; clock_gettime(CLOCK_REALTIME, &time_start); - mperf_get_tsc(&tsc_at_measure_start); - for (cpu = 0; cpu < cpu_count; cpu++) + for (cpu = 0; cpu < cpu_count; cpu++) { + mperf_get_tsc(&tsc_at_measure_start[cpu]); mperf_init_stats(cpu); + } - mperf_get_tsc(&dbg); - dprint("TSC diff: %llu\n", dbg - tsc_at_measure_start); return 0; } static int mperf_stop(void) { - unsigned long long dbg; int cpu; - for (cpu = 0; cpu < cpu_count; cpu++) + for (cpu = 0; cpu < cpu_count; cpu++) { mperf_measure_stats(cpu); + mperf_get_tsc(&tsc_at_measure_end[cpu]); + } - mperf_get_tsc(&tsc_at_measure_end); clock_gettime(CLOCK_REALTIME, &time_end); - - mperf_get_tsc(&dbg); - dprint("TSC diff: %llu\n", dbg - tsc_at_measure_end); - return 0; } @@ -353,7 +347,8 @@ struct cpuidle_monitor *mperf_register(void) aperf_previous_count = calloc(cpu_count, sizeof(unsigned long long)); mperf_current_count = calloc(cpu_count, sizeof(unsigned long long)); aperf_current_count = calloc(cpu_count, sizeof(unsigned long long)); - + tsc_at_measure_start = calloc(cpu_count, sizeof(unsigned long long)); + tsc_at_measure_end = calloc(cpu_count, sizeof(unsigned long long)); mperf_monitor.name_len = strlen(mperf_monitor.name); return &mperf_monitor; } @@ -364,6 +359,8 @@ void mperf_unregister(void) free(aperf_previous_count); free(mperf_current_count); free(aperf_current_count); + free(tsc_at_measure_start); + free(tsc_at_measure_end); free(is_valid); } diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild index fba7bec96acd..6f9347ade82c 100644 --- a/tools/testing/cxl/Kbuild +++ b/tools/testing/cxl/Kbuild @@ -6,6 +6,7 @@ ldflags-y += --wrap=acpi_pci_find_root ldflags-y += --wrap=nvdimm_bus_register ldflags-y += --wrap=devm_cxl_port_enumerate_dports ldflags-y += --wrap=devm_cxl_setup_hdm +ldflags-y += --wrap=devm_cxl_enable_hdm ldflags-y += --wrap=devm_cxl_add_passthrough_decoder ldflags-y += --wrap=devm_cxl_enumerate_decoders ldflags-y += --wrap=cxl_await_media_ready diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index ba572d03c687..34b48027b3de 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -1256,6 +1256,7 @@ static int cxl_mock_mem_probe(struct platform_device *pdev) if (rc) return rc; + cxlds->media_ready = true; rc = cxl_dev_state_identify(cxlds); if (rc) return rc; diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c index c4e53f22e421..284416527644 100644 --- a/tools/testing/cxl/test/mock.c +++ b/tools/testing/cxl/test/mock.c @@ -19,7 +19,7 @@ void register_cxl_mock_ops(struct cxl_mock_ops *ops) } EXPORT_SYMBOL_GPL(register_cxl_mock_ops); -static DEFINE_SRCU(cxl_mock_srcu); +DEFINE_STATIC_SRCU(cxl_mock_srcu); void unregister_cxl_mock_ops(struct cxl_mock_ops *ops) { @@ -149,6 +149,21 @@ struct cxl_hdm *__wrap_devm_cxl_setup_hdm(struct cxl_port *port, } EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_setup_hdm, CXL); +int __wrap_devm_cxl_enable_hdm(struct cxl_port *port, struct cxl_hdm *cxlhdm) +{ + int index, rc; + struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); + + if (ops && ops->is_mock_port(port->uport)) + rc = 0; + else + rc = devm_cxl_enable_hdm(port, cxlhdm); + put_cxl_mock_ops(index); + + return rc; +} +EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_enable_hdm, CXL); + int __wrap_devm_cxl_add_passthrough_decoder(struct cxl_port *port) { int rc, index; diff --git a/tools/testing/selftests/bpf/DENYLIST.aarch64 b/tools/testing/selftests/bpf/DENYLIST.aarch64 index 0a6837f97c32..08adc805878b 100644 --- a/tools/testing/selftests/bpf/DENYLIST.aarch64 +++ b/tools/testing/selftests/bpf/DENYLIST.aarch64 @@ -1,33 +1,6 @@ -bloom_filter_map # libbpf: prog 'check_bloom': failed to attach: ERROR: strerror_r(-524)=22 -bpf_cookie/lsm -bpf_cookie/multi_kprobe_attach_api -bpf_cookie/multi_kprobe_link_api -bpf_cookie/trampoline -bpf_loop/check_callback_fn_stop # link unexpected error: -524 -bpf_loop/check_invalid_flags -bpf_loop/check_nested_calls -bpf_loop/check_non_constant_callback -bpf_loop/check_nr_loops -bpf_loop/check_null_callback_ctx -bpf_loop/check_stack -bpf_mod_race # bpf_mod_kfunc_race__attach unexpected error: -524 (errno 524) -bpf_tcp_ca/dctcp_fallback -btf_dump/btf_dump: var_data # find type id unexpected find type id: actual -2 < expected 0 -cgroup_hierarchical_stats # attach unexpected error: -524 (errno 524) -d_path/basic # setup attach failed: -524 -deny_namespace # attach unexpected error: -524 (errno 524) -fentry_fexit # fentry_attach unexpected error: -1 (errno 524) -fentry_test # fentry_attach unexpected error: -1 (errno 524) -fexit_sleep # fexit_attach fexit attach failed: -1 -fexit_stress # fexit attach unexpected fexit attach: actual -524 < expected 0 -fexit_test # fexit_attach unexpected error: -1 (errno 524) -get_func_args_test # get_func_args_test__attach unexpected error: -524 (errno 524) (trampoline) -get_func_ip_test # get_func_ip_test__attach unexpected error: -524 (errno 524) (trampoline) -htab_update/reenter_update -kfree_skb # attach fentry unexpected error: -524 (trampoline) -kfunc_call/subprog # extern (var ksym) 'bpf_prog_active': not found in kernel BTF -kfunc_call/subprog_lskel # skel unexpected error: -2 -kfunc_dynptr_param/dynptr_data_null # libbpf: prog 'dynptr_data_null': failed to attach: ERROR: strerror_r(-524)=22 +bpf_cookie/multi_kprobe_attach_api # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3 +bpf_cookie/multi_kprobe_link_api # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3 +fexit_sleep # The test never returns. The remaining tests cannot start. kprobe_multi_bench_attach # bpf_program__attach_kprobe_multi_opts unexpected error: -95 kprobe_multi_test/attach_api_addrs # bpf_program__attach_kprobe_multi_opts unexpected error: -95 kprobe_multi_test/attach_api_pattern # bpf_program__attach_kprobe_multi_opts unexpected error: -95 @@ -35,51 +8,5 @@ kprobe_multi_test/attach_api_syms # bpf_program__attach_kprobe_mu kprobe_multi_test/bench_attach # bpf_program__attach_kprobe_multi_opts unexpected error: -95 kprobe_multi_test/link_api_addrs # link_fd unexpected link_fd: actual -95 < expected 0 kprobe_multi_test/link_api_syms # link_fd unexpected link_fd: actual -95 < expected 0 -kprobe_multi_test/skel_api # kprobe_multi__attach unexpected error: -524 (errno 524) -ksyms_module/libbpf # 'bpf_testmod_ksym_percpu': not found in kernel BTF -ksyms_module/lskel # test_ksyms_module_lskel__open_and_load unexpected error: -2 -libbpf_get_fd_by_id_opts # test_libbpf_get_fd_by_id_opts__attach unexpected error: -524 (errno 524) -linked_list -lookup_key # test_lookup_key__attach unexpected error: -524 (errno 524) -lru_bug # lru_bug__attach unexpected error: -524 (errno 524) -modify_return # modify_return__attach failed unexpected error: -524 (errno 524) -module_attach # skel_attach skeleton attach failed: -524 -module_fentry_shadow # bpf_link_create unexpected bpf_link_create: actual -524 < expected 0 -mptcp/base # run_test mptcp unexpected error: -524 (errno 524) -netcnt # packets unexpected packets: actual 10001 != expected 10000 -rcu_read_lock # failed to attach: ERROR: strerror_r(-524)=22 -recursion # skel_attach unexpected error: -524 (errno 524) -ringbuf # skel_attach skeleton attachment failed: -1 -setget_sockopt # attach_cgroup unexpected error: -524 -sk_storage_tracing # test_sk_storage_tracing__attach unexpected error: -524 (errno 524) -skc_to_unix_sock # could not attach BPF object unexpected error: -524 (errno 524) -socket_cookie # prog_attach unexpected error: -524 -stacktrace_build_id # compare_stack_ips stackmap vs. stack_amap err -1 errno 2 -task_local_storage/exit_creds # skel_attach unexpected error: -524 (errno 524) -task_local_storage/recursion # skel_attach unexpected error: -524 (errno 524) -test_bprm_opts # attach attach failed: -524 -test_ima # attach attach failed: -524 -test_local_storage # attach lsm attach failed: -524 -test_lsm # test_lsm_first_attach unexpected error: -524 (errno 524) -test_overhead # attach_fentry unexpected error: -524 -timer # timer unexpected error: -524 (errno 524) -timer_crash # timer_crash__attach unexpected error: -524 (errno 524) -timer_mim # timer_mim unexpected error: -524 (errno 524) -trace_printk # trace_printk__attach unexpected error: -1 (errno 524) -trace_vprintk # trace_vprintk__attach unexpected error: -1 (errno 524) -tracing_struct # tracing_struct__attach unexpected error: -524 (errno 524) -trampoline_count # attach_prog unexpected error: -524 -unpriv_bpf_disabled # skel_attach unexpected error: -524 (errno 524) -user_ringbuf/test_user_ringbuf_post_misaligned # misaligned_skel unexpected error: -524 (errno 524) -user_ringbuf/test_user_ringbuf_post_producer_wrong_offset -user_ringbuf/test_user_ringbuf_post_larger_than_ringbuf_sz -user_ringbuf/test_user_ringbuf_basic # ringbuf_basic_skel unexpected error: -524 (errno 524) -user_ringbuf/test_user_ringbuf_sample_full_ring_buffer -user_ringbuf/test_user_ringbuf_post_alignment_autoadjust -user_ringbuf/test_user_ringbuf_overfill -user_ringbuf/test_user_ringbuf_discards_properly_ignored -user_ringbuf/test_user_ringbuf_loop -user_ringbuf/test_user_ringbuf_msg_protocol -user_ringbuf/test_user_ringbuf_blocking_reserve -verify_pkcs7_sig # test_verify_pkcs7_sig__attach unexpected error: -524 (errno 524) -vmlinux # skel_attach skeleton attach failed: -524 +kprobe_multi_test/skel_api # libbpf: failed to load BPF skeleton 'kprobe_multi': -3 +module_attach # prog 'kprobe_multi': failed to auto-attach: -95 diff --git a/tools/testing/selftests/bpf/DENYLIST.s390x b/tools/testing/selftests/bpf/DENYLIST.s390x index c7463f3ec3c0..5061d9e24c16 100644 --- a/tools/testing/selftests/bpf/DENYLIST.s390x +++ b/tools/testing/selftests/bpf/DENYLIST.s390x @@ -26,3 +26,4 @@ user_ringbuf # failed to find kernel BTF type ID of verif_stats # trace_vprintk__open_and_load unexpected error: -9 (?) xdp_bonding # failed to auto-attach program 'trace_on_entry': -524 (trampoline) xdp_metadata # JIT does not support calling kernel function (kfunc) +test_task_under_cgroup # JIT does not support calling kernel function (kfunc) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index c49e5403ad0e..538df8fb8c42 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -88,8 +88,7 @@ TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \ xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata \ xdp_features -TEST_CUSTOM_PROGS = $(OUTPUT)/urandom_read $(OUTPUT)/sign-file -TEST_GEN_FILES += liburandom_read.so +TEST_GEN_FILES += liburandom_read.so urandom_read sign-file # Emit succinct information message describing current building step # $1 - generic step name (e.g., CC, LINK, etc); @@ -197,7 +196,7 @@ $(OUTPUT)/urandom_read: urandom_read.c urandom_read_aux.c $(OUTPUT)/liburandom_r $(OUTPUT)/sign-file: ../../../../scripts/sign-file.c $(call msg,SIGN-FILE,,$@) - $(Q)$(CC) $(shell $(HOSTPKG_CONFIG)--cflags libcrypto 2> /dev/null) \ + $(Q)$(CC) $(shell $(HOSTPKG_CONFIG) --cflags libcrypto 2> /dev/null) \ $< -o $@ \ $(shell $(HOSTPKG_CONFIG) --libs libcrypto 2> /dev/null || echo -lcrypto) diff --git a/tools/testing/selftests/bpf/bpf_kfuncs.h b/tools/testing/selftests/bpf/bpf_kfuncs.h index 8c993ec8ceea..642dda0e758a 100644 --- a/tools/testing/selftests/bpf/bpf_kfuncs.h +++ b/tools/testing/selftests/bpf/bpf_kfuncs.h @@ -35,4 +35,10 @@ extern void *bpf_dynptr_slice(const struct bpf_dynptr *ptr, __u32 offset, extern void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr *ptr, __u32 offset, void *buffer, __u32 buffer__szk) __ksym; +extern int bpf_dynptr_adjust(const struct bpf_dynptr *ptr, __u32 start, __u32 end) __ksym; +extern bool bpf_dynptr_is_null(const struct bpf_dynptr *ptr) __ksym; +extern bool bpf_dynptr_is_rdonly(const struct bpf_dynptr *ptr) __ksym; +extern __u32 bpf_dynptr_size(const struct bpf_dynptr *ptr) __ksym; +extern int bpf_dynptr_clone(const struct bpf_dynptr *ptr, struct bpf_dynptr *clone__init) __ksym; + #endif diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 52785ba671e6..cf216041876c 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -9,6 +9,7 @@ #include <linux/sysfs.h> #include <linux/tracepoint.h> #include "bpf_testmod.h" +#include "bpf_testmod_kfunc.h" #define CREATE_TRACE_POINTS #include "bpf_testmod-events.h" @@ -289,8 +290,171 @@ static const struct btf_kfunc_id_set bpf_testmod_common_kfunc_set = { .set = &bpf_testmod_common_kfunc_ids, }; +__bpf_kfunc u64 bpf_kfunc_call_test1(struct sock *sk, u32 a, u64 b, u32 c, u64 d) +{ + return a + b + c + d; +} + +__bpf_kfunc int bpf_kfunc_call_test2(struct sock *sk, u32 a, u32 b) +{ + return a + b; +} + +__bpf_kfunc struct sock *bpf_kfunc_call_test3(struct sock *sk) +{ + return sk; +} + +__bpf_kfunc long noinline bpf_kfunc_call_test4(signed char a, short b, int c, long d) +{ + /* Provoke the compiler to assume that the caller has sign-extended a, + * b and c on platforms where this is required (e.g. s390x). + */ + return (long)a + (long)b + (long)c + d; +} + +static struct prog_test_ref_kfunc prog_test_struct = { + .a = 42, + .b = 108, + .next = &prog_test_struct, + .cnt = REFCOUNT_INIT(1), +}; + +__bpf_kfunc struct prog_test_ref_kfunc * +bpf_kfunc_call_test_acquire(unsigned long *scalar_ptr) +{ + refcount_inc(&prog_test_struct.cnt); + return &prog_test_struct; +} + +__bpf_kfunc void bpf_kfunc_call_test_offset(struct prog_test_ref_kfunc *p) +{ + WARN_ON_ONCE(1); +} + +__bpf_kfunc struct prog_test_member * +bpf_kfunc_call_memb_acquire(void) +{ + WARN_ON_ONCE(1); + return NULL; +} + +__bpf_kfunc void bpf_kfunc_call_memb1_release(struct prog_test_member1 *p) +{ + WARN_ON_ONCE(1); +} + +static int *__bpf_kfunc_call_test_get_mem(struct prog_test_ref_kfunc *p, const int size) +{ + if (size > 2 * sizeof(int)) + return NULL; + + return (int *)p; +} + +__bpf_kfunc int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, + const int rdwr_buf_size) +{ + return __bpf_kfunc_call_test_get_mem(p, rdwr_buf_size); +} + +__bpf_kfunc int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, + const int rdonly_buf_size) +{ + return __bpf_kfunc_call_test_get_mem(p, rdonly_buf_size); +} + +/* the next 2 ones can't be really used for testing expect to ensure + * that the verifier rejects the call. + * Acquire functions must return struct pointers, so these ones are + * failing. + */ +__bpf_kfunc int *bpf_kfunc_call_test_acq_rdonly_mem(struct prog_test_ref_kfunc *p, + const int rdonly_buf_size) +{ + return __bpf_kfunc_call_test_get_mem(p, rdonly_buf_size); +} + +__bpf_kfunc void bpf_kfunc_call_int_mem_release(int *p) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_fail1(struct prog_test_fail1 *p) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_fail2(struct prog_test_fail2 *p) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_fail3(struct prog_test_fail3 *p) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_mem_len_pass1(void *mem, int mem__sz) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_mem_len_fail1(void *mem, int len) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_mem_len_fail2(u64 *mem, int len) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_ref(struct prog_test_ref_kfunc *p) +{ + /* p != NULL, but p->cnt could be 0 */ +} + +__bpf_kfunc void bpf_kfunc_call_test_destructive(void) +{ +} + +__bpf_kfunc static u32 bpf_kfunc_call_test_static_unused_arg(u32 arg, u32 unused) +{ + return arg; +} + BTF_SET8_START(bpf_testmod_check_kfunc_ids) BTF_ID_FLAGS(func, bpf_testmod_test_mod_kfunc) +BTF_ID_FLAGS(func, bpf_kfunc_call_test1) +BTF_ID_FLAGS(func, bpf_kfunc_call_test2) +BTF_ID_FLAGS(func, bpf_kfunc_call_test3) +BTF_ID_FLAGS(func, bpf_kfunc_call_test4) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_pass1) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_fail1) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_fail2) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_acquire, KF_ACQUIRE | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_kfunc_call_memb_acquire, KF_ACQUIRE | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_kfunc_call_memb1_release, KF_RELEASE) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_get_rdwr_mem, KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_get_rdonly_mem, KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_acq_rdonly_mem, KF_ACQUIRE | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_kfunc_call_int_mem_release, KF_RELEASE) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_pass_ctx) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_pass1) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_pass2) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_fail1) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_fail2) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_fail3) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_ref, KF_TRUSTED_ARGS | KF_RCU) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_destructive, KF_DESTRUCTIVE) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_static_unused_arg) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_offset) BTF_SET8_END(bpf_testmod_check_kfunc_ids) static const struct btf_kfunc_id_set bpf_testmod_kfunc_set = { @@ -312,6 +476,8 @@ static int bpf_testmod_init(void) ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_UNSPEC, &bpf_testmod_common_kfunc_set); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_testmod_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_testmod_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &bpf_testmod_kfunc_set); if (ret < 0) return ret; if (bpf_fentry_test1(0) < 0) diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h new file mode 100644 index 000000000000..9693c626646b --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _BPF_TESTMOD_KFUNC_H +#define _BPF_TESTMOD_KFUNC_H + +#ifndef __KERNEL__ +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#else +#define __ksym +struct prog_test_member1 { + int a; +}; + +struct prog_test_member { + struct prog_test_member1 m; + int c; +}; + +struct prog_test_ref_kfunc { + int a; + int b; + struct prog_test_member memb; + struct prog_test_ref_kfunc *next; + refcount_t cnt; +}; +#endif + +struct prog_test_pass1 { + int x0; + struct { + int x1; + struct { + int x2; + struct { + int x3; + }; + }; + }; +}; + +struct prog_test_pass2 { + int len; + short arr1[4]; + struct { + char arr2[4]; + unsigned long arr3[8]; + } x; +}; + +struct prog_test_fail1 { + void *p; + int x; +}; + +struct prog_test_fail2 { + int x8; + struct prog_test_pass1 x; +}; + +struct prog_test_fail3 { + int len; + char arr1[2]; + char arr2[]; +}; + +struct prog_test_ref_kfunc * +bpf_kfunc_call_test_acquire(unsigned long *scalar_ptr) __ksym; +void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; +void bpf_kfunc_call_test_ref(struct prog_test_ref_kfunc *p) __ksym; + +void bpf_kfunc_call_test_mem_len_pass1(void *mem, int len) __ksym; +int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, const int rdwr_buf_size) __ksym; +int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym; +int *bpf_kfunc_call_test_acq_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym; +void bpf_kfunc_call_int_mem_release(int *p) __ksym; + +/* The bpf_kfunc_call_test_static_unused_arg is defined as static, + * but bpf program compilation needs to see it as global symbol. + */ +#ifndef __KERNEL__ +u32 bpf_kfunc_call_test_static_unused_arg(u32 arg, u32 unused) __ksym; +#endif + +void bpf_testmod_test_mod_kfunc(int i) __ksym; + +__u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b, + __u32 c, __u64 d) __ksym; +int bpf_kfunc_call_test2(struct sock *sk, __u32 a, __u32 b) __ksym; +struct sock *bpf_kfunc_call_test3(struct sock *sk) __ksym; +long bpf_kfunc_call_test4(signed char a, short b, int c, long d) __ksym; + +void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb) __ksym; +void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p) __ksym; +void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p) __ksym; +void bpf_kfunc_call_test_mem_len_fail2(__u64 *mem, int len) __ksym; + +void bpf_kfunc_call_test_destructive(void) __ksym; + +#endif /* _BPF_TESTMOD_KFUNC_H */ diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index 596caa176582..a105c0cd008a 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -427,3 +427,26 @@ void close_netns(struct nstoken *token) close(token->orig_netns_fd); free(token); } + +int get_socket_local_port(int sock_fd) +{ + struct sockaddr_storage addr; + socklen_t addrlen = sizeof(addr); + int err; + + err = getsockname(sock_fd, (struct sockaddr *)&addr, &addrlen); + if (err < 0) + return err; + + if (addr.ss_family == AF_INET) { + struct sockaddr_in *sin = (struct sockaddr_in *)&addr; + + return sin->sin_port; + } else if (addr.ss_family == AF_INET6) { + struct sockaddr_in6 *sin = (struct sockaddr_in6 *)&addr; + + return sin->sin6_port; + } + + return -1; +} diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index f882c691b790..694185644da6 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -56,6 +56,7 @@ int fastopen_connect(int server_fd, const char *data, unsigned int data_len, int make_sockaddr(int family, const char *addr_str, __u16 port, struct sockaddr_storage *addr, socklen_t *len); char *ping_command(int family); +int get_socket_local_port(int sock_fd); struct nstoken; /** diff --git a/tools/testing/selftests/bpf/prog_tests/arg_parsing.c b/tools/testing/selftests/bpf/prog_tests/arg_parsing.c index b17bfa0e0aac..bb143de68875 100644 --- a/tools/testing/selftests/bpf/prog_tests/arg_parsing.c +++ b/tools/testing/selftests/bpf/prog_tests/arg_parsing.c @@ -96,12 +96,80 @@ static void test_parse_test_list(void) goto error; ASSERT_OK(strcmp("*bpf_cookie*", set.tests[0].name), "test name"); ASSERT_OK(strcmp("*trace*", set.tests[0].subtests[0]), "subtest name"); + free_test_filter_set(&set); + + ASSERT_OK(parse_test_list("t/subtest1,t/subtest2", &set, true), + "parsing"); + if (!ASSERT_EQ(set.cnt, 1, "count of test filters")) + goto error; + if (!ASSERT_OK_PTR(set.tests, "test filters initialized")) + goto error; + if (!ASSERT_EQ(set.tests[0].subtest_cnt, 2, "subtest filters count")) + goto error; + ASSERT_OK(strcmp("t", set.tests[0].name), "test name"); + ASSERT_OK(strcmp("subtest1", set.tests[0].subtests[0]), "subtest name"); + ASSERT_OK(strcmp("subtest2", set.tests[0].subtests[1]), "subtest name"); error: free_test_filter_set(&set); } +static void test_parse_test_list_file(void) +{ + struct test_filter_set set; + char tmpfile[80]; + FILE *fp; + int fd; + + snprintf(tmpfile, sizeof(tmpfile), "/tmp/bpf_arg_parsing_test.XXXXXX"); + fd = mkstemp(tmpfile); + if (!ASSERT_GE(fd, 0, "create tmp")) + return; + + fp = fdopen(fd, "w"); + if (!ASSERT_NEQ(fp, NULL, "fdopen tmp")) { + close(fd); + goto out_remove; + } + + fprintf(fp, "# comment\n"); + fprintf(fp, " test_with_spaces \n"); + fprintf(fp, "testA/subtest # comment\n"); + fprintf(fp, "testB#comment with no space\n"); + fprintf(fp, "testB # duplicate\n"); + fprintf(fp, "testA/subtest # subtest duplicate\n"); + fprintf(fp, "testA/subtest2\n"); + fprintf(fp, "testC_no_eof_newline"); + fflush(fp); + + if (!ASSERT_OK(ferror(fp), "prepare tmp")) + goto out_fclose; + + init_test_filter_set(&set); + + ASSERT_OK(parse_test_list_file(tmpfile, &set, true), "parse file"); + + ASSERT_EQ(set.cnt, 4, "test count"); + ASSERT_OK(strcmp("test_with_spaces", set.tests[0].name), "test 0 name"); + ASSERT_EQ(set.tests[0].subtest_cnt, 0, "test 0 subtest count"); + ASSERT_OK(strcmp("testA", set.tests[1].name), "test 1 name"); + ASSERT_EQ(set.tests[1].subtest_cnt, 2, "test 1 subtest count"); + ASSERT_OK(strcmp("subtest", set.tests[1].subtests[0]), "test 1 subtest 0"); + ASSERT_OK(strcmp("subtest2", set.tests[1].subtests[1]), "test 1 subtest 1"); + ASSERT_OK(strcmp("testB", set.tests[2].name), "test 2 name"); + ASSERT_OK(strcmp("testC_no_eof_newline", set.tests[3].name), "test 3 name"); + + free_test_filter_set(&set); + +out_fclose: + fclose(fp); +out_remove: + remove(tmpfile); +} + void test_arg_parsing(void) { if (test__start_subtest("test_parse_test_list")) test_parse_test_list(); + if (test__start_subtest("test_parse_test_list_file")) + test_parse_test_list_file(); } diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c b/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c index a4d0cc9d3367..fe2c502e5089 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c @@ -11,6 +11,7 @@ #include "ksym_race.skel.h" #include "bpf_mod_race.skel.h" #include "kfunc_call_race.skel.h" +#include "testing_helpers.h" /* This test crafts a race between btf_try_get_module and do_init_module, and * checks whether btf_try_get_module handles the invocation for a well-formed @@ -44,35 +45,10 @@ enum bpf_test_state { static _Atomic enum bpf_test_state state = _TS_INVALID; -static int sys_finit_module(int fd, const char *param_values, int flags) -{ - return syscall(__NR_finit_module, fd, param_values, flags); -} - -static int sys_delete_module(const char *name, unsigned int flags) -{ - return syscall(__NR_delete_module, name, flags); -} - -static int load_module(const char *mod) -{ - int ret, fd; - - fd = open("bpf_testmod.ko", O_RDONLY); - if (fd < 0) - return fd; - - ret = sys_finit_module(fd, "", 0); - close(fd); - if (ret < 0) - return ret; - return 0; -} - static void *load_module_thread(void *p) { - if (!ASSERT_NEQ(load_module("bpf_testmod.ko"), 0, "load_module_thread must fail")) + if (!ASSERT_NEQ(load_bpf_testmod(false), 0, "load_module_thread must fail")) atomic_store(&state, TS_MODULE_LOAD); else atomic_store(&state, TS_MODULE_LOAD_FAIL); @@ -124,7 +100,7 @@ static void test_bpf_mod_race_config(const struct test_config *config) if (!ASSERT_NEQ(fault_addr, MAP_FAILED, "mmap for uffd registration")) return; - if (!ASSERT_OK(sys_delete_module("bpf_testmod", 0), "unload bpf_testmod")) + if (!ASSERT_OK(unload_bpf_testmod(false), "unload bpf_testmod")) goto end_mmap; skel = bpf_mod_race__open(); @@ -202,8 +178,8 @@ end_destroy: bpf_mod_race__destroy(skel); ASSERT_OK(kern_sync_rcu(), "kern_sync_rcu"); end_module: - sys_delete_module("bpf_testmod", 0); - ASSERT_OK(load_module("bpf_testmod.ko"), "restore bpf_testmod"); + unload_bpf_testmod(false); + ASSERT_OK(load_bpf_testmod(false), "restore bpf_testmod"); end_mmap: munmap(fault_addr, 4096); atomic_store(&state, _TS_INVALID); diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c new file mode 100644 index 000000000000..31f1e815f671 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c @@ -0,0 +1,268 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ +#define _GNU_SOURCE +#include <test_progs.h> +#include <bpf/btf.h> +#include <fcntl.h> +#include <unistd.h> +#include <linux/unistd.h> +#include <linux/mount.h> +#include <sys/syscall.h> + +static inline int sys_fsopen(const char *fsname, unsigned flags) +{ + return syscall(__NR_fsopen, fsname, flags); +} + +static inline int sys_fsconfig(int fs_fd, unsigned cmd, const char *key, const void *val, int aux) +{ + return syscall(__NR_fsconfig, fs_fd, cmd, key, val, aux); +} + +static inline int sys_fsmount(int fs_fd, unsigned flags, unsigned ms_flags) +{ + return syscall(__NR_fsmount, fs_fd, flags, ms_flags); +} + +__attribute__((unused)) +static inline int sys_move_mount(int from_dfd, const char *from_path, + int to_dfd, const char *to_path, + unsigned int ms_flags) +{ + return syscall(__NR_move_mount, from_dfd, from_path, to_dfd, to_path, ms_flags); +} + +static void bpf_obj_pinning_detached(void) +{ + LIBBPF_OPTS(bpf_obj_pin_opts, pin_opts); + LIBBPF_OPTS(bpf_obj_get_opts, get_opts); + int fs_fd = -1, mnt_fd = -1; + int map_fd = -1, map_fd2 = -1; + int zero = 0, src_value, dst_value, err; + const char *map_name = "fsmount_map"; + + /* A bunch of below UAPI calls are constructed based on reading: + * https://brauner.io/2023/02/28/mounting-into-mount-namespaces.html + */ + + /* create VFS context */ + fs_fd = sys_fsopen("bpf", 0); + if (!ASSERT_GE(fs_fd, 0, "fs_fd")) + goto cleanup; + + /* instantiate FS object */ + err = sys_fsconfig(fs_fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0); + if (!ASSERT_OK(err, "fs_create")) + goto cleanup; + + /* create O_PATH fd for detached mount */ + mnt_fd = sys_fsmount(fs_fd, 0, 0); + if (!ASSERT_GE(mnt_fd, 0, "mnt_fd")) + goto cleanup; + + /* If we wanted to expose detached mount in the file system, we'd do + * something like below. But the whole point is that we actually don't + * even have to expose BPF FS in the file system to be able to work + * (pin/get objects) with it. + * + * err = sys_move_mount(mnt_fd, "", -EBADF, mnt_path, MOVE_MOUNT_F_EMPTY_PATH); + * if (!ASSERT_OK(err, "move_mount")) + * goto cleanup; + */ + + /* create BPF map to pin */ + map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, map_name, 4, 4, 1, NULL); + if (!ASSERT_GE(map_fd, 0, "map_fd")) + goto cleanup; + + /* pin BPF map into detached BPF FS through mnt_fd */ + pin_opts.file_flags = BPF_F_PATH_FD; + pin_opts.path_fd = mnt_fd; + err = bpf_obj_pin_opts(map_fd, map_name, &pin_opts); + if (!ASSERT_OK(err, "map_pin")) + goto cleanup; + + /* get BPF map from detached BPF FS through mnt_fd */ + get_opts.file_flags = BPF_F_PATH_FD; + get_opts.path_fd = mnt_fd; + map_fd2 = bpf_obj_get_opts(map_name, &get_opts); + if (!ASSERT_GE(map_fd2, 0, "map_get")) + goto cleanup; + + /* update map through one FD */ + src_value = 0xcafebeef; + err = bpf_map_update_elem(map_fd, &zero, &src_value, 0); + ASSERT_OK(err, "map_update"); + + /* check values written/read through different FDs do match */ + dst_value = 0; + err = bpf_map_lookup_elem(map_fd2, &zero, &dst_value); + ASSERT_OK(err, "map_lookup"); + ASSERT_EQ(dst_value, src_value, "map_value_eq1"); + ASSERT_EQ(dst_value, 0xcafebeef, "map_value_eq2"); + +cleanup: + if (map_fd >= 0) + ASSERT_OK(close(map_fd), "close_map_fd"); + if (map_fd2 >= 0) + ASSERT_OK(close(map_fd2), "close_map_fd2"); + if (fs_fd >= 0) + ASSERT_OK(close(fs_fd), "close_fs_fd"); + if (mnt_fd >= 0) + ASSERT_OK(close(mnt_fd), "close_mnt_fd"); +} + +enum path_kind +{ + PATH_STR_ABS, + PATH_STR_REL, + PATH_FD_REL, +}; + +static void validate_pin(int map_fd, const char *map_name, int src_value, + enum path_kind path_kind) +{ + LIBBPF_OPTS(bpf_obj_pin_opts, pin_opts); + char abs_path[PATH_MAX], old_cwd[PATH_MAX]; + const char *pin_path = NULL; + int zero = 0, dst_value, map_fd2, err; + + snprintf(abs_path, sizeof(abs_path), "/sys/fs/bpf/%s", map_name); + old_cwd[0] = '\0'; + + switch (path_kind) { + case PATH_STR_ABS: + /* absolute path */ + pin_path = abs_path; + break; + case PATH_STR_REL: + /* cwd + relative path */ + ASSERT_OK_PTR(getcwd(old_cwd, sizeof(old_cwd)), "getcwd"); + ASSERT_OK(chdir("/sys/fs/bpf"), "chdir"); + pin_path = map_name; + break; + case PATH_FD_REL: + /* dir fd + relative path */ + pin_opts.file_flags = BPF_F_PATH_FD; + pin_opts.path_fd = open("/sys/fs/bpf", O_PATH); + ASSERT_GE(pin_opts.path_fd, 0, "path_fd"); + pin_path = map_name; + break; + } + + /* pin BPF map using specified path definition */ + err = bpf_obj_pin_opts(map_fd, pin_path, &pin_opts); + ASSERT_OK(err, "obj_pin"); + + /* cleanup */ + if (pin_opts.path_fd >= 0) + close(pin_opts.path_fd); + if (old_cwd[0]) + ASSERT_OK(chdir(old_cwd), "restore_cwd"); + + map_fd2 = bpf_obj_get(abs_path); + if (!ASSERT_GE(map_fd2, 0, "map_get")) + goto cleanup; + + /* update map through one FD */ + err = bpf_map_update_elem(map_fd, &zero, &src_value, 0); + ASSERT_OK(err, "map_update"); + + /* check values written/read through different FDs do match */ + dst_value = 0; + err = bpf_map_lookup_elem(map_fd2, &zero, &dst_value); + ASSERT_OK(err, "map_lookup"); + ASSERT_EQ(dst_value, src_value, "map_value_eq"); +cleanup: + if (map_fd2 >= 0) + ASSERT_OK(close(map_fd2), "close_map_fd2"); + unlink(abs_path); +} + +static void validate_get(int map_fd, const char *map_name, int src_value, + enum path_kind path_kind) +{ + LIBBPF_OPTS(bpf_obj_get_opts, get_opts); + char abs_path[PATH_MAX], old_cwd[PATH_MAX]; + const char *pin_path = NULL; + int zero = 0, dst_value, map_fd2, err; + + snprintf(abs_path, sizeof(abs_path), "/sys/fs/bpf/%s", map_name); + /* pin BPF map using specified path definition */ + err = bpf_obj_pin(map_fd, abs_path); + if (!ASSERT_OK(err, "pin_map")) + return; + + old_cwd[0] = '\0'; + + switch (path_kind) { + case PATH_STR_ABS: + /* absolute path */ + pin_path = abs_path; + break; + case PATH_STR_REL: + /* cwd + relative path */ + ASSERT_OK_PTR(getcwd(old_cwd, sizeof(old_cwd)), "getcwd"); + ASSERT_OK(chdir("/sys/fs/bpf"), "chdir"); + pin_path = map_name; + break; + case PATH_FD_REL: + /* dir fd + relative path */ + get_opts.file_flags = BPF_F_PATH_FD; + get_opts.path_fd = open("/sys/fs/bpf", O_PATH); + ASSERT_GE(get_opts.path_fd, 0, "path_fd"); + pin_path = map_name; + break; + } + + map_fd2 = bpf_obj_get_opts(pin_path, &get_opts); + if (!ASSERT_GE(map_fd2, 0, "map_get")) + goto cleanup; + + /* cleanup */ + if (get_opts.path_fd >= 0) + close(get_opts.path_fd); + if (old_cwd[0]) + ASSERT_OK(chdir(old_cwd), "restore_cwd"); + + /* update map through one FD */ + err = bpf_map_update_elem(map_fd, &zero, &src_value, 0); + ASSERT_OK(err, "map_update"); + + /* check values written/read through different FDs do match */ + dst_value = 0; + err = bpf_map_lookup_elem(map_fd2, &zero, &dst_value); + ASSERT_OK(err, "map_lookup"); + ASSERT_EQ(dst_value, src_value, "map_value_eq"); +cleanup: + if (map_fd2 >= 0) + ASSERT_OK(close(map_fd2), "close_map_fd2"); + unlink(abs_path); +} + +static void bpf_obj_pinning_mounted(enum path_kind path_kind) +{ + const char *map_name = "mounted_map"; + int map_fd; + + /* create BPF map to pin */ + map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, map_name, 4, 4, 1, NULL); + if (!ASSERT_GE(map_fd, 0, "map_fd")) + return; + + validate_pin(map_fd, map_name, 100 + (int)path_kind, path_kind); + validate_get(map_fd, map_name, 200 + (int)path_kind, path_kind); + ASSERT_OK(close(map_fd), "close_map_fd"); +} + +void test_bpf_obj_pinning() +{ + if (test__start_subtest("detached")) + bpf_obj_pinning_detached(); + if (test__start_subtest("mounted-str-abs")) + bpf_obj_pinning_mounted(PATH_STR_ABS); + if (test__start_subtest("mounted-str-rel")) + bpf_obj_pinning_mounted(PATH_STR_REL); + if (test__start_subtest("mounted-fd-rel")) + bpf_obj_pinning_mounted(PATH_FD_REL); +} diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c b/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c index 4d2fa99273d8..2bb5773d6f99 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c @@ -25,6 +25,8 @@ static void test_setsockopt_set(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that sets EUNATCH, assert that * we actually get that error when we run setsockopt() */ @@ -59,6 +61,8 @@ static void test_setsockopt_set_and_get(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that sets EUNATCH, and one that gets the * previously set errno. Assert that we get the same errno back. */ @@ -100,6 +104,8 @@ static void test_setsockopt_default_zero(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that gets the previously set errno. * Assert that, without anything setting one, we get 0. */ @@ -134,6 +140,8 @@ static void test_setsockopt_default_zero_and_set(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that gets the previously set errno, and then * one that sets the errno to EUNATCH. Assert that the get does not * see EUNATCH set later, and does not prevent EUNATCH from being set. @@ -177,6 +185,8 @@ static void test_setsockopt_override(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that sets EUNATCH, then one that sets EISCONN, * and then one that gets the exported errno. Assert both the syscall * and the helper sees the last set errno. @@ -224,6 +234,8 @@ static void test_setsockopt_legacy_eperm(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that return a reject without setting errno * (legacy reject), and one that gets the errno. Assert that for * backward compatibility the syscall result in EPERM, and this @@ -268,6 +280,8 @@ static void test_setsockopt_legacy_no_override(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach setsockopt that sets EUNATCH, then one that return a reject * without setting errno, and then one that gets the exported errno. * Assert both the syscall and the helper's errno are unaffected by @@ -319,6 +333,8 @@ static void test_getsockopt_get(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach getsockopt that gets previously set errno. Assert that the * error from kernel is in both ctx_retval_value and retval_value. */ @@ -359,6 +375,8 @@ static void test_getsockopt_override(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach getsockopt that sets retval to -EISCONN. Assert that this * overrides the value from kernel. */ @@ -396,6 +414,8 @@ static void test_getsockopt_retval_sync(int cgroup_fd, int sock_fd) if (!ASSERT_OK_PTR(obj, "skel-load")) return; + obj->bss->page_size = sysconf(_SC_PAGESIZE); + /* Attach getsockopt that sets retval to -EISCONN, and one that clears * ctx retval. Assert that the clearing ctx retval is synced to helper * and clears any errors both from kernel and BPF.. diff --git a/tools/testing/selftests/bpf/prog_tests/dynptr.c b/tools/testing/selftests/bpf/prog_tests/dynptr.c index d176c34a7d2e..7cfac53c0d58 100644 --- a/tools/testing/selftests/bpf/prog_tests/dynptr.c +++ b/tools/testing/selftests/bpf/prog_tests/dynptr.c @@ -20,6 +20,14 @@ static struct { {"test_ringbuf", SETUP_SYSCALL_SLEEP}, {"test_skb_readonly", SETUP_SKB_PROG}, {"test_dynptr_skb_data", SETUP_SKB_PROG}, + {"test_adjust", SETUP_SYSCALL_SLEEP}, + {"test_adjust_err", SETUP_SYSCALL_SLEEP}, + {"test_zero_size_dynptr", SETUP_SYSCALL_SLEEP}, + {"test_dynptr_is_null", SETUP_SYSCALL_SLEEP}, + {"test_dynptr_is_rdonly", SETUP_SKB_PROG}, + {"test_dynptr_clone", SETUP_SKB_PROG}, + {"test_dynptr_skb_no_buff", SETUP_SKB_PROG}, + {"test_dynptr_skb_strcmp", SETUP_SKB_PROG}, }; static void verify_success(const char *prog_name, enum test_setup_type setup_type) diff --git a/tools/testing/selftests/bpf/prog_tests/global_map_resize.c b/tools/testing/selftests/bpf/prog_tests/global_map_resize.c new file mode 100644 index 000000000000..fd41425d2e5c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/global_map_resize.c @@ -0,0 +1,227 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ +#include <errno.h> +#include <sys/syscall.h> +#include <unistd.h> +#include "test_global_map_resize.skel.h" +#include "test_progs.h" + +static void run_prog_bss_array_sum(void) +{ + (void)syscall(__NR_getpid); +} + +static void run_prog_data_array_sum(void) +{ + (void)syscall(__NR_getuid); +} + +static void global_map_resize_bss_subtest(void) +{ + int err; + struct test_global_map_resize *skel; + struct bpf_map *map; + const __u32 desired_sz = sizeof(skel->bss->sum) + sysconf(_SC_PAGE_SIZE) * 2; + size_t array_len, actual_sz; + + skel = test_global_map_resize__open(); + if (!ASSERT_OK_PTR(skel, "test_global_map_resize__open")) + goto teardown; + + /* set some initial value before resizing. + * it is expected this non-zero value will be preserved + * while resizing. + */ + skel->bss->array[0] = 1; + + /* resize map value and verify the new size */ + map = skel->maps.bss; + err = bpf_map__set_value_size(map, desired_sz); + if (!ASSERT_OK(err, "bpf_map__set_value_size")) + goto teardown; + if (!ASSERT_EQ(bpf_map__value_size(map), desired_sz, "resize")) + goto teardown; + + /* set the expected number of elements based on the resized array */ + array_len = (desired_sz - sizeof(skel->bss->sum)) / sizeof(skel->bss->array[0]); + if (!ASSERT_GT(array_len, 1, "array_len")) + goto teardown; + + skel->bss = bpf_map__initial_value(skel->maps.bss, &actual_sz); + if (!ASSERT_OK_PTR(skel->bss, "bpf_map__initial_value (ptr)")) + goto teardown; + if (!ASSERT_EQ(actual_sz, desired_sz, "bpf_map__initial_value (size)")) + goto teardown; + + /* fill the newly resized array with ones, + * skipping the first element which was previously set + */ + for (int i = 1; i < array_len; i++) + skel->bss->array[i] = 1; + + /* set global const values before loading */ + skel->rodata->pid = getpid(); + skel->rodata->bss_array_len = array_len; + skel->rodata->data_array_len = 1; + + err = test_global_map_resize__load(skel); + if (!ASSERT_OK(err, "test_global_map_resize__load")) + goto teardown; + err = test_global_map_resize__attach(skel); + if (!ASSERT_OK(err, "test_global_map_resize__attach")) + goto teardown; + + /* run the bpf program which will sum the contents of the array. + * since the array was filled with ones,verify the sum equals array_len + */ + run_prog_bss_array_sum(); + if (!ASSERT_EQ(skel->bss->sum, array_len, "sum")) + goto teardown; + +teardown: + test_global_map_resize__destroy(skel); +} + +static void global_map_resize_data_subtest(void) +{ + int err; + struct test_global_map_resize *skel; + struct bpf_map *map; + const __u32 desired_sz = sysconf(_SC_PAGE_SIZE) * 2; + size_t array_len, actual_sz; + + skel = test_global_map_resize__open(); + if (!ASSERT_OK_PTR(skel, "test_global_map_resize__open")) + goto teardown; + + /* set some initial value before resizing. + * it is expected this non-zero value will be preserved + * while resizing. + */ + skel->data_custom->my_array[0] = 1; + + /* resize map value and verify the new size */ + map = skel->maps.data_custom; + err = bpf_map__set_value_size(map, desired_sz); + if (!ASSERT_OK(err, "bpf_map__set_value_size")) + goto teardown; + if (!ASSERT_EQ(bpf_map__value_size(map), desired_sz, "resize")) + goto teardown; + + /* set the expected number of elements based on the resized array */ + array_len = (desired_sz - sizeof(skel->bss->sum)) / sizeof(skel->data_custom->my_array[0]); + if (!ASSERT_GT(array_len, 1, "array_len")) + goto teardown; + + skel->data_custom = bpf_map__initial_value(skel->maps.data_custom, &actual_sz); + if (!ASSERT_OK_PTR(skel->data_custom, "bpf_map__initial_value (ptr)")) + goto teardown; + if (!ASSERT_EQ(actual_sz, desired_sz, "bpf_map__initial_value (size)")) + goto teardown; + + /* fill the newly resized array with ones, + * skipping the first element which was previously set + */ + for (int i = 1; i < array_len; i++) + skel->data_custom->my_array[i] = 1; + + /* set global const values before loading */ + skel->rodata->pid = getpid(); + skel->rodata->bss_array_len = 1; + skel->rodata->data_array_len = array_len; + + err = test_global_map_resize__load(skel); + if (!ASSERT_OK(err, "test_global_map_resize__load")) + goto teardown; + err = test_global_map_resize__attach(skel); + if (!ASSERT_OK(err, "test_global_map_resize__attach")) + goto teardown; + + /* run the bpf program which will sum the contents of the array. + * since the array was filled with ones,verify the sum equals array_len + */ + run_prog_data_array_sum(); + if (!ASSERT_EQ(skel->bss->sum, array_len, "sum")) + goto teardown; + +teardown: + test_global_map_resize__destroy(skel); +} + +static void global_map_resize_invalid_subtest(void) +{ + int err; + struct test_global_map_resize *skel; + struct bpf_map *map; + __u32 element_sz, desired_sz; + + skel = test_global_map_resize__open(); + if (!ASSERT_OK_PTR(skel, "test_global_map_resize__open")) + return; + + /* attempt to resize a global datasec map to size + * which does NOT align with array + */ + map = skel->maps.data_custom; + if (!ASSERT_NEQ(bpf_map__btf_value_type_id(map), 0, ".data.custom initial btf")) + goto teardown; + /* set desired size a fraction of element size beyond an aligned size */ + element_sz = sizeof(skel->data_custom->my_array[0]); + desired_sz = element_sz + element_sz / 2; + /* confirm desired size does NOT align with array */ + if (!ASSERT_NEQ(desired_sz % element_sz, 0, "my_array alignment")) + goto teardown; + err = bpf_map__set_value_size(map, desired_sz); + /* confirm resize is OK but BTF info is cleared */ + if (!ASSERT_OK(err, ".data.custom bpf_map__set_value_size") || + !ASSERT_EQ(bpf_map__btf_key_type_id(map), 0, ".data.custom clear btf key") || + !ASSERT_EQ(bpf_map__btf_value_type_id(map), 0, ".data.custom clear btf val")) + goto teardown; + + /* attempt to resize a global datasec map whose only var is NOT an array */ + map = skel->maps.data_non_array; + if (!ASSERT_NEQ(bpf_map__btf_value_type_id(map), 0, ".data.non_array initial btf")) + goto teardown; + /* set desired size to arbitrary value */ + desired_sz = 1024; + err = bpf_map__set_value_size(map, desired_sz); + /* confirm resize is OK but BTF info is cleared */ + if (!ASSERT_OK(err, ".data.non_array bpf_map__set_value_size") || + !ASSERT_EQ(bpf_map__btf_key_type_id(map), 0, ".data.non_array clear btf key") || + !ASSERT_EQ(bpf_map__btf_value_type_id(map), 0, ".data.non_array clear btf val")) + goto teardown; + + /* attempt to resize a global datasec map + * whose last var is NOT an array + */ + map = skel->maps.data_array_not_last; + if (!ASSERT_NEQ(bpf_map__btf_value_type_id(map), 0, ".data.array_not_last initial btf")) + goto teardown; + /* set desired size to a multiple of element size */ + element_sz = sizeof(skel->data_array_not_last->my_array_first[0]); + desired_sz = element_sz * 8; + /* confirm desired size aligns with array */ + if (!ASSERT_EQ(desired_sz % element_sz, 0, "my_array_first alignment")) + goto teardown; + err = bpf_map__set_value_size(map, desired_sz); + /* confirm resize is OK but BTF info is cleared */ + if (!ASSERT_OK(err, ".data.array_not_last bpf_map__set_value_size") || + !ASSERT_EQ(bpf_map__btf_key_type_id(map), 0, ".data.array_not_last clear btf key") || + !ASSERT_EQ(bpf_map__btf_value_type_id(map), 0, ".data.array_not_last clear btf val")) + goto teardown; + +teardown: + test_global_map_resize__destroy(skel); +} + +void test_global_map_resize(void) +{ + if (test__start_subtest("global_map_resize_bss")) + global_map_resize_bss_subtest(); + + if (test__start_subtest("global_map_resize_data")) + global_map_resize_data_subtest(); + + if (test__start_subtest("global_map_resize_invalid")) + global_map_resize_invalid_subtest(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/inner_array_lookup.c b/tools/testing/selftests/bpf/prog_tests/inner_array_lookup.c new file mode 100644 index 000000000000..9ab4cd195108 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/inner_array_lookup.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <test_progs.h> + +#include "inner_array_lookup.skel.h" + +void test_inner_array_lookup(void) +{ + int map1_fd, err; + int key = 3; + int val = 1; + struct inner_array_lookup *skel; + + skel = inner_array_lookup__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_load_skeleton")) + return; + + err = inner_array_lookup__attach(skel); + if (!ASSERT_OK(err, "skeleton_attach")) + goto cleanup; + + map1_fd = bpf_map__fd(skel->maps.inner_map1); + bpf_map_update_elem(map1_fd, &key, &val, 0); + + /* Probe should have set the element at index 3 to 2 */ + bpf_map_lookup_elem(map1_fd, &key, &val); + ASSERT_EQ(val, 2, "value_is_2"); + +cleanup: + inner_array_lookup__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/module_attach.c b/tools/testing/selftests/bpf/prog_tests/module_attach.c index 7fc01ff490db..f53d658ed080 100644 --- a/tools/testing/selftests/bpf/prog_tests/module_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/module_attach.c @@ -4,6 +4,7 @@ #include <test_progs.h> #include <stdbool.h> #include "test_module_attach.skel.h" +#include "testing_helpers.h" static int duration; @@ -32,11 +33,6 @@ static int trigger_module_test_writable(int *val) return 0; } -static int delete_module(const char *name, int flags) -{ - return syscall(__NR_delete_module, name, flags); -} - void test_module_attach(void) { const int READ_SZ = 456; @@ -93,21 +89,21 @@ void test_module_attach(void) if (!ASSERT_OK_PTR(link, "attach_fentry")) goto cleanup; - ASSERT_ERR(delete_module("bpf_testmod", 0), "delete_module"); + ASSERT_ERR(unload_bpf_testmod(false), "unload_bpf_testmod"); bpf_link__destroy(link); link = bpf_program__attach(skel->progs.handle_fexit); if (!ASSERT_OK_PTR(link, "attach_fexit")) goto cleanup; - ASSERT_ERR(delete_module("bpf_testmod", 0), "delete_module"); + ASSERT_ERR(unload_bpf_testmod(false), "unload_bpf_testmod"); bpf_link__destroy(link); link = bpf_program__attach(skel->progs.kprobe_multi); if (!ASSERT_OK_PTR(link, "attach_kprobe_multi")) goto cleanup; - ASSERT_ERR(delete_module("bpf_testmod", 0), "delete_module"); + ASSERT_ERR(unload_bpf_testmod(false), "unload_bpf_testmod"); bpf_link__destroy(link); cleanup: diff --git a/tools/testing/selftests/bpf/prog_tests/netcnt.c b/tools/testing/selftests/bpf/prog_tests/netcnt.c index d3915c58d0e1..c3333edd029f 100644 --- a/tools/testing/selftests/bpf/prog_tests/netcnt.c +++ b/tools/testing/selftests/bpf/prog_tests/netcnt.c @@ -67,12 +67,12 @@ void serial_test_netcnt(void) } /* No packets should be lost */ - ASSERT_EQ(packets, 10000, "packets"); + ASSERT_GE(packets, 10000, "packets"); /* Let's check that bytes counter matches the number of packets * multiplied by the size of ipv6 ICMP packet. */ - ASSERT_EQ(bytes, packets * 104, "bytes"); + ASSERT_GE(bytes, packets * 104, "bytes"); err: if (cg_fd != -1) diff --git a/tools/testing/selftests/bpf/prog_tests/sock_destroy.c b/tools/testing/selftests/bpf/prog_tests/sock_destroy.c new file mode 100644 index 000000000000..b0583309a94e --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sock_destroy.c @@ -0,0 +1,221 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <bpf/bpf_endian.h> + +#include "sock_destroy_prog.skel.h" +#include "sock_destroy_prog_fail.skel.h" +#include "network_helpers.h" + +#define TEST_NS "sock_destroy_netns" + +static void start_iter_sockets(struct bpf_program *prog) +{ + struct bpf_link *link; + char buf[50] = {}; + int iter_fd, len; + + link = bpf_program__attach_iter(prog, NULL); + if (!ASSERT_OK_PTR(link, "attach_iter")) + return; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (!ASSERT_GE(iter_fd, 0, "create_iter")) + goto free_link; + + while ((len = read(iter_fd, buf, sizeof(buf))) > 0) + ; + ASSERT_GE(len, 0, "read"); + + close(iter_fd); + +free_link: + bpf_link__destroy(link); +} + +static void test_tcp_client(struct sock_destroy_prog *skel) +{ + int serv = -1, clien = -1, accept_serv = -1, n; + + serv = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0); + if (!ASSERT_GE(serv, 0, "start_server")) + goto cleanup; + + clien = connect_to_fd(serv, 0); + if (!ASSERT_GE(clien, 0, "connect_to_fd")) + goto cleanup; + + accept_serv = accept(serv, NULL, NULL); + if (!ASSERT_GE(accept_serv, 0, "serv accept")) + goto cleanup; + + n = send(clien, "t", 1, 0); + if (!ASSERT_EQ(n, 1, "client send")) + goto cleanup; + + /* Run iterator program that destroys connected client sockets. */ + start_iter_sockets(skel->progs.iter_tcp6_client); + + n = send(clien, "t", 1, 0); + if (!ASSERT_LT(n, 0, "client_send on destroyed socket")) + goto cleanup; + ASSERT_EQ(errno, ECONNABORTED, "error code on destroyed socket"); + +cleanup: + if (clien != -1) + close(clien); + if (accept_serv != -1) + close(accept_serv); + if (serv != -1) + close(serv); +} + +static void test_tcp_server(struct sock_destroy_prog *skel) +{ + int serv = -1, clien = -1, accept_serv = -1, n, serv_port; + + serv = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0); + if (!ASSERT_GE(serv, 0, "start_server")) + goto cleanup; + serv_port = get_socket_local_port(serv); + if (!ASSERT_GE(serv_port, 0, "get_sock_local_port")) + goto cleanup; + skel->bss->serv_port = (__be16) serv_port; + + clien = connect_to_fd(serv, 0); + if (!ASSERT_GE(clien, 0, "connect_to_fd")) + goto cleanup; + + accept_serv = accept(serv, NULL, NULL); + if (!ASSERT_GE(accept_serv, 0, "serv accept")) + goto cleanup; + + n = send(clien, "t", 1, 0); + if (!ASSERT_EQ(n, 1, "client send")) + goto cleanup; + + /* Run iterator program that destroys server sockets. */ + start_iter_sockets(skel->progs.iter_tcp6_server); + + n = send(clien, "t", 1, 0); + if (!ASSERT_LT(n, 0, "client_send on destroyed socket")) + goto cleanup; + ASSERT_EQ(errno, ECONNRESET, "error code on destroyed socket"); + +cleanup: + if (clien != -1) + close(clien); + if (accept_serv != -1) + close(accept_serv); + if (serv != -1) + close(serv); +} + +static void test_udp_client(struct sock_destroy_prog *skel) +{ + int serv = -1, clien = -1, n = 0; + + serv = start_server(AF_INET6, SOCK_DGRAM, NULL, 0, 0); + if (!ASSERT_GE(serv, 0, "start_server")) + goto cleanup; + + clien = connect_to_fd(serv, 0); + if (!ASSERT_GE(clien, 0, "connect_to_fd")) + goto cleanup; + + n = send(clien, "t", 1, 0); + if (!ASSERT_EQ(n, 1, "client send")) + goto cleanup; + + /* Run iterator program that destroys sockets. */ + start_iter_sockets(skel->progs.iter_udp6_client); + + n = send(clien, "t", 1, 0); + if (!ASSERT_LT(n, 0, "client_send on destroyed socket")) + goto cleanup; + /* UDP sockets have an overriding error code after they are disconnected, + * so we don't check for ECONNABORTED error code. + */ + +cleanup: + if (clien != -1) + close(clien); + if (serv != -1) + close(serv); +} + +static void test_udp_server(struct sock_destroy_prog *skel) +{ + int *listen_fds = NULL, n, i, serv_port; + unsigned int num_listens = 5; + char buf[1]; + + /* Start reuseport servers. */ + listen_fds = start_reuseport_server(AF_INET6, SOCK_DGRAM, + "::1", 0, 0, num_listens); + if (!ASSERT_OK_PTR(listen_fds, "start_reuseport_server")) + goto cleanup; + serv_port = get_socket_local_port(listen_fds[0]); + if (!ASSERT_GE(serv_port, 0, "get_sock_local_port")) + goto cleanup; + skel->bss->serv_port = (__be16) serv_port; + + /* Run iterator program that destroys server sockets. */ + start_iter_sockets(skel->progs.iter_udp6_server); + + for (i = 0; i < num_listens; ++i) { + n = read(listen_fds[i], buf, sizeof(buf)); + if (!ASSERT_EQ(n, -1, "read") || + !ASSERT_EQ(errno, ECONNABORTED, "error code on destroyed socket")) + break; + } + ASSERT_EQ(i, num_listens, "server socket"); + +cleanup: + free_fds(listen_fds, num_listens); +} + +void test_sock_destroy(void) +{ + struct sock_destroy_prog *skel; + struct nstoken *nstoken = NULL; + int cgroup_fd; + + skel = sock_destroy_prog__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return; + + cgroup_fd = test__join_cgroup("/sock_destroy"); + if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup")) + goto cleanup; + + skel->links.sock_connect = bpf_program__attach_cgroup( + skel->progs.sock_connect, cgroup_fd); + if (!ASSERT_OK_PTR(skel->links.sock_connect, "prog_attach")) + goto cleanup; + + SYS(cleanup, "ip netns add %s", TEST_NS); + SYS(cleanup, "ip -net %s link set dev lo up", TEST_NS); + + nstoken = open_netns(TEST_NS); + if (!ASSERT_OK_PTR(nstoken, "open_netns")) + goto cleanup; + + if (test__start_subtest("tcp_client")) + test_tcp_client(skel); + if (test__start_subtest("tcp_server")) + test_tcp_server(skel); + if (test__start_subtest("udp_client")) + test_udp_client(skel); + if (test__start_subtest("udp_server")) + test_udp_server(skel); + + RUN_TESTS(sock_destroy_prog_fail); + +cleanup: + if (nstoken) + close_netns(nstoken); + SYS_NOFAIL("ip netns del " TEST_NS " &> /dev/null"); + if (cgroup_fd >= 0) + close(cgroup_fd); + sock_destroy_prog__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 0ce25a967481..064cc5e8d9ad 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -2,6 +2,7 @@ // Copyright (c) 2020 Cloudflare #include <error.h> #include <netinet/tcp.h> +#include <sys/epoll.h> #include "test_progs.h" #include "test_skmsg_load_helpers.skel.h" @@ -9,8 +10,12 @@ #include "test_sockmap_invalid_update.skel.h" #include "test_sockmap_skb_verdict_attach.skel.h" #include "test_sockmap_progs_query.skel.h" +#include "test_sockmap_pass_prog.skel.h" +#include "test_sockmap_drop_prog.skel.h" #include "bpf_iter_sockmap.skel.h" +#include "sockmap_helpers.h" + #define TCP_REPAIR 19 /* TCP sock is under repair right now */ #define TCP_REPAIR_ON 1 @@ -350,6 +355,126 @@ out: test_sockmap_progs_query__destroy(skel); } +#define MAX_EVENTS 10 +static void test_sockmap_skb_verdict_shutdown(void) +{ + struct epoll_event ev, events[MAX_EVENTS]; + int n, err, map, verdict, s, c1, p1; + struct test_sockmap_pass_prog *skel; + int epollfd; + int zero = 0; + char b; + + skel = test_sockmap_pass_prog__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + + verdict = bpf_program__fd(skel->progs.prog_skb_verdict); + map = bpf_map__fd(skel->maps.sock_map_rx); + + err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0); + if (!ASSERT_OK(err, "bpf_prog_attach")) + goto out; + + s = socket_loopback(AF_INET, SOCK_STREAM); + if (s < 0) + goto out; + err = create_pair(s, AF_INET, SOCK_STREAM, &c1, &p1); + if (err < 0) + goto out; + + err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST); + if (err < 0) + goto out_close; + + shutdown(p1, SHUT_WR); + + ev.events = EPOLLIN; + ev.data.fd = c1; + + epollfd = epoll_create1(0); + if (!ASSERT_GT(epollfd, -1, "epoll_create(0)")) + goto out_close; + err = epoll_ctl(epollfd, EPOLL_CTL_ADD, c1, &ev); + if (!ASSERT_OK(err, "epoll_ctl(EPOLL_CTL_ADD)")) + goto out_close; + err = epoll_wait(epollfd, events, MAX_EVENTS, -1); + if (!ASSERT_EQ(err, 1, "epoll_wait(fd)")) + goto out_close; + + n = recv(c1, &b, 1, SOCK_NONBLOCK); + ASSERT_EQ(n, 0, "recv_timeout(fin)"); +out_close: + close(c1); + close(p1); +out: + test_sockmap_pass_prog__destroy(skel); +} + +static void test_sockmap_skb_verdict_fionread(bool pass_prog) +{ + int expected, zero = 0, sent, recvd, avail; + int err, map, verdict, s, c0, c1, p0, p1; + struct test_sockmap_pass_prog *pass; + struct test_sockmap_drop_prog *drop; + char buf[256] = "0123456789"; + + if (pass_prog) { + pass = test_sockmap_pass_prog__open_and_load(); + if (!ASSERT_OK_PTR(pass, "open_and_load")) + return; + verdict = bpf_program__fd(pass->progs.prog_skb_verdict); + map = bpf_map__fd(pass->maps.sock_map_rx); + expected = sizeof(buf); + } else { + drop = test_sockmap_drop_prog__open_and_load(); + if (!ASSERT_OK_PTR(drop, "open_and_load")) + return; + verdict = bpf_program__fd(drop->progs.prog_skb_verdict); + map = bpf_map__fd(drop->maps.sock_map_rx); + /* On drop data is consumed immediately and copied_seq inc'd */ + expected = 0; + } + + + err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0); + if (!ASSERT_OK(err, "bpf_prog_attach")) + goto out; + + s = socket_loopback(AF_INET, SOCK_STREAM); + if (!ASSERT_GT(s, -1, "socket_loopback(s)")) + goto out; + err = create_socket_pairs(s, AF_INET, SOCK_STREAM, &c0, &c1, &p0, &p1); + if (!ASSERT_OK(err, "create_socket_pairs(s)")) + goto out; + + err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(c1)")) + goto out_close; + + sent = xsend(p1, &buf, sizeof(buf), 0); + ASSERT_EQ(sent, sizeof(buf), "xsend(p0)"); + err = ioctl(c1, FIONREAD, &avail); + ASSERT_OK(err, "ioctl(FIONREAD) error"); + ASSERT_EQ(avail, expected, "ioctl(FIONREAD)"); + /* On DROP test there will be no data to read */ + if (pass_prog) { + recvd = recv_timeout(c1, &buf, sizeof(buf), SOCK_NONBLOCK, IO_TIMEOUT_SEC); + ASSERT_EQ(recvd, sizeof(buf), "recv_timeout(c0)"); + } + +out_close: + close(c0); + close(p0); + close(c1); + close(p1); +out: + if (pass_prog) + test_sockmap_pass_prog__destroy(pass); + else + test_sockmap_drop_prog__destroy(drop); +} + void test_sockmap_basic(void) { if (test__start_subtest("sockmap create_update_free")) @@ -384,4 +509,10 @@ void test_sockmap_basic(void) test_sockmap_progs_query(BPF_SK_SKB_STREAM_VERDICT); if (test__start_subtest("sockmap skb_verdict progs query")) test_sockmap_progs_query(BPF_SK_SKB_VERDICT); + if (test__start_subtest("sockmap skb_verdict shutdown")) + test_sockmap_skb_verdict_shutdown(); + if (test__start_subtest("sockmap skb_verdict fionread")) + test_sockmap_skb_verdict_fionread(true); + if (test__start_subtest("sockmap skb_verdict fionread on drop")) + test_sockmap_skb_verdict_fionread(false); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h new file mode 100644 index 000000000000..d12665490a90 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h @@ -0,0 +1,390 @@ +#ifndef __SOCKMAP_HELPERS__ +#define __SOCKMAP_HELPERS__ + +#include <linux/vm_sockets.h> + +#define IO_TIMEOUT_SEC 30 +#define MAX_STRERR_LEN 256 +#define MAX_TEST_NAME 80 + +/* workaround for older vm_sockets.h */ +#ifndef VMADDR_CID_LOCAL +#define VMADDR_CID_LOCAL 1 +#endif + +#define __always_unused __attribute__((__unused__)) + +#define _FAIL(errnum, fmt...) \ + ({ \ + error_at_line(0, (errnum), __func__, __LINE__, fmt); \ + CHECK_FAIL(true); \ + }) +#define FAIL(fmt...) _FAIL(0, fmt) +#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt) +#define FAIL_LIBBPF(err, msg) \ + ({ \ + char __buf[MAX_STRERR_LEN]; \ + libbpf_strerror((err), __buf, sizeof(__buf)); \ + FAIL("%s: %s", (msg), __buf); \ + }) + +/* Wrappers that fail the test on error and report it. */ + +#define xaccept_nonblock(fd, addr, len) \ + ({ \ + int __ret = \ + accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC); \ + if (__ret == -1) \ + FAIL_ERRNO("accept"); \ + __ret; \ + }) + +#define xbind(fd, addr, len) \ + ({ \ + int __ret = bind((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("bind"); \ + __ret; \ + }) + +#define xclose(fd) \ + ({ \ + int __ret = close((fd)); \ + if (__ret == -1) \ + FAIL_ERRNO("close"); \ + __ret; \ + }) + +#define xconnect(fd, addr, len) \ + ({ \ + int __ret = connect((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("connect"); \ + __ret; \ + }) + +#define xgetsockname(fd, addr, len) \ + ({ \ + int __ret = getsockname((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("getsockname"); \ + __ret; \ + }) + +#define xgetsockopt(fd, level, name, val, len) \ + ({ \ + int __ret = getsockopt((fd), (level), (name), (val), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("getsockopt(" #name ")"); \ + __ret; \ + }) + +#define xlisten(fd, backlog) \ + ({ \ + int __ret = listen((fd), (backlog)); \ + if (__ret == -1) \ + FAIL_ERRNO("listen"); \ + __ret; \ + }) + +#define xsetsockopt(fd, level, name, val, len) \ + ({ \ + int __ret = setsockopt((fd), (level), (name), (val), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("setsockopt(" #name ")"); \ + __ret; \ + }) + +#define xsend(fd, buf, len, flags) \ + ({ \ + ssize_t __ret = send((fd), (buf), (len), (flags)); \ + if (__ret == -1) \ + FAIL_ERRNO("send"); \ + __ret; \ + }) + +#define xrecv_nonblock(fd, buf, len, flags) \ + ({ \ + ssize_t __ret = recv_timeout((fd), (buf), (len), (flags), \ + IO_TIMEOUT_SEC); \ + if (__ret == -1) \ + FAIL_ERRNO("recv"); \ + __ret; \ + }) + +#define xsocket(family, sotype, flags) \ + ({ \ + int __ret = socket(family, sotype, flags); \ + if (__ret == -1) \ + FAIL_ERRNO("socket"); \ + __ret; \ + }) + +#define xbpf_map_delete_elem(fd, key) \ + ({ \ + int __ret = bpf_map_delete_elem((fd), (key)); \ + if (__ret < 0) \ + FAIL_ERRNO("map_delete"); \ + __ret; \ + }) + +#define xbpf_map_lookup_elem(fd, key, val) \ + ({ \ + int __ret = bpf_map_lookup_elem((fd), (key), (val)); \ + if (__ret < 0) \ + FAIL_ERRNO("map_lookup"); \ + __ret; \ + }) + +#define xbpf_map_update_elem(fd, key, val, flags) \ + ({ \ + int __ret = bpf_map_update_elem((fd), (key), (val), (flags)); \ + if (__ret < 0) \ + FAIL_ERRNO("map_update"); \ + __ret; \ + }) + +#define xbpf_prog_attach(prog, target, type, flags) \ + ({ \ + int __ret = \ + bpf_prog_attach((prog), (target), (type), (flags)); \ + if (__ret < 0) \ + FAIL_ERRNO("prog_attach(" #type ")"); \ + __ret; \ + }) + +#define xbpf_prog_detach2(prog, target, type) \ + ({ \ + int __ret = bpf_prog_detach2((prog), (target), (type)); \ + if (__ret < 0) \ + FAIL_ERRNO("prog_detach2(" #type ")"); \ + __ret; \ + }) + +#define xpthread_create(thread, attr, func, arg) \ + ({ \ + int __ret = pthread_create((thread), (attr), (func), (arg)); \ + errno = __ret; \ + if (__ret) \ + FAIL_ERRNO("pthread_create"); \ + __ret; \ + }) + +#define xpthread_join(thread, retval) \ + ({ \ + int __ret = pthread_join((thread), (retval)); \ + errno = __ret; \ + if (__ret) \ + FAIL_ERRNO("pthread_join"); \ + __ret; \ + }) + +static inline int poll_read(int fd, unsigned int timeout_sec) +{ + struct timeval timeout = { .tv_sec = timeout_sec }; + fd_set rfds; + int r; + + FD_ZERO(&rfds); + FD_SET(fd, &rfds); + + r = select(fd + 1, &rfds, NULL, NULL, &timeout); + if (r == 0) + errno = ETIME; + + return r == 1 ? 0 : -1; +} + +static inline int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len, + unsigned int timeout_sec) +{ + if (poll_read(fd, timeout_sec)) + return -1; + + return accept(fd, addr, len); +} + +static inline int recv_timeout(int fd, void *buf, size_t len, int flags, + unsigned int timeout_sec) +{ + if (poll_read(fd, timeout_sec)) + return -1; + + return recv(fd, buf, len, flags); +} + +static inline void init_addr_loopback4(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss)); + + addr4->sin_family = AF_INET; + addr4->sin_port = 0; + addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); + *len = sizeof(*addr4); +} + +static inline void init_addr_loopback6(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss)); + + addr6->sin6_family = AF_INET6; + addr6->sin6_port = 0; + addr6->sin6_addr = in6addr_loopback; + *len = sizeof(*addr6); +} + +static inline void init_addr_loopback_vsock(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_vm *addr = memset(ss, 0, sizeof(*ss)); + + addr->svm_family = AF_VSOCK; + addr->svm_port = VMADDR_PORT_ANY; + addr->svm_cid = VMADDR_CID_LOCAL; + *len = sizeof(*addr); +} + +static inline void init_addr_loopback(int family, struct sockaddr_storage *ss, + socklen_t *len) +{ + switch (family) { + case AF_INET: + init_addr_loopback4(ss, len); + return; + case AF_INET6: + init_addr_loopback6(ss, len); + return; + case AF_VSOCK: + init_addr_loopback_vsock(ss, len); + return; + default: + FAIL("unsupported address family %d", family); + } +} + +static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss) +{ + return (struct sockaddr *)ss; +} + +static inline int add_to_sockmap(int sock_mapfd, int fd1, int fd2) +{ + u64 value; + u32 key; + int err; + + key = 0; + value = fd1; + err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); + if (err) + return err; + + key = 1; + value = fd2; + return xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); +} + +static inline int create_pair(int s, int family, int sotype, int *c, int *p) +{ + struct sockaddr_storage addr; + socklen_t len; + int err = 0; + + len = sizeof(addr); + err = xgetsockname(s, sockaddr(&addr), &len); + if (err) + return err; + + *c = xsocket(family, sotype, 0); + if (*c < 0) + return errno; + err = xconnect(*c, sockaddr(&addr), len); + if (err) { + err = errno; + goto close_cli0; + } + + *p = xaccept_nonblock(s, NULL, NULL); + if (*p < 0) { + err = errno; + goto close_cli0; + } + return err; +close_cli0: + close(*c); + return err; +} + +static inline int create_socket_pairs(int s, int family, int sotype, + int *c0, int *c1, int *p0, int *p1) +{ + int err; + + err = create_pair(s, family, sotype, c0, p0); + if (err) + return err; + + err = create_pair(s, family, sotype, c1, p1); + if (err) { + close(*c0); + close(*p0); + } + return err; +} + +static inline int enable_reuseport(int s, int progfd) +{ + int err, one = 1; + + err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one)); + if (err) + return -1; + err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd, + sizeof(progfd)); + if (err) + return -1; + + return 0; +} + +static inline int socket_loopback_reuseport(int family, int sotype, int progfd) +{ + struct sockaddr_storage addr; + socklen_t len; + int err, s; + + init_addr_loopback(family, &addr, &len); + + s = xsocket(family, sotype, 0); + if (s == -1) + return -1; + + if (progfd >= 0) + enable_reuseport(s, progfd); + + err = xbind(s, sockaddr(&addr), len); + if (err) + goto close; + + if (sotype & SOCK_DGRAM) + return s; + + err = xlisten(s, SOMAXCONN); + if (err) + goto close; + + return s; +close: + xclose(s); + return -1; +} + +static inline int socket_loopback(int family, int sotype) +{ + return socket_loopback_reuseport(family, sotype, -1); +} + + +#endif // __SOCKMAP_HELPERS__ diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index 141c1e5944ee..b4f6f3a50ae5 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -20,11 +20,6 @@ #include <unistd.h> #include <linux/vm_sockets.h> -/* workaround for older vm_sockets.h */ -#ifndef VMADDR_CID_LOCAL -#define VMADDR_CID_LOCAL 1 -#endif - #include <bpf/bpf.h> #include <bpf/libbpf.h> @@ -32,315 +27,7 @@ #include "test_progs.h" #include "test_sockmap_listen.skel.h" -#define IO_TIMEOUT_SEC 30 -#define MAX_STRERR_LEN 256 -#define MAX_TEST_NAME 80 - -#define __always_unused __attribute__((__unused__)) - -#define _FAIL(errnum, fmt...) \ - ({ \ - error_at_line(0, (errnum), __func__, __LINE__, fmt); \ - CHECK_FAIL(true); \ - }) -#define FAIL(fmt...) _FAIL(0, fmt) -#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt) -#define FAIL_LIBBPF(err, msg) \ - ({ \ - char __buf[MAX_STRERR_LEN]; \ - libbpf_strerror((err), __buf, sizeof(__buf)); \ - FAIL("%s: %s", (msg), __buf); \ - }) - -/* Wrappers that fail the test on error and report it. */ - -#define xaccept_nonblock(fd, addr, len) \ - ({ \ - int __ret = \ - accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC); \ - if (__ret == -1) \ - FAIL_ERRNO("accept"); \ - __ret; \ - }) - -#define xbind(fd, addr, len) \ - ({ \ - int __ret = bind((fd), (addr), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("bind"); \ - __ret; \ - }) - -#define xclose(fd) \ - ({ \ - int __ret = close((fd)); \ - if (__ret == -1) \ - FAIL_ERRNO("close"); \ - __ret; \ - }) - -#define xconnect(fd, addr, len) \ - ({ \ - int __ret = connect((fd), (addr), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("connect"); \ - __ret; \ - }) - -#define xgetsockname(fd, addr, len) \ - ({ \ - int __ret = getsockname((fd), (addr), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("getsockname"); \ - __ret; \ - }) - -#define xgetsockopt(fd, level, name, val, len) \ - ({ \ - int __ret = getsockopt((fd), (level), (name), (val), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("getsockopt(" #name ")"); \ - __ret; \ - }) - -#define xlisten(fd, backlog) \ - ({ \ - int __ret = listen((fd), (backlog)); \ - if (__ret == -1) \ - FAIL_ERRNO("listen"); \ - __ret; \ - }) - -#define xsetsockopt(fd, level, name, val, len) \ - ({ \ - int __ret = setsockopt((fd), (level), (name), (val), (len)); \ - if (__ret == -1) \ - FAIL_ERRNO("setsockopt(" #name ")"); \ - __ret; \ - }) - -#define xsend(fd, buf, len, flags) \ - ({ \ - ssize_t __ret = send((fd), (buf), (len), (flags)); \ - if (__ret == -1) \ - FAIL_ERRNO("send"); \ - __ret; \ - }) - -#define xrecv_nonblock(fd, buf, len, flags) \ - ({ \ - ssize_t __ret = recv_timeout((fd), (buf), (len), (flags), \ - IO_TIMEOUT_SEC); \ - if (__ret == -1) \ - FAIL_ERRNO("recv"); \ - __ret; \ - }) - -#define xsocket(family, sotype, flags) \ - ({ \ - int __ret = socket(family, sotype, flags); \ - if (__ret == -1) \ - FAIL_ERRNO("socket"); \ - __ret; \ - }) - -#define xbpf_map_delete_elem(fd, key) \ - ({ \ - int __ret = bpf_map_delete_elem((fd), (key)); \ - if (__ret < 0) \ - FAIL_ERRNO("map_delete"); \ - __ret; \ - }) - -#define xbpf_map_lookup_elem(fd, key, val) \ - ({ \ - int __ret = bpf_map_lookup_elem((fd), (key), (val)); \ - if (__ret < 0) \ - FAIL_ERRNO("map_lookup"); \ - __ret; \ - }) - -#define xbpf_map_update_elem(fd, key, val, flags) \ - ({ \ - int __ret = bpf_map_update_elem((fd), (key), (val), (flags)); \ - if (__ret < 0) \ - FAIL_ERRNO("map_update"); \ - __ret; \ - }) - -#define xbpf_prog_attach(prog, target, type, flags) \ - ({ \ - int __ret = \ - bpf_prog_attach((prog), (target), (type), (flags)); \ - if (__ret < 0) \ - FAIL_ERRNO("prog_attach(" #type ")"); \ - __ret; \ - }) - -#define xbpf_prog_detach2(prog, target, type) \ - ({ \ - int __ret = bpf_prog_detach2((prog), (target), (type)); \ - if (__ret < 0) \ - FAIL_ERRNO("prog_detach2(" #type ")"); \ - __ret; \ - }) - -#define xpthread_create(thread, attr, func, arg) \ - ({ \ - int __ret = pthread_create((thread), (attr), (func), (arg)); \ - errno = __ret; \ - if (__ret) \ - FAIL_ERRNO("pthread_create"); \ - __ret; \ - }) - -#define xpthread_join(thread, retval) \ - ({ \ - int __ret = pthread_join((thread), (retval)); \ - errno = __ret; \ - if (__ret) \ - FAIL_ERRNO("pthread_join"); \ - __ret; \ - }) - -static int poll_read(int fd, unsigned int timeout_sec) -{ - struct timeval timeout = { .tv_sec = timeout_sec }; - fd_set rfds; - int r; - - FD_ZERO(&rfds); - FD_SET(fd, &rfds); - - r = select(fd + 1, &rfds, NULL, NULL, &timeout); - if (r == 0) - errno = ETIME; - - return r == 1 ? 0 : -1; -} - -static int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len, - unsigned int timeout_sec) -{ - if (poll_read(fd, timeout_sec)) - return -1; - - return accept(fd, addr, len); -} - -static int recv_timeout(int fd, void *buf, size_t len, int flags, - unsigned int timeout_sec) -{ - if (poll_read(fd, timeout_sec)) - return -1; - - return recv(fd, buf, len, flags); -} - -static void init_addr_loopback4(struct sockaddr_storage *ss, socklen_t *len) -{ - struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss)); - - addr4->sin_family = AF_INET; - addr4->sin_port = 0; - addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); - *len = sizeof(*addr4); -} - -static void init_addr_loopback6(struct sockaddr_storage *ss, socklen_t *len) -{ - struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss)); - - addr6->sin6_family = AF_INET6; - addr6->sin6_port = 0; - addr6->sin6_addr = in6addr_loopback; - *len = sizeof(*addr6); -} - -static void init_addr_loopback_vsock(struct sockaddr_storage *ss, socklen_t *len) -{ - struct sockaddr_vm *addr = memset(ss, 0, sizeof(*ss)); - - addr->svm_family = AF_VSOCK; - addr->svm_port = VMADDR_PORT_ANY; - addr->svm_cid = VMADDR_CID_LOCAL; - *len = sizeof(*addr); -} - -static void init_addr_loopback(int family, struct sockaddr_storage *ss, - socklen_t *len) -{ - switch (family) { - case AF_INET: - init_addr_loopback4(ss, len); - return; - case AF_INET6: - init_addr_loopback6(ss, len); - return; - case AF_VSOCK: - init_addr_loopback_vsock(ss, len); - return; - default: - FAIL("unsupported address family %d", family); - } -} - -static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss) -{ - return (struct sockaddr *)ss; -} - -static int enable_reuseport(int s, int progfd) -{ - int err, one = 1; - - err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one)); - if (err) - return -1; - err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd, - sizeof(progfd)); - if (err) - return -1; - - return 0; -} - -static int socket_loopback_reuseport(int family, int sotype, int progfd) -{ - struct sockaddr_storage addr; - socklen_t len; - int err, s; - - init_addr_loopback(family, &addr, &len); - - s = xsocket(family, sotype, 0); - if (s == -1) - return -1; - - if (progfd >= 0) - enable_reuseport(s, progfd); - - err = xbind(s, sockaddr(&addr), len); - if (err) - goto close; - - if (sotype & SOCK_DGRAM) - return s; - - err = xlisten(s, SOMAXCONN); - if (err) - goto close; - - return s; -close: - xclose(s); - return -1; -} - -static int socket_loopback(int family, int sotype) -{ - return socket_loopback_reuseport(family, sotype, -1); -} +#include "sockmap_helpers.h" static void test_insert_invalid(struct test_sockmap_listen *skel __always_unused, int family, int sotype, int mapfd) @@ -984,31 +671,12 @@ static const char *redir_mode_str(enum redir_mode mode) } } -static int add_to_sockmap(int sock_mapfd, int fd1, int fd2) -{ - u64 value; - u32 key; - int err; - - key = 0; - value = fd1; - err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); - if (err) - return err; - - key = 1; - value = fd2; - return xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); -} - static void redir_to_connected(int family, int sotype, int sock_mapfd, int verd_mapfd, enum redir_mode mode) { const char *log_prefix = redir_mode_str(mode); - struct sockaddr_storage addr; int s, c0, c1, p0, p1; unsigned int pass; - socklen_t len; int err, n; u32 key; char b; @@ -1019,36 +687,13 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, if (s < 0) return; - len = sizeof(addr); - err = xgetsockname(s, sockaddr(&addr), &len); + err = create_socket_pairs(s, family, sotype, &c0, &c1, &p0, &p1); if (err) goto close_srv; - c0 = xsocket(family, sotype, 0); - if (c0 < 0) - goto close_srv; - err = xconnect(c0, sockaddr(&addr), len); - if (err) - goto close_cli0; - - p0 = xaccept_nonblock(s, NULL, NULL); - if (p0 < 0) - goto close_cli0; - - c1 = xsocket(family, sotype, 0); - if (c1 < 0) - goto close_peer0; - err = xconnect(c1, sockaddr(&addr), len); - if (err) - goto close_cli1; - - p1 = xaccept_nonblock(s, NULL, NULL); - if (p1 < 0) - goto close_cli1; - err = add_to_sockmap(sock_mapfd, p0, p1); if (err) - goto close_peer1; + goto close; n = write(mode == REDIR_INGRESS ? c1 : p1, "a", 1); if (n < 0) @@ -1056,12 +701,12 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, if (n == 0) FAIL("%s: incomplete write", log_prefix); if (n < 1) - goto close_peer1; + goto close; key = SK_PASS; err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass); if (err) - goto close_peer1; + goto close; if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); n = recv_timeout(c0, &b, 1, 0, IO_TIMEOUT_SEC); @@ -1070,13 +715,10 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, if (n == 0) FAIL("%s: incomplete recv", log_prefix); -close_peer1: +close: xclose(p1); -close_cli1: xclose(c1); -close_peer0: xclose(p0); -close_cli0: xclose(c0); close_srv: xclose(s); diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt.c b/tools/testing/selftests/bpf/prog_tests/sockopt.c index aa4debf62fc6..9e6a5e3ed4de 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt.c @@ -5,10 +5,15 @@ static char bpf_log_buf[4096]; static bool verbose; +#ifndef PAGE_SIZE +#define PAGE_SIZE 4096 +#endif + enum sockopt_test_error { OK = 0, DENY_LOAD, DENY_ATTACH, + EOPNOTSUPP_GETSOCKOPT, EPERM_GETSOCKOPT, EFAULT_GETSOCKOPT, EPERM_SETSOCKOPT, @@ -273,10 +278,31 @@ static struct sockopt_test { .error = EFAULT_GETSOCKOPT, }, { - .descr = "getsockopt: deny arbitrary ctx->retval", + .descr = "getsockopt: ignore >PAGE_SIZE optlen", .insns = { - /* ctx->retval = 123 */ - BPF_MOV64_IMM(BPF_REG_0, 123), + /* write 0xFF to the first optval byte */ + + /* r6 = ctx->optval */ + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, + offsetof(struct bpf_sockopt, optval)), + /* r2 = ctx->optval */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), + /* r6 = ctx->optval + 1 */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1), + + /* r7 = ctx->optval_end */ + BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_1, + offsetof(struct bpf_sockopt, optval_end)), + + /* if (ctx->optval + 1 <= ctx->optval_end) { */ + BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_7, 1), + /* ctx->optval[0] = 0xF0 */ + BPF_ST_MEM(BPF_B, BPF_REG_2, 0, 0xFF), + /* } */ + + /* retval changes are ignored */ + /* ctx->retval = 5 */ + BPF_MOV64_IMM(BPF_REG_0, 5), BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, offsetof(struct bpf_sockopt, retval)), @@ -287,9 +313,11 @@ static struct sockopt_test { .attach_type = BPF_CGROUP_GETSOCKOPT, .expected_attach_type = BPF_CGROUP_GETSOCKOPT, - .get_optlen = 64, - - .error = EFAULT_GETSOCKOPT, + .get_level = 1234, + .get_optname = 5678, + .get_optval = {}, /* the changes are ignored */ + .get_optlen = PAGE_SIZE + 1, + .error = EOPNOTSUPP_GETSOCKOPT, }, { .descr = "getsockopt: support smaller ctx->optlen", @@ -649,6 +677,45 @@ static struct sockopt_test { .error = EFAULT_SETSOCKOPT, }, { + .descr = "setsockopt: ignore >PAGE_SIZE optlen", + .insns = { + /* write 0xFF to the first optval byte */ + + /* r6 = ctx->optval */ + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, + offsetof(struct bpf_sockopt, optval)), + /* r2 = ctx->optval */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), + /* r6 = ctx->optval + 1 */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1), + + /* r7 = ctx->optval_end */ + BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_1, + offsetof(struct bpf_sockopt, optval_end)), + + /* if (ctx->optval + 1 <= ctx->optval_end) { */ + BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_7, 1), + /* ctx->optval[0] = 0xF0 */ + BPF_ST_MEM(BPF_B, BPF_REG_2, 0, 0xF0), + /* } */ + + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SETSOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, + + .set_level = SOL_IP, + .set_optname = IP_TOS, + .set_optval = {}, + .set_optlen = PAGE_SIZE + 1, + + .get_level = SOL_IP, + .get_optname = IP_TOS, + .get_optval = {}, /* the changes are ignored */ + .get_optlen = 4, + }, + { .descr = "setsockopt: allow changing ctx->optlen within bounds", .insns = { /* r6 = ctx->optval */ @@ -906,6 +973,13 @@ static int run_test(int cgroup_fd, struct sockopt_test *test) } if (test->set_optlen) { + if (test->set_optlen >= PAGE_SIZE) { + int num_pages = test->set_optlen / PAGE_SIZE; + int remainder = test->set_optlen % PAGE_SIZE; + + test->set_optlen = num_pages * sysconf(_SC_PAGESIZE) + remainder; + } + err = setsockopt(sock_fd, test->set_level, test->set_optname, test->set_optval, test->set_optlen); if (err) { @@ -921,7 +995,15 @@ static int run_test(int cgroup_fd, struct sockopt_test *test) } if (test->get_optlen) { + if (test->get_optlen >= PAGE_SIZE) { + int num_pages = test->get_optlen / PAGE_SIZE; + int remainder = test->get_optlen % PAGE_SIZE; + + test->get_optlen = num_pages * sysconf(_SC_PAGESIZE) + remainder; + } + optval = malloc(test->get_optlen); + memset(optval, 0, test->get_optlen); socklen_t optlen = test->get_optlen; socklen_t expected_get_optlen = test->get_optlen_ret ?: test->get_optlen; @@ -929,6 +1011,8 @@ static int run_test(int cgroup_fd, struct sockopt_test *test) err = getsockopt(sock_fd, test->get_level, test->get_optname, optval, &optlen); if (err) { + if (errno == EOPNOTSUPP && test->error == EOPNOTSUPP_GETSOCKOPT) + goto free_optval; if (errno == EPERM && test->error == EPERM_GETSOCKOPT) goto free_optval; if (errno == EFAULT && test->error == EFAULT_GETSOCKOPT) @@ -976,7 +1060,9 @@ void test_sockopt(void) return; for (i = 0; i < ARRAY_SIZE(tests); i++) { - test__start_subtest(tests[i].descr); + if (!test__start_subtest(tests[i].descr)) + continue; + ASSERT_OK(run_test(cgroup_fd, &tests[i]), tests[i].descr); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c index 60c17a8e2789..917f486db826 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c @@ -2,6 +2,8 @@ #include <test_progs.h> #include "cgroup_helpers.h" +#include "sockopt_inherit.skel.h" + #define SOL_CUSTOM 0xdeadbeef #define CUSTOM_INHERIT1 0 #define CUSTOM_INHERIT2 1 @@ -132,58 +134,30 @@ static int start_server(void) return fd; } -static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title, - const char *prog_name) -{ - enum bpf_attach_type attach_type; - enum bpf_prog_type prog_type; - struct bpf_program *prog; - int err; - - err = libbpf_prog_type_by_name(title, &prog_type, &attach_type); - if (err) { - log_err("Failed to deduct types for %s BPF program", prog_name); - return -1; - } - - prog = bpf_object__find_program_by_name(obj, prog_name); - if (!prog) { - log_err("Failed to find %s BPF program", prog_name); - return -1; - } - - err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd, - attach_type, 0); - if (err) { - log_err("Failed to attach %s BPF program", prog_name); - return -1; - } - - return 0; -} - static void run_test(int cgroup_fd) { + struct bpf_link *link_getsockopt = NULL; + struct bpf_link *link_setsockopt = NULL; int server_fd = -1, client_fd; - struct bpf_object *obj; + struct sockopt_inherit *obj; void *server_err; pthread_t tid; int err; - obj = bpf_object__open_file("sockopt_inherit.bpf.o", NULL); - if (!ASSERT_OK_PTR(obj, "obj_open")) + obj = sockopt_inherit__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) return; - err = bpf_object__load(obj); - if (!ASSERT_OK(err, "obj_load")) - goto close_bpf_object; + obj->bss->page_size = sysconf(_SC_PAGESIZE); - err = prog_attach(obj, cgroup_fd, "cgroup/getsockopt", "_getsockopt"); - if (!ASSERT_OK(err, "prog_attach _getsockopt")) + link_getsockopt = bpf_program__attach_cgroup(obj->progs._getsockopt, + cgroup_fd); + if (!ASSERT_OK_PTR(link_getsockopt, "cg-attach-getsockopt")) goto close_bpf_object; - err = prog_attach(obj, cgroup_fd, "cgroup/setsockopt", "_setsockopt"); - if (!ASSERT_OK(err, "prog_attach _setsockopt")) + link_setsockopt = bpf_program__attach_cgroup(obj->progs._setsockopt, + cgroup_fd); + if (!ASSERT_OK_PTR(link_setsockopt, "cg-attach-setsockopt")) goto close_bpf_object; server_fd = start_server(); @@ -217,7 +191,10 @@ static void run_test(int cgroup_fd) close_server_fd: close(server_fd); close_bpf_object: - bpf_object__close(obj); + bpf_link__destroy(link_getsockopt); + bpf_link__destroy(link_setsockopt); + + sockopt_inherit__destroy(obj); } void test_sockopt_inherit(void) diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c index 7f5659349011..759bbb6f8c5f 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c @@ -2,61 +2,13 @@ #include <test_progs.h> #include "cgroup_helpers.h" -static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title, const char *name) -{ - enum bpf_attach_type attach_type; - enum bpf_prog_type prog_type; - struct bpf_program *prog; - int err; - - err = libbpf_prog_type_by_name(title, &prog_type, &attach_type); - if (err) { - log_err("Failed to deduct types for %s BPF program", title); - return -1; - } - - prog = bpf_object__find_program_by_name(obj, name); - if (!prog) { - log_err("Failed to find %s BPF program", name); - return -1; - } - - err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd, - attach_type, BPF_F_ALLOW_MULTI); - if (err) { - log_err("Failed to attach %s BPF program", name); - return -1; - } - - return 0; -} +#include "sockopt_multi.skel.h" -static int prog_detach(struct bpf_object *obj, int cgroup_fd, const char *title, const char *name) -{ - enum bpf_attach_type attach_type; - enum bpf_prog_type prog_type; - struct bpf_program *prog; - int err; - - err = libbpf_prog_type_by_name(title, &prog_type, &attach_type); - if (err) - return -1; - - prog = bpf_object__find_program_by_name(obj, name); - if (!prog) - return -1; - - err = bpf_prog_detach2(bpf_program__fd(prog), cgroup_fd, - attach_type); - if (err) - return -1; - - return 0; -} - -static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, +static int run_getsockopt_test(struct sockopt_multi *obj, int cg_parent, int cg_child, int sock_fd) { + struct bpf_link *link_parent = NULL; + struct bpf_link *link_child = NULL; socklen_t optlen; __u8 buf; int err; @@ -89,8 +41,9 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, * - child: 0x80 -> 0x90 */ - err = prog_attach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child"); - if (err) + link_child = bpf_program__attach_cgroup(obj->progs._getsockopt_child, + cg_child); + if (!ASSERT_OK_PTR(link_child, "cg-attach-getsockopt_child")) goto detach; buf = 0x00; @@ -113,8 +66,9 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, * - parent: 0x90 -> 0xA0 */ - err = prog_attach(obj, cg_parent, "cgroup/getsockopt", "_getsockopt_parent"); - if (err) + link_parent = bpf_program__attach_cgroup(obj->progs._getsockopt_parent, + cg_parent); + if (!ASSERT_OK_PTR(link_parent, "cg-attach-getsockopt_parent")) goto detach; buf = 0x00; @@ -157,11 +111,8 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, * - parent: unexpected 0x40, EPERM */ - err = prog_detach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child"); - if (err) { - log_err("Failed to detach child program"); - goto detach; - } + bpf_link__destroy(link_child); + link_child = NULL; buf = 0x00; optlen = 1; @@ -198,15 +149,17 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, } detach: - prog_detach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child"); - prog_detach(obj, cg_parent, "cgroup/getsockopt", "_getsockopt_parent"); + bpf_link__destroy(link_child); + bpf_link__destroy(link_parent); return err; } -static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, +static int run_setsockopt_test(struct sockopt_multi *obj, int cg_parent, int cg_child, int sock_fd) { + struct bpf_link *link_parent = NULL; + struct bpf_link *link_child = NULL; socklen_t optlen; __u8 buf; int err; @@ -236,8 +189,9 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, /* Attach child program and make sure it adds 0x10. */ - err = prog_attach(obj, cg_child, "cgroup/setsockopt", "_setsockopt"); - if (err) + link_child = bpf_program__attach_cgroup(obj->progs._setsockopt, + cg_child); + if (!ASSERT_OK_PTR(link_child, "cg-attach-setsockopt_child")) goto detach; buf = 0x80; @@ -263,8 +217,9 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, /* Attach parent program and make sure it adds another 0x10. */ - err = prog_attach(obj, cg_parent, "cgroup/setsockopt", "_setsockopt"); - if (err) + link_parent = bpf_program__attach_cgroup(obj->progs._setsockopt, + cg_parent); + if (!ASSERT_OK_PTR(link_parent, "cg-attach-setsockopt_parent")) goto detach; buf = 0x80; @@ -289,8 +244,8 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, } detach: - prog_detach(obj, cg_child, "cgroup/setsockopt", "_setsockopt"); - prog_detach(obj, cg_parent, "cgroup/setsockopt", "_setsockopt"); + bpf_link__destroy(link_child); + bpf_link__destroy(link_parent); return err; } @@ -298,9 +253,8 @@ detach: void test_sockopt_multi(void) { int cg_parent = -1, cg_child = -1; - struct bpf_object *obj = NULL; + struct sockopt_multi *obj = NULL; int sock_fd = -1; - int err = -1; cg_parent = test__join_cgroup("/parent"); if (!ASSERT_GE(cg_parent, 0, "join_cgroup /parent")) @@ -310,13 +264,11 @@ void test_sockopt_multi(void) if (!ASSERT_GE(cg_child, 0, "join_cgroup /parent/child")) goto out; - obj = bpf_object__open_file("sockopt_multi.bpf.o", NULL); - if (!ASSERT_OK_PTR(obj, "obj_load")) + obj = sockopt_multi__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) goto out; - err = bpf_object__load(obj); - if (!ASSERT_OK(err, "obj_load")) - goto out; + obj->bss->page_size = sysconf(_SC_PAGESIZE); sock_fd = socket(AF_INET, SOCK_STREAM, 0); if (!ASSERT_GE(sock_fd, 0, "socket")) @@ -327,7 +279,7 @@ void test_sockopt_multi(void) out: close(sock_fd); - bpf_object__close(obj); + sockopt_multi__destroy(obj); close(cg_child); close(cg_parent); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_qos_to_cc.c b/tools/testing/selftests/bpf/prog_tests/sockopt_qos_to_cc.c index 6b53b3cb8dad..6b2d300e9fd4 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_qos_to_cc.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_qos_to_cc.c @@ -42,6 +42,8 @@ void test_sockopt_qos_to_cc(void) if (!ASSERT_OK_PTR(skel, "skel")) goto done; + skel->bss->page_size = sysconf(_SC_PAGESIZE); + sock_fd = socket(AF_INET6, SOCK_STREAM, 0); if (!ASSERT_GE(sock_fd, 0, "v6 socket open")) goto done; diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c index 4512dd808c33..05d0e07da394 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c @@ -209,7 +209,7 @@ static int getsetsockopt(void) err, errno); goto err; } - ASSERT_EQ(optlen, 4, "Unexpected NETLINK_LIST_MEMBERSHIPS value"); + ASSERT_EQ(optlen, 8, "Unexpected NETLINK_LIST_MEMBERSHIPS value"); free(big_buf); close(fd); diff --git a/tools/testing/selftests/bpf/prog_tests/task_under_cgroup.c b/tools/testing/selftests/bpf/prog_tests/task_under_cgroup.c new file mode 100644 index 000000000000..4224727fb364 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/task_under_cgroup.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Bytedance */ + +#include <sys/syscall.h> +#include <test_progs.h> +#include <cgroup_helpers.h> +#include "test_task_under_cgroup.skel.h" + +#define FOO "/foo" + +void test_task_under_cgroup(void) +{ + struct test_task_under_cgroup *skel; + int ret, foo; + pid_t pid; + + foo = test__join_cgroup(FOO); + if (!ASSERT_OK(foo < 0, "cgroup_join_foo")) + return; + + skel = test_task_under_cgroup__open(); + if (!ASSERT_OK_PTR(skel, "test_task_under_cgroup__open")) + goto cleanup; + + skel->rodata->local_pid = getpid(); + skel->bss->remote_pid = getpid(); + skel->rodata->cgid = get_cgroup_id(FOO); + + ret = test_task_under_cgroup__load(skel); + if (!ASSERT_OK(ret, "test_task_under_cgroup__load")) + goto cleanup; + + ret = test_task_under_cgroup__attach(skel); + if (!ASSERT_OK(ret, "test_task_under_cgroup__attach")) + goto cleanup; + + pid = fork(); + if (pid == 0) + exit(0); + + ret = (pid == -1); + if (ASSERT_OK(ret, "fork process")) + wait(NULL); + + test_task_under_cgroup__detach(skel); + + ASSERT_NEQ(skel->bss->remote_pid, skel->rodata->local_pid, + "test task_under_cgroup"); + +cleanup: + test_task_under_cgroup__destroy(skel); + close(foo); +} diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index 2497716ee379..531621adef42 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -55,6 +55,7 @@ #include "verifier_spill_fill.skel.h" #include "verifier_spin_lock.skel.h" #include "verifier_stack_ptr.skel.h" +#include "verifier_subprog_precision.skel.h" #include "verifier_subreg.skel.h" #include "verifier_uninit.skel.h" #include "verifier_unpriv.skel.h" @@ -154,6 +155,7 @@ void test_verifier_sock(void) { RUN(verifier_sock); } void test_verifier_spill_fill(void) { RUN(verifier_spill_fill); } void test_verifier_spin_lock(void) { RUN(verifier_spin_lock); } void test_verifier_stack_ptr(void) { RUN(verifier_stack_ptr); } +void test_verifier_subprog_precision(void) { RUN(verifier_subprog_precision); } void test_verifier_subreg(void) { RUN(verifier_subreg); } void test_verifier_uninit(void) { RUN(verifier_uninit); } void test_verifier_unpriv(void) { RUN(verifier_unpriv); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c index d19f79048ff6..c3b45745cbcc 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c @@ -18,6 +18,7 @@ #include <linux/if_bonding.h> #include <linux/limits.h> #include <linux/udp.h> +#include <uapi/linux/netdev.h> #include "xdp_dummy.skel.h" #include "xdp_redirect_multi_kern.skel.h" @@ -492,6 +493,123 @@ out: system("ip link del bond_nest2"); } +static void test_xdp_bonding_features(struct skeletons *skeletons) +{ + LIBBPF_OPTS(bpf_xdp_query_opts, query_opts); + int bond_idx, veth1_idx, err; + struct bpf_link *link = NULL; + + if (!ASSERT_OK(system("ip link add bond type bond"), "add bond")) + goto out; + + bond_idx = if_nametoindex("bond"); + if (!ASSERT_GE(bond_idx, 0, "if_nametoindex bond")) + goto out; + + /* query default xdp-feature for bond device */ + err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "bond bpf_xdp_query")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_MASK, + "bond query_opts.feature_flags")) + goto out; + + if (!ASSERT_OK(system("ip link add veth0 type veth peer name veth1"), + "add veth{0,1} pair")) + goto out; + + if (!ASSERT_OK(system("ip link add veth2 type veth peer name veth3"), + "add veth{2,3} pair")) + goto out; + + if (!ASSERT_OK(system("ip link set veth0 master bond"), + "add veth0 to master bond")) + goto out; + + /* xdp-feature for bond device should be obtained from the single slave + * device (veth0) + */ + err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "bond bpf_xdp_query")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_RX_SG, + "bond query_opts.feature_flags")) + goto out; + + veth1_idx = if_nametoindex("veth1"); + if (!ASSERT_GE(veth1_idx, 0, "if_nametoindex veth1")) + goto out; + + link = bpf_program__attach_xdp(skeletons->xdp_dummy->progs.xdp_dummy_prog, + veth1_idx); + if (!ASSERT_OK_PTR(link, "attach program to veth1")) + goto out; + + /* xdp-feature for veth0 are changed */ + err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "bond bpf_xdp_query")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_RX_SG | NETDEV_XDP_ACT_NDO_XMIT | + NETDEV_XDP_ACT_NDO_XMIT_SG, + "bond query_opts.feature_flags")) + goto out; + + if (!ASSERT_OK(system("ip link set veth2 master bond"), + "add veth2 to master bond")) + goto out; + + err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "bond bpf_xdp_query")) + goto out; + + /* xdp-feature for bond device should be set to the most restrict + * value obtained from attached slave devices (veth0 and veth2) + */ + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_RX_SG, + "bond query_opts.feature_flags")) + goto out; + + if (!ASSERT_OK(system("ip link set veth2 nomaster"), + "del veth2 to master bond")) + goto out; + + err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "bond bpf_xdp_query")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_RX_SG | NETDEV_XDP_ACT_NDO_XMIT | + NETDEV_XDP_ACT_NDO_XMIT_SG, + "bond query_opts.feature_flags")) + goto out; + + if (!ASSERT_OK(system("ip link set veth0 nomaster"), + "del veth0 to master bond")) + goto out; + + err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "bond bpf_xdp_query")) + goto out; + + ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_MASK, + "bond query_opts.feature_flags"); +out: + bpf_link__destroy(link); + system("ip link del veth0"); + system("ip link del veth2"); + system("ip link del bond"); +} + static int libbpf_debug_print(enum libbpf_print_level level, const char *format, va_list args) { @@ -546,6 +664,9 @@ void serial_test_xdp_bonding(void) if (test__start_subtest("xdp_bonding_nested")) test_xdp_bonding_nested(&skeletons); + if (test__start_subtest("xdp_bonding_features")) + test_xdp_bonding_features(&skeletons); + for (i = 0; i < ARRAY_SIZE(bond_test_cases); i++) { struct bond_test_case *test_case = &bond_test_cases[i]; diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h index d3c1217ba79a..38a57a2e70db 100644 --- a/tools/testing/selftests/bpf/progs/bpf_misc.h +++ b/tools/testing/selftests/bpf/progs/bpf_misc.h @@ -86,6 +86,10 @@ #define POINTER_VALUE 0xcafe4all #define TEST_DATA_LEN 64 +#ifndef __used +#define __used __attribute__((used)) +#endif + #if defined(__TARGET_ARCH_x86) #define SYSCALL_WRAPPER 1 #define SYS_PREFIX "__x64_" diff --git a/tools/testing/selftests/bpf/progs/cb_refs.c b/tools/testing/selftests/bpf/progs/cb_refs.c index 50f95ec61165..76d661b20e87 100644 --- a/tools/testing/selftests/bpf/progs/cb_refs.c +++ b/tools/testing/selftests/bpf/progs/cb_refs.c @@ -2,6 +2,7 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> +#include "../bpf_testmod/bpf_testmod_kfunc.h" struct map_value { struct prog_test_ref_kfunc __kptr *ptr; @@ -14,9 +15,6 @@ struct { __uint(max_entries, 16); } array_map SEC(".maps"); -extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; - static __noinline int cb1(void *map, void *key, void *value, void *ctx) { void *p = *(void **)ctx; diff --git a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c index b2a409e6382a..932b8ecd4ae3 100644 --- a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c +++ b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c @@ -12,6 +12,7 @@ __u32 invocations = 0; __u32 assertion_error = 0; __u32 retval_value = 0; __u32 ctx_retval_value = 0; +__u32 page_size = 0; SEC("cgroup/getsockopt") int get_retval(struct bpf_sockopt *ctx) @@ -20,6 +21,10 @@ int get_retval(struct bpf_sockopt *ctx) ctx_retval_value = ctx->retval; __sync_fetch_and_add(&invocations, 1); + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } @@ -31,6 +36,10 @@ int set_eisconn(struct bpf_sockopt *ctx) if (bpf_set_retval(-EISCONN)) assertion_error = 1; + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } @@ -41,5 +50,9 @@ int clear_retval(struct bpf_sockopt *ctx) ctx->retval = 0; + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } diff --git a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c index d6e5903e06ba..b7fa8804e19d 100644 --- a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c +++ b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c @@ -11,6 +11,7 @@ __u32 invocations = 0; __u32 assertion_error = 0; __u32 retval_value = 0; +__u32 page_size = 0; SEC("cgroup/setsockopt") int get_retval(struct bpf_sockopt *ctx) @@ -18,6 +19,10 @@ int get_retval(struct bpf_sockopt *ctx) retval_value = bpf_get_retval(); __sync_fetch_and_add(&invocations, 1); + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } @@ -29,6 +34,10 @@ int set_eunatch(struct bpf_sockopt *ctx) if (bpf_set_retval(-EUNATCH)) assertion_error = 1; + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 0; } @@ -40,6 +49,10 @@ int set_eisconn(struct bpf_sockopt *ctx) if (bpf_set_retval(-EISCONN)) assertion_error = 1; + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 0; } @@ -48,5 +61,9 @@ int legacy_eperm(struct bpf_sockopt *ctx) { __sync_fetch_and_add(&invocations, 1); + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 0; } diff --git a/tools/testing/selftests/bpf/progs/dynptr_fail.c b/tools/testing/selftests/bpf/progs/dynptr_fail.c index 759eb5c245cd..7ce7e827d5f0 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_fail.c +++ b/tools/testing/selftests/bpf/progs/dynptr_fail.c @@ -3,6 +3,7 @@ #include <errno.h> #include <string.h> +#include <stdbool.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> #include <linux/if_ether.h> @@ -1378,3 +1379,310 @@ int invalid_slice_rdwr_rdonly(struct __sk_buff *skb) return 0; } + +/* bpf_dynptr_adjust can only be called on initialized dynptrs */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #1") +int dynptr_adjust_invalid(void *ctx) +{ + struct bpf_dynptr ptr; + + /* this should fail */ + bpf_dynptr_adjust(&ptr, 1, 2); + + return 0; +} + +/* bpf_dynptr_is_null can only be called on initialized dynptrs */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #1") +int dynptr_is_null_invalid(void *ctx) +{ + struct bpf_dynptr ptr; + + /* this should fail */ + bpf_dynptr_is_null(&ptr); + + return 0; +} + +/* bpf_dynptr_is_rdonly can only be called on initialized dynptrs */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #1") +int dynptr_is_rdonly_invalid(void *ctx) +{ + struct bpf_dynptr ptr; + + /* this should fail */ + bpf_dynptr_is_rdonly(&ptr); + + return 0; +} + +/* bpf_dynptr_size can only be called on initialized dynptrs */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #1") +int dynptr_size_invalid(void *ctx) +{ + struct bpf_dynptr ptr; + + /* this should fail */ + bpf_dynptr_size(&ptr); + + return 0; +} + +/* Only initialized dynptrs can be cloned */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #1") +int clone_invalid1(void *ctx) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr ptr2; + + /* this should fail */ + bpf_dynptr_clone(&ptr1, &ptr2); + + return 0; +} + +/* Can't overwrite an existing dynptr when cloning */ +SEC("?xdp") +__failure __msg("cannot overwrite referenced dynptr") +int clone_invalid2(struct xdp_md *xdp) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr clone; + + bpf_dynptr_from_xdp(xdp, 0, &ptr1); + + bpf_ringbuf_reserve_dynptr(&ringbuf, 64, 0, &clone); + + /* this should fail */ + bpf_dynptr_clone(&ptr1, &clone); + + bpf_ringbuf_submit_dynptr(&clone, 0); + + return 0; +} + +/* Invalidating a dynptr should invalidate its clones */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #3") +int clone_invalidate1(void *ctx) +{ + struct bpf_dynptr clone; + struct bpf_dynptr ptr; + char read_data[64]; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone); + + bpf_ringbuf_submit_dynptr(&ptr, 0); + + /* this should fail */ + bpf_dynptr_read(read_data, sizeof(read_data), &clone, 0, 0); + + return 0; +} + +/* Invalidating a dynptr should invalidate its parent */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #3") +int clone_invalidate2(void *ctx) +{ + struct bpf_dynptr ptr; + struct bpf_dynptr clone; + char read_data[64]; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone); + + bpf_ringbuf_submit_dynptr(&clone, 0); + + /* this should fail */ + bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0, 0); + + return 0; +} + +/* Invalidating a dynptr should invalidate its siblings */ +SEC("?raw_tp") +__failure __msg("Expected an initialized dynptr as arg #3") +int clone_invalidate3(void *ctx) +{ + struct bpf_dynptr ptr; + struct bpf_dynptr clone1; + struct bpf_dynptr clone2; + char read_data[64]; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone1); + + bpf_dynptr_clone(&ptr, &clone2); + + bpf_ringbuf_submit_dynptr(&clone2, 0); + + /* this should fail */ + bpf_dynptr_read(read_data, sizeof(read_data), &clone1, 0, 0); + + return 0; +} + +/* Invalidating a dynptr should invalidate any data slices + * of its clones + */ +SEC("?raw_tp") +__failure __msg("invalid mem access 'scalar'") +int clone_invalidate4(void *ctx) +{ + struct bpf_dynptr ptr; + struct bpf_dynptr clone; + int *data; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone); + data = bpf_dynptr_data(&clone, 0, sizeof(val)); + if (!data) + return 0; + + bpf_ringbuf_submit_dynptr(&ptr, 0); + + /* this should fail */ + *data = 123; + + return 0; +} + +/* Invalidating a dynptr should invalidate any data slices + * of its parent + */ +SEC("?raw_tp") +__failure __msg("invalid mem access 'scalar'") +int clone_invalidate5(void *ctx) +{ + struct bpf_dynptr ptr; + struct bpf_dynptr clone; + int *data; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + data = bpf_dynptr_data(&ptr, 0, sizeof(val)); + if (!data) + return 0; + + bpf_dynptr_clone(&ptr, &clone); + + bpf_ringbuf_submit_dynptr(&clone, 0); + + /* this should fail */ + *data = 123; + + return 0; +} + +/* Invalidating a dynptr should invalidate any data slices + * of its sibling + */ +SEC("?raw_tp") +__failure __msg("invalid mem access 'scalar'") +int clone_invalidate6(void *ctx) +{ + struct bpf_dynptr ptr; + struct bpf_dynptr clone1; + struct bpf_dynptr clone2; + int *data; + + bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone1); + + bpf_dynptr_clone(&ptr, &clone2); + + data = bpf_dynptr_data(&clone1, 0, sizeof(val)); + if (!data) + return 0; + + bpf_ringbuf_submit_dynptr(&clone2, 0); + + /* this should fail */ + *data = 123; + + return 0; +} + +/* A skb clone's data slices should be invalid anytime packet data changes */ +SEC("?tc") +__failure __msg("invalid mem access 'scalar'") +int clone_skb_packet_data(struct __sk_buff *skb) +{ + char buffer[sizeof(__u32)] = {}; + struct bpf_dynptr clone; + struct bpf_dynptr ptr; + __u32 *data; + + bpf_dynptr_from_skb(skb, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone); + data = bpf_dynptr_slice_rdwr(&clone, 0, buffer, sizeof(buffer)); + if (!data) + return XDP_DROP; + + if (bpf_skb_pull_data(skb, skb->len)) + return SK_DROP; + + /* this should fail */ + *data = 123; + + return 0; +} + +/* A xdp clone's data slices should be invalid anytime packet data changes */ +SEC("?xdp") +__failure __msg("invalid mem access 'scalar'") +int clone_xdp_packet_data(struct xdp_md *xdp) +{ + char buffer[sizeof(__u32)] = {}; + struct bpf_dynptr clone; + struct bpf_dynptr ptr; + struct ethhdr *hdr; + __u32 *data; + + bpf_dynptr_from_xdp(xdp, 0, &ptr); + + bpf_dynptr_clone(&ptr, &clone); + data = bpf_dynptr_slice_rdwr(&clone, 0, buffer, sizeof(buffer)); + if (!data) + return XDP_DROP; + + if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(*hdr))) + return XDP_DROP; + + /* this should fail */ + *data = 123; + + return 0; +} + +/* Buffers that are provided must be sufficiently long */ +SEC("?cgroup_skb/egress") +__failure __msg("memory, len pair leads to invalid memory access") +int test_dynptr_skb_small_buff(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr; + char buffer[8] = {}; + __u64 *data; + + if (bpf_dynptr_from_skb(skb, 0, &ptr)) { + err = 1; + return 1; + } + + /* This may return NULL. SKB may require a buffer */ + data = bpf_dynptr_slice(&ptr, 0, buffer, 9); + + return !!data; +} diff --git a/tools/testing/selftests/bpf/progs/dynptr_success.c b/tools/testing/selftests/bpf/progs/dynptr_success.c index b2fa6c47ecc0..5985920d162e 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_success.c +++ b/tools/testing/selftests/bpf/progs/dynptr_success.c @@ -2,6 +2,7 @@ /* Copyright (c) 2022 Facebook */ #include <string.h> +#include <stdbool.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> #include "bpf_misc.h" @@ -207,3 +208,339 @@ int test_dynptr_skb_data(struct __sk_buff *skb) return 1; } + +SEC("tp/syscalls/sys_enter_nanosleep") +int test_adjust(void *ctx) +{ + struct bpf_dynptr ptr; + __u32 bytes = 64; + __u32 off = 10; + __u32 trim = 15; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + err = bpf_ringbuf_reserve_dynptr(&ringbuf, bytes, 0, &ptr); + if (err) { + err = 1; + goto done; + } + + if (bpf_dynptr_size(&ptr) != bytes) { + err = 2; + goto done; + } + + /* Advance the dynptr by off */ + err = bpf_dynptr_adjust(&ptr, off, bpf_dynptr_size(&ptr)); + if (err) { + err = 3; + goto done; + } + + if (bpf_dynptr_size(&ptr) != bytes - off) { + err = 4; + goto done; + } + + /* Trim the dynptr */ + err = bpf_dynptr_adjust(&ptr, off, 15); + if (err) { + err = 5; + goto done; + } + + /* Check that the size was adjusted correctly */ + if (bpf_dynptr_size(&ptr) != trim - off) { + err = 6; + goto done; + } + +done: + bpf_ringbuf_discard_dynptr(&ptr, 0); + return 0; +} + +SEC("tp/syscalls/sys_enter_nanosleep") +int test_adjust_err(void *ctx) +{ + char write_data[45] = "hello there, world!!"; + struct bpf_dynptr ptr; + __u32 size = 64; + __u32 off = 20; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + if (bpf_ringbuf_reserve_dynptr(&ringbuf, size, 0, &ptr)) { + err = 1; + goto done; + } + + /* Check that start can't be greater than end */ + if (bpf_dynptr_adjust(&ptr, 5, 1) != -EINVAL) { + err = 2; + goto done; + } + + /* Check that start can't be greater than size */ + if (bpf_dynptr_adjust(&ptr, size + 1, size + 1) != -ERANGE) { + err = 3; + goto done; + } + + /* Check that end can't be greater than size */ + if (bpf_dynptr_adjust(&ptr, 0, size + 1) != -ERANGE) { + err = 4; + goto done; + } + + if (bpf_dynptr_adjust(&ptr, off, size)) { + err = 5; + goto done; + } + + /* Check that you can't write more bytes than available into the dynptr + * after you've adjusted it + */ + if (bpf_dynptr_write(&ptr, 0, &write_data, sizeof(write_data), 0) != -E2BIG) { + err = 6; + goto done; + } + + /* Check that even after adjusting, submitting/discarding + * a ringbuf dynptr works + */ + bpf_ringbuf_submit_dynptr(&ptr, 0); + return 0; + +done: + bpf_ringbuf_discard_dynptr(&ptr, 0); + return 0; +} + +SEC("tp/syscalls/sys_enter_nanosleep") +int test_zero_size_dynptr(void *ctx) +{ + char write_data = 'x', read_data; + struct bpf_dynptr ptr; + __u32 size = 64; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + if (bpf_ringbuf_reserve_dynptr(&ringbuf, size, 0, &ptr)) { + err = 1; + goto done; + } + + /* After this, the dynptr has a size of 0 */ + if (bpf_dynptr_adjust(&ptr, size, size)) { + err = 2; + goto done; + } + + /* Test that reading + writing non-zero bytes is not ok */ + if (bpf_dynptr_read(&read_data, sizeof(read_data), &ptr, 0, 0) != -E2BIG) { + err = 3; + goto done; + } + + if (bpf_dynptr_write(&ptr, 0, &write_data, sizeof(write_data), 0) != -E2BIG) { + err = 4; + goto done; + } + + /* Test that reading + writing 0 bytes from a 0-size dynptr is ok */ + if (bpf_dynptr_read(&read_data, 0, &ptr, 0, 0)) { + err = 5; + goto done; + } + + if (bpf_dynptr_write(&ptr, 0, &write_data, 0, 0)) { + err = 6; + goto done; + } + + err = 0; + +done: + bpf_ringbuf_discard_dynptr(&ptr, 0); + return 0; +} + +SEC("tp/syscalls/sys_enter_nanosleep") +int test_dynptr_is_null(void *ctx) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr ptr2; + __u64 size = 4; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + /* Pass in invalid flags, get back an invalid dynptr */ + if (bpf_ringbuf_reserve_dynptr(&ringbuf, size, 123, &ptr1) != -EINVAL) { + err = 1; + goto exit_early; + } + + /* Test that the invalid dynptr is null */ + if (!bpf_dynptr_is_null(&ptr1)) { + err = 2; + goto exit_early; + } + + /* Get a valid dynptr */ + if (bpf_ringbuf_reserve_dynptr(&ringbuf, size, 0, &ptr2)) { + err = 3; + goto exit; + } + + /* Test that the valid dynptr is not null */ + if (bpf_dynptr_is_null(&ptr2)) { + err = 4; + goto exit; + } + +exit: + bpf_ringbuf_discard_dynptr(&ptr2, 0); +exit_early: + bpf_ringbuf_discard_dynptr(&ptr1, 0); + return 0; +} + +SEC("cgroup_skb/egress") +int test_dynptr_is_rdonly(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr ptr2; + struct bpf_dynptr ptr3; + + /* Pass in invalid flags, get back an invalid dynptr */ + if (bpf_dynptr_from_skb(skb, 123, &ptr1) != -EINVAL) { + err = 1; + return 0; + } + + /* Test that an invalid dynptr is_rdonly returns false */ + if (bpf_dynptr_is_rdonly(&ptr1)) { + err = 2; + return 0; + } + + /* Get a read-only dynptr */ + if (bpf_dynptr_from_skb(skb, 0, &ptr2)) { + err = 3; + return 0; + } + + /* Test that the dynptr is read-only */ + if (!bpf_dynptr_is_rdonly(&ptr2)) { + err = 4; + return 0; + } + + /* Get a read-writeable dynptr */ + if (bpf_ringbuf_reserve_dynptr(&ringbuf, 64, 0, &ptr3)) { + err = 5; + goto done; + } + + /* Test that the dynptr is read-only */ + if (bpf_dynptr_is_rdonly(&ptr3)) { + err = 6; + goto done; + } + +done: + bpf_ringbuf_discard_dynptr(&ptr3, 0); + return 0; +} + +SEC("cgroup_skb/egress") +int test_dynptr_clone(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr1; + struct bpf_dynptr ptr2; + __u32 off = 2, size; + + /* Get a dynptr */ + if (bpf_dynptr_from_skb(skb, 0, &ptr1)) { + err = 1; + return 0; + } + + if (bpf_dynptr_adjust(&ptr1, off, bpf_dynptr_size(&ptr1))) { + err = 2; + return 0; + } + + /* Clone the dynptr */ + if (bpf_dynptr_clone(&ptr1, &ptr2)) { + err = 3; + return 0; + } + + size = bpf_dynptr_size(&ptr1); + + /* Check that the clone has the same size and rd-only */ + if (bpf_dynptr_size(&ptr2) != size) { + err = 4; + return 0; + } + + if (bpf_dynptr_is_rdonly(&ptr2) != bpf_dynptr_is_rdonly(&ptr1)) { + err = 5; + return 0; + } + + /* Advance and trim the original dynptr */ + bpf_dynptr_adjust(&ptr1, 5, 5); + + /* Check that only original dynptr was affected, and the clone wasn't */ + if (bpf_dynptr_size(&ptr2) != size) { + err = 6; + return 0; + } + + return 0; +} + +SEC("?cgroup_skb/egress") +int test_dynptr_skb_no_buff(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr; + __u64 *data; + + if (bpf_dynptr_from_skb(skb, 0, &ptr)) { + err = 1; + return 1; + } + + /* This may return NULL. SKB may require a buffer */ + data = bpf_dynptr_slice(&ptr, 0, NULL, 1); + + return !!data; +} + +SEC("?cgroup_skb/egress") +int test_dynptr_skb_strcmp(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr; + char *data; + + if (bpf_dynptr_from_skb(skb, 0, &ptr)) { + err = 1; + return 1; + } + + /* This may return NULL. SKB may require a buffer */ + data = bpf_dynptr_slice(&ptr, 0, NULL, 10); + if (data) { + bpf_strncmp(data, 10, "foo"); + return 1; + } + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/inner_array_lookup.c b/tools/testing/selftests/bpf/progs/inner_array_lookup.c new file mode 100644 index 000000000000..c2c8f2fa451d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/inner_array_lookup.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct inner_map { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 5); + __type(key, int); + __type(value, int); +} inner_map1 SEC(".maps"); + +struct outer_map { + __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); + __uint(max_entries, 3); + __type(key, int); + __array(values, struct inner_map); +} outer_map1 SEC(".maps") = { + .values = { + [2] = &inner_map1, + }, +}; + +SEC("raw_tp/sys_enter") +int handle__sys_enter(void *ctx) +{ + int outer_key = 2, inner_key = 3; + int *val; + void *map; + + map = bpf_map_lookup_elem(&outer_map1, &outer_key); + if (!map) + return 1; + + val = bpf_map_lookup_elem(map, &inner_key); + if (!val) + return 1; + + if (*val == 1) + *val = 2; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c index be16143ae292..6b9b3c56f009 100644 --- a/tools/testing/selftests/bpf/progs/iters.c +++ b/tools/testing/selftests/bpf/progs/iters.c @@ -651,29 +651,25 @@ int iter_stack_array_loop(const void *ctx) return sum; } -#define ARR_SZ 16 - -static __noinline void fill(struct bpf_iter_num *it, int *arr, int mul) +static __noinline void fill(struct bpf_iter_num *it, int *arr, __u32 n, int mul) { - int *t; - __u64 i; + int *t, i; while ((t = bpf_iter_num_next(it))) { i = *t; - if (i >= ARR_SZ) + if (i >= n) break; arr[i] = i * mul; } } -static __noinline int sum(struct bpf_iter_num *it, int *arr) +static __noinline int sum(struct bpf_iter_num *it, int *arr, __u32 n) { - int *t, sum = 0;; - __u64 i; + int *t, i, sum = 0;; while ((t = bpf_iter_num_next(it))) { i = *t; - if (i >= ARR_SZ) + if (i >= n) break; sum += arr[i]; } @@ -685,7 +681,7 @@ SEC("raw_tp") __success int iter_pass_iter_ptr_to_subprog(const void *ctx) { - int arr1[ARR_SZ], arr2[ARR_SZ]; + int arr1[16], arr2[32]; struct bpf_iter_num it; int n, sum1, sum2; @@ -694,25 +690,25 @@ int iter_pass_iter_ptr_to_subprog(const void *ctx) /* fill arr1 */ n = ARRAY_SIZE(arr1); bpf_iter_num_new(&it, 0, n); - fill(&it, arr1, 2); + fill(&it, arr1, n, 2); bpf_iter_num_destroy(&it); /* fill arr2 */ n = ARRAY_SIZE(arr2); bpf_iter_num_new(&it, 0, n); - fill(&it, arr2, 10); + fill(&it, arr2, n, 10); bpf_iter_num_destroy(&it); /* sum arr1 */ n = ARRAY_SIZE(arr1); bpf_iter_num_new(&it, 0, n); - sum1 = sum(&it, arr1); + sum1 = sum(&it, arr1, n); bpf_iter_num_destroy(&it); /* sum arr2 */ n = ARRAY_SIZE(arr2); bpf_iter_num_new(&it, 0, n); - sum2 = sum(&it, arr2); + sum2 = sum(&it, arr2, n); bpf_iter_num_destroy(&it); bpf_printk("sum1=%d, sum2=%d", sum1, sum2); diff --git a/tools/testing/selftests/bpf/progs/jit_probe_mem.c b/tools/testing/selftests/bpf/progs/jit_probe_mem.c index 13f00ca2ed0a..f9789e668297 100644 --- a/tools/testing/selftests/bpf/progs/jit_probe_mem.c +++ b/tools/testing/selftests/bpf/progs/jit_probe_mem.c @@ -3,13 +3,11 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> +#include "../bpf_testmod/bpf_testmod_kfunc.h" static struct prog_test_ref_kfunc __kptr *v; long total_sum = -1; -extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; - SEC("tc") int test_jit_probe_mem(struct __sk_buff *ctx) { diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c b/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c index 767472bc5a97..7632d9ecb253 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c @@ -1,8 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <vmlinux.h> #include <bpf/bpf_helpers.h> - -extern void bpf_kfunc_call_test_destructive(void) __ksym; +#include "../bpf_testmod/bpf_testmod_kfunc.h" SEC("tc") int kfunc_destructive_test(void) diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_fail.c b/tools/testing/selftests/bpf/progs/kfunc_call_fail.c index b98313d391c6..4b0b7b79cdfb 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_fail.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_fail.c @@ -2,14 +2,7 @@ /* Copyright (c) 2021 Facebook */ #include <vmlinux.h> #include <bpf/bpf_helpers.h> - -extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; -extern void bpf_kfunc_call_test_mem_len_pass1(void *mem, int len) __ksym; -extern int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, const int rdwr_buf_size) __ksym; -extern int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym; -extern int *bpf_kfunc_call_test_acq_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym; -extern void bpf_kfunc_call_int_mem_release(int *p) __ksym; +#include "../bpf_testmod/bpf_testmod_kfunc.h" struct syscall_test_args { __u8 data[16]; diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_race.c b/tools/testing/selftests/bpf/progs/kfunc_call_race.c index 4e8fed75a4e0..d532af07decf 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_race.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_race.c @@ -1,8 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <vmlinux.h> #include <bpf/bpf_helpers.h> - -extern void bpf_testmod_test_mod_kfunc(int i) __ksym; +#include "../bpf_testmod/bpf_testmod_kfunc.h" SEC("tc") int kfunc_call_fail(struct __sk_buff *ctx) diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test.c b/tools/testing/selftests/bpf/progs/kfunc_call_test.c index 7daa8f5720b9..cf68d1e48a0f 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test.c @@ -2,22 +2,7 @@ /* Copyright (c) 2021 Facebook */ #include <vmlinux.h> #include <bpf/bpf_helpers.h> - -extern long bpf_kfunc_call_test4(signed char a, short b, int c, long d) __ksym; -extern int bpf_kfunc_call_test2(struct sock *sk, __u32 a, __u32 b) __ksym; -extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b, - __u32 c, __u64 d) __ksym; - -extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; -extern void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb) __ksym; -extern void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p) __ksym; -extern void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p) __ksym; -extern void bpf_kfunc_call_test_mem_len_pass1(void *mem, int len) __ksym; -extern void bpf_kfunc_call_test_mem_len_fail2(__u64 *mem, int len) __ksym; -extern int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, const int rdwr_buf_size) __ksym; -extern int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym; -extern u32 bpf_kfunc_call_test_static_unused_arg(u32 arg, u32 unused) __ksym; +#include "../bpf_testmod/bpf_testmod_kfunc.h" SEC("tc") int kfunc_call_test4(struct __sk_buff *skb) diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c index c1fdecabeabf..2380c75e74ce 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c @@ -1,13 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2021 Facebook */ -#include <linux/bpf.h> -#include <bpf/bpf_helpers.h> -#include "bpf_tcp_helpers.h" +#include "../bpf_testmod/bpf_testmod_kfunc.h" extern const int bpf_prog_active __ksym; -extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b, - __u32 c, __u64 d) __ksym; -extern struct sock *bpf_kfunc_call_test3(struct sock *sk) __ksym; int active_res = -1; int sk_state_res = -1; @@ -28,7 +23,7 @@ int __noinline f1(struct __sk_buff *skb) if (active) active_res = *active; - sk_state_res = bpf_kfunc_call_test3((struct sock *)sk)->sk_state; + sk_state_res = bpf_kfunc_call_test3((struct sock *)sk)->__sk_common.skc_state; return (__u32)bpf_kfunc_call_test1((struct sock *)sk, 1, 2, 3, 4); } diff --git a/tools/testing/selftests/bpf/progs/local_kptr_stash.c b/tools/testing/selftests/bpf/progs/local_kptr_stash.c index 0ef286da092b..06838083079c 100644 --- a/tools/testing/selftests/bpf/progs/local_kptr_stash.c +++ b/tools/testing/selftests/bpf/progs/local_kptr_stash.c @@ -5,7 +5,8 @@ #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_core_read.h> -#include "bpf_experimental.h" +#include "../bpf_experimental.h" +#include "../bpf_testmod/bpf_testmod_kfunc.h" struct node_data { long key; @@ -32,8 +33,6 @@ struct map_value { */ struct node_data *just_here_because_btf_bug; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; - struct { __uint(type, BPF_MAP_TYPE_ARRAY); __type(key, int); diff --git a/tools/testing/selftests/bpf/progs/map_kptr.c b/tools/testing/selftests/bpf/progs/map_kptr.c index d7150041e5d1..da30f0d59364 100644 --- a/tools/testing/selftests/bpf/progs/map_kptr.c +++ b/tools/testing/selftests/bpf/progs/map_kptr.c @@ -2,6 +2,7 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> +#include "../bpf_testmod/bpf_testmod_kfunc.h" struct map_value { struct prog_test_ref_kfunc __kptr_untrusted *unref_ptr; @@ -114,10 +115,6 @@ DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_HASH_OF_MAPS, hash_map, hash_of_hash_maps); DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_HASH_OF_MAPS, hash_malloc_map, hash_of_hash_malloc_maps); DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_HASH_OF_MAPS, lru_hash_map, hash_of_lru_hash_maps); -extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; -void bpf_kfunc_call_test_ref(struct prog_test_ref_kfunc *p) __ksym; - #define WRITE_ONCE(x, val) ((*(volatile typeof(x) *) &(x)) = (val)) static void test_kptr_unref(struct map_value *v) diff --git a/tools/testing/selftests/bpf/progs/map_kptr_fail.c b/tools/testing/selftests/bpf/progs/map_kptr_fail.c index da8c724f839b..450bb373b179 100644 --- a/tools/testing/selftests/bpf/progs/map_kptr_fail.c +++ b/tools/testing/selftests/bpf/progs/map_kptr_fail.c @@ -4,6 +4,7 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_core_read.h> #include "bpf_misc.h" +#include "../bpf_testmod/bpf_testmod_kfunc.h" struct map_value { char buf[8]; @@ -19,9 +20,6 @@ struct array_map { __uint(max_entries, 1); } array_map SEC(".maps"); -extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; -extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; - SEC("?tc") __failure __msg("kptr access size must be BPF_DW") int size_not_bpf_dw(struct __sk_buff *ctx) diff --git a/tools/testing/selftests/bpf/progs/sock_destroy_prog.c b/tools/testing/selftests/bpf/progs/sock_destroy_prog.c new file mode 100644 index 000000000000..9e0bf7a54cec --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sock_destroy_prog.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#include "bpf_tracing_net.h" + +__be16 serv_port = 0; + +int bpf_sock_destroy(struct sock_common *sk) __ksym; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} tcp_conn_sockets SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} udp_conn_sockets SEC(".maps"); + +SEC("cgroup/connect6") +int sock_connect(struct bpf_sock_addr *ctx) +{ + __u64 sock_cookie = 0; + int key = 0; + __u32 keyc = 0; + + if (ctx->family != AF_INET6 || ctx->user_family != AF_INET6) + return 1; + + sock_cookie = bpf_get_socket_cookie(ctx); + if (ctx->protocol == IPPROTO_TCP) + bpf_map_update_elem(&tcp_conn_sockets, &key, &sock_cookie, 0); + else if (ctx->protocol == IPPROTO_UDP) + bpf_map_update_elem(&udp_conn_sockets, &keyc, &sock_cookie, 0); + else + return 1; + + return 1; +} + +SEC("iter/tcp") +int iter_tcp6_client(struct bpf_iter__tcp *ctx) +{ + struct sock_common *sk_common = ctx->sk_common; + __u64 sock_cookie = 0; + __u64 *val; + int key = 0; + + if (!sk_common) + return 0; + + if (sk_common->skc_family != AF_INET6) + return 0; + + sock_cookie = bpf_get_socket_cookie(sk_common); + val = bpf_map_lookup_elem(&tcp_conn_sockets, &key); + if (!val) + return 0; + /* Destroy connected client sockets. */ + if (sock_cookie == *val) + bpf_sock_destroy(sk_common); + + return 0; +} + +SEC("iter/tcp") +int iter_tcp6_server(struct bpf_iter__tcp *ctx) +{ + struct sock_common *sk_common = ctx->sk_common; + const struct inet_connection_sock *icsk; + const struct inet_sock *inet; + struct tcp6_sock *tcp_sk; + __be16 srcp; + + if (!sk_common) + return 0; + + if (sk_common->skc_family != AF_INET6) + return 0; + + tcp_sk = bpf_skc_to_tcp6_sock(sk_common); + if (!tcp_sk) + return 0; + + icsk = &tcp_sk->tcp.inet_conn; + inet = &icsk->icsk_inet; + srcp = inet->inet_sport; + + /* Destroy server sockets. */ + if (srcp == serv_port) + bpf_sock_destroy(sk_common); + + return 0; +} + + +SEC("iter/udp") +int iter_udp6_client(struct bpf_iter__udp *ctx) +{ + struct udp_sock *udp_sk = ctx->udp_sk; + struct sock *sk = (struct sock *) udp_sk; + __u64 sock_cookie = 0, *val; + int key = 0; + + if (!sk) + return 0; + + sock_cookie = bpf_get_socket_cookie(sk); + val = bpf_map_lookup_elem(&udp_conn_sockets, &key); + if (!val) + return 0; + /* Destroy connected client sockets. */ + if (sock_cookie == *val) + bpf_sock_destroy((struct sock_common *)sk); + + return 0; +} + +SEC("iter/udp") +int iter_udp6_server(struct bpf_iter__udp *ctx) +{ + struct udp_sock *udp_sk = ctx->udp_sk; + struct sock *sk = (struct sock *) udp_sk; + struct inet_sock *inet; + __be16 srcp; + + if (!sk) + return 0; + + inet = &udp_sk->inet; + srcp = inet->inet_sport; + if (srcp == serv_port) + bpf_sock_destroy((struct sock_common *)sk); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/sock_destroy_prog_fail.c b/tools/testing/selftests/bpf/progs/sock_destroy_prog_fail.c new file mode 100644 index 000000000000..dd6850b58e25 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sock_destroy_prog_fail.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +int bpf_sock_destroy(struct sock_common *sk) __ksym; + +SEC("tp_btf/tcp_destroy_sock") +__failure __msg("calling kernel function bpf_sock_destroy is not allowed") +int BPF_PROG(trace_tcp_destroy_sock, struct sock *sk) +{ + /* should not load */ + bpf_sock_destroy((struct sock_common *)sk); + + return 0; +} + diff --git a/tools/testing/selftests/bpf/progs/sockopt_inherit.c b/tools/testing/selftests/bpf/progs/sockopt_inherit.c index 9fb241b97291..c8f59caa4639 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_inherit.c +++ b/tools/testing/selftests/bpf/progs/sockopt_inherit.c @@ -9,6 +9,8 @@ char _license[] SEC("license") = "GPL"; #define CUSTOM_INHERIT2 1 #define CUSTOM_LISTENER 2 +__u32 page_size = 0; + struct sockopt_inherit { __u8 val; }; @@ -55,7 +57,7 @@ int _getsockopt(struct bpf_sockopt *ctx) __u8 *optval = ctx->optval; if (ctx->level != SOL_CUSTOM) - return 1; /* only interested in SOL_CUSTOM */ + goto out; /* only interested in SOL_CUSTOM */ if (optval + 1 > optval_end) return 0; /* EPERM, bounds check */ @@ -70,6 +72,12 @@ int _getsockopt(struct bpf_sockopt *ctx) ctx->optlen = 1; return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } SEC("cgroup/setsockopt") @@ -80,7 +88,7 @@ int _setsockopt(struct bpf_sockopt *ctx) __u8 *optval = ctx->optval; if (ctx->level != SOL_CUSTOM) - return 1; /* only interested in SOL_CUSTOM */ + goto out; /* only interested in SOL_CUSTOM */ if (optval + 1 > optval_end) return 0; /* EPERM, bounds check */ @@ -93,4 +101,10 @@ int _setsockopt(struct bpf_sockopt *ctx) ctx->optlen = -1; return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } diff --git a/tools/testing/selftests/bpf/progs/sockopt_multi.c b/tools/testing/selftests/bpf/progs/sockopt_multi.c index 177a59069dae..96f29fce050b 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_multi.c +++ b/tools/testing/selftests/bpf/progs/sockopt_multi.c @@ -5,6 +5,8 @@ char _license[] SEC("license") = "GPL"; +__u32 page_size = 0; + SEC("cgroup/getsockopt") int _getsockopt_child(struct bpf_sockopt *ctx) { @@ -12,7 +14,7 @@ int _getsockopt_child(struct bpf_sockopt *ctx) __u8 *optval = ctx->optval; if (ctx->level != SOL_IP || ctx->optname != IP_TOS) - return 1; + goto out; if (optval + 1 > optval_end) return 0; /* EPERM, bounds check */ @@ -26,6 +28,12 @@ int _getsockopt_child(struct bpf_sockopt *ctx) ctx->optlen = 1; return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } SEC("cgroup/getsockopt") @@ -35,7 +43,7 @@ int _getsockopt_parent(struct bpf_sockopt *ctx) __u8 *optval = ctx->optval; if (ctx->level != SOL_IP || ctx->optname != IP_TOS) - return 1; + goto out; if (optval + 1 > optval_end) return 0; /* EPERM, bounds check */ @@ -49,6 +57,12 @@ int _getsockopt_parent(struct bpf_sockopt *ctx) ctx->optlen = 1; return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } SEC("cgroup/setsockopt") @@ -58,7 +72,7 @@ int _setsockopt(struct bpf_sockopt *ctx) __u8 *optval = ctx->optval; if (ctx->level != SOL_IP || ctx->optname != IP_TOS) - return 1; + goto out; if (optval + 1 > optval_end) return 0; /* EPERM, bounds check */ @@ -67,4 +81,10 @@ int _setsockopt(struct bpf_sockopt *ctx) ctx->optlen = 1; return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } diff --git a/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c b/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c index 1bce83b6e3a7..dbe235ede7f3 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c +++ b/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c @@ -9,6 +9,8 @@ char _license[] SEC("license") = "GPL"; +__u32 page_size = 0; + SEC("cgroup/setsockopt") int sockopt_qos_to_cc(struct bpf_sockopt *ctx) { @@ -19,7 +21,7 @@ int sockopt_qos_to_cc(struct bpf_sockopt *ctx) char cc_cubic[TCP_CA_NAME_MAX] = "cubic"; if (ctx->level != SOL_IPV6 || ctx->optname != IPV6_TCLASS) - return 1; + goto out; if (optval + 1 > optval_end) return 0; /* EPERM, bounds check */ @@ -36,4 +38,10 @@ int sockopt_qos_to_cc(struct bpf_sockopt *ctx) return 0; } return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c index fe1df4cd206e..cb990a7d3d45 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_sk.c +++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c @@ -37,7 +37,7 @@ int _getsockopt(struct bpf_sockopt *ctx) /* Bypass AF_NETLINK. */ sk = ctx->sk; if (sk && sk->family == AF_NETLINK) - return 1; + goto out; /* Make sure bpf_get_netns_cookie is callable. */ @@ -52,8 +52,7 @@ int _getsockopt(struct bpf_sockopt *ctx) * let next BPF program in the cgroup chain or kernel * handle it. */ - ctx->optlen = 0; /* bypass optval>PAGE_SIZE */ - return 1; + goto out; } if (ctx->level == SOL_SOCKET && ctx->optname == SO_SNDBUF) { @@ -61,7 +60,7 @@ int _getsockopt(struct bpf_sockopt *ctx) * let next BPF program in the cgroup chain or kernel * handle it. */ - return 1; + goto out; } if (ctx->level == SOL_TCP && ctx->optname == TCP_CONGESTION) { @@ -69,7 +68,7 @@ int _getsockopt(struct bpf_sockopt *ctx) * let next BPF program in the cgroup chain or kernel * handle it. */ - return 1; + goto out; } if (ctx->level == SOL_TCP && ctx->optname == TCP_ZEROCOPY_RECEIVE) { @@ -85,7 +84,7 @@ int _getsockopt(struct bpf_sockopt *ctx) if (((struct tcp_zerocopy_receive *)optval)->address != 0) return 0; /* unexpected data */ - return 1; + goto out; } if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) { @@ -129,6 +128,12 @@ int _getsockopt(struct bpf_sockopt *ctx) ctx->optlen = 1; return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } SEC("cgroup/setsockopt") @@ -142,7 +147,7 @@ int _setsockopt(struct bpf_sockopt *ctx) /* Bypass AF_NETLINK. */ sk = ctx->sk; if (sk && sk->family == AF_NETLINK) - return 1; + goto out; /* Make sure bpf_get_netns_cookie is callable. */ @@ -224,4 +229,10 @@ int _setsockopt(struct bpf_sockopt *ctx) */ return 1; + +out: + /* optval larger than PAGE_SIZE use kernel's buffer. */ + if (ctx->optlen > page_size) + ctx->optlen = 0; + return 1; } diff --git a/tools/testing/selftests/bpf/progs/test_global_func1.c b/tools/testing/selftests/bpf/progs/test_global_func1.c index b85fc8c423ba..17a9f59bf5f3 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func1.c +++ b/tools/testing/selftests/bpf/progs/test_global_func1.c @@ -10,6 +10,8 @@ static __attribute__ ((noinline)) int f0(int var, struct __sk_buff *skb) { + asm volatile (""); + return skb->len; } diff --git a/tools/testing/selftests/bpf/progs/test_global_map_resize.c b/tools/testing/selftests/bpf/progs/test_global_map_resize.c new file mode 100644 index 000000000000..2588f2384246 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_global_map_resize.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +/* rodata section */ +const volatile pid_t pid; +const volatile size_t bss_array_len; +const volatile size_t data_array_len; + +/* bss section */ +int sum = 0; +int array[1]; + +/* custom data secton */ +int my_array[1] SEC(".data.custom"); + +/* custom data section which should NOT be resizable, + * since it contains a single var which is not an array + */ +int my_int SEC(".data.non_array"); + +/* custom data section which should NOT be resizable, + * since its last var is not an array + */ +int my_array_first[1] SEC(".data.array_not_last"); +int my_int_last SEC(".data.array_not_last"); + +SEC("tp/syscalls/sys_enter_getpid") +int bss_array_sum(void *ctx) +{ + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + sum = 0; + + for (size_t i = 0; i < bss_array_len; ++i) + sum += array[i]; + + return 0; +} + +SEC("tp/syscalls/sys_enter_getuid") +int data_array_sum(void *ctx) +{ + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + sum = 0; + + for (size_t i = 0; i < data_array_len; ++i) + sum += my_array[i]; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields.c b/tools/testing/selftests/bpf/progs/test_sock_fields.c index bbad3c2d9aa5..f75e531bf36f 100644 --- a/tools/testing/selftests/bpf/progs/test_sock_fields.c +++ b/tools/testing/selftests/bpf/progs/test_sock_fields.c @@ -265,7 +265,10 @@ static __noinline bool sk_dst_port__load_word(struct bpf_sock *sk) static __noinline bool sk_dst_port__load_half(struct bpf_sock *sk) { - __u16 *half = (__u16 *)&sk->dst_port; + __u16 *half; + + asm volatile (""); + half = (__u16 *)&sk->dst_port; return half[0] == bpf_htons(0xcafe); } diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_drop_prog.c b/tools/testing/selftests/bpf/progs/test_sockmap_drop_prog.c new file mode 100644 index 000000000000..29314805ce42 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_drop_prog.c @@ -0,0 +1,32 @@ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_rx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_tx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_msg SEC(".maps"); + +SEC("sk_skb") +int prog_skb_verdict(struct __sk_buff *skb) +{ + return SK_DROP; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h index baf9ebc6d903..99d2ea9fb658 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h +++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h @@ -191,7 +191,7 @@ SEC("sockops") int bpf_sockmap(struct bpf_sock_ops *skops) { __u32 lport, rport; - int op, err, ret; + int op, ret; op = (int) skops->op; @@ -203,10 +203,10 @@ int bpf_sockmap(struct bpf_sock_ops *skops) if (lport == 10000) { ret = 1; #ifdef SOCKMAP - err = bpf_sock_map_update(skops, &sock_map, &ret, + bpf_sock_map_update(skops, &sock_map, &ret, BPF_NOEXIST); #else - err = bpf_sock_hash_update(skops, &sock_map, &ret, + bpf_sock_hash_update(skops, &sock_map, &ret, BPF_NOEXIST); #endif } @@ -218,10 +218,10 @@ int bpf_sockmap(struct bpf_sock_ops *skops) if (bpf_ntohl(rport) == 10001) { ret = 10; #ifdef SOCKMAP - err = bpf_sock_map_update(skops, &sock_map, &ret, + bpf_sock_map_update(skops, &sock_map, &ret, BPF_NOEXIST); #else - err = bpf_sock_hash_update(skops, &sock_map, &ret, + bpf_sock_hash_update(skops, &sock_map, &ret, BPF_NOEXIST); #endif } @@ -230,8 +230,6 @@ int bpf_sockmap(struct bpf_sock_ops *skops) break; } - __sink(err); - return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_pass_prog.c b/tools/testing/selftests/bpf/progs/test_sockmap_pass_prog.c new file mode 100644 index 000000000000..1d86a717a290 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_pass_prog.c @@ -0,0 +1,32 @@ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_rx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_tx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_msg SEC(".maps"); + +SEC("sk_skb") +int prog_skb_verdict(struct __sk_buff *skb) +{ + return SK_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c b/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c new file mode 100644 index 000000000000..56cdc0a553f0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Bytedance */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +#include "bpf_misc.h" + +struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym; +long bpf_task_under_cgroup(struct task_struct *task, struct cgroup *ancestor) __ksym; +void bpf_cgroup_release(struct cgroup *p) __ksym; +struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym; +void bpf_task_release(struct task_struct *p) __ksym; + +const volatile int local_pid; +const volatile __u64 cgid; +int remote_pid; + +SEC("tp_btf/task_newtask") +int BPF_PROG(handle__task_newtask, struct task_struct *task, u64 clone_flags) +{ + struct cgroup *cgrp = NULL; + struct task_struct *acquired; + + if (local_pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + acquired = bpf_task_acquire(task); + if (!acquired) + return 0; + + if (local_pid == acquired->tgid) + goto out; + + cgrp = bpf_cgroup_from_id(cgid); + if (!cgrp) + goto out; + + if (bpf_task_under_cgroup(acquired, cgrp)) + remote_pid = acquired->tgid; + +out: + if (cgrp) + bpf_cgroup_release(cgrp); + bpf_task_release(acquired); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c b/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c index 25ee4a22e48d..78c368e71797 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c @@ -2,6 +2,7 @@ /* Copyright (c) 2022 Meta */ #include <stddef.h> #include <string.h> +#include <stdbool.h> #include <linux/bpf.h> #include <linux/if_ether.h> #include <linux/if_packet.h> diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c new file mode 100644 index 000000000000..db6b3143338b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c @@ -0,0 +1,536 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <errno.h> +#include <string.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#define ARRAY_SIZE(x) (sizeof(x) / sizeof(x[0])) + +int vals[] SEC(".data.vals") = {1, 2, 3, 4}; + +__naked __noinline __used +static unsigned long identity_subprog() +{ + /* the simplest *static* 64-bit identity function */ + asm volatile ( + "r0 = r1;" + "exit;" + ); +} + +__noinline __used +unsigned long global_identity_subprog(__u64 x) +{ + /* the simplest *global* 64-bit identity function */ + return x; +} + +__naked __noinline __used +static unsigned long callback_subprog() +{ + /* the simplest callback function */ + asm volatile ( + "r0 = 0;" + "exit;" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("7: (0f) r1 += r0") +__msg("mark_precise: frame0: regs=r0 stack= before 6: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r0 stack= before 5: (27) r0 *= 4") +__msg("mark_precise: frame0: regs=r0 stack= before 11: (95) exit") +__msg("mark_precise: frame1: regs=r0 stack= before 10: (bf) r0 = r1") +__msg("mark_precise: frame1: regs=r1 stack= before 4: (85) call pc+5") +__msg("mark_precise: frame0: regs=r1 stack= before 3: (bf) r1 = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3") +__naked int subprog_result_precise(void) +{ + asm volatile ( + "r6 = 3;" + /* pass r6 through r1 into subprog to get it back as r0; + * this whole chain will have to be marked as precise later + */ + "r1 = r6;" + "call identity_subprog;" + /* now use subprog's returned value (which is a + * r6 -> r1 -> r0 chain), as index into vals array, forcing + * all of that to be known precisely + */ + "r0 *= 4;" + "r1 = %[vals];" + /* here r0->r1->r6 chain is forced to be precise and has to be + * propagated back to the beginning, including through the + * subprog call + */ + "r1 += r0;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("9: (0f) r1 += r0") +__msg("mark_precise: frame0: last_idx 9 first_idx 0") +__msg("mark_precise: frame0: regs=r0 stack= before 8: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r0 stack= before 7: (27) r0 *= 4") +__msg("mark_precise: frame0: regs=r0 stack= before 5: (a5) if r0 < 0x4 goto pc+1") +__msg("mark_precise: frame0: regs=r0 stack= before 4: (85) call pc+7") +__naked int global_subprog_result_precise(void) +{ + asm volatile ( + "r6 = 3;" + /* pass r6 through r1 into subprog to get it back as r0; + * given global_identity_subprog is global, precision won't + * propagate all the way back to r6 + */ + "r1 = r6;" + "call global_identity_subprog;" + /* now use subprog's returned value (which is unknown now, so + * we need to clamp it), as index into vals array, forcing r0 + * to be marked precise (with no effect on r6, though) + */ + "if r0 < %[vals_arr_sz] goto 1f;" + "r0 = %[vals_arr_sz] - 1;" + "1:" + "r0 *= 4;" + "r1 = %[vals];" + /* here r0 is forced to be precise and has to be + * propagated back to the global subprog call, but it + * shouldn't go all the way to mark r6 as precise + */ + "r1 += r0;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals), + __imm_const(vals_arr_sz, ARRAY_SIZE(vals)) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("14: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 14 first_idx 10") +__msg("mark_precise: frame0: regs=r6 stack= before 13: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 12: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 11: (25) if r6 > 0x3 goto pc+4") +__msg("mark_precise: frame0: regs=r6 stack= before 10: (bf) r6 = r0") +__msg("mark_precise: frame0: parent state regs=r0 stack=:") +__msg("mark_precise: frame0: last_idx 18 first_idx 0") +__msg("mark_precise: frame0: regs=r0 stack= before 18: (95) exit") +__naked int callback_result_precise(void) +{ + asm volatile ( + "r6 = 3;" + + /* call subprog and use result; r0 shouldn't propagate back to + * callback_subprog + */ + "r1 = r6;" /* nr_loops */ + "r2 = %[callback_subprog];" /* callback_fn */ + "r3 = 0;" /* callback_ctx */ + "r4 = 0;" /* flags */ + "call %[bpf_loop];" + + "r6 = r0;" + "if r6 > 3 goto 1f;" + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the bpf_loop() call, but not beyond + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "1:" + "exit;" + : + : __imm_ptr(vals), + __imm_ptr(callback_subprog), + __imm(bpf_loop) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("7: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 7 first_idx 0") +__msg("mark_precise: frame0: regs=r6 stack= before 6: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 5: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 11: (95) exit") +__msg("mark_precise: frame1: regs= stack= before 10: (bf) r0 = r1") +__msg("mark_precise: frame1: regs= stack= before 4: (85) call pc+5") +__msg("mark_precise: frame0: regs=r6 stack= before 3: (b7) r1 = 0") +__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3") +__naked int parent_callee_saved_reg_precise(void) +{ + asm volatile ( + "r6 = 3;" + + /* call subprog and ignore result; we need this call only to + * complicate jump history + */ + "r1 = 0;" + "call identity_subprog;" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) subprog call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("7: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 7 first_idx 0") +__msg("mark_precise: frame0: regs=r6 stack= before 6: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 5: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 4: (85) call pc+5") +__msg("mark_precise: frame0: regs=r6 stack= before 3: (b7) r1 = 0") +__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3") +__naked int parent_callee_saved_reg_precise_global(void) +{ + asm volatile ( + "r6 = 3;" + + /* call subprog and ignore result; we need this call only to + * complicate jump history + */ + "r1 = 0;" + "call global_identity_subprog;" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) subprog call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("12: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 12 first_idx 10") +__msg("mark_precise: frame0: regs=r6 stack= before 11: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 10: (27) r6 *= 4") +__msg("mark_precise: frame0: parent state regs=r6 stack=:") +__msg("mark_precise: frame0: last_idx 16 first_idx 0") +__msg("mark_precise: frame0: regs=r6 stack= before 16: (95) exit") +__msg("mark_precise: frame1: regs= stack= before 15: (b7) r0 = 0") +__msg("mark_precise: frame1: regs= stack= before 9: (85) call bpf_loop#181") +__msg("mark_precise: frame0: regs=r6 stack= before 8: (b7) r4 = 0") +__msg("mark_precise: frame0: regs=r6 stack= before 7: (b7) r3 = 0") +__msg("mark_precise: frame0: regs=r6 stack= before 6: (bf) r2 = r8") +__msg("mark_precise: frame0: regs=r6 stack= before 5: (b7) r1 = 1") +__msg("mark_precise: frame0: regs=r6 stack= before 4: (b7) r6 = 3") +__naked int parent_callee_saved_reg_precise_with_callback(void) +{ + asm volatile ( + "r6 = 3;" + + /* call subprog and ignore result; we need this call only to + * complicate jump history + */ + "r1 = 1;" /* nr_loops */ + "r2 = %[callback_subprog];" /* callback_fn */ + "r3 = 0;" /* callback_ctx */ + "r4 = 0;" /* flags */ + "call %[bpf_loop];" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) callback call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals), + __imm_ptr(callback_subprog), + __imm(bpf_loop) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("9: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 9 first_idx 6") +__msg("mark_precise: frame0: regs=r6 stack= before 8: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 7: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 6: (79) r6 = *(u64 *)(r10 -8)") +__msg("mark_precise: frame0: parent state regs= stack=-8:") +__msg("mark_precise: frame0: last_idx 13 first_idx 0") +__msg("mark_precise: frame0: regs= stack=-8 before 13: (95) exit") +__msg("mark_precise: frame1: regs= stack= before 12: (bf) r0 = r1") +__msg("mark_precise: frame1: regs= stack= before 5: (85) call pc+6") +__msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r1 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 3: (7b) *(u64 *)(r10 -8) = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3") +__naked int parent_stack_slot_precise(void) +{ + asm volatile ( + /* spill reg */ + "r6 = 3;" + "*(u64 *)(r10 - 8) = r6;" + + /* call subprog and ignore result; we need this call only to + * complicate jump history + */ + "r1 = 0;" + "call identity_subprog;" + + /* restore reg from stack; in this case we'll be carrying + * stack mask when going back into subprog through jump + * history + */ + "r6 = *(u64 *)(r10 - 8);" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) subprog call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("9: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 9 first_idx 6") +__msg("mark_precise: frame0: regs=r6 stack= before 8: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 7: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 6: (79) r6 = *(u64 *)(r10 -8)") +__msg("mark_precise: frame0: parent state regs= stack=-8:") +__msg("mark_precise: frame0: last_idx 5 first_idx 0") +__msg("mark_precise: frame0: regs= stack=-8 before 5: (85) call pc+6") +__msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r1 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 3: (7b) *(u64 *)(r10 -8) = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3") +__naked int parent_stack_slot_precise_global(void) +{ + asm volatile ( + /* spill reg */ + "r6 = 3;" + "*(u64 *)(r10 - 8) = r6;" + + /* call subprog and ignore result; we need this call only to + * complicate jump history + */ + "r1 = 0;" + "call global_identity_subprog;" + + /* restore reg from stack; in this case we'll be carrying + * stack mask when going back into subprog through jump + * history + */ + "r6 = *(u64 *)(r10 - 8);" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) subprog call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("14: (0f) r1 += r6") +__msg("mark_precise: frame0: last_idx 14 first_idx 11") +__msg("mark_precise: frame0: regs=r6 stack= before 13: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r6 stack= before 12: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 11: (79) r6 = *(u64 *)(r10 -8)") +__msg("mark_precise: frame0: parent state regs= stack=-8:") +__msg("mark_precise: frame0: last_idx 18 first_idx 0") +__msg("mark_precise: frame0: regs= stack=-8 before 18: (95) exit") +__msg("mark_precise: frame1: regs= stack= before 17: (b7) r0 = 0") +__msg("mark_precise: frame1: regs= stack= before 10: (85) call bpf_loop#181") +__msg("mark_precise: frame0: regs= stack=-8 before 9: (b7) r4 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 8: (b7) r3 = 0") +__msg("mark_precise: frame0: regs= stack=-8 before 7: (bf) r2 = r8") +__msg("mark_precise: frame0: regs= stack=-8 before 6: (bf) r1 = r6") +__msg("mark_precise: frame0: regs= stack=-8 before 5: (7b) *(u64 *)(r10 -8) = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 4: (b7) r6 = 3") +__naked int parent_stack_slot_precise_with_callback(void) +{ + asm volatile ( + /* spill reg */ + "r6 = 3;" + "*(u64 *)(r10 - 8) = r6;" + + /* ensure we have callback frame in jump history */ + "r1 = r6;" /* nr_loops */ + "r2 = %[callback_subprog];" /* callback_fn */ + "r3 = 0;" /* callback_ctx */ + "r4 = 0;" /* flags */ + "call %[bpf_loop];" + + /* restore reg from stack; in this case we'll be carrying + * stack mask when going back into subprog through jump + * history + */ + "r6 = *(u64 *)(r10 - 8);" + + "r6 *= 4;" + "r1 = %[vals];" + /* here r6 is forced to be precise and has to be propagated + * back to the beginning, handling (and ignoring) subprog call + */ + "r1 += r6;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals), + __imm_ptr(callback_subprog), + __imm(bpf_loop) + : __clobber_common, "r6" + ); +} + +__noinline __used +static __u64 subprog_with_precise_arg(__u64 x) +{ + return vals[x]; /* x is forced to be precise */ +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("8: (0f) r2 += r1") +__msg("mark_precise: frame1: last_idx 8 first_idx 0") +__msg("mark_precise: frame1: regs=r1 stack= before 6: (18) r2 = ") +__msg("mark_precise: frame1: regs=r1 stack= before 5: (67) r1 <<= 2") +__msg("mark_precise: frame1: regs=r1 stack= before 2: (85) call pc+2") +__msg("mark_precise: frame0: regs=r1 stack= before 1: (bf) r1 = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 0: (b7) r6 = 3") +__naked int subprog_arg_precise(void) +{ + asm volatile ( + "r6 = 3;" + "r1 = r6;" + /* subprog_with_precise_arg expects its argument to be + * precise, so r1->r6 will be marked precise from inside the + * subprog + */ + "call subprog_with_precise_arg;" + "r0 += r6;" + "exit;" + : + : + : __clobber_common, "r6" + ); +} + +/* r1 is pointer to stack slot; + * r2 is a register to spill into that slot + * subprog also spills r2 into its own stack slot + */ +__naked __noinline __used +static __u64 subprog_spill_reg_precise(void) +{ + asm volatile ( + /* spill to parent stack */ + "*(u64 *)(r1 + 0) = r2;" + /* spill to subprog stack (we use -16 offset to avoid + * accidental confusion with parent's -8 stack slot in + * verifier log output) + */ + "*(u64 *)(r10 - 16) = r2;" + /* use both spills as return result to propagete precision everywhere */ + "r0 = *(u64 *)(r10 - 16);" + "r2 = *(u64 *)(r1 + 0);" + "r0 += r2;" + "exit;" + ); +} + +SEC("?raw_tp") +__success __log_level(2) +/* precision backtracking can't currently handle stack access not through r10, + * so we won't be able to mark stack slot fp-8 as precise, and so will + * fallback to forcing all as precise + */ +__msg("mark_precise: frame0: falling back to forcing all scalars precise") +__naked int subprog_spill_into_parent_stack_slot_precise(void) +{ + asm volatile ( + "r6 = 1;" + + /* pass pointer to stack slot and r6 to subprog; + * r6 will be marked precise and spilled into fp-8 slot, which + * also should be marked precise + */ + "r1 = r10;" + "r1 += -8;" + "r2 = r6;" + "call subprog_spill_reg_precise;" + + /* restore reg from stack; in this case we'll be carrying + * stack mask when going back into subprog through jump + * history + */ + "r7 = *(u64 *)(r10 - 8);" + + "r7 *= 4;" + "r1 = %[vals];" + /* here r7 is forced to be precise and has to be propagated + * back to the beginning, handling subprog call and logic + */ + "r1 += r7;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6", "r7" + ); +} + +__naked __noinline __used +static __u64 subprog_with_checkpoint(void) +{ + asm volatile ( + "r0 = 0;" + /* guaranteed checkpoint if BPF_F_TEST_STATE_FREQ is used */ + "goto +0;" + "exit;" + ); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c index e1c787815e44..b2dfd7066c6e 100644 --- a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c @@ -77,7 +77,9 @@ int rx(struct xdp_md *ctx) } err = bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp); - if (err) + if (!err) + meta->xdp_timestamp = bpf_ktime_get_tai_ns(); + else meta->rx_timestamp = 0; /* Used by AF_XDP as not avail signal */ err = bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type); diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index ea82921110da..4d582cac2c09 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -11,7 +11,6 @@ #include <signal.h> #include <string.h> #include <execinfo.h> /* backtrace */ -#include <linux/membarrier.h> #include <sys/sysinfo.h> /* get_nprocs */ #include <netinet/in.h> #include <sys/select.h> @@ -629,68 +628,6 @@ out: return err; } -static int finit_module(int fd, const char *param_values, int flags) -{ - return syscall(__NR_finit_module, fd, param_values, flags); -} - -static int delete_module(const char *name, int flags) -{ - return syscall(__NR_delete_module, name, flags); -} - -/* - * Trigger synchronize_rcu() in kernel. - */ -int kern_sync_rcu(void) -{ - return syscall(__NR_membarrier, MEMBARRIER_CMD_SHARED, 0, 0); -} - -static void unload_bpf_testmod(void) -{ - if (kern_sync_rcu()) - fprintf(env.stderr, "Failed to trigger kernel-side RCU sync!\n"); - if (delete_module("bpf_testmod", 0)) { - if (errno == ENOENT) { - if (verbose()) - fprintf(stdout, "bpf_testmod.ko is already unloaded.\n"); - return; - } - fprintf(env.stderr, "Failed to unload bpf_testmod.ko from kernel: %d\n", -errno); - return; - } - if (verbose()) - fprintf(stdout, "Successfully unloaded bpf_testmod.ko.\n"); -} - -static int load_bpf_testmod(void) -{ - int fd; - - /* ensure previous instance of the module is unloaded */ - unload_bpf_testmod(); - - if (verbose()) - fprintf(stdout, "Loading bpf_testmod.ko...\n"); - - fd = open("bpf_testmod.ko", O_RDONLY); - if (fd < 0) { - fprintf(env.stderr, "Can't find bpf_testmod.ko kernel module: %d\n", -errno); - return -ENOENT; - } - if (finit_module(fd, "", 0)) { - fprintf(env.stderr, "Failed to load bpf_testmod.ko into the kernel: %d\n", -errno); - close(fd); - return -EINVAL; - } - close(fd); - - if (verbose()) - fprintf(stdout, "Successfully loaded bpf_testmod.ko.\n"); - return 0; -} - /* extern declarations for test funcs */ #define DEFINE_TEST(name) \ extern void test_##name(void) __weak; \ @@ -714,7 +651,13 @@ static struct test_state test_states[ARRAY_SIZE(prog_test_defs)]; const char *argp_program_version = "test_progs 0.1"; const char *argp_program_bug_address = "<bpf@vger.kernel.org>"; -static const char argp_program_doc[] = "BPF selftests test runner"; +static const char argp_program_doc[] = +"BPF selftests test runner\v" +"Options accepting the NAMES parameter take either a comma-separated list\n" +"of test names, or a filename prefixed with @. The file contains one name\n" +"(or wildcard pattern) per line, and comments beginning with # are ignored.\n" +"\n" +"These options can be passed repeatedly to read multiple files.\n"; enum ARG_KEYS { ARG_TEST_NUM = 'n', @@ -797,6 +740,7 @@ extern int extra_prog_load_log_flags; static error_t parse_arg(int key, char *arg, struct argp_state *state) { struct test_env *env = state->input; + int err = 0; switch (key) { case ARG_TEST_NUM: { @@ -821,18 +765,28 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) } case ARG_TEST_NAME_GLOB_ALLOWLIST: case ARG_TEST_NAME: { - if (parse_test_list(arg, - &env->test_selector.whitelist, - key == ARG_TEST_NAME_GLOB_ALLOWLIST)) - return -ENOMEM; + if (arg[0] == '@') + err = parse_test_list_file(arg + 1, + &env->test_selector.whitelist, + key == ARG_TEST_NAME_GLOB_ALLOWLIST); + else + err = parse_test_list(arg, + &env->test_selector.whitelist, + key == ARG_TEST_NAME_GLOB_ALLOWLIST); + break; } case ARG_TEST_NAME_GLOB_DENYLIST: case ARG_TEST_NAME_BLACKLIST: { - if (parse_test_list(arg, - &env->test_selector.blacklist, - key == ARG_TEST_NAME_GLOB_DENYLIST)) - return -ENOMEM; + if (arg[0] == '@') + err = parse_test_list_file(arg + 1, + &env->test_selector.blacklist, + key == ARG_TEST_NAME_GLOB_DENYLIST); + else + err = parse_test_list(arg, + &env->test_selector.blacklist, + key == ARG_TEST_NAME_GLOB_DENYLIST); + break; } case ARG_VERIFIER_STATS: @@ -900,7 +854,7 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) default: return ARGP_ERR_UNKNOWN; } - return 0; + return err; } /* @@ -1703,9 +1657,14 @@ int main(int argc, char **argv) env.stderr = stderr; env.has_testmod = true; - if (!env.list_test_names && load_bpf_testmod()) { - fprintf(env.stderr, "WARNING! Selftests relying on bpf_testmod.ko will be skipped.\n"); - env.has_testmod = false; + if (!env.list_test_names) { + /* ensure previous instance of the module is unloaded */ + unload_bpf_testmod(verbose()); + + if (load_bpf_testmod(verbose())) { + fprintf(env.stderr, "WARNING! Selftests relying on bpf_testmod.ko will be skipped.\n"); + env.has_testmod = false; + } } /* initializing tests */ @@ -1802,7 +1761,7 @@ int main(int argc, char **argv) close(env.saved_netns_fd); out: if (!env.list_test_names && env.has_testmod) - unload_bpf_testmod(); + unload_bpf_testmod(verbose()); free_test_selector(&env.test_selector); free_test_selector(&env.subtest_selector); diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index 0ed3134333d4..77bd492c6024 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -405,7 +405,6 @@ static inline void *u64_to_ptr(__u64 ptr) int bpf_find_map(const char *test, struct bpf_object *obj, const char *name); int compare_map_keys(int map1_fd, int map2_fd); int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len); -int kern_sync_rcu(void); int trigger_module_test_read(int read_sz); int trigger_module_test_write(int write_sz); int write_sysctl(const char *sysctl, const char *value); diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index e4657c5bc3f1..71704a38cac3 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -40,6 +40,7 @@ #include "bpf_util.h" #include "test_btf.h" #include "../../../include/linux/filter.h" +#include "testing_helpers.h" #ifndef ENOTSUPP #define ENOTSUPP 524 @@ -873,8 +874,140 @@ static int create_map_kptr(void) return fd; } +static void set_root(bool set) +{ + __u64 caps; + + if (set) { + if (cap_enable_effective(1ULL << CAP_SYS_ADMIN, &caps)) + perror("cap_disable_effective(CAP_SYS_ADMIN)"); + } else { + if (cap_disable_effective(1ULL << CAP_SYS_ADMIN, &caps)) + perror("cap_disable_effective(CAP_SYS_ADMIN)"); + } +} + +static __u64 ptr_to_u64(const void *ptr) +{ + return (uintptr_t) ptr; +} + +static struct btf *btf__load_testmod_btf(struct btf *vmlinux) +{ + struct bpf_btf_info info; + __u32 len = sizeof(info); + struct btf *btf = NULL; + char name[64]; + __u32 id = 0; + int err, fd; + + /* Iterate all loaded BTF objects and find bpf_testmod, + * we need SYS_ADMIN cap for that. + */ + set_root(true); + + while (true) { + err = bpf_btf_get_next_id(id, &id); + if (err) { + if (errno == ENOENT) + break; + perror("bpf_btf_get_next_id failed"); + break; + } + + fd = bpf_btf_get_fd_by_id(id); + if (fd < 0) { + if (errno == ENOENT) + continue; + perror("bpf_btf_get_fd_by_id failed"); + break; + } + + memset(&info, 0, sizeof(info)); + info.name_len = sizeof(name); + info.name = ptr_to_u64(name); + len = sizeof(info); + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) { + close(fd); + perror("bpf_obj_get_info_by_fd failed"); + break; + } + + if (strcmp("bpf_testmod", name)) { + close(fd); + continue; + } + + btf = btf__load_from_kernel_by_id_split(id, vmlinux); + if (!btf) { + close(fd); + break; + } + + /* We need the fd to stay open so it can be used in fd_array. + * The final cleanup call to btf__free will free btf object + * and close the file descriptor. + */ + btf__set_fd(btf, fd); + break; + } + + set_root(false); + return btf; +} + +static struct btf *testmod_btf; +static struct btf *vmlinux_btf; + +static void kfuncs_cleanup(void) +{ + btf__free(testmod_btf); + btf__free(vmlinux_btf); +} + +static void fixup_prog_kfuncs(struct bpf_insn *prog, int *fd_array, + struct kfunc_btf_id_pair *fixup_kfunc_btf_id) +{ + /* Patch in kfunc BTF IDs */ + while (fixup_kfunc_btf_id->kfunc) { + int btf_id = 0; + + /* try to find kfunc in kernel BTF */ + vmlinux_btf = vmlinux_btf ?: btf__load_vmlinux_btf(); + if (vmlinux_btf) { + btf_id = btf__find_by_name_kind(vmlinux_btf, + fixup_kfunc_btf_id->kfunc, + BTF_KIND_FUNC); + btf_id = btf_id < 0 ? 0 : btf_id; + } + + /* kfunc not found in kernel BTF, try bpf_testmod BTF */ + if (!btf_id) { + testmod_btf = testmod_btf ?: btf__load_testmod_btf(vmlinux_btf); + if (testmod_btf) { + btf_id = btf__find_by_name_kind(testmod_btf, + fixup_kfunc_btf_id->kfunc, + BTF_KIND_FUNC); + btf_id = btf_id < 0 ? 0 : btf_id; + if (btf_id) { + /* We put bpf_testmod module fd into fd_array + * and its index 1 into instruction 'off'. + */ + *fd_array = btf__fd(testmod_btf); + prog[fixup_kfunc_btf_id->insn_idx].off = 1; + } + } + } + + prog[fixup_kfunc_btf_id->insn_idx].imm = btf_id; + fixup_kfunc_btf_id++; + } +} + static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, - struct bpf_insn *prog, int *map_fds) + struct bpf_insn *prog, int *map_fds, int *fd_array) { int *fixup_map_hash_8b = test->fixup_map_hash_8b; int *fixup_map_hash_48b = test->fixup_map_hash_48b; @@ -899,7 +1032,6 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, int *fixup_map_ringbuf = test->fixup_map_ringbuf; int *fixup_map_timer = test->fixup_map_timer; int *fixup_map_kptr = test->fixup_map_kptr; - struct kfunc_btf_id_pair *fixup_kfunc_btf_id = test->fixup_kfunc_btf_id; if (test->fill_helper) { test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn)); @@ -1100,25 +1232,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, } while (*fixup_map_kptr); } - /* Patch in kfunc BTF IDs */ - if (fixup_kfunc_btf_id->kfunc) { - struct btf *btf; - int btf_id; - - do { - btf_id = 0; - btf = btf__load_vmlinux_btf(); - if (btf) { - btf_id = btf__find_by_name_kind(btf, - fixup_kfunc_btf_id->kfunc, - BTF_KIND_FUNC); - btf_id = btf_id < 0 ? 0 : btf_id; - } - btf__free(btf); - prog[fixup_kfunc_btf_id->insn_idx].imm = btf_id; - fixup_kfunc_btf_id++; - } while (fixup_kfunc_btf_id->kfunc); - } + fixup_prog_kfuncs(prog, fd_array, test->fixup_kfunc_btf_id); } struct libcap { @@ -1445,6 +1559,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, int run_errs, run_successes; int map_fds[MAX_NR_MAPS]; const char *expected_err; + int fd_array[2] = { -1, -1 }; int saved_errno; int fixup_skips; __u32 pflags; @@ -1458,7 +1573,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, if (!prog_type) prog_type = BPF_PROG_TYPE_SOCKET_FILTER; fixup_skips = skips; - do_test_fixup(test, prog_type, prog, map_fds); + do_test_fixup(test, prog_type, prog, map_fds, &fd_array[1]); if (test->fill_insns) { prog = test->fill_insns; prog_len = test->prog_len; @@ -1492,6 +1607,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv, else opts.log_level = DEFAULT_LIBBPF_LOG_LEVEL; opts.prog_flags = pflags; + if (fd_array[1] != -1) + opts.fd_array = &fd_array[0]; if ((prog_type == BPF_PROG_TYPE_TRACING || prog_type == BPF_PROG_TYPE_LSM) && test->kfunc) { @@ -1684,6 +1801,12 @@ static int do_test(bool unpriv, unsigned int from, unsigned int to) { int i, passes = 0, errors = 0; + /* ensure previous instance of the module is unloaded */ + unload_bpf_testmod(verbose); + + if (load_bpf_testmod(verbose)) + return EXIT_FAILURE; + for (i = from; i < to; i++) { struct bpf_test *test = &tests[i]; @@ -1711,6 +1834,9 @@ static int do_test(bool unpriv, unsigned int from, unsigned int to) } } + unload_bpf_testmod(verbose); + kfuncs_cleanup(); + printf("Summary: %d PASSED, %d SKIPPED, %d FAILED\n", passes, skips, errors); return errors ? EXIT_FAILURE : EXIT_SUCCESS; diff --git a/tools/testing/selftests/bpf/test_xsk.sh b/tools/testing/selftests/bpf/test_xsk.sh index 377fb157a57c..c2ad50f26b63 100755 --- a/tools/testing/selftests/bpf/test_xsk.sh +++ b/tools/testing/selftests/bpf/test_xsk.sh @@ -68,9 +68,6 @@ # Run with verbose output: # sudo ./test_xsk.sh -v # -# Run and dump packet contents: -# sudo ./test_xsk.sh -D -# # Set up veth interfaces and leave them up so xskxceiver can be launched in a debugger: # sudo ./test_xsk.sh -d # @@ -81,11 +78,10 @@ ETH="" -while getopts "vDi:d" flag +while getopts "vi:d" flag do case "${flag}" in v) verbose=1;; - D) dump_pkts=1;; d) debug=1;; i) ETH=${OPTARG};; esac @@ -157,10 +153,6 @@ if [[ $verbose -eq 1 ]]; then ARGS+="-v " fi -if [[ $dump_pkts -eq 1 ]]; then - ARGS="-D " -fi - retval=$? test_status $retval "${TEST_NAME}" diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c index 0b5e0829e5be..8d994884c7b4 100644 --- a/tools/testing/selftests/bpf/testing_helpers.c +++ b/tools/testing/selftests/bpf/testing_helpers.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) /* Copyright (C) 2019 Netronome Systems, Inc. */ /* Copyright (C) 2020 Facebook, Inc. */ +#include <ctype.h> #include <stdlib.h> #include <string.h> #include <errno.h> @@ -8,6 +9,7 @@ #include <bpf/libbpf.h> #include "test_progs.h" #include "testing_helpers.h" +#include <linux/membarrier.h> int parse_num_list(const char *s, bool **num_set, int *num_set_len) { @@ -70,92 +72,168 @@ int parse_num_list(const char *s, bool **num_set, int *num_set_len) return 0; } -int parse_test_list(const char *s, - struct test_filter_set *set, - bool is_glob_pattern) +static int do_insert_test(struct test_filter_set *set, + char *test_str, + char *subtest_str) { - char *input, *state = NULL, *next; - struct test_filter *tmp, *tests = NULL; - int i, j, cnt = 0; + struct test_filter *tmp, *test; + char **ctmp; + int i; - input = strdup(s); - if (!input) + for (i = 0; i < set->cnt; i++) { + test = &set->tests[i]; + + if (strcmp(test_str, test->name) == 0) { + free(test_str); + goto subtest; + } + } + + tmp = realloc(set->tests, sizeof(*test) * (set->cnt + 1)); + if (!tmp) return -ENOMEM; - while ((next = strtok_r(state ? NULL : input, ",", &state))) { - char *subtest_str = strchr(next, '/'); - char *pattern = NULL; - int glob_chars = 0; + set->tests = tmp; + test = &set->tests[set->cnt]; - tmp = realloc(tests, sizeof(*tests) * (cnt + 1)); - if (!tmp) - goto err; - tests = tmp; + test->name = test_str; + test->subtests = NULL; + test->subtest_cnt = 0; - tests[cnt].subtest_cnt = 0; - tests[cnt].subtests = NULL; + set->cnt++; - if (is_glob_pattern) { - pattern = "%s"; - } else { - pattern = "*%s*"; - glob_chars = 2; - } +subtest: + if (!subtest_str) + return 0; - if (subtest_str) { - char **tmp_subtests = NULL; - int subtest_cnt = tests[cnt].subtest_cnt; - - *subtest_str = '\0'; - subtest_str += 1; - tmp_subtests = realloc(tests[cnt].subtests, - sizeof(*tmp_subtests) * - (subtest_cnt + 1)); - if (!tmp_subtests) - goto err; - tests[cnt].subtests = tmp_subtests; - - tests[cnt].subtests[subtest_cnt] = - malloc(strlen(subtest_str) + glob_chars + 1); - if (!tests[cnt].subtests[subtest_cnt]) - goto err; - sprintf(tests[cnt].subtests[subtest_cnt], - pattern, - subtest_str); - - tests[cnt].subtest_cnt++; + for (i = 0; i < test->subtest_cnt; i++) { + if (strcmp(subtest_str, test->subtests[i]) == 0) { + free(subtest_str); + return 0; } + } - tests[cnt].name = malloc(strlen(next) + glob_chars + 1); - if (!tests[cnt].name) - goto err; - sprintf(tests[cnt].name, pattern, next); + ctmp = realloc(test->subtests, + sizeof(*test->subtests) * (test->subtest_cnt + 1)); + if (!ctmp) + return -ENOMEM; - cnt++; + test->subtests = ctmp; + test->subtests[test->subtest_cnt] = subtest_str; + + test->subtest_cnt++; + + return 0; +} + +static int insert_test(struct test_filter_set *set, + char *test_spec, + bool is_glob_pattern) +{ + char *pattern, *subtest_str, *ext_test_str, *ext_subtest_str = NULL; + int glob_chars = 0; + + if (is_glob_pattern) { + pattern = "%s"; + } else { + pattern = "*%s*"; + glob_chars = 2; } - tmp = realloc(set->tests, sizeof(*tests) * (cnt + set->cnt)); - if (!tmp) + subtest_str = strchr(test_spec, '/'); + if (subtest_str) { + *subtest_str = '\0'; + subtest_str += 1; + } + + ext_test_str = malloc(strlen(test_spec) + glob_chars + 1); + if (!ext_test_str) goto err; - memcpy(tmp + set->cnt, tests, sizeof(*tests) * cnt); - set->tests = tmp; - set->cnt += cnt; + sprintf(ext_test_str, pattern, test_spec); - free(tests); - free(input); - return 0; + if (subtest_str) { + ext_subtest_str = malloc(strlen(subtest_str) + glob_chars + 1); + if (!ext_subtest_str) + goto err; + + sprintf(ext_subtest_str, pattern, subtest_str); + } + + return do_insert_test(set, ext_test_str, ext_subtest_str); err: - for (i = 0; i < cnt; i++) { - for (j = 0; j < tests[i].subtest_cnt; j++) - free(tests[i].subtests[j]); + free(ext_test_str); + free(ext_subtest_str); + + return -ENOMEM; +} + +int parse_test_list_file(const char *path, + struct test_filter_set *set, + bool is_glob_pattern) +{ + char *buf = NULL, *capture_start, *capture_end, *scan_end; + size_t buflen = 0; + int err = 0; + FILE *f; + + f = fopen(path, "r"); + if (!f) { + err = -errno; + fprintf(stderr, "Failed to open '%s': %d\n", path, err); + return err; + } + + while (getline(&buf, &buflen, f) != -1) { + capture_start = buf; + + while (isspace(*capture_start)) + ++capture_start; + + capture_end = capture_start; + scan_end = capture_start; + + while (*scan_end && *scan_end != '#') { + if (!isspace(*scan_end)) + capture_end = scan_end; + + ++scan_end; + } + + if (capture_end == capture_start) + continue; + + *(++capture_end) = '\0'; + + err = insert_test(set, capture_start, is_glob_pattern); + if (err) + break; + } + + fclose(f); + return err; +} + +int parse_test_list(const char *s, + struct test_filter_set *set, + bool is_glob_pattern) +{ + char *input, *state = NULL, *test_spec; + int err = 0; + + input = strdup(s); + if (!input) + return -ENOMEM; - free(tests[i].name); + while ((test_spec = strtok_r(state ? NULL : input, ",", &state))) { + err = insert_test(set, test_spec, is_glob_pattern); + if (err) + break; } - free(tests); + free(input); - return -ENOMEM; + return err; } __u32 link_info_prog_id(const struct bpf_link *link, struct bpf_link_info *info) @@ -249,3 +327,63 @@ __u64 read_perf_max_sample_freq(void) fclose(f); return sample_freq; } + +static int finit_module(int fd, const char *param_values, int flags) +{ + return syscall(__NR_finit_module, fd, param_values, flags); +} + +static int delete_module(const char *name, int flags) +{ + return syscall(__NR_delete_module, name, flags); +} + +int unload_bpf_testmod(bool verbose) +{ + if (kern_sync_rcu()) + fprintf(stdout, "Failed to trigger kernel-side RCU sync!\n"); + if (delete_module("bpf_testmod", 0)) { + if (errno == ENOENT) { + if (verbose) + fprintf(stdout, "bpf_testmod.ko is already unloaded.\n"); + return -1; + } + fprintf(stdout, "Failed to unload bpf_testmod.ko from kernel: %d\n", -errno); + return -1; + } + if (verbose) + fprintf(stdout, "Successfully unloaded bpf_testmod.ko.\n"); + return 0; +} + +int load_bpf_testmod(bool verbose) +{ + int fd; + + if (verbose) + fprintf(stdout, "Loading bpf_testmod.ko...\n"); + + fd = open("bpf_testmod.ko", O_RDONLY); + if (fd < 0) { + fprintf(stdout, "Can't find bpf_testmod.ko kernel module: %d\n", -errno); + return -ENOENT; + } + if (finit_module(fd, "", 0)) { + fprintf(stdout, "Failed to load bpf_testmod.ko into the kernel: %d\n", -errno); + close(fd); + return -EINVAL; + } + close(fd); + + if (verbose) + fprintf(stdout, "Successfully loaded bpf_testmod.ko.\n"); + return 0; +} + +/* + * Trigger synchronize_rcu() in kernel. + */ +int kern_sync_rcu(void) +{ + return syscall(__NR_membarrier, MEMBARRIER_CMD_SHARED, 0, 0); +} diff --git a/tools/testing/selftests/bpf/testing_helpers.h b/tools/testing/selftests/bpf/testing_helpers.h index eb8790f928e4..5312323881b6 100644 --- a/tools/testing/selftests/bpf/testing_helpers.h +++ b/tools/testing/selftests/bpf/testing_helpers.h @@ -1,5 +1,9 @@ /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ /* Copyright (C) 2020 Facebook, Inc. */ + +#ifndef __TESTING_HELPERS_H +#define __TESTING_HELPERS_H + #include <stdbool.h> #include <bpf/bpf.h> #include <bpf/libbpf.h> @@ -20,5 +24,13 @@ struct test_filter_set; int parse_test_list(const char *s, struct test_filter_set *test_set, bool is_glob_pattern); +int parse_test_list_file(const char *path, + struct test_filter_set *test_set, + bool is_glob_pattern); __u64 read_perf_max_sample_freq(void); +int load_bpf_testmod(bool verbose); +int unload_bpf_testmod(bool verbose); +int kern_sync_rcu(void); + +#endif /* __TESTING_HELPERS_H */ diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c index 6c03a7d805f9..b8c0aae8e7ec 100644 --- a/tools/testing/selftests/bpf/verifier/precise.c +++ b/tools/testing/selftests/bpf/verifier/precise.c @@ -38,25 +38,24 @@ .fixup_map_array_48b = { 1 }, .result = VERBOSE_ACCEPT, .errstr = - "26: (85) call bpf_probe_read_kernel#113\ - last_idx 26 first_idx 20\ - regs=4 stack=0 before 25\ - regs=4 stack=0 before 24\ - regs=4 stack=0 before 23\ - regs=4 stack=0 before 22\ - regs=4 stack=0 before 20\ - parent didn't have regs=4 stack=0 marks\ - last_idx 19 first_idx 10\ - regs=4 stack=0 before 19\ - regs=200 stack=0 before 18\ - regs=300 stack=0 before 17\ - regs=201 stack=0 before 15\ - regs=201 stack=0 before 14\ - regs=200 stack=0 before 13\ - regs=200 stack=0 before 12\ - regs=200 stack=0 before 11\ - regs=200 stack=0 before 10\ - parent already had regs=0 stack=0 marks", + "mark_precise: frame0: last_idx 26 first_idx 20\ + mark_precise: frame0: regs=r2 stack= before 25\ + mark_precise: frame0: regs=r2 stack= before 24\ + mark_precise: frame0: regs=r2 stack= before 23\ + mark_precise: frame0: regs=r2 stack= before 22\ + mark_precise: frame0: regs=r2 stack= before 20\ + mark_precise: frame0: parent state regs=r2 stack=:\ + mark_precise: frame0: last_idx 19 first_idx 10\ + mark_precise: frame0: regs=r2 stack= before 19\ + mark_precise: frame0: regs=r9 stack= before 18\ + mark_precise: frame0: regs=r8,r9 stack= before 17\ + mark_precise: frame0: regs=r0,r9 stack= before 15\ + mark_precise: frame0: regs=r0,r9 stack= before 14\ + mark_precise: frame0: regs=r9 stack= before 13\ + mark_precise: frame0: regs=r9 stack= before 12\ + mark_precise: frame0: regs=r9 stack= before 11\ + mark_precise: frame0: regs=r9 stack= before 10\ + mark_precise: frame0: parent state regs= stack=:", }, { "precise: test 2", @@ -100,20 +99,20 @@ .flags = BPF_F_TEST_STATE_FREQ, .errstr = "26: (85) call bpf_probe_read_kernel#113\ - last_idx 26 first_idx 22\ - regs=4 stack=0 before 25\ - regs=4 stack=0 before 24\ - regs=4 stack=0 before 23\ - regs=4 stack=0 before 22\ - parent didn't have regs=4 stack=0 marks\ - last_idx 20 first_idx 20\ - regs=4 stack=0 before 20\ - parent didn't have regs=4 stack=0 marks\ - last_idx 19 first_idx 17\ - regs=4 stack=0 before 19\ - regs=200 stack=0 before 18\ - regs=300 stack=0 before 17\ - parent already had regs=0 stack=0 marks", + mark_precise: frame0: last_idx 26 first_idx 22\ + mark_precise: frame0: regs=r2 stack= before 25\ + mark_precise: frame0: regs=r2 stack= before 24\ + mark_precise: frame0: regs=r2 stack= before 23\ + mark_precise: frame0: regs=r2 stack= before 22\ + mark_precise: frame0: parent state regs=r2 stack=:\ + mark_precise: frame0: last_idx 20 first_idx 20\ + mark_precise: frame0: regs=r2 stack= before 20\ + mark_precise: frame0: parent state regs=r2 stack=:\ + mark_precise: frame0: last_idx 19 first_idx 17\ + mark_precise: frame0: regs=r2 stack= before 19\ + mark_precise: frame0: regs=r9 stack= before 18\ + mark_precise: frame0: regs=r8,r9 stack= before 17\ + mark_precise: frame0: parent state regs= stack=:", }, { "precise: cross frame pruning", @@ -153,15 +152,16 @@ }, .prog_type = BPF_PROG_TYPE_XDP, .flags = BPF_F_TEST_STATE_FREQ, - .errstr = "5: (2d) if r4 > r0 goto pc+0\ - last_idx 5 first_idx 5\ - parent didn't have regs=10 stack=0 marks\ - last_idx 4 first_idx 2\ - regs=10 stack=0 before 4\ - regs=10 stack=0 before 3\ - regs=0 stack=1 before 2\ - last_idx 5 first_idx 5\ - parent didn't have regs=1 stack=0 marks", + .errstr = "mark_precise: frame0: last_idx 5 first_idx 5\ + mark_precise: frame0: parent state regs=r4 stack=:\ + mark_precise: frame0: last_idx 4 first_idx 2\ + mark_precise: frame0: regs=r4 stack= before 4\ + mark_precise: frame0: regs=r4 stack= before 3\ + mark_precise: frame0: regs= stack=-8 before 2\ + mark_precise: frame0: falling back to forcing all scalars precise\ + force_precise: frame0: forcing r0 to be precise\ + mark_precise: frame0: last_idx 5 first_idx 5\ + mark_precise: frame0: parent state regs= stack=:", .result = VERBOSE_ACCEPT, .retval = -1, }, @@ -179,16 +179,19 @@ }, .prog_type = BPF_PROG_TYPE_XDP, .flags = BPF_F_TEST_STATE_FREQ, - .errstr = "last_idx 6 first_idx 6\ - parent didn't have regs=10 stack=0 marks\ - last_idx 5 first_idx 3\ - regs=10 stack=0 before 5\ - regs=10 stack=0 before 4\ - regs=0 stack=1 before 3\ - last_idx 6 first_idx 6\ - parent didn't have regs=1 stack=0 marks\ - last_idx 5 first_idx 3\ - regs=1 stack=0 before 5", + .errstr = "mark_precise: frame0: last_idx 6 first_idx 6\ + mark_precise: frame0: parent state regs=r4 stack=:\ + mark_precise: frame0: last_idx 5 first_idx 3\ + mark_precise: frame0: regs=r4 stack= before 5\ + mark_precise: frame0: regs=r4 stack= before 4\ + mark_precise: frame0: regs= stack=-8 before 3\ + mark_precise: frame0: falling back to forcing all scalars precise\ + force_precise: frame0: forcing r0 to be precise\ + force_precise: frame0: forcing r0 to be precise\ + force_precise: frame0: forcing r0 to be precise\ + force_precise: frame0: forcing r0 to be precise\ + mark_precise: frame0: last_idx 6 first_idx 6\ + mark_precise: frame0: parent state regs= stack=:", .result = VERBOSE_ACCEPT, .retval = -1, }, @@ -217,3 +220,39 @@ .errstr = "invalid access to memory, mem_size=1 off=42 size=8", .result = REJECT, }, +{ + "precise: program doesn't prematurely prune branches", + .insns = { + BPF_ALU64_IMM(BPF_MOV, BPF_REG_6, 0x400), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_7, 0), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_8, 0), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_9, 0x80000000), + BPF_ALU64_IMM(BPF_MOD, BPF_REG_6, 0x401), + BPF_JMP_IMM(BPF_JA, 0, 0, 0), + BPF_JMP_REG(BPF_JLE, BPF_REG_6, BPF_REG_9, 2), + BPF_ALU64_IMM(BPF_MOD, BPF_REG_6, 1), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_9, 0), + BPF_JMP_REG(BPF_JLE, BPF_REG_6, BPF_REG_9, 1), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_6, 0), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), + BPF_LD_MAP_FD(BPF_REG_4, 0), + BPF_ALU64_REG(BPF_MOV, BPF_REG_1, BPF_REG_4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_6, 10), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_6, 8192), + BPF_ALU64_REG(BPF_MOV, BPF_REG_1, BPF_REG_0), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_6), + BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_3, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 13 }, + .prog_type = BPF_PROG_TYPE_XDP, + .result = REJECT, + .errstr = "register with unbounded min value is not allowed", +}, diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c index 1db7185181da..655095810d4a 100644 --- a/tools/testing/selftests/bpf/veristat.c +++ b/tools/testing/selftests/bpf/veristat.c @@ -141,6 +141,7 @@ static struct env { bool verbose; bool debug; bool quiet; + bool force_checkpoints; enum resfmt out_fmt; bool show_version; bool comparison_mode; @@ -209,6 +210,8 @@ static const struct argp_option opts[] = { { "log-level", 'l', "LEVEL", 0, "Verifier log level (default 0 for normal mode, 1 for verbose mode)" }, { "log-fixed", OPT_LOG_FIXED, NULL, 0, "Disable verifier log rotation" }, { "log-size", OPT_LOG_SIZE, "BYTES", 0, "Customize verifier log size (default to 16MB)" }, + { "test-states", 't', NULL, 0, + "Force frequent BPF verifier state checkpointing (set BPF_F_TEST_STATE_FREQ program flag)" }, { "quiet", 'q', NULL, 0, "Quiet mode" }, { "emit", 'e', "SPEC", 0, "Specify stats to be emitted" }, { "sort", 's', "SPEC", 0, "Specify sort order" }, @@ -284,6 +287,9 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) argp_usage(state); } break; + case 't': + env.force_checkpoints = true; + break; case 'C': env.comparison_mode = true; break; @@ -989,6 +995,9 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf /* increase chances of successful BPF object loading */ fixup_obj(obj, prog, base_filename); + if (env.force_checkpoints) + bpf_program__set_flags(prog, bpf_program__flags(prog) | BPF_F_TEST_STATE_FREQ); + err = bpf_object__load(obj); env.progs_processed++; diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c index 987cf0db5ebc..613321eb84c1 100644 --- a/tools/testing/selftests/bpf/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c @@ -27,6 +27,7 @@ #include <sys/mman.h> #include <net/if.h> #include <poll.h> +#include <time.h> #include "xdp_metadata.h" @@ -134,18 +135,52 @@ static void refill_rx(struct xsk *xsk, __u64 addr) } } -static void verify_xdp_metadata(void *data) +#define NANOSEC_PER_SEC 1000000000 /* 10^9 */ +static __u64 gettime(clockid_t clock_id) +{ + struct timespec t; + int res; + + /* See man clock_gettime(2) for type of clock_id's */ + res = clock_gettime(clock_id, &t); + + if (res < 0) + error(res, errno, "Error with clock_gettime()"); + + return (__u64) t.tv_sec * NANOSEC_PER_SEC + t.tv_nsec; +} + +static void verify_xdp_metadata(void *data, clockid_t clock_id) { struct xdp_meta *meta; meta = data - sizeof(*meta); - printf("rx_timestamp: %llu\n", meta->rx_timestamp); if (meta->rx_hash_err < 0) printf("No rx_hash err=%d\n", meta->rx_hash_err); else printf("rx_hash: 0x%X with RSS type:0x%X\n", meta->rx_hash, meta->rx_hash_type); + + printf("rx_timestamp: %llu (sec:%0.4f)\n", meta->rx_timestamp, + (double)meta->rx_timestamp / NANOSEC_PER_SEC); + if (meta->rx_timestamp) { + __u64 usr_clock = gettime(clock_id); + __u64 xdp_clock = meta->xdp_timestamp; + __s64 delta_X = xdp_clock - meta->rx_timestamp; + __s64 delta_X2U = usr_clock - xdp_clock; + + printf("XDP RX-time: %llu (sec:%0.4f) delta sec:%0.4f (%0.3f usec)\n", + xdp_clock, (double)xdp_clock / NANOSEC_PER_SEC, + (double)delta_X / NANOSEC_PER_SEC, + (double)delta_X / 1000); + + printf("AF_XDP time: %llu (sec:%0.4f) delta sec:%0.4f (%0.3f usec)\n", + usr_clock, (double)usr_clock / NANOSEC_PER_SEC, + (double)delta_X2U / NANOSEC_PER_SEC, + (double)delta_X2U / 1000); + } + } static void verify_skb_metadata(int fd) @@ -193,7 +228,7 @@ static void verify_skb_metadata(int fd) printf("skb hwtstamp is not found!\n"); } -static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd) +static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t clock_id) { const struct xdp_desc *rx_desc; struct pollfd fds[rxq + 1]; @@ -243,7 +278,8 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd) addr = xsk_umem__add_offset_to_addr(rx_desc->addr); printf("%p: rx_desc[%u]->addr=%llx addr=%llx comp_addr=%llx\n", xsk, idx, rx_desc->addr, addr, comp_addr); - verify_xdp_metadata(xsk_umem__get_data(xsk->umem_area, addr)); + verify_xdp_metadata(xsk_umem__get_data(xsk->umem_area, addr), + clock_id); xsk_ring_cons__release(&xsk->rx, 1); refill_rx(xsk, comp_addr); } @@ -370,6 +406,7 @@ static void timestamping_enable(int fd, int val) int main(int argc, char *argv[]) { + clockid_t clock_id = CLOCK_TAI; int server_fd = -1; int ret; int i; @@ -443,7 +480,7 @@ int main(int argc, char *argv[]) error(1, -ret, "bpf_xdp_attach"); signal(SIGINT, handle_signal); - ret = verify_metadata(rx_xsk, rxq, server_fd); + ret = verify_metadata(rx_xsk, rxq, server_fd, clock_id); close(server_fd); cleanup(); if (ret) diff --git a/tools/testing/selftests/bpf/xdp_metadata.h b/tools/testing/selftests/bpf/xdp_metadata.h index 0c4624dc6f2f..938a729bd307 100644 --- a/tools/testing/selftests/bpf/xdp_metadata.h +++ b/tools/testing/selftests/bpf/xdp_metadata.h @@ -11,6 +11,7 @@ struct xdp_meta { __u64 rx_timestamp; + __u64 xdp_timestamp; __u32 rx_hash; union { __u32 rx_hash_type; diff --git a/tools/testing/selftests/bpf/xsk.h b/tools/testing/selftests/bpf/xsk.h index 04ed8b544712..8da8d557768b 100644 --- a/tools/testing/selftests/bpf/xsk.h +++ b/tools/testing/selftests/bpf/xsk.h @@ -134,6 +134,11 @@ static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, __u32 nb) __atomic_store_n(prod->producer, *prod->producer + nb, __ATOMIC_RELEASE); } +static inline void xsk_ring_prod__cancel(struct xsk_ring_prod *prod, __u32 nb) +{ + prod->cached_prod -= nb; +} + static inline __u32 xsk_ring_cons__peek(struct xsk_ring_cons *cons, __u32 nb, __u32 *idx) { __u32 entries = xsk_cons_nb_avail(cons, nb); diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c index f144d0604ddf..218d7f694e5c 100644 --- a/tools/testing/selftests/bpf/xskxceiver.c +++ b/tools/testing/selftests/bpf/xskxceiver.c @@ -76,16 +76,13 @@ #include <asm/barrier.h> #include <linux/if_link.h> #include <linux/if_ether.h> -#include <linux/ip.h> #include <linux/mman.h> -#include <linux/udp.h> #include <arpa/inet.h> #include <net/if.h> #include <locale.h> #include <poll.h> #include <pthread.h> #include <signal.h> -#include <stdbool.h> #include <stdio.h> #include <stdlib.h> #include <string.h> @@ -94,10 +91,8 @@ #include <sys/socket.h> #include <sys/time.h> #include <sys/types.h> -#include <sys/queue.h> #include <time.h> #include <unistd.h> -#include <stdatomic.h> #include "xsk_xdp_progs.skel.h" #include "xsk.h" @@ -109,10 +104,6 @@ static const char *MAC1 = "\x00\x0A\x56\x9E\xEE\x62"; static const char *MAC2 = "\x00\x0A\x56\x9E\xEE\x61"; -static const char *IP1 = "192.168.100.162"; -static const char *IP2 = "192.168.100.161"; -static const u16 UDP_PORT1 = 2020; -static const u16 UDP_PORT2 = 2121; static void __exit_with_error(int error, const char *file, const char *func, int line) { @@ -147,112 +138,25 @@ static void report_failure(struct test_spec *test) test->fail = true; } -static void memset32_htonl(void *dest, u32 val, u32 size) -{ - u32 *ptr = (u32 *)dest; - int i; - - val = htonl(val); - - for (i = 0; i < (size & (~0x3)); i += 4) - ptr[i >> 2] = val; -} - -/* - * Fold a partial checksum - * This function code has been taken from - * Linux kernel include/asm-generic/checksum.h - */ -static __u16 csum_fold(__u32 csum) -{ - u32 sum = (__force u32)csum; - - sum = (sum & 0xffff) + (sum >> 16); - sum = (sum & 0xffff) + (sum >> 16); - return (__force __u16)~sum; -} - -/* - * This function code has been taken from - * Linux kernel lib/checksum.c - */ -static u32 from64to32(u64 x) -{ - /* add up 32-bit and 32-bit for 32+c bit */ - x = (x & 0xffffffff) + (x >> 32); - /* add up carry.. */ - x = (x & 0xffffffff) + (x >> 32); - return (u32)x; -} - -/* - * This function code has been taken from - * Linux kernel lib/checksum.c - */ -static __u32 csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum) -{ - unsigned long long s = (__force u32)sum; - - s += (__force u32)saddr; - s += (__force u32)daddr; -#ifdef __BIG_ENDIAN__ - s += proto + len; -#else - s += (proto + len) << 8; -#endif - return (__force __u32)from64to32(s); -} - -/* - * This function has been taken from - * Linux kernel include/asm-generic/checksum.h +/* The payload is a word consisting of a packet sequence number in the upper + * 16-bits and a intra packet data sequence number in the lower 16 bits. So the 3rd packet's + * 5th word of data will contain the number (2<<16) | 4 as they are numbered from 0. */ -static __u16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum) -{ - return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum)); -} - -static u16 udp_csum(u32 saddr, u32 daddr, u32 len, u8 proto, u16 *udp_pkt) +static void write_payload(void *dest, u32 pkt_nb, u32 start, u32 size) { - u32 csum = 0; - u32 cnt = 0; - - /* udp hdr and data */ - for (; cnt < len; cnt += 2) - csum += udp_pkt[cnt >> 1]; + u32 *ptr = (u32 *)dest, i; - return csum_tcpudp_magic(saddr, daddr, len, proto, csum); + start /= sizeof(*ptr); + size /= sizeof(*ptr); + for (i = 0; i < size; i++) + ptr[i] = htonl(pkt_nb << 16 | (i + start)); } static void gen_eth_hdr(struct ifobject *ifobject, struct ethhdr *eth_hdr) { memcpy(eth_hdr->h_dest, ifobject->dst_mac, ETH_ALEN); memcpy(eth_hdr->h_source, ifobject->src_mac, ETH_ALEN); - eth_hdr->h_proto = htons(ETH_P_IP); -} - -static void gen_ip_hdr(struct ifobject *ifobject, struct iphdr *ip_hdr) -{ - ip_hdr->version = IP_PKT_VER; - ip_hdr->ihl = 0x5; - ip_hdr->tos = IP_PKT_TOS; - ip_hdr->tot_len = htons(IP_PKT_SIZE); - ip_hdr->id = 0; - ip_hdr->frag_off = 0; - ip_hdr->ttl = IPDEFTTL; - ip_hdr->protocol = IPPROTO_UDP; - ip_hdr->saddr = ifobject->src_ip; - ip_hdr->daddr = ifobject->dst_ip; - ip_hdr->check = 0; -} - -static void gen_udp_hdr(u32 payload, void *pkt, struct ifobject *ifobject, - struct udphdr *udp_hdr) -{ - udp_hdr->source = htons(ifobject->src_port); - udp_hdr->dest = htons(ifobject->dst_port); - udp_hdr->len = htons(UDP_PKT_SIZE); - memset32_htonl(pkt + PKT_HDR_SIZE, payload, UDP_PKT_DATA_SIZE); + eth_hdr->h_proto = htons(ETH_P_LOOPBACK); } static bool is_umem_valid(struct ifobject *ifobj) @@ -260,19 +164,18 @@ static bool is_umem_valid(struct ifobject *ifobj) return !!ifobj->umem->umem; } -static void gen_udp_csum(struct udphdr *udp_hdr, struct iphdr *ip_hdr) +static u32 mode_to_xdp_flags(enum test_mode mode) { - udp_hdr->check = 0; - udp_hdr->check = - udp_csum(ip_hdr->saddr, ip_hdr->daddr, UDP_PKT_SIZE, IPPROTO_UDP, (u16 *)udp_hdr); + return (mode == TEST_MODE_SKB) ? XDP_FLAGS_SKB_MODE : XDP_FLAGS_DRV_MODE; } -static u32 mode_to_xdp_flags(enum test_mode mode) +static u64 umem_size(struct xsk_umem_info *umem) { - return (mode == TEST_MODE_SKB) ? XDP_FLAGS_SKB_MODE : XDP_FLAGS_DRV_MODE; + return umem->num_frames * umem->frame_size; } -static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size) +static int xsk_configure_umem(struct ifobject *ifobj, struct xsk_umem_info *umem, void *buffer, + u64 size) { struct xsk_umem_config cfg = { .fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, @@ -292,9 +195,31 @@ static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size return ret; umem->buffer = buffer; + if (ifobj->shared_umem && ifobj->rx_on) { + umem->base_addr = umem_size(umem); + umem->next_buffer = umem_size(umem); + } + return 0; } +static u64 umem_alloc_buffer(struct xsk_umem_info *umem) +{ + u64 addr; + + addr = umem->next_buffer; + umem->next_buffer += umem->frame_size; + if (umem->next_buffer >= umem->base_addr + umem_size(umem)) + umem->next_buffer = umem->base_addr; + + return addr; +} + +static void umem_reset_alloc(struct xsk_umem_info *umem) +{ + umem->next_buffer = 0; +} + static void enable_busy_poll(struct xsk_socket_info *xsk) { int sock_opt; @@ -354,7 +279,7 @@ static bool ifobj_zc_avail(struct ifobject *ifobject) exit_with_error(ENOMEM); } umem->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; - ret = xsk_configure_umem(umem, bufs, umem_sz); + ret = xsk_configure_umem(ifobject, umem, bufs, umem_sz); if (ret) exit_with_error(-ret); @@ -380,7 +305,6 @@ out: static struct option long_options[] = { {"interface", required_argument, 0, 'i'}, {"busy-poll", no_argument, 0, 'b'}, - {"dump-pkts", no_argument, 0, 'D'}, {"verbose", no_argument, 0, 'v'}, {0, 0, 0, 0} }; @@ -391,7 +315,6 @@ static void usage(const char *prog) " Usage: %s [OPTIONS]\n" " Options:\n" " -i, --interface Use interface\n" - " -D, --dump-pkts Dump packets L2 - L5\n" " -v, --verbose Verbose output\n" " -b, --busy-poll Enable busy poll\n"; @@ -415,7 +338,7 @@ static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj opterr = 0; for (;;) { - c = getopt_long(argc, argv, "i:Dvb", long_options, &option_index); + c = getopt_long(argc, argv, "i:vb", long_options, &option_index); if (c == -1) break; @@ -437,9 +360,6 @@ static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj interface_nb++; break; - case 'D': - opt_pkt_dump = true; - break; case 'v': opt_verbose = true; break; @@ -482,9 +402,6 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, memset(ifobj->umem, 0, sizeof(*ifobj->umem)); ifobj->umem->num_frames = DEFAULT_UMEM_BUFFERS; ifobj->umem->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; - if (ifobj->shared_umem && ifobj->rx_on) - ifobj->umem->base_addr = DEFAULT_UMEM_BUFFERS * - XSK_UMEM__DEFAULT_FRAME_SIZE; for (j = 0; j < MAX_SOCKETS; j++) { memset(&ifobj->xsk_arr[j], 0, sizeof(ifobj->xsk_arr[j])); @@ -554,24 +471,24 @@ static void test_spec_set_xdp_prog(struct test_spec *test, struct bpf_program *x static void pkt_stream_reset(struct pkt_stream *pkt_stream) { if (pkt_stream) - pkt_stream->rx_pkt_nb = 0; + pkt_stream->current_pkt_nb = 0; } -static struct pkt *pkt_stream_get_pkt(struct pkt_stream *pkt_stream, u32 pkt_nb) +static struct pkt *pkt_stream_get_next_tx_pkt(struct pkt_stream *pkt_stream) { - if (pkt_nb >= pkt_stream->nb_pkts) + if (pkt_stream->current_pkt_nb >= pkt_stream->nb_pkts) return NULL; - return &pkt_stream->pkts[pkt_nb]; + return &pkt_stream->pkts[pkt_stream->current_pkt_nb++]; } static struct pkt *pkt_stream_get_next_rx_pkt(struct pkt_stream *pkt_stream, u32 *pkts_sent) { - while (pkt_stream->rx_pkt_nb < pkt_stream->nb_pkts) { + while (pkt_stream->current_pkt_nb < pkt_stream->nb_pkts) { (*pkts_sent)++; - if (pkt_stream->pkts[pkt_stream->rx_pkt_nb].valid) - return &pkt_stream->pkts[pkt_stream->rx_pkt_nb++]; - pkt_stream->rx_pkt_nb++; + if (pkt_stream->pkts[pkt_stream->current_pkt_nb].valid) + return &pkt_stream->pkts[pkt_stream->current_pkt_nb++]; + pkt_stream->current_pkt_nb++; } return NULL; } @@ -616,9 +533,21 @@ static struct pkt_stream *__pkt_stream_alloc(u32 nb_pkts) return pkt_stream; } -static void pkt_set(struct xsk_umem_info *umem, struct pkt *pkt, u64 addr, u32 len) +static u32 ceil_u32(u32 a, u32 b) +{ + return (a + b - 1) / b; +} + +static u32 pkt_nb_frags(u32 frame_size, struct pkt *pkt) +{ + if (!pkt || !pkt->valid) + return 1; + return ceil_u32(pkt->len, frame_size); +} + +static void pkt_set(struct xsk_umem_info *umem, struct pkt *pkt, int offset, u32 len) { - pkt->addr = addr + umem->base_addr; + pkt->offset = offset; pkt->len = len; if (len > umem->frame_size - XDP_PACKET_HEADROOM - MIN_PKT_SIZE * 2 - umem->frame_headroom) pkt->valid = false; @@ -626,6 +555,11 @@ static void pkt_set(struct xsk_umem_info *umem, struct pkt *pkt, u64 addr, u32 l pkt->valid = true; } +static u32 pkt_get_buffer_len(struct xsk_umem_info *umem, u32 len) +{ + return ceil_u32(len, umem->frame_size) * umem->frame_size; +} + static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb_pkts, u32 pkt_len) { struct pkt_stream *pkt_stream; @@ -635,10 +569,13 @@ static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb if (!pkt_stream) exit_with_error(ENOMEM); + pkt_stream->nb_pkts = nb_pkts; + pkt_stream->max_pkt_len = pkt_len; for (i = 0; i < nb_pkts; i++) { - pkt_set(umem, &pkt_stream->pkts[i], (i % umem->num_frames) * umem->frame_size, - pkt_len); - pkt_stream->pkts[i].payload = i; + struct pkt *pkt = &pkt_stream->pkts[i]; + + pkt_set(umem, pkt, 0, pkt_len); + pkt->pkt_nb = i; } return pkt_stream; @@ -669,8 +606,7 @@ static void __pkt_stream_replace_half(struct ifobject *ifobj, u32 pkt_len, pkt_stream = pkt_stream_clone(umem, ifobj->pkt_stream); for (i = 1; i < ifobj->pkt_stream->nb_pkts; i += 2) - pkt_set(umem, &pkt_stream->pkts[i], - (i % umem->num_frames) * umem->frame_size + offset, pkt_len); + pkt_set(umem, &pkt_stream->pkts[i], offset, pkt_len); ifobj->pkt_stream = pkt_stream; } @@ -694,30 +630,31 @@ static void pkt_stream_receive_half(struct test_spec *test) pkt_stream->pkts[i].valid = false; } -static struct pkt *pkt_generate(struct ifobject *ifobject, u32 pkt_nb) +static u64 pkt_get_addr(struct pkt *pkt, struct xsk_umem_info *umem) { - struct pkt *pkt = pkt_stream_get_pkt(ifobject->pkt_stream, pkt_nb); - struct udphdr *udp_hdr; - struct ethhdr *eth_hdr; - struct iphdr *ip_hdr; - void *data; + if (!pkt->valid) + return pkt->offset; + return pkt->offset + umem_alloc_buffer(umem); +} - if (!pkt) - return NULL; - if (!pkt->valid || pkt->len < MIN_PKT_SIZE) - return pkt; +static void pkt_generate(struct ifobject *ifobject, u64 addr, u32 len, u32 pkt_nb, + u32 bytes_written) +{ + void *data = xsk_umem__get_data(ifobject->umem->buffer, addr); - data = xsk_umem__get_data(ifobject->umem->buffer, pkt->addr); - udp_hdr = (struct udphdr *)(data + sizeof(struct ethhdr) + sizeof(struct iphdr)); - ip_hdr = (struct iphdr *)(data + sizeof(struct ethhdr)); - eth_hdr = (struct ethhdr *)data; + if (len < MIN_PKT_SIZE) + return; - gen_udp_hdr(pkt_nb, data, ifobject, udp_hdr); - gen_ip_hdr(ifobject, ip_hdr); - gen_udp_csum(udp_hdr, ip_hdr); - gen_eth_hdr(ifobject, eth_hdr); + if (!bytes_written) { + gen_eth_hdr(ifobject, data); - return pkt; + len -= PKT_HDR_SIZE; + data += PKT_HDR_SIZE; + } else { + bytes_written -= PKT_HDR_SIZE; + } + + write_payload(data, pkt_nb, bytes_written, len); } static void __pkt_stream_generate_custom(struct ifobject *ifobj, @@ -731,10 +668,14 @@ static void __pkt_stream_generate_custom(struct ifobject *ifobj, exit_with_error(ENOMEM); for (i = 0; i < nb_pkts; i++) { - pkt_stream->pkts[i].addr = pkts[i].addr + ifobj->umem->base_addr; - pkt_stream->pkts[i].len = pkts[i].len; - pkt_stream->pkts[i].payload = i; - pkt_stream->pkts[i].valid = pkts[i].valid; + struct pkt *pkt = &pkt_stream->pkts[i]; + + pkt->offset = pkts[i].offset; + pkt->len = pkts[i].len; + pkt->pkt_nb = i; + pkt->valid = pkts[i].valid; + if (pkt->len > pkt_stream->max_pkt_len) + pkt_stream->max_pkt_len = pkt->len; } ifobj->pkt_stream = pkt_stream; @@ -746,53 +687,62 @@ static void pkt_stream_generate_custom(struct test_spec *test, struct pkt *pkts, __pkt_stream_generate_custom(test->ifobj_rx, pkts, nb_pkts); } -static void pkt_dump(void *pkt, u32 len) -{ - char s[INET_ADDRSTRLEN]; - struct ethhdr *ethhdr; - struct udphdr *udphdr; - struct iphdr *iphdr; - u32 payload, i; - - ethhdr = pkt; - iphdr = pkt + sizeof(*ethhdr); - udphdr = pkt + sizeof(*ethhdr) + sizeof(*iphdr); - - /*extract L2 frame */ - fprintf(stdout, "DEBUG>> L2: dst mac: "); - for (i = 0; i < ETH_ALEN; i++) - fprintf(stdout, "%02X", ethhdr->h_dest[i]); - - fprintf(stdout, "\nDEBUG>> L2: src mac: "); - for (i = 0; i < ETH_ALEN; i++) - fprintf(stdout, "%02X", ethhdr->h_source[i]); - - /*extract L3 frame */ - fprintf(stdout, "\nDEBUG>> L3: ip_hdr->ihl: %02X\n", iphdr->ihl); - fprintf(stdout, "DEBUG>> L3: ip_hdr->saddr: %s\n", - inet_ntop(AF_INET, &iphdr->saddr, s, sizeof(s))); - fprintf(stdout, "DEBUG>> L3: ip_hdr->daddr: %s\n", - inet_ntop(AF_INET, &iphdr->daddr, s, sizeof(s))); - /*extract L4 frame */ - fprintf(stdout, "DEBUG>> L4: udp_hdr->src: %d\n", ntohs(udphdr->source)); - fprintf(stdout, "DEBUG>> L4: udp_hdr->dst: %d\n", ntohs(udphdr->dest)); - /*extract L5 frame */ - payload = ntohl(*((u32 *)(pkt + PKT_HDR_SIZE))); +static void pkt_print_data(u32 *data, u32 cnt) +{ + u32 i; + + for (i = 0; i < cnt; i++) { + u32 seqnum, pkt_nb; - fprintf(stdout, "DEBUG>> L5: payload: %d\n", payload); - fprintf(stdout, "---------------------------------------\n"); + seqnum = ntohl(*data) & 0xffff; + pkt_nb = ntohl(*data) >> 16; + fprintf(stdout, "%u:%u ", pkt_nb, seqnum); + data++; + } } -static bool is_offset_correct(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream, u64 addr, - u64 pkt_stream_addr) +static void pkt_dump(void *pkt, u32 len, bool eth_header) +{ + struct ethhdr *ethhdr = pkt; + u32 i, *data; + + if (eth_header) { + /*extract L2 frame */ + fprintf(stdout, "DEBUG>> L2: dst mac: "); + for (i = 0; i < ETH_ALEN; i++) + fprintf(stdout, "%02X", ethhdr->h_dest[i]); + + fprintf(stdout, "\nDEBUG>> L2: src mac: "); + for (i = 0; i < ETH_ALEN; i++) + fprintf(stdout, "%02X", ethhdr->h_source[i]); + + data = pkt + PKT_HDR_SIZE; + } else { + data = pkt; + } + + /*extract L5 frame */ + fprintf(stdout, "\nDEBUG>> L5: seqnum: "); + pkt_print_data(data, PKT_DUMP_NB_TO_PRINT); + fprintf(stdout, "...."); + if (len > PKT_DUMP_NB_TO_PRINT * sizeof(u32)) { + fprintf(stdout, "\n.... "); + pkt_print_data(data + len / sizeof(u32) - PKT_DUMP_NB_TO_PRINT, + PKT_DUMP_NB_TO_PRINT); + } + fprintf(stdout, "\n---------------------------------------\n"); +} + +static bool is_offset_correct(struct xsk_umem_info *umem, struct pkt *pkt, u64 addr) { u32 headroom = umem->unaligned_mode ? 0 : umem->frame_headroom; - u32 offset = addr % umem->frame_size, expected_offset = 0; + u32 offset = addr % umem->frame_size, expected_offset; + int pkt_offset = pkt->valid ? pkt->offset : 0; - if (!pkt_stream->use_addr_for_fill) - pkt_stream_addr = 0; + if (!umem->unaligned_mode) + pkt_offset = 0; - expected_offset += (pkt_stream_addr + headroom + XDP_PACKET_HEADROOM) % umem->frame_size; + expected_offset = (pkt_offset + headroom + XDP_PACKET_HEADROOM) % umem->frame_size; if (offset == expected_offset) return true; @@ -806,9 +756,9 @@ static bool is_metadata_correct(struct pkt *pkt, void *buffer, u64 addr) void *data = xsk_umem__get_data(buffer, addr); struct xdp_info *meta = data - sizeof(struct xdp_info); - if (meta->count != pkt->payload) { + if (meta->count != pkt->pkt_nb) { ksft_print_msg("[%s] expected meta_count [%d], got meta_count [%d]\n", - __func__, pkt->payload, meta->count); + __func__, pkt->pkt_nb, meta->count); return false; } @@ -818,11 +768,11 @@ static bool is_metadata_correct(struct pkt *pkt, void *buffer, u64 addr) static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len) { void *data = xsk_umem__get_data(buffer, addr); - struct iphdr *iphdr = (struct iphdr *)(data + sizeof(struct ethhdr)); + u32 seqnum, pkt_data; if (!pkt) { ksft_print_msg("[%s] too many packets received\n", __func__); - return false; + goto error; } if (len < MIN_PKT_SIZE || pkt->len < MIN_PKT_SIZE) { @@ -833,28 +783,23 @@ static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len) if (pkt->len != len) { ksft_print_msg("[%s] expected length [%d], got length [%d]\n", __func__, pkt->len, len); - return false; + goto error; } - if (iphdr->version == IP_PKT_VER && iphdr->tos == IP_PKT_TOS) { - u32 seqnum = ntohl(*((u32 *)(data + PKT_HDR_SIZE))); - - if (opt_pkt_dump) - pkt_dump(data, PKT_SIZE); + pkt_data = ntohl(*((u32 *)(data + PKT_HDR_SIZE))); + seqnum = pkt_data >> 16; - if (pkt->payload != seqnum) { - ksft_print_msg("[%s] expected seqnum [%d], got seqnum [%d]\n", - __func__, pkt->payload, seqnum); - return false; - } - } else { - ksft_print_msg("Invalid frame received: "); - ksft_print_msg("[IP_PKT_VER: %02X], [IP_PKT_TOS: %02X]\n", iphdr->version, - iphdr->tos); - return false; + if (pkt->pkt_nb != seqnum) { + ksft_print_msg("[%s] expected seqnum [%d], got seqnum [%d]\n", + __func__, pkt->pkt_nb, seqnum); + goto error; } return true; + +error: + pkt_dump(data, len, true); + return false; } static void kick_tx(struct xsk_socket_info *xsk) @@ -976,7 +921,7 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds) addr = xsk_umem__add_offset_to_addr(addr); if (!is_pkt_valid(pkt, umem->buffer, addr, desc->len) || - !is_offset_correct(umem, pkt_stream, addr, pkt->addr) || + !is_offset_correct(umem, pkt, addr) || (ifobj->use_metadata && !is_metadata_correct(pkt, umem->buffer, addr))) return TEST_FAILURE; @@ -992,8 +937,6 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds) pthread_mutex_lock(&pacing_mutex); pkts_in_flight -= pkts_sent; - if (pkts_in_flight < umem->num_frames) - pthread_cond_signal(&pacing_cond); pthread_mutex_unlock(&pacing_mutex); pkts_sent = 0; } @@ -1001,14 +944,21 @@ static int receive_pkts(struct test_spec *test, struct pollfd *fds) return TEST_PASS; } -static int __send_pkts(struct ifobject *ifobject, u32 *pkt_nb, struct pollfd *fds, - bool timeout) +static int __send_pkts(struct ifobject *ifobject, struct pollfd *fds, bool timeout) { struct xsk_socket_info *xsk = ifobject->xsk; + struct xsk_umem_info *umem = ifobject->umem; + u32 i, idx = 0, valid_pkts = 0, buffer_len; bool use_poll = ifobject->use_poll; - u32 i, idx = 0, valid_pkts = 0; int ret; + buffer_len = pkt_get_buffer_len(umem, ifobject->pkt_stream->max_pkt_len); + /* pkts_in_flight might be negative if many invalid packets are sent */ + if (pkts_in_flight >= (int)((umem_size(umem) - BATCH_SIZE * buffer_len) / buffer_len)) { + kick_tx(xsk); + return TEST_CONTINUE; + } + while (xsk_ring_prod__reserve(&xsk->tx, BATCH_SIZE, &idx) < BATCH_SIZE) { if (use_poll) { ret = poll(fds, 1, POLL_TMOUT); @@ -1034,25 +984,21 @@ static int __send_pkts(struct ifobject *ifobject, u32 *pkt_nb, struct pollfd *fd for (i = 0; i < BATCH_SIZE; i++) { struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i); - struct pkt *pkt = pkt_generate(ifobject, *pkt_nb); + struct pkt *pkt = pkt_stream_get_next_tx_pkt(ifobject->pkt_stream); if (!pkt) break; - tx_desc->addr = pkt->addr; + tx_desc->addr = pkt_get_addr(pkt, umem); tx_desc->len = pkt->len; - (*pkt_nb)++; - if (pkt->valid) + if (pkt->valid) { valid_pkts++; + pkt_generate(ifobject, tx_desc->addr, tx_desc->len, pkt->pkt_nb, 0); + } } pthread_mutex_lock(&pacing_mutex); pkts_in_flight += valid_pkts; - /* pkts_in_flight might be negative if many invalid packets are sent */ - if (pkts_in_flight >= (int)(ifobject->umem->num_frames - BATCH_SIZE)) { - kick_tx(xsk); - pthread_cond_wait(&pacing_cond, &pacing_mutex); - } pthread_mutex_unlock(&pacing_mutex); xsk_ring_prod__submit(&xsk->tx, i); @@ -1088,18 +1034,21 @@ static void wait_for_tx_completion(struct xsk_socket_info *xsk) static int send_pkts(struct test_spec *test, struct ifobject *ifobject) { + struct pkt_stream *pkt_stream = ifobject->pkt_stream; bool timeout = !is_umem_valid(test->ifobj_rx); struct pollfd fds = { }; - u32 pkt_cnt = 0, ret; + u32 ret; fds.fd = xsk_socket__fd(ifobject->xsk->xsk); fds.events = POLLOUT; - while (pkt_cnt < ifobject->pkt_stream->nb_pkts) { - ret = __send_pkts(ifobject, &pkt_cnt, &fds, timeout); + while (pkt_stream->current_pkt_nb < pkt_stream->nb_pkts) { + ret = __send_pkts(ifobject, &fds, timeout); + if (ret == TEST_CONTINUE && !test->fail) + continue; if ((ret || test->fail) && !timeout) return TEST_FAILURE; - else if (ret == TEST_PASS && timeout) + if (ret == TEST_PASS && timeout) return ret; } @@ -1249,11 +1198,14 @@ static void thread_common_ops_tx(struct test_spec *test, struct ifobject *ifobje ifobject->xsk = &ifobject->xsk_arr[0]; ifobject->xskmap = test->ifobj_rx->xskmap; memcpy(ifobject->umem, test->ifobj_rx->umem, sizeof(struct xsk_umem_info)); + ifobject->umem->base_addr = 0; } -static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream) +static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream, + bool fill_up) { - u32 idx = 0, i, buffers_to_fill; + u32 rx_frame_size = umem->frame_size - XDP_PACKET_HEADROOM; + u32 idx = 0, filled = 0, buffers_to_fill, nb_pkts; int ret; if (umem->num_frames < XSK_RING_PROD__DEFAULT_NUM_DESCS) @@ -1264,22 +1216,33 @@ static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream ret = xsk_ring_prod__reserve(&umem->fq, buffers_to_fill, &idx); if (ret != buffers_to_fill) exit_with_error(ENOSPC); - for (i = 0; i < buffers_to_fill; i++) { - u64 addr; - if (pkt_stream->use_addr_for_fill) { - struct pkt *pkt = pkt_stream_get_pkt(pkt_stream, i); + while (filled < buffers_to_fill) { + struct pkt *pkt = pkt_stream_get_next_rx_pkt(pkt_stream, &nb_pkts); + u64 addr; + u32 i; + + for (i = 0; i < pkt_nb_frags(rx_frame_size, pkt); i++) { + if (!pkt) { + if (!fill_up) + break; + addr = filled * umem->frame_size + umem->base_addr; + } else if (pkt->offset >= 0) { + addr = pkt->offset % umem->frame_size + umem_alloc_buffer(umem); + } else { + addr = pkt->offset + umem_alloc_buffer(umem); + } - if (!pkt) + *xsk_ring_prod__fill_addr(&umem->fq, idx++) = addr; + if (++filled >= buffers_to_fill) break; - addr = pkt->addr; - } else { - addr = i * umem->frame_size; } - - *xsk_ring_prod__fill_addr(&umem->fq, idx++) = addr; } - xsk_ring_prod__submit(&umem->fq, i); + xsk_ring_prod__submit(&umem->fq, filled); + xsk_ring_prod__cancel(&umem->fq, buffers_to_fill - filled); + + pkt_stream_reset(pkt_stream); + umem_reset_alloc(umem); } static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) @@ -1300,12 +1263,10 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) if (bufs == MAP_FAILED) exit_with_error(errno); - ret = xsk_configure_umem(ifobject->umem, bufs, umem_sz); + ret = xsk_configure_umem(ifobject, ifobject->umem, bufs, umem_sz); if (ret) exit_with_error(-ret); - xsk_populate_fill_ring(ifobject->umem, ifobject->pkt_stream); - xsk_configure_socket(test, ifobject, ifobject->umem, false); ifobject->xsk = &ifobject->xsk_arr[0]; @@ -1313,6 +1274,8 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) if (!ifobject->rx_on) return; + xsk_populate_fill_ring(ifobject->umem, ifobject->pkt_stream, ifobject->use_fill_ring); + ret = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk->xsk); if (ret) exit_with_error(errno); @@ -1370,12 +1333,8 @@ static void *worker_testapp_validate_rx(void *arg) if (!err && ifobject->validation_func) err = ifobject->validation_func(ifobject); - if (err) { + if (err) report_failure(test); - pthread_mutex_lock(&pacing_mutex); - pthread_cond_signal(&pacing_cond); - pthread_mutex_unlock(&pacing_mutex); - } pthread_exit(NULL); } @@ -1402,11 +1361,20 @@ static void handler(int signum) pthread_exit(NULL); } -static bool xdp_prog_changed(struct test_spec *test, struct ifobject *ifobj) +static bool xdp_prog_changed_rx(struct test_spec *test) { + struct ifobject *ifobj = test->ifobj_rx; + return ifobj->xdp_prog != test->xdp_prog_rx || ifobj->mode != test->mode; } +static bool xdp_prog_changed_tx(struct test_spec *test) +{ + struct ifobject *ifobj = test->ifobj_tx; + + return ifobj->xdp_prog != test->xdp_prog_tx || ifobj->mode != test->mode; +} + static void xsk_reattach_xdp(struct ifobject *ifobj, struct bpf_program *xdp_prog, struct bpf_map *xskmap, enum test_mode mode) { @@ -1433,13 +1401,13 @@ static void xsk_reattach_xdp(struct ifobject *ifobj, struct bpf_program *xdp_pro static void xsk_attach_xdp_progs(struct test_spec *test, struct ifobject *ifobj_rx, struct ifobject *ifobj_tx) { - if (xdp_prog_changed(test, ifobj_rx)) + if (xdp_prog_changed_rx(test)) xsk_reattach_xdp(ifobj_rx, test->xdp_prog_rx, test->xskmap_rx, test->mode); if (!ifobj_tx || ifobj_tx->shared_umem) return; - if (xdp_prog_changed(test, ifobj_tx)) + if (xdp_prog_changed_tx(test)) xsk_reattach_xdp(ifobj_tx, test->xdp_prog_tx, test->xskmap_tx, test->mode); } @@ -1448,9 +1416,11 @@ static int __testapp_validate_traffic(struct test_spec *test, struct ifobject *i { pthread_t t0, t1; - if (ifobj2) + if (ifobj2) { if (pthread_barrier_init(&barr, NULL, 2)) exit_with_error(errno); + pkt_stream_reset(ifobj2->pkt_stream); + } test->current_step++; pkt_stream_reset(ifobj1->pkt_stream); @@ -1493,6 +1463,12 @@ static int testapp_validate_traffic(struct test_spec *test) struct ifobject *ifobj_rx = test->ifobj_rx; struct ifobject *ifobj_tx = test->ifobj_tx; + if ((ifobj_rx->umem->unaligned_mode && !ifobj_rx->unaligned_supp) || + (ifobj_tx->umem->unaligned_mode && !ifobj_tx->unaligned_supp)) { + ksft_test_result_skip("No huge pages present.\n"); + return TEST_SKIP; + } + xsk_attach_xdp_progs(test, ifobj_rx, ifobj_tx); return __testapp_validate_traffic(test, ifobj_rx, ifobj_tx); } @@ -1502,16 +1478,18 @@ static int testapp_validate_traffic_single_thread(struct test_spec *test, struct return __testapp_validate_traffic(test, ifobj, NULL); } -static void testapp_teardown(struct test_spec *test) +static int testapp_teardown(struct test_spec *test) { int i; test_spec_set_name(test, "TEARDOWN"); for (i = 0; i < MAX_TEARDOWN_ITER; i++) { if (testapp_validate_traffic(test)) - return; + return TEST_FAILURE; test_spec_reset(test); } + + return TEST_PASS; } static void swap_directions(struct ifobject **ifobj1, struct ifobject **ifobj2) @@ -1526,20 +1504,23 @@ static void swap_directions(struct ifobject **ifobj1, struct ifobject **ifobj2) *ifobj2 = tmp_ifobj; } -static void testapp_bidi(struct test_spec *test) +static int testapp_bidi(struct test_spec *test) { + int res; + test_spec_set_name(test, "BIDIRECTIONAL"); test->ifobj_tx->rx_on = true; test->ifobj_rx->tx_on = true; test->total_steps = 2; if (testapp_validate_traffic(test)) - return; + return TEST_FAILURE; print_verbose("Switching Tx/Rx vectors\n"); swap_directions(&test->ifobj_rx, &test->ifobj_tx); - __testapp_validate_traffic(test, test->ifobj_rx, test->ifobj_tx); + res = __testapp_validate_traffic(test, test->ifobj_rx, test->ifobj_tx); swap_directions(&test->ifobj_rx, &test->ifobj_tx); + return res; } static void swap_xsk_resources(struct ifobject *ifobj_tx, struct ifobject *ifobj_rx) @@ -1556,160 +1537,139 @@ static void swap_xsk_resources(struct ifobject *ifobj_tx, struct ifobject *ifobj exit_with_error(errno); } -static void testapp_bpf_res(struct test_spec *test) +static int testapp_bpf_res(struct test_spec *test) { test_spec_set_name(test, "BPF_RES"); test->total_steps = 2; test->nb_sockets = 2; if (testapp_validate_traffic(test)) - return; + return TEST_FAILURE; swap_xsk_resources(test->ifobj_tx, test->ifobj_rx); - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_headroom(struct test_spec *test) +static int testapp_headroom(struct test_spec *test) { test_spec_set_name(test, "UMEM_HEADROOM"); test->ifobj_rx->umem->frame_headroom = UMEM_HEADROOM_TEST_SIZE; - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_stats_rx_dropped(struct test_spec *test) +static int testapp_stats_rx_dropped(struct test_spec *test) { test_spec_set_name(test, "STAT_RX_DROPPED"); + if (test->mode == TEST_MODE_ZC) { + ksft_test_result_skip("Can not run RX_DROPPED test for ZC mode\n"); + return TEST_SKIP; + } + pkt_stream_replace_half(test, MIN_PKT_SIZE * 4, 0); test->ifobj_rx->umem->frame_headroom = test->ifobj_rx->umem->frame_size - XDP_PACKET_HEADROOM - MIN_PKT_SIZE * 3; pkt_stream_receive_half(test); test->ifobj_rx->validation_func = validate_rx_dropped; - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_stats_tx_invalid_descs(struct test_spec *test) +static int testapp_stats_tx_invalid_descs(struct test_spec *test) { test_spec_set_name(test, "STAT_TX_INVALID"); pkt_stream_replace_half(test, XSK_UMEM__INVALID_FRAME_SIZE, 0); test->ifobj_tx->validation_func = validate_tx_invalid_descs; - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_stats_rx_full(struct test_spec *test) +static int testapp_stats_rx_full(struct test_spec *test) { test_spec_set_name(test, "STAT_RX_FULL"); - pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, PKT_SIZE); + pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE); test->ifobj_rx->pkt_stream = pkt_stream_generate(test->ifobj_rx->umem, - DEFAULT_UMEM_BUFFERS, PKT_SIZE); - if (!test->ifobj_rx->pkt_stream) - exit_with_error(ENOMEM); + DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE); test->ifobj_rx->xsk->rxqsize = DEFAULT_UMEM_BUFFERS; test->ifobj_rx->release_rx = false; test->ifobj_rx->validation_func = validate_rx_full; - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_stats_fill_empty(struct test_spec *test) +static int testapp_stats_fill_empty(struct test_spec *test) { test_spec_set_name(test, "STAT_RX_FILL_EMPTY"); - pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, PKT_SIZE); + pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE); test->ifobj_rx->pkt_stream = pkt_stream_generate(test->ifobj_rx->umem, - DEFAULT_UMEM_BUFFERS, PKT_SIZE); - if (!test->ifobj_rx->pkt_stream) - exit_with_error(ENOMEM); + DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE); test->ifobj_rx->use_fill_ring = false; test->ifobj_rx->validation_func = validate_fill_empty; - testapp_validate_traffic(test); -} - -/* Simple test */ -static bool hugepages_present(struct ifobject *ifobject) -{ - size_t mmap_sz = 2 * ifobject->umem->num_frames * ifobject->umem->frame_size; - void *bufs; - - bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB | MAP_HUGE_2MB, -1, 0); - if (bufs == MAP_FAILED) - return false; - - mmap_sz = ceil_u64(mmap_sz, HUGEPAGE_SIZE) * HUGEPAGE_SIZE; - munmap(bufs, mmap_sz); - return true; + return testapp_validate_traffic(test); } -static bool testapp_unaligned(struct test_spec *test) +static int testapp_unaligned(struct test_spec *test) { - if (!hugepages_present(test->ifobj_tx)) { - ksft_test_result_skip("No 2M huge pages present.\n"); - return false; - } - test_spec_set_name(test, "UNALIGNED_MODE"); test->ifobj_tx->umem->unaligned_mode = true; test->ifobj_rx->umem->unaligned_mode = true; - /* Let half of the packets straddle a buffer boundrary */ - pkt_stream_replace_half(test, PKT_SIZE, -PKT_SIZE / 2); - test->ifobj_rx->pkt_stream->use_addr_for_fill = true; - testapp_validate_traffic(test); + /* Let half of the packets straddle a 4K buffer boundary */ + pkt_stream_replace_half(test, MIN_PKT_SIZE, -MIN_PKT_SIZE / 2); - return true; + return testapp_validate_traffic(test); } -static void testapp_single_pkt(struct test_spec *test) +static int testapp_single_pkt(struct test_spec *test) { - struct pkt pkts[] = {{0x1000, PKT_SIZE, 0, true}}; + struct pkt pkts[] = {{0, MIN_PKT_SIZE, 0, true}}; pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)); - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_invalid_desc(struct test_spec *test) +static int testapp_invalid_desc(struct test_spec *test) { - u64 umem_size = test->ifobj_tx->umem->num_frames * test->ifobj_tx->umem->frame_size; + struct xsk_umem_info *umem = test->ifobj_tx->umem; + u64 umem_size = umem->num_frames * umem->frame_size; struct pkt pkts[] = { /* Zero packet address allowed */ - {0, PKT_SIZE, 0, true}, + {0, MIN_PKT_SIZE, 0, true}, /* Allowed packet */ - {0x1000, PKT_SIZE, 0, true}, + {0, MIN_PKT_SIZE, 0, true}, /* Straddling the start of umem */ - {-2, PKT_SIZE, 0, false}, + {-2, MIN_PKT_SIZE, 0, false}, /* Packet too large */ - {0x2000, XSK_UMEM__INVALID_FRAME_SIZE, 0, false}, + {0, XSK_UMEM__INVALID_FRAME_SIZE, 0, false}, /* Up to end of umem allowed */ - {umem_size - PKT_SIZE, PKT_SIZE, 0, true}, + {umem_size - MIN_PKT_SIZE - 2 * umem->frame_size, MIN_PKT_SIZE, 0, true}, /* After umem ends */ - {umem_size, PKT_SIZE, 0, false}, + {umem_size, MIN_PKT_SIZE, 0, false}, /* Straddle the end of umem */ - {umem_size - PKT_SIZE / 2, PKT_SIZE, 0, false}, - /* Straddle a page boundrary */ - {0x3000 - PKT_SIZE / 2, PKT_SIZE, 0, false}, - /* Straddle a 2K boundrary */ - {0x3800 - PKT_SIZE / 2, PKT_SIZE, 0, true}, + {umem_size - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false}, + /* Straddle a 4K boundary */ + {0x1000 - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false}, + /* Straddle a 2K boundary */ + {0x800 - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, true}, /* Valid packet for synch so that something is received */ - {0x4000, PKT_SIZE, 0, true}}; + {0, MIN_PKT_SIZE, 0, true}}; - if (test->ifobj_tx->umem->unaligned_mode) { - /* Crossing a page boundrary allowed */ + if (umem->unaligned_mode) { + /* Crossing a page boundary allowed */ pkts[7].valid = true; } - if (test->ifobj_tx->umem->frame_size == XSK_UMEM__DEFAULT_FRAME_SIZE / 2) { - /* Crossing a 2K frame size boundrary not allowed */ + if (umem->frame_size == XSK_UMEM__DEFAULT_FRAME_SIZE / 2) { + /* Crossing a 2K frame size boundary not allowed */ pkts[8].valid = false; } if (test->ifobj_tx->shared_umem) { - pkts[4].addr += umem_size; - pkts[5].addr += umem_size; - pkts[6].addr += umem_size; + pkts[4].offset += umem_size; + pkts[5].offset += umem_size; + pkts[6].offset += umem_size; } pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)); - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_xdp_drop(struct test_spec *test) +static int testapp_xdp_drop(struct test_spec *test) { struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs; struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs; @@ -1719,10 +1679,10 @@ static void testapp_xdp_drop(struct test_spec *test) skel_rx->maps.xsk, skel_tx->maps.xsk); pkt_stream_receive_half(test); - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_xdp_metadata_count(struct test_spec *test) +static int testapp_xdp_metadata_count(struct test_spec *test) { struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs; struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs; @@ -1743,10 +1703,10 @@ static void testapp_xdp_metadata_count(struct test_spec *test) if (bpf_map_update_elem(bpf_map__fd(data_map), &key, &count, BPF_ANY)) exit_with_error(errno); - testapp_validate_traffic(test); + return testapp_validate_traffic(test); } -static void testapp_poll_txq_tmout(struct test_spec *test) +static int testapp_poll_txq_tmout(struct test_spec *test) { test_spec_set_name(test, "POLL_TXQ_FULL"); @@ -1754,14 +1714,14 @@ static void testapp_poll_txq_tmout(struct test_spec *test) /* create invalid frame by set umem frame_size and pkt length equal to 2048 */ test->ifobj_tx->umem->frame_size = 2048; pkt_stream_replace(test, 2 * DEFAULT_PKT_CNT, 2048); - testapp_validate_traffic_single_thread(test, test->ifobj_tx); + return testapp_validate_traffic_single_thread(test, test->ifobj_tx); } -static void testapp_poll_rxq_tmout(struct test_spec *test) +static int testapp_poll_rxq_tmout(struct test_spec *test) { test_spec_set_name(test, "POLL_RXQ_EMPTY"); test->ifobj_rx->use_poll = true; - testapp_validate_traffic_single_thread(test, test->ifobj_rx); + return testapp_validate_traffic_single_thread(test, test->ifobj_rx); } static int xsk_load_xdp_programs(struct ifobject *ifobj) @@ -1778,25 +1738,30 @@ static void xsk_unload_xdp_programs(struct ifobject *ifobj) xsk_xdp_progs__destroy(ifobj->xdp_progs); } +/* Simple test */ +static bool hugepages_present(void) +{ + size_t mmap_sz = 2 * DEFAULT_UMEM_BUFFERS * XSK_UMEM__DEFAULT_FRAME_SIZE; + void *bufs; + + bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, MAP_HUGE_2MB); + if (bufs == MAP_FAILED) + return false; + + mmap_sz = ceil_u64(mmap_sz, HUGEPAGE_SIZE) * HUGEPAGE_SIZE; + munmap(bufs, mmap_sz); + return true; +} + static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *src_mac, - const char *dst_ip, const char *src_ip, const u16 dst_port, - const u16 src_port, thread_func_t func_ptr) + thread_func_t func_ptr) { - struct in_addr ip; int err; memcpy(ifobj->dst_mac, dst_mac, ETH_ALEN); memcpy(ifobj->src_mac, src_mac, ETH_ALEN); - inet_aton(dst_ip, &ip); - ifobj->dst_ip = ip.s_addr; - - inet_aton(src_ip, &ip); - ifobj->src_ip = ip.s_addr; - - ifobj->dst_port = dst_port; - ifobj->src_port = src_port; - ifobj->func_ptr = func_ptr; err = xsk_load_xdp_programs(ifobj); @@ -1804,94 +1769,87 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char * printf("Error loading XDP program\n"); exit_with_error(err); } + + if (hugepages_present()) + ifobj->unaligned_supp = true; } static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_type type) { + int ret = TEST_SKIP; + switch (type) { case TEST_TYPE_STATS_RX_DROPPED: - if (mode == TEST_MODE_ZC) { - ksft_test_result_skip("Can not run RX_DROPPED test for ZC mode\n"); - return; - } - testapp_stats_rx_dropped(test); + ret = testapp_stats_rx_dropped(test); break; case TEST_TYPE_STATS_TX_INVALID_DESCS: - testapp_stats_tx_invalid_descs(test); + ret = testapp_stats_tx_invalid_descs(test); break; case TEST_TYPE_STATS_RX_FULL: - testapp_stats_rx_full(test); + ret = testapp_stats_rx_full(test); break; case TEST_TYPE_STATS_FILL_EMPTY: - testapp_stats_fill_empty(test); + ret = testapp_stats_fill_empty(test); break; case TEST_TYPE_TEARDOWN: - testapp_teardown(test); + ret = testapp_teardown(test); break; case TEST_TYPE_BIDI: - testapp_bidi(test); + ret = testapp_bidi(test); break; case TEST_TYPE_BPF_RES: - testapp_bpf_res(test); + ret = testapp_bpf_res(test); break; case TEST_TYPE_RUN_TO_COMPLETION: test_spec_set_name(test, "RUN_TO_COMPLETION"); - testapp_validate_traffic(test); + ret = testapp_validate_traffic(test); break; case TEST_TYPE_RUN_TO_COMPLETION_SINGLE_PKT: test_spec_set_name(test, "RUN_TO_COMPLETION_SINGLE_PKT"); - testapp_single_pkt(test); + ret = testapp_single_pkt(test); break; case TEST_TYPE_RUN_TO_COMPLETION_2K_FRAME: test_spec_set_name(test, "RUN_TO_COMPLETION_2K_FRAME_SIZE"); test->ifobj_tx->umem->frame_size = 2048; test->ifobj_rx->umem->frame_size = 2048; - pkt_stream_replace(test, DEFAULT_PKT_CNT, PKT_SIZE); - testapp_validate_traffic(test); + pkt_stream_replace(test, DEFAULT_PKT_CNT, MIN_PKT_SIZE); + ret = testapp_validate_traffic(test); break; case TEST_TYPE_RX_POLL: test->ifobj_rx->use_poll = true; test_spec_set_name(test, "POLL_RX"); - testapp_validate_traffic(test); + ret = testapp_validate_traffic(test); break; case TEST_TYPE_TX_POLL: test->ifobj_tx->use_poll = true; test_spec_set_name(test, "POLL_TX"); - testapp_validate_traffic(test); + ret = testapp_validate_traffic(test); break; case TEST_TYPE_POLL_TXQ_TMOUT: - testapp_poll_txq_tmout(test); + ret = testapp_poll_txq_tmout(test); break; case TEST_TYPE_POLL_RXQ_TMOUT: - testapp_poll_rxq_tmout(test); + ret = testapp_poll_rxq_tmout(test); break; case TEST_TYPE_ALIGNED_INV_DESC: test_spec_set_name(test, "ALIGNED_INV_DESC"); - testapp_invalid_desc(test); + ret = testapp_invalid_desc(test); break; case TEST_TYPE_ALIGNED_INV_DESC_2K_FRAME: test_spec_set_name(test, "ALIGNED_INV_DESC_2K_FRAME_SIZE"); test->ifobj_tx->umem->frame_size = 2048; test->ifobj_rx->umem->frame_size = 2048; - testapp_invalid_desc(test); + ret = testapp_invalid_desc(test); break; case TEST_TYPE_UNALIGNED_INV_DESC: - if (!hugepages_present(test->ifobj_tx)) { - ksft_test_result_skip("No 2M huge pages present.\n"); - return; - } test_spec_set_name(test, "UNALIGNED_INV_DESC"); test->ifobj_tx->umem->unaligned_mode = true; test->ifobj_rx->umem->unaligned_mode = true; - testapp_invalid_desc(test); + ret = testapp_invalid_desc(test); break; case TEST_TYPE_UNALIGNED_INV_DESC_4K1_FRAME: { u64 page_size, umem_size; - if (!hugepages_present(test->ifobj_tx)) { - ksft_test_result_skip("No 2M huge pages present.\n"); - return; - } test_spec_set_name(test, "UNALIGNED_INV_DESC_4K1_FRAME_SIZE"); /* Odd frame size so the UMEM doesn't end near a page boundary. */ test->ifobj_tx->umem->frame_size = 4001; @@ -1903,29 +1861,28 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_ */ page_size = sysconf(_SC_PAGESIZE); umem_size = test->ifobj_tx->umem->num_frames * test->ifobj_tx->umem->frame_size; - assert(umem_size % page_size > PKT_SIZE); - assert(umem_size % page_size < page_size - PKT_SIZE); - testapp_invalid_desc(test); + assert(umem_size % page_size > MIN_PKT_SIZE); + assert(umem_size % page_size < page_size - MIN_PKT_SIZE); + ret = testapp_invalid_desc(test); break; } case TEST_TYPE_UNALIGNED: - if (!testapp_unaligned(test)) - return; + ret = testapp_unaligned(test); break; case TEST_TYPE_HEADROOM: - testapp_headroom(test); + ret = testapp_headroom(test); break; case TEST_TYPE_XDP_DROP_HALF: - testapp_xdp_drop(test); + ret = testapp_xdp_drop(test); break; case TEST_TYPE_XDP_METADATA_COUNT: - testapp_xdp_metadata_count(test); + ret = testapp_xdp_metadata_count(test); break; default: break; } - if (!test->fail) + if (ret == TEST_PASS) ksft_test_result_pass("PASS: %s %s%s\n", mode_string(test), busy_poll_string(test), test->name); pkt_stream_restore_default(test); @@ -2030,14 +1987,12 @@ int main(int argc, char **argv) modes++; } - init_iface(ifobj_rx, MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2, - worker_testapp_validate_rx); - init_iface(ifobj_tx, MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1, - worker_testapp_validate_tx); + init_iface(ifobj_rx, MAC1, MAC2, worker_testapp_validate_rx); + init_iface(ifobj_tx, MAC2, MAC1, worker_testapp_validate_tx); test_spec_init(&test, ifobj_tx, ifobj_rx, 0); - tx_pkt_stream_default = pkt_stream_generate(ifobj_tx->umem, DEFAULT_PKT_CNT, PKT_SIZE); - rx_pkt_stream_default = pkt_stream_generate(ifobj_rx->umem, DEFAULT_PKT_CNT, PKT_SIZE); + tx_pkt_stream_default = pkt_stream_generate(ifobj_tx->umem, DEFAULT_PKT_CNT, MIN_PKT_SIZE); + rx_pkt_stream_default = pkt_stream_generate(ifobj_rx->umem, DEFAULT_PKT_CNT, MIN_PKT_SIZE); if (!tx_pkt_stream_default || !rx_pkt_stream_default) exit_with_error(ENOMEM); test.tx_pkt_stream_default = tx_pkt_stream_default; diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h index c535aeab2ca3..aaf27e067640 100644 --- a/tools/testing/selftests/bpf/xskxceiver.h +++ b/tools/testing/selftests/bpf/xskxceiver.h @@ -30,22 +30,14 @@ #define TEST_PASS 0 #define TEST_FAILURE -1 #define TEST_CONTINUE 1 +#define TEST_SKIP 2 #define MAX_INTERFACES 2 #define MAX_INTERFACE_NAME_CHARS 16 #define MAX_SOCKETS 2 #define MAX_TEST_NAME_SIZE 32 #define MAX_TEARDOWN_ITER 10 -#define PKT_HDR_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) + \ - sizeof(struct udphdr)) -#define MIN_ETH_PKT_SIZE 64 -#define ETH_FCS_SIZE 4 -#define MIN_PKT_SIZE (MIN_ETH_PKT_SIZE - ETH_FCS_SIZE) -#define PKT_SIZE (MIN_PKT_SIZE) -#define IP_PKT_SIZE (PKT_SIZE - sizeof(struct ethhdr)) -#define IP_PKT_VER 0x4 -#define IP_PKT_TOS 0x9 -#define UDP_PKT_SIZE (IP_PKT_SIZE - sizeof(struct iphdr)) -#define UDP_PKT_DATA_SIZE (UDP_PKT_SIZE - sizeof(struct udphdr)) +#define PKT_HDR_SIZE (sizeof(struct ethhdr) + 2) /* Just to align the data in the packet */ +#define MIN_PKT_SIZE 64 #define USLEEP_MAX 10000 #define SOCK_RECONF_CTR 10 #define BATCH_SIZE 64 @@ -57,6 +49,7 @@ #define UMEM_HEADROOM_TEST_SIZE 128 #define XSK_UMEM__INVALID_FRAME_SIZE (XSK_UMEM__DEFAULT_FRAME_SIZE + 1) #define HUGEPAGE_SIZE (2 * 1024 * 1024) +#define PKT_DUMP_NB_TO_PRINT 16 #define print_verbose(x...) do { if (opt_verbose) ksft_print_msg(x); } while (0) @@ -93,13 +86,13 @@ enum test_type { TEST_TYPE_MAX }; -static bool opt_pkt_dump; static bool opt_verbose; struct xsk_umem_info { struct xsk_ring_prod fq; struct xsk_ring_cons cq; struct xsk_umem *umem; + u64 next_buffer; u32 num_frames; u32 frame_headroom; void *buffer; @@ -118,17 +111,17 @@ struct xsk_socket_info { }; struct pkt { - u64 addr; + int offset; u32 len; - u32 payload; + u32 pkt_nb; bool valid; }; struct pkt_stream { u32 nb_pkts; - u32 rx_pkt_nb; + u32 current_pkt_nb; struct pkt *pkts; - bool use_addr_for_fill; + u32 max_pkt_len; }; struct ifobject; @@ -148,11 +141,7 @@ struct ifobject { struct bpf_program *xdp_prog; enum test_mode mode; int ifindex; - u32 dst_ip; - u32 src_ip; u32 bind_flags; - u16 src_port; - u16 dst_port; bool tx_on; bool rx_on; bool use_poll; @@ -161,6 +150,7 @@ struct ifobject { bool release_rx; bool shared_umem; bool use_metadata; + bool unaligned_supp; u8 dst_mac[ETH_ALEN]; u8 src_mac[ETH_ALEN]; }; @@ -184,7 +174,6 @@ struct test_spec { pthread_barrier_t barr; pthread_mutex_t pacing_mutex = PTHREAD_MUTEX_INITIALIZER; -pthread_cond_t pacing_cond = PTHREAD_COND_INITIALIZER; int pkts_in_flight; diff --git a/tools/testing/selftests/drivers/net/mlxsw/egress_vid_classification.sh b/tools/testing/selftests/drivers/net/mlxsw/egress_vid_classification.sh index 0cf9e47e3209..a5c2aec52898 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/egress_vid_classification.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/egress_vid_classification.sh @@ -16,10 +16,9 @@ # +----------------|--+ +--|-----------------+ # | | # +----------------|-------------------------|-----------------+ -# | SW | | | +# | SW $swp1 + + $swp2 | +# | | | | # | +--------------|-------------------------|---------------+ | -# | | $swp1 + + $swp2 | | -# | | | | | | # | | $swp1.10 + + $swp2.10 | | # | | | | # | | br0 | | diff --git a/tools/testing/selftests/drivers/net/mlxsw/ingress_rif_conf_1d.sh b/tools/testing/selftests/drivers/net/mlxsw/ingress_rif_conf_1d.sh index df2b09966886..7d7f862c809c 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/ingress_rif_conf_1d.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/ingress_rif_conf_1d.sh @@ -15,10 +15,9 @@ # +----------------|--+ +--|-----------------+ # | | # +----------------|-------------------------|-----------------+ -# | SW | | | +# | SW $swp1 + + $swp2 | +# | | | | # | +--------------|-------------------------|---------------+ | -# | | $swp1 + + $swp2 | | -# | | | | | | # | | $swp1.10 + + $swp2.10 | | # | | | | # | | br0 | | diff --git a/tools/testing/selftests/ftrace/Makefile b/tools/testing/selftests/ftrace/Makefile index d6e106fbce11..a1e955d2de4c 100644 --- a/tools/testing/selftests/ftrace/Makefile +++ b/tools/testing/selftests/ftrace/Makefile @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 all: -TEST_PROGS := ftracetest +TEST_PROGS_EXTENDED := ftracetest +TEST_PROGS := ftracetest-ktap TEST_FILES := test.d settings EXTRA_CLEAN := $(OUTPUT)/logs/* diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest index c3311c8c4089..2506621e75df 100755 --- a/tools/testing/selftests/ftrace/ftracetest +++ b/tools/testing/selftests/ftrace/ftracetest @@ -13,6 +13,7 @@ echo "Usage: ftracetest [options] [testcase(s)] [testcase-directory(s)]" echo " Options:" echo " -h|--help Show help message" echo " -k|--keep Keep passed test logs" +echo " -K|--ktap Output in KTAP format" echo " -v|--verbose Increase verbosity of test messages" echo " -vv Alias of -v -v (Show all results in stdout)" echo " -vvv Alias of -v -v -v (Show all commands immediately)" @@ -85,6 +86,10 @@ parse_opts() { # opts KEEP_LOG=1 shift 1 ;; + --ktap|-K) + KTAP=1 + shift 1 + ;; --verbose|-v|-vv|-vvv) if [ $VERBOSE -eq -1 ]; then usage "--console can not use with --verbose" @@ -178,6 +183,7 @@ TEST_DIR=$TOP_DIR/test.d TEST_CASES=`find_testcases $TEST_DIR` LOG_DIR=$TOP_DIR/logs/`date +%Y%m%d-%H%M%S`/ KEEP_LOG=0 +KTAP=0 DEBUG=0 VERBOSE=0 UNSUPPORTED_RESULT=0 @@ -229,7 +235,7 @@ prlog() { # messages newline= shift fi - printf "$*$newline" + [ "$KTAP" != "1" ] && printf "$*$newline" [ "$LOG_FILE" ] && printf "$*$newline" | strip_esc >> $LOG_FILE } catlog() { #file @@ -260,11 +266,11 @@ TOTAL_RESULT=0 INSTANCE= CASENO=0 +CASENAME= testcase() { # testfile CASENO=$((CASENO+1)) - desc=`grep "^#[ \t]*description:" $1 | cut -f2- -d:` - prlog -n "[$CASENO]$INSTANCE$desc" + CASENAME=`grep "^#[ \t]*description:" $1 | cut -f2- -d:` } checkreq() { # testfile @@ -277,40 +283,68 @@ test_on_instance() { # testfile grep -q "^#[ \t]*flags:.*instance" $1 } +ktaptest() { # result comment + if [ "$KTAP" != "1" ]; then + return + fi + + local result= + if [ "$1" = "1" ]; then + result="ok" + else + result="not ok" + fi + shift + + local comment=$* + if [ "$comment" != "" ]; then + comment="# $comment" + fi + + echo $CASENO $result $INSTANCE$CASENAME $comment +} + eval_result() { # sigval case $1 in $PASS) prlog " [${color_green}PASS${color_reset}]" + ktaptest 1 PASSED_CASES="$PASSED_CASES $CASENO" return 0 ;; $FAIL) prlog " [${color_red}FAIL${color_reset}]" + ktaptest 0 FAILED_CASES="$FAILED_CASES $CASENO" return 1 # this is a bug. ;; $UNRESOLVED) prlog " [${color_blue}UNRESOLVED${color_reset}]" + ktaptest 0 UNRESOLVED UNRESOLVED_CASES="$UNRESOLVED_CASES $CASENO" return $UNRESOLVED_RESULT # depends on use case ;; $UNTESTED) prlog " [${color_blue}UNTESTED${color_reset}]" + ktaptest 1 SKIP UNTESTED_CASES="$UNTESTED_CASES $CASENO" return 0 ;; $UNSUPPORTED) prlog " [${color_blue}UNSUPPORTED${color_reset}]" + ktaptest 1 SKIP UNSUPPORTED_CASES="$UNSUPPORTED_CASES $CASENO" return $UNSUPPORTED_RESULT # depends on use case ;; $XFAIL) prlog " [${color_green}XFAIL${color_reset}]" + ktaptest 1 XFAIL XFAILED_CASES="$XFAILED_CASES $CASENO" return 0 ;; *) prlog " [${color_blue}UNDEFINED${color_reset}]" + ktaptest 0 error UNDEFINED_CASES="$UNDEFINED_CASES $CASENO" return 1 # this must be a test bug ;; @@ -371,6 +405,7 @@ __run_test() { # testfile run_test() { # testfile local testname=`basename $1` testcase $1 + prlog -n "[$CASENO]$INSTANCE$CASENAME" if [ ! -z "$LOG_FILE" ] ; then local testlog=`mktemp $LOG_DIR/${CASENO}-${testname}-log.XXXXXX` else @@ -405,6 +440,17 @@ run_test() { # testfile # load in the helper functions . $TEST_DIR/functions +if [ "$KTAP" = "1" ]; then + echo "TAP version 13" + + casecount=`echo $TEST_CASES | wc -w` + for t in $TEST_CASES; do + test_on_instance $t || continue + casecount=$((casecount+1)) + done + echo "1..${casecount}" +fi + # Main loop for t in $TEST_CASES; do run_test $t @@ -439,6 +485,17 @@ prlog "# of unsupported: " `echo $UNSUPPORTED_CASES | wc -w` prlog "# of xfailed: " `echo $XFAILED_CASES | wc -w` prlog "# of undefined(test bug): " `echo $UNDEFINED_CASES | wc -w` +if [ "$KTAP" = "1" ]; then + echo -n "# Totals:" + echo -n " pass:"`echo $PASSED_CASES | wc -w` + echo -n " faii:"`echo $FAILED_CASES | wc -w` + echo -n " xfail:"`echo $XFAILED_CASES | wc -w` + echo -n " xpass:0" + echo -n " skip:"`echo $UNTESTED_CASES $UNSUPPORTED_CASES | wc -w` + echo -n " error:"`echo $UNRESOLVED_CASES $UNDEFINED_CASES | wc -w` + echo +fi + cleanup # if no error, return 0 diff --git a/tools/testing/selftests/ftrace/ftracetest-ktap b/tools/testing/selftests/ftrace/ftracetest-ktap new file mode 100755 index 000000000000..b3284679ef3a --- /dev/null +++ b/tools/testing/selftests/ftrace/ftracetest-ktap @@ -0,0 +1,8 @@ +#!/bin/sh -e +# SPDX-License-Identifier: GPL-2.0-only +# +# ftracetest-ktap: Wrapper to integrate ftracetest with the kselftest runner +# +# Copyright (C) Arm Ltd., 2023 + +./ftracetest -K diff --git a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc index e2ff3bf4df80..2de7c61d1ae3 100644 --- a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc +++ b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc @@ -9,18 +9,33 @@ fail() { #msg exit_fail } -echo "Test event filter function name" +sample_events() { + echo > trace + echo 1 > events/kmem/kmem_cache_free/enable + echo 1 > tracing_on + ls > /dev/null + echo 0 > tracing_on + echo 0 > events/kmem/kmem_cache_free/enable +} + echo 0 > tracing_on echo 0 > events/enable + +echo "Get the most frequently calling function" +sample_events + +target_func=`cut -d: -f3 trace | sed 's/call_site=\([^+]*\)+0x.*/\1/' | sort | uniq -c | sort | tail -n 1 | sed 's/^[ 0-9]*//'` +if [ -z "$target_func" ]; then + exit_fail +fi echo > trace -echo 'call_site.function == exit_mmap' > events/kmem/kmem_cache_free/filter -echo 1 > events/kmem/kmem_cache_free/enable -echo 1 > tracing_on -ls > /dev/null -echo 0 > events/kmem/kmem_cache_free/enable -hitcnt=`grep kmem_cache_free trace| grep exit_mmap | wc -l` -misscnt=`grep kmem_cache_free trace| grep -v exit_mmap | wc -l` +echo "Test event filter function name" +echo "call_site.function == $target_func" > events/kmem/kmem_cache_free/filter +sample_events + +hitcnt=`grep kmem_cache_free trace| grep $target_func | wc -l` +misscnt=`grep kmem_cache_free trace| grep -v $target_func | wc -l` if [ $hitcnt -eq 0 ]; then exit_fail @@ -30,20 +45,14 @@ if [ $misscnt -gt 0 ]; then exit_fail fi -address=`grep ' exit_mmap$' /proc/kallsyms | cut -d' ' -f1` +address=`grep " ${target_func}\$" /proc/kallsyms | cut -d' ' -f1` echo "Test event filter function address" -echo 0 > tracing_on -echo 0 > events/enable -echo > trace echo "call_site.function == 0x$address" > events/kmem/kmem_cache_free/filter -echo 1 > events/kmem/kmem_cache_free/enable -echo 1 > tracing_on -sleep 1 -echo 0 > events/kmem/kmem_cache_free/enable +sample_events -hitcnt=`grep kmem_cache_free trace| grep exit_mmap | wc -l` -misscnt=`grep kmem_cache_free trace| grep -v exit_mmap | wc -l` +hitcnt=`grep kmem_cache_free trace| grep $target_func | wc -l` +misscnt=`grep kmem_cache_free trace| grep -v $target_func | wc -l` if [ $hitcnt -eq 0 ]; then exit_fail diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack-legacy.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack-legacy.tc new file mode 100644 index 000000000000..d0cd91a93069 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack-legacy.tc @@ -0,0 +1,24 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: event trigger - test inter-event histogram trigger trace action with dynamic string param (legacy stack) +# requires: set_event synthetic_events events/sched/sched_process_exec/hist "long[] stack' >> synthetic_events":README + +fail() { #msg + echo $1 + exit_fail +} + +echo "Test create synthetic event with stack" + +# Test the old stacktrace keyword (for backward compatibility) +echo 's:wake_lat pid_t pid; u64 delta; unsigned long[] stack;' > dynamic_events +echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=stacktrace if prev_state == 1||prev_state == 2' >> events/sched/sched_switch/trigger +echo 'hist:keys=prev_pid:delta=common_timestamp.usecs-$ts,s=$st:onmax($delta).trace(wake_lat,prev_pid,$delta,$s)' >> events/sched/sched_switch/trigger +echo 1 > events/synthetic/wake_lat/enable +sleep 1 + +if ! grep -q "=>.*sched" trace; then + fail "Failed to create synthetic event with stack" +fi + +exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc index 755dbe94ccf4..8f1cc9a86a06 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-stack.tc @@ -1,7 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # description: event trigger - test inter-event histogram trigger trace action with dynamic string param -# requires: set_event synthetic_events events/sched/sched_process_exec/hist "long[]' >> synthetic_events":README +# requires: set_event synthetic_events events/sched/sched_process_exec/hist "can be any field, or the special string 'common_stacktrace'":README fail() { #msg echo $1 @@ -10,9 +10,8 @@ fail() { #msg echo "Test create synthetic event with stack" - echo 's:wake_lat pid_t pid; u64 delta; unsigned long[] stack;' > dynamic_events -echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=stacktrace if prev_state == 1||prev_state == 2' >> events/sched/sched_switch/trigger +echo 'hist:keys=next_pid:ts=common_timestamp.usecs,st=common_stacktrace if prev_state == 1||prev_state == 2' >> events/sched/sched_switch/trigger echo 'hist:keys=prev_pid:delta=common_timestamp.usecs-$ts,s=$st:onmax($delta).trace(wake_lat,prev_pid,$delta,$s)' >> events/sched/sched_switch/trigger echo 1 > events/synthetic/wake_lat/enable sleep 1 diff --git a/tools/testing/selftests/gpio/gpio-sim.sh b/tools/testing/selftests/gpio/gpio-sim.sh index 9f539d454ee4..fa2ce2b9dd5f 100755 --- a/tools/testing/selftests/gpio/gpio-sim.sh +++ b/tools/testing/selftests/gpio/gpio-sim.sh @@ -389,6 +389,9 @@ create_chip chip create_bank chip bank set_num_lines chip bank 8 enable_chip chip +DEVNAME=`configfs_dev_name chip` +CHIPNAME=`configfs_chip_name chip bank` +SYSFS_PATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/value" $BASE_DIR/gpio-mockup-cdev -b pull-up /dev/`configfs_chip_name chip bank` 0 test `cat $SYSFS_PATH` = "1" || fail "bias setting does not work" remove_chip chip diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 7a5ff646e7e7..4761b768b773 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -116,6 +116,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/sev_migrate_tests TEST_GEN_PROGS_x86_64 += x86_64/amx_test TEST_GEN_PROGS_x86_64 += x86_64/max_vcpuid_cap_test TEST_GEN_PROGS_x86_64 += x86_64/triple_fault_event_test +TEST_GEN_PROGS_x86_64 += x86_64/recalc_apic_map_test TEST_GEN_PROGS_x86_64 += access_tracking_perf_test TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test diff --git a/tools/testing/selftests/kvm/x86_64/recalc_apic_map_test.c b/tools/testing/selftests/kvm/x86_64/recalc_apic_map_test.c new file mode 100644 index 000000000000..4c416ebe7d66 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/recalc_apic_map_test.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Test edge cases and race conditions in kvm_recalculate_apic_map(). + */ + +#include <sys/ioctl.h> +#include <pthread.h> +#include <time.h> + +#include "processor.h" +#include "test_util.h" +#include "kvm_util.h" +#include "apic.h" + +#define TIMEOUT 5 /* seconds */ + +#define LAPIC_DISABLED 0 +#define LAPIC_X2APIC (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE) +#define MAX_XAPIC_ID 0xff + +static void *race(void *arg) +{ + struct kvm_lapic_state lapic = {}; + struct kvm_vcpu *vcpu = arg; + + while (1) { + /* Trigger kvm_recalculate_apic_map(). */ + vcpu_ioctl(vcpu, KVM_SET_LAPIC, &lapic); + pthread_testcancel(); + } + + return NULL; +} + +int main(void) +{ + struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; + struct kvm_vcpu *vcpuN; + struct kvm_vm *vm; + pthread_t thread; + time_t t; + int i; + + kvm_static_assert(KVM_MAX_VCPUS > MAX_XAPIC_ID); + + /* + * Create the max number of vCPUs supported by selftests so that KVM + * has decent amount of work to do when recalculating the map, i.e. to + * make the problematic window large enough to hit. + */ + vm = vm_create_with_vcpus(KVM_MAX_VCPUS, NULL, vcpus); + + /* + * Enable x2APIC on all vCPUs so that KVM doesn't bail from the recalc + * due to vCPUs having aliased xAPIC IDs (truncated to 8 bits). + */ + for (i = 0; i < KVM_MAX_VCPUS; i++) + vcpu_set_msr(vcpus[i], MSR_IA32_APICBASE, LAPIC_X2APIC); + + ASSERT_EQ(pthread_create(&thread, NULL, race, vcpus[0]), 0); + + vcpuN = vcpus[KVM_MAX_VCPUS - 1]; + for (t = time(NULL) + TIMEOUT; time(NULL) < t;) { + vcpu_set_msr(vcpuN, MSR_IA32_APICBASE, LAPIC_X2APIC); + vcpu_set_msr(vcpuN, MSR_IA32_APICBASE, LAPIC_DISABLED); + } + + ASSERT_EQ(pthread_cancel(thread), 0); + ASSERT_EQ(pthread_join(thread, NULL), 0); + + kvm_vm_free(vm); + + return 0; +} diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 80f06aa62034..f27a7338b60e 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -8,8 +8,10 @@ diag_uid fin_ack_lat gro hwtstamp_config +io_uring_zerocopy_tx ioam6_parser ip_defrag +ip_local_port_range ipsec ipv6_flowlabel ipv6_flowlabel_mgr @@ -26,6 +28,7 @@ reuseport_bpf_cpu reuseport_bpf_numa reuseport_dualstack rxtimestamp +sctp_hello sk_bind_sendto_listen sk_connect_zero_addr socket diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index a47b26ab48f2..0f5e88c8f4ff 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -2283,7 +2283,7 @@ EOF ################################################################################ # main -while getopts :t:pP46hv:w: o +while getopts :t:pP46hvw: o do case $o in t) TESTS=$OPTARG;; diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 7da8ec838c63..35d89dfa6f11 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -68,7 +68,7 @@ setup() cleanup() { $IP link del dev dummy0 &> /dev/null - ip netns del ns1 + ip netns del ns1 &> /dev/null ip netns del ns2 &> /dev/null } diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index a474c60fe348..9d0062b542e5 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -83,6 +83,7 @@ TEST_PROGS = bridge_igmp.sh \ tc_chains.sh \ tc_flower_router.sh \ tc_flower.sh \ + tc_flower_l2_miss.sh \ tc_mpls_l2vpn.sh \ tc_police.sh \ tc_shblocks.sh \ diff --git a/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh index fa6a88c50750..de2b2d5480dd 100755 --- a/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh +++ b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh @@ -1,6 +1,28 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# +------------------------+ +----------------------+ +# | H1 (vrf) | | H2 (vrf) | +# | + $h1.555 | | + $h2 | +# | | 192.0.2.1/28 | | | 192.0.2.130/28 | +# | | 2001:db8:1::1/64 | | | 2001:db8:2::2/64 | +# | | | | | | +# | + $h1 | | | | +# +----|-------------------+ +--|-------------------+ +# | | +# +----|--------------------------------------------------|-------------------+ +# | SW | | | +# | +--|-------------------------------+ + $swp2 | +# | | + $swp1 | 192.0.2.129/28 | +# | | vid 555 | 2001:db8:2::1/64 | +# | | | | +# | | + BR1 (802.1q) | | +# | | vid 555 pvid untagged | | +# | | 192.0.2.2/28 | | +# | | 2001:db8:1::2/64 | | +# | +----------------------------------+ | +# +---------------------------------------------------------------------------+ + ALL_TESTS=" ping_ipv4 ping_ipv6 @@ -41,7 +63,7 @@ h2_destroy() router_create() { - ip link add name br1 type bridge vlan_filtering 1 + ip link add name br1 type bridge vlan_filtering 1 vlan_default_pvid 0 ip link set dev br1 up ip link set dev $swp1 master br1 diff --git a/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh new file mode 100755 index 000000000000..37b0369b5246 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh @@ -0,0 +1,350 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +-----------------------+ +----------------------+ +# | H1 (vrf) | | H2 (vrf) | +# | + $h1 | | $h2 + | +# | | 192.0.2.1/28 | | 192.0.2.2/28 | | +# | | 2001:db8:1::1/64 | | 2001:db8:1::2/64 | | +# +----|------------------+ +------------------|---+ +# | | +# +----|-------------------------------------------------------------------|---+ +# | SW | | | +# | +-|-------------------------------------------------------------------|-+ | +# | | + $swp1 BR $swp2 + | | +# | +-----------------------------------------------------------------------+ | +# +----------------------------------------------------------------------------+ + +ALL_TESTS=" + test_l2_miss_unicast + test_l2_miss_multicast + test_l2_miss_ll_multicast + test_l2_miss_broadcast +" + +NUM_NETIFS=4 +source lib.sh +source tc_common.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/28 2001:db8:1::1/64 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.2/28 2001:db8:1::2/64 +} + +h2_destroy() +{ + simple_if_fini $h2 192.0.2.2/28 2001:db8:1::2/64 +} + +switch_create() +{ + ip link add name br1 up type bridge + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + ip link set dev $swp2 master br1 + ip link set dev $swp2 up + + tc qdisc add dev $swp2 clsact +} + +switch_destroy() +{ + tc qdisc del dev $swp2 clsact + + ip link set dev $swp2 down + ip link set dev $swp2 nomaster + ip link set dev $swp1 down + ip link set dev $swp1 nomaster + ip link del dev br1 +} + +test_l2_miss_unicast() +{ + local dmac=00:01:02:03:04:05 + local dip=192.0.2.2 + local sip=192.0.2.1 + + RET=0 + + # Unknown unicast. + tc filter add dev $swp2 egress protocol ipv4 handle 101 pref 1 \ + flower indev $swp1 l2_miss true dst_mac $dmac src_ip $sip \ + dst_ip $dip action pass + # Known unicast. + tc filter add dev $swp2 egress protocol ipv4 handle 102 pref 1 \ + flower indev $swp1 l2_miss false dst_mac $dmac src_ip $sip \ + dst_ip $dip action pass + + # Before adding FDB entry. + $MZ $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 1 + check_err $? "Unknown unicast filter was not hit before adding FDB entry" + + tc_check_packets "dev $swp2 egress" 102 0 + check_err $? "Known unicast filter was hit before adding FDB entry" + + # Adding FDB entry. + bridge fdb replace $dmac dev $swp2 master static + + $MZ $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 1 + check_err $? "Unknown unicast filter was hit after adding FDB entry" + + tc_check_packets "dev $swp2 egress" 102 1 + check_err $? "Known unicast filter was not hit after adding FDB entry" + + # Deleting FDB entry. + bridge fdb del $dmac dev $swp2 master static + + $MZ $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 2 + check_err $? "Unknown unicast filter was not hit after deleting FDB entry" + + tc_check_packets "dev $swp2 egress" 102 1 + check_err $? "Known unicast filter was hit after deleting FDB entry" + + tc filter del dev $swp2 egress protocol ipv4 pref 1 handle 102 flower + tc filter del dev $swp2 egress protocol ipv4 pref 1 handle 101 flower + + log_test "L2 miss - Unicast" +} + +test_l2_miss_multicast_common() +{ + local proto=$1; shift + local sip=$1; shift + local dip=$1; shift + local mode=$1; shift + local name=$1; shift + + RET=0 + + # Unregistered multicast. + tc filter add dev $swp2 egress protocol $proto handle 101 pref 1 \ + flower indev $swp1 l2_miss true src_ip $sip dst_ip $dip \ + action pass + # Registered multicast. + tc filter add dev $swp2 egress protocol $proto handle 102 pref 1 \ + flower indev $swp1 l2_miss false src_ip $sip dst_ip $dip \ + action pass + + # Before adding MDB entry. + $MZ $mode $h1 -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 1 + check_err $? "Unregistered multicast filter was not hit before adding MDB entry" + + tc_check_packets "dev $swp2 egress" 102 0 + check_err $? "Registered multicast filter was hit before adding MDB entry" + + # Adding MDB entry. + bridge mdb replace dev br1 port $swp2 grp $dip permanent + + $MZ $mode $h1 -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 1 + check_err $? "Unregistered multicast filter was hit after adding MDB entry" + + tc_check_packets "dev $swp2 egress" 102 1 + check_err $? "Registered multicast filter was not hit after adding MDB entry" + + # Deleting MDB entry. + bridge mdb del dev br1 port $swp2 grp $dip + + $MZ $mode $h1 -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 2 + check_err $? "Unregistered multicast filter was not hit after deleting MDB entry" + + tc_check_packets "dev $swp2 egress" 102 1 + check_err $? "Registered multicast filter was hit after deleting MDB entry" + + tc filter del dev $swp2 egress protocol $proto pref 1 handle 102 flower + tc filter del dev $swp2 egress protocol $proto pref 1 handle 101 flower + + log_test "L2 miss - Multicast ($name)" +} + +test_l2_miss_multicast_ipv4() +{ + local proto="ipv4" + local sip=192.0.2.1 + local dip=239.1.1.1 + local mode="-4" + local name="IPv4" + + test_l2_miss_multicast_common $proto $sip $dip $mode $name +} + +test_l2_miss_multicast_ipv6() +{ + local proto="ipv6" + local sip=2001:db8:1::1 + local dip=ff0e::1 + local mode="-6" + local name="IPv6" + + test_l2_miss_multicast_common $proto $sip $dip $mode $name +} + +test_l2_miss_multicast() +{ + # Configure $swp2 as a multicast router port so that it will forward + # both registered and unregistered multicast traffic. + bridge link set dev $swp2 mcast_router 2 + + # Forwarding according to MDB entries only takes place when the bridge + # detects that there is a valid querier in the network. Set the bridge + # as the querier and assign it a valid IPv6 link-local address to be + # used as the source address for MLD queries. + ip link set dev br1 type bridge mcast_querier 1 + ip -6 address add fe80::1/64 nodad dev br1 + # Wait the default Query Response Interval (10 seconds) for the bridge + # to determine that there are no other queriers in the network. + sleep 10 + + test_l2_miss_multicast_ipv4 + test_l2_miss_multicast_ipv6 + + ip -6 address del fe80::1/64 dev br1 + ip link set dev br1 type bridge mcast_querier 0 + bridge link set dev $swp2 mcast_router 1 +} + +test_l2_miss_multicast_common2() +{ + local name=$1; shift + local dmac=$1; shift + local dip=224.0.0.1 + local sip=192.0.2.1 + +} + +test_l2_miss_ll_multicast_common() +{ + local proto=$1; shift + local dmac=$1; shift + local sip=$1; shift + local dip=$1; shift + local mode=$1; shift + local name=$1; shift + + RET=0 + + tc filter add dev $swp2 egress protocol $proto handle 101 pref 1 \ + flower indev $swp1 l2_miss true dst_mac $dmac src_ip $sip \ + dst_ip $dip action pass + + $MZ $mode $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 1 + check_err $? "Filter was not hit" + + tc filter del dev $swp2 egress protocol $proto pref 1 handle 101 flower + + log_test "L2 miss - Link-local multicast ($name)" +} + +test_l2_miss_ll_multicast_ipv4() +{ + local proto=ipv4 + local dmac=01:00:5e:00:00:01 + local sip=192.0.2.1 + local dip=224.0.0.1 + local mode="-4" + local name="IPv4" + + test_l2_miss_ll_multicast_common $proto $dmac $sip $dip $mode $name +} + +test_l2_miss_ll_multicast_ipv6() +{ + local proto=ipv6 + local dmac=33:33:00:00:00:01 + local sip=2001:db8:1::1 + local dip=ff02::1 + local mode="-6" + local name="IPv6" + + test_l2_miss_ll_multicast_common $proto $dmac $sip $dip $mode $name +} + +test_l2_miss_ll_multicast() +{ + test_l2_miss_ll_multicast_ipv4 + test_l2_miss_ll_multicast_ipv6 +} + +test_l2_miss_broadcast() +{ + local dmac=ff:ff:ff:ff:ff:ff + local smac=00:01:02:03:04:05 + + RET=0 + + tc filter add dev $swp2 egress protocol all handle 101 pref 1 \ + flower l2_miss true dst_mac $dmac src_mac $smac \ + action pass + tc filter add dev $swp2 egress protocol all handle 102 pref 1 \ + flower l2_miss false dst_mac $dmac src_mac $smac \ + action pass + + $MZ $h1 -a $smac -b $dmac -c 1 -p 100 -q + + tc_check_packets "dev $swp2 egress" 101 0 + check_err $? "L2 miss filter was hit when should not" + + tc_check_packets "dev $swp2 egress" 102 1 + check_err $? "L2 no miss filter was not hit when should" + + tc filter del dev $swp2 egress protocol all pref 1 handle 102 flower + tc filter del dev $swp2 egress protocol all pref 1 handle 101 flower + + log_test "L2 miss - Broadcast" +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + h1_create + h2_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h2_destroy + h1_destroy + vrf_cleanup +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index 43a723626126..7b936a926859 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -9,7 +9,7 @@ TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \ TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq -TEST_FILES := settings +TEST_FILES := mptcp_lib.sh settings EXTRA_CLEAN := *.pcap diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index ef628b16fe9b..4eacdb1ab962 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + sec=$(date +%s) rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) ns="ns1-$rndh" @@ -31,6 +33,8 @@ cleanup() ip netns del $ns } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index a43d3e2f59bb..c1f7bac19942 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + time_start=$(date +%s) optstring="S:R:d:e:l:r:h4cm:f:tC" @@ -141,6 +143,8 @@ cleanup() done } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 26310c17b4c6..85474e029784 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -10,6 +10,8 @@ # because it's invoked by variable name, see how the "tests" array is used #shellcheck disable=SC2317 +. "$(dirname "${0}")/mptcp_lib.sh" + ret=0 sin="" sinfail="" @@ -17,6 +19,7 @@ sout="" cin="" cinfail="" cinsent="" +tmpfile="" cout="" capout="" ns1="" @@ -34,6 +37,7 @@ evts_ns1="" evts_ns2="" evts_ns1_pid=0 evts_ns2_pid=0 +stats_dumped=0 declare -A all_tests declare -a only_tests_ids @@ -87,6 +91,7 @@ init_partial() fi done + stats_dumped=0 check_invert=0 validate_checksum=$checksum FAILING_LINKS="" @@ -136,6 +141,8 @@ cleanup_partial() check_tools() { + mptcp_lib_check_mptcp + if ! ip -Version &> /dev/null; then echo "SKIP: Could not run test without ip tool" exit $ksft_skip @@ -175,6 +182,7 @@ cleanup() { rm -f "$cin" "$cout" "$sinfail" rm -f "$sin" "$sout" "$cinsent" "$cinfail" + rm -f "$tmpfile" rm -rf $evts_ns1 $evts_ns2 cleanup_partial } @@ -347,6 +355,9 @@ fail_test() { ret=1 failed_tests[${TEST_COUNT}]="${TEST_NAME}" + + [ "${stats_dumped}" = 0 ] && dump_stats + stats_dumped=1 } get_failed_tests_ids() @@ -383,9 +394,16 @@ check_transfer() fail_test return 1 fi - bytes="--bytes=${bytes}" + + # note: BusyBox's "cmp" command doesn't support --bytes + tmpfile=$(mktemp) + head --bytes="$bytes" "$in" > "$tmpfile" + mv "$tmpfile" "$in" + head --bytes="$bytes" "$out" > "$tmpfile" + mv "$tmpfile" "$out" + tmpfile="" fi - cmp -l "$in" "$out" ${bytes} | while read -r i a b; do + cmp -l "$in" "$out" | while read -r i a b; do local sum=$((0${a} + 0${b})) if [ $check_invert -eq 0 ] || [ $sum -ne $((0xff)) ]; then echo "[ FAIL ] $what does not match (in, out):" @@ -849,7 +867,15 @@ do_transfer() sed -n 's/.*\(token:\)\([[:digit:]]*\).*$/\2/p;q') ip netns exec ${listener_ns} ./pm_nl_ctl ann $addr token $tk id $id sleep 1 + sp=$(grep "type:10" "$evts_ns1" | + sed -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q') + da=$(grep "type:10" "$evts_ns1" | + sed -n 's/.*\(daddr6:\)\([0-9a-f:.]*\).*$/\2/p;q') + dp=$(grep "type:10" "$evts_ns1" | + sed -n 's/.*\(dport:\)\([[:digit:]]*\).*$/\2/p;q') ip netns exec ${listener_ns} ./pm_nl_ctl rem token $tk id $id + ip netns exec ${listener_ns} ./pm_nl_ctl dsf lip "::ffff:$addr" \ + lport $sp rip $da rport $dp token $tk fi counter=$((counter + 1)) @@ -915,6 +941,7 @@ do_transfer() sleep 1 sp=$(grep "type:10" "$evts_ns2" | sed -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q') + ip netns exec ${connector_ns} ./pm_nl_ctl rem token $tk id $id ip netns exec ${connector_ns} ./pm_nl_ctl dsf lip $addr lport $sp \ rip $da rport $dp token $tk fi @@ -1120,7 +1147,6 @@ chk_csum_nr() local csum_ns1=${1:-0} local csum_ns2=${2:-0} local count - local dump_stats local extra_msg="" local allow_multi_errors_ns1=0 local allow_multi_errors_ns2=0 @@ -1144,7 +1170,6 @@ chk_csum_nr() { [ "$count" -lt $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 1 ]; }; then echo "[fail] got $count data checksum error[s] expected $csum_ns1" fail_test - dump_stats=1 else echo -n "[ ok ]" fi @@ -1158,11 +1183,9 @@ chk_csum_nr() { [ "$count" -lt $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 1 ]; }; then echo "[fail] got $count data checksum error[s] expected $csum_ns2" fail_test - dump_stats=1 else echo -n "[ ok ]" fi - [ "${dump_stats}" = 1 ] && dump_stats echo "$extra_msg" } @@ -1173,7 +1196,6 @@ chk_fail_nr() local fail_rx=$2 local ns_invert=${3:-""} local count - local dump_stats local ns_tx=$ns1 local ns_rx=$ns2 local extra_msg="" @@ -1205,7 +1227,6 @@ chk_fail_nr() { [ "$count" -gt "$fail_tx" ] && [ $allow_tx_lost -eq 1 ]; }; then echo "[fail] got $count MP_FAIL[s] TX expected $fail_tx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi @@ -1220,13 +1241,10 @@ chk_fail_nr() { [ "$count" -gt "$fail_rx" ] && [ $allow_rx_lost -eq 1 ]; }; then echo "[fail] got $count MP_FAIL[s] RX expected $fail_rx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi - [ "${dump_stats}" = 1 ] && dump_stats - echo "$extra_msg" } @@ -1236,7 +1254,6 @@ chk_fclose_nr() local fclose_rx=$2 local ns_invert=$3 local count - local dump_stats local ns_tx=$ns2 local ns_rx=$ns1 local extra_msg=" " @@ -1254,7 +1271,6 @@ chk_fclose_nr() if [ "$count" != "$fclose_tx" ]; then echo "[fail] got $count MP_FASTCLOSE[s] TX expected $fclose_tx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi @@ -1266,13 +1282,10 @@ chk_fclose_nr() if [ "$count" != "$fclose_rx" ]; then echo "[fail] got $count MP_FASTCLOSE[s] RX expected $fclose_rx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi - [ "${dump_stats}" = 1 ] && dump_stats - echo "$extra_msg" } @@ -1282,7 +1295,6 @@ chk_rst_nr() local rst_rx=$2 local ns_invert=${3:-""} local count - local dump_stats local ns_tx=$ns1 local ns_rx=$ns2 local extra_msg="" @@ -1299,7 +1311,6 @@ chk_rst_nr() if [ $count -lt $rst_tx ]; then echo "[fail] got $count MP_RST[s] TX expected $rst_tx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi @@ -1310,13 +1321,10 @@ chk_rst_nr() if [ "$count" -lt "$rst_rx" ]; then echo "[fail] got $count MP_RST[s] RX expected $rst_rx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi - [ "${dump_stats}" = 1 ] && dump_stats - echo "$extra_msg" } @@ -1325,7 +1333,6 @@ chk_infi_nr() local infi_tx=$1 local infi_rx=$2 local count - local dump_stats printf "%-${nr_blank}s %s" " " "itx" count=$(ip netns exec $ns2 nstat -as | grep InfiniteMapTx | awk '{print $2}') @@ -1333,7 +1340,6 @@ chk_infi_nr() if [ "$count" != "$infi_tx" ]; then echo "[fail] got $count infinite map[s] TX expected $infi_tx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi @@ -1344,12 +1350,9 @@ chk_infi_nr() if [ "$count" != "$infi_rx" ]; then echo "[fail] got $count infinite map[s] RX expected $infi_rx" fail_test - dump_stats=1 else echo "[ ok ]" fi - - [ "${dump_stats}" = 1 ] && dump_stats } chk_join_nr() @@ -1364,7 +1367,6 @@ chk_join_nr() local infi_nr=${8:-0} local corrupted_pkts=${9:-0} local count - local dump_stats local with_cookie local title="${TEST_NAME}" @@ -1378,7 +1380,6 @@ chk_join_nr() if [ "$count" != "$syn_nr" ]; then echo "[fail] got $count JOIN[s] syn expected $syn_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi @@ -1396,7 +1397,6 @@ chk_join_nr() else echo "[fail] got $count JOIN[s] synack expected $syn_ack_nr" fail_test - dump_stats=1 fi else echo -n "[ ok ]" @@ -1408,11 +1408,9 @@ chk_join_nr() if [ "$count" != "$ack_nr" ]; then echo "[fail] got $count JOIN[s] ack expected $ack_nr" fail_test - dump_stats=1 else echo "[ ok ]" fi - [ "${dump_stats}" = 1 ] && dump_stats if [ $validate_checksum -eq 1 ]; then chk_csum_nr $csum_ns1 $csum_ns2 chk_fail_nr $fail_nr $fail_nr @@ -1472,7 +1470,6 @@ chk_add_nr() local mis_syn_nr=${7:-0} local mis_ack_nr=${8:-0} local count - local dump_stats local timeout timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout) @@ -1486,18 +1483,16 @@ chk_add_nr() if [ "$count" != "$add_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_nr" ]; }; then echo "[fail] got $count ADD_ADDR[s] expected $add_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi echo -n " - echo " - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtEchoAdd | awk '{print $2}') + count=$(ip netns exec $ns1 nstat -as MPTcpExtEchoAdd | grep MPTcpExtEchoAdd | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$echo_nr" ]; then echo "[fail] got $count ADD_ADDR echo[s] expected $echo_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi @@ -1509,7 +1504,6 @@ chk_add_nr() if [ "$count" != "$port_nr" ]; then echo "[fail] got $count ADD_ADDR[s] with a port-number expected $port_nr" fail_test - dump_stats=1 else echo "[ ok ]" fi @@ -1522,7 +1516,6 @@ chk_add_nr() echo "[fail] got $count JOIN[s] syn with a different \ port-number expected $syn_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi @@ -1535,7 +1528,6 @@ chk_add_nr() echo "[fail] got $count JOIN[s] synack with a different \ port-number expected $syn_ack_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi @@ -1548,7 +1540,6 @@ chk_add_nr() echo "[fail] got $count JOIN[s] ack with a different \ port-number expected $ack_nr" fail_test - dump_stats=1 else echo "[ ok ]" fi @@ -1561,7 +1552,6 @@ chk_add_nr() echo "[fail] got $count JOIN[s] syn with a mismatched \ port-number expected $mis_syn_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi @@ -1574,15 +1564,45 @@ chk_add_nr() echo "[fail] got $count JOIN[s] ack with a mismatched \ port-number expected $mis_ack_nr" fail_test - dump_stats=1 else echo "[ ok ]" fi else echo "" fi +} + +chk_add_tx_nr() +{ + local add_tx_nr=$1 + local echo_tx_nr=$2 + local timeout + local count + + timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout) + + printf "%-${nr_blank}s %s" " " "add TX" + count=$(ip netns exec $ns1 nstat -as MPTcpExtAddAddrTx | grep MPTcpExtAddAddrTx | awk '{print $2}') + [ -z "$count" ] && count=0 + + # if the test configured a short timeout tolerate greater then expected + # add addrs options, due to retransmissions + if [ "$count" != "$add_tx_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_tx_nr" ]; }; then + echo "[fail] got $count ADD_ADDR[s] TX, expected $add_tx_nr" + fail_test + else + echo -n "[ ok ]" + fi - [ "${dump_stats}" = 1 ] && dump_stats + echo -n " - echo TX " + count=$(ip netns exec $ns2 nstat -as MPTcpExtEchoAddTx | grep MPTcpExtEchoAddTx | awk '{print $2}') + [ -z "$count" ] && count=0 + if [ "$count" != "$echo_tx_nr" ]; then + echo "[fail] got $count ADD_ADDR echo[s] TX, expected $echo_tx_nr" + fail_test + else + echo "[ ok ]" + fi } chk_rm_nr() @@ -1592,7 +1612,6 @@ chk_rm_nr() local invert local simult local count - local dump_stats local addr_ns=$ns1 local subflow_ns=$ns2 local extra_msg="" @@ -1614,12 +1633,11 @@ chk_rm_nr() fi printf "%-${nr_blank}s %s" " " "rm " - count=$(ip netns exec $addr_ns nstat -as | grep MPTcpExtRmAddr | awk '{print $2}') + count=$(ip netns exec $addr_ns nstat -as MPTcpExtRmAddr | grep MPTcpExtRmAddr | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$rm_addr_nr" ]; then echo "[fail] got $count RM_ADDR[s] expected $rm_addr_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi @@ -1643,19 +1661,32 @@ chk_rm_nr() else echo "[fail] got $count RM_SUBFLOW[s] expected in range [$rm_subflow_nr:$((rm_subflow_nr*2))]" fail_test - dump_stats=1 fi return fi if [ "$count" != "$rm_subflow_nr" ]; then echo "[fail] got $count RM_SUBFLOW[s] expected $rm_subflow_nr" fail_test - dump_stats=1 else echo -n "[ ok ]" fi - [ "${dump_stats}" = 1 ] && dump_stats + echo "$extra_msg" +} + +chk_rm_tx_nr() +{ + local rm_addr_tx_nr=$1 + + printf "%-${nr_blank}s %s" " " "rm TX " + count=$(ip netns exec $ns2 nstat -as MPTcpExtRmAddrTx | grep MPTcpExtRmAddrTx | awk '{print $2}') + [ -z "$count" ] && count=0 + if [ "$count" != "$rm_addr_tx_nr" ]; then + echo "[fail] got $count RM_ADDR[s] expected $rm_addr_tx_nr" + fail_test + else + echo -n "[ ok ]" + fi echo "$extra_msg" } @@ -1665,7 +1696,6 @@ chk_prio_nr() local mp_prio_nr_tx=$1 local mp_prio_nr_rx=$2 local count - local dump_stats printf "%-${nr_blank}s %s" " " "ptx" count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPPrioTx | awk '{print $2}') @@ -1673,7 +1703,6 @@ chk_prio_nr() if [ "$count" != "$mp_prio_nr_tx" ]; then echo "[fail] got $count MP_PRIO[s] TX expected $mp_prio_nr_tx" fail_test - dump_stats=1 else echo -n "[ ok ]" fi @@ -1684,12 +1713,9 @@ chk_prio_nr() if [ "$count" != "$mp_prio_nr_rx" ]; then echo "[fail] got $count MP_PRIO[s] RX expected $mp_prio_nr_rx" fail_test - dump_stats=1 else echo "[ ok ]" fi - - [ "${dump_stats}" = 1 ] && dump_stats } chk_subflow_nr() @@ -1721,7 +1747,6 @@ chk_subflow_nr() ss -N $ns1 -tOni ss -N $ns1 -tOni | grep token ip -n $ns1 mptcp endpoint - dump_stats fi } @@ -1761,7 +1786,6 @@ chk_mptcp_info() if [ "$dump_stats" = 1 ]; then ss -N $ns1 -inmHM ss -N $ns2 -inmHM - dump_stats fi } @@ -1939,6 +1963,7 @@ signal_address_tests() pm_nl_add_endpoint $ns1 10.0.2.1 flags signal run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 + chk_add_tx_nr 1 1 chk_add_nr 1 1 fi @@ -2120,6 +2145,7 @@ add_addr_timeout_tests() pm_nl_add_endpoint $ns1 10.0.2.1 flags signal run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow chk_join_nr 1 1 1 + chk_add_tx_nr 4 4 chk_add_nr 4 0 fi @@ -2165,6 +2191,7 @@ remove_tests() pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 0 -1 slow chk_join_nr 1 1 1 + chk_rm_tx_nr 1 chk_rm_nr 1 1 fi @@ -2263,6 +2290,7 @@ remove_tests() pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow chk_join_nr 3 3 3 + chk_rm_tx_nr 0 chk_rm_nr 0 3 simult fi @@ -3129,7 +3157,7 @@ userspace_tests() pm_nl_set_limits $ns1 0 1 run_tests $ns1 $ns2 10.0.1.1 0 0 userspace_1 slow chk_join_nr 1 1 1 - chk_rm_nr 0 1 + chk_rm_nr 1 1 kill_events_pids fi } diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh new file mode 100644 index 000000000000..3286536b79d5 --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -0,0 +1,40 @@ +#! /bin/bash +# SPDX-License-Identifier: GPL-2.0 + +readonly KSFT_FAIL=1 +readonly KSFT_SKIP=4 + +# SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES env var can be set when validating all +# features using the last version of the kernel and the selftests to make sure +# a test is not being skipped by mistake. +mptcp_lib_expect_all_features() { + [ "${SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES:-}" = "1" ] +} + +# $1: msg +mptcp_lib_fail_if_expected_feature() { + if mptcp_lib_expect_all_features; then + echo "ERROR: missing feature: ${*}" + exit ${KSFT_FAIL} + fi + + return 1 +} + +# $1: file +mptcp_lib_has_file() { + local f="${1}" + + if [ -f "${f}" ]; then + return 0 + fi + + mptcp_lib_fail_if_expected_feature "${f} file not found" +} + +mptcp_lib_check_mptcp() { + if ! mptcp_lib_has_file "/proc/sys/net/mptcp/enabled"; then + echo "SKIP: MPTCP support is not available" + exit ${KSFT_SKIP} + fi +} diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh index 1b70c0a304ce..ff5adbb9c7f2 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + ret=0 sin="" sout="" @@ -84,6 +86,8 @@ cleanup() rm -f "$sin" "$sout" } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index 89839d1ff9d8..32f7533e0919 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + ksft_skip=4 ret=0 @@ -34,6 +36,8 @@ cleanup() ip netns del $ns1 } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 9f22f7e5027d..36a3c9d92e20 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + sec=$(date +%s) rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) ns1="ns1-$rndh" @@ -34,6 +36,8 @@ cleanup() done } +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index b1eb7bce599d..8092399d911f 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -1,6 +1,10 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +. "$(dirname "${0}")/mptcp_lib.sh" + +mptcp_lib_check_mptcp + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Cannot not run test without ip tool" diff --git a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh index 1003119773e5..f96282362811 100755 --- a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh @@ -232,10 +232,14 @@ setup_rt_networking() local nsname=rt-${rt} ip netns add ${nsname} + + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.default.accept_dad=0 + ip link set veth-rt-${rt} netns ${nsname} ip -netns ${nsname} link set veth-rt-${rt} name veth0 - ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${rt}/64 dev veth0 + ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${rt}/64 dev veth0 nodad ip -netns ${nsname} link set veth0 up ip -netns ${nsname} link set lo up @@ -254,6 +258,12 @@ setup_hs() # set the networking for the host ip netns add ${hsname} + + # disable the rp_filter otherwise the kernel gets confused about how + # to route decap ipv4 packets. + ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0 + ip netns exec ${rtname} sysctl -wq net.ipv4.conf.default.rp_filter=0 + ip -netns ${hsname} link add veth0 type veth peer name ${rtveth} ip -netns ${hsname} link set ${rtveth} netns ${rtname} ip -netns ${hsname} addr add ${IPv4_HS_NETWORK}.${hs}/24 dev veth0 @@ -272,11 +282,6 @@ setup_hs() ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.proxy_arp=1 - # disable the rp_filter otherwise the kernel gets confused about how - # to route decap ipv4 packets. - ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0 - ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.rp_filter=0 - ip netns exec ${rtname} sh -c "echo 1 > /proc/sys/net/vrf/strict_mode" } diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index e699548d4247..eccea9845c65 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -15,6 +15,7 @@ #include <linux/tcp.h> #include <linux/socket.h> +#include <sys/epoll.h> #include <sys/types.h> #include <sys/sendfile.h> #include <sys/socket.h> @@ -1637,6 +1638,136 @@ TEST_F(tls_err, timeo) } } +TEST_F(tls_err, poll_partial_rec) +{ + struct pollfd pfd = { }; + ssize_t rec_len; + char rec[256]; + char buf[128]; + + if (self->notls) + SKIP(return, "no TLS support"); + + pfd.fd = self->cfd2; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 1), 0); + + memrnd(buf, sizeof(buf)); + EXPECT_EQ(send(self->fd, buf, sizeof(buf), 0), sizeof(buf)); + rec_len = recv(self->cfd, rec, sizeof(rec), 0); + EXPECT_GT(rec_len, sizeof(buf)); + + /* Write 100B, not the full record ... */ + EXPECT_EQ(send(self->fd2, rec, 100, 0), 100); + /* ... no full record should mean no POLLIN */ + pfd.fd = self->cfd2; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 1), 0); + /* Now write the rest, and it should all pop out of the other end. */ + EXPECT_EQ(send(self->fd2, rec + 100, rec_len - 100, 0), rec_len - 100); + pfd.fd = self->cfd2; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 1), 1); + EXPECT_EQ(recv(self->cfd2, rec, sizeof(rec), 0), sizeof(buf)); + EXPECT_EQ(memcmp(buf, rec, sizeof(buf)), 0); +} + +TEST_F(tls_err, epoll_partial_rec) +{ + struct epoll_event ev, events[10]; + ssize_t rec_len; + char rec[256]; + char buf[128]; + int epollfd; + + if (self->notls) + SKIP(return, "no TLS support"); + + epollfd = epoll_create1(0); + ASSERT_GE(epollfd, 0); + + memset(&ev, 0, sizeof(ev)); + ev.events = EPOLLIN; + ev.data.fd = self->cfd2; + ASSERT_GE(epoll_ctl(epollfd, EPOLL_CTL_ADD, self->cfd2, &ev), 0); + + EXPECT_EQ(epoll_wait(epollfd, events, 10, 0), 0); + + memrnd(buf, sizeof(buf)); + EXPECT_EQ(send(self->fd, buf, sizeof(buf), 0), sizeof(buf)); + rec_len = recv(self->cfd, rec, sizeof(rec), 0); + EXPECT_GT(rec_len, sizeof(buf)); + + /* Write 100B, not the full record ... */ + EXPECT_EQ(send(self->fd2, rec, 100, 0), 100); + /* ... no full record should mean no POLLIN */ + EXPECT_EQ(epoll_wait(epollfd, events, 10, 0), 0); + /* Now write the rest, and it should all pop out of the other end. */ + EXPECT_EQ(send(self->fd2, rec + 100, rec_len - 100, 0), rec_len - 100); + EXPECT_EQ(epoll_wait(epollfd, events, 10, 0), 1); + EXPECT_EQ(recv(self->cfd2, rec, sizeof(rec), 0), sizeof(buf)); + EXPECT_EQ(memcmp(buf, rec, sizeof(buf)), 0); + + close(epollfd); +} + +TEST_F(tls_err, poll_partial_rec_async) +{ + struct pollfd pfd = { }; + ssize_t rec_len; + char rec[256]; + char buf[128]; + char token; + int p[2]; + int ret; + + if (self->notls) + SKIP(return, "no TLS support"); + + ASSERT_GE(pipe(p), 0); + + memrnd(buf, sizeof(buf)); + EXPECT_EQ(send(self->fd, buf, sizeof(buf), 0), sizeof(buf)); + rec_len = recv(self->cfd, rec, sizeof(rec), 0); + EXPECT_GT(rec_len, sizeof(buf)); + + ret = fork(); + ASSERT_GE(ret, 0); + + if (ret) { + int status, pid2; + + close(p[1]); + usleep(1000); /* Give child a head start */ + + EXPECT_EQ(send(self->fd2, rec, 100, 0), 100); + + EXPECT_EQ(read(p[0], &token, 1), 1); /* Barrier #1 */ + + EXPECT_EQ(send(self->fd2, rec + 100, rec_len - 100, 0), + rec_len - 100); + + pid2 = wait(&status); + EXPECT_EQ(pid2, ret); + EXPECT_EQ(status, 0); + } else { + close(p[0]); + + /* Child should sleep in poll(), never get a wake */ + pfd.fd = self->cfd2; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 5), 0); + + EXPECT_EQ(write(p[1], &token, 1), 1); /* Barrier #1 */ + + pfd.fd = self->cfd2; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 5), 1); + + exit(!_metadata->passed); + } +} + TEST(non_established) { struct tls12_crypto_info_aes_gcm_256 tls12; struct sockaddr_in addr; diff --git a/tools/testing/selftests/sgx/Makefile b/tools/testing/selftests/sgx/Makefile index 75af864e07b6..50aab6b57da3 100644 --- a/tools/testing/selftests/sgx/Makefile +++ b/tools/testing/selftests/sgx/Makefile @@ -17,6 +17,7 @@ ENCL_CFLAGS := -Wall -Werror -static -nostdlib -nostartfiles -fPIC \ -fno-stack-protector -mrdrnd $(INCLUDES) TEST_CUSTOM_PROGS := $(OUTPUT)/test_sgx +TEST_FILES := $(OUTPUT)/test_encl.elf ifeq ($(CAN_BUILD_X86_64), 1) all: $(TEST_CUSTOM_PROGS) $(OUTPUT)/test_encl.elf diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json index 44fbfc6caec7..e3d2de5c184f 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json @@ -155,5 +155,28 @@ "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" ] - } + }, + { + "id": "0531", + "name": "Replace mq with invalid parent ID", + "category": [ + "qdisc", + "mq" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "echo \"1 1 16\" > /sys/bus/netdevsim/new_device", + "$TC qdisc add dev $ETH root handle ffff: mq" + ], + "cmdUnderTest": "$TC qdisc replace dev $ETH parent ffff:fff1 handle ffff: mq", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $ETH", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent ffff", + "matchCount": "16", + "teardown": [ + "echo \"1\" > /sys/bus/netdevsim/del_device" + ] + } ] diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index cb5c13eee193..479802a892d4 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3962,18 +3962,19 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) } vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus); - r = xa_insert(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, GFP_KERNEL_ACCOUNT); - BUG_ON(r == -EBUSY); + r = xa_reserve(&kvm->vcpu_array, vcpu->vcpu_idx, GFP_KERNEL_ACCOUNT); if (r) goto unlock_vcpu_destroy; /* Now it's all set up, let userspace reach it */ kvm_get_kvm(kvm); r = create_vcpu_fd(vcpu); - if (r < 0) { - xa_erase(&kvm->vcpu_array, vcpu->vcpu_idx); - kvm_put_kvm_no_destroy(kvm); - goto unlock_vcpu_destroy; + if (r < 0) + goto kvm_put_xa_release; + + if (KVM_BUG_ON(!!xa_store(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, 0), kvm)) { + r = -EINVAL; + goto kvm_put_xa_release; } /* @@ -3988,6 +3989,9 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) kvm_create_vcpu_debugfs(vcpu); return r; +kvm_put_xa_release: + kvm_put_kvm_no_destroy(kvm); + xa_release(&kvm->vcpu_array, vcpu->vcpu_idx); unlock_vcpu_destroy: mutex_unlock(&kvm->lock); kvm_dirty_ring_free(&vcpu->dirty_ring); @@ -5184,7 +5188,20 @@ static void hardware_disable_all(void) static int hardware_enable_all(void) { atomic_t failed = ATOMIC_INIT(0); - int r = 0; + int r; + + /* + * Do not enable hardware virtualization if the system is going down. + * If userspace initiated a forced reboot, e.g. reboot -f, then it's + * possible for an in-flight KVM_CREATE_VM to trigger hardware enabling + * after kvm_reboot() is called. Note, this relies on system_state + * being set _before_ kvm_reboot(), which is why KVM uses a syscore ops + * hook instead of registering a dedicated reboot notifier (the latter + * runs before system_state is updated). + */ + if (system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF || + system_state == SYSTEM_RESTART) + return -EBUSY; /* * When onlining a CPU, cpu_online_mask is set before kvm_online_cpu() @@ -5197,6 +5214,8 @@ static int hardware_enable_all(void) cpus_read_lock(); mutex_lock(&kvm_lock); + r = 0; + kvm_usage_count++; if (kvm_usage_count == 1) { on_each_cpu(hardware_enable_nolock, &failed, 1); @@ -5213,26 +5232,24 @@ static int hardware_enable_all(void) return r; } -static int kvm_reboot(struct notifier_block *notifier, unsigned long val, - void *v) +static void kvm_shutdown(void) { /* - * Some (well, at least mine) BIOSes hang on reboot if - * in vmx root mode. - * - * And Intel TXT required VMX off for all cpu when system shutdown. + * Disable hardware virtualization and set kvm_rebooting to indicate + * that KVM has asynchronously disabled hardware virtualization, i.e. + * that relevant errors and exceptions aren't entirely unexpected. + * Some flavors of hardware virtualization need to be disabled before + * transferring control to firmware (to perform shutdown/reboot), e.g. + * on x86, virtualization can block INIT interrupts, which are used by + * firmware to pull APs back under firmware control. Note, this path + * is used for both shutdown and reboot scenarios, i.e. neither name is + * 100% comprehensive. */ pr_info("kvm: exiting hardware virtualization\n"); kvm_rebooting = true; on_each_cpu(hardware_disable_nolock, NULL, 1); - return NOTIFY_OK; } -static struct notifier_block kvm_reboot_notifier = { - .notifier_call = kvm_reboot, - .priority = 0, -}; - static int kvm_suspend(void) { /* @@ -5263,6 +5280,7 @@ static void kvm_resume(void) static struct syscore_ops kvm_syscore_ops = { .suspend = kvm_suspend, .resume = kvm_resume, + .shutdown = kvm_shutdown, }; #else /* CONFIG_KVM_GENERIC_HARDWARE_ENABLING */ static int hardware_enable_all(void) @@ -5967,7 +5985,6 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) if (r) return r; - register_reboot_notifier(&kvm_reboot_notifier); register_syscore_ops(&kvm_syscore_ops); #endif @@ -6039,7 +6056,6 @@ err_cpu_kick_mask: err_vcpu_cache: #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING unregister_syscore_ops(&kvm_syscore_ops); - unregister_reboot_notifier(&kvm_reboot_notifier); cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); #endif return r; @@ -6065,7 +6081,6 @@ void kvm_exit(void) kvm_async_pf_deinit(); #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING unregister_syscore_ops(&kvm_syscore_ops); - unregister_reboot_notifier(&kvm_reboot_notifier); cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); #endif kvm_irqfd_exit(); |