diff options
1479 files changed, 16587 insertions, 12596 deletions
diff --git a/.clang-format b/.clang-format index f49620f506f1..f3923a1f9858 100644 --- a/.clang-format +++ b/.clang-format @@ -78,6 +78,8 @@ ForEachMacros: - 'ata_qc_for_each_with_internal' - 'ax25_for_each' - 'ax25_uid_for_each' + - '__bio_for_each_bvec' + - 'bio_for_each_bvec' - 'bio_for_each_integrity_vec' - '__bio_for_each_segment' - 'bio_for_each_segment' @@ -118,10 +120,12 @@ ForEachMacros: - 'drm_for_each_legacy_plane' - 'drm_for_each_plane' - 'drm_for_each_plane_mask' + - 'drm_for_each_privobj' - 'drm_mm_for_each_hole' - 'drm_mm_for_each_node' - 'drm_mm_for_each_node_in_range' - 'drm_mm_for_each_node_safe' + - 'flow_action_for_each' - 'for_each_active_drhd_unit' - 'for_each_active_iommu' - 'for_each_available_child_of_node' @@ -158,6 +162,9 @@ ForEachMacros: - 'for_each_dss_dev' - 'for_each_efi_memory_desc' - 'for_each_efi_memory_desc_in_map' + - 'for_each_element' + - 'for_each_element_extid' + - 'for_each_element_id' - 'for_each_endpoint_of_node' - 'for_each_evictable_lru' - 'for_each_fib6_node_rt_rcu' @@ -195,6 +202,7 @@ ForEachMacros: - 'for_each_net_rcu' - 'for_each_new_connector_in_state' - 'for_each_new_crtc_in_state' + - 'for_each_new_mst_mgr_in_state' - 'for_each_new_plane_in_state' - 'for_each_new_private_obj_in_state' - 'for_each_node' @@ -210,8 +218,10 @@ ForEachMacros: - 'for_each_of_pci_range' - 'for_each_old_connector_in_state' - 'for_each_old_crtc_in_state' + - 'for_each_old_mst_mgr_in_state' - 'for_each_oldnew_connector_in_state' - 'for_each_oldnew_crtc_in_state' + - 'for_each_oldnew_mst_mgr_in_state' - 'for_each_oldnew_plane_in_state' - 'for_each_oldnew_plane_in_state_reverse' - 'for_each_oldnew_private_obj_in_state' @@ -243,6 +253,9 @@ ForEachMacros: - 'for_each_sg_dma_page' - 'for_each_sg_page' - 'for_each_sibling_event' + - 'for_each_subelement' + - 'for_each_subelement_extid' + - 'for_each_subelement_id' - '__for_each_thread' - 'for_each_thread' - 'for_each_zone' @@ -252,6 +265,8 @@ ForEachMacros: - 'fwnode_for_each_child_node' - 'fwnode_graph_for_each_endpoint' - 'gadget_for_each_ep' + - 'genradix_for_each' + - 'genradix_for_each_from' - 'hash_for_each' - 'hash_for_each_possible' - 'hash_for_each_possible_rcu' @@ -293,7 +308,11 @@ ForEachMacros: - 'key_for_each' - 'key_for_each_safe' - 'klp_for_each_func' + - 'klp_for_each_func_safe' + - 'klp_for_each_func_static' - 'klp_for_each_object' + - 'klp_for_each_object_safe' + - 'klp_for_each_object_static' - 'kvm_for_each_memslot' - 'kvm_for_each_vcpu' - 'list_for_each' @@ -324,6 +343,8 @@ ForEachMacros: - 'media_device_for_each_intf' - 'media_device_for_each_link' - 'media_device_for_each_pad' + - 'mp_bvec_for_each_page' + - 'mp_bvec_for_each_segment' - 'nanddev_io_for_each_page' - 'netdev_for_each_lower_dev' - 'netdev_for_each_lower_private' @@ -375,6 +396,7 @@ ForEachMacros: - 'rht_for_each_rcu' - 'rht_for_each_rcu_continue' - '__rq_for_each_bio' + - 'rq_for_each_bvec' - 'rq_for_each_segment' - 'scsi_for_each_prot_sg' - 'scsi_for_each_sg' @@ -410,6 +432,8 @@ ForEachMacros: - 'v4l2_m2m_for_each_src_buf_safe' - 'virtio_device_for_each_vq' - 'xa_for_each' + - 'xa_for_each_marked' + - 'xa_for_each_start' - 'xas_for_each' - 'xas_for_each_conflict' - 'xas_for_each_marked' @@ -156,6 +156,8 @@ Morten Welinder <welinder@darter.rentec.com> Morten Welinder <welinder@troll.com> Mythri P K <mythripk@ti.com> Nguyen Anh Quynh <aquynh@gmail.com> +Nicolas Pitre <nico@fluxnic.net> <nicolas.pitre@linaro.org> +Nicolas Pitre <nico@fluxnic.net> <nico@linaro.org> Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Patrick Mochel <mochel@digitalimplant.org> Paul Burton <paul.burton@mips.com> <paul.burton@imgtec.com> @@ -224,3 +226,5 @@ Yakir Yang <kuankuan.y@gmail.com> <ykk@rock-chips.com> Yusuke Goda <goda.yusuke@renesas.com> Gustavo Padovan <gustavo@las.ic.unicamp.br> Gustavo Padovan <padovan@profusion.mobi> +Changbin Du <changbin.du@intel.com> <changbin.du@intel.com> +Changbin Du <changbin.du@intel.com> <changbin.du@gmail.com> diff --git a/Documentation/accounting/psi.txt b/Documentation/accounting/psi.txt index b8ca28b60215..7e71c9c1d8e9 100644 --- a/Documentation/accounting/psi.txt +++ b/Documentation/accounting/psi.txt @@ -56,12 +56,12 @@ situation from a state where some tasks are stalled but the CPU is still doing productive work. As such, time spent in this subset of the stall state is tracked separately and exported in the "full" averages. -The ratios are tracked as recent trends over ten, sixty, and three -hundred second windows, which gives insight into short term events as -well as medium and long term trends. The total absolute stall time is -tracked and exported as well, to allow detection of latency spikes -which wouldn't necessarily make a dent in the time averages, or to -average trends over custom time frames. +The ratios (in %) are tracked as recent trends over ten, sixty, and +three hundred second windows, which gives insight into short term events +as well as medium and long term trends. The total absolute stall time +(in us) is tracked and exported as well, to allow detection of latency +spikes which wouldn't necessarily make a dent in the time averages, +or to average trends over custom time frames. Cgroup2 interface ================= diff --git a/Documentation/bpf/btf.rst b/Documentation/bpf/btf.rst index 9a60a5d60e38..7313d354f20e 100644 --- a/Documentation/bpf/btf.rst +++ b/Documentation/bpf/btf.rst @@ -148,16 +148,16 @@ The ``btf_type.size * 8`` must be equal to or greater than ``BTF_INT_BITS()`` for the type. The maximum value of ``BTF_INT_BITS()`` is 128. The ``BTF_INT_OFFSET()`` specifies the starting bit offset to calculate values -for this int. For example, a bitfield struct member has: * btf member bit -offset 100 from the start of the structure, * btf member pointing to an int -type, * the int type has ``BTF_INT_OFFSET() = 2`` and ``BTF_INT_BITS() = 4`` +for this int. For example, a bitfield struct member has: + * btf member bit offset 100 from the start of the structure, + * btf member pointing to an int type, + * the int type has ``BTF_INT_OFFSET() = 2`` and ``BTF_INT_BITS() = 4`` Then in the struct memory layout, this member will occupy ``4`` bits starting from bits ``100 + 2 = 102``. Alternatively, the bitfield struct member can be the following to access the same bits as the above: - * btf member bit offset 102, * btf member pointing to an int type, * the int type has ``BTF_INT_OFFSET() = 0`` and ``BTF_INT_BITS() = 4`` diff --git a/Documentation/devicetree/bindings/arm/cpus.yaml b/Documentation/devicetree/bindings/arm/cpus.yaml index 365dcf384d73..82dd7582e945 100644 --- a/Documentation/devicetree/bindings/arm/cpus.yaml +++ b/Documentation/devicetree/bindings/arm/cpus.yaml @@ -228,7 +228,7 @@ patternProperties: - renesas,r9a06g032-smp - rockchip,rk3036-smp - rockchip,rk3066-smp - - socionext,milbeaut-m10v-smp + - socionext,milbeaut-m10v-smp - ste,dbx500-smp cpu-release-addr: diff --git a/Documentation/devicetree/bindings/hwmon/adc128d818.txt b/Documentation/devicetree/bindings/hwmon/adc128d818.txt index 08bab0e94d25..d0ae46d7bac3 100644 --- a/Documentation/devicetree/bindings/hwmon/adc128d818.txt +++ b/Documentation/devicetree/bindings/hwmon/adc128d818.txt @@ -26,7 +26,7 @@ Required node properties: Optional node properties: - - ti,mode: Operation mode (see above). + - ti,mode: Operation mode (u8) (see above). Example (operation mode 2): @@ -34,5 +34,5 @@ Example (operation mode 2): adc128d818@1d { compatible = "ti,adc128d818"; reg = <0x1d>; - ti,mode = <2>; + ti,mode = /bits/ 8 <2>; }; diff --git a/Documentation/devicetree/bindings/i2c/i2c-xscale.txt b/Documentation/devicetree/bindings/i2c/i2c-iop3xx.txt index dcc8390e0d24..dcc8390e0d24 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-xscale.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-iop3xx.txt diff --git a/Documentation/devicetree/bindings/i2c/i2c-mtk.txt b/Documentation/devicetree/bindings/i2c/i2c-mt65xx.txt index ee4c32454198..ee4c32454198 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-mtk.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-mt65xx.txt diff --git a/Documentation/devicetree/bindings/i2c/i2c-st-ddci2c.txt b/Documentation/devicetree/bindings/i2c/i2c-stu300.txt index bd81a482634f..bd81a482634f 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-st-ddci2c.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-stu300.txt diff --git a/Documentation/devicetree/bindings/i2c/i2c-sunxi-p2wi.txt b/Documentation/devicetree/bindings/i2c/i2c-sun6i-p2wi.txt index 49df0053347a..49df0053347a 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-sunxi-p2wi.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-sun6i-p2wi.txt diff --git a/Documentation/devicetree/bindings/i2c/i2c-vt8500.txt b/Documentation/devicetree/bindings/i2c/i2c-wmt.txt index 94a425eaa6c7..94a425eaa6c7 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-vt8500.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-wmt.txt diff --git a/Documentation/devicetree/bindings/net/davinci_emac.txt b/Documentation/devicetree/bindings/net/davinci_emac.txt index 24c5cdaba8d2..ca83dcc84fb8 100644 --- a/Documentation/devicetree/bindings/net/davinci_emac.txt +++ b/Documentation/devicetree/bindings/net/davinci_emac.txt @@ -20,6 +20,8 @@ Required properties: Optional properties: - phy-handle: See ethernet.txt file in the same directory. If absent, davinci_emac driver defaults to 100/FULL. +- nvmem-cells: phandle, reference to an nvmem node for the MAC address +- nvmem-cell-names: string, should be "mac-address" if nvmem is to be used - ti,davinci-rmii-en: 1 byte, 1 means use RMII - ti,davinci-no-bd-ram: boolean, does EMAC have BD RAM? diff --git a/Documentation/devicetree/bindings/net/dsa/qca8k.txt b/Documentation/devicetree/bindings/net/dsa/qca8k.txt index bbcb255c3150..93a7469e70d4 100644 --- a/Documentation/devicetree/bindings/net/dsa/qca8k.txt +++ b/Documentation/devicetree/bindings/net/dsa/qca8k.txt @@ -12,10 +12,15 @@ Required properties: Subnodes: The integrated switch subnode should be specified according to the binding -described in dsa/dsa.txt. As the QCA8K switches do not have a N:N mapping of -port and PHY id, each subnode describing a port needs to have a valid phandle -referencing the internal PHY connected to it. The CPU port of this switch is -always port 0. +described in dsa/dsa.txt. If the QCA8K switch is connect to a SoC's external +mdio-bus each subnode describing a port needs to have a valid phandle +referencing the internal PHY it is connected to. This is because there's no +N:N mapping of port and PHY id. + +Don't use mixed external and internal mdio-bus configurations, as this is +not supported by the hardware. + +The CPU port of this switch is always port 0. A CPU port node has the following optional node: @@ -31,8 +36,9 @@ For QCA8K the 'fixed-link' sub-node supports only the following properties: - 'full-duplex' (boolean, optional), to indicate that full duplex is used. When absent, half duplex is assumed. -Example: +Examples: +for the external mdio-bus configuration: &mdio0 { phy_port1: phy@0 { @@ -55,12 +61,12 @@ Example: reg = <4>; }; - switch0@0 { + switch@10 { compatible = "qca,qca8337"; #address-cells = <1>; #size-cells = <0>; - reg = <0>; + reg = <0x10>; ports { #address-cells = <1>; @@ -108,3 +114,56 @@ Example: }; }; }; + +for the internal master mdio-bus configuration: + + &mdio0 { + switch@10 { + compatible = "qca,qca8337"; + #address-cells = <1>; + #size-cells = <0>; + + reg = <0x10>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + label = "cpu"; + ethernet = <&gmac1>; + phy-mode = "rgmii"; + fixed-link { + speed = 1000; + full-duplex; + }; + }; + + port@1 { + reg = <1>; + label = "lan1"; + }; + + port@2 { + reg = <2>; + label = "lan2"; + }; + + port@3 { + reg = <3>; + label = "lan3"; + }; + + port@4 { + reg = <4>; + label = "lan4"; + }; + + port@5 { + reg = <5>; + label = "wan"; + }; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/net/ethernet.txt b/Documentation/devicetree/bindings/net/ethernet.txt index cfc376bc977a..a68621580584 100644 --- a/Documentation/devicetree/bindings/net/ethernet.txt +++ b/Documentation/devicetree/bindings/net/ethernet.txt @@ -10,15 +10,14 @@ Documentation/devicetree/bindings/phy/phy-bindings.txt. the boot program; should be used in cases where the MAC address assigned to the device by the boot program is different from the "local-mac-address" property; -- nvmem-cells: phandle, reference to an nvmem node for the MAC address; -- nvmem-cell-names: string, should be "mac-address" if nvmem is to be used; - max-speed: number, specifies maximum speed in Mbit/s supported by the device; - max-frame-size: number, maximum transfer unit (IEEE defined MTU), rather than the maximum frame size (there's contradiction in the Devicetree Specification). - phy-mode: string, operation mode of the PHY interface. This is now a de-facto standard property; supported values are: - * "internal" + * "internal" (Internal means there is not a standard bus between the MAC and + the PHY, something proprietary is being used to embed the PHY in the MAC.) * "mii" * "gmii" * "sgmii" diff --git a/Documentation/devicetree/bindings/net/macb.txt b/Documentation/devicetree/bindings/net/macb.txt index 174f292d8a3e..8b80515729d7 100644 --- a/Documentation/devicetree/bindings/net/macb.txt +++ b/Documentation/devicetree/bindings/net/macb.txt @@ -26,6 +26,10 @@ Required properties: Optional elements: 'tsu_clk' - clocks: Phandles to input clocks. +Optional properties: +- nvmem-cells: phandle, reference to an nvmem node for the MAC address +- nvmem-cell-names: string, should be "mac-address" if nvmem is to be used + Optional properties for PHY child node: - reset-gpios : Should specify the gpio for phy reset - magic-packet : If present, indicates that the hardware supports waking diff --git a/Documentation/devicetree/bindings/serial/mtk-uart.txt b/Documentation/devicetree/bindings/serial/mtk-uart.txt index 742cb470595b..bcfb13194f16 100644 --- a/Documentation/devicetree/bindings/serial/mtk-uart.txt +++ b/Documentation/devicetree/bindings/serial/mtk-uart.txt @@ -16,6 +16,7 @@ Required properties: * "mediatek,mt8127-uart" for MT8127 compatible UARTS * "mediatek,mt8135-uart" for MT8135 compatible UARTS * "mediatek,mt8173-uart" for MT8173 compatible UARTS + * "mediatek,mt8183-uart", "mediatek,mt6577-uart" for MT8183 compatible UARTS * "mediatek,mt6577-uart" for MT6577 and all of the above - reg: The base address of the UART register bank. diff --git a/Documentation/driver-api/usb/power-management.rst b/Documentation/driver-api/usb/power-management.rst index 79beb807996b..4a74cf6f2797 100644 --- a/Documentation/driver-api/usb/power-management.rst +++ b/Documentation/driver-api/usb/power-management.rst @@ -370,11 +370,15 @@ autosuspend the interface's device. When the usage counter is = 0 then the interface is considered to be idle, and the kernel may autosuspend the device. -Drivers need not be concerned about balancing changes to the usage -counter; the USB core will undo any remaining "get"s when a driver -is unbound from its interface. As a corollary, drivers must not call -any of the ``usb_autopm_*`` functions after their ``disconnect`` -routine has returned. +Drivers must be careful to balance their overall changes to the usage +counter. Unbalanced "get"s will remain in effect when a driver is +unbound from its interface, preventing the device from going into +runtime suspend should the interface be bound to a driver again. On +the other hand, drivers are allowed to achieve this balance by calling +the ``usb_autopm_*`` functions even after their ``disconnect`` routine +has returned -- say from within a work-queue routine -- provided they +retain an active reference to the interface (via ``usb_get_intf`` and +``usb_put_intf``). Drivers using the async routines are responsible for their own synchronization and mutual exclusion. diff --git a/Documentation/filesystems/mount_api.txt b/Documentation/filesystems/mount_api.txt index 944d1965e917..00ff0cfccfa7 100644 --- a/Documentation/filesystems/mount_api.txt +++ b/Documentation/filesystems/mount_api.txt @@ -12,11 +12,13 @@ CONTENTS (4) Filesystem context security. - (5) VFS filesystem context operations. + (5) VFS filesystem context API. - (6) Parameter description. + (6) Superblock creation helpers. - (7) Parameter helper functions. + (7) Parameter description. + + (8) Parameter helper functions. ======== @@ -41,12 +43,15 @@ The creation of new mounts is now to be done in a multistep process: (7) Destroy the context. -To support this, the file_system_type struct gains a new field: +To support this, the file_system_type struct gains two new fields: int (*init_fs_context)(struct fs_context *fc); + const struct fs_parameter_description *parameters; -which is invoked to set up the filesystem-specific parts of a filesystem -context, including the additional space. +The first is invoked to set up the filesystem-specific parts of a filesystem +context, including the additional space, and the second points to the +parameter description for validation at registration time and querying by a +future system call. Note that security initialisation is done *after* the filesystem is called so that the namespaces may be adjusted first. @@ -73,9 +78,9 @@ context. This is represented by the fs_context structure: void *s_fs_info; unsigned int sb_flags; unsigned int sb_flags_mask; + unsigned int s_iflags; + unsigned int lsm_flags; enum fs_context_purpose purpose:8; - bool sloppy:1; - bool silent:1; ... }; @@ -141,6 +146,10 @@ The fs_context fields are as follows: Which bits SB_* flags are to be set/cleared in super_block::s_flags. + (*) unsigned int s_iflags + + These will be bitwise-OR'd with s->s_iflags when a superblock is created. + (*) enum fs_context_purpose This indicates the purpose for which the context is intended. The @@ -150,17 +159,6 @@ The fs_context fields are as follows: FS_CONTEXT_FOR_SUBMOUNT -- New automatic submount of extant mount FS_CONTEXT_FOR_RECONFIGURE -- Change an existing mount - (*) bool sloppy - (*) bool silent - - These are set if the sloppy or silent mount options are given. - - [NOTE] sloppy is probably unnecessary when userspace passes over one - option at a time since the error can just be ignored if userspace deems it - to be unimportant. - - [NOTE] silent is probably redundant with sb_flags & SB_SILENT. - The mount context is created by calling vfs_new_fs_context() or vfs_dup_fs_context() and is destroyed with put_fs_context(). Note that the structure is not refcounted. @@ -342,28 +340,47 @@ number of operations used by the new mount code for this purpose: It should return 0 on success or a negative error code on failure. -================================= -VFS FILESYSTEM CONTEXT OPERATIONS -================================= +========================== +VFS FILESYSTEM CONTEXT API +========================== -There are four operations for creating a filesystem context and -one for destroying a context: +There are four operations for creating a filesystem context and one for +destroying a context: - (*) struct fs_context *vfs_new_fs_context(struct file_system_type *fs_type, - struct dentry *reference, - unsigned int sb_flags, - unsigned int sb_flags_mask, - enum fs_context_purpose purpose); + (*) struct fs_context *fs_context_for_mount( + struct file_system_type *fs_type, + unsigned int sb_flags); - Create a filesystem context for a given filesystem type and purpose. This - allocates the filesystem context, sets the superblock flags, initialises - the security and calls fs_type->init_fs_context() to initialise the - filesystem private data. + Allocate a filesystem context for the purpose of setting up a new mount, + whether that be with a new superblock or sharing an existing one. This + sets the superblock flags, initialises the security and calls + fs_type->init_fs_context() to initialise the filesystem private data. - reference can be NULL or it may indicate the root dentry of a superblock - that is going to be reconfigured (FS_CONTEXT_FOR_RECONFIGURE) or - the automount point that triggered a submount (FS_CONTEXT_FOR_SUBMOUNT). - This is provided as a source of namespace information. + fs_type specifies the filesystem type that will manage the context and + sb_flags presets the superblock flags stored therein. + + (*) struct fs_context *fs_context_for_reconfigure( + struct dentry *dentry, + unsigned int sb_flags, + unsigned int sb_flags_mask); + + Allocate a filesystem context for the purpose of reconfiguring an + existing superblock. dentry provides a reference to the superblock to be + configured. sb_flags and sb_flags_mask indicate which superblock flags + need changing and to what. + + (*) struct fs_context *fs_context_for_submount( + struct file_system_type *fs_type, + struct dentry *reference); + + Allocate a filesystem context for the purpose of creating a new mount for + an automount point or other derived superblock. fs_type specifies the + filesystem type that will manage the context and the reference dentry + supplies the parameters. Namespaces are propagated from the reference + dentry's superblock also. + + Note that it's not a requirement that the reference dentry be of the same + filesystem type as fs_type. (*) struct fs_context *vfs_dup_fs_context(struct fs_context *src_fc); @@ -390,20 +407,6 @@ context pointer or a negative error code. For the remaining operations, if an error occurs, a negative error code will be returned. - (*) int vfs_get_tree(struct fs_context *fc); - - Get or create the mountable root and superblock, using the parameters in - the filesystem context to select/configure the superblock. This invokes - the ->validate() op and then the ->get_tree() op. - - [NOTE] ->validate() could perhaps be rolled into ->get_tree() and - ->reconfigure(). - - (*) struct vfsmount *vfs_create_mount(struct fs_context *fc); - - Create a mount given the parameters in the specified filesystem context. - Note that this does not attach the mount to anything. - (*) int vfs_parse_fs_param(struct fs_context *fc, struct fs_parameter *param); @@ -432,17 +435,80 @@ returned. clear the pointer, but then becomes responsible for disposing of the object. - (*) int vfs_parse_fs_string(struct fs_context *fc, char *key, + (*) int vfs_parse_fs_string(struct fs_context *fc, const char *key, const char *value, size_t v_size); - A wrapper around vfs_parse_fs_param() that just passes a constant string. + A wrapper around vfs_parse_fs_param() that copies the value string it is + passed. (*) int generic_parse_monolithic(struct fs_context *fc, void *data); Parse a sys_mount() data page, assuming the form to be a text list consisting of key[=val] options separated by commas. Each item in the list is passed to vfs_mount_option(). This is the default when the - ->parse_monolithic() operation is NULL. + ->parse_monolithic() method is NULL. + + (*) int vfs_get_tree(struct fs_context *fc); + + Get or create the mountable root and superblock, using the parameters in + the filesystem context to select/configure the superblock. This invokes + the ->get_tree() method. + + (*) struct vfsmount *vfs_create_mount(struct fs_context *fc); + + Create a mount given the parameters in the specified filesystem context. + Note that this does not attach the mount to anything. + + +=========================== +SUPERBLOCK CREATION HELPERS +=========================== + +A number of VFS helpers are available for use by filesystems for the creation +or looking up of superblocks. + + (*) struct super_block * + sget_fc(struct fs_context *fc, + int (*test)(struct super_block *sb, struct fs_context *fc), + int (*set)(struct super_block *sb, struct fs_context *fc)); + + This is the core routine. If test is non-NULL, it searches for an + existing superblock matching the criteria held in the fs_context, using + the test function to match them. If no match is found, a new superblock + is created and the set function is called to set it up. + + Prior to the set function being called, fc->s_fs_info will be transferred + to sb->s_fs_info - and fc->s_fs_info will be cleared if set returns + success (ie. 0). + +The following helpers all wrap sget_fc(): + + (*) int vfs_get_super(struct fs_context *fc, + enum vfs_get_super_keying keying, + int (*fill_super)(struct super_block *sb, + struct fs_context *fc)) + + This creates/looks up a deviceless superblock. The keying indicates how + many superblocks of this type may exist and in what manner they may be + shared: + + (1) vfs_get_single_super + + Only one such superblock may exist in the system. Any further + attempt to get a new superblock gets this one (and any parameter + differences are ignored). + + (2) vfs_get_keyed_super + + Multiple superblocks of this type may exist and they're keyed on + their s_fs_info pointer (for example this may refer to a + namespace). + + (3) vfs_get_independent_super + + Multiple independent superblocks of this type may exist. This + function never matches an existing one and always creates a new + one. ===================== @@ -454,35 +520,22 @@ There's a core description struct that links everything together: struct fs_parameter_description { const char name[16]; - u8 nr_params; - u8 nr_alt_keys; - u8 nr_enums; - bool ignore_unknown; - bool no_source; - const char *const *keys; - const struct constant_table *alt_keys; const struct fs_parameter_spec *specs; const struct fs_parameter_enum *enums; }; For example: - enum afs_param { + enum { Opt_autocell, Opt_bar, Opt_dyn, Opt_foo, Opt_source, - nr__afs_params }; static const struct fs_parameter_description afs_fs_parameters = { .name = "kAFS", - .nr_params = nr__afs_params, - .nr_alt_keys = ARRAY_SIZE(afs_param_alt_keys), - .nr_enums = ARRAY_SIZE(afs_param_enums), - .keys = afs_param_keys, - .alt_keys = afs_param_alt_keys, .specs = afs_param_specs, .enums = afs_param_enums, }; @@ -494,28 +547,24 @@ The members are as follows: The name to be used in error messages generated by the parse helper functions. - (2) u8 nr_params; - - The number of discrete parameter identifiers. This indicates the number - of elements in the ->types[] array and also limits the values that may be - used in the values that the ->keys[] array maps to. - - It is expected that, for example, two parameters that are related, say - "acl" and "noacl" with have the same ID, but will be flagged to indicate - that one is the inverse of the other. The value can then be picked out - from the parse result. + (2) const struct fs_parameter_specification *specs; - (3) const struct fs_parameter_specification *specs; + Table of parameter specifications, terminated with a null entry, where the + entries are of type: - Table of parameter specifications, where the entries are of type: - - struct fs_parameter_type { - enum fs_parameter_spec type:8; - u8 flags; + struct fs_parameter_spec { + const char *name; + u8 opt; + enum fs_parameter_type type:8; + unsigned short flags; }; - and the parameter identifier is the index to the array. 'type' indicates - the desired value type and must be one of: + The 'name' field is a string to match exactly to the parameter key (no + wildcards, patterns and no case-independence) and 'opt' is the value that + will be returned by the fs_parser() function in the case of a successful + match. + + The 'type' field indicates the desired value type and must be one of: TYPE NAME EXPECTED VALUE RESULT IN ======================= ======================= ===================== @@ -525,85 +574,65 @@ The members are as follows: fs_param_is_u32_octal 32-bit octal int result->uint_32 fs_param_is_u32_hex 32-bit hex int result->uint_32 fs_param_is_s32 32-bit signed int result->int_32 + fs_param_is_u64 64-bit unsigned int result->uint_64 fs_param_is_enum Enum value name result->uint_32 fs_param_is_string Arbitrary string param->string fs_param_is_blob Binary blob param->blob fs_param_is_blockdev Blockdev path * Needs lookup fs_param_is_path Path * Needs lookup - fs_param_is_fd File descriptor param->file - - And each parameter can be qualified with 'flags': - - fs_param_v_optional The value is optional - fs_param_neg_with_no If key name is prefixed with "no", it is false - fs_param_neg_with_empty If value is "", it is false - fs_param_deprecated The parameter is deprecated. - - For example: - - static const struct fs_parameter_spec afs_param_specs[nr__afs_params] = { - [Opt_autocell] = { fs_param_is flag }, - [Opt_bar] = { fs_param_is_enum }, - [Opt_dyn] = { fs_param_is flag }, - [Opt_foo] = { fs_param_is_bool, fs_param_neg_with_no }, - [Opt_source] = { fs_param_is_string }, - }; + fs_param_is_fd File descriptor result->int_32 Note that if the value is of fs_param_is_bool type, fs_parse() will try to match any string value against "0", "1", "no", "yes", "false", "true". - [!] NOTE that the table must be sorted according to primary key name so - that ->keys[] is also sorted. - - (4) const char *const *keys; - - Table of primary key names for the parameters. There must be one entry - per defined parameter. The table is optional if ->nr_params is 0. The - table is just an array of names e.g.: + Each parameter can also be qualified with 'flags': - static const char *const afs_param_keys[nr__afs_params] = { - [Opt_autocell] = "autocell", - [Opt_bar] = "bar", - [Opt_dyn] = "dyn", - [Opt_foo] = "foo", - [Opt_source] = "source", - }; - - [!] NOTE that the table must be sorted such that the table can be searched - with bsearch() using strcmp(). This means that the Opt_* values must - correspond to the entries in this table. - - (5) const struct constant_table *alt_keys; - u8 nr_alt_keys; - - Table of additional key names and their mappings to parameter ID plus the - number of elements in the table. This is optional. The table is just an - array of { name, integer } pairs, e.g.: + fs_param_v_optional The value is optional + fs_param_neg_with_no result->negated set if key is prefixed with "no" + fs_param_neg_with_empty result->negated set if value is "" + fs_param_deprecated The parameter is deprecated. - static const struct constant_table afs_param_keys[] = { - { "baz", Opt_bar }, - { "dynamic", Opt_dyn }, + These are wrapped with a number of convenience wrappers: + + MACRO SPECIFIES + ======================= =============================================== + fsparam_flag() fs_param_is_flag + fsparam_flag_no() fs_param_is_flag, fs_param_neg_with_no + fsparam_bool() fs_param_is_bool + fsparam_u32() fs_param_is_u32 + fsparam_u32oct() fs_param_is_u32_octal + fsparam_u32hex() fs_param_is_u32_hex + fsparam_s32() fs_param_is_s32 + fsparam_u64() fs_param_is_u64 + fsparam_enum() fs_param_is_enum + fsparam_string() fs_param_is_string + fsparam_blob() fs_param_is_blob + fsparam_bdev() fs_param_is_blockdev + fsparam_path() fs_param_is_path + fsparam_fd() fs_param_is_fd + + all of which take two arguments, name string and option number - for + example: + + static const struct fs_parameter_spec afs_param_specs[] = { + fsparam_flag ("autocell", Opt_autocell), + fsparam_flag ("dyn", Opt_dyn), + fsparam_string ("source", Opt_source), + fsparam_flag_no ("foo", Opt_foo), + {} }; - [!] NOTE that the table must be sorted such that strcmp() can be used with - bsearch() to search the entries. - - The parameter ID can also be fs_param_key_removed to indicate that a - deprecated parameter has been removed and that an error will be given. - This differs from fs_param_deprecated where the parameter may still have - an effect. - - Further, the behaviour of the parameter may differ when an alternate name - is used (for instance with NFS, "v3", "v4.2", etc. are alternate names). + An addition macro, __fsparam() is provided that takes an additional pair + of arguments to specify the type and the flags for anything that doesn't + match one of the above macros. (6) const struct fs_parameter_enum *enums; - u8 nr_enums; - Table of enum value names to integer mappings and the number of elements - stored therein. This is of type: + Table of enum value names to integer mappings, terminated with a null + entry. This is of type: struct fs_parameter_enum { - u8 param_id; + u8 opt; char name[14]; u8 value; }; @@ -621,11 +650,6 @@ The members are as follows: try to look the value up in the enum table and the result will be stored in the parse result. - (7) bool no_source; - - If this is set, fs_parse() will ignore any "source" parameter and not - pass it to the filesystem. - The parser should be pointed to by the parser pointer in the file_system_type struct as this will provide validation on registration (if CONFIG_VALIDATE_FS_PARSER=y) and will allow the description to be queried from @@ -650,9 +674,8 @@ process the parameters it is given. int value; }; - and it must be sorted such that it can be searched using bsearch() using - strcmp(). If a match is found, the corresponding value is returned. If a - match isn't found, the not_found value is returned instead. + If a match is found, the corresponding value is returned. If a match + isn't found, the not_found value is returned instead. (*) bool validate_constant_table(const struct constant_table *tbl, size_t tbl_size, @@ -665,36 +688,36 @@ process the parameters it is given. should just be set to lie inside the low-to-high range. If all is good, true is returned. If the table is invalid, errors are - logged to dmesg, the stack is dumped and false is returned. + logged to dmesg and false is returned. + + (*) bool fs_validate_description(const struct fs_parameter_description *desc); + + This performs some validation checks on a parameter description. It + returns true if the description is good and false if it is not. It will + log errors to dmesg if validation fails. (*) int fs_parse(struct fs_context *fc, - const struct fs_param_parser *parser, + const struct fs_parameter_description *desc, struct fs_parameter *param, - struct fs_param_parse_result *result); + struct fs_parse_result *result); This is the main interpreter of parameters. It uses the parameter - description (parser) to look up the name of the parameter to use and to - convert that to a parameter ID (stored in result->key). + description to look up a parameter by key name and to convert that to an + option number (which it returns). If successful, and if the parameter type indicates the result is a boolean, integer or enum type, the value is converted by this function and - the result stored in result->{boolean,int_32,uint_32}. + the result stored in result->{boolean,int_32,uint_32,uint_64}. If a match isn't initially made, the key is prefixed with "no" and no value is present then an attempt will be made to look up the key with the prefix removed. If this matches a parameter for which the type has flag - fs_param_neg_with_no set, then a match will be made and the value will be - set to false/0/NULL. - - If the parameter is successfully matched and, optionally, parsed - correctly, 1 is returned. If the parameter isn't matched and - parser->ignore_unknown is set, then 0 is returned. Otherwise -EINVAL is - returned. - - (*) bool fs_validate_description(const struct fs_parameter_description *desc); + fs_param_neg_with_no set, then a match will be made and result->negated + will be set to true. - This is validates the parameter description. It returns true if the - description is good and false if it is not. + If the parameter isn't matched, -ENOPARAM will be returned; if the + parameter is matched, but the value is erroneous, -EINVAL will be + returned; otherwise the parameter's option number will be returned. (*) int fs_lookup_param(struct fs_context *fc, struct fs_parameter *value, diff --git a/Documentation/i2c/busses/i2c-i801 b/Documentation/i2c/busses/i2c-i801 index d1ee484a787d..ee9984f35868 100644 --- a/Documentation/i2c/busses/i2c-i801 +++ b/Documentation/i2c/busses/i2c-i801 @@ -36,6 +36,7 @@ Supported adapters: * Intel Cannon Lake (PCH) * Intel Cedar Fork (PCH) * Intel Ice Lake (PCH) + * Intel Comet Lake (PCH) Datasheets: Publicly available at the Intel website On Intel Patsburg and later chipsets, both the normal host SMBus controller diff --git a/Documentation/lzo.txt b/Documentation/lzo.txt index f79934225d8d..ca983328976b 100644 --- a/Documentation/lzo.txt +++ b/Documentation/lzo.txt @@ -102,9 +102,11 @@ Byte sequences dictionary which is empty, and that it will always be invalid at this place. - 17 : bitstream version. If the first byte is 17, the next byte - gives the bitstream version (version 1 only). If the first byte - is not 17, the bitstream version is 0. + 17 : bitstream version. If the first byte is 17, and compressed + stream length is at least 5 bytes (length of shortest possible + versioned bitstream), the next byte gives the bitstream version + (version 1 only). + Otherwise, the bitstream version is 0. 18..21 : copy 0..3 literals state = (byte - 17) = 0..3 [ copy <state> literals ] diff --git a/Documentation/media/uapi/rc/rc-tables.rst b/Documentation/media/uapi/rc/rc-tables.rst index f460031d8531..177ac44fa0fa 100644 --- a/Documentation/media/uapi/rc/rc-tables.rst +++ b/Documentation/media/uapi/rc/rc-tables.rst @@ -623,7 +623,7 @@ the remote via /dev/input/event devices. - .. row 78 - - ``KEY_SCREEN`` + - ``KEY_ASPECT_RATIO`` - Select screen aspect ratio @@ -631,7 +631,7 @@ the remote via /dev/input/event devices. - .. row 79 - - ``KEY_ZOOM`` + - ``KEY_FULL_SCREEN`` - Put device into zoom/full screen mode diff --git a/Documentation/networking/bpf_flow_dissector.rst b/Documentation/networking/bpf_flow_dissector.rst new file mode 100644 index 000000000000..b375ae2ec2c4 --- /dev/null +++ b/Documentation/networking/bpf_flow_dissector.rst @@ -0,0 +1,126 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================== +BPF Flow Dissector +================== + +Overview +======== + +Flow dissector is a routine that parses metadata out of the packets. It's +used in the various places in the networking subsystem (RFS, flow hash, etc). + +BPF flow dissector is an attempt to reimplement C-based flow dissector logic +in BPF to gain all the benefits of BPF verifier (namely, limits on the +number of instructions and tail calls). + +API +=== + +BPF flow dissector programs operate on an ``__sk_buff``. However, only the +limited set of fields is allowed: ``data``, ``data_end`` and ``flow_keys``. +``flow_keys`` is ``struct bpf_flow_keys`` and contains flow dissector input +and output arguments. + +The inputs are: + * ``nhoff`` - initial offset of the networking header + * ``thoff`` - initial offset of the transport header, initialized to nhoff + * ``n_proto`` - L3 protocol type, parsed out of L2 header + +Flow dissector BPF program should fill out the rest of the ``struct +bpf_flow_keys`` fields. Input arguments ``nhoff/thoff/n_proto`` should be +also adjusted accordingly. + +The return code of the BPF program is either BPF_OK to indicate successful +dissection, or BPF_DROP to indicate parsing error. + +__sk_buff->data +=============== + +In the VLAN-less case, this is what the initial state of the BPF flow +dissector looks like:: + + +------+------+------------+-----------+ + | DMAC | SMAC | ETHER_TYPE | L3_HEADER | + +------+------+------------+-----------+ + ^ + | + +-- flow dissector starts here + + +.. code:: c + + skb->data + flow_keys->nhoff point to the first byte of L3_HEADER + flow_keys->thoff = nhoff + flow_keys->n_proto = ETHER_TYPE + +In case of VLAN, flow dissector can be called with the two different states. + +Pre-VLAN parsing:: + + +------+------+------+-----+-----------+-----------+ + | DMAC | SMAC | TPID | TCI |ETHER_TYPE | L3_HEADER | + +------+------+------+-----+-----------+-----------+ + ^ + | + +-- flow dissector starts here + +.. code:: c + + skb->data + flow_keys->nhoff point the to first byte of TCI + flow_keys->thoff = nhoff + flow_keys->n_proto = TPID + +Please note that TPID can be 802.1AD and, hence, BPF program would +have to parse VLAN information twice for double tagged packets. + + +Post-VLAN parsing:: + + +------+------+------+-----+-----------+-----------+ + | DMAC | SMAC | TPID | TCI |ETHER_TYPE | L3_HEADER | + +------+------+------+-----+-----------+-----------+ + ^ + | + +-- flow dissector starts here + +.. code:: c + + skb->data + flow_keys->nhoff point the to first byte of L3_HEADER + flow_keys->thoff = nhoff + flow_keys->n_proto = ETHER_TYPE + +In this case VLAN information has been processed before the flow dissector +and BPF flow dissector is not required to handle it. + + +The takeaway here is as follows: BPF flow dissector program can be called with +the optional VLAN header and should gracefully handle both cases: when single +or double VLAN is present and when it is not present. The same program +can be called for both cases and would have to be written carefully to +handle both cases. + + +Reference Implementation +======================== + +See ``tools/testing/selftests/bpf/progs/bpf_flow.c`` for the reference +implementation and ``tools/testing/selftests/bpf/flow_dissector_load.[hc]`` +for the loader. bpftool can be used to load BPF flow dissector program as well. + +The reference implementation is organized as follows: + * ``jmp_table`` map that contains sub-programs for each supported L3 protocol + * ``_dissect`` routine - entry point; it does input ``n_proto`` parsing and + does ``bpf_tail_call`` to the appropriate L3 handler + +Since BPF at this point doesn't support looping (or any jumping back), +jmp_table is used instead to handle multiple levels of encapsulation (and +IPv6 options). + + +Current Limitations +=================== +BPF flow dissector doesn't support exporting all the metadata that in-kernel +C-based implementation can export. Notable example is single VLAN (802.1Q) +and double VLAN (802.1AD) tags. Please refer to the ``struct bpf_flow_keys`` +for a set of information that's currently can be exported from the BPF context. diff --git a/Documentation/networking/decnet.txt b/Documentation/networking/decnet.txt index e12a4900cf72..d192f8b9948b 100644 --- a/Documentation/networking/decnet.txt +++ b/Documentation/networking/decnet.txt @@ -22,8 +22,6 @@ you'll need the following options as well... CONFIG_DECNET_ROUTER (to be able to add/delete routes) CONFIG_NETFILTER (will be required for the DECnet routing daemon) - CONFIG_DECNET_ROUTE_FWMARK is optional - Don't turn on SIOCGIFCONF support for DECnet unless you are really sure that you need it, in general you won't and it can cause ifconfig to malfunction. diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index 5449149be496..984e68f9e026 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -9,6 +9,7 @@ Contents: netdev-FAQ af_xdp batman-adv + bpf_flow_dissector can can_ucan_protocol device_drivers/freescale/dpaa2/index diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index acdfb5d2bcaa..c4ac35234f05 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -422,6 +422,7 @@ tcp_min_rtt_wlen - INTEGER minimum RTT when it is moved to a longer path (e.g., due to traffic engineering). A longer window makes the filter more resistant to RTT inflations such as transient congestion. The unit is seconds. + Possible values: 0 - 86400 (1 day) Default: 300 tcp_moderate_rcvbuf - BOOLEAN @@ -1336,6 +1337,7 @@ tag - INTEGER Default value is 0. xfrm4_gc_thresh - INTEGER + (Obsolete since linux-4.14) The threshold at which we will start garbage collecting for IPv4 destination cache entries. At twice this value the system will refuse new allocations. @@ -1919,6 +1921,7 @@ echo_ignore_all - BOOLEAN Default: 0 xfrm6_gc_thresh - INTEGER + (Obsolete since linux-4.14) The threshold at which we will start garbage collecting for IPv6 destination cache entries. At twice this value the system will refuse new allocations. diff --git a/Documentation/networking/msg_zerocopy.rst b/Documentation/networking/msg_zerocopy.rst index 18c1415e7bfa..ace56204dd03 100644 --- a/Documentation/networking/msg_zerocopy.rst +++ b/Documentation/networking/msg_zerocopy.rst @@ -50,7 +50,7 @@ the excellent reporting over at LWN.net or read the original code. patchset [PATCH net-next v4 0/9] socket sendmsg MSG_ZEROCOPY - http://lkml.kernel.org/r/20170803202945.70750-1-willemdebruijn.kernel@gmail.com + https://lkml.kernel.org/netdev/20170803202945.70750-1-willemdebruijn.kernel@gmail.com Interface diff --git a/Documentation/networking/netdev-FAQ.rst b/Documentation/networking/netdev-FAQ.rst index 0ac5fa77f501..642fa963be3c 100644 --- a/Documentation/networking/netdev-FAQ.rst +++ b/Documentation/networking/netdev-FAQ.rst @@ -131,6 +131,19 @@ 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. +Q: I made changes to only a few patches in a patch series should I resend only those changed? +--------------------------------------------------------------------------------------------- +A: No, please resend the entire patch series and make sure you do number your +patches such that it is clear this is the latest and greatest set of patches +that can be applied. + +Q: I submitted multiple versions of a patch series and it looks like a version other than the last one has been accepted, what should I do? +------------------------------------------------------------------------------------------------------------------------------------------- +A: There is no revert possible, once it is pushed out, it stays like that. +Please send incremental versions on top of what has been merged in order to fix +the patches the way they would look like if your latest patch series was to be +merged. + Q: How can I tell what patches are queued up for backporting to the various stable releases? -------------------------------------------------------------------------------------------- A: Normally Greg Kroah-Hartman collects stable commits himself, but for diff --git a/Documentation/networking/nf_flowtable.txt b/Documentation/networking/nf_flowtable.txt index 54128c50d508..ca2136c76042 100644 --- a/Documentation/networking/nf_flowtable.txt +++ b/Documentation/networking/nf_flowtable.txt @@ -44,10 +44,10 @@ including the Netfilter hooks and the flowtable fastpath bypass. / \ / \ |Routing | / \ --> ingress ---> prerouting ---> |decision| | postrouting |--> neigh_xmit \_________/ \__________/ ---------- \____________/ ^ - | ^ | | ^ | - flowtable | | ____\/___ | | - | | | / \ | | - __\/___ | --------->| forward |------------ | + | ^ | ^ | + flowtable | ____\/___ | | + | | / \ | | + __\/___ | | forward |------------ | |-----| | \_________/ | |-----| | 'flow offload' rule | |-----| | adds entry to | diff --git a/Documentation/networking/rxrpc.txt b/Documentation/networking/rxrpc.txt index 2df5894353d6..cd7303d7fa25 100644 --- a/Documentation/networking/rxrpc.txt +++ b/Documentation/networking/rxrpc.txt @@ -1009,16 +1009,18 @@ The kernel interface functions are as follows: (*) Check call still alive. - u32 rxrpc_kernel_check_life(struct socket *sock, - struct rxrpc_call *call); + bool rxrpc_kernel_check_life(struct socket *sock, + struct rxrpc_call *call, + u32 *_life); void rxrpc_kernel_probe_life(struct socket *sock, struct rxrpc_call *call); - The first function returns a number that is updated when ACKs are received - from the peer (notably including PING RESPONSE ACKs which we can elicit by - sending PING ACKs to see if the call still exists on the server). The - caller should compare the numbers of two calls to see if the call is still - alive after waiting for a suitable interval. + The first function passes back in *_life a number that is updated when + ACKs are received from the peer (notably including PING RESPONSE ACKs + which we can elicit by sending PING ACKs to see if the call still exists + on the server). The caller should compare the numbers of two calls to see + if the call is still alive after waiting for a suitable interval. It also + returns true as long as the call hasn't yet reached the completed state. This allows the caller to work out if the server is still contactable and if the call is still alive on the server while waiting for the server to diff --git a/Documentation/networking/snmp_counter.rst b/Documentation/networking/snmp_counter.rst index 52b026be028f..38a4edc4522b 100644 --- a/Documentation/networking/snmp_counter.rst +++ b/Documentation/networking/snmp_counter.rst @@ -413,7 +413,7 @@ algorithm. .. _F-RTO: https://tools.ietf.org/html/rfc5682 TCP Fast Path -============ +============= When kernel receives a TCP packet, it has two paths to handler the packet, one is fast path, another is slow path. The comment in kernel code provides a good explanation of them, I pasted them below:: @@ -681,6 +681,7 @@ The TCP stack receives an out of order duplicate packet, so it sends a DSACK to the sender. * TcpExtTCPDSACKRecv + The TCP stack receives a DSACK, which indicates an acknowledged duplicate packet is received. @@ -690,7 +691,7 @@ The TCP stack receives a DSACK, which indicate an out of order duplicate packet is received. invalid SACK and DSACK -==================== +====================== When a SACK (or DSACK) block is invalid, a corresponding counter would be updated. The validation method is base on the start/end sequence number of the SACK block. For more details, please refer the comment @@ -704,11 +705,13 @@ explaination: .. _Add counters for discarded SACK blocks: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=18f02545a9a16c9a89778b91a162ad16d510bb32 * TcpExtTCPSACKDiscard + This counter indicates how many SACK blocks are invalid. If the invalid SACK block is caused by ACK recording, the TCP stack will only ignore it and won't update this counter. * TcpExtTCPDSACKIgnoredOld and TcpExtTCPDSACKIgnoredNoUndo + When a DSACK block is invalid, one of these two counters would be updated. Which counter will be updated depends on the undo_marker flag of the TCP socket. If the undo_marker is not set, the TCP stack isn't @@ -719,7 +722,7 @@ will be updated. If the undo_marker is set, TcpExtTCPDSACKIgnoredOld will be updated. As implied in its name, it might be an old packet. SACK shift -========= +========== The linux networking stack stores data in sk_buff struct (skb for short). If a SACK block acrosses multiple skb, the TCP stack will try to re-arrange data in these skb. E.g. if a SACK block acknowledges seq @@ -730,12 +733,15 @@ seq 14 to 20. All data in skb2 will be moved to skb1, and skb2 will be discard, this operation is 'merge'. * TcpExtTCPSackShifted + A skb is shifted * TcpExtTCPSackMerged + A skb is merged * TcpExtTCPSackShiftFallback + A skb should be shifted or merged, but the TCP stack doesn't do it for some reasons. diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index 6af24cdb25cc..3f13d8599337 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -866,14 +866,14 @@ The intent is that compaction has less work to do in the future and to increase the success rate of future high-order allocations such as SLUB allocations, THP and hugetlbfs pages. -To make it sensible with respect to the watermark_scale_factor parameter, -the unit is in fractions of 10,000. The default value of 15,000 means -that up to 150% of the high watermark will be reclaimed in the event of -a pageblock being mixed due to fragmentation. The level of reclaim is -determined by the number of fragmentation events that occurred in the -recent past. If this value is smaller than a pageblock then a pageblocks -worth of pages will be reclaimed (e.g. 2MB on 64-bit x86). A boost factor -of 0 will disable the feature. +To make it sensible with respect to the watermark_scale_factor +parameter, the unit is in fractions of 10,000. The default value of +15,000 on !DISCONTIGMEM configurations means that up to 150% of the high +watermark will be reclaimed in the event of a pageblock being mixed due +to fragmentation. The level of reclaim is determined by the number of +fragmentation events that occurred in the recent past. If this value is +smaller than a pageblock then a pageblocks worth of pages will be reclaimed +(e.g. 2MB on 64-bit x86). A boost factor of 0 will disable the feature. ============================================================= diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 7de9eee73fcd..64b38dfcc243 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -5,25 +5,32 @@ The Definitive KVM (Kernel-based Virtual Machine) API Documentation ---------------------- The kvm API is a set of ioctls that are issued to control various aspects -of a virtual machine. The ioctls belong to three classes +of a virtual machine. The ioctls belong to three classes: - System ioctls: These query and set global attributes which affect the whole kvm subsystem. In addition a system ioctl is used to create - virtual machines + virtual machines. - VM ioctls: These query and set attributes that affect an entire virtual machine, for example memory layout. In addition a VM ioctl is used to - create virtual cpus (vcpus). + create virtual cpus (vcpus) and devices. - Only run VM ioctls from the same process (address space) that was used - to create the VM. + VM ioctls must be issued from the same process (address space) that was + used to create the VM. - vcpu ioctls: These query and set attributes that control the operation of a single virtual cpu. - Only run vcpu ioctls from the same thread that was used to create the - vcpu. + vcpu ioctls should be issued from the same thread that was used to create + the vcpu, except for asynchronous vcpu ioctl that are marked as such in + the documentation. Otherwise, the first ioctl after switching threads + could see a performance impact. + - device ioctls: These query and set attributes that control the operation + of a single device. + + device ioctls must be issued from the same process (address space) that + was used to create the VM. 2. File descriptors ------------------- @@ -32,17 +39,34 @@ The kvm API is centered around file descriptors. An initial open("/dev/kvm") obtains a handle to the kvm subsystem; this handle can be used to issue system ioctls. A KVM_CREATE_VM ioctl on this handle will create a VM file descriptor which can be used to issue VM -ioctls. A KVM_CREATE_VCPU ioctl on a VM fd will create a virtual cpu -and return a file descriptor pointing to it. Finally, ioctls on a vcpu -fd can be used to control the vcpu, including the important task of -actually running guest code. +ioctls. A KVM_CREATE_VCPU or KVM_CREATE_DEVICE ioctl on a VM fd will +create a virtual cpu or device and return a file descriptor pointing to +the new resource. Finally, ioctls on a vcpu or device fd can be used +to control the vcpu or device. For vcpus, this includes the important +task of actually running guest code. In general file descriptors can be migrated among processes by means of fork() and the SCM_RIGHTS facility of unix domain socket. These kinds of tricks are explicitly not supported by kvm. While they will not cause harm to the host, their actual behavior is not guaranteed by -the API. The only supported use is one virtual machine per process, -and one vcpu per thread. +the API. See "General description" for details on the ioctl usage +model that is supported by KVM. + +It is important to note that althought VM ioctls may only be issued from +the process that created the VM, a VM's lifecycle is associated with its +file descriptor, not its creator (process). In other words, the VM and +its resources, *including the associated address space*, are not freed +until the last reference to the VM's file descriptor has been released. +For example, if fork() is issued after ioctl(KVM_CREATE_VM), the VM will +not be freed until both the parent (original) process and its child have +put their references to the VM's file descriptor. + +Because a VM's resources are not freed until the last reference to its +file descriptor is released, creating additional references to a VM via +via fork(), dup(), etc... without careful consideration is strongly +discouraged and may have unwanted side effects, e.g. memory allocated +by and on behalf of the VM's process may not be freed/unaccounted when +the VM is shut down. It is important to note that althought VM ioctls may only be issued from @@ -297,7 +321,7 @@ cpu's hardware control block. 4.8 KVM_GET_DIRTY_LOG (vm ioctl) Capability: basic -Architectures: x86 +Architectures: all Type: vm ioctl Parameters: struct kvm_dirty_log (in/out) Returns: 0 on success, -1 on error @@ -515,11 +539,15 @@ c) KVM_INTERRUPT_SET_LEVEL Note that any value for 'irq' other than the ones stated above is invalid and incurs unexpected behavior. +This is an asynchronous vcpu ioctl and can be invoked from any thread. + MIPS: Queues an external interrupt to be injected into the virtual CPU. A negative interrupt number dequeues the interrupt. +This is an asynchronous vcpu ioctl and can be invoked from any thread. + 4.17 KVM_DEBUG_GUEST @@ -1086,14 +1114,12 @@ struct kvm_userspace_memory_region { #define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0) #define KVM_MEM_READONLY (1UL << 1) -This ioctl allows the user to create or modify a guest physical memory -slot. When changing an existing slot, it may be moved in the guest -physical memory space, or its flags may be modified. It may not be -resized. Slots may not overlap in guest physical address space. -Bits 0-15 of "slot" specifies the slot id and this value should be -less than the maximum number of user memory slots supported per VM. -The maximum allowed slots can be queried using KVM_CAP_NR_MEMSLOTS, -if this capability is supported by the architecture. +This ioctl allows the user to create, modify or delete a guest physical +memory slot. Bits 0-15 of "slot" specify the slot id and this value +should be less than the maximum number of user memory slots supported per +VM. The maximum allowed slots can be queried using KVM_CAP_NR_MEMSLOTS, +if this capability is supported by the architecture. Slots may not +overlap in guest physical address space. If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of "slot" specifies the address space which is being modified. They must be @@ -1102,6 +1128,10 @@ KVM_CAP_MULTI_ADDRESS_SPACE capability. Slots in separate address spaces are unrelated; the restriction on overlapping slots only applies within each address space. +Deleting a slot is done by passing zero for memory_size. When changing +an existing slot, it may be moved in the guest physical memory space, +or its flags may be modified, but it may not be resized. + Memory for the region is taken starting at the address denoted by the field userspace_addr, which must point at user addressable memory for the entire memory slot size. Any object may back this memory, including @@ -2493,7 +2523,7 @@ KVM_S390_MCHK (vm, vcpu) - machine check interrupt; cr 14 bits in parm, machine checks needing further payload are not supported by this ioctl) -Note that the vcpu ioctl is asynchronous to vcpu execution. +This is an asynchronous vcpu ioctl and can be invoked from any thread. 4.78 KVM_PPC_GET_HTAB_FD @@ -3042,8 +3072,7 @@ KVM_S390_INT_EMERGENCY - sigp emergency; parameters in .emerg KVM_S390_INT_EXTERNAL_CALL - sigp external call; parameters in .extcall KVM_S390_MCHK - machine check interrupt; parameters in .mchk - -Note that the vcpu ioctl is asynchronous to vcpu execution. +This is an asynchronous vcpu ioctl and can be invoked from any thread. 4.94 KVM_S390_GET_IRQ_STATE @@ -3781,7 +3810,7 @@ to I/O ports. 4.117 KVM_CLEAR_DIRTY_LOG (vm ioctl) Capability: KVM_CAP_MANUAL_DIRTY_LOG_PROTECT -Architectures: x86 +Architectures: x86, arm, arm64, mips Type: vm ioctl Parameters: struct kvm_dirty_log (in) Returns: 0 on success, -1 on error @@ -3801,8 +3830,9 @@ The ioctl clears the dirty status of pages in a memory slot, according to the bitmap that is passed in struct kvm_clear_dirty_log's dirty_bitmap field. Bit 0 of the bitmap corresponds to page "first_page" in the memory slot, and num_pages is the size in bits of the input bitmap. -Both first_page and num_pages must be a multiple of 64. For each bit -that is set in the input bitmap, the corresponding page is marked "clean" +first_page must be a multiple of 64; num_pages must also be a multiple of +64 unless first_page + num_pages is the size of the memory slot. For each +bit that is set in the input bitmap, the corresponding page is marked "clean" in KVM's dirty bitmap, and dirty tracking is re-enabled for that page (for example via write-protection, or by clearing the dirty bit in a page table entry). @@ -4770,7 +4800,7 @@ and injected exceptions. 7.18 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT -Architectures: all +Architectures: x86, arm, arm64, mips Parameters: args[0] whether feature should be enabled or not With this capability enabled, KVM_GET_DIRTY_LOG will not automatically diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt index f365102c80f5..2efe0efc516e 100644 --- a/Documentation/virtual/kvm/mmu.txt +++ b/Documentation/virtual/kvm/mmu.txt @@ -142,7 +142,7 @@ Shadow pages contain the following information: If clear, this page corresponds to a guest page table denoted by the gfn field. role.quadrant: - When role.cr4_pae=0, the guest uses 32-bit gptes while the host uses 64-bit + When role.gpte_is_8_bytes=0, the guest uses 32-bit gptes while the host uses 64-bit sptes. That means a guest page table contains more ptes than the host, so multiple shadow pages are needed to shadow one guest page. For first-level shadow pages, role.quadrant can be 0 or 1 and denotes the @@ -158,9 +158,9 @@ Shadow pages contain the following information: The page is invalid and should not be used. It is a root page that is currently pinned (by a cpu hardware register pointing to it); once it is unpinned it will be destroyed. - role.cr4_pae: - Contains the value of cr4.pae for which the page is valid (e.g. whether - 32-bit or 64-bit gptes are in use). + role.gpte_is_8_bytes: + Reflects the size of the guest PTE for which the page is valid, i.e. '1' + if 64-bit gptes are in use, '0' if 32-bit gptes are in use. role.nxe: Contains the value of efer.nxe for which the page is valid. role.cr0_wp: @@ -173,6 +173,9 @@ Shadow pages contain the following information: Contains the value of cr4.smap && !cr0.wp for which the page is valid (pages for which this is true are different from other pages; see the treatment of cr0.wp=0 below). + role.ept_sp: + This is a virtual flag to denote a shadowed nested EPT page. ept_sp + is true if "cr0_wp && smap_andnot_wp", an otherwise invalid combination. role.smm: Is 1 if the page is valid in system management mode. This field determines which of the kvm_memslots array was used to build this diff --git a/MAINTAINERS b/MAINTAINERS index 3e5a5d263f29..057a72a85156 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1893,14 +1893,15 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-nomadik.git ARM/NUVOTON NPCM ARCHITECTURE M: Avi Fishman <avifishman70@gmail.com> M: Tomer Maimon <tmaimon77@gmail.com> +M: Tali Perry <tali.perry1@gmail.com> R: Patrick Venture <venture@google.com> R: Nancy Yuen <yuenn@google.com> -R: Brendan Higgins <brendanhiggins@google.com> +R: Benjamin Fair <benjaminfair@google.com> L: openbmc@lists.ozlabs.org (moderated for non-subscribers) S: Supported F: arch/arm/mach-npcm/ F: arch/arm/boot/dts/nuvoton-npcm* -F: include/dt-bindings/clock/nuvoton,npcm7xx-clks.h +F: include/dt-bindings/clock/nuvoton,npcm7xx-clock.h F: drivers/*/*npcm* F: Documentation/devicetree/bindings/*/*npcm* F: Documentation/devicetree/bindings/*/*/*npcm* @@ -2356,7 +2357,7 @@ F: arch/arm/mm/cache-uniphier.c F: arch/arm64/boot/dts/socionext/uniphier* F: drivers/bus/uniphier-system-bus.c F: drivers/clk/uniphier/ -F: drivers/dmaengine/uniphier-mdmac.c +F: drivers/dma/uniphier-mdmac.c F: drivers/gpio/gpio-uniphier.c F: drivers/i2c/busses/i2c-uniphier* F: drivers/irqchip/irq-uniphier-aidet.c @@ -3120,6 +3121,7 @@ F: drivers/cpufreq/bmips-cpufreq.c BROADCOM BMIPS MIPS ARCHITECTURE M: Kevin Cernekee <cernekee@gmail.com> M: Florian Fainelli <f.fainelli@gmail.com> +L: bcm-kernel-feedback-list@broadcom.com L: linux-mips@vger.kernel.org T: git git://github.com/broadcom/stblinux.git S: Maintained @@ -4129,7 +4131,7 @@ F: drivers/cpuidle/* F: include/linux/cpuidle.h CRAMFS FILESYSTEM -M: Nicolas Pitre <nico@linaro.org> +M: Nicolas Pitre <nico@fluxnic.net> S: Maintained F: Documentation/filesystems/cramfs.txt F: fs/cramfs/ @@ -5833,7 +5835,7 @@ L: netdev@vger.kernel.org S: Maintained F: Documentation/ABI/testing/sysfs-bus-mdio F: Documentation/devicetree/bindings/net/mdio* -F: Documentation/networking/phy.txt +F: Documentation/networking/phy.rst F: drivers/net/phy/ F: drivers/of/of_mdio.c F: drivers/of/of_net.c @@ -6408,7 +6410,6 @@ L: linux-kernel@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking/core S: Maintained F: kernel/futex.c -F: kernel/futex_compat.c F: include/asm-generic/futex.h F: include/linux/futex.h F: include/uapi/linux/futex.h @@ -6461,7 +6462,7 @@ S: Maintained F: drivers/media/radio/radio-gemtek* GENERIC GPIO I2C DRIVER -M: Haavard Skinnemoen <hskinnemoen@gmail.com> +M: Wolfram Sang <wsa+renesas@sang-engineering.com> S: Supported F: drivers/i2c/busses/i2c-gpio.c F: include/linux/platform_data/i2c-gpio.h @@ -7333,7 +7334,6 @@ F: Documentation/devicetree/bindings/i3c/ F: Documentation/driver-api/i3c F: drivers/i3c/ F: include/linux/i3c/ -F: include/dt-bindings/i3c/ I3C DRIVER FOR SYNOPSYS DESIGNWARE M: Vitor Soares <vitor.soares@synopsys.com> @@ -7516,7 +7516,7 @@ F: include/net/mac802154.h F: include/net/af_ieee802154.h F: include/net/cfg802154.h F: include/net/ieee802154_netdev.h -F: Documentation/networking/ieee802154.txt +F: Documentation/networking/ieee802154.rst IFE PROTOCOL M: Yotam Gigi <yotam.gi@gmail.com> @@ -8708,6 +8708,7 @@ F: scripts/leaking_addresses.pl LED SUBSYSTEM M: Jacek Anaszewski <jacek.anaszewski@gmail.com> M: Pavel Machek <pavel@ucw.cz> +R: Dan Murphy <dmurphy@ti.com> L: linux-leds@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/j.anaszewski/linux-leds.git S: Maintained @@ -10145,7 +10146,7 @@ F: drivers/spi/spi-at91-usart.c F: Documentation/devicetree/bindings/mfd/atmel-usart.txt MICROCHIP KSZ SERIES ETHERNET SWITCH DRIVER -M: Woojung Huh <Woojung.Huh@microchip.com> +M: Woojung Huh <woojung.huh@microchip.com> M: Microchip Linux Driver Support <UNGLinuxDriver@microchip.com> L: netdev@vger.kernel.org S: Maintained @@ -13982,7 +13983,7 @@ F: drivers/media/rc/serial_ir.c SFC NETWORK DRIVER M: Solarflare linux maintainers <linux-net-drivers@solarflare.com> M: Edward Cree <ecree@solarflare.com> -M: Bert Kenward <bkenward@solarflare.com> +M: Martin Habets <mhabets@solarflare.com> L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/sfc/ @@ -16509,7 +16510,7 @@ F: drivers/char/virtio_console.c F: include/linux/virtio_console.h F: include/uapi/linux/virtio_console.h -VIRTIO CORE, NET AND BLOCK DRIVERS +VIRTIO CORE AND NET DRIVERS M: "Michael S. Tsirkin" <mst@redhat.com> M: Jason Wang <jasowang@redhat.com> L: virtualization@lists.linux-foundation.org @@ -16524,6 +16525,19 @@ F: include/uapi/linux/virtio_*.h F: drivers/crypto/virtio/ F: mm/balloon_compaction.c +VIRTIO BLOCK AND SCSI DRIVERS +M: "Michael S. Tsirkin" <mst@redhat.com> +M: Jason Wang <jasowang@redhat.com> +R: Paolo Bonzini <pbonzini@redhat.com> +R: Stefan Hajnoczi <stefanha@redhat.com> +L: virtualization@lists.linux-foundation.org +S: Maintained +F: drivers/block/virtio_blk.c +F: drivers/scsi/virtio_scsi.c +F: include/uapi/linux/virtio_blk.h +F: include/uapi/linux/virtio_scsi.h +F: drivers/vhost/scsi.c + VIRTIO CRYPTO DRIVER M: Gonglei <arei.gonglei@huawei.com> L: virtualization@lists.linux-foundation.org @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 1 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc7 NAME = Shy Crocodile # *DOCUMENTATION* @@ -31,26 +31,12 @@ _all: # descending is started. They are now explicitly listed as the # prepare rule. -# Ugly workaround for Debian make-kpkg: -# make-kpkg directly includes the top Makefile of Linux kernel. In such a case, -# skip sub-make to support debian_* targets in ruleset/kernel_version.mk, but -# displays warning to discourage such abusage. -ifneq ($(word 2, $(MAKEFILE_LIST)),) -$(warning Do not include top Makefile of Linux Kernel) -sub-make-done := 1 -MAKEFLAGS += -rR -endif - -ifneq ($(sub-make-done),1) +ifneq ($(sub_make_done),1) # Do not use make's built-in rules and variables # (this increases performance and avoids hard-to-debug behaviour) MAKEFLAGS += -rR -# 'MAKEFLAGS += -rR' does not become immediately effective for old -# GNU Make versions. Cancel implicit rules for this Makefile. -$(lastword $(MAKEFILE_LIST)): ; - # Avoid funny character set dependencies unexport LC_ALL LC_COLLATE=C @@ -153,6 +139,7 @@ $(if $(KBUILD_OUTPUT),, \ # 'sub-make' below. MAKEFLAGS += --include-dir=$(CURDIR) +need-sub-make := 1 else # Do not print "Entering directory ..." at all for in-tree build. @@ -160,6 +147,18 @@ MAKEFLAGS += --no-print-directory endif # ifneq ($(KBUILD_OUTPUT),) +ifneq ($(filter 3.%,$(MAKE_VERSION)),) +# 'MAKEFLAGS += -rR' does not immediately become effective for GNU Make 3.x +# We need to invoke sub-make to avoid implicit rules in the top Makefile. +need-sub-make := 1 +# Cancel implicit rules for this Makefile. +$(lastword $(MAKEFILE_LIST)): ; +endif + +export sub_make_done := 1 + +ifeq ($(need-sub-make),1) + PHONY += $(MAKECMDGOALS) sub-make $(filter-out _all sub-make $(CURDIR)/Makefile, $(MAKECMDGOALS)) _all: sub-make @@ -167,12 +166,15 @@ $(filter-out _all sub-make $(CURDIR)/Makefile, $(MAKECMDGOALS)) _all: sub-make # Invoke a second make in the output directory, passing relevant variables sub-make: - $(Q)$(MAKE) sub-make-done=1 \ + $(Q)$(MAKE) \ $(if $(KBUILD_OUTPUT),-C $(KBUILD_OUTPUT) KBUILD_SRC=$(CURDIR)) \ -f $(CURDIR)/Makefile $(filter-out _all sub-make,$(MAKECMDGOALS)) -else # sub-make-done +endif # need-sub-make +endif # sub_make_done + # We process the rest of the Makefile if this is the final invocation of make +ifeq ($(need-sub-make),) # Do not print "Entering directory ...", # but we want to display it when entering to the output directory @@ -497,7 +499,8 @@ outputmakefile: ifneq ($(KBUILD_SRC),) $(Q)ln -fsn $(srctree) source $(Q)$(CONFIG_SHELL) $(srctree)/scripts/mkmakefile $(srctree) - $(Q){ echo "# this is build directory, ignore it"; echo "*"; } > .gitignore + $(Q)test -e .gitignore || \ + { echo "# this is build directory, ignore it"; echo "*"; } > .gitignore endif ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),) @@ -675,9 +678,10 @@ KBUILD_CFLAGS += $(call cc-disable-warning,frame-address,) KBUILD_CFLAGS += $(call cc-disable-warning, format-truncation) KBUILD_CFLAGS += $(call cc-disable-warning, format-overflow) KBUILD_CFLAGS += $(call cc-disable-warning, int-in-bool-context) +KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member) ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE -KBUILD_CFLAGS += $(call cc-option,-Oz,-Os) +KBUILD_CFLAGS += -Os else KBUILD_CFLAGS += -O2 endif @@ -716,7 +720,6 @@ ifdef CONFIG_CC_IS_CLANG KBUILD_CPPFLAGS += $(call cc-option,-Qunused-arguments,) KBUILD_CFLAGS += $(call cc-disable-warning, format-invalid-specifier) KBUILD_CFLAGS += $(call cc-disable-warning, gnu) -KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member) # Quiet clang warning: comparison of unsigned expression < 0 is always false KBUILD_CFLAGS += $(call cc-disable-warning, tautological-compare) # CLANG uses a _MergedGlobals as optimization, but this breaks modpost, as the @@ -950,9 +953,11 @@ mod_sign_cmd = true endif export mod_sign_cmd +HOST_LIBELF_LIBS = $(shell pkg-config libelf --libs 2>/dev/null || echo -lelf) + ifdef CONFIG_STACK_VALIDATION has_libelf := $(call try-run,\ - echo "int main() {}" | $(HOSTCC) -xc -o /dev/null -lelf -,1,0) + echo "int main() {}" | $(HOSTCC) -xc -o /dev/null $(HOST_LIBELF_LIBS) -,1,0) ifeq ($(has_libelf),1) objtool_target := tools/objtool FORCE else @@ -1757,7 +1762,7 @@ existing-targets := $(wildcard $(sort $(targets))) endif # ifeq ($(config-targets),1) endif # ifeq ($(mixed-targets),1) -endif # sub-make-done +endif # need-sub-make PHONY += FORCE FORCE: diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild index dc0ab28baca1..70b783333965 100644 --- a/arch/alpha/include/asm/Kbuild +++ b/arch/alpha/include/asm/Kbuild @@ -6,6 +6,7 @@ generic-y += exec.h generic-y += export.h generic-y += fb.h generic-y += irq_work.h +generic-y += kvm_para.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += preempt.h diff --git a/arch/alpha/include/uapi/asm/kvm_para.h b/arch/alpha/include/uapi/asm/kvm_para.h deleted file mode 100644 index baacc4996d18..000000000000 --- a/arch/alpha/include/uapi/asm/kvm_para.h +++ /dev/null @@ -1,2 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#include <asm-generic/kvm_para.h> diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index 63ed39cbd3bd..165f268beafc 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -463,3 +463,7 @@ 532 common getppid sys_getppid # all other architectures have common numbers for new syscall, alpha # is the exception. +534 common pidfd_send_signal sys_pidfd_send_signal +535 common io_uring_setup sys_io_uring_setup +536 common io_uring_enter sys_io_uring_enter +537 common io_uring_register sys_io_uring_register diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index 69bc1c9e8e50..7425bb0f2d1b 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -18,8 +18,8 @@ model = "snps,hsdk"; compatible = "snps,hsdk"; - #address-cells = <1>; - #size-cells = <1>; + #address-cells = <2>; + #size-cells = <2>; chosen { bootargs = "earlycon=uart8250,mmio32,0xf0005000,115200n8 console=ttyS0,115200n8 debug print-fatal-signals=1"; @@ -105,7 +105,7 @@ #size-cells = <1>; interrupt-parent = <&idu_intc>; - ranges = <0x00000000 0xf0000000 0x10000000>; + ranges = <0x00000000 0x0 0xf0000000 0x10000000>; cgu_rst: reset-controller@8a0 { compatible = "snps,hsdk-reset"; @@ -269,9 +269,10 @@ }; memory@80000000 { - #address-cells = <1>; - #size-cells = <1>; + #address-cells = <2>; + #size-cells = <2>; device_type = "memory"; - reg = <0x80000000 0x40000000>; /* 1 GiB */ + reg = <0x0 0x80000000 0x0 0x40000000>; /* 1 GB lowmem */ + /* 0x1 0x00000000 0x0 0x40000000>; 1 GB highmem */ }; }; diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild index b41f8881ecc8..decc306a3b52 100644 --- a/arch/arc/include/asm/Kbuild +++ b/arch/arc/include/asm/Kbuild @@ -11,6 +11,7 @@ generic-y += hardirq.h generic-y += hw_irq.h generic-y += irq_regs.h generic-y += irq_work.h +generic-y += kvm_para.h generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h diff --git a/arch/arc/include/asm/syscall.h b/arch/arc/include/asm/syscall.h index 29de09804306..c7a4201ed62b 100644 --- a/arch/arc/include/asm/syscall.h +++ b/arch/arc/include/asm/syscall.h @@ -55,12 +55,11 @@ syscall_set_return_value(struct task_struct *task, struct pt_regs *regs, */ static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args) + unsigned long *args) { unsigned long *inside_ptregs = &(regs->r0); - inside_ptregs -= i; - - BUG_ON((i + n) > 6); + unsigned int n = 6; + unsigned int i = 0; while (n--) { args[i++] = (*inside_ptregs); diff --git a/arch/arc/include/uapi/asm/Kbuild b/arch/arc/include/uapi/asm/Kbuild index 755bb11323d8..1c72f04ff75d 100644 --- a/arch/arc/include/uapi/asm/Kbuild +++ b/arch/arc/include/uapi/asm/Kbuild @@ -1,2 +1 @@ -generic-y += kvm_para.h generic-y += ucontext.h diff --git a/arch/arc/lib/memset-archs.S b/arch/arc/lib/memset-archs.S index f230bb7092fd..b3373f5c88e0 100644 --- a/arch/arc/lib/memset-archs.S +++ b/arch/arc/lib/memset-archs.S @@ -30,10 +30,10 @@ #else -.macro PREALLOC_INSTR +.macro PREALLOC_INSTR reg, off .endm -.macro PREFETCHW_INSTR +.macro PREFETCHW_INSTR reg, off .endm #endif diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index 4135abec3fb0..63e6e6504699 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -113,10 +113,24 @@ static void read_decode_cache_bcr_arcv2(int cpu) } READ_BCR(ARC_REG_CLUSTER_BCR, cbcr); - if (cbcr.c) + if (cbcr.c) { ioc_exists = 1; - else + + /* + * As for today we don't support both IOC and ZONE_HIGHMEM enabled + * simultaneously. This happens because as of today IOC aperture covers + * only ZONE_NORMAL (low mem) and any dma transactions outside this + * region won't be HW coherent. + * If we want to use both IOC and ZONE_HIGHMEM we can use + * bounce_buffer to handle dma transactions to HIGHMEM. + * Also it is possible to modify dma_direct cache ops or increase IOC + * aperture size if we are planning to use HIGHMEM without PAE. + */ + if (IS_ENABLED(CONFIG_HIGHMEM) || is_pae40_enabled()) + ioc_enable = 0; + } else { ioc_enable = 0; + } /* HS 2.0 didn't have AUX_VOL */ if (cpuinfo_arc700[cpu].core.family > 0x51) { @@ -1158,19 +1172,6 @@ noinline void __init arc_ioc_setup(void) if (!ioc_enable) return; - /* - * As for today we don't support both IOC and ZONE_HIGHMEM enabled - * simultaneously. This happens because as of today IOC aperture covers - * only ZONE_NORMAL (low mem) and any dma transactions outside this - * region won't be HW coherent. - * If we want to use both IOC and ZONE_HIGHMEM we can use - * bounce_buffer to handle dma transactions to HIGHMEM. - * Also it is possible to modify dma_direct cache ops or increase IOC - * aperture size if we are planning to use HIGHMEM without PAE. - */ - if (IS_ENABLED(CONFIG_HIGHMEM)) - panic("IOC and HIGHMEM can't be used simultaneously"); - /* Flush + invalidate + disable L1 dcache */ __dc_disable(); diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 054ead960f98..9aed25a6019b 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -73,7 +73,7 @@ config ARM select HAVE_EFFICIENT_UNALIGNED_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && MMU select HAVE_EXIT_THREAD select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL - select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL + select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL && !CC_IS_CLANG select HAVE_FUNCTION_TRACER if !XIP_KERNEL select HAVE_GCC_PLUGINS select HAVE_HW_BREAKPOINT if PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7) @@ -596,6 +596,7 @@ config ARCH_DAVINCI select HAVE_IDE select PM_GENERIC_DOMAINS if PM select PM_GENERIC_DOMAINS_OF if PM && OF + select REGMAP_MMIO select RESET_CONTROLLER select SPARSE_IRQ select USE_OF diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug index 6d6e0330930b..e388af4594a6 100644 --- a/arch/arm/Kconfig.debug +++ b/arch/arm/Kconfig.debug @@ -47,8 +47,8 @@ config DEBUG_WX choice prompt "Choose kernel unwinder" - default UNWINDER_ARM if AEABI && !FUNCTION_GRAPH_TRACER - default UNWINDER_FRAME_POINTER if !AEABI || FUNCTION_GRAPH_TRACER + default UNWINDER_ARM if AEABI + default UNWINDER_FRAME_POINTER if !AEABI help This determines which method will be used for unwinding kernel stack traces for panics, oopses, bugs, warnings, perf, /proc/<pid>/stack, @@ -65,7 +65,7 @@ config UNWINDER_FRAME_POINTER config UNWINDER_ARM bool "ARM EABI stack unwinder" - depends on AEABI + depends on AEABI && !FUNCTION_GRAPH_TRACER select ARM_UNWIND help This option enables stack unwinding support in the kernel diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 6c7ccb428c07..7135820f76d4 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -1438,7 +1438,21 @@ ENTRY(efi_stub_entry) @ Preserve return value of efi_entry() in r4 mov r4, r0 - bl cache_clean_flush + + @ our cache maintenance code relies on CP15 barrier instructions + @ but since we arrived here with the MMU and caches configured + @ by UEFI, we must check that the CP15BEN bit is set in SCTLR. + @ Note that this bit is RAO/WI on v6 and earlier, so the ISB in + @ the enable path will be executed on v7+ only. + mrc p15, 0, r1, c1, c0, 0 @ read SCTLR + tst r1, #(1 << 5) @ CP15BEN bit set? + bne 0f + orr r1, r1, #(1 << 5) @ CP15 barrier instructions + mcr p15, 0, r1, c1, c0, 0 @ write SCTLR + ARM( .inst 0xf57ff06f @ v7+ isb ) + THUMB( isb ) + +0: bl cache_clean_flush bl cache_off @ Set parameters for booting zImage according to boot protocol diff --git a/arch/arm/boot/dts/am335x-evm.dts b/arch/arm/boot/dts/am335x-evm.dts index dce5be5df97b..edcff79879e7 100644 --- a/arch/arm/boot/dts/am335x-evm.dts +++ b/arch/arm/boot/dts/am335x-evm.dts @@ -57,6 +57,24 @@ enable-active-high; }; + /* TPS79501 */ + v1_8d_reg: fixedregulator-v1_8d { + compatible = "regulator-fixed"; + regulator-name = "v1_8d"; + vin-supply = <&vbat>; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + }; + + /* TPS79501 */ + v3_3d_reg: fixedregulator-v3_3d { + compatible = "regulator-fixed"; + regulator-name = "v3_3d"; + vin-supply = <&vbat>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + matrix_keypad: matrix_keypad0 { compatible = "gpio-matrix-keypad"; debounce-delay-ms = <5>; @@ -499,10 +517,10 @@ status = "okay"; /* Regulators */ - AVDD-supply = <&vaux2_reg>; - IOVDD-supply = <&vaux2_reg>; - DRVDD-supply = <&vaux2_reg>; - DVDD-supply = <&vbat>; + AVDD-supply = <&v3_3d_reg>; + IOVDD-supply = <&v3_3d_reg>; + DRVDD-supply = <&v3_3d_reg>; + DVDD-supply = <&v1_8d_reg>; }; }; diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts index b128998097ce..2c2d8b5b8cf5 100644 --- a/arch/arm/boot/dts/am335x-evmsk.dts +++ b/arch/arm/boot/dts/am335x-evmsk.dts @@ -73,6 +73,24 @@ enable-active-high; }; + /* TPS79518 */ + v1_8d_reg: fixedregulator-v1_8d { + compatible = "regulator-fixed"; + regulator-name = "v1_8d"; + vin-supply = <&vbat>; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + }; + + /* TPS78633 */ + v3_3d_reg: fixedregulator-v3_3d { + compatible = "regulator-fixed"; + regulator-name = "v3_3d"; + vin-supply = <&vbat>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + leds { pinctrl-names = "default"; pinctrl-0 = <&user_leds_s0>; @@ -501,10 +519,10 @@ status = "okay"; /* Regulators */ - AVDD-supply = <&vaux2_reg>; - IOVDD-supply = <&vaux2_reg>; - DRVDD-supply = <&vaux2_reg>; - DVDD-supply = <&vbat>; + AVDD-supply = <&v3_3d_reg>; + IOVDD-supply = <&v3_3d_reg>; + DRVDD-supply = <&v3_3d_reg>; + DVDD-supply = <&v1_8d_reg>; }; }; diff --git a/arch/arm/boot/dts/am33xx-l4.dtsi b/arch/arm/boot/dts/am33xx-l4.dtsi index f459ec316a22..ca6d9f02a800 100644 --- a/arch/arm/boot/dts/am33xx-l4.dtsi +++ b/arch/arm/boot/dts/am33xx-l4.dtsi @@ -1762,7 +1762,7 @@ reg = <0xcc000 0x4>; reg-names = "rev"; /* Domains (P, C): per_pwrdm, l4ls_clkdm */ - clocks = <&l4ls_clkctrl AM3_D_CAN0_CLKCTRL 0>; + clocks = <&l4ls_clkctrl AM3_L4LS_D_CAN0_CLKCTRL 0>; clock-names = "fck"; #address-cells = <1>; #size-cells = <1>; @@ -1785,7 +1785,7 @@ reg = <0xd0000 0x4>; reg-names = "rev"; /* Domains (P, C): per_pwrdm, l4ls_clkdm */ - clocks = <&l4ls_clkctrl AM3_D_CAN1_CLKCTRL 0>; + clocks = <&l4ls_clkctrl AM3_L4LS_D_CAN1_CLKCTRL 0>; clock-names = "fck"; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/bcm2835-rpi-b-rev2.dts b/arch/arm/boot/dts/bcm2835-rpi-b-rev2.dts index 5641d162dfdb..28e7513ce617 100644 --- a/arch/arm/boot/dts/bcm2835-rpi-b-rev2.dts +++ b/arch/arm/boot/dts/bcm2835-rpi-b-rev2.dts @@ -93,7 +93,7 @@ }; &hdmi { - hpd-gpios = <&gpio 46 GPIO_ACTIVE_LOW>; + hpd-gpios = <&gpio 46 GPIO_ACTIVE_HIGH>; }; &pwm { diff --git a/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi b/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi index b715ab0fa1ff..e8d800fec637 100644 --- a/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi +++ b/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi @@ -114,9 +114,9 @@ reg = <2>; }; - switch@0 { + switch@10 { compatible = "qca,qca8334"; - reg = <0>; + reg = <10>; switch_ports: ports { #address-cells = <1>; @@ -125,7 +125,7 @@ ethphy0: port@0 { reg = <0>; label = "cpu"; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; ethernet = <&fec>; fixed-link { diff --git a/arch/arm/boot/dts/imx6qdl-icore-rqs.dtsi b/arch/arm/boot/dts/imx6qdl-icore-rqs.dtsi index 1d1b4bd0670f..a4217f564a53 100644 --- a/arch/arm/boot/dts/imx6qdl-icore-rqs.dtsi +++ b/arch/arm/boot/dts/imx6qdl-icore-rqs.dtsi @@ -264,7 +264,7 @@ pinctrl-2 = <&pinctrl_usdhc3_200mhz>; vmcc-supply = <®_sd3_vmmc>; cd-gpios = <&gpio1 1 GPIO_ACTIVE_LOW>; - bus-witdh = <4>; + bus-width = <4>; no-1-8-v; status = "okay"; }; @@ -275,7 +275,7 @@ pinctrl-1 = <&pinctrl_usdhc4_100mhz>; pinctrl-2 = <&pinctrl_usdhc4_200mhz>; vmcc-supply = <®_sd4_vmmc>; - bus-witdh = <8>; + bus-width = <8>; no-1-8-v; non-removable; status = "okay"; diff --git a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi index 433bf09a1954..027df06c5dc7 100644 --- a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi +++ b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi @@ -91,6 +91,7 @@ pinctrl-0 = <&pinctrl_enet>; phy-handle = <ðphy>; phy-mode = "rgmii"; + phy-reset-duration = <10>; /* in msecs */ phy-reset-gpios = <&gpio3 23 GPIO_ACTIVE_LOW>; phy-supply = <&vdd_eth_io_reg>; status = "disabled"; diff --git a/arch/arm/boot/dts/imx6ull-pinfunc-snvs.h b/arch/arm/boot/dts/imx6ull-pinfunc-snvs.h index f6fb6783c193..54cfe72295aa 100644 --- a/arch/arm/boot/dts/imx6ull-pinfunc-snvs.h +++ b/arch/arm/boot/dts/imx6ull-pinfunc-snvs.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2016 Freescale Semiconductor, Inc. * Copyright (C) 2017 NXP diff --git a/arch/arm/boot/dts/rk3288-tinker.dtsi b/arch/arm/boot/dts/rk3288-tinker.dtsi index aa107ee41b8b..ef653c3209bc 100644 --- a/arch/arm/boot/dts/rk3288-tinker.dtsi +++ b/arch/arm/boot/dts/rk3288-tinker.dtsi @@ -254,6 +254,7 @@ }; vccio_sd: LDO_REG5 { + regulator-boot-on; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; regulator-name = "vccio_sd"; @@ -430,7 +431,7 @@ bus-width = <4>; cap-mmc-highspeed; cap-sd-highspeed; - card-detect-delay = <200>; + broken-cd; disable-wp; /* wp not hooked up */ pinctrl-names = "default"; pinctrl-0 = <&sdmmc_clk &sdmmc_cmd &sdmmc_cd &sdmmc_bus4>; diff --git a/arch/arm/boot/dts/rk3288-veyron.dtsi b/arch/arm/boot/dts/rk3288-veyron.dtsi index 0bc2409f6903..192dbc089ade 100644 --- a/arch/arm/boot/dts/rk3288-veyron.dtsi +++ b/arch/arm/boot/dts/rk3288-veyron.dtsi @@ -25,8 +25,6 @@ gpio_keys: gpio-keys { compatible = "gpio-keys"; - #address-cells = <1>; - #size-cells = <0>; pinctrl-names = "default"; pinctrl-0 = <&pwr_key_l>; diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi index ca7d52daa8fb..a024d1e7e74c 100644 --- a/arch/arm/boot/dts/rk3288.dtsi +++ b/arch/arm/boot/dts/rk3288.dtsi @@ -70,7 +70,7 @@ compatible = "arm,cortex-a12"; reg = <0x501>; resets = <&cru SRST_CORE1>; - operating-points = <&cpu_opp_table>; + operating-points-v2 = <&cpu_opp_table>; #cooling-cells = <2>; /* min followed by max */ clock-latency = <40000>; clocks = <&cru ARMCLK>; @@ -80,7 +80,7 @@ compatible = "arm,cortex-a12"; reg = <0x502>; resets = <&cru SRST_CORE2>; - operating-points = <&cpu_opp_table>; + operating-points-v2 = <&cpu_opp_table>; #cooling-cells = <2>; /* min followed by max */ clock-latency = <40000>; clocks = <&cru ARMCLK>; @@ -90,7 +90,7 @@ compatible = "arm,cortex-a12"; reg = <0x503>; resets = <&cru SRST_CORE3>; - operating-points = <&cpu_opp_table>; + operating-points-v2 = <&cpu_opp_table>; #cooling-cells = <2>; /* min followed by max */ clock-latency = <40000>; clocks = <&cru ARMCLK>; @@ -1119,8 +1119,6 @@ clock-names = "ref", "pclk"; power-domains = <&power RK3288_PD_VIO>; rockchip,grf = <&grf>; - #address-cells = <1>; - #size-cells = <0>; status = "disabled"; ports { @@ -1282,27 +1280,27 @@ gpu_opp_table: gpu-opp-table { compatible = "operating-points-v2"; - opp@100000000 { + opp-100000000 { opp-hz = /bits/ 64 <100000000>; opp-microvolt = <950000>; }; - opp@200000000 { + opp-200000000 { opp-hz = /bits/ 64 <200000000>; opp-microvolt = <950000>; }; - opp@300000000 { + opp-300000000 { opp-hz = /bits/ 64 <300000000>; opp-microvolt = <1000000>; }; - opp@400000000 { + opp-400000000 { opp-hz = /bits/ 64 <400000000>; opp-microvolt = <1100000>; }; - opp@500000000 { + opp-500000000 { opp-hz = /bits/ 64 <500000000>; opp-microvolt = <1200000>; }; - opp@600000000 { + opp-600000000 { opp-hz = /bits/ 64 <600000000>; opp-microvolt = <1250000>; }; diff --git a/arch/arm/boot/dts/sama5d2-pinfunc.h b/arch/arm/boot/dts/sama5d2-pinfunc.h index 1c01a6f843d8..28a2e45752fe 100644 --- a/arch/arm/boot/dts/sama5d2-pinfunc.h +++ b/arch/arm/boot/dts/sama5d2-pinfunc.h @@ -518,7 +518,7 @@ #define PIN_PC9__GPIO PINMUX_PIN(PIN_PC9, 0, 0) #define PIN_PC9__FIQ PINMUX_PIN(PIN_PC9, 1, 3) #define PIN_PC9__GTSUCOMP PINMUX_PIN(PIN_PC9, 2, 1) -#define PIN_PC9__ISC_D0 PINMUX_PIN(PIN_PC9, 2, 1) +#define PIN_PC9__ISC_D0 PINMUX_PIN(PIN_PC9, 3, 1) #define PIN_PC9__TIOA4 PINMUX_PIN(PIN_PC9, 4, 2) #define PIN_PC10 74 #define PIN_PC10__GPIO PINMUX_PIN(PIN_PC10, 0, 0) diff --git a/arch/arm/configs/imx_v4_v5_defconfig b/arch/arm/configs/imx_v4_v5_defconfig index 8661dd9b064a..b37f8e675e40 100644 --- a/arch/arm/configs/imx_v4_v5_defconfig +++ b/arch/arm/configs/imx_v4_v5_defconfig @@ -170,6 +170,9 @@ CONFIG_IMX_SDMA=y # CONFIG_IOMMU_SUPPORT is not set CONFIG_IIO=y CONFIG_FSL_MX25_ADC=y +CONFIG_PWM=y +CONFIG_PWM_IMX1=y +CONFIG_PWM_IMX27=y CONFIG_EXT4_FS=y # CONFIG_DNOTIFY is not set CONFIG_VFAT_FS=y diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig index 5586a5074a96..50fb01d70b10 100644 --- a/arch/arm/configs/imx_v6_v7_defconfig +++ b/arch/arm/configs/imx_v6_v7_defconfig @@ -398,7 +398,7 @@ CONFIG_MAG3110=y CONFIG_MPL3115=y CONFIG_PWM=y CONFIG_PWM_FSL_FTM=y -CONFIG_PWM_IMX=y +CONFIG_PWM_IMX27=y CONFIG_NVMEM_IMX_OCOTP=y CONFIG_NVMEM_VF610_OCOTP=y CONFIG_TEE=y diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index 2de96a180166..31de4ab93005 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -381,6 +381,17 @@ static inline int kvm_read_guest_lock(struct kvm *kvm, return ret; } +static inline int kvm_write_guest_lock(struct kvm *kvm, gpa_t gpa, + const void *data, unsigned long len) +{ + int srcu_idx = srcu_read_lock(&kvm->srcu); + int ret = kvm_write_guest(kvm, gpa, data, len); + + srcu_read_unlock(&kvm->srcu, srcu_idx); + + return ret; +} + static inline void *kvm_get_hyp_vector(void) { switch(read_cpuid_part()) { diff --git a/arch/arm/include/asm/stage2_pgtable.h b/arch/arm/include/asm/stage2_pgtable.h index de2089501b8b..9e11dce55e06 100644 --- a/arch/arm/include/asm/stage2_pgtable.h +++ b/arch/arm/include/asm/stage2_pgtable.h @@ -75,6 +75,8 @@ static inline bool kvm_stage2_has_pud(struct kvm *kvm) #define S2_PMD_MASK PMD_MASK #define S2_PMD_SIZE PMD_SIZE +#define S2_PUD_MASK PUD_MASK +#define S2_PUD_SIZE PUD_SIZE static inline bool kvm_stage2_has_pmd(struct kvm *kvm) { diff --git a/arch/arm/include/asm/syscall.h b/arch/arm/include/asm/syscall.h index 06dea6bce293..080ce70cab12 100644 --- a/arch/arm/include/asm/syscall.h +++ b/arch/arm/include/asm/syscall.h @@ -55,53 +55,22 @@ static inline void syscall_set_return_value(struct task_struct *task, static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args) { - if (n == 0) - return; - - if (i + n > SYSCALL_MAX_ARGS) { - unsigned long *args_bad = args + SYSCALL_MAX_ARGS - i; - unsigned int n_bad = n + i - SYSCALL_MAX_ARGS; - pr_warn("%s called with max args %d, handling only %d\n", - __func__, i + n, SYSCALL_MAX_ARGS); - memset(args_bad, 0, n_bad * sizeof(args[0])); - n = SYSCALL_MAX_ARGS - i; - } - - if (i == 0) { - args[0] = regs->ARM_ORIG_r0; - args++; - i++; - n--; - } - - memcpy(args, ®s->ARM_r0 + i, n * sizeof(args[0])); + args[0] = regs->ARM_ORIG_r0; + args++; + + memcpy(args, ®s->ARM_r0 + 1, 5 * sizeof(args[0])); } static inline void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, const unsigned long *args) { - if (n == 0) - return; - - if (i + n > SYSCALL_MAX_ARGS) { - pr_warn("%s called with max args %d, handling only %d\n", - __func__, i + n, SYSCALL_MAX_ARGS); - n = SYSCALL_MAX_ARGS - i; - } - - if (i == 0) { - regs->ARM_ORIG_r0 = args[0]; - args++; - i++; - n--; - } - - memcpy(®s->ARM_r0 + i, args, n * sizeof(args[0])); + regs->ARM_ORIG_r0 = args[0]; + args++; + + memcpy(®s->ARM_r0 + 1, args, 5 * sizeof(args[0])); } static inline int syscall_get_arch(void) diff --git a/arch/arm/include/uapi/asm/Kbuild b/arch/arm/include/uapi/asm/Kbuild index 23b4464c0995..ce8573157774 100644 --- a/arch/arm/include/uapi/asm/Kbuild +++ b/arch/arm/include/uapi/asm/Kbuild @@ -3,3 +3,4 @@ generated-y += unistd-common.h generated-y += unistd-oabi.h generated-y += unistd-eabi.h +generic-y += kvm_para.h diff --git a/arch/arm/include/uapi/asm/kvm_para.h b/arch/arm/include/uapi/asm/kvm_para.h deleted file mode 100644 index baacc4996d18..000000000000 --- a/arch/arm/include/uapi/asm/kvm_para.h +++ /dev/null @@ -1,2 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#include <asm-generic/kvm_para.h> diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S index c08d2d890f7b..b38bbd011b35 100644 --- a/arch/arm/kernel/head-nommu.S +++ b/arch/arm/kernel/head-nommu.S @@ -133,9 +133,9 @@ __secondary_data: */ .text __after_proc_init: -#ifdef CONFIG_ARM_MPU M_CLASS(movw r12, #:lower16:BASEADDR_V7M_SCB) M_CLASS(movt r12, #:upper16:BASEADDR_V7M_SCB) +#ifdef CONFIG_ARM_MPU M_CLASS(ldr r3, [r12, 0x50]) AR_CLASS(mrc p15, 0, r3, c0, c1, 4) @ Read ID_MMFR0 and r3, r3, #(MMFR0_PMSA) @ PMSA field diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c index 51e808adb00c..2a757dcaa1a5 100644 --- a/arch/arm/mach-at91/pm.c +++ b/arch/arm/mach-at91/pm.c @@ -591,13 +591,13 @@ static int __init at91_pm_backup_init(void) np = of_find_compatible_node(NULL, NULL, "atmel,sama5d2-securam"); if (!np) - goto securam_fail; + goto securam_fail_no_ref_dev; pdev = of_find_device_by_node(np); of_node_put(np); if (!pdev) { pr_warn("%s: failed to find securam device!\n", __func__); - goto securam_fail; + goto securam_fail_no_ref_dev; } sram_pool = gen_pool_get(&pdev->dev, NULL); @@ -620,6 +620,8 @@ static int __init at91_pm_backup_init(void) return 0; securam_fail: + put_device(&pdev->dev); +securam_fail_no_ref_dev: iounmap(pm_data.sfrbu); pm_data.sfrbu = NULL; return ret; diff --git a/arch/arm/mach-imx/cpuidle-imx6q.c b/arch/arm/mach-imx/cpuidle-imx6q.c index bfeb25aaf9a2..326e870d7123 100644 --- a/arch/arm/mach-imx/cpuidle-imx6q.c +++ b/arch/arm/mach-imx/cpuidle-imx6q.c @@ -16,30 +16,23 @@ #include "cpuidle.h" #include "hardware.h" -static atomic_t master = ATOMIC_INIT(0); -static DEFINE_SPINLOCK(master_lock); +static int num_idle_cpus = 0; +static DEFINE_SPINLOCK(cpuidle_lock); static int imx6q_enter_wait(struct cpuidle_device *dev, struct cpuidle_driver *drv, int index) { - if (atomic_inc_return(&master) == num_online_cpus()) { - /* - * With this lock, we prevent other cpu to exit and enter - * this function again and become the master. - */ - if (!spin_trylock(&master_lock)) - goto idle; + spin_lock(&cpuidle_lock); + if (++num_idle_cpus == num_online_cpus()) imx6_set_lpm(WAIT_UNCLOCKED); - cpu_do_idle(); - imx6_set_lpm(WAIT_CLOCKED); - spin_unlock(&master_lock); - goto done; - } + spin_unlock(&cpuidle_lock); -idle: cpu_do_idle(); -done: - atomic_dec(&master); + + spin_lock(&cpuidle_lock); + if (num_idle_cpus-- == num_online_cpus()) + imx6_set_lpm(WAIT_CLOCKED); + spin_unlock(&cpuidle_lock); return index; } diff --git a/arch/arm/mach-imx/mach-imx51.c b/arch/arm/mach-imx/mach-imx51.c index c7169c2f94c4..08c7892866c2 100644 --- a/arch/arm/mach-imx/mach-imx51.c +++ b/arch/arm/mach-imx/mach-imx51.c @@ -59,6 +59,7 @@ static void __init imx51_m4if_setup(void) return; m4if_base = of_iomap(np, 0); + of_node_put(np); if (!m4if_base) { pr_err("Unable to map M4IF registers\n"); return; diff --git a/arch/arm/mach-iop13xx/setup.c b/arch/arm/mach-iop13xx/setup.c index 53c316f7301e..fe4932fda01d 100644 --- a/arch/arm/mach-iop13xx/setup.c +++ b/arch/arm/mach-iop13xx/setup.c @@ -300,7 +300,7 @@ static struct resource iop13xx_adma_2_resources[] = { } }; -static u64 iop13xx_adma_dmamask = DMA_BIT_MASK(64); +static u64 iop13xx_adma_dmamask = DMA_BIT_MASK(32); static struct iop_adma_platform_data iop13xx_adma_0_data = { .hw_id = 0, .pool_size = PAGE_SIZE, @@ -324,7 +324,7 @@ static struct platform_device iop13xx_adma_0_channel = { .resource = iop13xx_adma_0_resources, .dev = { .dma_mask = &iop13xx_adma_dmamask, - .coherent_dma_mask = DMA_BIT_MASK(64), + .coherent_dma_mask = DMA_BIT_MASK(32), .platform_data = (void *) &iop13xx_adma_0_data, }, }; @@ -336,7 +336,7 @@ static struct platform_device iop13xx_adma_1_channel = { .resource = iop13xx_adma_1_resources, .dev = { .dma_mask = &iop13xx_adma_dmamask, - .coherent_dma_mask = DMA_BIT_MASK(64), + .coherent_dma_mask = DMA_BIT_MASK(32), .platform_data = (void *) &iop13xx_adma_1_data, }, }; @@ -348,7 +348,7 @@ static struct platform_device iop13xx_adma_2_channel = { .resource = iop13xx_adma_2_resources, .dev = { .dma_mask = &iop13xx_adma_dmamask, - .coherent_dma_mask = DMA_BIT_MASK(64), + .coherent_dma_mask = DMA_BIT_MASK(32), .platform_data = (void *) &iop13xx_adma_2_data, }, }; diff --git a/arch/arm/mach-iop13xx/tpmi.c b/arch/arm/mach-iop13xx/tpmi.c index db511ec2b1df..116feb6b261e 100644 --- a/arch/arm/mach-iop13xx/tpmi.c +++ b/arch/arm/mach-iop13xx/tpmi.c @@ -152,7 +152,7 @@ static struct resource iop13xx_tpmi_3_resources[] = { } }; -u64 iop13xx_tpmi_mask = DMA_BIT_MASK(64); +u64 iop13xx_tpmi_mask = DMA_BIT_MASK(32); static struct platform_device iop13xx_tpmi_0_device = { .name = "iop-tpmi", .id = 0, @@ -160,7 +160,7 @@ static struct platform_device iop13xx_tpmi_0_device = { .resource = iop13xx_tpmi_0_resources, .dev = { .dma_mask = &iop13xx_tpmi_mask, - .coherent_dma_mask = DMA_BIT_MASK(64), + .coherent_dma_mask = DMA_BIT_MASK(32), }, }; @@ -171,7 +171,7 @@ static struct platform_device iop13xx_tpmi_1_device = { .resource = iop13xx_tpmi_1_resources, .dev = { .dma_mask = &iop13xx_tpmi_mask, - .coherent_dma_mask = DMA_BIT_MASK(64), + .coherent_dma_mask = DMA_BIT_MASK(32), }, }; @@ -182,7 +182,7 @@ static struct platform_device iop13xx_tpmi_2_device = { .resource = iop13xx_tpmi_2_resources, .dev = { .dma_mask = &iop13xx_tpmi_mask, - .coherent_dma_mask = DMA_BIT_MASK(64), + .coherent_dma_mask = DMA_BIT_MASK(32), }, }; @@ -193,7 +193,7 @@ static struct platform_device iop13xx_tpmi_3_device = { .resource = iop13xx_tpmi_3_resources, .dev = { .dma_mask = &iop13xx_tpmi_mask, - .coherent_dma_mask = DMA_BIT_MASK(64), + .coherent_dma_mask = DMA_BIT_MASK(32), }, }; diff --git a/arch/arm/mach-milbeaut/platsmp.c b/arch/arm/mach-milbeaut/platsmp.c index 591543c81399..3ea880f5fcb7 100644 --- a/arch/arm/mach-milbeaut/platsmp.c +++ b/arch/arm/mach-milbeaut/platsmp.c @@ -65,6 +65,7 @@ static void m10v_smp_init(unsigned int max_cpus) writel(KERNEL_UNBOOT_FLAG, m10v_smp_base + cpu * 4); } +#ifdef CONFIG_HOTPLUG_CPU static void m10v_cpu_die(unsigned int l_cpu) { gic_cpu_if_down(0); @@ -83,12 +84,15 @@ static int m10v_cpu_kill(unsigned int l_cpu) return 1; } +#endif static struct smp_operations m10v_smp_ops __initdata = { .smp_prepare_cpus = m10v_smp_init, .smp_boot_secondary = m10v_boot_secondary, +#ifdef CONFIG_HOTPLUG_CPU .cpu_die = m10v_cpu_die, .cpu_kill = m10v_cpu_kill, +#endif }; CPU_METHOD_OF_DECLARE(m10v_smp, "socionext,milbeaut-m10v-smp", &m10v_smp_ops); diff --git a/arch/arm/mach-omap1/board-ams-delta.c b/arch/arm/mach-omap1/board-ams-delta.c index be30c3c061b4..1b15d593837e 100644 --- a/arch/arm/mach-omap1/board-ams-delta.c +++ b/arch/arm/mach-omap1/board-ams-delta.c @@ -182,6 +182,7 @@ static struct resource latch1_resources[] = { static struct bgpio_pdata latch1_pdata = { .label = LATCH1_LABEL, + .base = -1, .ngpio = LATCH1_NGPIO, }; @@ -219,6 +220,7 @@ static struct resource latch2_resources[] = { static struct bgpio_pdata latch2_pdata = { .label = LATCH2_LABEL, + .base = -1, .ngpio = LATCH2_NGPIO, }; diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c index 1444b4b4bd9f..439e143cad7b 100644 --- a/arch/arm/mach-omap2/display.c +++ b/arch/arm/mach-omap2/display.c @@ -250,8 +250,10 @@ static int __init omapdss_init_of(void) if (!node) return 0; - if (!of_device_is_available(node)) + if (!of_device_is_available(node)) { + of_node_put(node); return 0; + } pdev = of_find_device_by_node(node); diff --git a/arch/arm/plat-iop/adma.c b/arch/arm/plat-iop/adma.c index a4d1f8de3b5b..d9612221e484 100644 --- a/arch/arm/plat-iop/adma.c +++ b/arch/arm/plat-iop/adma.c @@ -143,7 +143,7 @@ struct platform_device iop3xx_dma_0_channel = { .resource = iop3xx_dma_0_resources, .dev = { .dma_mask = &iop3xx_adma_dmamask, - .coherent_dma_mask = DMA_BIT_MASK(64), + .coherent_dma_mask = DMA_BIT_MASK(32), .platform_data = (void *) &iop3xx_dma_0_data, }, }; @@ -155,7 +155,7 @@ struct platform_device iop3xx_dma_1_channel = { .resource = iop3xx_dma_1_resources, .dev = { .dma_mask = &iop3xx_adma_dmamask, - .coherent_dma_mask = DMA_BIT_MASK(64), + .coherent_dma_mask = DMA_BIT_MASK(32), .platform_data = (void *) &iop3xx_dma_1_data, }, }; @@ -167,7 +167,7 @@ struct platform_device iop3xx_aau_channel = { .resource = iop3xx_aau_resources, .dev = { .dma_mask = &iop3xx_adma_dmamask, - .coherent_dma_mask = DMA_BIT_MASK(64), + .coherent_dma_mask = DMA_BIT_MASK(32), .platform_data = (void *) &iop3xx_aau_data, }, }; diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c index a6c81ce00f52..8647cb80a93b 100644 --- a/arch/arm/plat-orion/common.c +++ b/arch/arm/plat-orion/common.c @@ -622,7 +622,7 @@ static struct platform_device orion_xor0_shared = { .resource = orion_xor0_shared_resources, .dev = { .dma_mask = &orion_xor_dmamask, - .coherent_dma_mask = DMA_BIT_MASK(64), + .coherent_dma_mask = DMA_BIT_MASK(32), .platform_data = &orion_xor0_pdata, }, }; @@ -683,7 +683,7 @@ static struct platform_device orion_xor1_shared = { .resource = orion_xor1_shared_resources, .dev = { .dma_mask = &orion_xor_dmamask, - .coherent_dma_mask = DMA_BIT_MASK(64), + .coherent_dma_mask = DMA_BIT_MASK(32), .platform_data = &orion_xor1_pdata, }, }; diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index 9016f4081bb9..0393917eaa57 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -437,3 +437,7 @@ 421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait 422 common futex_time64 sys_futex 423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index 70498a033cf5..b5ca9c50876d 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -27,6 +27,7 @@ config ARCH_BCM2835 bool "Broadcom BCM2835 family" select TIMER_OF select GPIOLIB + select MFD_CORE select PINCTRL select PINCTRL_BCM2835 select ARM_AMBA diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi index 7c649f6b14cb..cd7c76e58b09 100644 --- a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi +++ b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi @@ -162,6 +162,7 @@ rx-fifo-depth = <16384>; snps,multicast-filter-bins = <256>; iommus = <&smmu 1>; + altr,sysmgr-syscon = <&sysmgr 0x44 0>; status = "disabled"; }; @@ -179,6 +180,7 @@ rx-fifo-depth = <16384>; snps,multicast-filter-bins = <256>; iommus = <&smmu 2>; + altr,sysmgr-syscon = <&sysmgr 0x48 0>; status = "disabled"; }; @@ -196,6 +198,7 @@ rx-fifo-depth = <16384>; snps,multicast-filter-bins = <256>; iommus = <&smmu 3>; + altr,sysmgr-syscon = <&sysmgr 0x4c 0>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra186.dtsi b/arch/arm64/boot/dts/nvidia/tegra186.dtsi index bb2045be8814..97aeb946ed5e 100644 --- a/arch/arm64/boot/dts/nvidia/tegra186.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra186.dtsi @@ -321,7 +321,6 @@ nvidia,default-trim = <0x9>; nvidia,dqs-trim = <63>; mmc-hs400-1_8v; - supports-cqe; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/renesas/r8a774c0.dtsi b/arch/arm64/boot/dts/renesas/r8a774c0.dtsi index 61a0afb74e63..1ea684af99c4 100644 --- a/arch/arm64/boot/dts/renesas/r8a774c0.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a774c0.dtsi @@ -2,7 +2,7 @@ /* * Device Tree Source for the RZ/G2E (R8A774C0) SoC * - * Copyright (C) 2018 Renesas Electronics Corp. + * Copyright (C) 2018-2019 Renesas Electronics Corp. */ #include <dt-bindings/clock/r8a774c0-cpg-mssr.h> @@ -1150,9 +1150,8 @@ <&cpg CPG_CORE R8A774C0_CLK_S3D1C>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; - dmas = <&dmac1 0x5b>, <&dmac1 0x5a>, - <&dmac2 0x5b>, <&dmac2 0x5a>; - dma-names = "tx", "rx", "tx", "rx"; + dmas = <&dmac0 0x5b>, <&dmac0 0x5a>; + dma-names = "tx", "rx"; power-domains = <&sysc R8A774C0_PD_ALWAYS_ON>; resets = <&cpg 202>; status = "disabled"; diff --git a/arch/arm64/boot/dts/renesas/r8a77990.dtsi b/arch/arm64/boot/dts/renesas/r8a77990.dtsi index a69faa60ea4d..d2ad665fe2d9 100644 --- a/arch/arm64/boot/dts/renesas/r8a77990.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a77990.dtsi @@ -2,7 +2,7 @@ /* * Device Tree Source for the R-Car E3 (R8A77990) SoC * - * Copyright (C) 2018 Renesas Electronics Corp. + * Copyright (C) 2018-2019 Renesas Electronics Corp. */ #include <dt-bindings/clock/r8a77990-cpg-mssr.h> @@ -1067,9 +1067,8 @@ <&cpg CPG_CORE R8A77990_CLK_S3D1C>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; - dmas = <&dmac1 0x5b>, <&dmac1 0x5a>, - <&dmac2 0x5b>, <&dmac2 0x5a>; - dma-names = "tx", "rx", "tx", "rx"; + dmas = <&dmac0 0x5b>, <&dmac0 0x5a>; + dma-names = "tx", "rx"; power-domains = <&sysc R8A77990_PD_ALWAYS_ON>; resets = <&cpg 202>; status = "disabled"; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts b/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts index 33c44e857247..0e34354b2092 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts @@ -108,8 +108,8 @@ snps,reset-gpio = <&gpio1 RK_PC2 GPIO_ACTIVE_LOW>; snps,reset-active-low; snps,reset-delays-us = <0 10000 50000>; - tx_delay = <0x25>; - rx_delay = <0x11>; + tx_delay = <0x24>; + rx_delay = <0x18>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts index 2157a528276b..79b4d1d4b5d6 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts @@ -46,8 +46,7 @@ vcc_host1_5v: vcc_otg_5v: vcc-host1-5v-regulator { compatible = "regulator-fixed"; - enable-active-high; - gpio = <&gpio0 RK_PA2 GPIO_ACTIVE_HIGH>; + gpio = <&gpio0 RK_PA2 GPIO_ACTIVE_LOW>; pinctrl-names = "default"; pinctrl-0 = <&usb20_host_drv>; regulator-name = "vcc_host1_5v"; diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index 84f14b132e8f..dabef1a21649 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -1445,11 +1445,11 @@ sdmmc0 { sdmmc0_clk: sdmmc0-clk { - rockchip,pins = <1 RK_PA6 1 &pcfg_pull_none_4ma>; + rockchip,pins = <1 RK_PA6 1 &pcfg_pull_none_8ma>; }; sdmmc0_cmd: sdmmc0-cmd { - rockchip,pins = <1 RK_PA4 1 &pcfg_pull_up_4ma>; + rockchip,pins = <1 RK_PA4 1 &pcfg_pull_up_8ma>; }; sdmmc0_dectn: sdmmc0-dectn { @@ -1461,14 +1461,14 @@ }; sdmmc0_bus1: sdmmc0-bus1 { - rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_4ma>; + rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_8ma>; }; sdmmc0_bus4: sdmmc0-bus4 { - rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_4ma>, - <1 RK_PA1 1 &pcfg_pull_up_4ma>, - <1 RK_PA2 1 &pcfg_pull_up_4ma>, - <1 RK_PA3 1 &pcfg_pull_up_4ma>; + rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_8ma>, + <1 RK_PA1 1 &pcfg_pull_up_8ma>, + <1 RK_PA2 1 &pcfg_pull_up_8ma>, + <1 RK_PA3 1 &pcfg_pull_up_8ma>; }; sdmmc0_gpio: sdmmc0-gpio { @@ -1642,50 +1642,50 @@ rgmiim1_pins: rgmiim1-pins { rockchip,pins = /* mac_txclk */ - <1 RK_PB4 2 &pcfg_pull_none_12ma>, + <1 RK_PB4 2 &pcfg_pull_none_8ma>, /* mac_rxclk */ - <1 RK_PB5 2 &pcfg_pull_none_2ma>, + <1 RK_PB5 2 &pcfg_pull_none_4ma>, /* mac_mdio */ - <1 RK_PC3 2 &pcfg_pull_none_2ma>, + <1 RK_PC3 2 &pcfg_pull_none_4ma>, /* mac_txen */ - <1 RK_PD1 2 &pcfg_pull_none_12ma>, + <1 RK_PD1 2 &pcfg_pull_none_8ma>, /* mac_clk */ - <1 RK_PC5 2 &pcfg_pull_none_2ma>, + <1 RK_PC5 2 &pcfg_pull_none_4ma>, /* mac_rxdv */ - <1 RK_PC6 2 &pcfg_pull_none_2ma>, + <1 RK_PC6 2 &pcfg_pull_none_4ma>, /* mac_mdc */ - <1 RK_PC7 2 &pcfg_pull_none_2ma>, + <1 RK_PC7 2 &pcfg_pull_none_4ma>, /* mac_rxd1 */ - <1 RK_PB2 2 &pcfg_pull_none_2ma>, + <1 RK_PB2 2 &pcfg_pull_none_4ma>, /* mac_rxd0 */ - <1 RK_PB3 2 &pcfg_pull_none_2ma>, + <1 RK_PB3 2 &pcfg_pull_none_4ma>, /* mac_txd1 */ - <1 RK_PB0 2 &pcfg_pull_none_12ma>, + <1 RK_PB0 2 &pcfg_pull_none_8ma>, /* mac_txd0 */ - <1 RK_PB1 2 &pcfg_pull_none_12ma>, + <1 RK_PB1 2 &pcfg_pull_none_8ma>, /* mac_rxd3 */ - <1 RK_PB6 2 &pcfg_pull_none_2ma>, + <1 RK_PB6 2 &pcfg_pull_none_4ma>, /* mac_rxd2 */ - <1 RK_PB7 2 &pcfg_pull_none_2ma>, + <1 RK_PB7 2 &pcfg_pull_none_4ma>, /* mac_txd3 */ - <1 RK_PC0 2 &pcfg_pull_none_12ma>, + <1 RK_PC0 2 &pcfg_pull_none_8ma>, /* mac_txd2 */ - <1 RK_PC1 2 &pcfg_pull_none_12ma>, + <1 RK_PC1 2 &pcfg_pull_none_8ma>, /* mac_txclk */ - <0 RK_PB0 1 &pcfg_pull_none>, + <0 RK_PB0 1 &pcfg_pull_none_8ma>, /* mac_txen */ - <0 RK_PB4 1 &pcfg_pull_none>, + <0 RK_PB4 1 &pcfg_pull_none_8ma>, /* mac_clk */ - <0 RK_PD0 1 &pcfg_pull_none>, + <0 RK_PD0 1 &pcfg_pull_none_4ma>, /* mac_txd1 */ - <0 RK_PC0 1 &pcfg_pull_none>, + <0 RK_PC0 1 &pcfg_pull_none_8ma>, /* mac_txd0 */ - <0 RK_PC1 1 &pcfg_pull_none>, + <0 RK_PC1 1 &pcfg_pull_none_8ma>, /* mac_txd3 */ - <0 RK_PC7 1 &pcfg_pull_none>, + <0 RK_PC7 1 &pcfg_pull_none_8ma>, /* mac_txd2 */ - <0 RK_PC6 1 &pcfg_pull_none>; + <0 RK_PC6 1 &pcfg_pull_none_8ma>; }; rmiim1_pins: rmiim1-pins { diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dts b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dts index 4a543f2117d4..844eac939a97 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dts @@ -158,6 +158,7 @@ }; &hdmi { + ddc-i2c-bus = <&i2c3>; pinctrl-names = "default"; pinctrl-0 = <&hdmi_cec>; status = "okay"; diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h index cccb83ad7fa8..c7e1a7837706 100644 --- a/arch/arm64/include/asm/futex.h +++ b/arch/arm64/include/asm/futex.h @@ -30,8 +30,8 @@ do { \ " prfm pstl1strm, %2\n" \ "1: ldxr %w1, %2\n" \ insn "\n" \ -"2: stlxr %w3, %w0, %2\n" \ -" cbnz %w3, 1b\n" \ +"2: stlxr %w0, %w3, %2\n" \ +" cbnz %w0, 1b\n" \ " dmb ish\n" \ "3:\n" \ " .pushsection .fixup,\"ax\"\n" \ @@ -57,23 +57,23 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr) switch (op) { case FUTEX_OP_SET: - __futex_atomic_op("mov %w0, %w4", + __futex_atomic_op("mov %w3, %w4", ret, oldval, uaddr, tmp, oparg); break; case FUTEX_OP_ADD: - __futex_atomic_op("add %w0, %w1, %w4", + __futex_atomic_op("add %w3, %w1, %w4", ret, oldval, uaddr, tmp, oparg); break; case FUTEX_OP_OR: - __futex_atomic_op("orr %w0, %w1, %w4", + __futex_atomic_op("orr %w3, %w1, %w4", ret, oldval, uaddr, tmp, oparg); break; case FUTEX_OP_ANDN: - __futex_atomic_op("and %w0, %w1, %w4", + __futex_atomic_op("and %w3, %w1, %w4", ret, oldval, uaddr, tmp, ~oparg); break; case FUTEX_OP_XOR: - __futex_atomic_op("eor %w0, %w1, %w4", + __futex_atomic_op("eor %w3, %w1, %w4", ret, oldval, uaddr, tmp, oparg); break; default: diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index b0742a16c6c9..ebeefcf835e8 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -445,6 +445,17 @@ static inline int kvm_read_guest_lock(struct kvm *kvm, return ret; } +static inline int kvm_write_guest_lock(struct kvm *kvm, gpa_t gpa, + const void *data, unsigned long len) +{ + int srcu_idx = srcu_read_lock(&kvm->srcu); + int ret = kvm_write_guest(kvm, gpa, data, len); + + srcu_read_unlock(&kvm->srcu, srcu_idx); + + return ret; +} + #ifdef CONFIG_KVM_INDIRECT_VECTORS /* * EL2 vectors can be mapped and rerouted in a number of ways, diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h index 905e1bb0e7bd..cd9f4e9d04d3 100644 --- a/arch/arm64/include/asm/module.h +++ b/arch/arm64/include/asm/module.h @@ -73,4 +73,9 @@ static inline bool is_forbidden_offset_for_adrp(void *place) struct plt_entry get_plt_entry(u64 dst, void *pc); bool plt_entries_equal(const struct plt_entry *a, const struct plt_entry *b); +static inline bool plt_entry_is_initialized(const struct plt_entry *e) +{ + return e->adrp || e->add || e->br; +} + #endif /* __ASM_MODULE_H */ diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h index ad8be16a39c9..a179df3674a1 100644 --- a/arch/arm64/include/asm/syscall.h +++ b/arch/arm64/include/asm/syscall.h @@ -65,52 +65,22 @@ static inline void syscall_set_return_value(struct task_struct *task, static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args) { - if (n == 0) - return; - - if (i + n > SYSCALL_MAX_ARGS) { - unsigned long *args_bad = args + SYSCALL_MAX_ARGS - i; - unsigned int n_bad = n + i - SYSCALL_MAX_ARGS; - pr_warning("%s called with max args %d, handling only %d\n", - __func__, i + n, SYSCALL_MAX_ARGS); - memset(args_bad, 0, n_bad * sizeof(args[0])); - } - - if (i == 0) { - args[0] = regs->orig_x0; - args++; - i++; - n--; - } - - memcpy(args, ®s->regs[i], n * sizeof(args[0])); + args[0] = regs->orig_x0; + args++; + + memcpy(args, ®s->regs[1], 5 * sizeof(args[0])); } static inline void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, const unsigned long *args) { - if (n == 0) - return; - - if (i + n > SYSCALL_MAX_ARGS) { - pr_warning("%s called with max args %d, handling only %d\n", - __func__, i + n, SYSCALL_MAX_ARGS); - n = SYSCALL_MAX_ARGS - i; - } - - if (i == 0) { - regs->orig_x0 = args[0]; - args++; - i++; - n--; - } - - memcpy(®s->regs[i], args, n * sizeof(args[0])); + regs->orig_x0 = args[0]; + args++; + + memcpy(®s->regs[1], args, 5 * sizeof(args[0])); } /* diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index d1dd93436e1e..f2a83ff6b73c 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -44,7 +44,7 @@ #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5) #define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800) -#define __NR_compat_syscalls 424 +#define __NR_compat_syscalls 428 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 5590f2623690..23f1a44acada 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -866,6 +866,14 @@ __SYSCALL(__NR_rt_sigtimedwait_time64, compat_sys_rt_sigtimedwait_time64) __SYSCALL(__NR_futex_time64, sys_futex) #define __NR_sched_rr_get_interval_time64 423 __SYSCALL(__NR_sched_rr_get_interval_time64, sys_sched_rr_get_interval) +#define __NR_pidfd_send_signal 424 +__SYSCALL(__NR_pidfd_send_signal, sys_pidfd_send_signal) +#define __NR_io_uring_setup 425 +__SYSCALL(__NR_io_uring_setup, sys_io_uring_setup) +#define __NR_io_uring_enter 426 +__SYSCALL(__NR_io_uring_enter, sys_io_uring_enter) +#define __NR_io_uring_register 427 +__SYSCALL(__NR_io_uring_register, sys_io_uring_register) /* * Please add new compat syscalls above this comment and update diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index 8e4431a8821f..65a51331088e 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -103,12 +103,16 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) * to be revisited if support for multiple ftrace entry points * is added in the future, but for now, the pr_err() below * deals with a theoretical issue only. + * + * Note that PLTs are place relative, and plt_entries_equal() + * checks whether they point to the same target. Here, we need + * to check if the actual opcodes are in fact identical, + * regardless of the offset in memory so use memcmp() instead. */ trampoline = get_plt_entry(addr, mod->arch.ftrace_trampoline); - if (!plt_entries_equal(mod->arch.ftrace_trampoline, - &trampoline)) { - if (!plt_entries_equal(mod->arch.ftrace_trampoline, - &(struct plt_entry){})) { + if (memcmp(mod->arch.ftrace_trampoline, &trampoline, + sizeof(trampoline))) { + if (plt_entry_is_initialized(mod->arch.ftrace_trampoline)) { pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n"); return -EINVAL; } diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c index 5ba4465e44f0..ea94cf8f9dc6 100644 --- a/arch/arm64/kernel/sdei.c +++ b/arch/arm64/kernel/sdei.c @@ -94,6 +94,9 @@ static bool on_sdei_normal_stack(unsigned long sp, struct stack_info *info) unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_normal_ptr); unsigned long high = low + SDEI_STACK_SIZE; + if (!low) + return false; + if (sp < low || sp >= high) return false; @@ -111,6 +114,9 @@ static bool on_sdei_critical_stack(unsigned long sp, struct stack_info *info) unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_critical_ptr); unsigned long high = low + SDEI_STACK_SIZE; + if (!low) + return false; + if (sp < low || sp >= high) return false; diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index f8482fe5a190..413d566405d1 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -217,7 +217,7 @@ static void __init request_standard_resources(void) num_standard_resources = memblock.memory.cnt; res_size = num_standard_resources * sizeof(*standard_resources); - standard_resources = memblock_alloc_low(res_size, SMP_CACHE_BYTES); + standard_resources = memblock_alloc(res_size, SMP_CACHE_BYTES); if (!standard_resources) panic("%s: Failed to allocate %zu bytes\n", __func__, res_size); diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 8ad119c3f665..29755989f616 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -102,10 +102,16 @@ static void dump_instr(const char *lvl, struct pt_regs *regs) void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) { struct stackframe frame; - int skip; + int skip = 0; pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk); + if (regs) { + if (user_mode(regs)) + return; + skip = 1; + } + if (!tsk) tsk = current; @@ -126,7 +132,6 @@ void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) frame.graph = 0; #endif - skip = !!regs; printk("Call trace:\n"); do { /* skip until specified stack frame */ @@ -176,15 +181,13 @@ static int __die(const char *str, int err, struct pt_regs *regs) return ret; print_modules(); - __show_regs(regs); pr_emerg("Process %.*s (pid: %d, stack limit = 0x%p)\n", TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk), end_of_stack(tsk)); + show_regs(regs); - if (!user_mode(regs)) { - dump_backtrace(regs, tsk); + if (!user_mode(regs)) dump_instr(KERN_EMERG, regs); - } return ret; } diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index f16a5f8ff2b4..e2a0500cd7a2 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -123,6 +123,9 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) int ret = -EINVAL; bool loaded; + /* Reset PMU outside of the non-preemptible section */ + kvm_pmu_vcpu_reset(vcpu); + preempt_disable(); loaded = (vcpu->cpu != -1); if (loaded) @@ -170,9 +173,6 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) vcpu->arch.reset_state.reset = false; } - /* Reset PMU */ - kvm_pmu_vcpu_reset(vcpu); - /* Default workaround setup is enabled (if supported) */ if (kvm_arm_have_ssbd() == KVM_SSBD_KERNEL) vcpu->arch.workaround_flags |= VCPU_WORKAROUND_2_FLAG; diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 6bc135042f5e..7cae155e81a5 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -363,7 +363,7 @@ void __init arm64_memblock_init(void) * Otherwise, this is a no-op */ u64 base = phys_initrd_start & PAGE_MASK; - u64 size = PAGE_ALIGN(phys_initrd_size); + u64 size = PAGE_ALIGN(phys_initrd_start + phys_initrd_size) - base; /* * We can only add back the initrd memory if we don't end up diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild index 63b4a1705182..249c9f6f26dc 100644 --- a/arch/c6x/include/asm/Kbuild +++ b/arch/c6x/include/asm/Kbuild @@ -19,6 +19,7 @@ generic-y += irq_work.h generic-y += kdebug.h generic-y += kmap_types.h generic-y += kprobes.h +generic-y += kvm_para.h generic-y += local.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h diff --git a/arch/c6x/include/asm/syscall.h b/arch/c6x/include/asm/syscall.h index ae2be315ee9c..15ba8599858e 100644 --- a/arch/c6x/include/asm/syscall.h +++ b/arch/c6x/include/asm/syscall.h @@ -46,78 +46,27 @@ static inline void syscall_set_return_value(struct task_struct *task, } static inline void syscall_get_arguments(struct task_struct *task, - struct pt_regs *regs, unsigned int i, - unsigned int n, unsigned long *args) + struct pt_regs *regs, + unsigned long *args) { - switch (i) { - case 0: - if (!n--) - break; - *args++ = regs->a4; - case 1: - if (!n--) - break; - *args++ = regs->b4; - case 2: - if (!n--) - break; - *args++ = regs->a6; - case 3: - if (!n--) - break; - *args++ = regs->b6; - case 4: - if (!n--) - break; - *args++ = regs->a8; - case 5: - if (!n--) - break; - *args++ = regs->b8; - case 6: - if (!n--) - break; - default: - BUG(); - } + *args++ = regs->a4; + *args++ = regs->b4; + *args++ = regs->a6; + *args++ = regs->b6; + *args++ = regs->a8; + *args = regs->b8; } static inline void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, const unsigned long *args) { - switch (i) { - case 0: - if (!n--) - break; - regs->a4 = *args++; - case 1: - if (!n--) - break; - regs->b4 = *args++; - case 2: - if (!n--) - break; - regs->a6 = *args++; - case 3: - if (!n--) - break; - regs->b6 = *args++; - case 4: - if (!n--) - break; - regs->a8 = *args++; - case 5: - if (!n--) - break; - regs->a9 = *args++; - case 6: - if (!n) - break; - default: - BUG(); - } + regs->a4 = *args++; + regs->b4 = *args++; + regs->a6 = *args++; + regs->b6 = *args++; + regs->a8 = *args++; + regs->a9 = *args; } #endif /* __ASM_C6X_SYSCALLS_H */ diff --git a/arch/c6x/include/uapi/asm/Kbuild b/arch/c6x/include/uapi/asm/Kbuild index 755bb11323d8..1c72f04ff75d 100644 --- a/arch/c6x/include/uapi/asm/Kbuild +++ b/arch/c6x/include/uapi/asm/Kbuild @@ -1,2 +1 @@ -generic-y += kvm_para.h generic-y += ucontext.h diff --git a/arch/csky/include/asm/syscall.h b/arch/csky/include/asm/syscall.h index d637445737b7..bda0a446c63e 100644 --- a/arch/csky/include/asm/syscall.h +++ b/arch/csky/include/asm/syscall.h @@ -43,30 +43,20 @@ syscall_set_return_value(struct task_struct *task, struct pt_regs *regs, static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args) + unsigned long *args) { - BUG_ON(i + n > 6); - if (i == 0) { - args[0] = regs->orig_a0; - args++; - i++; - n--; - } - memcpy(args, ®s->a1 + i * sizeof(regs->a1), n * sizeof(args[0])); + args[0] = regs->orig_a0; + args++; + memcpy(args, ®s->a1, 5 * sizeof(args[0])); } static inline void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, const unsigned long *args) + const unsigned long *args) { - BUG_ON(i + n > 6); - if (i == 0) { - regs->orig_a0 = args[0]; - args++; - i++; - n--; - } - memcpy(®s->a1 + i * sizeof(regs->a1), args, n * sizeof(regs->a0)); + regs->orig_a0 = args[0]; + args++; + memcpy(®s->a1, args, 5 * sizeof(regs->a1)); } static inline int diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild index 3e7c8ecf151e..e3dead402e5f 100644 --- a/arch/h8300/include/asm/Kbuild +++ b/arch/h8300/include/asm/Kbuild @@ -23,6 +23,7 @@ generic-y += irq_work.h generic-y += kdebug.h generic-y += kmap_types.h generic-y += kprobes.h +generic-y += kvm_para.h generic-y += linkage.h generic-y += local.h generic-y += local64.h diff --git a/arch/h8300/include/asm/syscall.h b/arch/h8300/include/asm/syscall.h index 924990401237..ddd483c6ca95 100644 --- a/arch/h8300/include/asm/syscall.h +++ b/arch/h8300/include/asm/syscall.h @@ -17,34 +17,14 @@ syscall_get_nr(struct task_struct *task, struct pt_regs *regs) static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args) + unsigned long *args) { - BUG_ON(i + n > 6); - - while (n > 0) { - switch (i) { - case 0: - *args++ = regs->er1; - break; - case 1: - *args++ = regs->er2; - break; - case 2: - *args++ = regs->er3; - break; - case 3: - *args++ = regs->er4; - break; - case 4: - *args++ = regs->er5; - break; - case 5: - *args++ = regs->er6; - break; - } - i++; - n--; - } + *args++ = regs->er1; + *args++ = regs->er2; + *args++ = regs->er3; + *args++ = regs->er4; + *args++ = regs->er5; + *args = regs->er6; } diff --git a/arch/h8300/include/uapi/asm/Kbuild b/arch/h8300/include/uapi/asm/Kbuild index 755bb11323d8..1c72f04ff75d 100644 --- a/arch/h8300/include/uapi/asm/Kbuild +++ b/arch/h8300/include/uapi/asm/Kbuild @@ -1,2 +1 @@ -generic-y += kvm_para.h generic-y += ucontext.h diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild index b25fd42aa0f4..d046e8ccdf78 100644 --- a/arch/hexagon/include/asm/Kbuild +++ b/arch/hexagon/include/asm/Kbuild @@ -19,6 +19,7 @@ generic-y += irq_work.h generic-y += kdebug.h generic-y += kmap_types.h generic-y += kprobes.h +generic-y += kvm_para.h generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h diff --git a/arch/hexagon/include/asm/syscall.h b/arch/hexagon/include/asm/syscall.h index 4af9c7b6f13a..ae3a1e24fabd 100644 --- a/arch/hexagon/include/asm/syscall.h +++ b/arch/hexagon/include/asm/syscall.h @@ -37,10 +37,8 @@ static inline long syscall_get_nr(struct task_struct *task, static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args) { - BUG_ON(i + n > 6); - memcpy(args, &(®s->r00)[i], n * sizeof(args[0])); + memcpy(args, &(®s->r00)[0], 6 * sizeof(args[0])); } #endif diff --git a/arch/hexagon/include/uapi/asm/kvm_para.h b/arch/hexagon/include/uapi/asm/kvm_para.h deleted file mode 100644 index baacc4996d18..000000000000 --- a/arch/hexagon/include/uapi/asm/kvm_para.h +++ /dev/null @@ -1,2 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#include <asm-generic/kvm_para.h> diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild index 43e21fe3499c..11f191689c9e 100644 --- a/arch/ia64/include/asm/Kbuild +++ b/arch/ia64/include/asm/Kbuild @@ -2,6 +2,7 @@ generated-y += syscall_table.h generic-y += compat.h generic-y += exec.h generic-y += irq_work.h +generic-y += kvm_para.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += preempt.h diff --git a/arch/ia64/include/asm/syscall.h b/arch/ia64/include/asm/syscall.h index 1d0b875fec44..0d9e7fab4a79 100644 --- a/arch/ia64/include/asm/syscall.h +++ b/arch/ia64/include/asm/syscall.h @@ -59,26 +59,19 @@ static inline void syscall_set_return_value(struct task_struct *task, } extern void ia64_syscall_get_set_arguments(struct task_struct *task, - struct pt_regs *regs, unsigned int i, unsigned int n, - unsigned long *args, int rw); + struct pt_regs *regs, unsigned long *args, int rw); static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args) { - BUG_ON(i + n > 6); - - ia64_syscall_get_set_arguments(task, regs, i, n, args, 0); + ia64_syscall_get_set_arguments(task, regs, args, 0); } static inline void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args) { - BUG_ON(i + n > 6); - - ia64_syscall_get_set_arguments(task, regs, i, n, args, 1); + ia64_syscall_get_set_arguments(task, regs, args, 1); } static inline int syscall_get_arch(void) diff --git a/arch/ia64/include/uapi/asm/Kbuild b/arch/ia64/include/uapi/asm/Kbuild index 20018cb883a9..62a9522af51e 100644 --- a/arch/ia64/include/uapi/asm/Kbuild +++ b/arch/ia64/include/uapi/asm/Kbuild @@ -1,2 +1 @@ generated-y += unistd_64.h -generic-y += kvm_para.h diff --git a/arch/ia64/kernel/ptrace.c b/arch/ia64/kernel/ptrace.c index 6d50ede0ed69..bf9c24d9ce84 100644 --- a/arch/ia64/kernel/ptrace.c +++ b/arch/ia64/kernel/ptrace.c @@ -2179,12 +2179,11 @@ static void syscall_get_set_args_cb(struct unw_frame_info *info, void *data) } void ia64_syscall_get_set_arguments(struct task_struct *task, - struct pt_regs *regs, unsigned int i, unsigned int n, - unsigned long *args, int rw) + struct pt_regs *regs, unsigned long *args, int rw) { struct syscall_get_set_args data = { - .i = i, - .n = n, + .i = 0, + .n = 6, .args = args, .regs = regs, .rw = rw, diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index ab9cda5f6136..56e3d0b685e1 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -344,3 +344,7 @@ 332 common pkey_free sys_pkey_free 333 common rseq sys_rseq # 334 through 423 are reserved to sync up with other architectures +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild index 95f8f631c4df..2c359d9e80f6 100644 --- a/arch/m68k/include/asm/Kbuild +++ b/arch/m68k/include/asm/Kbuild @@ -13,6 +13,7 @@ generic-y += irq_work.h generic-y += kdebug.h generic-y += kmap_types.h generic-y += kprobes.h +generic-y += kvm_para.h generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h diff --git a/arch/m68k/include/uapi/asm/Kbuild b/arch/m68k/include/uapi/asm/Kbuild index 8a7ad40be463..7417847dc438 100644 --- a/arch/m68k/include/uapi/asm/Kbuild +++ b/arch/m68k/include/uapi/asm/Kbuild @@ -1,2 +1 @@ generated-y += unistd_32.h -generic-y += kvm_para.h diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 125c14178979..df4ec3ec71d1 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -423,3 +423,7 @@ 421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait 422 common futex_time64 sys_futex 423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild index 791cc8d54d0a..1a8285c3f693 100644 --- a/arch/microblaze/include/asm/Kbuild +++ b/arch/microblaze/include/asm/Kbuild @@ -17,6 +17,7 @@ generic-y += irq_work.h generic-y += kdebug.h generic-y += kmap_types.h generic-y += kprobes.h +generic-y += kvm_para.h generic-y += linkage.h generic-y += local.h generic-y += local64.h diff --git a/arch/microblaze/include/asm/syscall.h b/arch/microblaze/include/asm/syscall.h index 220decd605a4..833d3a53dab3 100644 --- a/arch/microblaze/include/asm/syscall.h +++ b/arch/microblaze/include/asm/syscall.h @@ -82,18 +82,22 @@ static inline void microblaze_set_syscall_arg(struct pt_regs *regs, static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args) { + unsigned int i = 0; + unsigned int n = 6; + while (n--) *args++ = microblaze_get_syscall_arg(regs, i++); } static inline void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, const unsigned long *args) { + unsigned int i = 0; + unsigned int n = 6; + while (n--) microblaze_set_syscall_arg(regs, i++, *args++); } diff --git a/arch/microblaze/include/uapi/asm/Kbuild b/arch/microblaze/include/uapi/asm/Kbuild index 3ce84fbb2678..13f59631c576 100644 --- a/arch/microblaze/include/uapi/asm/Kbuild +++ b/arch/microblaze/include/uapi/asm/Kbuild @@ -1,3 +1,2 @@ generated-y += unistd_32.h -generic-y += kvm_para.h generic-y += ucontext.h diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index 8ee3a8c18498..4964947732af 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -429,3 +429,7 @@ 421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait 422 common futex_time64 sys_futex 423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c index 4a70c5de8c92..25a57895a3a3 100644 --- a/arch/mips/ath79/setup.c +++ b/arch/mips/ath79/setup.c @@ -210,12 +210,6 @@ const char *get_system_type(void) return ath79_sys_type; } -int get_c0_perfcount_int(void) -{ - return ATH79_MISC_IRQ(5); -} -EXPORT_SYMBOL_GPL(get_c0_perfcount_int); - unsigned int get_c0_compare_int(void) { return CP0_LEGACY_COMPARE_IRQ; diff --git a/arch/mips/configs/generic/board-ocelot.config b/arch/mips/configs/generic/board-ocelot.config index f607888d2483..184eb65a6ba7 100644 --- a/arch/mips/configs/generic/board-ocelot.config +++ b/arch/mips/configs/generic/board-ocelot.config @@ -1,6 +1,10 @@ # require CONFIG_CPU_MIPS32_R2=y CONFIG_LEGACY_BOARD_OCELOT=y +CONFIG_FIT_IMAGE_FDT_OCELOT=y + +CONFIG_BRIDGE=y +CONFIG_GENERIC_PHY=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y @@ -19,6 +23,8 @@ CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_OF_PLATFORM=y CONFIG_NETDEVICES=y +CONFIG_NET_SWITCHDEV=y +CONFIG_NET_DSA=y CONFIG_MSCC_OCELOT_SWITCH=y CONFIG_MSCC_OCELOT_SWITCH_OCELOT=y CONFIG_MDIO_MSCC_MIIM=y @@ -35,6 +41,8 @@ CONFIG_SPI_DESIGNWARE=y CONFIG_SPI_DW_MMIO=y CONFIG_SPI_SPIDEV=y +CONFIG_PINCTRL_OCELOT=y + CONFIG_GPIO_SYSFS=y CONFIG_POWER_RESET=y diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h index 6cf8ffb5367e..a2b4748655df 100644 --- a/arch/mips/include/asm/syscall.h +++ b/arch/mips/include/asm/syscall.h @@ -116,9 +116,10 @@ static inline void syscall_set_return_value(struct task_struct *task, static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args) { + unsigned int i = 0; + unsigned int n = 6; int ret; /* O32 ABI syscall() */ diff --git a/arch/mips/kernel/kgdb.c b/arch/mips/kernel/kgdb.c index 6e574c02e4c3..ea781b29f7f1 100644 --- a/arch/mips/kernel/kgdb.c +++ b/arch/mips/kernel/kgdb.c @@ -33,6 +33,7 @@ #include <asm/processor.h> #include <asm/sigcontext.h> #include <linux/uaccess.h> +#include <asm/irq_regs.h> static struct hard_trap_info { unsigned char tt; /* Trap type code for MIPS R3xxx and R4xxx */ @@ -214,7 +215,7 @@ void kgdb_call_nmi_hook(void *ignored) old_fs = get_fs(); set_fs(KERNEL_DS); - kgdb_nmicallback(raw_smp_processor_id(), NULL); + kgdb_nmicallback(raw_smp_processor_id(), get_irq_regs()); set_fs(old_fs); } diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index 0057c910bc2f..3a62f80958e1 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -1419,7 +1419,7 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall) sd.nr = syscall; sd.arch = syscall_get_arch(); - syscall_get_arguments(current, regs, 0, 6, args); + syscall_get_arguments(current, regs, args); for (i = 0; i < 6; i++) sd.args[i] = args[i]; sd.instruction_pointer = KSTK_EIP(current); diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index f158c5894a9a..feb2653490df 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -125,7 +125,7 @@ trace_a_syscall: subu t1, v0, __NR_O32_Linux move a1, v0 bnez t1, 1f /* __NR_syscall at offset 0 */ - lw a1, PT_R4(sp) /* Arg1 for __NR_syscall case */ + ld a1, PT_R4(sp) /* Arg1 for __NR_syscall case */ .set pop 1: jal syscall_trace_enter diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 15f4117900ee..9392dfe33f97 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -362,3 +362,7 @@ 421 n32 rt_sigtimedwait_time64 compat_sys_rt_sigtimedwait_time64 422 n32 futex_time64 sys_futex 423 n32 sched_rr_get_interval_time64 sys_sched_rr_get_interval +424 n32 pidfd_send_signal sys_pidfd_send_signal +425 n32 io_uring_setup sys_io_uring_setup +426 n32 io_uring_enter sys_io_uring_enter +427 n32 io_uring_register sys_io_uring_register diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index c85502e67b44..cd0c8aa21fba 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -338,3 +338,7 @@ 327 n64 rseq sys_rseq 328 n64 io_pgetevents sys_io_pgetevents # 329 through 423 are reserved to sync up with other architectures +424 n64 pidfd_send_signal sys_pidfd_send_signal +425 n64 io_uring_setup sys_io_uring_setup +426 n64 io_uring_enter sys_io_uring_enter +427 n64 io_uring_register sys_io_uring_register diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 2e063d0f837e..e849e8ffe4a2 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -411,3 +411,7 @@ 421 o32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64 422 o32 futex_time64 sys_futex sys_futex 423 o32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval +424 o32 pidfd_send_signal sys_pidfd_send_signal +425 o32 io_uring_setup sys_io_uring_setup +426 o32 io_uring_enter sys_io_uring_enter +427 o32 io_uring_register sys_io_uring_register diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c index 0effd3cba9a7..98bf0c222b5f 100644 --- a/arch/mips/net/ebpf_jit.c +++ b/arch/mips/net/ebpf_jit.c @@ -186,8 +186,9 @@ enum which_ebpf_reg { * separate frame pointer, so BPF_REG_10 relative accesses are * adjusted to be $sp relative. */ -int ebpf_to_mips_reg(struct jit_ctx *ctx, const struct bpf_insn *insn, - enum which_ebpf_reg w) +static int ebpf_to_mips_reg(struct jit_ctx *ctx, + const struct bpf_insn *insn, + enum which_ebpf_reg w) { int ebpf_reg = (w == src_reg || w == src_reg_no_fp) ? insn->src_reg : insn->dst_reg; diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c index 710a59764b01..a32f843cdbe0 100644 --- a/arch/mips/sgi-ip27/ip27-irq.c +++ b/arch/mips/sgi-ip27/ip27-irq.c @@ -118,7 +118,6 @@ static void shutdown_bridge_irq(struct irq_data *d) { struct hub_irq_data *hd = irq_data_get_irq_chip_data(d); struct bridge_controller *bc; - int pin = hd->pin; if (!hd) return; @@ -126,7 +125,7 @@ static void shutdown_bridge_irq(struct irq_data *d) disable_hub_irq(d); bc = hd->bc; - bridge_clr(bc, b_int_enable, (1 << pin)); + bridge_clr(bc, b_int_enable, (1 << hd->pin)); bridge_read(bc, b_wid_tflush); } diff --git a/arch/nds32/include/asm/syscall.h b/arch/nds32/include/asm/syscall.h index f7e5e86765fe..671ebd357496 100644 --- a/arch/nds32/include/asm/syscall.h +++ b/arch/nds32/include/asm/syscall.h @@ -108,81 +108,41 @@ void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs, * syscall_get_arguments - extract system call parameter values * @task: task of interest, must be blocked * @regs: task_pt_regs() of @task - * @i: argument index [0,5] - * @n: number of arguments; n+i must be [1,6]. * @args: array filled with argument values * - * Fetches @n arguments to the system call starting with the @i'th argument - * (from 0 through 5). Argument @i is stored in @args[0], and so on. - * An arch inline version is probably optimal when @i and @n are constants. + * Fetches 6 arguments to the system call (from 0 through 5). The first + * argument is stored in @args[0], and so on. * * It's only valid to call this when @task is stopped for tracing on * entry to a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT. - * It's invalid to call this with @i + @n > 6; we only support system calls - * taking up to 6 arguments. */ #define SYSCALL_MAX_ARGS 6 void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args) + unsigned long *args) { - if (n == 0) - return; - if (i + n > SYSCALL_MAX_ARGS) { - unsigned long *args_bad = args + SYSCALL_MAX_ARGS - i; - unsigned int n_bad = n + i - SYSCALL_MAX_ARGS; - pr_warning("%s called with max args %d, handling only %d\n", - __func__, i + n, SYSCALL_MAX_ARGS); - memset(args_bad, 0, n_bad * sizeof(args[0])); - memset(args_bad, 0, n_bad * sizeof(args[0])); - } - - if (i == 0) { - args[0] = regs->orig_r0; - args++; - i++; - n--; - } - - memcpy(args, ®s->uregs[0] + i, n * sizeof(args[0])); + args[0] = regs->orig_r0; + args++; + memcpy(args, ®s->uregs[0] + 1, 5 * sizeof(args[0])); } /** * syscall_set_arguments - change system call parameter value * @task: task of interest, must be in system call entry tracing * @regs: task_pt_regs() of @task - * @i: argument index [0,5] - * @n: number of arguments; n+i must be [1,6]. * @args: array of argument values to store * - * Changes @n arguments to the system call starting with the @i'th argument. - * Argument @i gets value @args[0], and so on. - * An arch inline version is probably optimal when @i and @n are constants. + * Changes 6 arguments to the system call. The first argument gets value + * @args[0], and so on. * * It's only valid to call this when @task is stopped for tracing on * entry to a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT. - * It's invalid to call this with @i + @n > 6; we only support system calls - * taking up to 6 arguments. */ void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, const unsigned long *args) { - if (n == 0) - return; - - if (i + n > SYSCALL_MAX_ARGS) { - pr_warn("%s called with max args %d, handling only %d\n", - __func__, i + n, SYSCALL_MAX_ARGS); - n = SYSCALL_MAX_ARGS - i; - } - - if (i == 0) { - regs->orig_r0 = args[0]; - args++; - i++; - n--; - } + regs->orig_r0 = args[0]; + args++; - memcpy(®s->uregs[0] + i, args, n * sizeof(args[0])); + memcpy(®s->uregs[0] + 1, args, 5 * sizeof(args[0])); } #endif /* _ASM_NDS32_SYSCALL_H */ diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild index 8fde4fa2c34f..88a667d12aaa 100644 --- a/arch/nios2/include/asm/Kbuild +++ b/arch/nios2/include/asm/Kbuild @@ -23,6 +23,7 @@ generic-y += irq_work.h generic-y += kdebug.h generic-y += kmap_types.h generic-y += kprobes.h +generic-y += kvm_para.h generic-y += local.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h diff --git a/arch/nios2/include/asm/syscall.h b/arch/nios2/include/asm/syscall.h index 9de220854c4a..d7624ed06efb 100644 --- a/arch/nios2/include/asm/syscall.h +++ b/arch/nios2/include/asm/syscall.h @@ -58,81 +58,25 @@ static inline void syscall_set_return_value(struct task_struct *task, } static inline void syscall_get_arguments(struct task_struct *task, - struct pt_regs *regs, unsigned int i, unsigned int n, - unsigned long *args) + struct pt_regs *regs, unsigned long *args) { - BUG_ON(i + n > 6); - - switch (i) { - case 0: - if (!n--) - break; - *args++ = regs->r4; - case 1: - if (!n--) - break; - *args++ = regs->r5; - case 2: - if (!n--) - break; - *args++ = regs->r6; - case 3: - if (!n--) - break; - *args++ = regs->r7; - case 4: - if (!n--) - break; - *args++ = regs->r8; - case 5: - if (!n--) - break; - *args++ = regs->r9; - case 6: - if (!n--) - break; - default: - BUG(); - } + *args++ = regs->r4; + *args++ = regs->r5; + *args++ = regs->r6; + *args++ = regs->r7; + *args++ = regs->r8; + *args = regs->r9; } static inline void syscall_set_arguments(struct task_struct *task, - struct pt_regs *regs, unsigned int i, unsigned int n, - const unsigned long *args) + struct pt_regs *regs, const unsigned long *args) { - BUG_ON(i + n > 6); - - switch (i) { - case 0: - if (!n--) - break; - regs->r4 = *args++; - case 1: - if (!n--) - break; - regs->r5 = *args++; - case 2: - if (!n--) - break; - regs->r6 = *args++; - case 3: - if (!n--) - break; - regs->r7 = *args++; - case 4: - if (!n--) - break; - regs->r8 = *args++; - case 5: - if (!n--) - break; - regs->r9 = *args++; - case 6: - if (!n) - break; - default: - BUG(); - } + regs->r4 = *args++; + regs->r5 = *args++; + regs->r6 = *args++; + regs->r7 = *args++; + regs->r8 = *args++; + regs->r9 = *args; } #endif diff --git a/arch/nios2/include/uapi/asm/Kbuild b/arch/nios2/include/uapi/asm/Kbuild index 755bb11323d8..1c72f04ff75d 100644 --- a/arch/nios2/include/uapi/asm/Kbuild +++ b/arch/nios2/include/uapi/asm/Kbuild @@ -1,2 +1 @@ -generic-y += kvm_para.h generic-y += ucontext.h diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild index 5a73e2956ac4..22aa97136c01 100644 --- a/arch/openrisc/include/asm/Kbuild +++ b/arch/openrisc/include/asm/Kbuild @@ -20,6 +20,7 @@ generic-y += irq_work.h generic-y += kdebug.h generic-y += kmap_types.h generic-y += kprobes.h +generic-y += kvm_para.h generic-y += local.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h diff --git a/arch/openrisc/include/asm/syscall.h b/arch/openrisc/include/asm/syscall.h index 2db9f1cf0694..b4ff07c1baed 100644 --- a/arch/openrisc/include/asm/syscall.h +++ b/arch/openrisc/include/asm/syscall.h @@ -56,20 +56,16 @@ syscall_set_return_value(struct task_struct *task, struct pt_regs *regs, static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args) + unsigned long *args) { - BUG_ON(i + n > 6); - - memcpy(args, ®s->gpr[3 + i], n * sizeof(args[0])); + memcpy(args, ®s->gpr[3], 6 * sizeof(args[0])); } static inline void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, const unsigned long *args) + const unsigned long *args) { - BUG_ON(i + n > 6); - - memcpy(®s->gpr[3 + i], args, n * sizeof(args[0])); + memcpy(®s->gpr[3], args, 6 * sizeof(args[0])); } static inline int syscall_get_arch(void) diff --git a/arch/openrisc/include/uapi/asm/Kbuild b/arch/openrisc/include/uapi/asm/Kbuild index 755bb11323d8..1c72f04ff75d 100644 --- a/arch/openrisc/include/uapi/asm/Kbuild +++ b/arch/openrisc/include/uapi/asm/Kbuild @@ -1,2 +1 @@ -generic-y += kvm_para.h generic-y += ucontext.h diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild index 6f49e77d82a2..9bcd0c903dbb 100644 --- a/arch/parisc/include/asm/Kbuild +++ b/arch/parisc/include/asm/Kbuild @@ -11,6 +11,7 @@ generic-y += irq_regs.h generic-y += irq_work.h generic-y += kdebug.h generic-y += kprobes.h +generic-y += kvm_para.h generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h diff --git a/arch/parisc/include/asm/ptrace.h b/arch/parisc/include/asm/ptrace.h index 2a27b275ab09..9ff033d261ab 100644 --- a/arch/parisc/include/asm/ptrace.h +++ b/arch/parisc/include/asm/ptrace.h @@ -22,13 +22,14 @@ unsigned long profile_pc(struct pt_regs *); static inline unsigned long regs_return_value(struct pt_regs *regs) { - return regs->gr[20]; + return regs->gr[28]; } static inline void instruction_pointer_set(struct pt_regs *regs, unsigned long val) { - regs->iaoq[0] = val; + regs->iaoq[0] = val; + regs->iaoq[1] = val + 4; } /* Query offset/name of register from its name/offset */ diff --git a/arch/parisc/include/asm/syscall.h b/arch/parisc/include/asm/syscall.h index 8bff1a58c97f..62a6d477fae0 100644 --- a/arch/parisc/include/asm/syscall.h +++ b/arch/parisc/include/asm/syscall.h @@ -18,29 +18,15 @@ static inline long syscall_get_nr(struct task_struct *tsk, } static inline void syscall_get_arguments(struct task_struct *tsk, - struct pt_regs *regs, unsigned int i, - unsigned int n, unsigned long *args) + struct pt_regs *regs, + unsigned long *args) { - BUG_ON(i); - - switch (n) { - case 6: - args[5] = regs->gr[21]; - case 5: - args[4] = regs->gr[22]; - case 4: - args[3] = regs->gr[23]; - case 3: - args[2] = regs->gr[24]; - case 2: - args[1] = regs->gr[25]; - case 1: - args[0] = regs->gr[26]; - case 0: - break; - default: - BUG(); - } + args[5] = regs->gr[21]; + args[4] = regs->gr[22]; + args[3] = regs->gr[23]; + args[2] = regs->gr[24]; + args[1] = regs->gr[25]; + args[0] = regs->gr[26]; } static inline long syscall_get_return_value(struct task_struct *task, diff --git a/arch/parisc/include/uapi/asm/Kbuild b/arch/parisc/include/uapi/asm/Kbuild index 22fdbd08cdc8..2bd5b392277c 100644 --- a/arch/parisc/include/uapi/asm/Kbuild +++ b/arch/parisc/include/uapi/asm/Kbuild @@ -1,3 +1,2 @@ generated-y += unistd_32.h generated-y += unistd_64.h -generic-y += kvm_para.h diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index eb39e7e380d7..841db71958cd 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -210,12 +210,6 @@ void __cpuidle arch_cpu_idle(void) static int __init parisc_idle_init(void) { - const char *marker; - - /* check QEMU/SeaBIOS marker in PAGE0 */ - marker = (char *) &PAGE0->pad0; - running_on_qemu = (memcmp(marker, "SeaBIOS", 8) == 0); - if (!running_on_qemu) cpu_idle_poll_ctrl(1); diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c index 15dd9e21be7e..d908058d05c1 100644 --- a/arch/parisc/kernel/setup.c +++ b/arch/parisc/kernel/setup.c @@ -397,6 +397,9 @@ void __init start_parisc(void) int ret, cpunum; struct pdc_coproc_cfg coproc_cfg; + /* check QEMU/SeaBIOS marker in PAGE0 */ + running_on_qemu = (memcmp(&PAGE0->pad0, "SeaBIOS", 8) == 0); + cpunum = smp_processor_id(); init_cpu_topology(); diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index b26766c6647d..fe8ca623add8 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -420,3 +420,7 @@ 421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64 422 32 futex_time64 sys_futex sys_futex 423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig index 5ba131c30f6b..1bcd468ab422 100644 --- a/arch/powerpc/configs/skiroot_defconfig +++ b/arch/powerpc/configs/skiroot_defconfig @@ -266,6 +266,7 @@ CONFIG_UDF_FS=m CONFIG_MSDOS_FS=m CONFIG_VFAT_FS=m CONFIG_PROC_KCORE=y +CONFIG_HUGETLBFS=y # CONFIG_MISC_FILESYSTEMS is not set # CONFIG_NETWORK_FILESYSTEMS is not set CONFIG_NLS=y diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index 598cdcdd1355..8ddd4a91bdc1 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -352,7 +352,7 @@ static inline bool strict_kernel_rwx_enabled(void) #if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME) && \ defined (CONFIG_PPC_64K_PAGES) #define MAX_PHYSMEM_BITS 51 -#elif defined(CONFIG_SPARSEMEM) +#elif defined(CONFIG_PPC64) #define MAX_PHYSMEM_BITS 46 #endif diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index c5698a523bb1..23f7ed796f38 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -302,6 +302,7 @@ /* Misc instructions for BPF compiler */ #define PPC_INST_LBZ 0x88000000 #define PPC_INST_LD 0xe8000000 +#define PPC_INST_LDX 0x7c00002a #define PPC_INST_LHZ 0xa0000000 #define PPC_INST_LWZ 0x80000000 #define PPC_INST_LHBRX 0x7c00062c @@ -309,6 +310,7 @@ #define PPC_INST_STB 0x98000000 #define PPC_INST_STH 0xb0000000 #define PPC_INST_STD 0xf8000000 +#define PPC_INST_STDX 0x7c00012a #define PPC_INST_STDU 0xf8000001 #define PPC_INST_STW 0x90000000 #define PPC_INST_STWU 0x94000000 diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h index 1a0e7a8b1c81..1243045bad2d 100644 --- a/arch/powerpc/include/asm/syscall.h +++ b/arch/powerpc/include/asm/syscall.h @@ -65,22 +65,20 @@ static inline void syscall_set_return_value(struct task_struct *task, static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args) { unsigned long val, mask = -1UL; - - BUG_ON(i + n > 6); + unsigned int n = 6; #ifdef CONFIG_COMPAT if (test_tsk_thread_flag(task, TIF_32BIT)) mask = 0xffffffff; #endif while (n--) { - if (n == 0 && i == 0) + if (n == 0) val = regs->orig_gpr3; else - val = regs->gpr[3 + i + n]; + val = regs->gpr[3 + n]; args[n] = val & mask; } @@ -88,15 +86,12 @@ static inline void syscall_get_arguments(struct task_struct *task, static inline void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, const unsigned long *args) { - BUG_ON(i + n > 6); - memcpy(®s->gpr[3 + i], args, n * sizeof(args[0])); + memcpy(®s->gpr[3], args, 6 * sizeof(args[0])); /* Also copy the first argument into orig_gpr3 */ - if (i == 0 && n > 0) - regs->orig_gpr3 = args[0]; + regs->orig_gpr3 = args[0]; } static inline int syscall_get_arch(void) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index a5b8fbae56a0..9481a117e242 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -656,11 +656,17 @@ EXC_COMMON_BEGIN(data_access_slb_common) ld r4,PACA_EXSLB+EX_DAR(r13) std r4,_DAR(r1) addi r3,r1,STACK_FRAME_OVERHEAD +BEGIN_MMU_FTR_SECTION + /* HPT case, do SLB fault */ bl do_slb_fault cmpdi r3,0 bne- 1f b fast_exception_return 1: /* Error case */ +MMU_FTR_SECTION_ELSE + /* Radix case, access is outside page table range */ + li r3,-EFAULT +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) std r3,RESULT(r1) bl save_nvgprs RECONCILE_IRQ_STATE(r10, r11) @@ -705,11 +711,17 @@ EXC_COMMON_BEGIN(instruction_access_slb_common) EXCEPTION_PROLOG_COMMON(0x480, PACA_EXSLB) ld r4,_NIP(r1) addi r3,r1,STACK_FRAME_OVERHEAD +BEGIN_MMU_FTR_SECTION + /* HPT case, do SLB fault */ bl do_slb_fault cmpdi r3,0 bne- 1f b fast_exception_return 1: /* Error case */ +MMU_FTR_SECTION_ELSE + /* Radix case, access is outside page table range */ + li r3,-EFAULT +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) std r3,RESULT(r1) bl save_nvgprs RECONCILE_IRQ_STATE(r10, r11) diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index 48051c8977c5..e25b615e9f9e 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -851,10 +851,6 @@ __secondary_start: tophys(r4,r2) addi r4,r4,THREAD /* phys address of our thread_struct */ mtspr SPRN_SPRG_THREAD,r4 -#ifdef CONFIG_PPC_RTAS - li r3,0 - stw r3, RTAS_SP(r4) /* 0 => not in RTAS */ -#endif lis r4, (swapper_pg_dir - PAGE_OFFSET)@h ori r4, r4, (swapper_pg_dir - PAGE_OFFSET)@l mtspr SPRN_SPRG_PGDIR, r4 @@ -941,10 +937,6 @@ start_here: tophys(r4,r2) addi r4,r4,THREAD /* init task's THREAD */ mtspr SPRN_SPRG_THREAD,r4 -#ifdef CONFIG_PPC_RTAS - li r3,0 - stw r3, RTAS_SP(r4) /* 0 => not in RTAS */ -#endif lis r4, (swapper_pg_dir - PAGE_OFFSET)@h ori r4, r4, (swapper_pg_dir - PAGE_OFFSET)@l mtspr SPRN_SPRG_PGDIR, r4 diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c index 683b5b3805bd..cd381e2291df 100644 --- a/arch/powerpc/kernel/kvm.c +++ b/arch/powerpc/kernel/kvm.c @@ -22,6 +22,7 @@ #include <linux/kvm_host.h> #include <linux/init.h> #include <linux/export.h> +#include <linux/kmemleak.h> #include <linux/kvm_para.h> #include <linux/slab.h> #include <linux/of.h> @@ -712,6 +713,12 @@ static void kvm_use_magic_page(void) static __init void kvm_free_tmp(void) { + /* + * Inform kmemleak about the hole in the .bss section since the + * corresponding pages will be unmapped with DEBUG_PAGEALLOC=y. + */ + kmemleak_free_part(&kvm_tmp[kvm_tmp_index], + ARRAY_SIZE(kvm_tmp) - kvm_tmp_index); free_reserved_area(&kvm_tmp[kvm_tmp_index], &kvm_tmp[ARRAY_SIZE(kvm_tmp)], -1, NULL); } diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index b18abb0c3dae..00f5a63c8d9a 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -505,3 +505,7 @@ 421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64 422 32 futex_time64 sys_futex sys_futex 423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S index 1e0bc5955a40..afd516b572f8 100644 --- a/arch/powerpc/kernel/vdso32/gettimeofday.S +++ b/arch/powerpc/kernel/vdso32/gettimeofday.S @@ -98,7 +98,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime) * can be used, r7 contains NSEC_PER_SEC. */ - lwz r5,WTOM_CLOCK_SEC(r9) + lwz r5,(WTOM_CLOCK_SEC+LOPART)(r9) lwz r6,WTOM_CLOCK_NSEC(r9) /* We now have our offset in r5,r6. We create a fake dependency diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index f02b04973710..f100e331e69b 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -543,14 +543,14 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, if (ret != H_SUCCESS) return ret; + idx = srcu_read_lock(&vcpu->kvm->srcu); + ret = kvmppc_tce_validate(stt, tce); if (ret != H_SUCCESS) - return ret; + goto unlock_exit; dir = iommu_tce_direction(tce); - idx = srcu_read_lock(&vcpu->kvm->srcu); - if ((dir != DMA_NONE) && kvmppc_tce_to_ua(vcpu->kvm, tce, &ua, NULL)) { ret = H_PARAMETER; goto unlock_exit; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 06964350b97a..b2b29d4f9842 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -3423,7 +3423,9 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit, vcpu->arch.shregs.sprg2 = mfspr(SPRN_SPRG2); vcpu->arch.shregs.sprg3 = mfspr(SPRN_SPRG3); - mtspr(SPRN_PSSCR, host_psscr); + /* Preserve PSSCR[FAKE_SUSPEND] until we've called kvmppc_save_tm_hv */ + mtspr(SPRN_PSSCR, host_psscr | + (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG)); mtspr(SPRN_HFSCR, host_hfscr); mtspr(SPRN_CIABR, host_ciabr); mtspr(SPRN_DAWR, host_dawr); diff --git a/arch/powerpc/lib/memcmp_64.S b/arch/powerpc/lib/memcmp_64.S index 844d8e774492..b7f6f6e0b6e8 100644 --- a/arch/powerpc/lib/memcmp_64.S +++ b/arch/powerpc/lib/memcmp_64.S @@ -215,11 +215,20 @@ _GLOBAL_TOC(memcmp) beq .Lzero .Lcmp_rest_lt8bytes: - /* Here we have only less than 8 bytes to compare with. at least s1 - * Address is aligned with 8 bytes. - * The next double words are load and shift right with appropriate - * bits. + /* + * Here we have less than 8 bytes to compare. At least s1 is aligned to + * 8 bytes, but s2 may not be. We must make sure s2 + 7 doesn't cross a + * page boundary, otherwise we might read past the end of the buffer and + * trigger a page fault. We use 4K as the conservative minimum page + * size. If we detect that case we go to the byte-by-byte loop. + * + * Otherwise the next double word is loaded from s1 and s2, and shifted + * right to compare the appropriate bits. */ + clrldi r6,r4,(64-12) // r6 = r4 & 0xfff + cmpdi r6,0xff8 + bgt .Lshort + subfic r6,r5,8 slwi r6,r6,3 LD rA,0,r3 diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c index e7a9c4f6bfca..8330f135294f 100644 --- a/arch/powerpc/mm/mmu_context_iommu.c +++ b/arch/powerpc/mm/mmu_context_iommu.c @@ -95,28 +95,15 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua, unsigned long entries, unsigned long dev_hpa, struct mm_iommu_table_group_mem_t **pmem) { - struct mm_iommu_table_group_mem_t *mem; - long i, ret, locked_entries = 0; + struct mm_iommu_table_group_mem_t *mem, *mem2; + long i, ret, locked_entries = 0, pinned = 0; unsigned int pageshift; - - mutex_lock(&mem_list_mutex); - - list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list, - next) { - /* Overlap? */ - if ((mem->ua < (ua + (entries << PAGE_SHIFT))) && - (ua < (mem->ua + - (mem->entries << PAGE_SHIFT)))) { - ret = -EINVAL; - goto unlock_exit; - } - - } + unsigned long entry, chunk; if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) { ret = mm_iommu_adjust_locked_vm(mm, entries, true); if (ret) - goto unlock_exit; + return ret; locked_entries = entries; } @@ -148,17 +135,27 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua, } down_read(&mm->mmap_sem); - ret = get_user_pages_longterm(ua, entries, FOLL_WRITE, mem->hpages, NULL); + chunk = (1UL << (PAGE_SHIFT + MAX_ORDER - 1)) / + sizeof(struct vm_area_struct *); + chunk = min(chunk, entries); + for (entry = 0; entry < entries; entry += chunk) { + unsigned long n = min(entries - entry, chunk); + + ret = get_user_pages_longterm(ua + (entry << PAGE_SHIFT), n, + FOLL_WRITE, mem->hpages + entry, NULL); + if (ret == n) { + pinned += n; + continue; + } + if (ret > 0) + pinned += ret; + break; + } up_read(&mm->mmap_sem); - if (ret != entries) { - /* free the reference taken */ - for (i = 0; i < ret; i++) - put_page(mem->hpages[i]); - - vfree(mem->hpas); - kfree(mem); - ret = -EFAULT; - goto unlock_exit; + if (pinned != entries) { + if (!ret) + ret = -EFAULT; + goto free_exit; } pageshift = PAGE_SHIFT; @@ -183,21 +180,43 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua, } good_exit: - ret = 0; atomic64_set(&mem->mapped, 1); mem->used = 1; mem->ua = ua; mem->entries = entries; - *pmem = mem; - list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list); + mutex_lock(&mem_list_mutex); -unlock_exit: - if (locked_entries && ret) - mm_iommu_adjust_locked_vm(mm, locked_entries, false); + list_for_each_entry_rcu(mem2, &mm->context.iommu_group_mem_list, next) { + /* Overlap? */ + if ((mem2->ua < (ua + (entries << PAGE_SHIFT))) && + (ua < (mem2->ua + + (mem2->entries << PAGE_SHIFT)))) { + ret = -EINVAL; + mutex_unlock(&mem_list_mutex); + goto free_exit; + } + } + + list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list); mutex_unlock(&mem_list_mutex); + *pmem = mem; + + return 0; + +free_exit: + /* free the reference taken */ + for (i = 0; i < pinned; i++) + put_page(mem->hpages[i]); + + vfree(mem->hpas); + kfree(mem); + +unlock_exit: + mm_iommu_adjust_locked_vm(mm, locked_entries, false); + return ret; } @@ -266,7 +285,7 @@ static void mm_iommu_release(struct mm_iommu_table_group_mem_t *mem) long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem) { long ret = 0; - unsigned long entries, dev_hpa; + unsigned long unlock_entries = 0; mutex_lock(&mem_list_mutex); @@ -287,17 +306,17 @@ long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem) goto unlock_exit; } + if (mem->dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) + unlock_entries = mem->entries; + /* @mapped became 0 so now mappings are disabled, release the region */ - entries = mem->entries; - dev_hpa = mem->dev_hpa; mm_iommu_release(mem); - if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) - mm_iommu_adjust_locked_vm(mm, entries, false); - unlock_exit: mutex_unlock(&mem_list_mutex); + mm_iommu_adjust_locked_vm(mm, unlock_entries, false); + return ret; } EXPORT_SYMBOL_GPL(mm_iommu_put); diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c index f29d2f118b44..5d9c3ff728c9 100644 --- a/arch/powerpc/mm/ppc_mmu_32.c +++ b/arch/powerpc/mm/ppc_mmu_32.c @@ -98,10 +98,20 @@ static int find_free_bat(void) return -1; } +/* + * This function calculates the size of the larger block usable to map the + * beginning of an area based on the start address and size of that area: + * - max block size is 8M on 601 and 256 on other 6xx. + * - base address must be aligned to the block size. So the maximum block size + * is identified by the lowest bit set to 1 in the base address (for instance + * if base is 0x16000000, max size is 0x02000000). + * - block size has to be a power of two. This is calculated by finding the + * highest bit set to 1. + */ static unsigned int block_size(unsigned long base, unsigned long top) { unsigned int max_size = (cpu_has_feature(CPU_FTR_601) ? 8 : 256) << 20; - unsigned int base_shift = (fls(base) - 1) & 31; + unsigned int base_shift = (ffs(base) - 1) & 31; unsigned int block_shift = (fls(top - base) - 1) & 31; return min3(max_size, 1U << base_shift, 1U << block_shift); @@ -157,7 +167,7 @@ static unsigned long __init __mmu_mapin_ram(unsigned long base, unsigned long to unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top) { - int done; + unsigned long done; unsigned long border = (unsigned long)__init_begin - PAGE_OFFSET; if (__map_without_bats) { @@ -169,10 +179,10 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top) return __mmu_mapin_ram(base, top); done = __mmu_mapin_ram(base, border); - if (done != border - base) + if (done != border) return done; - return done + __mmu_mapin_ram(border, top); + return __mmu_mapin_ram(border, top); } void mmu_mark_initmem_nx(void) diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h index 549e9490ff2a..dcac37745b05 100644 --- a/arch/powerpc/net/bpf_jit.h +++ b/arch/powerpc/net/bpf_jit.h @@ -51,6 +51,8 @@ #define PPC_LIS(r, i) PPC_ADDIS(r, 0, i) #define PPC_STD(r, base, i) EMIT(PPC_INST_STD | ___PPC_RS(r) | \ ___PPC_RA(base) | ((i) & 0xfffc)) +#define PPC_STDX(r, base, b) EMIT(PPC_INST_STDX | ___PPC_RS(r) | \ + ___PPC_RA(base) | ___PPC_RB(b)) #define PPC_STDU(r, base, i) EMIT(PPC_INST_STDU | ___PPC_RS(r) | \ ___PPC_RA(base) | ((i) & 0xfffc)) #define PPC_STW(r, base, i) EMIT(PPC_INST_STW | ___PPC_RS(r) | \ @@ -65,7 +67,9 @@ #define PPC_LBZ(r, base, i) EMIT(PPC_INST_LBZ | ___PPC_RT(r) | \ ___PPC_RA(base) | IMM_L(i)) #define PPC_LD(r, base, i) EMIT(PPC_INST_LD | ___PPC_RT(r) | \ - ___PPC_RA(base) | IMM_L(i)) + ___PPC_RA(base) | ((i) & 0xfffc)) +#define PPC_LDX(r, base, b) EMIT(PPC_INST_LDX | ___PPC_RT(r) | \ + ___PPC_RA(base) | ___PPC_RB(b)) #define PPC_LWZ(r, base, i) EMIT(PPC_INST_LWZ | ___PPC_RT(r) | \ ___PPC_RA(base) | IMM_L(i)) #define PPC_LHZ(r, base, i) EMIT(PPC_INST_LHZ | ___PPC_RT(r) | \ @@ -85,17 +89,6 @@ ___PPC_RA(a) | ___PPC_RB(b)) #define PPC_BPF_STDCX(s, a, b) EMIT(PPC_INST_STDCX | ___PPC_RS(s) | \ ___PPC_RA(a) | ___PPC_RB(b)) - -#ifdef CONFIG_PPC64 -#define PPC_BPF_LL(r, base, i) do { PPC_LD(r, base, i); } while(0) -#define PPC_BPF_STL(r, base, i) do { PPC_STD(r, base, i); } while(0) -#define PPC_BPF_STLU(r, base, i) do { PPC_STDU(r, base, i); } while(0) -#else -#define PPC_BPF_LL(r, base, i) do { PPC_LWZ(r, base, i); } while(0) -#define PPC_BPF_STL(r, base, i) do { PPC_STW(r, base, i); } while(0) -#define PPC_BPF_STLU(r, base, i) do { PPC_STWU(r, base, i); } while(0) -#endif - #define PPC_CMPWI(a, i) EMIT(PPC_INST_CMPWI | ___PPC_RA(a) | IMM_L(i)) #define PPC_CMPDI(a, i) EMIT(PPC_INST_CMPDI | ___PPC_RA(a) | IMM_L(i)) #define PPC_CMPW(a, b) EMIT(PPC_INST_CMPW | ___PPC_RA(a) | \ diff --git a/arch/powerpc/net/bpf_jit32.h b/arch/powerpc/net/bpf_jit32.h index dc50a8d4b3b9..21744d8aa053 100644 --- a/arch/powerpc/net/bpf_jit32.h +++ b/arch/powerpc/net/bpf_jit32.h @@ -122,6 +122,10 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh); #define PPC_NTOHS_OFFS(r, base, i) PPC_LHZ_OFFS(r, base, i) #endif +#define PPC_BPF_LL(r, base, i) do { PPC_LWZ(r, base, i); } while(0) +#define PPC_BPF_STL(r, base, i) do { PPC_STW(r, base, i); } while(0) +#define PPC_BPF_STLU(r, base, i) do { PPC_STWU(r, base, i); } while(0) + #define SEEN_DATAREF 0x10000 /* might call external helpers */ #define SEEN_XREG 0x20000 /* X reg is used */ #define SEEN_MEM 0x40000 /* SEEN_MEM+(1<<n) = use mem[n] for temporary diff --git a/arch/powerpc/net/bpf_jit64.h b/arch/powerpc/net/bpf_jit64.h index 3609be4692b3..47f441f351a6 100644 --- a/arch/powerpc/net/bpf_jit64.h +++ b/arch/powerpc/net/bpf_jit64.h @@ -68,6 +68,26 @@ static const int b2p[] = { /* PPC NVR range -- update this if we ever use NVRs below r27 */ #define BPF_PPC_NVR_MIN 27 +/* + * WARNING: These can use TMP_REG_2 if the offset is not at word boundary, + * so ensure that it isn't in use already. + */ +#define PPC_BPF_LL(r, base, i) do { \ + if ((i) % 4) { \ + PPC_LI(b2p[TMP_REG_2], (i)); \ + PPC_LDX(r, base, b2p[TMP_REG_2]); \ + } else \ + PPC_LD(r, base, i); \ + } while(0) +#define PPC_BPF_STL(r, base, i) do { \ + if ((i) % 4) { \ + PPC_LI(b2p[TMP_REG_2], (i)); \ + PPC_STDX(r, base, b2p[TMP_REG_2]); \ + } else \ + PPC_STD(r, base, i); \ + } while(0) +#define PPC_BPF_STLU(r, base, i) do { PPC_STDU(r, base, i); } while(0) + #define SEEN_FUNC 0x1000 /* might call external helpers */ #define SEEN_STACK 0x2000 /* uses BPF stack */ #define SEEN_TAILCALL 0x4000 /* uses tail calls */ diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 4194d3cfb60c..21a1dcd4b156 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -252,7 +252,7 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 * if (tail_call_cnt > MAX_TAIL_CALL_CNT) * goto out; */ - PPC_LD(b2p[TMP_REG_1], 1, bpf_jit_stack_tailcallcnt(ctx)); + PPC_BPF_LL(b2p[TMP_REG_1], 1, bpf_jit_stack_tailcallcnt(ctx)); PPC_CMPLWI(b2p[TMP_REG_1], MAX_TAIL_CALL_CNT); PPC_BCC(COND_GT, out); @@ -265,7 +265,7 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 /* prog = array->ptrs[index]; */ PPC_MULI(b2p[TMP_REG_1], b2p_index, 8); PPC_ADD(b2p[TMP_REG_1], b2p[TMP_REG_1], b2p_bpf_array); - PPC_LD(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_array, ptrs)); + PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_array, ptrs)); /* * if (prog == NULL) @@ -275,7 +275,7 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 PPC_BCC(COND_EQ, out); /* goto *(prog->bpf_func + prologue_size); */ - PPC_LD(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_prog, bpf_func)); + PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_prog, bpf_func)); #ifdef PPC64_ELF_ABI_v1 /* skip past the function descriptor */ PPC_ADDI(b2p[TMP_REG_1], b2p[TMP_REG_1], @@ -606,7 +606,7 @@ bpf_alu32_trunc: * the instructions generated will remain the * same across all passes */ - PPC_STD(dst_reg, 1, bpf_jit_stack_local(ctx)); + PPC_BPF_STL(dst_reg, 1, bpf_jit_stack_local(ctx)); PPC_ADDI(b2p[TMP_REG_1], 1, bpf_jit_stack_local(ctx)); PPC_LDBRX(dst_reg, 0, b2p[TMP_REG_1]); break; @@ -662,7 +662,7 @@ emit_clear: PPC_LI32(b2p[TMP_REG_1], imm); src_reg = b2p[TMP_REG_1]; } - PPC_STD(src_reg, dst_reg, off); + PPC_BPF_STL(src_reg, dst_reg, off); break; /* @@ -709,7 +709,7 @@ emit_clear: break; /* dst = *(u64 *)(ul) (src + off) */ case BPF_LDX | BPF_MEM | BPF_DW: - PPC_LD(dst_reg, src_reg, off); + PPC_BPF_LL(dst_reg, src_reg, off); break; /* diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 842b2c7e156a..50cd09b4e05d 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -324,7 +324,7 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK config PPC_RADIX_MMU bool "Radix MMU Support" - depends on PPC_BOOK3S_64 + depends on PPC_BOOK3S_64 && HUGETLB_PAGE select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA default y help diff --git a/arch/powerpc/platforms/pseries/pseries_energy.c b/arch/powerpc/platforms/pseries/pseries_energy.c index 6ed22127391b..921f12182f3e 100644 --- a/arch/powerpc/platforms/pseries/pseries_energy.c +++ b/arch/powerpc/platforms/pseries/pseries_energy.c @@ -77,18 +77,27 @@ static u32 cpu_to_drc_index(int cpu) ret = drc.drc_index_start + (thread_index * drc.sequential_inc); } else { - const __be32 *indexes; - - indexes = of_get_property(dn, "ibm,drc-indexes", NULL); - if (indexes == NULL) - goto err_of_node_put; + u32 nr_drc_indexes, thread_drc_index; /* - * The first element indexes[0] is the number of drc_indexes - * returned in the list. Hence thread_index+1 will get the - * drc_index corresponding to core number thread_index. + * The first element of ibm,drc-indexes array is the + * number of drc_indexes returned in the list. Hence + * thread_index+1 will get the drc_index corresponding + * to core number thread_index. */ - ret = indexes[thread_index + 1]; + rc = of_property_read_u32_index(dn, "ibm,drc-indexes", + 0, &nr_drc_indexes); + if (rc) + goto err_of_node_put; + + WARN_ON_ONCE(thread_index > nr_drc_indexes); + rc = of_property_read_u32_index(dn, "ibm,drc-indexes", + thread_index + 1, + &thread_drc_index); + if (rc) + goto err_of_node_put; + + ret = thread_drc_index; } rc = 0; diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index d97d52772789..452dcfd7e5dd 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -550,6 +550,7 @@ static void pseries_print_mce_info(struct pt_regs *regs, "UE", "SLB", "ERAT", + "Unknown", "TLB", "D-Cache", "Unknown", diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig new file mode 100644 index 000000000000..1a911ed8e772 --- /dev/null +++ b/arch/riscv/configs/rv32_defconfig @@ -0,0 +1,84 @@ +CONFIG_SYSVIPC=y +CONFIG_POSIX_MQUEUE=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_CGROUPS=y +CONFIG_CGROUP_SCHED=y +CONFIG_CFS_BANDWIDTH=y +CONFIG_CGROUP_BPF=y +CONFIG_NAMESPACES=y +CONFIG_USER_NS=y +CONFIG_CHECKPOINT_RESTORE=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_EXPERT=y +CONFIG_BPF_SYSCALL=y +CONFIG_ARCH_RV32I=y +CONFIG_SMP=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_INET=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +CONFIG_IP_PNP_RARP=y +CONFIG_NETLINK_DIAG=y +CONFIG_PCI=y +CONFIG_PCIEPORTBUS=y +CONFIG_PCI_HOST_GENERIC=y +CONFIG_PCIE_XILINX=y +CONFIG_DEVTMPFS=y +CONFIG_BLK_DEV_LOOP=y +CONFIG_VIRTIO_BLK=y +CONFIG_BLK_DEV_SD=y +CONFIG_BLK_DEV_SR=y +CONFIG_ATA=y +CONFIG_SATA_AHCI=y +CONFIG_SATA_AHCI_PLATFORM=y +CONFIG_NETDEVICES=y +CONFIG_VIRTIO_NET=y +CONFIG_MACB=y +CONFIG_E1000E=y +CONFIG_R8169=y +CONFIG_MICROSEMI_PHY=y +CONFIG_INPUT_MOUSEDEV=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_OF_PLATFORM=y +CONFIG_SERIAL_EARLYCON_RISCV_SBI=y +CONFIG_HVC_RISCV_SBI=y +# CONFIG_PTP_1588_CLOCK is not set +CONFIG_DRM=y +CONFIG_DRM_RADEON=y +CONFIG_FRAMEBUFFER_CONSOLE=y +CONFIG_USB=y +CONFIG_USB_XHCI_HCD=y +CONFIG_USB_XHCI_PLATFORM=y +CONFIG_USB_EHCI_HCD=y +CONFIG_USB_EHCI_HCD_PLATFORM=y +CONFIG_USB_OHCI_HCD=y +CONFIG_USB_OHCI_HCD_PLATFORM=y +CONFIG_USB_STORAGE=y +CONFIG_USB_UAS=y +CONFIG_VIRTIO_MMIO=y +CONFIG_SIFIVE_PLIC=y +CONFIG_EXT4_FS=y +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_AUTOFS4_FS=y +CONFIG_MSDOS_FS=y +CONFIG_VFAT_FS=y +CONFIG_TMPFS=y +CONFIG_TMPFS_POSIX_ACL=y +CONFIG_NFS_FS=y +CONFIG_NFS_V4=y +CONFIG_NFS_V4_1=y +CONFIG_NFS_V4_2=y +CONFIG_ROOT_NFS=y +CONFIG_CRYPTO_USER_API_HASH=y +CONFIG_CRYPTO_DEV_VIRTIO=y +CONFIG_PRINTK_TIME=y +# CONFIG_RCU_TRACE is not set diff --git a/arch/riscv/include/asm/fixmap.h b/arch/riscv/include/asm/fixmap.h index 57afe604b495..c207f6634b91 100644 --- a/arch/riscv/include/asm/fixmap.h +++ b/arch/riscv/include/asm/fixmap.h @@ -26,7 +26,7 @@ enum fixed_addresses { }; #define FIXADDR_SIZE (__end_of_fixed_addresses * PAGE_SIZE) -#define FIXADDR_TOP (PAGE_OFFSET) +#define FIXADDR_TOP (VMALLOC_START) #define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) #define FIXMAP_PAGE_IO PAGE_KERNEL diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h index bba3da6ef157..a3d5273ded7c 100644 --- a/arch/riscv/include/asm/syscall.h +++ b/arch/riscv/include/asm/syscall.h @@ -72,32 +72,20 @@ static inline void syscall_set_return_value(struct task_struct *task, static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args) { - BUG_ON(i + n > 6); - if (i == 0) { - args[0] = regs->orig_a0; - args++; - i++; - n--; - } - memcpy(args, ®s->a1 + i * sizeof(regs->a1), n * sizeof(args[0])); + args[0] = regs->orig_a0; + args++; + memcpy(args, ®s->a1, 5 * sizeof(args[0])); } static inline void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, const unsigned long *args) { - BUG_ON(i + n > 6); - if (i == 0) { - regs->orig_a0 = args[0]; - args++; - i++; - n--; - } - memcpy(®s->a1 + i * sizeof(regs->a1), args, n * sizeof(regs->a0)); + regs->orig_a0 = args[0]; + args++; + memcpy(®s->a1, args, 5 * sizeof(regs->a1)); } static inline int syscall_get_arch(void) diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index a00168b980d2..fb53a8089e76 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -300,7 +300,7 @@ do { \ " .balign 4\n" \ "4:\n" \ " li %0, %6\n" \ - " jump 2b, %1\n" \ + " jump 3b, %1\n" \ " .previous\n" \ " .section __ex_table,\"a\"\n" \ " .balign " RISCV_SZPTR "\n" \ diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index f13f7f276639..598568168d35 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -4,7 +4,6 @@ ifdef CONFIG_FTRACE CFLAGS_REMOVE_ftrace.o = -pg -CFLAGS_REMOVE_setup.o = -pg endif extra-y += head.o @@ -29,8 +28,6 @@ obj-y += vdso.o obj-y += cacheinfo.o obj-y += vdso/ -CFLAGS_setup.o := -mcmodel=medany - obj-$(CONFIG_FPU) += fpu.o obj-$(CONFIG_SMP) += smpboot.o obj-$(CONFIG_SMP) += smp.o diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c index 7dd308129b40..2872edce894d 100644 --- a/arch/riscv/kernel/module.c +++ b/arch/riscv/kernel/module.c @@ -141,7 +141,7 @@ static int apply_r_riscv_hi20_rela(struct module *me, u32 *location, { s32 hi20; - if (IS_ENABLED(CMODEL_MEDLOW)) { + if (IS_ENABLED(CONFIG_CMODEL_MEDLOW)) { pr_err( "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n", me->name, (long long)v, location); diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index ecb654f6a79e..540a331d1376 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -48,14 +48,6 @@ struct screen_info screen_info = { }; #endif -unsigned long va_pa_offset; -EXPORT_SYMBOL(va_pa_offset); -unsigned long pfn_base; -EXPORT_SYMBOL(pfn_base); - -unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss; -EXPORT_SYMBOL(empty_zero_page); - /* The lucky hart to first increment this variable will boot the other cores */ atomic_t hart_lottery; unsigned long boot_cpu_hartid; diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile index eb22ab49b3e0..b68aac701803 100644 --- a/arch/riscv/mm/Makefile +++ b/arch/riscv/mm/Makefile @@ -1,3 +1,9 @@ + +CFLAGS_init.o := -mcmodel=medany +ifdef CONFIG_FTRACE +CFLAGS_REMOVE_init.o = -pg +endif + obj-y += init.o obj-y += fault.o obj-y += extable.o diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index b379a75ac6a6..bc7b77e34d09 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -25,6 +25,10 @@ #include <asm/pgtable.h> #include <asm/io.h> +unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] + __page_aligned_bss; +EXPORT_SYMBOL(empty_zero_page); + static void __init zone_sizes_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES] = { 0, }; @@ -117,6 +121,14 @@ void __init setup_bootmem(void) */ memblock_reserve(reg->base, vmlinux_end - reg->base); mem_size = min(reg->size, (phys_addr_t)-PAGE_OFFSET); + + /* + * Remove memblock from the end of usable area to the + * end of region + */ + if (reg->base + mem_size < end) + memblock_remove(reg->base + mem_size, + end - reg->base - mem_size); } } BUG_ON(mem_size == 0); @@ -143,6 +155,11 @@ void __init setup_bootmem(void) } } +unsigned long va_pa_offset; +EXPORT_SYMBOL(va_pa_offset); +unsigned long pfn_base; +EXPORT_SYMBOL(pfn_base); + pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss; pgd_t trampoline_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE); @@ -172,6 +189,25 @@ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot) } } +/* + * setup_vm() is called from head.S with MMU-off. + * + * Following requirements should be honoured for setup_vm() to work + * correctly: + * 1) It should use PC-relative addressing for accessing kernel symbols. + * To achieve this we always use GCC cmodel=medany. + * 2) The compiler instrumentation for FTRACE will not work for setup_vm() + * so disable compiler instrumentation when FTRACE is enabled. + * + * Currently, the above requirements are honoured by using custom CFLAGS + * for init.o in mm/Makefile. + */ + +#ifndef __riscv_cmodel_medany +#error "setup_vm() is called from head.S before relocate so it should " + "not use absolute addressing." +#endif + asmlinkage void __init setup_vm(void) { extern char _start; diff --git a/arch/s390/boot/mem_detect.c b/arch/s390/boot/mem_detect.c index 4cb771ba13fa..5d316fe40480 100644 --- a/arch/s390/boot/mem_detect.c +++ b/arch/s390/boot/mem_detect.c @@ -25,7 +25,7 @@ static void *mem_detect_alloc_extended(void) { unsigned long offset = ALIGN(mem_safe_offset(), sizeof(u64)); - if (IS_ENABLED(BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE && + if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE && INITRD_START < offset + ENTRIES_EXTENDED_MAX) offset = ALIGN(INITRD_START + INITRD_SIZE, sizeof(u64)); diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h index 1a6a7092d942..e94a0a28b5eb 100644 --- a/arch/s390/include/asm/ap.h +++ b/arch/s390/include/asm/ap.h @@ -360,4 +360,15 @@ static inline struct ap_queue_status ap_dqap(ap_qid_t qid, return reg1; } +/* + * Interface to tell the AP bus code that a configuration + * change has happened. The bus code should at least do + * an ap bus resource rescan. + */ +#if IS_ENABLED(CONFIG_ZCRYPT) +void ap_bus_cfg_chg(void); +#else +static inline void ap_bus_cfg_chg(void){}; +#endif + #endif /* _ASM_S390_AP_H_ */ diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h index 7d22a474a040..f74639a05f0f 100644 --- a/arch/s390/include/asm/elf.h +++ b/arch/s390/include/asm/elf.h @@ -252,11 +252,14 @@ do { \ /* * Cache aliasing on the latest machines calls for a mapping granularity - * of 512KB. For 64-bit processes use a 512KB alignment and a randomization - * of up to 1GB. For 31-bit processes the virtual address space is limited, - * use no alignment and limit the randomization to 8MB. + * of 512KB for the anonymous mapping base. For 64-bit processes use a + * 512KB alignment and a randomization of up to 1GB. For 31-bit processes + * the virtual address space is limited, use no alignment and limit the + * randomization to 8MB. + * For the additional randomization of the program break use 32MB for + * 64-bit and 8MB for 31-bit. */ -#define BRK_RND_MASK (is_compat_task() ? 0x7ffUL : 0x3ffffUL) +#define BRK_RND_MASK (is_compat_task() ? 0x7ffUL : 0x1fffUL) #define MMAP_RND_MASK (is_compat_task() ? 0x7ffUL : 0x3ff80UL) #define MMAP_ALIGN_MASK (is_compat_task() ? 0 : 0x7fUL) #define STACK_RND_MASK MMAP_RND_MASK diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h index cc0947e08b6f..5b9f10b1e55d 100644 --- a/arch/s390/include/asm/lowcore.h +++ b/arch/s390/include/asm/lowcore.h @@ -91,52 +91,53 @@ struct lowcore { __u64 hardirq_timer; /* 0x02e8 */ __u64 softirq_timer; /* 0x02f0 */ __u64 steal_timer; /* 0x02f8 */ - __u64 last_update_timer; /* 0x0300 */ - __u64 last_update_clock; /* 0x0308 */ - __u64 int_clock; /* 0x0310 */ - __u64 mcck_clock; /* 0x0318 */ - __u64 clock_comparator; /* 0x0320 */ - __u64 boot_clock[2]; /* 0x0328 */ + __u64 avg_steal_timer; /* 0x0300 */ + __u64 last_update_timer; /* 0x0308 */ + __u64 last_update_clock; /* 0x0310 */ + __u64 int_clock; /* 0x0318*/ + __u64 mcck_clock; /* 0x0320 */ + __u64 clock_comparator; /* 0x0328 */ + __u64 boot_clock[2]; /* 0x0330 */ /* Current process. */ - __u64 current_task; /* 0x0338 */ - __u64 kernel_stack; /* 0x0340 */ + __u64 current_task; /* 0x0340 */ + __u64 kernel_stack; /* 0x0348 */ /* Interrupt, DAT-off and restartstack. */ - __u64 async_stack; /* 0x0348 */ - __u64 nodat_stack; /* 0x0350 */ - __u64 restart_stack; /* 0x0358 */ + __u64 async_stack; /* 0x0350 */ + __u64 nodat_stack; /* 0x0358 */ + __u64 restart_stack; /* 0x0360 */ /* Restart function and parameter. */ - __u64 restart_fn; /* 0x0360 */ - __u64 restart_data; /* 0x0368 */ - __u64 restart_source; /* 0x0370 */ + __u64 restart_fn; /* 0x0368 */ + __u64 restart_data; /* 0x0370 */ + __u64 restart_source; /* 0x0378 */ /* Address space pointer. */ - __u64 kernel_asce; /* 0x0378 */ - __u64 user_asce; /* 0x0380 */ - __u64 vdso_asce; /* 0x0388 */ + __u64 kernel_asce; /* 0x0380 */ + __u64 user_asce; /* 0x0388 */ + __u64 vdso_asce; /* 0x0390 */ /* * The lpp and current_pid fields form a * 64-bit value that is set as program * parameter with the LPP instruction. */ - __u32 lpp; /* 0x0390 */ - __u32 current_pid; /* 0x0394 */ + __u32 lpp; /* 0x0398 */ + __u32 current_pid; /* 0x039c */ /* SMP info area */ - __u32 cpu_nr; /* 0x0398 */ - __u32 softirq_pending; /* 0x039c */ - __u32 preempt_count; /* 0x03a0 */ - __u32 spinlock_lockval; /* 0x03a4 */ - __u32 spinlock_index; /* 0x03a8 */ - __u32 fpu_flags; /* 0x03ac */ - __u64 percpu_offset; /* 0x03b0 */ - __u64 vdso_per_cpu_data; /* 0x03b8 */ - __u64 machine_flags; /* 0x03c0 */ - __u64 gmap; /* 0x03c8 */ - __u8 pad_0x03d0[0x0400-0x03d0]; /* 0x03d0 */ + __u32 cpu_nr; /* 0x03a0 */ + __u32 softirq_pending; /* 0x03a4 */ + __u32 preempt_count; /* 0x03a8 */ + __u32 spinlock_lockval; /* 0x03ac */ + __u32 spinlock_index; /* 0x03b0 */ + __u32 fpu_flags; /* 0x03b4 */ + __u64 percpu_offset; /* 0x03b8 */ + __u64 vdso_per_cpu_data; /* 0x03c0 */ + __u64 machine_flags; /* 0x03c8 */ + __u64 gmap; /* 0x03d0 */ + __u8 pad_0x03d8[0x0400-0x03d8]; /* 0x03d8 */ /* br %r1 trampoline */ __u16 br_r1_trampoline; /* 0x0400 */ diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h index 96f9a9151fde..59c3e91f2cdb 100644 --- a/arch/s390/include/asm/syscall.h +++ b/arch/s390/include/asm/syscall.h @@ -56,40 +56,32 @@ static inline void syscall_set_return_value(struct task_struct *task, static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args) { unsigned long mask = -1UL; + unsigned int n = 6; - /* - * No arguments for this syscall, there's nothing to do. - */ - if (!n) - return; - - BUG_ON(i + n > 6); #ifdef CONFIG_COMPAT if (test_tsk_thread_flag(task, TIF_31BIT)) mask = 0xffffffff; #endif while (n-- > 0) - if (i + n > 0) - args[n] = regs->gprs[2 + i + n] & mask; - if (i == 0) - args[0] = regs->orig_gpr2 & mask; + if (n > 0) + args[n] = regs->gprs[2 + n] & mask; + + args[0] = regs->orig_gpr2 & mask; } static inline void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, const unsigned long *args) { - BUG_ON(i + n > 6); + unsigned int n = 6; + while (n-- > 0) - if (i + n > 0) - regs->gprs[2 + i + n] = args[n]; - if (i == 0) - regs->orig_gpr2 = args[0]; + if (n > 0) + regs->gprs[2 + n] = args[n]; + regs->orig_gpr2 = args[0]; } static inline int syscall_get_arch(void) diff --git a/arch/s390/kernel/fpu.c b/arch/s390/kernel/fpu.c index 594464f2129d..0da378e2eb25 100644 --- a/arch/s390/kernel/fpu.c +++ b/arch/s390/kernel/fpu.c @@ -23,7 +23,7 @@ void __kernel_fpu_begin(struct kernel_fpu *state, u32 flags) if (flags & KERNEL_FPC) /* Save floating point control */ - asm volatile("stfpc %0" : "=m" (state->fpc)); + asm volatile("stfpc %0" : "=Q" (state->fpc)); if (!MACHINE_HAS_VX) { if (flags & KERNEL_VXR_V0V7) { diff --git a/arch/s390/kernel/perf_cpum_cf_diag.c b/arch/s390/kernel/perf_cpum_cf_diag.c index c6fad208c2fa..b6854812d2ed 100644 --- a/arch/s390/kernel/perf_cpum_cf_diag.c +++ b/arch/s390/kernel/perf_cpum_cf_diag.c @@ -196,23 +196,30 @@ static void cf_diag_perf_event_destroy(struct perf_event *event) */ static int __hw_perf_event_init(struct perf_event *event) { - struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events); struct perf_event_attr *attr = &event->attr; + struct cpu_cf_events *cpuhw; enum cpumf_ctr_set i; int err = 0; - debug_sprintf_event(cf_diag_dbg, 5, - "%s event %p cpu %d authorized %#x\n", __func__, - event, event->cpu, cpuhw->info.auth_ctl); + debug_sprintf_event(cf_diag_dbg, 5, "%s event %p cpu %d\n", __func__, + event, event->cpu); event->hw.config = attr->config; event->hw.config_base = 0; - local64_set(&event->count, 0); - /* Add all authorized counter sets to config_base */ + /* Add all authorized counter sets to config_base. The + * the hardware init function is either called per-cpu or just once + * for all CPUS (event->cpu == -1). This depends on the whether + * counting is started for all CPUs or on a per workload base where + * the perf event moves from one CPU to another CPU. + * Checking the authorization on any CPU is fine as the hardware + * applies the same authorization settings to all CPUs. + */ + cpuhw = &get_cpu_var(cpu_cf_events); for (i = CPUMF_CTR_SET_BASIC; i < CPUMF_CTR_SET_MAX; ++i) if (cpuhw->info.auth_ctl & cpumf_ctr_ctl[i]) event->hw.config_base |= cpumf_ctr_ctl[i]; + put_cpu_var(cpu_cf_events); /* No authorized counter sets, nothing to count/sample */ if (!event->hw.config_base) { diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 3fe1c77c361b..bd197baf1dc3 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -266,7 +266,8 @@ static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu) lc->percpu_offset = __per_cpu_offset[cpu]; lc->kernel_asce = S390_lowcore.kernel_asce; lc->machine_flags = S390_lowcore.machine_flags; - lc->user_timer = lc->system_timer = lc->steal_timer = 0; + lc->user_timer = lc->system_timer = + lc->steal_timer = lc->avg_steal_timer = 0; __ctl_store(lc->cregs_save_area, 0, 15); save_access_regs((unsigned int *) lc->access_regs_save_area); memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list, diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index 02579f95f391..061418f787c3 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -426,3 +426,7 @@ 421 32 rt_sigtimedwait_time64 - compat_sys_rt_sigtimedwait_time64 422 32 futex_time64 - sys_futex 423 32 sched_rr_get_interval_time64 - sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register sys_io_uring_register diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index 98f850e00008..c475ca49cfc6 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -37,7 +37,7 @@ static inline u64 get_vtimer(void) { u64 timer; - asm volatile("stpt %0" : "=m" (timer)); + asm volatile("stpt %0" : "=Q" (timer)); return timer; } @@ -48,7 +48,7 @@ static inline void set_vtimer(u64 expires) asm volatile( " stpt %0\n" /* Store current cpu timer value */ " spt %1" /* Set new value imm. afterwards */ - : "=m" (timer) : "m" (expires)); + : "=Q" (timer) : "Q" (expires)); S390_lowcore.system_timer += S390_lowcore.last_update_timer - timer; S390_lowcore.last_update_timer = expires; } @@ -124,7 +124,7 @@ static void account_system_index_scaled(struct task_struct *p, u64 cputime, */ static int do_account_vtime(struct task_struct *tsk) { - u64 timer, clock, user, guest, system, hardirq, softirq, steal; + u64 timer, clock, user, guest, system, hardirq, softirq; timer = S390_lowcore.last_update_timer; clock = S390_lowcore.last_update_clock; @@ -135,8 +135,8 @@ static int do_account_vtime(struct task_struct *tsk) #else " stck %1" /* Store current tod clock value */ #endif - : "=m" (S390_lowcore.last_update_timer), - "=m" (S390_lowcore.last_update_clock)); + : "=Q" (S390_lowcore.last_update_timer), + "=Q" (S390_lowcore.last_update_clock)); clock = S390_lowcore.last_update_clock - clock; timer -= S390_lowcore.last_update_timer; @@ -182,12 +182,6 @@ static int do_account_vtime(struct task_struct *tsk) if (softirq) account_system_index_scaled(tsk, softirq, CPUTIME_SOFTIRQ); - steal = S390_lowcore.steal_timer; - if ((s64) steal > 0) { - S390_lowcore.steal_timer = 0; - account_steal_time(cputime_to_nsecs(steal)); - } - return virt_timer_forward(user + guest + system + hardirq + softirq); } @@ -213,8 +207,19 @@ void vtime_task_switch(struct task_struct *prev) */ void vtime_flush(struct task_struct *tsk) { + u64 steal, avg_steal; + if (do_account_vtime(tsk)) virt_timer_expire(); + + steal = S390_lowcore.steal_timer; + avg_steal = S390_lowcore.avg_steal_timer / 2; + if ((s64) steal > 0) { + S390_lowcore.steal_timer = 0; + account_steal_time(steal); + avg_steal += steal; + } + S390_lowcore.avg_steal_timer = avg_steal; } /* diff --git a/arch/sh/boards/of-generic.c b/arch/sh/boards/of-generic.c index 958f46da3a79..d91065e81a4e 100644 --- a/arch/sh/boards/of-generic.c +++ b/arch/sh/boards/of-generic.c @@ -164,10 +164,10 @@ static struct sh_machine_vector __initmv sh_of_generic_mv = { struct sh_clk_ops; -void __init arch_init_clk_ops(struct sh_clk_ops **ops, int idx) +void __init __weak arch_init_clk_ops(struct sh_clk_ops **ops, int idx) { } -void __init plat_irq_setup(void) +void __init __weak plat_irq_setup(void) { } diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild index a6ef3fee5f85..7bf2cb680d32 100644 --- a/arch/sh/include/asm/Kbuild +++ b/arch/sh/include/asm/Kbuild @@ -9,6 +9,7 @@ generic-y += emergency-restart.h generic-y += exec.h generic-y += irq_regs.h generic-y += irq_work.h +generic-y += kvm_para.h generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h diff --git a/arch/sh/include/asm/syscall_32.h b/arch/sh/include/asm/syscall_32.h index 6e118799831c..8c9d7e5e5dcc 100644 --- a/arch/sh/include/asm/syscall_32.h +++ b/arch/sh/include/asm/syscall_32.h @@ -48,51 +48,28 @@ static inline void syscall_set_return_value(struct task_struct *task, static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args) { - /* - * Do this simply for now. If we need to start supporting - * fetching arguments from arbitrary indices, this will need some - * extra logic. Presently there are no in-tree users that depend - * on this behaviour. - */ - BUG_ON(i); /* Argument pattern is: R4, R5, R6, R7, R0, R1 */ - switch (n) { - case 6: args[5] = regs->regs[1]; - case 5: args[4] = regs->regs[0]; - case 4: args[3] = regs->regs[7]; - case 3: args[2] = regs->regs[6]; - case 2: args[1] = regs->regs[5]; - case 1: args[0] = regs->regs[4]; - case 0: - break; - default: - BUG(); - } + args[5] = regs->regs[1]; + args[4] = regs->regs[0]; + args[3] = regs->regs[7]; + args[2] = regs->regs[6]; + args[1] = regs->regs[5]; + args[0] = regs->regs[4]; } static inline void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, const unsigned long *args) { - /* Same note as above applies */ - BUG_ON(i); - - switch (n) { - case 6: regs->regs[1] = args[5]; - case 5: regs->regs[0] = args[4]; - case 4: regs->regs[7] = args[3]; - case 3: regs->regs[6] = args[2]; - case 2: regs->regs[5] = args[1]; - case 1: regs->regs[4] = args[0]; - break; - default: - BUG(); - } + regs->regs[1] = args[5]; + regs->regs[0] = args[4]; + regs->regs[7] = args[3]; + regs->regs[6] = args[2]; + regs->regs[5] = args[1]; + regs->regs[4] = args[0]; } static inline int syscall_get_arch(void) diff --git a/arch/sh/include/asm/syscall_64.h b/arch/sh/include/asm/syscall_64.h index 43882580c7f9..22fad97da066 100644 --- a/arch/sh/include/asm/syscall_64.h +++ b/arch/sh/include/asm/syscall_64.h @@ -47,20 +47,16 @@ static inline void syscall_set_return_value(struct task_struct *task, static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args) { - BUG_ON(i + n > 6); - memcpy(args, ®s->regs[2 + i], n * sizeof(args[0])); + memcpy(args, ®s->regs[2], 6 * sizeof(args[0])); } static inline void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, const unsigned long *args) { - BUG_ON(i + n > 6); - memcpy(®s->regs[2 + i], args, n * sizeof(args[0])); + memcpy(®s->regs[2], args, 6 * sizeof(args[0])); } static inline int syscall_get_arch(void) diff --git a/arch/sh/include/uapi/asm/Kbuild b/arch/sh/include/uapi/asm/Kbuild index ecfbd40924dd..b8812c74c1de 100644 --- a/arch/sh/include/uapi/asm/Kbuild +++ b/arch/sh/include/uapi/asm/Kbuild @@ -1,5 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 generated-y += unistd_32.h -generic-y += kvm_para.h generic-y += ucontext.h diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index bfda678576e4..480b057556ee 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -426,3 +426,7 @@ 421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait 422 common futex_time64 sys_futex 423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index b82f64e28f55..a22cfd5c0ee8 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -9,6 +9,7 @@ generic-y += exec.h generic-y += export.h generic-y += irq_regs.h generic-y += irq_work.h +generic-y += kvm_para.h generic-y += linkage.h generic-y += local.h generic-y += local64.h diff --git a/arch/sparc/include/asm/syscall.h b/arch/sparc/include/asm/syscall.h index 053989e3f6a6..4d075434e816 100644 --- a/arch/sparc/include/asm/syscall.h +++ b/arch/sparc/include/asm/syscall.h @@ -96,11 +96,11 @@ static inline void syscall_set_return_value(struct task_struct *task, static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args) { int zero_extend = 0; unsigned int j; + unsigned int n = 6; #ifdef CONFIG_SPARC64 if (test_tsk_thread_flag(task, TIF_32BIT)) @@ -108,7 +108,7 @@ static inline void syscall_get_arguments(struct task_struct *task, #endif for (j = 0; j < n; j++) { - unsigned long val = regs->u_regs[UREG_I0 + i + j]; + unsigned long val = regs->u_regs[UREG_I0 + j]; if (zero_extend) args[j] = (u32) val; @@ -119,13 +119,12 @@ static inline void syscall_get_arguments(struct task_struct *task, static inline void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, const unsigned long *args) { - unsigned int j; + unsigned int i; - for (j = 0; j < n; j++) - regs->u_regs[UREG_I0 + i + j] = args[j]; + for (i = 0; i < 6; i++) + regs->u_regs[UREG_I0 + i] = args[i]; } static inline int syscall_get_arch(void) diff --git a/arch/sparc/include/uapi/asm/kvm_para.h b/arch/sparc/include/uapi/asm/kvm_para.h deleted file mode 100644 index baacc4996d18..000000000000 --- a/arch/sparc/include/uapi/asm/kvm_para.h +++ /dev/null @@ -1,2 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#include <asm-generic/kvm_para.h> diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c index a8af6023c126..14b93c5564e3 100644 --- a/arch/sparc/kernel/pci_sun4v.c +++ b/arch/sparc/kernel/pci_sun4v.c @@ -73,6 +73,11 @@ static inline void iommu_batch_start(struct device *dev, unsigned long prot, uns p->npages = 0; } +static inline bool iommu_use_atu(struct iommu *iommu, u64 mask) +{ + return iommu->atu && mask > DMA_BIT_MASK(32); +} + /* Interrupts must be disabled. */ static long iommu_batch_flush(struct iommu_batch *p, u64 mask) { @@ -92,7 +97,7 @@ static long iommu_batch_flush(struct iommu_batch *p, u64 mask) prot &= (HV_PCI_MAP_ATTR_READ | HV_PCI_MAP_ATTR_WRITE); while (npages != 0) { - if (mask <= DMA_BIT_MASK(32) || !pbm->iommu->atu) { + if (!iommu_use_atu(pbm->iommu, mask)) { num = pci_sun4v_iommu_map(devhandle, HV_PCI_TSBID(0, entry), npages, @@ -179,7 +184,6 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size, unsigned long flags, order, first_page, npages, n; unsigned long prot = 0; struct iommu *iommu; - struct atu *atu; struct iommu_map_table *tbl; struct page *page; void *ret; @@ -205,13 +209,11 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size, memset((char *)first_page, 0, PAGE_SIZE << order); iommu = dev->archdata.iommu; - atu = iommu->atu; - mask = dev->coherent_dma_mask; - if (mask <= DMA_BIT_MASK(32) || !atu) + if (!iommu_use_atu(iommu, mask)) tbl = &iommu->tbl; else - tbl = &atu->tbl; + tbl = &iommu->atu->tbl; entry = iommu_tbl_range_alloc(dev, tbl, npages, NULL, (unsigned long)(-1), 0); @@ -333,7 +335,7 @@ static void dma_4v_free_coherent(struct device *dev, size_t size, void *cpu, atu = iommu->atu; devhandle = pbm->devhandle; - if (dvma <= DMA_BIT_MASK(32)) { + if (!iommu_use_atu(iommu, dvma)) { tbl = &iommu->tbl; iotsb_num = 0; /* we don't care for legacy iommu */ } else { @@ -374,7 +376,7 @@ static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page, npages >>= IO_PAGE_SHIFT; mask = *dev->dma_mask; - if (mask <= DMA_BIT_MASK(32)) + if (!iommu_use_atu(iommu, mask)) tbl = &iommu->tbl; else tbl = &atu->tbl; @@ -510,7 +512,7 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist, IO_PAGE_SIZE) >> IO_PAGE_SHIFT; mask = *dev->dma_mask; - if (mask <= DMA_BIT_MASK(32)) + if (!iommu_use_atu(iommu, mask)) tbl = &iommu->tbl; else tbl = &atu->tbl; diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index b9a5a04b2d2c..a1dd24307b00 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -469,3 +469,7 @@ 421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64 422 32 futex_time64 sys_futex sys_futex 423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register diff --git a/arch/um/include/asm/syscall-generic.h b/arch/um/include/asm/syscall-generic.h index 9fb9cf8cd39a..98e50c50c12e 100644 --- a/arch/um/include/asm/syscall-generic.h +++ b/arch/um/include/asm/syscall-generic.h @@ -53,84 +53,30 @@ static inline void syscall_set_return_value(struct task_struct *task, static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args) { const struct uml_pt_regs *r = ®s->regs; - switch (i) { - case 0: - if (!n--) - break; - *args++ = UPT_SYSCALL_ARG1(r); - case 1: - if (!n--) - break; - *args++ = UPT_SYSCALL_ARG2(r); - case 2: - if (!n--) - break; - *args++ = UPT_SYSCALL_ARG3(r); - case 3: - if (!n--) - break; - *args++ = UPT_SYSCALL_ARG4(r); - case 4: - if (!n--) - break; - *args++ = UPT_SYSCALL_ARG5(r); - case 5: - if (!n--) - break; - *args++ = UPT_SYSCALL_ARG6(r); - case 6: - if (!n--) - break; - default: - BUG(); - break; - } + *args++ = UPT_SYSCALL_ARG1(r); + *args++ = UPT_SYSCALL_ARG2(r); + *args++ = UPT_SYSCALL_ARG3(r); + *args++ = UPT_SYSCALL_ARG4(r); + *args++ = UPT_SYSCALL_ARG5(r); + *args = UPT_SYSCALL_ARG6(r); } static inline void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, const unsigned long *args) { struct uml_pt_regs *r = ®s->regs; - switch (i) { - case 0: - if (!n--) - break; - UPT_SYSCALL_ARG1(r) = *args++; - case 1: - if (!n--) - break; - UPT_SYSCALL_ARG2(r) = *args++; - case 2: - if (!n--) - break; - UPT_SYSCALL_ARG3(r) = *args++; - case 3: - if (!n--) - break; - UPT_SYSCALL_ARG4(r) = *args++; - case 4: - if (!n--) - break; - UPT_SYSCALL_ARG5(r) = *args++; - case 5: - if (!n--) - break; - UPT_SYSCALL_ARG6(r) = *args++; - case 6: - if (!n--) - break; - default: - BUG(); - break; - } + UPT_SYSCALL_ARG1(r) = *args++; + UPT_SYSCALL_ARG2(r) = *args++; + UPT_SYSCALL_ARG3(r) = *args++; + UPT_SYSCALL_ARG4(r) = *args++; + UPT_SYSCALL_ARG5(r) = *args++; + UPT_SYSCALL_ARG6(r) = *args; } /* See arch/x86/um/asm/syscall.h for syscall_get_arch() definition. */ diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild index 1d1544b6ca74..d77d953c04c1 100644 --- a/arch/unicore32/include/asm/Kbuild +++ b/arch/unicore32/include/asm/Kbuild @@ -18,6 +18,7 @@ generic-y += irq_work.h generic-y += kdebug.h generic-y += kmap_types.h generic-y += kprobes.h +generic-y += kvm_para.h generic-y += local.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h diff --git a/arch/unicore32/include/uapi/asm/Kbuild b/arch/unicore32/include/uapi/asm/Kbuild index 755bb11323d8..1c72f04ff75d 100644 --- a/arch/unicore32/include/uapi/asm/Kbuild +++ b/arch/unicore32/include/uapi/asm/Kbuild @@ -1,2 +1 @@ -generic-y += kvm_para.h generic-y += ucontext.h diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 01dbb05bc498..62fc3fda1a05 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2217,14 +2217,8 @@ config RANDOMIZE_MEMORY_PHYSICAL_PADDING If unsure, leave at the default value. config HOTPLUG_CPU - bool "Support for hot-pluggable CPUs" + def_bool y depends on SMP - ---help--- - Say Y here to allow turning CPUs off and on. CPUs can be - controlled through /sys/devices/system/cpu. - ( Note: power management support will enable this option - automatically on SMP systems. ) - Say N if you want to disable CPU hotplug. config BOOTPARAM_HOTPLUG_CPU0 bool "Set default setting of cpu0_hotpluggable" diff --git a/arch/x86/crypto/poly1305-avx2-x86_64.S b/arch/x86/crypto/poly1305-avx2-x86_64.S index 3b6e70d085da..8457cdd47f75 100644 --- a/arch/x86/crypto/poly1305-avx2-x86_64.S +++ b/arch/x86/crypto/poly1305-avx2-x86_64.S @@ -323,6 +323,12 @@ ENTRY(poly1305_4block_avx2) vpaddq t2,t1,t1 vmovq t1x,d4 + # Now do a partial reduction mod (2^130)-5, carrying h0 -> h1 -> h2 -> + # h3 -> h4 -> h0 -> h1 to get h0,h2,h3,h4 < 2^26 and h1 < 2^26 + a small + # amount. Careful: we must not assume the carry bits 'd0 >> 26', + # 'd1 >> 26', 'd2 >> 26', 'd3 >> 26', and '(d4 >> 26) * 5' fit in 32-bit + # integers. It's true in a single-block implementation, but not here. + # d1 += d0 >> 26 mov d0,%rax shr $26,%rax @@ -361,16 +367,16 @@ ENTRY(poly1305_4block_avx2) # h0 += (d4 >> 26) * 5 mov d4,%rax shr $26,%rax - lea (%eax,%eax,4),%eax - add %eax,%ebx + lea (%rax,%rax,4),%rax + add %rax,%rbx # h4 = d4 & 0x3ffffff mov d4,%rax and $0x3ffffff,%eax mov %eax,h4 # h1 += h0 >> 26 - mov %ebx,%eax - shr $26,%eax + mov %rbx,%rax + shr $26,%rax add %eax,h1 # h0 = h0 & 0x3ffffff andl $0x3ffffff,%ebx diff --git a/arch/x86/crypto/poly1305-sse2-x86_64.S b/arch/x86/crypto/poly1305-sse2-x86_64.S index e6add74d78a5..6f0be7a86964 100644 --- a/arch/x86/crypto/poly1305-sse2-x86_64.S +++ b/arch/x86/crypto/poly1305-sse2-x86_64.S @@ -253,16 +253,16 @@ ENTRY(poly1305_block_sse2) # h0 += (d4 >> 26) * 5 mov d4,%rax shr $26,%rax - lea (%eax,%eax,4),%eax - add %eax,%ebx + lea (%rax,%rax,4),%rax + add %rax,%rbx # h4 = d4 & 0x3ffffff mov d4,%rax and $0x3ffffff,%eax mov %eax,h4 # h1 += h0 >> 26 - mov %ebx,%eax - shr $26,%eax + mov %rbx,%rax + shr $26,%rax add %eax,h1 # h0 = h0 & 0x3ffffff andl $0x3ffffff,%ebx @@ -524,6 +524,12 @@ ENTRY(poly1305_2block_sse2) paddq t2,t1 movq t1,d4 + # Now do a partial reduction mod (2^130)-5, carrying h0 -> h1 -> h2 -> + # h3 -> h4 -> h0 -> h1 to get h0,h2,h3,h4 < 2^26 and h1 < 2^26 + a small + # amount. Careful: we must not assume the carry bits 'd0 >> 26', + # 'd1 >> 26', 'd2 >> 26', 'd3 >> 26', and '(d4 >> 26) * 5' fit in 32-bit + # integers. It's true in a single-block implementation, but not here. + # d1 += d0 >> 26 mov d0,%rax shr $26,%rax @@ -562,16 +568,16 @@ ENTRY(poly1305_2block_sse2) # h0 += (d4 >> 26) * 5 mov d4,%rax shr $26,%rax - lea (%eax,%eax,4),%eax - add %eax,%ebx + lea (%rax,%rax,4),%rax + add %rax,%rbx # h4 = d4 & 0x3ffffff mov d4,%rax and $0x3ffffff,%eax mov %eax,h4 # h1 += h0 >> 26 - mov %ebx,%eax - shr $26,%eax + mov %rbx,%rax + shr $26,%rax add %eax,h1 # h0 = h0 & 0x3ffffff andl $0x3ffffff,%ebx diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index 007b3fe9d727..98c7d12b945c 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -29,12 +29,12 @@ extern int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz); extern time_t __vdso_time(time_t *t); #ifdef CONFIG_PARAVIRT_CLOCK -extern u8 pvclock_page +extern u8 pvclock_page[PAGE_SIZE] __attribute__((visibility("hidden"))); #endif #ifdef CONFIG_HYPERV_TSCPAGE -extern u8 hvclock_page +extern u8 hvclock_page[PAGE_SIZE] __attribute__((visibility("hidden"))); #endif diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index 7d2d7c801dba..d45f3fbd232e 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -3,10 +3,14 @@ #include <linux/types.h> #include <linux/init.h> #include <linux/slab.h> +#include <linux/delay.h> #include <asm/apicdef.h> +#include <asm/nmi.h> #include "../perf_event.h" +static DEFINE_PER_CPU(unsigned int, perf_nmi_counter); + static __initconst const u64 amd_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] @@ -113,22 +117,39 @@ static __initconst const u64 amd_hw_cache_event_ids }; /* - * AMD Performance Monitor K7 and later. + * AMD Performance Monitor K7 and later, up to and including Family 16h: */ static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] = { - [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, - [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, - [PERF_COUNT_HW_CACHE_REFERENCES] = 0x077d, - [PERF_COUNT_HW_CACHE_MISSES] = 0x077e, - [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, - [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, - [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00d0, /* "Decoder empty" event */ - [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x00d1, /* "Dispatch stalls" event */ + [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, + [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0x077d, + [PERF_COUNT_HW_CACHE_MISSES] = 0x077e, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, + [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00d0, /* "Decoder empty" event */ + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x00d1, /* "Dispatch stalls" event */ +}; + +/* + * AMD Performance Monitor Family 17h and later: + */ +static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] = +{ + [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, + [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0xff60, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, + [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x0287, + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x0187, }; static u64 amd_pmu_event_map(int hw_event) { + if (boot_cpu_data.x86 >= 0x17) + return amd_f17h_perfmon_event_map[hw_event]; + return amd_perfmon_event_map[hw_event]; } @@ -429,6 +450,132 @@ static void amd_pmu_cpu_dead(int cpu) } } +/* + * When a PMC counter overflows, an NMI is used to process the event and + * reset the counter. NMI latency can result in the counter being updated + * before the NMI can run, which can result in what appear to be spurious + * NMIs. This function is intended to wait for the NMI to run and reset + * the counter to avoid possible unhandled NMI messages. + */ +#define OVERFLOW_WAIT_COUNT 50 + +static void amd_pmu_wait_on_overflow(int idx) +{ + unsigned int i; + u64 counter; + + /* + * Wait for the counter to be reset if it has overflowed. This loop + * should exit very, very quickly, but just in case, don't wait + * forever... + */ + for (i = 0; i < OVERFLOW_WAIT_COUNT; i++) { + rdmsrl(x86_pmu_event_addr(idx), counter); + if (counter & (1ULL << (x86_pmu.cntval_bits - 1))) + break; + + /* Might be in IRQ context, so can't sleep */ + udelay(1); + } +} + +static void amd_pmu_disable_all(void) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + int idx; + + x86_pmu_disable_all(); + + /* + * This shouldn't be called from NMI context, but add a safeguard here + * to return, since if we're in NMI context we can't wait for an NMI + * to reset an overflowed counter value. + */ + if (in_nmi()) + return; + + /* + * Check each counter for overflow and wait for it to be reset by the + * NMI if it has overflowed. This relies on the fact that all active + * counters are always enabled when this function is caled and + * ARCH_PERFMON_EVENTSEL_INT is always set. + */ + for (idx = 0; idx < x86_pmu.num_counters; idx++) { + if (!test_bit(idx, cpuc->active_mask)) + continue; + + amd_pmu_wait_on_overflow(idx); + } +} + +static void amd_pmu_disable_event(struct perf_event *event) +{ + x86_pmu_disable_event(event); + + /* + * This can be called from NMI context (via x86_pmu_stop). The counter + * may have overflowed, but either way, we'll never see it get reset + * by the NMI if we're already in the NMI. And the NMI latency support + * below will take care of any pending NMI that might have been + * generated by the overflow. + */ + if (in_nmi()) + return; + + amd_pmu_wait_on_overflow(event->hw.idx); +} + +/* + * Because of NMI latency, if multiple PMC counters are active or other sources + * of NMIs are received, the perf NMI handler can handle one or more overflowed + * PMC counters outside of the NMI associated with the PMC overflow. If the NMI + * doesn't arrive at the LAPIC in time to become a pending NMI, then the kernel + * back-to-back NMI support won't be active. This PMC handler needs to take into + * account that this can occur, otherwise this could result in unknown NMI + * messages being issued. Examples of this is PMC overflow while in the NMI + * handler when multiple PMCs are active or PMC overflow while handling some + * other source of an NMI. + * + * Attempt to mitigate this by using the number of active PMCs to determine + * whether to return NMI_HANDLED if the perf NMI handler did not handle/reset + * any PMCs. The per-CPU perf_nmi_counter variable is set to a minimum of the + * number of active PMCs or 2. The value of 2 is used in case an NMI does not + * arrive at the LAPIC in time to be collapsed into an already pending NMI. + */ +static int amd_pmu_handle_irq(struct pt_regs *regs) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + int active, handled; + + /* + * Obtain the active count before calling x86_pmu_handle_irq() since + * it is possible that x86_pmu_handle_irq() may make a counter + * inactive (through x86_pmu_stop). + */ + active = __bitmap_weight(cpuc->active_mask, X86_PMC_IDX_MAX); + + /* Process any counter overflows */ + handled = x86_pmu_handle_irq(regs); + + /* + * If a counter was handled, record the number of possible remaining + * NMIs that can occur. + */ + if (handled) { + this_cpu_write(perf_nmi_counter, + min_t(unsigned int, 2, active)); + + return handled; + } + + if (!this_cpu_read(perf_nmi_counter)) + return NMI_DONE; + + this_cpu_dec(perf_nmi_counter); + + return NMI_HANDLED; +} + static struct event_constraint * amd_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event) @@ -621,11 +768,11 @@ static ssize_t amd_event_sysfs_show(char *page, u64 config) static __initconst const struct x86_pmu amd_pmu = { .name = "AMD", - .handle_irq = x86_pmu_handle_irq, - .disable_all = x86_pmu_disable_all, + .handle_irq = amd_pmu_handle_irq, + .disable_all = amd_pmu_disable_all, .enable_all = x86_pmu_enable_all, .enable = x86_pmu_enable_event, - .disable = x86_pmu_disable_event, + .disable = amd_pmu_disable_event, .hw_config = amd_pmu_hw_config, .schedule_events = x86_schedule_events, .eventsel = MSR_K7_EVNTSEL0, @@ -732,7 +879,7 @@ void amd_pmu_enable_virt(void) cpuc->perf_ctr_virt_mask = 0; /* Reload all events */ - x86_pmu_disable_all(); + amd_pmu_disable_all(); x86_pmu_enable_all(0); } EXPORT_SYMBOL_GPL(amd_pmu_enable_virt); @@ -750,7 +897,7 @@ void amd_pmu_disable_virt(void) cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY; /* Reload all events */ - x86_pmu_disable_all(); + amd_pmu_disable_all(); x86_pmu_enable_all(0); } EXPORT_SYMBOL_GPL(amd_pmu_disable_virt); diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index e2b1447192a8..81911e11a15d 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1349,8 +1349,9 @@ void x86_pmu_stop(struct perf_event *event, int flags) struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; - if (__test_and_clear_bit(hwc->idx, cpuc->active_mask)) { + if (test_bit(hwc->idx, cpuc->active_mask)) { x86_pmu.disable(event); + __clear_bit(hwc->idx, cpuc->active_mask); cpuc->events[hwc->idx] = NULL; WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); hwc->state |= PERF_HES_STOPPED; @@ -1447,16 +1448,8 @@ int x86_pmu_handle_irq(struct pt_regs *regs) apic_write(APIC_LVTPC, APIC_DM_NMI); for (idx = 0; idx < x86_pmu.num_counters; idx++) { - if (!test_bit(idx, cpuc->active_mask)) { - /* - * Though we deactivated the counter some cpus - * might still deliver spurious interrupts still - * in flight. Catch them: - */ - if (__test_and_clear_bit(idx, cpuc->running)) - handled++; + if (!test_bit(idx, cpuc->active_mask)) continue; - } event = cpuc->events[idx]; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 8baa441d8000..f9451566cd9b 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3131,7 +3131,7 @@ static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event) flags &= ~PERF_SAMPLE_TIME; if (!event->attr.exclude_kernel) flags &= ~PERF_SAMPLE_REGS_USER; - if (event->attr.sample_regs_user & ~PEBS_REGS) + if (event->attr.sample_regs_user & ~PEBS_GP_REGS) flags &= ~(PERF_SAMPLE_REGS_USER | PERF_SAMPLE_REGS_INTR); return flags; } @@ -3185,7 +3185,7 @@ static int intel_pmu_hw_config(struct perf_event *event) return ret; if (event->attr.precise_ip) { - if (!event->attr.freq) { + if (!(event->attr.freq || event->attr.wakeup_events)) { event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD; if (!(event->attr.sample_type & ~intel_pmu_large_pebs_flags(event))) @@ -3575,6 +3575,12 @@ static void intel_pmu_cpu_starting(int cpu) cpuc->lbr_sel = NULL; + if (x86_pmu.flags & PMU_FL_TFA) { + WARN_ON_ONCE(cpuc->tfa_shadow); + cpuc->tfa_shadow = ~0ULL; + intel_set_tfa(cpuc, false); + } + if (x86_pmu.version > 1) flip_smm_bit(&x86_pmu.attr_freeze_on_smi); diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 94a4b7fc75d0..d41de9af7a39 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -76,15 +76,15 @@ * Scope: Package (physical package) * MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter. * perf code: 0x04 - * Available model: HSW ULT,CNL + * Available model: HSW ULT,KBL,CNL * Scope: Package (physical package) * MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter. * perf code: 0x05 - * Available model: HSW ULT,CNL + * Available model: HSW ULT,KBL,CNL * Scope: Package (physical package) * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. * perf code: 0x06 - * Available model: HSW ULT,GLM,CNL + * Available model: HSW ULT,KBL,GLM,CNL * Scope: Package (physical package) * */ @@ -566,8 +566,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates), X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_X, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, snb_cstates), - X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, hswult_cstates), + X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, hswult_cstates), X86_CSTATES_MODEL(INTEL_FAM6_CANNONLAKE_MOBILE, cnl_cstates), diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index a75955741c50..1e98a42b560a 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -96,25 +96,25 @@ struct amd_nb { PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER | \ PERF_SAMPLE_PERIOD) -#define PEBS_REGS \ - (PERF_REG_X86_AX | \ - PERF_REG_X86_BX | \ - PERF_REG_X86_CX | \ - PERF_REG_X86_DX | \ - PERF_REG_X86_DI | \ - PERF_REG_X86_SI | \ - PERF_REG_X86_SP | \ - PERF_REG_X86_BP | \ - PERF_REG_X86_IP | \ - PERF_REG_X86_FLAGS | \ - PERF_REG_X86_R8 | \ - PERF_REG_X86_R9 | \ - PERF_REG_X86_R10 | \ - PERF_REG_X86_R11 | \ - PERF_REG_X86_R12 | \ - PERF_REG_X86_R13 | \ - PERF_REG_X86_R14 | \ - PERF_REG_X86_R15) +#define PEBS_GP_REGS \ + ((1ULL << PERF_REG_X86_AX) | \ + (1ULL << PERF_REG_X86_BX) | \ + (1ULL << PERF_REG_X86_CX) | \ + (1ULL << PERF_REG_X86_DX) | \ + (1ULL << PERF_REG_X86_DI) | \ + (1ULL << PERF_REG_X86_SI) | \ + (1ULL << PERF_REG_X86_SP) | \ + (1ULL << PERF_REG_X86_BP) | \ + (1ULL << PERF_REG_X86_IP) | \ + (1ULL << PERF_REG_X86_FLAGS) | \ + (1ULL << PERF_REG_X86_R8) | \ + (1ULL << PERF_REG_X86_R9) | \ + (1ULL << PERF_REG_X86_R10) | \ + (1ULL << PERF_REG_X86_R11) | \ + (1ULL << PERF_REG_X86_R12) | \ + (1ULL << PERF_REG_X86_R13) | \ + (1ULL << PERF_REG_X86_R14) | \ + (1ULL << PERF_REG_X86_R15)) /* * Per register state. diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 93c4bf598fb0..feab24cac610 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -226,7 +226,9 @@ struct x86_emulate_ops { unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt); void (*set_hflags)(struct x86_emulate_ctxt *ctxt, unsigned hflags); - int (*pre_leave_smm)(struct x86_emulate_ctxt *ctxt, u64 smbase); + int (*pre_leave_smm)(struct x86_emulate_ctxt *ctxt, + const char *smstate); + void (*post_leave_smm)(struct x86_emulate_ctxt *ctxt); }; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index a5db4475e72d..c79abe7ca093 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -126,7 +126,7 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) } #define KVM_PERMILLE_MMU_PAGES 20 -#define KVM_MIN_ALLOC_MMU_PAGES 64 +#define KVM_MIN_ALLOC_MMU_PAGES 64UL #define KVM_MMU_HASH_SHIFT 12 #define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT) #define KVM_MIN_FREE_MMU_PAGES 5 @@ -253,14 +253,14 @@ struct kvm_mmu_memory_cache { * kvm_memory_slot.arch.gfn_track which is 16 bits, so the role bits used * by indirect shadow page can not be more than 15 bits. * - * Currently, we used 14 bits that are @level, @cr4_pae, @quadrant, @access, + * Currently, we used 14 bits that are @level, @gpte_is_8_bytes, @quadrant, @access, * @nxe, @cr0_wp, @smep_andnot_wp and @smap_andnot_wp. */ union kvm_mmu_page_role { u32 word; struct { unsigned level:4; - unsigned cr4_pae:1; + unsigned gpte_is_8_bytes:1; unsigned quadrant:2; unsigned direct:1; unsigned access:3; @@ -295,6 +295,7 @@ union kvm_mmu_extended_role { unsigned int valid:1; unsigned int execonly:1; unsigned int cr0_pg:1; + unsigned int cr4_pae:1; unsigned int cr4_pse:1; unsigned int cr4_pke:1; unsigned int cr4_smap:1; @@ -350,6 +351,7 @@ struct kvm_mmu_page { }; struct kvm_pio_request { + unsigned long linear_rip; unsigned long count; int in; int port; @@ -568,6 +570,7 @@ struct kvm_vcpu_arch { bool tpr_access_reporting; u64 ia32_xss; u64 microcode_version; + u64 arch_capabilities; /* * Paging state of the vcpu @@ -842,9 +845,9 @@ enum kvm_irqchip_mode { }; struct kvm_arch { - unsigned int n_used_mmu_pages; - unsigned int n_requested_mmu_pages; - unsigned int n_max_mmu_pages; + unsigned long n_used_mmu_pages; + unsigned long n_requested_mmu_pages; + unsigned long n_max_mmu_pages; unsigned int indirect_shadow_pages; struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES]; /* @@ -1180,7 +1183,7 @@ struct kvm_x86_ops { int (*smi_allowed)(struct kvm_vcpu *vcpu); int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate); - int (*pre_leave_smm)(struct kvm_vcpu *vcpu, u64 smbase); + int (*pre_leave_smm)(struct kvm_vcpu *vcpu, const char *smstate); int (*enable_smi_window)(struct kvm_vcpu *vcpu); int (*mem_enc_op)(struct kvm *kvm, void __user *argp); @@ -1192,6 +1195,8 @@ struct kvm_x86_ops { int (*nested_enable_evmcs)(struct kvm_vcpu *vcpu, uint16_t *vmcs_version); uint16_t (*nested_get_evmcs_version)(struct kvm_vcpu *vcpu); + + bool (*need_emulation_on_page_fault)(struct kvm_vcpu *vcpu); }; struct kvm_arch_async_pf { @@ -1252,8 +1257,8 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, gfn_t gfn_offset, unsigned long mask); void kvm_mmu_zap_all(struct kvm *kvm); void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen); -unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm); -void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages); +unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm); +void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages); int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3); bool pdptrs_changed(struct kvm_vcpu *vcpu); @@ -1588,4 +1593,7 @@ static inline int kvm_cpu_get_apicid(int mps_cpu) #define put_smstate(type, buf, offset, val) \ *(type *)((buf) + (offset) - 0x7e00) = val +#define GET_SMSTATE(type, buf, offset) \ + (*(type *)((buf) + (offset) - 0x7e00)) + #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 2779ace16d23..50b3e2d963c9 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -46,7 +46,7 @@ void ptdump_walk_user_pgd_level_checkwx(void); */ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __visible; -#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) +#define ZERO_PAGE(vaddr) ((void)(vaddr),virt_to_page(empty_zero_page)) extern spinlock_t pgd_lock; extern struct list_head pgd_list; diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index d653139857af..4c305471ec33 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -91,11 +91,9 @@ static inline void syscall_set_return_value(struct task_struct *task, static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args) { - BUG_ON(i + n > 6); - memcpy(args, ®s->bx + i, n * sizeof(args[0])); + memcpy(args, ®s->bx, 6 * sizeof(args[0])); } static inline void syscall_set_arguments(struct task_struct *task, @@ -116,124 +114,50 @@ static inline int syscall_get_arch(void) static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args) { # ifdef CONFIG_IA32_EMULATION - if (task->thread_info.status & TS_COMPAT) - switch (i) { - case 0: - if (!n--) break; - *args++ = regs->bx; - case 1: - if (!n--) break; - *args++ = regs->cx; - case 2: - if (!n--) break; - *args++ = regs->dx; - case 3: - if (!n--) break; - *args++ = regs->si; - case 4: - if (!n--) break; - *args++ = regs->di; - case 5: - if (!n--) break; - *args++ = regs->bp; - case 6: - if (!n--) break; - default: - BUG(); - break; - } - else + if (task->thread_info.status & TS_COMPAT) { + *args++ = regs->bx; + *args++ = regs->cx; + *args++ = regs->dx; + *args++ = regs->si; + *args++ = regs->di; + *args = regs->bp; + } else # endif - switch (i) { - case 0: - if (!n--) break; - *args++ = regs->di; - case 1: - if (!n--) break; - *args++ = regs->si; - case 2: - if (!n--) break; - *args++ = regs->dx; - case 3: - if (!n--) break; - *args++ = regs->r10; - case 4: - if (!n--) break; - *args++ = regs->r8; - case 5: - if (!n--) break; - *args++ = regs->r9; - case 6: - if (!n--) break; - default: - BUG(); - break; - } + { + *args++ = regs->di; + *args++ = regs->si; + *args++ = regs->dx; + *args++ = regs->r10; + *args++ = regs->r8; + *args = regs->r9; + } } static inline void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, const unsigned long *args) { # ifdef CONFIG_IA32_EMULATION - if (task->thread_info.status & TS_COMPAT) - switch (i) { - case 0: - if (!n--) break; - regs->bx = *args++; - case 1: - if (!n--) break; - regs->cx = *args++; - case 2: - if (!n--) break; - regs->dx = *args++; - case 3: - if (!n--) break; - regs->si = *args++; - case 4: - if (!n--) break; - regs->di = *args++; - case 5: - if (!n--) break; - regs->bp = *args++; - case 6: - if (!n--) break; - default: - BUG(); - break; - } - else + if (task->thread_info.status & TS_COMPAT) { + regs->bx = *args++; + regs->cx = *args++; + regs->dx = *args++; + regs->si = *args++; + regs->di = *args++; + regs->bp = *args; + } else # endif - switch (i) { - case 0: - if (!n--) break; - regs->di = *args++; - case 1: - if (!n--) break; - regs->si = *args++; - case 2: - if (!n--) break; - regs->dx = *args++; - case 3: - if (!n--) break; - regs->r10 = *args++; - case 4: - if (!n--) break; - regs->r8 = *args++; - case 5: - if (!n--) break; - regs->r9 = *args++; - case 6: - if (!n--) break; - default: - BUG(); - break; - } + { + regs->di = *args++; + regs->si = *args++; + regs->dx = *args++; + regs->r10 = *args++; + regs->r8 = *args++; + regs->r9 = *args; + } } static inline int syscall_get_arch(void) diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index de6f0d59a24f..2863c2026655 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -206,6 +206,9 @@ xen_single_call(unsigned int call, __HYPERCALL_DECLS; __HYPERCALL_5ARG(a1, a2, a3, a4, a5); + if (call >= PAGE_SIZE / sizeof(hypercall_page[0])) + return -EINVAL; + asm volatile(CALL_NOSPEC : __HYPERCALL_5PARAM : [thunk_target] "a" (&hypercall_page[call]) diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index dabfcf7c3941..7a0e64ccd6ff 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -381,6 +381,7 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) #define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) #define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2) +#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3) #define KVM_STATE_NESTED_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_RUN_PENDING 0x00000002 diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index f0b0c90dd398..d213ec5c3766 100644 --- a/arch/x86/include/uapi/asm/vmx.h +++ b/arch/x86/include/uapi/asm/vmx.h @@ -146,6 +146,7 @@ #define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1 #define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2 +#define VMX_ABORT_VMCS_CORRUPTED 3 #define VMX_ABORT_LOAD_HOST_MSR_FAIL 4 #endif /* _UAPIVMX_H */ diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index a034cb808e7e..fed46ddb1eef 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -569,6 +569,7 @@ void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) unsigned long *sara = stack_addr(regs); ri->ret_addr = (kprobe_opcode_t *) *sara; + ri->fp = sara; /* Replace the return addr with trampoline addr */ *sara = (unsigned long) &kretprobe_trampoline; @@ -748,26 +749,48 @@ asm( NOKPROBE_SYMBOL(kretprobe_trampoline); STACK_FRAME_NON_STANDARD(kretprobe_trampoline); +static struct kprobe kretprobe_kprobe = { + .addr = (void *)kretprobe_trampoline, +}; + /* * Called from kretprobe_trampoline */ static __used void *trampoline_handler(struct pt_regs *regs) { + struct kprobe_ctlblk *kcb; struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; struct hlist_node *tmp; unsigned long flags, orig_ret_address = 0; unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline; kprobe_opcode_t *correct_ret_addr = NULL; + void *frame_pointer; + bool skipped = false; + + preempt_disable(); + + /* + * Set a dummy kprobe for avoiding kretprobe recursion. + * Since kretprobe never run in kprobe handler, kprobe must not + * be running at this point. + */ + kcb = get_kprobe_ctlblk(); + __this_cpu_write(current_kprobe, &kretprobe_kprobe); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; INIT_HLIST_HEAD(&empty_rp); kretprobe_hash_lock(current, &head, &flags); /* fixup registers */ #ifdef CONFIG_X86_64 regs->cs = __KERNEL_CS; + /* On x86-64, we use pt_regs->sp for return address holder. */ + frame_pointer = ®s->sp; #else regs->cs = __KERNEL_CS | get_kernel_rpl(); regs->gs = 0; + /* On x86-32, we use pt_regs->flags for return address holder. */ + frame_pointer = ®s->flags; #endif regs->ip = trampoline_address; regs->orig_ax = ~0UL; @@ -789,8 +812,25 @@ static __used void *trampoline_handler(struct pt_regs *regs) if (ri->task != current) /* another task is sharing our hash bucket */ continue; + /* + * Return probes must be pushed on this hash list correct + * order (same as return order) so that it can be poped + * correctly. However, if we find it is pushed it incorrect + * order, this means we find a function which should not be + * probed, because the wrong order entry is pushed on the + * path of processing other kretprobe itself. + */ + if (ri->fp != frame_pointer) { + if (!skipped) + pr_warn("kretprobe is stacked incorrectly. Trying to fixup.\n"); + skipped = true; + continue; + } orig_ret_address = (unsigned long)ri->ret_addr; + if (skipped) + pr_warn("%ps must be blacklisted because of incorrect kretprobe order\n", + ri->rp->kp.addr); if (orig_ret_address != trampoline_address) /* @@ -808,14 +848,15 @@ static __used void *trampoline_handler(struct pt_regs *regs) if (ri->task != current) /* another task is sharing our hash bucket */ continue; + if (ri->fp != frame_pointer) + continue; orig_ret_address = (unsigned long)ri->ret_addr; if (ri->rp && ri->rp->handler) { __this_cpu_write(current_kprobe, &ri->rp->kp); - get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE; ri->ret_addr = correct_ret_addr; ri->rp->handler(ri, regs); - __this_cpu_write(current_kprobe, NULL); + __this_cpu_write(current_kprobe, &kretprobe_kprobe); } recycle_rp_inst(ri, &empty_rp); @@ -831,6 +872,9 @@ static __used void *trampoline_handler(struct pt_regs *regs) kretprobe_hash_unlock(current, &flags); + __this_cpu_write(current_kprobe, NULL); + preempt_enable(); + hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index c338984c850d..d0d5dd44b4f4 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2331,24 +2331,18 @@ static int em_lseg(struct x86_emulate_ctxt *ctxt) static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt) { +#ifdef CONFIG_X86_64 u32 eax, ebx, ecx, edx; eax = 0x80000001; ecx = 0; ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false); return edx & bit(X86_FEATURE_LM); +#else + return false; +#endif } -#define GET_SMSTATE(type, smbase, offset) \ - ({ \ - type __val; \ - int r = ctxt->ops->read_phys(ctxt, smbase + offset, &__val, \ - sizeof(__val)); \ - if (r != X86EMUL_CONTINUE) \ - return X86EMUL_UNHANDLEABLE; \ - __val; \ - }) - static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags) { desc->g = (flags >> 23) & 1; @@ -2361,27 +2355,30 @@ static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags) desc->type = (flags >> 8) & 15; } -static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, u64 smbase, int n) +static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, const char *smstate, + int n) { struct desc_struct desc; int offset; u16 selector; - selector = GET_SMSTATE(u32, smbase, 0x7fa8 + n * 4); + selector = GET_SMSTATE(u32, smstate, 0x7fa8 + n * 4); if (n < 3) offset = 0x7f84 + n * 12; else offset = 0x7f2c + (n - 3) * 12; - set_desc_base(&desc, GET_SMSTATE(u32, smbase, offset + 8)); - set_desc_limit(&desc, GET_SMSTATE(u32, smbase, offset + 4)); - rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, offset)); + set_desc_base(&desc, GET_SMSTATE(u32, smstate, offset + 8)); + set_desc_limit(&desc, GET_SMSTATE(u32, smstate, offset + 4)); + rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, offset)); ctxt->ops->set_segment(ctxt, selector, &desc, 0, n); return X86EMUL_CONTINUE; } -static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n) +#ifdef CONFIG_X86_64 +static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, const char *smstate, + int n) { struct desc_struct desc; int offset; @@ -2390,15 +2387,16 @@ static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n) offset = 0x7e00 + n * 16; - selector = GET_SMSTATE(u16, smbase, offset); - rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smbase, offset + 2) << 8); - set_desc_limit(&desc, GET_SMSTATE(u32, smbase, offset + 4)); - set_desc_base(&desc, GET_SMSTATE(u32, smbase, offset + 8)); - base3 = GET_SMSTATE(u32, smbase, offset + 12); + selector = GET_SMSTATE(u16, smstate, offset); + rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smstate, offset + 2) << 8); + set_desc_limit(&desc, GET_SMSTATE(u32, smstate, offset + 4)); + set_desc_base(&desc, GET_SMSTATE(u32, smstate, offset + 8)); + base3 = GET_SMSTATE(u32, smstate, offset + 12); ctxt->ops->set_segment(ctxt, selector, &desc, base3, n); return X86EMUL_CONTINUE; } +#endif static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt, u64 cr0, u64 cr3, u64 cr4) @@ -2445,7 +2443,8 @@ static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt, return X86EMUL_CONTINUE; } -static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase) +static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, + const char *smstate) { struct desc_struct desc; struct desc_ptr dt; @@ -2453,53 +2452,55 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase) u32 val, cr0, cr3, cr4; int i; - cr0 = GET_SMSTATE(u32, smbase, 0x7ffc); - cr3 = GET_SMSTATE(u32, smbase, 0x7ff8); - ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7ff4) | X86_EFLAGS_FIXED; - ctxt->_eip = GET_SMSTATE(u32, smbase, 0x7ff0); + cr0 = GET_SMSTATE(u32, smstate, 0x7ffc); + cr3 = GET_SMSTATE(u32, smstate, 0x7ff8); + ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7ff4) | X86_EFLAGS_FIXED; + ctxt->_eip = GET_SMSTATE(u32, smstate, 0x7ff0); for (i = 0; i < 8; i++) - *reg_write(ctxt, i) = GET_SMSTATE(u32, smbase, 0x7fd0 + i * 4); + *reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4); - val = GET_SMSTATE(u32, smbase, 0x7fcc); + val = GET_SMSTATE(u32, smstate, 0x7fcc); ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1); - val = GET_SMSTATE(u32, smbase, 0x7fc8); + val = GET_SMSTATE(u32, smstate, 0x7fc8); ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1); - selector = GET_SMSTATE(u32, smbase, 0x7fc4); - set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7f64)); - set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7f60)); - rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7f5c)); + selector = GET_SMSTATE(u32, smstate, 0x7fc4); + set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f64)); + set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7f60)); + rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7f5c)); ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_TR); - selector = GET_SMSTATE(u32, smbase, 0x7fc0); - set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7f80)); - set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7f7c)); - rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7f78)); + selector = GET_SMSTATE(u32, smstate, 0x7fc0); + set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f80)); + set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7f7c)); + rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7f78)); ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_LDTR); - dt.address = GET_SMSTATE(u32, smbase, 0x7f74); - dt.size = GET_SMSTATE(u32, smbase, 0x7f70); + dt.address = GET_SMSTATE(u32, smstate, 0x7f74); + dt.size = GET_SMSTATE(u32, smstate, 0x7f70); ctxt->ops->set_gdt(ctxt, &dt); - dt.address = GET_SMSTATE(u32, smbase, 0x7f58); - dt.size = GET_SMSTATE(u32, smbase, 0x7f54); + dt.address = GET_SMSTATE(u32, smstate, 0x7f58); + dt.size = GET_SMSTATE(u32, smstate, 0x7f54); ctxt->ops->set_idt(ctxt, &dt); for (i = 0; i < 6; i++) { - int r = rsm_load_seg_32(ctxt, smbase, i); + int r = rsm_load_seg_32(ctxt, smstate, i); if (r != X86EMUL_CONTINUE) return r; } - cr4 = GET_SMSTATE(u32, smbase, 0x7f14); + cr4 = GET_SMSTATE(u32, smstate, 0x7f14); - ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7ef8)); + ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7ef8)); return rsm_enter_protected_mode(ctxt, cr0, cr3, cr4); } -static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase) +#ifdef CONFIG_X86_64 +static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, + const char *smstate) { struct desc_struct desc; struct desc_ptr dt; @@ -2509,43 +2510,43 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase) int i, r; for (i = 0; i < 16; i++) - *reg_write(ctxt, i) = GET_SMSTATE(u64, smbase, 0x7ff8 - i * 8); + *reg_write(ctxt, i) = GET_SMSTATE(u64, smstate, 0x7ff8 - i * 8); - ctxt->_eip = GET_SMSTATE(u64, smbase, 0x7f78); - ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7f70) | X86_EFLAGS_FIXED; + ctxt->_eip = GET_SMSTATE(u64, smstate, 0x7f78); + ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7f70) | X86_EFLAGS_FIXED; - val = GET_SMSTATE(u32, smbase, 0x7f68); + val = GET_SMSTATE(u32, smstate, 0x7f68); ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1); - val = GET_SMSTATE(u32, smbase, 0x7f60); + val = GET_SMSTATE(u32, smstate, 0x7f60); ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1); - cr0 = GET_SMSTATE(u64, smbase, 0x7f58); - cr3 = GET_SMSTATE(u64, smbase, 0x7f50); - cr4 = GET_SMSTATE(u64, smbase, 0x7f48); - ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7f00)); - val = GET_SMSTATE(u64, smbase, 0x7ed0); + cr0 = GET_SMSTATE(u64, smstate, 0x7f58); + cr3 = GET_SMSTATE(u64, smstate, 0x7f50); + cr4 = GET_SMSTATE(u64, smstate, 0x7f48); + ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7f00)); + val = GET_SMSTATE(u64, smstate, 0x7ed0); ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA); - selector = GET_SMSTATE(u32, smbase, 0x7e90); - rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7e92) << 8); - set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7e94)); - set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7e98)); - base3 = GET_SMSTATE(u32, smbase, 0x7e9c); + selector = GET_SMSTATE(u32, smstate, 0x7e90); + rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e92) << 8); + set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7e94)); + set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7e98)); + base3 = GET_SMSTATE(u32, smstate, 0x7e9c); ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_TR); - dt.size = GET_SMSTATE(u32, smbase, 0x7e84); - dt.address = GET_SMSTATE(u64, smbase, 0x7e88); + dt.size = GET_SMSTATE(u32, smstate, 0x7e84); + dt.address = GET_SMSTATE(u64, smstate, 0x7e88); ctxt->ops->set_idt(ctxt, &dt); - selector = GET_SMSTATE(u32, smbase, 0x7e70); - rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7e72) << 8); - set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7e74)); - set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7e78)); - base3 = GET_SMSTATE(u32, smbase, 0x7e7c); + selector = GET_SMSTATE(u32, smstate, 0x7e70); + rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e72) << 8); + set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7e74)); + set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7e78)); + base3 = GET_SMSTATE(u32, smstate, 0x7e7c); ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_LDTR); - dt.size = GET_SMSTATE(u32, smbase, 0x7e64); - dt.address = GET_SMSTATE(u64, smbase, 0x7e68); + dt.size = GET_SMSTATE(u32, smstate, 0x7e64); + dt.address = GET_SMSTATE(u64, smstate, 0x7e68); ctxt->ops->set_gdt(ctxt, &dt); r = rsm_enter_protected_mode(ctxt, cr0, cr3, cr4); @@ -2553,37 +2554,49 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase) return r; for (i = 0; i < 6; i++) { - r = rsm_load_seg_64(ctxt, smbase, i); + r = rsm_load_seg_64(ctxt, smstate, i); if (r != X86EMUL_CONTINUE) return r; } return X86EMUL_CONTINUE; } +#endif static int em_rsm(struct x86_emulate_ctxt *ctxt) { unsigned long cr0, cr4, efer; + char buf[512]; u64 smbase; int ret; if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_MASK) == 0) return emulate_ud(ctxt); + smbase = ctxt->ops->get_smbase(ctxt); + + ret = ctxt->ops->read_phys(ctxt, smbase + 0xfe00, buf, sizeof(buf)); + if (ret != X86EMUL_CONTINUE) + return X86EMUL_UNHANDLEABLE; + + if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0) + ctxt->ops->set_nmi_mask(ctxt, false); + + ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) & + ~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK)); + /* * Get back to real mode, to prepare a safe state in which to load * CR0/CR3/CR4/EFER. It's all a bit more complicated if the vCPU * supports long mode. */ - cr4 = ctxt->ops->get_cr(ctxt, 4); if (emulator_has_longmode(ctxt)) { struct desc_struct cs_desc; /* Zero CR4.PCIDE before CR0.PG. */ - if (cr4 & X86_CR4_PCIDE) { + cr4 = ctxt->ops->get_cr(ctxt, 4); + if (cr4 & X86_CR4_PCIDE) ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE); - cr4 &= ~X86_CR4_PCIDE; - } /* A 32-bit code segment is required to clear EFER.LMA. */ memset(&cs_desc, 0, sizeof(cs_desc)); @@ -2597,39 +2610,39 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt) if (cr0 & X86_CR0_PE) ctxt->ops->set_cr(ctxt, 0, cr0 & ~(X86_CR0_PG | X86_CR0_PE)); - /* Now clear CR4.PAE (which must be done before clearing EFER.LME). */ - if (cr4 & X86_CR4_PAE) - ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE); - - /* And finally go back to 32-bit mode. */ - efer = 0; - ctxt->ops->set_msr(ctxt, MSR_EFER, efer); + if (emulator_has_longmode(ctxt)) { + /* Clear CR4.PAE before clearing EFER.LME. */ + cr4 = ctxt->ops->get_cr(ctxt, 4); + if (cr4 & X86_CR4_PAE) + ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE); - smbase = ctxt->ops->get_smbase(ctxt); + /* And finally go back to 32-bit mode. */ + efer = 0; + ctxt->ops->set_msr(ctxt, MSR_EFER, efer); + } /* * Give pre_leave_smm() a chance to make ISA-specific changes to the * vCPU state (e.g. enter guest mode) before loading state from the SMM * state-save area. */ - if (ctxt->ops->pre_leave_smm(ctxt, smbase)) + if (ctxt->ops->pre_leave_smm(ctxt, buf)) return X86EMUL_UNHANDLEABLE; +#ifdef CONFIG_X86_64 if (emulator_has_longmode(ctxt)) - ret = rsm_load_state_64(ctxt, smbase + 0x8000); + ret = rsm_load_state_64(ctxt, buf); else - ret = rsm_load_state_32(ctxt, smbase + 0x8000); +#endif + ret = rsm_load_state_32(ctxt, buf); if (ret != X86EMUL_CONTINUE) { /* FIXME: should triple fault */ return X86EMUL_UNHANDLEABLE; } - if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0) - ctxt->ops->set_nmi_mask(ctxt, false); + ctxt->ops->post_leave_smm(ctxt); - ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) & - ~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK)); return X86EMUL_CONTINUE; } diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 27c43525a05f..cc24b3a32c44 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -526,7 +526,9 @@ static int stimer_set_config(struct kvm_vcpu_hv_stimer *stimer, u64 config, new_config.enable = 0; stimer->config.as_uint64 = new_config.as_uint64; - stimer_mark_pending(stimer, false); + if (stimer->config.enable) + stimer_mark_pending(stimer, false); + return 0; } @@ -542,7 +544,10 @@ static int stimer_set_count(struct kvm_vcpu_hv_stimer *stimer, u64 count, stimer->config.enable = 0; else if (stimer->config.auto_enable) stimer->config.enable = 1; - stimer_mark_pending(stimer, false); + + if (stimer->config.enable) + stimer_mark_pending(stimer, false); + return 0; } @@ -1366,7 +1371,16 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa, valid_bank_mask = BIT_ULL(0); sparse_banks[0] = flush.processor_mask; - all_cpus = flush.flags & HV_FLUSH_ALL_PROCESSORS; + + /* + * Work around possible WS2012 bug: it sends hypercalls + * with processor_mask = 0x0 and HV_FLUSH_ALL_PROCESSORS clear, + * while also expecting us to flush something and crashing if + * we don't. Let's treat processor_mask == 0 same as + * HV_FLUSH_ALL_PROCESSORS. + */ + all_cpus = (flush.flags & HV_FLUSH_ALL_PROCESSORS) || + flush.processor_mask == 0; } else { if (unlikely(kvm_read_guest(kvm, ingpa, &flush_ex, sizeof(flush_ex)))) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 991fdf7fc17f..bd13fdddbdc4 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -70,7 +70,6 @@ #define APIC_BROADCAST 0xFF #define X2APIC_BROADCAST 0xFFFFFFFFul -static bool lapic_timer_advance_adjust_done = false; #define LAPIC_TIMER_ADVANCE_ADJUST_DONE 100 /* step-by-step approximation to mitigate fluctuation */ #define LAPIC_TIMER_ADVANCE_ADJUST_STEP 8 @@ -138,6 +137,7 @@ static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map, if (offset <= max_apic_id) { u8 cluster_size = min(max_apic_id - offset + 1, 16U); + offset = array_index_nospec(offset, map->max_apic_id + 1); *cluster = &map->phys_map[offset]; *mask = dest_id & (0xffff >> (16 - cluster_size)); } else { @@ -901,7 +901,8 @@ static inline bool kvm_apic_map_get_dest_lapic(struct kvm *kvm, if (irq->dest_id > map->max_apic_id) { *bitmap = 0; } else { - *dst = &map->phys_map[irq->dest_id]; + u32 dest_id = array_index_nospec(irq->dest_id, map->max_apic_id + 1); + *dst = &map->phys_map[dest_id]; *bitmap = 1; } return true; @@ -1480,14 +1481,32 @@ static bool lapic_timer_int_injected(struct kvm_vcpu *vcpu) return false; } +static inline void __wait_lapic_expire(struct kvm_vcpu *vcpu, u64 guest_cycles) +{ + u64 timer_advance_ns = vcpu->arch.apic->lapic_timer.timer_advance_ns; + + /* + * If the guest TSC is running at a different ratio than the host, then + * convert the delay to nanoseconds to achieve an accurate delay. Note + * that __delay() uses delay_tsc whenever the hardware has TSC, thus + * always for VMX enabled hardware. + */ + if (vcpu->arch.tsc_scaling_ratio == kvm_default_tsc_scaling_ratio) { + __delay(min(guest_cycles, + nsec_to_cycles(vcpu, timer_advance_ns))); + } else { + u64 delay_ns = guest_cycles * 1000000ULL; + do_div(delay_ns, vcpu->arch.virtual_tsc_khz); + ndelay(min_t(u32, delay_ns, timer_advance_ns)); + } +} + void wait_lapic_expire(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; + u32 timer_advance_ns = apic->lapic_timer.timer_advance_ns; u64 guest_tsc, tsc_deadline, ns; - if (!lapic_in_kernel(vcpu)) - return; - if (apic->lapic_timer.expired_tscdeadline == 0) return; @@ -1499,33 +1518,37 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu) guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); trace_kvm_wait_lapic_expire(vcpu->vcpu_id, guest_tsc - tsc_deadline); - /* __delay is delay_tsc whenever the hardware has TSC, thus always. */ if (guest_tsc < tsc_deadline) - __delay(min(tsc_deadline - guest_tsc, - nsec_to_cycles(vcpu, lapic_timer_advance_ns))); + __wait_lapic_expire(vcpu, tsc_deadline - guest_tsc); - if (!lapic_timer_advance_adjust_done) { + if (!apic->lapic_timer.timer_advance_adjust_done) { /* too early */ if (guest_tsc < tsc_deadline) { ns = (tsc_deadline - guest_tsc) * 1000000ULL; do_div(ns, vcpu->arch.virtual_tsc_khz); - lapic_timer_advance_ns -= min((unsigned int)ns, - lapic_timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP); + timer_advance_ns -= min((u32)ns, + timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP); } else { /* too late */ ns = (guest_tsc - tsc_deadline) * 1000000ULL; do_div(ns, vcpu->arch.virtual_tsc_khz); - lapic_timer_advance_ns += min((unsigned int)ns, - lapic_timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP); + timer_advance_ns += min((u32)ns, + timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP); } if (abs(guest_tsc - tsc_deadline) < LAPIC_TIMER_ADVANCE_ADJUST_DONE) - lapic_timer_advance_adjust_done = true; + apic->lapic_timer.timer_advance_adjust_done = true; + if (unlikely(timer_advance_ns > 5000)) { + timer_advance_ns = 0; + apic->lapic_timer.timer_advance_adjust_done = true; + } + apic->lapic_timer.timer_advance_ns = timer_advance_ns; } } static void start_sw_tscdeadline(struct kvm_lapic *apic) { - u64 guest_tsc, tscdeadline = apic->lapic_timer.tscdeadline; + struct kvm_timer *ktimer = &apic->lapic_timer; + u64 guest_tsc, tscdeadline = ktimer->tscdeadline; u64 ns = 0; ktime_t expire; struct kvm_vcpu *vcpu = apic->vcpu; @@ -1540,13 +1563,15 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic) now = ktime_get(); guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); - if (likely(tscdeadline > guest_tsc)) { - ns = (tscdeadline - guest_tsc) * 1000000ULL; - do_div(ns, this_tsc_khz); + + ns = (tscdeadline - guest_tsc) * 1000000ULL; + do_div(ns, this_tsc_khz); + + if (likely(tscdeadline > guest_tsc) && + likely(ns > apic->lapic_timer.timer_advance_ns)) { expire = ktime_add_ns(now, ns); - expire = ktime_sub_ns(expire, lapic_timer_advance_ns); - hrtimer_start(&apic->lapic_timer.timer, - expire, HRTIMER_MODE_ABS_PINNED); + expire = ktime_sub_ns(expire, ktimer->timer_advance_ns); + hrtimer_start(&ktimer->timer, expire, HRTIMER_MODE_ABS_PINNED); } else apic_timer_expired(apic); @@ -2253,7 +2278,7 @@ static enum hrtimer_restart apic_timer_fn(struct hrtimer *data) return HRTIMER_NORESTART; } -int kvm_create_lapic(struct kvm_vcpu *vcpu) +int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns) { struct kvm_lapic *apic; @@ -2277,6 +2302,14 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu) hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); apic->lapic_timer.timer.function = apic_timer_fn; + if (timer_advance_ns == -1) { + apic->lapic_timer.timer_advance_ns = 1000; + apic->lapic_timer.timer_advance_adjust_done = false; + } else { + apic->lapic_timer.timer_advance_ns = timer_advance_ns; + apic->lapic_timer.timer_advance_adjust_done = true; + } + /* * APIC is created enabled. This will prevent kvm_lapic_set_base from diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index ff6ef9c3d760..d6d049ba3045 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -31,8 +31,10 @@ struct kvm_timer { u32 timer_mode_mask; u64 tscdeadline; u64 expired_tscdeadline; + u32 timer_advance_ns; atomic_t pending; /* accumulated triggered timers */ bool hv_timer_in_use; + bool timer_advance_adjust_done; }; struct kvm_lapic { @@ -62,7 +64,7 @@ struct kvm_lapic { struct dest_map; -int kvm_create_lapic(struct kvm_vcpu *vcpu); +int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns); void kvm_free_lapic(struct kvm_vcpu *vcpu); int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 7837ab001d80..d9c7b45d231f 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -182,7 +182,7 @@ struct kvm_shadow_walk_iterator { static const union kvm_mmu_page_role mmu_base_role_mask = { .cr0_wp = 1, - .cr4_pae = 1, + .gpte_is_8_bytes = 1, .nxe = 1, .smep_andnot_wp = 1, .smap_andnot_wp = 1, @@ -2007,7 +2007,7 @@ static int is_empty_shadow_page(u64 *spt) * aggregate version in order to make the slab shrinker * faster */ -static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, int nr) +static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, unsigned long nr) { kvm->arch.n_used_mmu_pages += nr; percpu_counter_add(&kvm_total_used_mmu_pages, nr); @@ -2205,6 +2205,7 @@ static bool kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, static void kvm_mmu_commit_zap_page(struct kvm *kvm, struct list_head *invalid_list); + #define for_each_valid_sp(_kvm, _sp, _gfn) \ hlist_for_each_entry(_sp, \ &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)], hash_link) \ @@ -2215,12 +2216,17 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm, for_each_valid_sp(_kvm, _sp, _gfn) \ if ((_sp)->gfn != (_gfn) || (_sp)->role.direct) {} else +static inline bool is_ept_sp(struct kvm_mmu_page *sp) +{ + return sp->role.cr0_wp && sp->role.smap_andnot_wp; +} + /* @sp->gfn should be write-protected at the call site */ static bool __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, struct list_head *invalid_list) { - if (sp->role.cr4_pae != !!is_pae(vcpu) - || vcpu->arch.mmu->sync_page(vcpu, sp) == 0) { + if ((!is_ept_sp(sp) && sp->role.gpte_is_8_bytes != !!is_pae(vcpu)) || + vcpu->arch.mmu->sync_page(vcpu, sp) == 0) { kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list); return false; } @@ -2232,7 +2238,7 @@ static bool kvm_mmu_remote_flush_or_zap(struct kvm *kvm, struct list_head *invalid_list, bool remote_flush) { - if (!remote_flush && !list_empty(invalid_list)) + if (!remote_flush && list_empty(invalid_list)) return false; if (!list_empty(invalid_list)) @@ -2423,7 +2429,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, role.level = level; role.direct = direct; if (role.direct) - role.cr4_pae = 0; + role.gpte_is_8_bytes = true; role.access = access; if (!vcpu->arch.mmu->direct_map && vcpu->arch.mmu->root_level <= PT32_ROOT_LEVEL) { @@ -2757,7 +2763,7 @@ static bool prepare_zap_oldest_mmu_page(struct kvm *kvm, * Changing the number of mmu pages allocated to the vm * Note: if goal_nr_mmu_pages is too small, you will get dead lock */ -void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages) +void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long goal_nr_mmu_pages) { LIST_HEAD(invalid_list); @@ -4775,6 +4781,7 @@ static union kvm_mmu_extended_role kvm_calc_mmu_role_ext(struct kvm_vcpu *vcpu) union kvm_mmu_extended_role ext = {0}; ext.cr0_pg = !!is_paging(vcpu); + ext.cr4_pae = !!is_pae(vcpu); ext.cr4_smep = !!kvm_read_cr4_bits(vcpu, X86_CR4_SMEP); ext.cr4_smap = !!kvm_read_cr4_bits(vcpu, X86_CR4_SMAP); ext.cr4_pse = !!is_pse(vcpu); @@ -4794,7 +4801,6 @@ static union kvm_mmu_role kvm_calc_mmu_role_common(struct kvm_vcpu *vcpu, role.base.access = ACC_ALL; role.base.nxe = !!is_nx(vcpu); - role.base.cr4_pae = !!is_pae(vcpu); role.base.cr0_wp = is_write_protection(vcpu); role.base.smm = is_smm(vcpu); role.base.guest_mode = is_guest_mode(vcpu); @@ -4815,6 +4821,7 @@ kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only) role.base.ad_disabled = (shadow_accessed_mask == 0); role.base.level = kvm_x86_ops->get_tdp_level(vcpu); role.base.direct = true; + role.base.gpte_is_8_bytes = true; return role; } @@ -4879,6 +4886,7 @@ kvm_calc_shadow_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only) role.base.smap_andnot_wp = role.ext.cr4_smap && !is_write_protection(vcpu); role.base.direct = !is_paging(vcpu); + role.base.gpte_is_8_bytes = !!is_pae(vcpu); if (!is_long_mode(vcpu)) role.base.level = PT32E_ROOT_LEVEL; @@ -4918,18 +4926,26 @@ static union kvm_mmu_role kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty, bool execonly) { - union kvm_mmu_role role; + union kvm_mmu_role role = {0}; - /* Base role is inherited from root_mmu */ - role.base.word = vcpu->arch.root_mmu.mmu_role.base.word; - role.ext = kvm_calc_mmu_role_ext(vcpu); + /* SMM flag is inherited from root_mmu */ + role.base.smm = vcpu->arch.root_mmu.mmu_role.base.smm; role.base.level = PT64_ROOT_4LEVEL; + role.base.gpte_is_8_bytes = true; role.base.direct = false; role.base.ad_disabled = !accessed_dirty; role.base.guest_mode = true; role.base.access = ACC_ALL; + /* + * WP=1 and NOT_WP=1 is an impossible combination, use WP and the + * SMAP variation to denote shadow EPT entries. + */ + role.base.cr0_wp = true; + role.base.smap_andnot_wp = true; + + role.ext = kvm_calc_mmu_role_ext(vcpu); role.ext.execonly = execonly; return role; @@ -5179,7 +5195,7 @@ static bool detect_write_misaligned(struct kvm_mmu_page *sp, gpa_t gpa, gpa, bytes, sp->role.word); offset = offset_in_page(gpa); - pte_size = sp->role.cr4_pae ? 8 : 4; + pte_size = sp->role.gpte_is_8_bytes ? 8 : 4; /* * Sometimes, the OS only writes the last one bytes to update status @@ -5203,7 +5219,7 @@ static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte) page_offset = offset_in_page(gpa); level = sp->role.level; *nspte = 1; - if (!sp->role.cr4_pae) { + if (!sp->role.gpte_is_8_bytes) { page_offset <<= 1; /* 32->64 */ /* * A 32-bit pde maps 4MB while the shadow pdes map @@ -5393,10 +5409,12 @@ emulate: * This can happen if a guest gets a page-fault on data access but the HW * table walker is not able to read the instruction page (e.g instruction * page is not present in memory). In those cases we simply restart the - * guest. + * guest, with the exception of AMD Erratum 1096 which is unrecoverable. */ - if (unlikely(insn && !insn_len)) - return 1; + if (unlikely(insn && !insn_len)) { + if (!kvm_x86_ops->need_emulation_on_page_fault(vcpu)) + return 1; + } er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len); @@ -5509,7 +5527,9 @@ slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { if (flush && lock_flush_tlb) { - kvm_flush_remote_tlbs(kvm); + kvm_flush_remote_tlbs_with_address(kvm, + start_gfn, + iterator.gfn - start_gfn + 1); flush = false; } cond_resched_lock(&kvm->mmu_lock); @@ -5517,7 +5537,8 @@ slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, } if (flush && lock_flush_tlb) { - kvm_flush_remote_tlbs(kvm); + kvm_flush_remote_tlbs_with_address(kvm, start_gfn, + end_gfn - start_gfn + 1); flush = false; } @@ -6011,10 +6032,10 @@ out: /* * Calculate mmu pages needed for kvm. */ -unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm) +unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm) { - unsigned int nr_mmu_pages; - unsigned int nr_pages = 0; + unsigned long nr_mmu_pages; + unsigned long nr_pages = 0; struct kvm_memslots *slots; struct kvm_memory_slot *memslot; int i; @@ -6027,8 +6048,7 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm) } nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000; - nr_mmu_pages = max(nr_mmu_pages, - (unsigned int) KVM_MIN_ALLOC_MMU_PAGES); + nr_mmu_pages = max(nr_mmu_pages, KVM_MIN_ALLOC_MMU_PAGES); return nr_mmu_pages; } diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index bbdc60f2fae8..54c2a377795b 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -64,7 +64,7 @@ bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu); int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, u64 fault_address, char *insn, int insn_len); -static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm) +static inline unsigned long kvm_mmu_available_pages(struct kvm *kvm) { if (kvm->arch.n_max_mmu_pages > kvm->arch.n_used_mmu_pages) return kvm->arch.n_max_mmu_pages - diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index 9f6c855a0043..dd30dccd2ad5 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -29,10 +29,10 @@ \ role.word = __entry->role; \ \ - trace_seq_printf(p, "sp gfn %llx l%u%s q%u%s %s%s" \ + trace_seq_printf(p, "sp gfn %llx l%u %u-byte q%u%s %s%s" \ " %snxe %sad root %u %s%c", \ __entry->gfn, role.level, \ - role.cr4_pae ? " pae" : "", \ + role.gpte_is_8_bytes ? 8 : 4, \ role.quadrant, \ role.direct ? " direct" : "", \ access_str[role.access], \ diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 58ead7db71a3..e39741997893 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -281,9 +281,13 @@ static int kvm_pmu_rdpmc_vmware(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) { bool fast_mode = idx & (1u << 31); + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); struct kvm_pmc *pmc; u64 ctr_val; + if (!pmu->version) + return 1; + if (is_vmware_backdoor_pmc(idx)) return kvm_pmu_rdpmc_vmware(vcpu, idx, data); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index b5b128a0a051..406b558abfef 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -262,6 +262,7 @@ struct amd_svm_iommu_ir { }; #define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF) +#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31 #define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31) #define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK (0xFFULL) @@ -2692,6 +2693,7 @@ static int npf_interception(struct vcpu_svm *svm) static int db_interception(struct vcpu_svm *svm) { struct kvm_run *kvm_run = svm->vcpu.run; + struct kvm_vcpu *vcpu = &svm->vcpu; if (!(svm->vcpu.guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) && @@ -2702,6 +2704,8 @@ static int db_interception(struct vcpu_svm *svm) if (svm->nmi_singlestep) { disable_nmi_singlestep(svm); + /* Make sure we check for pending NMIs upon entry */ + kvm_make_request(KVM_REQ_EVENT, vcpu); } if (svm->vcpu.guest_debug & @@ -4517,14 +4521,25 @@ static int avic_incomplete_ipi_interception(struct vcpu_svm *svm) kvm_lapic_reg_write(apic, APIC_ICR, icrl); break; case AVIC_IPI_FAILURE_TARGET_NOT_RUNNING: { + int i; + struct kvm_vcpu *vcpu; + struct kvm *kvm = svm->vcpu.kvm; struct kvm_lapic *apic = svm->vcpu.arch.apic; /* - * Update ICR high and low, then emulate sending IPI, - * which is handled when writing APIC_ICR. + * At this point, we expect that the AVIC HW has already + * set the appropriate IRR bits on the valid target + * vcpus. So, we just need to kick the appropriate vcpu. */ - kvm_lapic_reg_write(apic, APIC_ICR2, icrh); - kvm_lapic_reg_write(apic, APIC_ICR, icrl); + kvm_for_each_vcpu(i, vcpu, kvm) { + bool m = kvm_apic_match_dest(vcpu, apic, + icrl & KVM_APIC_SHORT_MASK, + GET_APIC_DEST_FIELD(icrh), + icrl & KVM_APIC_DEST_MASK); + + if (m && !avic_vcpu_is_running(vcpu)) + kvm_vcpu_wake_up(vcpu); + } break; } case AVIC_IPI_FAILURE_INVALID_TARGET: @@ -4596,7 +4611,7 @@ static void avic_invalidate_logical_id_entry(struct kvm_vcpu *vcpu) u32 *entry = avic_get_logical_id_entry(vcpu, svm->ldr_reg, flat); if (entry) - WRITE_ONCE(*entry, (u32) ~AVIC_LOGICAL_ID_ENTRY_VALID_MASK); + clear_bit(AVIC_LOGICAL_ID_ENTRY_VALID_BIT, (unsigned long *)entry); } static int avic_handle_ldr_update(struct kvm_vcpu *vcpu) @@ -5621,6 +5636,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) svm->vmcb->save.cr2 = vcpu->arch.cr2; clgi(); + kvm_load_guest_xcr0(vcpu); /* * If this vCPU has touched SPEC_CTRL, restore the guest's value if @@ -5766,6 +5782,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) kvm_before_interrupt(&svm->vcpu); + kvm_put_guest_xcr0(vcpu); stgi(); /* Any pending NMI will happen here */ @@ -6215,32 +6232,24 @@ static int svm_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate) return 0; } -static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase) +static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) { struct vcpu_svm *svm = to_svm(vcpu); struct vmcb *nested_vmcb; struct page *page; - struct { - u64 guest; - u64 vmcb; - } svm_state_save; - int ret; + u64 guest; + u64 vmcb; - ret = kvm_vcpu_read_guest(vcpu, smbase + 0xfed8, &svm_state_save, - sizeof(svm_state_save)); - if (ret) - return ret; + guest = GET_SMSTATE(u64, smstate, 0x7ed8); + vmcb = GET_SMSTATE(u64, smstate, 0x7ee0); - if (svm_state_save.guest) { - vcpu->arch.hflags &= ~HF_SMM_MASK; - nested_vmcb = nested_svm_map(svm, svm_state_save.vmcb, &page); - if (nested_vmcb) - enter_svm_guest_mode(svm, svm_state_save.vmcb, nested_vmcb, page); - else - ret = 1; - vcpu->arch.hflags |= HF_SMM_MASK; + if (guest) { + nested_vmcb = nested_svm_map(svm, vmcb, &page); + if (!nested_vmcb) + return 1; + enter_svm_guest_mode(svm, vmcb, nested_vmcb, page); } - return ret; + return 0; } static int enable_smi_window(struct kvm_vcpu *vcpu) @@ -6422,11 +6431,11 @@ e_free: return ret; } -static int get_num_contig_pages(int idx, struct page **inpages, - unsigned long npages) +static unsigned long get_num_contig_pages(unsigned long idx, + struct page **inpages, unsigned long npages) { unsigned long paddr, next_paddr; - int i = idx + 1, pages = 1; + unsigned long i = idx + 1, pages = 1; /* find the number of contiguous pages starting from idx */ paddr = __sme_page_pa(inpages[idx]); @@ -6445,12 +6454,12 @@ static int get_num_contig_pages(int idx, struct page **inpages, static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) { - unsigned long vaddr, vaddr_end, next_vaddr, npages, size; + unsigned long vaddr, vaddr_end, next_vaddr, npages, pages, size, i; struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; struct kvm_sev_launch_update_data params; struct sev_data_launch_update_data *data; struct page **inpages; - int i, ret, pages; + int ret; if (!sev_guest(kvm)) return -ENOTTY; @@ -6799,7 +6808,8 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) struct page **src_p, **dst_p; struct kvm_sev_dbg debug; unsigned long n; - int ret, size; + unsigned int size; + int ret; if (!sev_guest(kvm)) return -ENOTTY; @@ -6807,6 +6817,11 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) if (copy_from_user(&debug, (void __user *)(uintptr_t)argp->data, sizeof(debug))) return -EFAULT; + if (!debug.len || debug.src_uaddr + debug.len < debug.src_uaddr) + return -EINVAL; + if (!debug.dst_uaddr) + return -EINVAL; + vaddr = debug.src_uaddr; size = debug.len; vaddr_end = vaddr + size; @@ -6857,8 +6872,8 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) dst_vaddr, len, &argp->error); - sev_unpin_memory(kvm, src_p, 1); - sev_unpin_memory(kvm, dst_p, 1); + sev_unpin_memory(kvm, src_p, n); + sev_unpin_memory(kvm, dst_p, n); if (ret) goto err; @@ -7098,6 +7113,36 @@ static int nested_enable_evmcs(struct kvm_vcpu *vcpu, return -ENODEV; } +static bool svm_need_emulation_on_page_fault(struct kvm_vcpu *vcpu) +{ + bool is_user, smap; + + is_user = svm_get_cpl(vcpu) == 3; + smap = !kvm_read_cr4_bits(vcpu, X86_CR4_SMAP); + + /* + * Detect and workaround Errata 1096 Fam_17h_00_0Fh + * + * In non SEV guest, hypervisor will be able to read the guest + * memory to decode the instruction pointer when insn_len is zero + * so we return true to indicate that decoding is possible. + * + * But in the SEV guest, the guest memory is encrypted with the + * guest specific key and hypervisor will not be able to decode the + * instruction pointer so we will not able to workaround it. Lets + * print the error and request to kill the guest. + */ + if (is_user && smap) { + if (!sev_guest(vcpu->kvm)) + return true; + + pr_err_ratelimited("KVM: Guest triggered AMD Erratum 1096\n"); + kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + } + + return false; +} + static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .cpu_has_kvm_support = has_svm, .disabled_by_bios = is_disabled, @@ -7231,6 +7276,8 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .nested_enable_evmcs = nested_enable_evmcs, .nested_get_evmcs_version = nested_get_evmcs_version, + + .need_emulation_on_page_fault = svm_need_emulation_on_page_fault, }; static int __init svm_init(void) diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 6432d08c7de7..4d47a2631d1f 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -438,13 +438,13 @@ TRACE_EVENT(kvm_apic_ipi, ); TRACE_EVENT(kvm_apic_accept_irq, - TP_PROTO(__u32 apicid, __u16 dm, __u8 tm, __u8 vec), + TP_PROTO(__u32 apicid, __u16 dm, __u16 tm, __u8 vec), TP_ARGS(apicid, dm, tm, vec), TP_STRUCT__entry( __field( __u32, apicid ) __field( __u16, dm ) - __field( __u8, tm ) + __field( __u16, tm ) __field( __u8, vec ) ), diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index f24a2c225070..0c601d079cd2 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -500,6 +500,17 @@ static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1, } } +static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) { + int msr; + + for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { + unsigned word = msr / BITS_PER_LONG; + + msr_bitmap[word] = ~0; + msr_bitmap[word + (0x800 / sizeof(long))] = ~0; + } +} + /* * Merge L0's and L1's MSR bitmap, return false to indicate that * we do not use the hardware. @@ -541,39 +552,44 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, return false; msr_bitmap_l1 = (unsigned long *)kmap(page); - if (nested_cpu_has_apic_reg_virt(vmcs12)) { - /* - * L0 need not intercept reads for MSRs between 0x800 and 0x8ff, it - * just lets the processor take the value from the virtual-APIC page; - * take those 256 bits directly from the L1 bitmap. - */ - for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { - unsigned word = msr / BITS_PER_LONG; - msr_bitmap_l0[word] = msr_bitmap_l1[word]; - msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0; - } - } else { - for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { - unsigned word = msr / BITS_PER_LONG; - msr_bitmap_l0[word] = ~0; - msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0; - } - } - nested_vmx_disable_intercept_for_msr( - msr_bitmap_l1, msr_bitmap_l0, - X2APIC_MSR(APIC_TASKPRI), - MSR_TYPE_W); + /* + * To keep the control flow simple, pay eight 8-byte writes (sixteen + * 4-byte writes on 32-bit systems) up front to enable intercepts for + * the x2APIC MSR range and selectively disable them below. + */ + enable_x2apic_msr_intercepts(msr_bitmap_l0); + + if (nested_cpu_has_virt_x2apic_mode(vmcs12)) { + if (nested_cpu_has_apic_reg_virt(vmcs12)) { + /* + * L0 need not intercept reads for MSRs between 0x800 + * and 0x8ff, it just lets the processor take the value + * from the virtual-APIC page; take those 256 bits + * directly from the L1 bitmap. + */ + for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) { + unsigned word = msr / BITS_PER_LONG; + + msr_bitmap_l0[word] = msr_bitmap_l1[word]; + } + } - if (nested_cpu_has_vid(vmcs12)) { - nested_vmx_disable_intercept_for_msr( - msr_bitmap_l1, msr_bitmap_l0, - X2APIC_MSR(APIC_EOI), - MSR_TYPE_W); nested_vmx_disable_intercept_for_msr( msr_bitmap_l1, msr_bitmap_l0, - X2APIC_MSR(APIC_SELF_IPI), - MSR_TYPE_W); + X2APIC_MSR(APIC_TASKPRI), + MSR_TYPE_R | MSR_TYPE_W); + + if (nested_cpu_has_vid(vmcs12)) { + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + X2APIC_MSR(APIC_EOI), + MSR_TYPE_W); + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, + X2APIC_MSR(APIC_SELF_IPI), + MSR_TYPE_W); + } } if (spec_ctrl) @@ -2585,6 +2601,11 @@ static int nested_check_host_control_regs(struct kvm_vcpu *vcpu, !nested_host_cr4_valid(vcpu, vmcs12->host_cr4) || !nested_cr3_valid(vcpu, vmcs12->host_cr3)) return -EINVAL; + + if (is_noncanonical_address(vmcs12->host_ia32_sysenter_esp, vcpu) || + is_noncanonical_address(vmcs12->host_ia32_sysenter_eip, vcpu)) + return -EINVAL; + /* * If the load IA32_EFER VM-exit control is 1, bits reserved in the * IA32_EFER MSR must be 0 in the field for that register. In addition, @@ -2852,20 +2873,27 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) /* * If translation failed, VM entry will fail because * prepare_vmcs02 set VIRTUAL_APIC_PAGE_ADDR to -1ull. - * Failing the vm entry is _not_ what the processor - * does but it's basically the only possibility we - * have. We could still enter the guest if CR8 load - * exits are enabled, CR8 store exits are enabled, and - * virtualize APIC access is disabled; in this case - * the processor would never use the TPR shadow and we - * could simply clear the bit from the execution - * control. But such a configuration is useless, so - * let's keep the code simple. */ if (!is_error_page(page)) { vmx->nested.virtual_apic_page = page; hpa = page_to_phys(vmx->nested.virtual_apic_page); vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, hpa); + } else if (nested_cpu_has(vmcs12, CPU_BASED_CR8_LOAD_EXITING) && + nested_cpu_has(vmcs12, CPU_BASED_CR8_STORE_EXITING) && + !nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { + /* + * The processor will never use the TPR shadow, simply + * clear the bit from the execution control. Such a + * configuration is useless, but it happens in tests. + * For any other configuration, failing the vm entry is + * _not_ what the processor does but it's basically the + * only possibility we have. + */ + vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL, + CPU_BASED_TPR_SHADOW); + } else { + printk("bad virtual-APIC page address\n"); + dump_vmcs(); } } @@ -3768,8 +3796,18 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) vmx_set_cr4(vcpu, vmcs_readl(CR4_READ_SHADOW)); nested_ept_uninit_mmu_context(vcpu); - vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); - __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); + + /* + * This is only valid if EPT is in use, otherwise the vmcs01 GUEST_CR3 + * points to shadow pages! Fortunately we only get here after a WARN_ON + * if EPT is disabled, so a VMabort is perfectly fine. + */ + if (enable_ept) { + vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); + __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); + } else { + nested_vmx_abort(vcpu, VMX_ABORT_VMCS_CORRUPTED); + } /* * Use ept_save_pdptrs(vcpu) to load the MMU's cached PDPTRs @@ -5385,7 +5423,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, return ret; /* Empty 'VMXON' state is permitted */ - if (kvm_state->size < sizeof(kvm_state) + sizeof(*vmcs12)) + if (kvm_state->size < sizeof(*kvm_state) + sizeof(*vmcs12)) return 0; if (kvm_state->vmx.vmcs_pa != -1ull) { @@ -5429,7 +5467,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, vmcs12->vmcs_link_pointer != -1ull) { struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu); - if (kvm_state->size < sizeof(kvm_state) + 2 * sizeof(*vmcs12)) + if (kvm_state->size < sizeof(*kvm_state) + 2 * sizeof(*vmcs12)) return -EINVAL; if (copy_from_user(shadow_vmcs12, @@ -5717,6 +5755,14 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)) { int i; + /* + * Without EPT it is not possible to restore L1's CR3 and PDPTR on + * VMfail, because they are not available in vmcs01. Just always + * use hardware checks. + */ + if (!enable_ept) + nested_early_check = 1; + if (!cpu_has_vmx_shadow_vmcs()) enable_shadow_vmcs = 0; if (enable_shadow_vmcs) { diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 7b272738c576..d4cb1945b2e3 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -3,6 +3,7 @@ #include <asm/asm.h> #include <asm/bitsperlong.h> #include <asm/kvm_vcpu_regs.h> +#include <asm/nospec-branch.h> #define WORD_SIZE (BITS_PER_LONG / 8) @@ -77,6 +78,17 @@ ENDPROC(vmx_vmenter) * referred to by VMCS.HOST_RIP. */ ENTRY(vmx_vmexit) +#ifdef CONFIG_RETPOLINE + ALTERNATIVE "jmp .Lvmexit_skip_rsb", "", X86_FEATURE_RETPOLINE + /* Preserve guest's RAX, it's used to stuff the RSB. */ + push %_ASM_AX + + /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ + FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE + + pop %_ASM_AX +.Lvmexit_skip_rsb: +#endif ret ENDPROC(vmx_vmexit) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index c73375e01ab8..0c955bb286ff 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1683,12 +1683,6 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = to_vmx(vcpu)->spec_ctrl; break; - case MSR_IA32_ARCH_CAPABILITIES: - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES)) - return 1; - msr_info->data = to_vmx(vcpu)->arch_capabilities; - break; case MSR_IA32_SYSENTER_CS: msr_info->data = vmcs_read32(GUEST_SYSENTER_CS); break; @@ -1895,11 +1889,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD, MSR_TYPE_W); break; - case MSR_IA32_ARCH_CAPABILITIES: - if (!msr_info->host_initiated) - return 1; - vmx->arch_capabilities = data; - break; case MSR_IA32_CR_PAT: if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data)) @@ -4088,8 +4077,6 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx) ++vmx->nmsrs; } - vmx->arch_capabilities = kvm_get_arch_capabilities(); - vm_exit_controls_init(vmx, vmx_vmexit_ctrl()); /* 22.2.1, 20.8.1 */ @@ -5616,7 +5603,7 @@ static void vmx_dump_dtsel(char *name, uint32_t limit) vmcs_readl(limit + GUEST_GDTR_BASE - GUEST_GDTR_LIMIT)); } -static void dump_vmcs(void) +void dump_vmcs(void) { u32 vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS); u32 vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS); @@ -6423,6 +6410,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) vmx_set_interrupt_shadow(vcpu, 0); + kvm_load_guest_xcr0(vcpu); + if (static_cpu_has(X86_FEATURE_PKU) && kvm_read_cr4_bits(vcpu, X86_CR4_PKE) && vcpu->arch.pkru != vmx->host_pkru) @@ -6473,9 +6462,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0); - /* Eliminate branch target predictions from guest mode */ - vmexit_fill_RSB(); - /* All fields are clean at this point */ if (static_branch_unlikely(&enable_evmcs)) current_evmcs->hv_clean_fields |= @@ -6519,6 +6505,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) __write_pkru(vmx->host_pkru); } + kvm_put_guest_xcr0(vcpu); + vmx->nested.nested_run_pending = 0; vmx->idt_vectoring_info = 0; @@ -6865,6 +6853,30 @@ static void nested_vmx_entry_exit_ctls_update(struct kvm_vcpu *vcpu) } } +static bool guest_cpuid_has_pmu(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *entry; + union cpuid10_eax eax; + + entry = kvm_find_cpuid_entry(vcpu, 0xa, 0); + if (!entry) + return false; + + eax.full = entry->eax; + return (eax.split.version_id > 0); +} + +static void nested_vmx_procbased_ctls_update(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + bool pmu_enabled = guest_cpuid_has_pmu(vcpu); + + if (pmu_enabled) + vmx->nested.msrs.procbased_ctls_high |= CPU_BASED_RDPMC_EXITING; + else + vmx->nested.msrs.procbased_ctls_high &= ~CPU_BASED_RDPMC_EXITING; +} + static void update_intel_pt_cfg(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -6953,6 +6965,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) if (nested_vmx_allowed(vcpu)) { nested_vmx_cr_fixed1_bits_update(vcpu); nested_vmx_entry_exit_ctls_update(vcpu); + nested_vmx_procbased_ctls_update(vcpu); } if (boot_cpu_has(X86_FEATURE_INTEL_PT) && @@ -7016,6 +7029,7 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc) { struct vcpu_vmx *vmx; u64 tscl, guest_tscl, delta_tsc, lapic_timer_advance_cycles; + struct kvm_timer *ktimer = &vcpu->arch.apic->lapic_timer; if (kvm_mwait_in_guest(vcpu->kvm)) return -EOPNOTSUPP; @@ -7024,7 +7038,8 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc) tscl = rdtsc(); guest_tscl = kvm_read_l1_tsc(vcpu, tscl); delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl; - lapic_timer_advance_cycles = nsec_to_cycles(vcpu, lapic_timer_advance_ns); + lapic_timer_advance_cycles = nsec_to_cycles(vcpu, + ktimer->timer_advance_ns); if (delta_tsc > lapic_timer_advance_cycles) delta_tsc -= lapic_timer_advance_cycles; @@ -7382,7 +7397,7 @@ static int vmx_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate) return 0; } -static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase) +static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) { struct vcpu_vmx *vmx = to_vmx(vcpu); int ret; @@ -7393,9 +7408,7 @@ static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase) } if (vmx->nested.smm.guest_mode) { - vcpu->arch.hflags &= ~HF_SMM_MASK; ret = nested_vmx_enter_non_root_mode(vcpu, false); - vcpu->arch.hflags |= HF_SMM_MASK; if (ret) return ret; @@ -7409,6 +7422,11 @@ static int enable_smi_window(struct kvm_vcpu *vcpu) return 0; } +static bool vmx_need_emulation_on_page_fault(struct kvm_vcpu *vcpu) +{ + return 0; +} + static __init int hardware_setup(void) { unsigned long host_bndcfgs; @@ -7711,6 +7729,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .set_nested_state = NULL, .get_vmcs12_pages = NULL, .nested_enable_evmcs = NULL, + .need_emulation_on_page_fault = vmx_need_emulation_on_page_fault, }; static void vmx_cleanup_l1d_flush(void) diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 1554cb45b393..f879529906b4 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -190,7 +190,6 @@ struct vcpu_vmx { u64 msr_guest_kernel_gs_base; #endif - u64 arch_capabilities; u64 spec_ctrl; u32 vm_entry_controls_shadow; @@ -518,4 +517,6 @@ static inline void decache_tsc_multiplier(struct vcpu_vmx *vmx) vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio); } +void dump_vmcs(void); + #endif /* __KVM_X86_VMX_H */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 65e4559eef2f..b5edc8e3ce1d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -136,10 +136,14 @@ EXPORT_SYMBOL_GPL(kvm_default_tsc_scaling_ratio); static u32 __read_mostly tsc_tolerance_ppm = 250; module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR); -/* lapic timer advance (tscdeadline mode only) in nanoseconds */ -unsigned int __read_mostly lapic_timer_advance_ns = 1000; +/* + * lapic timer advance (tscdeadline mode only) in nanoseconds. '-1' enables + * adaptive tuning starting from default advancment of 1000ns. '0' disables + * advancement entirely. Any other value is used as-is and disables adaptive + * tuning, i.e. allows priveleged userspace to set an exact advancement time. + */ +static int __read_mostly lapic_timer_advance_ns = -1; module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR); -EXPORT_SYMBOL_GPL(lapic_timer_advance_ns); static bool __read_mostly vector_hashing = true; module_param(vector_hashing, bool, S_IRUGO); @@ -800,7 +804,7 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw) } EXPORT_SYMBOL_GPL(kvm_lmsw); -static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) +void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) { if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) && !vcpu->guest_xcr0_loaded) { @@ -810,8 +814,9 @@ static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu) vcpu->guest_xcr0_loaded = 1; } } +EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0); -static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) +void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) { if (vcpu->guest_xcr0_loaded) { if (vcpu->arch.xcr0 != host_xcr0) @@ -819,6 +824,7 @@ static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu) vcpu->guest_xcr0_loaded = 0; } } +EXPORT_SYMBOL_GPL(kvm_put_guest_xcr0); static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { @@ -1125,7 +1131,7 @@ static u32 msrs_to_save[] = { #endif MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, - MSR_IA32_SPEC_CTRL, MSR_IA32_ARCH_CAPABILITIES, + MSR_IA32_SPEC_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, @@ -1158,6 +1164,7 @@ static u32 emulated_msrs[] = { MSR_IA32_TSC_ADJUST, MSR_IA32_TSCDEADLINE, + MSR_IA32_ARCH_CAPABILITIES, MSR_IA32_MISC_ENABLE, MSR_IA32_MCG_STATUS, MSR_IA32_MCG_CTL, @@ -2443,6 +2450,11 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (msr_info->host_initiated) vcpu->arch.microcode_version = data; break; + case MSR_IA32_ARCH_CAPABILITIES: + if (!msr_info->host_initiated) + return 1; + vcpu->arch.arch_capabilities = data; + break; case MSR_EFER: return set_efer(vcpu, data); case MSR_K7_HWCR: @@ -2747,6 +2759,12 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_UCODE_REV: msr_info->data = vcpu->arch.microcode_version; break; + case MSR_IA32_ARCH_CAPABILITIES: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES)) + return 1; + msr_info->data = vcpu->arch.arch_capabilities; + break; case MSR_IA32_TSC: msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + vcpu->arch.tsc_offset; break; @@ -3081,7 +3099,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; case KVM_CAP_NESTED_STATE: r = kvm_x86_ops->get_nested_state ? - kvm_x86_ops->get_nested_state(NULL, 0, 0) : 0; + kvm_x86_ops->get_nested_state(NULL, NULL, 0) : 0; break; default: break; @@ -3516,7 +3534,7 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, memset(&events->reserved, 0, sizeof(events->reserved)); } -static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags); +static void kvm_smm_changed(struct kvm_vcpu *vcpu); static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) @@ -3576,12 +3594,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.apic->sipi_vector = events->sipi_vector; if (events->flags & KVM_VCPUEVENT_VALID_SMM) { - u32 hflags = vcpu->arch.hflags; - if (events->smi.smm) - hflags |= HF_SMM_MASK; - else - hflags &= ~HF_SMM_MASK; - kvm_set_hflags(vcpu, hflags); + if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) { + if (events->smi.smm) + vcpu->arch.hflags |= HF_SMM_MASK; + else + vcpu->arch.hflags &= ~HF_SMM_MASK; + kvm_smm_changed(vcpu); + } vcpu->arch.smi_pending = events->smi.pending; @@ -4258,7 +4277,7 @@ static int kvm_vm_ioctl_set_identity_map_addr(struct kvm *kvm, } static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, - u32 kvm_nr_mmu_pages) + unsigned long kvm_nr_mmu_pages) { if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES) return -EINVAL; @@ -4272,7 +4291,7 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, return 0; } -static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm) +static unsigned long kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm) { return kvm->arch.n_max_mmu_pages; } @@ -5946,12 +5965,18 @@ static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt) static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags) { - kvm_set_hflags(emul_to_vcpu(ctxt), emul_flags); + emul_to_vcpu(ctxt)->arch.hflags = emul_flags; } -static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt, u64 smbase) +static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt, + const char *smstate) { - return kvm_x86_ops->pre_leave_smm(emul_to_vcpu(ctxt), smbase); + return kvm_x86_ops->pre_leave_smm(emul_to_vcpu(ctxt), smstate); +} + +static void emulator_post_leave_smm(struct x86_emulate_ctxt *ctxt) +{ + kvm_smm_changed(emul_to_vcpu(ctxt)); } static const struct x86_emulate_ops emulate_ops = { @@ -5994,6 +6019,7 @@ static const struct x86_emulate_ops emulate_ops = { .get_hflags = emulator_get_hflags, .set_hflags = emulator_set_hflags, .pre_leave_smm = emulator_pre_leave_smm, + .post_leave_smm = emulator_post_leave_smm, }; static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) @@ -6235,16 +6261,6 @@ static void kvm_smm_changed(struct kvm_vcpu *vcpu) kvm_mmu_reset_context(vcpu); } -static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags) -{ - unsigned changed = vcpu->arch.hflags ^ emul_flags; - - vcpu->arch.hflags = emul_flags; - - if (changed & HF_SMM_MASK) - kvm_smm_changed(vcpu); -} - static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7, unsigned long *db) { @@ -6523,15 +6539,45 @@ int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, } EXPORT_SYMBOL_GPL(kvm_emulate_instruction_from_buffer); +static int complete_fast_pio_out_port_0x7e(struct kvm_vcpu *vcpu) +{ + vcpu->arch.pio.count = 0; + return 1; +} + +static int complete_fast_pio_out(struct kvm_vcpu *vcpu) +{ + vcpu->arch.pio.count = 0; + + if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.pio.linear_rip))) + return 1; + + return kvm_skip_emulated_instruction(vcpu); +} + static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port) { unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX); int ret = emulator_pio_out_emulated(&vcpu->arch.emulate_ctxt, size, port, &val, 1); - /* do not return to emulator after return from userspace */ - vcpu->arch.pio.count = 0; - return ret; + if (ret) + return ret; + + /* + * Workaround userspace that relies on old KVM behavior of %rip being + * incremented prior to exiting to userspace to handle "OUT 0x7e". + */ + if (port == 0x7e && + kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_OUT_7E_INC_RIP)) { + vcpu->arch.complete_userspace_io = + complete_fast_pio_out_port_0x7e; + kvm_skip_emulated_instruction(vcpu); + } else { + vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu); + vcpu->arch.complete_userspace_io = complete_fast_pio_out; + } + return 0; } static int complete_fast_pio_in(struct kvm_vcpu *vcpu) @@ -6541,6 +6587,11 @@ static int complete_fast_pio_in(struct kvm_vcpu *vcpu) /* We should only ever be called with arch.pio.count equal to 1 */ BUG_ON(vcpu->arch.pio.count != 1); + if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.pio.linear_rip))) { + vcpu->arch.pio.count = 0; + return 1; + } + /* For size less than 4 we merge, else we zero extend */ val = (vcpu->arch.pio.size < 4) ? kvm_register_read(vcpu, VCPU_REGS_RAX) : 0; @@ -6553,7 +6604,7 @@ static int complete_fast_pio_in(struct kvm_vcpu *vcpu) vcpu->arch.pio.port, &val, 1); kvm_register_write(vcpu, VCPU_REGS_RAX, val); - return 1; + return kvm_skip_emulated_instruction(vcpu); } static int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, @@ -6572,6 +6623,7 @@ static int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, return ret; } + vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu); vcpu->arch.complete_userspace_io = complete_fast_pio_in; return 0; @@ -6579,16 +6631,13 @@ static int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in) { - int ret = kvm_skip_emulated_instruction(vcpu); + int ret; - /* - * TODO: we might be squashing a KVM_GUESTDBG_SINGLESTEP-triggered - * KVM_EXIT_DEBUG here. - */ if (in) - return kvm_fast_pio_in(vcpu, size, port) && ret; + ret = kvm_fast_pio_in(vcpu, size, port); else - return kvm_fast_pio_out(vcpu, size, port) && ret; + ret = kvm_fast_pio_out(vcpu, size, port); + return ret && kvm_skip_emulated_instruction(vcpu); } EXPORT_SYMBOL_GPL(kvm_fast_pio); @@ -7413,9 +7462,9 @@ static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, char *buf) put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase); } +#ifdef CONFIG_X86_64 static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf) { -#ifdef CONFIG_X86_64 struct desc_ptr dt; struct kvm_segment seg; unsigned long val; @@ -7465,10 +7514,8 @@ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf) for (i = 0; i < 6; i++) enter_smm_save_seg_64(vcpu, buf, i); -#else - WARN_ON_ONCE(1); -#endif } +#endif static void enter_smm(struct kvm_vcpu *vcpu) { @@ -7479,9 +7526,11 @@ static void enter_smm(struct kvm_vcpu *vcpu) trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true); memset(buf, 0, 512); +#ifdef CONFIG_X86_64 if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) enter_smm_save_state_64(vcpu, buf); else +#endif enter_smm_save_state_32(vcpu, buf); /* @@ -7539,8 +7588,10 @@ static void enter_smm(struct kvm_vcpu *vcpu) kvm_set_segment(vcpu, &ds, VCPU_SREG_GS); kvm_set_segment(vcpu, &ds, VCPU_SREG_SS); +#ifdef CONFIG_X86_64 if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) kvm_x86_ops->set_efer(vcpu, 0); +#endif kvm_update_cpuid(vcpu); kvm_mmu_reset_context(vcpu); @@ -7837,15 +7888,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto cancel_injection; } - kvm_load_guest_xcr0(vcpu); - if (req_immediate_exit) { kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_x86_ops->request_immediate_exit(vcpu); } trace_kvm_entry(vcpu->vcpu_id); - if (lapic_timer_advance_ns) + if (lapic_in_kernel(vcpu) && + vcpu->arch.apic->lapic_timer.timer_advance_ns) wait_lapic_expire(vcpu); guest_enter_irqoff(); @@ -7891,8 +7941,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); - kvm_put_guest_xcr0(vcpu); - kvm_before_interrupt(vcpu); kvm_x86_ops->handle_external_intr(vcpu); kvm_after_interrupt(vcpu); @@ -8733,6 +8781,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { + vcpu->arch.arch_capabilities = kvm_get_arch_capabilities(); vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT; kvm_vcpu_mtrr_init(vcpu); vcpu_load(vcpu); @@ -9034,7 +9083,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) if (irqchip_in_kernel(vcpu->kvm)) { vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu); - r = kvm_create_lapic(vcpu); + r = kvm_create_lapic(vcpu, lapic_timer_advance_ns); if (r < 0) goto fail_mmu_destroy; } else @@ -9429,13 +9478,9 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - int nr_mmu_pages = 0; - if (!kvm->arch.n_requested_mmu_pages) - nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm); - - if (nr_mmu_pages) - kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages); + kvm_mmu_change_mmu_pages(kvm, + kvm_mmu_calculate_default_mmu_pages(kvm)); /* * Dirty logging tracks sptes in 4k granularity, meaning that large diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 28406aa1136d..534d3f28bb01 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -294,8 +294,6 @@ extern u64 kvm_supported_xcr0(void); extern unsigned int min_timer_period_us; -extern unsigned int lapic_timer_advance_ns; - extern bool enable_vmware_backdoor; extern struct static_key kvm_no_apic_vcpu; @@ -347,4 +345,6 @@ static inline void kvm_after_interrupt(struct kvm_vcpu *vcpu) __this_cpu_write(current_vcpu, NULL); } +void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu); +void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu); #endif diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild index 42b6cb3d16f7..3843198e03d4 100644 --- a/arch/xtensa/include/asm/Kbuild +++ b/arch/xtensa/include/asm/Kbuild @@ -15,6 +15,7 @@ generic-y += irq_work.h generic-y += kdebug.h generic-y += kmap_types.h generic-y += kprobes.h +generic-y += kvm_para.h generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h index f7dd895b2353..0c14018d1c26 100644 --- a/arch/xtensa/include/asm/processor.h +++ b/arch/xtensa/include/asm/processor.h @@ -187,15 +187,18 @@ struct thread_struct { /* Clearing a0 terminates the backtrace. */ #define start_thread(regs, new_pc, new_sp) \ - memset(regs, 0, sizeof(*regs)); \ - regs->pc = new_pc; \ - regs->ps = USER_PS_VALUE; \ - regs->areg[1] = new_sp; \ - regs->areg[0] = 0; \ - regs->wmask = 1; \ - regs->depc = 0; \ - regs->windowbase = 0; \ - regs->windowstart = 1; + do { \ + memset((regs), 0, sizeof(*(regs))); \ + (regs)->pc = (new_pc); \ + (regs)->ps = USER_PS_VALUE; \ + (regs)->areg[1] = (new_sp); \ + (regs)->areg[0] = 0; \ + (regs)->wmask = 1; \ + (regs)->depc = 0; \ + (regs)->windowbase = 0; \ + (regs)->windowstart = 1; \ + (regs)->syscall = NO_SYSCALL; \ + } while (0) /* Forward declaration */ struct task_struct; diff --git a/arch/xtensa/include/asm/syscall.h b/arch/xtensa/include/asm/syscall.h index a168bf81c7f4..91dc06d58060 100644 --- a/arch/xtensa/include/asm/syscall.h +++ b/arch/xtensa/include/asm/syscall.h @@ -59,45 +59,24 @@ static inline void syscall_set_return_value(struct task_struct *task, static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args) { static const unsigned int reg[] = XTENSA_SYSCALL_ARGUMENT_REGS; - unsigned int j; + unsigned int i; - if (n == 0) - return; - - WARN_ON_ONCE(i + n > SYSCALL_MAX_ARGS); - - for (j = 0; j < n; ++j) { - if (i + j < SYSCALL_MAX_ARGS) - args[j] = regs->areg[reg[i + j]]; - else - args[j] = 0; - } + for (i = 0; i < 6; ++i) + args[i] = regs->areg[reg[i]]; } static inline void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, const unsigned long *args) { static const unsigned int reg[] = XTENSA_SYSCALL_ARGUMENT_REGS; - unsigned int j; - - if (n == 0) - return; - - if (WARN_ON_ONCE(i + n > SYSCALL_MAX_ARGS)) { - if (i < SYSCALL_MAX_ARGS) - n = SYSCALL_MAX_ARGS - i; - else - return; - } + unsigned int i; - for (j = 0; j < n; ++j) - regs->areg[reg[i + j]] = args[j]; + for (i = 0; i < 6; ++i) + regs->areg[reg[i]] = args[i]; } asmlinkage long xtensa_rt_sigreturn(struct pt_regs*); diff --git a/arch/xtensa/include/uapi/asm/Kbuild b/arch/xtensa/include/uapi/asm/Kbuild index 8a7ad40be463..7417847dc438 100644 --- a/arch/xtensa/include/uapi/asm/Kbuild +++ b/arch/xtensa/include/uapi/asm/Kbuild @@ -1,2 +1 @@ generated-y += unistd_32.h -generic-y += kvm_para.h diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S index e50f5124dc6f..e54af8b7e0f8 100644 --- a/arch/xtensa/kernel/entry.S +++ b/arch/xtensa/kernel/entry.S @@ -1860,6 +1860,8 @@ ENTRY(system_call) l32i a7, a2, PT_SYSCALL 1: + s32i a7, a1, 4 + /* syscall = sys_call_table[syscall_nr] */ movi a4, sys_call_table @@ -1893,8 +1895,12 @@ ENTRY(system_call) retw 1: + l32i a4, a1, 4 + l32i a3, a2, PT_SYSCALL + s32i a4, a2, PT_SYSCALL mov a6, a2 call4 do_syscall_trace_leave + s32i a3, a2, PT_SYSCALL retw ENDPROC(system_call) diff --git a/arch/xtensa/kernel/stacktrace.c b/arch/xtensa/kernel/stacktrace.c index 174c11f13bba..b9f82510c650 100644 --- a/arch/xtensa/kernel/stacktrace.c +++ b/arch/xtensa/kernel/stacktrace.c @@ -253,10 +253,14 @@ static int return_address_cb(struct stackframe *frame, void *data) return 1; } +/* + * level == 0 is for the return address from the caller of this function, + * not from this function itself. + */ unsigned long return_address(unsigned level) { struct return_addr_data r = { - .skip = level + 1, + .skip = level, }; walk_stackframe(stack_pointer(NULL), return_address_cb, &r); return r.addr; diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index 6af49929de85..30084eaf8422 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -394,3 +394,7 @@ 421 common rt_sigtimedwait_time64 sys_rt_sigtimedwait 422 common futex_time64 sys_futex 423 common sched_rr_get_interval_time64 sys_sched_rr_get_interval +424 common pidfd_send_signal sys_pidfd_send_signal +425 common io_uring_setup sys_io_uring_setup +426 common io_uring_enter sys_io_uring_enter +427 common io_uring_register sys_io_uring_register diff --git a/arch/xtensa/mm/mmu.c b/arch/xtensa/mm/mmu.c index 2fb7d1172228..03678c4afc39 100644 --- a/arch/xtensa/mm/mmu.c +++ b/arch/xtensa/mm/mmu.c @@ -33,7 +33,7 @@ static void * __init init_pmd(unsigned long vaddr, unsigned long n_pages) pte = memblock_alloc_low(n_pages * sizeof(pte_t), PAGE_SIZE); if (!pte) - panic("%s: Failed to allocate %zu bytes align=%lx\n", + panic("%s: Failed to allocate %lu bytes align=%lx\n", __func__, n_pages * sizeof(pte_t), PAGE_SIZE); for (i = 0; i < n_pages; ++i) diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 4c592496a16a..5ba1e0d841b4 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -674,7 +674,7 @@ static bool bfq_symmetric_scenario(struct bfq_data *bfqd) * at least two nodes. */ return !(varied_queue_weights || multiple_classes_busy -#ifdef BFQ_GROUP_IOSCHED_ENABLED +#ifdef CONFIG_BFQ_GROUP_IOSCHED || bfqd->num_groups_with_pending_reqs > 0 #endif ); @@ -2822,7 +2822,7 @@ static void bfq_dispatch_remove(struct request_queue *q, struct request *rq) bfq_remove_request(q, rq); } -static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq) +static bool __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq) { /* * If this bfqq is shared between multiple processes, check @@ -2855,9 +2855,11 @@ static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq) /* * All in-service entities must have been properly deactivated * or requeued before executing the next function, which - * resets all in-service entites as no more in service. + * resets all in-service entities as no more in service. This + * may cause bfqq to be freed. If this happens, the next + * function returns true. */ - __bfq_bfqd_reset_in_service(bfqd); + return __bfq_bfqd_reset_in_service(bfqd); } /** @@ -3262,7 +3264,6 @@ void bfq_bfqq_expire(struct bfq_data *bfqd, bool slow; unsigned long delta = 0; struct bfq_entity *entity = &bfqq->entity; - int ref; /* * Check whether the process is slow (see bfq_bfqq_is_slow). @@ -3347,10 +3348,8 @@ void bfq_bfqq_expire(struct bfq_data *bfqd, * reason. */ __bfq_bfqq_recalc_budget(bfqd, bfqq, reason); - ref = bfqq->ref; - __bfq_bfqq_expire(bfqd, bfqq); - - if (ref == 1) /* bfqq is gone, no more actions on it */ + if (__bfq_bfqq_expire(bfqd, bfqq)) + /* bfqq is gone, no more actions on it */ return; bfqq->injected_service = 0; @@ -5397,7 +5396,7 @@ static unsigned int bfq_update_depths(struct bfq_data *bfqd, return min_shallow; } -static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index) +static void bfq_depth_updated(struct blk_mq_hw_ctx *hctx) { struct bfq_data *bfqd = hctx->queue->elevator->elevator_data; struct blk_mq_tags *tags = hctx->sched_tags; @@ -5405,6 +5404,11 @@ static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index) min_shallow = bfq_update_depths(bfqd, &tags->bitmap_tags); sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, min_shallow); +} + +static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index) +{ + bfq_depth_updated(hctx); return 0; } @@ -5827,6 +5831,7 @@ static struct elevator_type iosched_bfq_mq = { .requests_merged = bfq_requests_merged, .request_merged = bfq_request_merged, .has_work = bfq_has_work, + .depth_updated = bfq_depth_updated, .init_hctx = bfq_init_hctx, .init_sched = bfq_init_queue, .exit_sched = bfq_exit_queue, diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index 062e1c4787f4..86394e503ca9 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -995,7 +995,7 @@ bool __bfq_deactivate_entity(struct bfq_entity *entity, bool ins_into_idle_tree); bool next_queue_may_preempt(struct bfq_data *bfqd); struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd); -void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd); +bool __bfq_bfqd_reset_in_service(struct bfq_data *bfqd); void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq, bool ins_into_idle_tree, bool expiration); void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq); diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c index 63311d1ff1ed..ae4d000ac0af 100644 --- a/block/bfq-wf2q.c +++ b/block/bfq-wf2q.c @@ -1012,7 +1012,7 @@ static void __bfq_activate_entity(struct bfq_entity *entity, entity->on_st = true; } -#ifdef BFQ_GROUP_IOSCHED_ENABLED +#ifdef CONFIG_BFQ_GROUP_IOSCHED if (!bfq_entity_to_bfqq(entity)) { /* bfq_group */ struct bfq_group *bfqg = container_of(entity, struct bfq_group, entity); @@ -1605,7 +1605,8 @@ struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd) return bfqq; } -void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd) +/* returns true if the in-service queue gets freed */ +bool __bfq_bfqd_reset_in_service(struct bfq_data *bfqd) { struct bfq_queue *in_serv_bfqq = bfqd->in_service_queue; struct bfq_entity *in_serv_entity = &in_serv_bfqq->entity; @@ -1629,8 +1630,20 @@ void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd) * service tree either, then release the service reference to * the queue it represents (taken with bfq_get_entity). */ - if (!in_serv_entity->on_st) + if (!in_serv_entity->on_st) { + /* + * If no process is referencing in_serv_bfqq any + * longer, then the service reference may be the only + * reference to the queue. If this is the case, then + * bfqq gets freed here. + */ + int ref = in_serv_bfqq->ref; bfq_put_queue(in_serv_bfqq); + if (ref == 1) + return true; + } + + return false; } void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq, diff --git a/block/bio.c b/block/bio.c index b64cedc7f87c..716510ecd7ff 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1298,8 +1298,11 @@ struct bio *bio_copy_user_iov(struct request_queue *q, } } - if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes) + if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes) { + if (!map_data) + __free_page(page); break; + } len -= bytes; offset = 0; diff --git a/block/blk-core.c b/block/blk-core.c index 4673ebe42255..a55389ba8779 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1245,8 +1245,6 @@ static int blk_cloned_rq_check_limits(struct request_queue *q, */ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq) { - blk_qc_t unused; - if (blk_cloned_rq_check_limits(q, rq)) return BLK_STS_IOERR; @@ -1262,7 +1260,7 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request * * bypass a potential scheduler on the bottom device for * insert. */ - return blk_mq_try_issue_directly(rq->mq_hctx, rq, &unused, true, true); + return blk_mq_request_issue_directly(rq, true); } EXPORT_SYMBOL_GPL(blk_insert_cloned_request); diff --git a/block/blk-flush.c b/block/blk-flush.c index 6e0f2d97fc6d..d95f94892015 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -220,7 +220,7 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error) blk_mq_tag_set_rq(hctx, flush_rq->tag, fq->orig_rq); flush_rq->tag = -1; } else { - blk_mq_put_driver_tag_hctx(hctx, flush_rq); + blk_mq_put_driver_tag(flush_rq); flush_rq->internal_tag = -1; } @@ -324,7 +324,7 @@ static void mq_flush_data_end_io(struct request *rq, blk_status_t error) if (q->elevator) { WARN_ON(rq->tag < 0); - blk_mq_put_driver_tag_hctx(hctx, rq); + blk_mq_put_driver_tag(rq); } /* diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 40905539afed..aa6bc5c02643 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -423,10 +423,12 @@ void blk_mq_sched_insert_requests(struct blk_mq_hw_ctx *hctx, * busy in case of 'none' scheduler, and this way may save * us one extra enqueue & dequeue to sw queue. */ - if (!hctx->dispatch_busy && !e && !run_queue_async) + if (!hctx->dispatch_busy && !e && !run_queue_async) { blk_mq_try_issue_list_directly(hctx, list); - else - blk_mq_insert_requests(hctx, ctx, list); + if (list_empty(list)) + return; + } + blk_mq_insert_requests(hctx, ctx, list); } blk_mq_run_hw_queue(hctx, run_queue_async); diff --git a/block/blk-mq.c b/block/blk-mq.c index 70b210a308c4..fc60ed7e940e 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -59,7 +59,8 @@ static int blk_mq_poll_stats_bkt(const struct request *rq) } /* - * Check if any of the ctx's have pending work in this hardware queue + * Check if any of the ctx, dispatch list or elevator + * have pending work in this hardware queue. */ static bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx) { @@ -653,6 +654,13 @@ bool blk_mq_complete_request(struct request *rq) } EXPORT_SYMBOL(blk_mq_complete_request); +void blk_mq_complete_request_sync(struct request *rq) +{ + WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); + rq->q->mq_ops->complete(rq); +} +EXPORT_SYMBOL_GPL(blk_mq_complete_request_sync); + int blk_mq_request_started(struct request *rq) { return blk_mq_rq_state(rq) != MQ_RQ_IDLE; @@ -1071,7 +1079,13 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode, hctx = container_of(wait, struct blk_mq_hw_ctx, dispatch_wait); spin_lock(&hctx->dispatch_wait_lock); - list_del_init(&wait->entry); + if (!list_empty(&wait->entry)) { + struct sbitmap_queue *sbq; + + list_del_init(&wait->entry); + sbq = &hctx->tags->bitmap_tags; + atomic_dec(&sbq->ws_active); + } spin_unlock(&hctx->dispatch_wait_lock); blk_mq_run_hw_queue(hctx, true); @@ -1087,6 +1101,7 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode, static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx, struct request *rq) { + struct sbitmap_queue *sbq = &hctx->tags->bitmap_tags; struct wait_queue_head *wq; wait_queue_entry_t *wait; bool ret; @@ -1109,7 +1124,7 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx, if (!list_empty_careful(&wait->entry)) return false; - wq = &bt_wait_ptr(&hctx->tags->bitmap_tags, hctx)->wait; + wq = &bt_wait_ptr(sbq, hctx)->wait; spin_lock_irq(&wq->lock); spin_lock(&hctx->dispatch_wait_lock); @@ -1119,6 +1134,7 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx, return false; } + atomic_inc(&sbq->ws_active); wait->flags &= ~WQ_FLAG_EXCLUSIVE; __add_wait_queue(wq, wait); @@ -1139,6 +1155,7 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx, * someone else gets the wakeup. */ list_del_init(&wait->entry); + atomic_dec(&sbq->ws_active); spin_unlock(&hctx->dispatch_wait_lock); spin_unlock_irq(&wq->lock); @@ -1701,11 +1718,12 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) unsigned int depth; list_splice_init(&plug->mq_list, &list); - plug->rq_count = 0; if (plug->rq_count > 2 && plug->multiple_queues) list_sort(NULL, &list, plug_rq_cmp); + plug->rq_count = 0; + this_q = NULL; this_hctx = NULL; this_ctx = NULL; @@ -1790,74 +1808,76 @@ static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx, return ret; } -blk_status_t blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, +static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, struct request *rq, blk_qc_t *cookie, - bool bypass, bool last) + bool bypass_insert, bool last) { struct request_queue *q = rq->q; bool run_queue = true; - blk_status_t ret = BLK_STS_RESOURCE; - int srcu_idx; - bool force = false; - hctx_lock(hctx, &srcu_idx); /* - * hctx_lock is needed before checking quiesced flag. + * RCU or SRCU read lock is needed before checking quiesced flag. * - * When queue is stopped or quiesced, ignore 'bypass', insert - * and return BLK_STS_OK to caller, and avoid driver to try to - * dispatch again. + * When queue is stopped or quiesced, ignore 'bypass_insert' from + * blk_mq_request_issue_directly(), and return BLK_STS_OK to caller, + * and avoid driver to try to dispatch again. */ - if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q))) { + if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)) { run_queue = false; - bypass = false; - goto out_unlock; + bypass_insert = false; + goto insert; } - if (unlikely(q->elevator && !bypass)) - goto out_unlock; + if (q->elevator && !bypass_insert) + goto insert; if (!blk_mq_get_dispatch_budget(hctx)) - goto out_unlock; + goto insert; if (!blk_mq_get_driver_tag(rq)) { blk_mq_put_dispatch_budget(hctx); - goto out_unlock; + goto insert; } - /* - * Always add a request that has been through - *.queue_rq() to the hardware dispatch list. - */ - force = true; - ret = __blk_mq_issue_directly(hctx, rq, cookie, last); -out_unlock: + return __blk_mq_issue_directly(hctx, rq, cookie, last); +insert: + if (bypass_insert) + return BLK_STS_RESOURCE; + + blk_mq_request_bypass_insert(rq, run_queue); + return BLK_STS_OK; +} + +static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, + struct request *rq, blk_qc_t *cookie) +{ + blk_status_t ret; + int srcu_idx; + + might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING); + + hctx_lock(hctx, &srcu_idx); + + ret = __blk_mq_try_issue_directly(hctx, rq, cookie, false, true); + if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) + blk_mq_request_bypass_insert(rq, true); + else if (ret != BLK_STS_OK) + blk_mq_end_request(rq, ret); + + hctx_unlock(hctx, srcu_idx); +} + +blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last) +{ + blk_status_t ret; + int srcu_idx; + blk_qc_t unused_cookie; + struct blk_mq_hw_ctx *hctx = rq->mq_hctx; + + hctx_lock(hctx, &srcu_idx); + ret = __blk_mq_try_issue_directly(hctx, rq, &unused_cookie, true, last); hctx_unlock(hctx, srcu_idx); - switch (ret) { - case BLK_STS_OK: - break; - case BLK_STS_DEV_RESOURCE: - case BLK_STS_RESOURCE: - if (force) { - blk_mq_request_bypass_insert(rq, run_queue); - /* - * We have to return BLK_STS_OK for the DM - * to avoid livelock. Otherwise, we return - * the real result to indicate whether the - * request is direct-issued successfully. - */ - ret = bypass ? BLK_STS_OK : ret; - } else if (!bypass) { - blk_mq_sched_insert_request(rq, false, - run_queue, false); - } - break; - default: - if (!bypass) - blk_mq_end_request(rq, ret); - break; - } return ret; } @@ -1865,20 +1885,22 @@ out_unlock: void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, struct list_head *list) { - blk_qc_t unused; - blk_status_t ret = BLK_STS_OK; - while (!list_empty(list)) { + blk_status_t ret; struct request *rq = list_first_entry(list, struct request, queuelist); list_del_init(&rq->queuelist); - if (ret == BLK_STS_OK) - ret = blk_mq_try_issue_directly(hctx, rq, &unused, - false, + ret = blk_mq_request_issue_directly(rq, list_empty(list)); + if (ret != BLK_STS_OK) { + if (ret == BLK_STS_RESOURCE || + ret == BLK_STS_DEV_RESOURCE) { + blk_mq_request_bypass_insert(rq, list_empty(list)); - else - blk_mq_sched_insert_request(rq, false, true, false); + break; + } + blk_mq_end_request(rq, ret); + } } /* @@ -1886,7 +1908,7 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, * the driver there was more coming, but that turned out to * be a lie. */ - if (ret != BLK_STS_OK && hctx->queue->mq_ops->commit_rqs) + if (!list_empty(list) && hctx->queue->mq_ops->commit_rqs) hctx->queue->mq_ops->commit_rqs(hctx); } @@ -1993,19 +2015,21 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) plug->rq_count--; } blk_add_rq_to_plug(plug, rq); + trace_block_plug(q); blk_mq_put_ctx(data.ctx); if (same_queue_rq) { data.hctx = same_queue_rq->mq_hctx; + trace_block_unplug(q, 1, true); blk_mq_try_issue_directly(data.hctx, same_queue_rq, - &cookie, false, true); + &cookie); } } else if ((q->nr_hw_queues > 1 && is_sync) || (!q->elevator && !data.hctx->dispatch_busy)) { blk_mq_put_ctx(data.ctx); blk_mq_bio_to_request(rq, bio); - blk_mq_try_issue_directly(data.hctx, rq, &cookie, false, true); + blk_mq_try_issue_directly(data.hctx, rq, &cookie); } else { blk_mq_put_ctx(data.ctx); blk_mq_bio_to_request(rq, bio); @@ -2322,7 +2346,7 @@ static int blk_mq_init_hctx(struct request_queue *q, return 0; free_fq: - kfree(hctx->fq); + blk_free_flush_queue(hctx->fq); exit_hctx: if (set->ops->exit_hctx) set->ops->exit_hctx(hctx, hctx_idx); @@ -3111,6 +3135,8 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr) } if (ret) break; + if (q->elevator && q->elevator->type->ops.depth_updated) + q->elevator->type->ops.depth_updated(hctx); } if (!ret) diff --git a/block/blk-mq.h b/block/blk-mq.h index 0ed8e5a8729f..423ea88ab6fb 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -70,10 +70,8 @@ void blk_mq_request_bypass_insert(struct request *rq, bool run_queue); void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, struct list_head *list); -blk_status_t blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, - struct request *rq, - blk_qc_t *cookie, - bool bypass, bool last); +/* Used by blk_insert_cloned_request() to issue request directly */ +blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last); void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, struct list_head *list); @@ -224,15 +222,6 @@ static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx, } } -static inline void blk_mq_put_driver_tag_hctx(struct blk_mq_hw_ctx *hctx, - struct request *rq) -{ - if (rq->tag == -1 || rq->internal_tag == -1) - return; - - __blk_mq_put_driver_tag(hctx, rq); -} - static inline void blk_mq_put_driver_tag(struct request *rq) { if (rq->tag == -1 || rq->internal_tag == -1) diff --git a/crypto/lrw.c b/crypto/lrw.c index 0430ccd08728..08a0e458bc3e 100644 --- a/crypto/lrw.c +++ b/crypto/lrw.c @@ -212,8 +212,12 @@ static void crypt_done(struct crypto_async_request *areq, int err) { struct skcipher_request *req = areq->data; - if (!err) + if (!err) { + struct rctx *rctx = skcipher_request_ctx(req); + + rctx->subreq.base.flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; err = xor_tweak_post(req); + } skcipher_request_complete(req, err); } diff --git a/crypto/testmgr.h b/crypto/testmgr.h index f267633cf13a..d18a37629f05 100644 --- a/crypto/testmgr.h +++ b/crypto/testmgr.h @@ -5634,7 +5634,49 @@ static const struct hash_testvec poly1305_tv_template[] = { .psize = 80, .digest = "\x13\x00\x00\x00\x00\x00\x00\x00" "\x00\x00\x00\x00\x00\x00\x00\x00", - }, + }, { /* Regression test for overflow in AVX2 implementation */ + .plaintext = "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff\xff\xff\xff\xff" + "\xff\xff\xff\xff", + .psize = 300, + .digest = "\xfb\x5e\x96\xd8\x61\xd5\xc7\xc8" + "\x78\xe5\x87\xcc\x2d\x5a\x22\xe1", + } }; /* NHPoly1305 test vectors from https://github.com/google/adiantum */ diff --git a/crypto/xts.c b/crypto/xts.c index 847f54f76789..2f948328cabb 100644 --- a/crypto/xts.c +++ b/crypto/xts.c @@ -137,8 +137,12 @@ static void crypt_done(struct crypto_async_request *areq, int err) { struct skcipher_request *req = areq->data; - if (!err) + if (!err) { + struct rctx *rctx = skcipher_request_ctx(req); + + rctx->subreq.base.flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; err = xor_tweak_post(req); + } skcipher_request_complete(req, err); } diff --git a/drivers/acpi/acpica/nsobject.c b/drivers/acpi/acpica/nsobject.c index 8638f43cfc3d..79d86da1c892 100644 --- a/drivers/acpi/acpica/nsobject.c +++ b/drivers/acpi/acpica/nsobject.c @@ -186,6 +186,10 @@ void acpi_ns_detach_object(struct acpi_namespace_node *node) } } + if (obj_desc->common.type == ACPI_TYPE_REGION) { + acpi_ut_remove_address_range(obj_desc->region.space_id, node); + } + /* Clear the Node entry in all cases */ node->object = NULL; diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 6ecbbabf1233..eec263c9019e 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -1043,9 +1043,6 @@ void __init acpi_early_init(void) acpi_permanent_mmap = true; - /* Initialize debug output. Linux does not use ACPICA defaults */ - acpi_dbg_level = ACPI_LV_INFO | ACPI_LV_REPAIR; - #ifdef CONFIG_X86 /* * If the machine falls into the DMI check table, diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 1b207fca1420..d4244e7d0e38 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -1150,8 +1150,13 @@ int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps) cpc_read(cpunum, nominal_reg, &nom); perf_caps->nominal_perf = nom; - cpc_read(cpunum, guaranteed_reg, &guaranteed); - perf_caps->guaranteed_perf = guaranteed; + if (guaranteed_reg->type != ACPI_TYPE_BUFFER || + IS_NULL_REG(&guaranteed_reg->cpc_entry.reg)) { + perf_caps->guaranteed_perf = 0; + } else { + cpc_read(cpunum, guaranteed_reg, &guaranteed); + perf_caps->guaranteed_perf = guaranteed; + } cpc_read(cpunum, lowest_non_linear_reg, &min_nonlinear); perf_caps->lowest_nonlinear_perf = min_nonlinear; diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 5a389a4f4f65..f1ed0befe303 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -567,6 +567,12 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, goto out; } + dev_dbg(dev, "%s cmd: %s output length: %d\n", dimm_name, + cmd_name, out_obj->buffer.length); + print_hex_dump_debug(cmd_name, DUMP_PREFIX_OFFSET, 4, 4, + out_obj->buffer.pointer, + min_t(u32, 128, out_obj->buffer.length), true); + if (call_pkg) { call_pkg->nd_fw_size = out_obj->buffer.length; memcpy(call_pkg->nd_payload + call_pkg->nd_size_in, @@ -585,12 +591,6 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, return 0; } - dev_dbg(dev, "%s cmd: %s output length: %d\n", dimm_name, - cmd_name, out_obj->buffer.length); - print_hex_dump_debug(cmd_name, DUMP_PREFIX_OFFSET, 4, 4, - out_obj->buffer.pointer, - min_t(u32, 128, out_obj->buffer.length), true); - for (i = 0, offset = 0; i < desc->out_num; i++) { u32 out_size = nd_cmd_out_size(nvdimm, cmd, desc, i, buf, (u32 *) out_obj->buffer.pointer, diff --git a/drivers/acpi/nfit/intel.c b/drivers/acpi/nfit/intel.c index f70de71f79d6..cddd0fcf622c 100644 --- a/drivers/acpi/nfit/intel.c +++ b/drivers/acpi/nfit/intel.c @@ -122,9 +122,8 @@ static int intel_security_change_key(struct nvdimm *nvdimm, if (!test_bit(cmd, &nfit_mem->dsm_mask)) return -ENOTTY; - if (old_data) - memcpy(nd_cmd.cmd.old_pass, old_data->data, - sizeof(nd_cmd.cmd.old_pass)); + memcpy(nd_cmd.cmd.old_pass, old_data->data, + sizeof(nd_cmd.cmd.old_pass)); memcpy(nd_cmd.cmd.new_pass, new_data->data, sizeof(nd_cmd.cmd.new_pass)); rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL); @@ -336,9 +335,8 @@ static int __maybe_unused intel_security_overwrite(struct nvdimm *nvdimm, /* flush all cache before we erase DIMM */ nvdimm_invalidate_cache(); - if (nkey) - memcpy(nd_cmd.cmd.passphrase, nkey->data, - sizeof(nd_cmd.cmd.passphrase)); + memcpy(nd_cmd.cmd.passphrase, nkey->data, + sizeof(nd_cmd.cmd.passphrase)); rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL); if (rc < 0) return rc; diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 8685882da64c..4b9c7ca492e6 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2057,7 +2057,8 @@ static size_t binder_get_object(struct binder_proc *proc, size_t object_size = 0; read_size = min_t(size_t, sizeof(*object), buffer->data_size - offset); - if (read_size < sizeof(*hdr) || !IS_ALIGNED(offset, sizeof(u32))) + if (offset > buffer->data_size || read_size < sizeof(*hdr) || + !IS_ALIGNED(offset, sizeof(u32))) return 0; binder_alloc_copy_from_buffer(&proc->alloc, object, buffer, offset, read_size); diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index 6389467670a0..195f120c4e8c 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -927,14 +927,13 @@ enum lru_status binder_alloc_free_page(struct list_head *item, index = page - alloc->pages; page_addr = (uintptr_t)alloc->buffer + index * PAGE_SIZE; + + mm = alloc->vma_vm_mm; + if (!mmget_not_zero(mm)) + goto err_mmget; + if (!down_write_trylock(&mm->mmap_sem)) + goto err_down_write_mmap_sem_failed; vma = binder_alloc_get_vma(alloc); - if (vma) { - if (!mmget_not_zero(alloc->vma_vm_mm)) - goto err_mmget; - mm = alloc->vma_vm_mm; - if (!down_read_trylock(&mm->mmap_sem)) - goto err_down_write_mmap_sem_failed; - } list_lru_isolate(lru, item); spin_unlock(lock); @@ -945,10 +944,9 @@ enum lru_status binder_alloc_free_page(struct list_head *item, zap_page_range(vma, page_addr, PAGE_SIZE); trace_binder_unmap_user_end(alloc, index); - - up_read(&mm->mmap_sem); - mmput(mm); } + up_write(&mm->mmap_sem); + mmput(mm); trace_binder_unmap_kernel_start(alloc, index); diff --git a/drivers/ata/libata-zpodd.c b/drivers/ata/libata-zpodd.c index b3ed8f9953a8..173e6f2dd9af 100644 --- a/drivers/ata/libata-zpodd.c +++ b/drivers/ata/libata-zpodd.c @@ -52,38 +52,52 @@ static int eject_tray(struct ata_device *dev) /* Per the spec, only slot type and drawer type ODD can be supported */ static enum odd_mech_type zpodd_get_mech_type(struct ata_device *dev) { - char buf[16]; + char *buf; unsigned int ret; - struct rm_feature_desc *desc = (void *)(buf + 8); + struct rm_feature_desc *desc; struct ata_taskfile tf; static const char cdb[] = { GPCMD_GET_CONFIGURATION, 2, /* only 1 feature descriptor requested */ 0, 3, /* 3, removable medium feature */ 0, 0, 0,/* reserved */ - 0, sizeof(buf), + 0, 16, 0, 0, 0, }; + buf = kzalloc(16, GFP_KERNEL); + if (!buf) + return ODD_MECH_TYPE_UNSUPPORTED; + desc = (void *)(buf + 8); + ata_tf_init(dev, &tf); tf.flags = ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE; tf.command = ATA_CMD_PACKET; tf.protocol = ATAPI_PROT_PIO; - tf.lbam = sizeof(buf); + tf.lbam = 16; ret = ata_exec_internal(dev, &tf, cdb, DMA_FROM_DEVICE, - buf, sizeof(buf), 0); - if (ret) + buf, 16, 0); + if (ret) { + kfree(buf); return ODD_MECH_TYPE_UNSUPPORTED; + } - if (be16_to_cpu(desc->feature_code) != 3) + if (be16_to_cpu(desc->feature_code) != 3) { + kfree(buf); return ODD_MECH_TYPE_UNSUPPORTED; + } - if (desc->mech_type == 0 && desc->load == 0 && desc->eject == 1) + if (desc->mech_type == 0 && desc->load == 0 && desc->eject == 1) { + kfree(buf); return ODD_MECH_TYPE_SLOT; - else if (desc->mech_type == 1 && desc->load == 0 && desc->eject == 1) + } else if (desc->mech_type == 1 && desc->load == 0 && + desc->eject == 1) { + kfree(buf); return ODD_MECH_TYPE_DRAWER; - else + } else { + kfree(buf); return ODD_MECH_TYPE_UNSUPPORTED; + } } /* Test if ODD is zero power ready by sense code */ diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c index 11e1663bdc4d..b2c06da4f62e 100644 --- a/drivers/atm/firestream.c +++ b/drivers/atm/firestream.c @@ -1646,7 +1646,7 @@ static irqreturn_t fs_irq (int irq, void *dev_id) } if (status & ISR_TBRQ_W) { - fs_dprintk (FS_DEBUG_IRQ, "Data tramsitted!\n"); + fs_dprintk (FS_DEBUG_IRQ, "Data transmitted!\n"); process_txdone_queue (dev, &dev->tx_relq); } diff --git a/drivers/base/memory.c b/drivers/base/memory.c index cb8347500ce2..e49028a60429 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -506,7 +506,7 @@ static ssize_t probe_store(struct device *dev, struct device_attribute *attr, ret = lock_device_hotplug_sysfs(); if (ret) - goto out; + return ret; nid = memory_add_physaddr_to_nid(phys_addr); ret = __add_memory(nid, phys_addr, diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c index 417a9f15c116..d7ac09c092f2 100644 --- a/drivers/block/null_blk_main.c +++ b/drivers/block/null_blk_main.c @@ -1748,6 +1748,11 @@ static int __init null_init(void) return -EINVAL; } + if (g_home_node != NUMA_NO_NODE && g_home_node >= nr_online_nodes) { + pr_err("null_blk: invalid home_node value\n"); + g_home_node = NUMA_NO_NODE; + } + if (g_queue_mode == NULL_Q_RQ) { pr_err("null_blk: legacy IO path no longer available\n"); return -EINVAL; diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c index 377a694dc228..6d415b20fb70 100644 --- a/drivers/block/paride/pcd.c +++ b/drivers/block/paride/pcd.c @@ -314,6 +314,7 @@ static void pcd_init_units(void) disk->queue = blk_mq_init_sq_queue(&cd->tag_set, &pcd_mq_ops, 1, BLK_MQ_F_SHOULD_MERGE); if (IS_ERR(disk->queue)) { + put_disk(disk); disk->queue = NULL; continue; } @@ -750,6 +751,8 @@ static int pcd_detect(void) printk("%s: No CD-ROM drive found\n", name); for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) { + if (!cd->disk) + continue; blk_cleanup_queue(cd->disk->queue); cd->disk->queue = NULL; blk_mq_free_tag_set(&cd->tag_set); @@ -1010,8 +1013,14 @@ static int __init pcd_init(void) pcd_probe_capabilities(); if (register_blkdev(major, name)) { - for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) + for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) { + if (!cd->disk) + continue; + + blk_cleanup_queue(cd->disk->queue); + blk_mq_free_tag_set(&cd->tag_set); put_disk(cd->disk); + } return -EBUSY; } @@ -1032,6 +1041,9 @@ static void __exit pcd_exit(void) int unit; for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) { + if (!cd->disk) + continue; + if (cd->present) { del_gendisk(cd->disk); pi_release(cd->pi); diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c index 103b617cdc31..35e6e271b219 100644 --- a/drivers/block/paride/pf.c +++ b/drivers/block/paride/pf.c @@ -762,6 +762,8 @@ static int pf_detect(void) printk("%s: No ATAPI disk detected\n", name); for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) { + if (!pf->disk) + continue; blk_cleanup_queue(pf->disk->queue); pf->disk->queue = NULL; blk_mq_free_tag_set(&pf->tag_set); @@ -1029,8 +1031,13 @@ static int __init pf_init(void) pf_busy = 0; if (register_blkdev(major, name)) { - for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) + for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) { + if (!pf->disk) + continue; + blk_cleanup_queue(pf->disk->queue); + blk_mq_free_tag_set(&pf->tag_set); put_disk(pf->disk); + } return -EBUSY; } @@ -1051,6 +1058,9 @@ static void __exit pf_exit(void) int unit; unregister_blkdev(major, name); for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) { + if (!pf->disk) + continue; + if (pf->present) del_gendisk(pf->disk); diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 4bc083b7c9b5..2a7ca4a1e6f7 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -513,6 +513,8 @@ static int init_vq(struct virtio_blk *vblk) if (err) num_vqs = 1; + num_vqs = min_t(unsigned int, nr_cpu_ids, num_vqs); + vblk->vqs = kmalloc_array(num_vqs, sizeof(*vblk->vqs), GFP_KERNEL); if (!vblk->vqs) return -ENOMEM; diff --git a/drivers/block/xsysace.c b/drivers/block/xsysace.c index 87ccef4bd69e..32a21b8d1d85 100644 --- a/drivers/block/xsysace.c +++ b/drivers/block/xsysace.c @@ -1090,6 +1090,8 @@ static int ace_setup(struct ace_device *ace) return 0; err_read: + /* prevent double queue cleanup */ + ace->gd->queue = NULL; put_disk(ace->gd); err_alloc_disk: blk_cleanup_queue(ace->queue); diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index e7a5f1d1c314..d58a359a6622 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -290,18 +290,8 @@ static ssize_t idle_store(struct device *dev, struct zram *zram = dev_to_zram(dev); unsigned long nr_pages = zram->disksize >> PAGE_SHIFT; int index; - char mode_buf[8]; - ssize_t sz; - sz = strscpy(mode_buf, buf, sizeof(mode_buf)); - if (sz <= 0) - return -EINVAL; - - /* ignore trailing new line */ - if (mode_buf[sz - 1] == '\n') - mode_buf[sz - 1] = 0x00; - - if (strcmp(mode_buf, "all")) + if (!sysfs_streq(buf, "all")) return -EINVAL; down_read(&zram->init_lock); @@ -635,25 +625,15 @@ static ssize_t writeback_store(struct device *dev, struct bio bio; struct bio_vec bio_vec; struct page *page; - ssize_t ret, sz; - char mode_buf[8]; - int mode = -1; + ssize_t ret; + int mode; unsigned long blk_idx = 0; - sz = strscpy(mode_buf, buf, sizeof(mode_buf)); - if (sz <= 0) - return -EINVAL; - - /* ignore trailing newline */ - if (mode_buf[sz - 1] == '\n') - mode_buf[sz - 1] = 0x00; - - if (!strcmp(mode_buf, "idle")) + if (sysfs_streq(buf, "idle")) mode = IDLE_WRITEBACK; - else if (!strcmp(mode_buf, "huge")) + else if (sysfs_streq(buf, "huge")) mode = HUGE_WRITEBACK; - - if (mode == -1) + else return -EINVAL; down_read(&zram->init_lock); @@ -794,18 +774,18 @@ struct zram_work { struct zram *zram; unsigned long entry; struct bio *bio; + struct bio_vec bvec; }; #if PAGE_SIZE != 4096 static void zram_sync_read(struct work_struct *work) { - struct bio_vec bvec; struct zram_work *zw = container_of(work, struct zram_work, work); struct zram *zram = zw->zram; unsigned long entry = zw->entry; struct bio *bio = zw->bio; - read_from_bdev_async(zram, &bvec, entry, bio); + read_from_bdev_async(zram, &zw->bvec, entry, bio); } /* @@ -818,6 +798,7 @@ static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec, { struct zram_work work; + work.bvec = *bvec; work.zram = zram; work.entry = entry; work.bio = bio; diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index ded198328f21..7db48ae65cd2 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -2942,6 +2942,7 @@ static int btusb_config_oob_wake(struct hci_dev *hdev) return 0; } + irq_set_status_flags(irq, IRQ_NOAUTOEN); ret = devm_request_irq(&hdev->dev, irq, btusb_oob_wake_handler, 0, "OOB Wake-on-BT", data); if (ret) { @@ -2956,7 +2957,6 @@ static int btusb_config_oob_wake(struct hci_dev *hdev) } data->oob_wake_irq = irq; - disable_irq(irq); bt_dev_info(hdev, "OOB Wake-on-BT configured at IRQ %u", irq); return 0; } diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig index 72866a004f07..466ebd84ad17 100644 --- a/drivers/char/Kconfig +++ b/drivers/char/Kconfig @@ -348,7 +348,7 @@ config XILINX_HWICAP config R3964 tristate "Siemens R3964 line discipline" - depends on TTY + depends on TTY && BROKEN ---help--- This driver allows synchronous communication with devices using the Siemens R3964 packet protocol. Unless you are dealing with special diff --git a/drivers/char/ipmi/ipmi_dmi.c b/drivers/char/ipmi/ipmi_dmi.c index ff0b199be472..f2411468f33f 100644 --- a/drivers/char/ipmi/ipmi_dmi.c +++ b/drivers/char/ipmi/ipmi_dmi.c @@ -66,7 +66,6 @@ static void __init dmi_add_platform_ipmi(unsigned long base_addr, return; } - memset(&p, 0, sizeof(p)); p.addr = base_addr; p.space = space; p.regspacing = offset; diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index e8ba67834746..00bf4b17edbf 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -214,6 +214,9 @@ struct ipmi_user { /* Does this interface receive IPMI events? */ bool gets_events; + + /* Free must run in process context for RCU cleanup. */ + struct work_struct remove_work; }; static struct ipmi_user *acquire_ipmi_user(struct ipmi_user *user, int *index) @@ -1157,6 +1160,15 @@ static int intf_err_seq(struct ipmi_smi *intf, return rv; } +static void free_user_work(struct work_struct *work) +{ + struct ipmi_user *user = container_of(work, struct ipmi_user, + remove_work); + + cleanup_srcu_struct(&user->release_barrier); + kfree(user); +} + int ipmi_create_user(unsigned int if_num, const struct ipmi_user_hndl *handler, void *handler_data, @@ -1200,6 +1212,8 @@ int ipmi_create_user(unsigned int if_num, goto out_kfree; found: + INIT_WORK(&new_user->remove_work, free_user_work); + rv = init_srcu_struct(&new_user->release_barrier); if (rv) goto out_kfree; @@ -1260,8 +1274,9 @@ EXPORT_SYMBOL(ipmi_get_smi_info); static void free_user(struct kref *ref) { struct ipmi_user *user = container_of(ref, struct ipmi_user, refcount); - cleanup_srcu_struct(&user->release_barrier); - kfree(user); + + /* SRCU cleanup must happen in task context. */ + schedule_work(&user->remove_work); } static void _ipmi_destroy_user(struct ipmi_user *user) diff --git a/drivers/char/ipmi/ipmi_si_hardcode.c b/drivers/char/ipmi/ipmi_si_hardcode.c index 01946cad3d13..682221eebd66 100644 --- a/drivers/char/ipmi/ipmi_si_hardcode.c +++ b/drivers/char/ipmi/ipmi_si_hardcode.c @@ -118,6 +118,8 @@ void __init ipmi_hardcode_init(void) char *str; char *si_type[SI_MAX_PARMS]; + memset(si_type, 0, sizeof(si_type)); + /* Parse out the si_type string into its components. */ str = si_type_str; if (*str != '\0') { diff --git a/drivers/char/tpm/eventlog/tpm2.c b/drivers/char/tpm/eventlog/tpm2.c index d8b77133a83a..f824563fc28d 100644 --- a/drivers/char/tpm/eventlog/tpm2.c +++ b/drivers/char/tpm/eventlog/tpm2.c @@ -37,8 +37,8 @@ * * Returns size of the event. If it is an invalid event, returns 0. */ -static int calc_tpm2_event_size(struct tcg_pcr_event2_head *event, - struct tcg_pcr_event *event_header) +static size_t calc_tpm2_event_size(struct tcg_pcr_event2_head *event, + struct tcg_pcr_event *event_header) { struct tcg_efi_specid_event_head *efispecid; struct tcg_event_field *event_field; diff --git a/drivers/char/tpm/tpm-dev-common.c b/drivers/char/tpm/tpm-dev-common.c index 8856cce5a23b..817ae09a369e 100644 --- a/drivers/char/tpm/tpm-dev-common.c +++ b/drivers/char/tpm/tpm-dev-common.c @@ -233,12 +233,19 @@ __poll_t tpm_common_poll(struct file *file, poll_table *wait) __poll_t mask = 0; poll_wait(file, &priv->async_wait, wait); + mutex_lock(&priv->buffer_mutex); - if (!priv->response_read || priv->response_length) + /* + * The response_length indicates if there is still response + * (or part of it) to be consumed. Partial reads decrease it + * by the number of bytes read, and write resets it the zero. + */ + if (priv->response_length) mask = EPOLLIN | EPOLLRDNORM; else mask = EPOLLOUT | EPOLLWRNORM; + mutex_unlock(&priv->buffer_mutex); return mask; } diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index 83ece5639f86..ae1030c9b086 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -402,15 +402,13 @@ int tpm_pm_suspend(struct device *dev) if (chip->flags & TPM_CHIP_FLAG_ALWAYS_POWERED) return 0; - if (chip->flags & TPM_CHIP_FLAG_TPM2) { - mutex_lock(&chip->tpm_mutex); - if (!tpm_chip_start(chip)) { + if (!tpm_chip_start(chip)) { + if (chip->flags & TPM_CHIP_FLAG_TPM2) tpm2_shutdown(chip, TPM2_SU_STATE); - tpm_chip_stop(chip); - } - mutex_unlock(&chip->tpm_mutex); - } else { - rc = tpm1_pm_suspend(chip, tpm_suspend_pcr); + else + rc = tpm1_pm_suspend(chip, tpm_suspend_pcr); + + tpm_chip_stop(chip); } return rc; diff --git a/drivers/clk/at91/clk-programmable.c b/drivers/clk/at91/clk-programmable.c index 89d6f3736dbf..f8edbb65eda3 100644 --- a/drivers/clk/at91/clk-programmable.c +++ b/drivers/clk/at91/clk-programmable.c @@ -20,8 +20,7 @@ #define PROG_ID_MAX 7 #define PROG_STATUS_MASK(id) (1 << ((id) + 8)) -#define PROG_PRES_MASK 0x7 -#define PROG_PRES(layout, pckr) ((pckr >> layout->pres_shift) & PROG_PRES_MASK) +#define PROG_PRES(layout, pckr) ((pckr >> layout->pres_shift) & layout->pres_mask) #define PROG_MAX_RM9200_CSS 3 struct clk_programmable { @@ -37,20 +36,29 @@ static unsigned long clk_programmable_recalc_rate(struct clk_hw *hw, unsigned long parent_rate) { struct clk_programmable *prog = to_clk_programmable(hw); + const struct clk_programmable_layout *layout = prog->layout; unsigned int pckr; + unsigned long rate; regmap_read(prog->regmap, AT91_PMC_PCKR(prog->id), &pckr); - return parent_rate >> PROG_PRES(prog->layout, pckr); + if (layout->is_pres_direct) + rate = parent_rate / (PROG_PRES(layout, pckr) + 1); + else + rate = parent_rate >> PROG_PRES(layout, pckr); + + return rate; } static int clk_programmable_determine_rate(struct clk_hw *hw, struct clk_rate_request *req) { + struct clk_programmable *prog = to_clk_programmable(hw); + const struct clk_programmable_layout *layout = prog->layout; struct clk_hw *parent; long best_rate = -EINVAL; unsigned long parent_rate; - unsigned long tmp_rate; + unsigned long tmp_rate = 0; int shift; int i; @@ -60,10 +68,18 @@ static int clk_programmable_determine_rate(struct clk_hw *hw, continue; parent_rate = clk_hw_get_rate(parent); - for (shift = 0; shift < PROG_PRES_MASK; shift++) { - tmp_rate = parent_rate >> shift; - if (tmp_rate <= req->rate) - break; + if (layout->is_pres_direct) { + for (shift = 0; shift <= layout->pres_mask; shift++) { + tmp_rate = parent_rate / (shift + 1); + if (tmp_rate <= req->rate) + break; + } + } else { + for (shift = 0; shift < layout->pres_mask; shift++) { + tmp_rate = parent_rate >> shift; + if (tmp_rate <= req->rate) + break; + } } if (tmp_rate > req->rate) @@ -137,16 +153,23 @@ static int clk_programmable_set_rate(struct clk_hw *hw, unsigned long rate, if (!div) return -EINVAL; - shift = fls(div) - 1; + if (layout->is_pres_direct) { + shift = div - 1; - if (div != (1 << shift)) - return -EINVAL; + if (shift > layout->pres_mask) + return -EINVAL; + } else { + shift = fls(div) - 1; - if (shift >= PROG_PRES_MASK) - return -EINVAL; + if (div != (1 << shift)) + return -EINVAL; + + if (shift >= layout->pres_mask) + return -EINVAL; + } regmap_update_bits(prog->regmap, AT91_PMC_PCKR(prog->id), - PROG_PRES_MASK << layout->pres_shift, + layout->pres_mask << layout->pres_shift, shift << layout->pres_shift); return 0; @@ -202,19 +225,25 @@ at91_clk_register_programmable(struct regmap *regmap, } const struct clk_programmable_layout at91rm9200_programmable_layout = { + .pres_mask = 0x7, .pres_shift = 2, .css_mask = 0x3, .have_slck_mck = 0, + .is_pres_direct = 0, }; const struct clk_programmable_layout at91sam9g45_programmable_layout = { + .pres_mask = 0x7, .pres_shift = 2, .css_mask = 0x3, .have_slck_mck = 1, + .is_pres_direct = 0, }; const struct clk_programmable_layout at91sam9x5_programmable_layout = { + .pres_mask = 0x7, .pres_shift = 4, .css_mask = 0x7, .have_slck_mck = 0, + .is_pres_direct = 0, }; diff --git a/drivers/clk/at91/pmc.h b/drivers/clk/at91/pmc.h index 672a79bda88c..a0e5ce9c9b9e 100644 --- a/drivers/clk/at91/pmc.h +++ b/drivers/clk/at91/pmc.h @@ -71,9 +71,11 @@ struct clk_pll_characteristics { }; struct clk_programmable_layout { + u8 pres_mask; u8 pres_shift; u8 css_mask; u8 have_slck_mck; + u8 is_pres_direct; }; extern const struct clk_programmable_layout at91rm9200_programmable_layout; diff --git a/drivers/clk/at91/sama5d2.c b/drivers/clk/at91/sama5d2.c index 1f70cb164b06..81943fac4537 100644 --- a/drivers/clk/at91/sama5d2.c +++ b/drivers/clk/at91/sama5d2.c @@ -125,6 +125,14 @@ static const struct { .pll = true }, }; +static const struct clk_programmable_layout sama5d2_programmable_layout = { + .pres_mask = 0xff, + .pres_shift = 4, + .css_mask = 0x7, + .have_slck_mck = 0, + .is_pres_direct = 1, +}; + static void __init sama5d2_pmc_setup(struct device_node *np) { struct clk_range range = CLK_RANGE(0, 0); @@ -249,7 +257,7 @@ static void __init sama5d2_pmc_setup(struct device_node *np) hw = at91_clk_register_programmable(regmap, name, parent_names, 6, i, - &at91sam9x5_programmable_layout); + &sama5d2_programmable_layout); if (IS_ERR(hw)) goto err_free; } diff --git a/drivers/clk/clkdev.c b/drivers/clk/clkdev.c index 8c4435c53f09..6e787cc9e5b9 100644 --- a/drivers/clk/clkdev.c +++ b/drivers/clk/clkdev.c @@ -46,6 +46,8 @@ static struct clk_lookup *clk_find(const char *dev_id, const char *con_id) if (con_id) best_possible += 1; + lockdep_assert_held(&clocks_mutex); + list_for_each_entry(p, &clocks, node) { match = 0; if (p->dev_id) { @@ -402,7 +404,10 @@ void devm_clk_release_clkdev(struct device *dev, const char *con_id, struct clk_lookup *cl; int rval; + mutex_lock(&clocks_mutex); cl = clk_find(dev_id, con_id); + mutex_unlock(&clocks_mutex); + WARN_ON(!cl); rval = devres_release(dev, devm_clkdev_release, devm_clk_match_clkdev, cl); diff --git a/drivers/clk/imx/clk-pll14xx.c b/drivers/clk/imx/clk-pll14xx.c index 1acfa3e3cfb4..113d71042199 100644 --- a/drivers/clk/imx/clk-pll14xx.c +++ b/drivers/clk/imx/clk-pll14xx.c @@ -362,7 +362,7 @@ struct clk *imx_clk_pll14xx(const char *name, const char *parent_name, switch (pll_clk->type) { case PLL_1416X: - if (!pll->rate_table) + if (!pll_clk->rate_table) init.ops = &clk_pll1416x_min_ops; else init.ops = &clk_pll1416x_ops; diff --git a/drivers/clk/mediatek/clk-gate.c b/drivers/clk/mediatek/clk-gate.c index 9628d4e7690b..85daf826619a 100644 --- a/drivers/clk/mediatek/clk-gate.c +++ b/drivers/clk/mediatek/clk-gate.c @@ -169,11 +169,10 @@ struct clk *mtk_clk_register_gate( return ERR_PTR(-ENOMEM); init.name = name; - init.flags = CLK_SET_RATE_PARENT; + init.flags = flags | CLK_SET_RATE_PARENT; init.parent_names = parent_name ? &parent_name : NULL; init.num_parents = parent_name ? 1 : 0; init.ops = ops; - init.flags = flags; cg->regmap = regmap; cg->set_ofs = set_ofs; diff --git a/drivers/clk/meson/clk-pll.c b/drivers/clk/meson/clk-pll.c index 41e16dd7272a..7a14ac9b2fec 100644 --- a/drivers/clk/meson/clk-pll.c +++ b/drivers/clk/meson/clk-pll.c @@ -120,7 +120,7 @@ static bool meson_clk_pll_is_better(unsigned long rate, return true; } else { /* Round down */ - if (now < rate && best < now) + if (now <= rate && best < now) return true; } diff --git a/drivers/clk/meson/g12a.c b/drivers/clk/meson/g12a.c index 0e1ce8c03259..f7b11e1eeebe 100644 --- a/drivers/clk/meson/g12a.c +++ b/drivers/clk/meson/g12a.c @@ -960,14 +960,14 @@ static struct clk_regmap g12a_sd_emmc_c_clk0 = { /* VPU Clock */ static const char * const g12a_vpu_parent_names[] = { - "fclk_div4", "fclk_div3", "fclk_div5", "fclk_div7", + "fclk_div3", "fclk_div4", "fclk_div5", "fclk_div7", "mpll1", "vid_pll", "hifi_pll", "gp0_pll", }; static struct clk_regmap g12a_vpu_0_sel = { .data = &(struct clk_regmap_mux_data){ .offset = HHI_VPU_CLK_CNTL, - .mask = 0x3, + .mask = 0x7, .shift = 9, }, .hw.init = &(struct clk_init_data){ @@ -1011,7 +1011,7 @@ static struct clk_regmap g12a_vpu_0 = { static struct clk_regmap g12a_vpu_1_sel = { .data = &(struct clk_regmap_mux_data){ .offset = HHI_VPU_CLK_CNTL, - .mask = 0x3, + .mask = 0x7, .shift = 25, }, .hw.init = &(struct clk_init_data){ diff --git a/drivers/clk/meson/gxbb.c b/drivers/clk/meson/gxbb.c index 04df2e208ed6..29ffb4fde714 100644 --- a/drivers/clk/meson/gxbb.c +++ b/drivers/clk/meson/gxbb.c @@ -2216,6 +2216,7 @@ static struct clk_regmap gxbb_vdec_1_div = { .offset = HHI_VDEC_CLK_CNTL, .shift = 0, .width = 7, + .flags = CLK_DIVIDER_ROUND_CLOSEST, }, .hw.init = &(struct clk_init_data){ .name = "vdec_1_div", @@ -2261,6 +2262,7 @@ static struct clk_regmap gxbb_vdec_hevc_div = { .offset = HHI_VDEC2_CLK_CNTL, .shift = 16, .width = 7, + .flags = CLK_DIVIDER_ROUND_CLOSEST, }, .hw.init = &(struct clk_init_data){ .name = "vdec_hevc_div", diff --git a/drivers/clk/meson/vid-pll-div.c b/drivers/clk/meson/vid-pll-div.c index 08bcc01c0923..daff235bc763 100644 --- a/drivers/clk/meson/vid-pll-div.c +++ b/drivers/clk/meson/vid-pll-div.c @@ -82,8 +82,8 @@ static unsigned long meson_vid_pll_div_recalc_rate(struct clk_hw *hw, div = _get_table_val(meson_parm_read(clk->map, &pll_div->val), meson_parm_read(clk->map, &pll_div->sel)); if (!div || !div->divider) { - pr_info("%s: Invalid config value for vid_pll_div\n", __func__); - return parent_rate; + pr_debug("%s: Invalid config value for vid_pll_div\n", __func__); + return 0; } return DIV_ROUND_UP_ULL(parent_rate * div->multiplier, div->divider); diff --git a/drivers/clk/sunxi-ng/ccu_nkmp.c b/drivers/clk/sunxi-ng/ccu_nkmp.c index 9b49adb20d07..cbcdf664f336 100644 --- a/drivers/clk/sunxi-ng/ccu_nkmp.c +++ b/drivers/clk/sunxi-ng/ccu_nkmp.c @@ -167,7 +167,7 @@ static int ccu_nkmp_set_rate(struct clk_hw *hw, unsigned long rate, unsigned long parent_rate) { struct ccu_nkmp *nkmp = hw_to_ccu_nkmp(hw); - u32 n_mask, k_mask, m_mask, p_mask; + u32 n_mask = 0, k_mask = 0, m_mask = 0, p_mask = 0; struct _ccu_nkmp _nkmp; unsigned long flags; u32 reg; @@ -186,10 +186,24 @@ static int ccu_nkmp_set_rate(struct clk_hw *hw, unsigned long rate, ccu_nkmp_find_best(parent_rate, rate, &_nkmp); - n_mask = GENMASK(nkmp->n.width + nkmp->n.shift - 1, nkmp->n.shift); - k_mask = GENMASK(nkmp->k.width + nkmp->k.shift - 1, nkmp->k.shift); - m_mask = GENMASK(nkmp->m.width + nkmp->m.shift - 1, nkmp->m.shift); - p_mask = GENMASK(nkmp->p.width + nkmp->p.shift - 1, nkmp->p.shift); + /* + * If width is 0, GENMASK() macro may not generate expected mask (0) + * as it falls under undefined behaviour by C standard due to shifts + * which are equal or greater than width of left operand. This can + * be easily avoided by explicitly checking if width is 0. + */ + if (nkmp->n.width) + n_mask = GENMASK(nkmp->n.width + nkmp->n.shift - 1, + nkmp->n.shift); + if (nkmp->k.width) + k_mask = GENMASK(nkmp->k.width + nkmp->k.shift - 1, + nkmp->k.shift); + if (nkmp->m.width) + m_mask = GENMASK(nkmp->m.width + nkmp->m.shift - 1, + nkmp->m.shift); + if (nkmp->p.width) + p_mask = GENMASK(nkmp->p.width + nkmp->p.shift - 1, + nkmp->p.shift); spin_lock_irqsave(nkmp->common.lock, flags); diff --git a/drivers/clk/x86/clk-pmc-atom.c b/drivers/clk/x86/clk-pmc-atom.c index d977193842df..19174835693b 100644 --- a/drivers/clk/x86/clk-pmc-atom.c +++ b/drivers/clk/x86/clk-pmc-atom.c @@ -165,7 +165,7 @@ static const struct clk_ops plt_clk_ops = { }; static struct clk_plt *plt_clk_register(struct platform_device *pdev, int id, - void __iomem *base, + const struct pmc_clk_data *pmc_data, const char **parent_names, int num_parents) { @@ -184,9 +184,17 @@ static struct clk_plt *plt_clk_register(struct platform_device *pdev, int id, init.num_parents = num_parents; pclk->hw.init = &init; - pclk->reg = base + PMC_CLK_CTL_OFFSET + id * PMC_CLK_CTL_SIZE; + pclk->reg = pmc_data->base + PMC_CLK_CTL_OFFSET + id * PMC_CLK_CTL_SIZE; spin_lock_init(&pclk->lock); + /* + * On some systems, the pmc_plt_clocks already enabled by the + * firmware are being marked as critical to avoid them being + * gated by the clock framework. + */ + if (pmc_data->critical && plt_clk_is_enabled(&pclk->hw)) + init.flags |= CLK_IS_CRITICAL; + ret = devm_clk_hw_register(&pdev->dev, &pclk->hw); if (ret) { pclk = ERR_PTR(ret); @@ -332,7 +340,7 @@ static int plt_clk_probe(struct platform_device *pdev) return PTR_ERR(parent_names); for (i = 0; i < PMC_CLK_NUM; i++) { - data->clks[i] = plt_clk_register(pdev, i, pmc_data->base, + data->clks[i] = plt_clk_register(pdev, i, pmc_data, parent_names, data->nparents); if (IS_ERR(data->clks[i])) { err = PTR_ERR(data->clks[i]); diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index 171502a356aa..4b3d143f0f8a 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -145,6 +145,7 @@ config VT8500_TIMER config NPCM7XX_TIMER bool "NPCM7xx timer driver" if COMPILE_TEST depends on HAS_IOMEM + select TIMER_OF select CLKSRC_MMIO help Enable 24-bit TIMER0 and TIMER1 counters in the NPCM7xx architecture, diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index aa4ec53281ce..ea373cfbcecb 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -9,7 +9,7 @@ * published by the Free Software Foundation. */ -#define pr_fmt(fmt) "arm_arch_timer: " fmt +#define pr_fmt(fmt) "arch_timer: " fmt #include <linux/init.h> #include <linux/kernel.h> @@ -33,9 +33,6 @@ #include <clocksource/arm_arch_timer.h> -#undef pr_fmt -#define pr_fmt(fmt) "arch_timer: " fmt - #define CNTTIDR 0x08 #define CNTTIDR_VIRT(n) (BIT(1) << ((n) * 4)) diff --git a/drivers/clocksource/timer-oxnas-rps.c b/drivers/clocksource/timer-oxnas-rps.c index eed6feff8b5f..30c6f4ce672b 100644 --- a/drivers/clocksource/timer-oxnas-rps.c +++ b/drivers/clocksource/timer-oxnas-rps.c @@ -296,4 +296,4 @@ err_alloc: TIMER_OF_DECLARE(ox810se_rps, "oxsemi,ox810se-rps-timer", oxnas_rps_timer_init); TIMER_OF_DECLARE(ox820_rps, - "oxsemi,ox820se-rps-timer", oxnas_rps_timer_init); + "oxsemi,ox820-rps-timer", oxnas_rps_timer_init); diff --git a/drivers/clocksource/timer-ti-dm.c b/drivers/clocksource/timer-ti-dm.c index 3352da6ed61f..ee8ec5a8cb16 100644 --- a/drivers/clocksource/timer-ti-dm.c +++ b/drivers/clocksource/timer-ti-dm.c @@ -585,34 +585,6 @@ static int omap_dm_timer_set_load(struct omap_dm_timer *timer, int autoreload, return 0; } -/* Optimized set_load which removes costly spin wait in timer_start */ -static int omap_dm_timer_set_load_start(struct omap_dm_timer *timer, - int autoreload, unsigned int load) -{ - u32 l; - - if (unlikely(!timer)) - return -EINVAL; - - omap_dm_timer_enable(timer); - - l = omap_dm_timer_read_reg(timer, OMAP_TIMER_CTRL_REG); - if (autoreload) { - l |= OMAP_TIMER_CTRL_AR; - omap_dm_timer_write_reg(timer, OMAP_TIMER_LOAD_REG, load); - } else { - l &= ~OMAP_TIMER_CTRL_AR; - } - l |= OMAP_TIMER_CTRL_ST; - - __omap_dm_timer_load_start(timer, l, load, timer->posted); - - /* Save the context */ - timer->context.tclr = l; - timer->context.tldr = load; - timer->context.tcrr = load; - return 0; -} static int omap_dm_timer_set_match(struct omap_dm_timer *timer, int enable, unsigned int match) { diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index e22f0dbaebb1..2986119dd31f 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -385,7 +385,10 @@ static int intel_pstate_get_cppc_guranteed(int cpu) if (ret) return ret; - return cppc_perf.guaranteed_perf; + if (cppc_perf.guaranteed_perf) + return cppc_perf.guaranteed_perf; + + return cppc_perf.nominal_perf; } #else /* CONFIG_ACPI_CPPC_LIB */ @@ -2593,6 +2596,9 @@ static int __init intel_pstate_init(void) const struct x86_cpu_id *id; int rc; + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return -ENODEV; + if (no_load) return -ENODEV; @@ -2608,7 +2614,7 @@ static int __init intel_pstate_init(void) } else { id = x86_match_cpu(intel_pstate_cpu_ids); if (!id) { - pr_info("CPU ID not supported\n"); + pr_info("CPU model not supported\n"); return -ENODEV; } diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c index 3f49427766b8..2b51e0718c9f 100644 --- a/drivers/cpufreq/scpi-cpufreq.c +++ b/drivers/cpufreq/scpi-cpufreq.c @@ -189,8 +189,8 @@ static int scpi_cpufreq_exit(struct cpufreq_policy *policy) clk_put(priv->clk); dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table); - kfree(priv); dev_pm_opp_remove_all_dynamic(priv->cpu_dev); + kfree(priv); return 0; } diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c index b1eadc6652b5..7205d9f4029e 100644 --- a/drivers/crypto/caam/caamhash.c +++ b/drivers/crypto/caam/caamhash.c @@ -865,19 +865,18 @@ static int ahash_update_ctx(struct ahash_request *req) if (ret) goto unmap_ctx; - if (mapped_nents) { + if (mapped_nents) sg_to_sec4_sg_last(req->src, mapped_nents, edesc->sec4_sg + sec4_sg_src_index, 0); - if (*next_buflen) - scatterwalk_map_and_copy(next_buf, req->src, - to_hash - *buflen, - *next_buflen, 0); - } else { + else sg_to_sec4_set_last(edesc->sec4_sg + sec4_sg_src_index - 1); - } + if (*next_buflen) + scatterwalk_map_and_copy(next_buf, req->src, + to_hash - *buflen, + *next_buflen, 0); desc = edesc->hw_desc; edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg, diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c index ec8a291d62ba..54093ffd0aef 100644 --- a/drivers/dma/bcm2835-dma.c +++ b/drivers/dma/bcm2835-dma.c @@ -671,7 +671,7 @@ static struct dma_async_tx_descriptor *bcm2835_dma_prep_slave_sg( d = bcm2835_dma_create_cb_chain(chan, direction, false, info, extra, frames, src, dst, 0, 0, - GFP_KERNEL); + GFP_NOWAIT); if (!d) return NULL; diff --git a/drivers/dma/mediatek/mtk-cqdma.c b/drivers/dma/mediatek/mtk-cqdma.c index 131f3974740d..814853842e29 100644 --- a/drivers/dma/mediatek/mtk-cqdma.c +++ b/drivers/dma/mediatek/mtk-cqdma.c @@ -253,7 +253,7 @@ static void mtk_cqdma_start(struct mtk_cqdma_pchan *pc, #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT mtk_dma_set(pc, MTK_CQDMA_DST2, cvd->dest >> MTK_CQDMA_ADDR2_SHFIT); #else - mtk_dma_set(pc, MTK_CQDMA_SRC2, 0); + mtk_dma_set(pc, MTK_CQDMA_DST2, 0); #endif /* setup the length */ diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c index 2b4f25698169..e2a5398f89b5 100644 --- a/drivers/dma/sh/rcar-dmac.c +++ b/drivers/dma/sh/rcar-dmac.c @@ -1282,6 +1282,9 @@ static unsigned int rcar_dmac_chan_get_residue(struct rcar_dmac_chan *chan, enum dma_status status; unsigned int residue = 0; unsigned int dptr = 0; + unsigned int chcrb; + unsigned int tcrb; + unsigned int i; if (!desc) return 0; @@ -1330,14 +1333,31 @@ static unsigned int rcar_dmac_chan_get_residue(struct rcar_dmac_chan *chan, } /* + * We need to read two registers. + * Make sure the control register does not skip to next chunk + * while reading the counter. + * Trying it 3 times should be enough: Initial read, retry, retry + * for the paranoid. + */ + for (i = 0; i < 3; i++) { + chcrb = rcar_dmac_chan_read(chan, RCAR_DMACHCRB) & + RCAR_DMACHCRB_DPTR_MASK; + tcrb = rcar_dmac_chan_read(chan, RCAR_DMATCRB); + /* Still the same? */ + if (chcrb == (rcar_dmac_chan_read(chan, RCAR_DMACHCRB) & + RCAR_DMACHCRB_DPTR_MASK)) + break; + } + WARN_ONCE(i >= 3, "residue might be not continuous!"); + + /* * In descriptor mode the descriptor running pointer is not maintained * by the interrupt handler, find the running descriptor from the * descriptor pointer field in the CHCRB register. In non-descriptor * mode just use the running descriptor pointer. */ if (desc->hwdescs.use) { - dptr = (rcar_dmac_chan_read(chan, RCAR_DMACHCRB) & - RCAR_DMACHCRB_DPTR_MASK) >> RCAR_DMACHCRB_DPTR_SHIFT; + dptr = chcrb >> RCAR_DMACHCRB_DPTR_SHIFT; if (dptr == 0) dptr = desc->nchunks; dptr--; @@ -1355,7 +1375,7 @@ static unsigned int rcar_dmac_chan_get_residue(struct rcar_dmac_chan *chan, } /* Add the residue for the current chunk. */ - residue += rcar_dmac_chan_read(chan, RCAR_DMATCRB) << desc->xfer_shift; + residue += tcrb << desc->xfer_shift; return residue; } @@ -1368,6 +1388,7 @@ static enum dma_status rcar_dmac_tx_status(struct dma_chan *chan, enum dma_status status; unsigned long flags; unsigned int residue; + bool cyclic; status = dma_cookie_status(chan, cookie, txstate); if (status == DMA_COMPLETE || !txstate) @@ -1375,10 +1396,11 @@ static enum dma_status rcar_dmac_tx_status(struct dma_chan *chan, spin_lock_irqsave(&rchan->lock, flags); residue = rcar_dmac_chan_get_residue(rchan, cookie); + cyclic = rchan->desc.running ? rchan->desc.running->cyclic : false; spin_unlock_irqrestore(&rchan->lock, flags); /* if there's no residue, the cookie is complete */ - if (!residue) + if (!residue && !cyclic) return DMA_COMPLETE; dma_set_residue(txstate, residue); diff --git a/drivers/dma/stm32-mdma.c b/drivers/dma/stm32-mdma.c index 4e0eede599a8..ac0301b69593 100644 --- a/drivers/dma/stm32-mdma.c +++ b/drivers/dma/stm32-mdma.c @@ -1578,11 +1578,9 @@ static int stm32_mdma_probe(struct platform_device *pdev) dmadev->nr_channels = nr_channels; dmadev->nr_requests = nr_requests; - ret = device_property_read_u32_array(&pdev->dev, "st,ahb-addr-masks", + device_property_read_u32_array(&pdev->dev, "st,ahb-addr-masks", dmadev->ahb_addr_masks, count); - if (ret) - return ret; dmadev->nr_ahb_addr_masks = count; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); diff --git a/drivers/extcon/Kconfig b/drivers/extcon/Kconfig index 8e17149655f0..540e8cd16ee6 100644 --- a/drivers/extcon/Kconfig +++ b/drivers/extcon/Kconfig @@ -116,7 +116,7 @@ config EXTCON_PALMAS config EXTCON_PTN5150 tristate "NXP PTN5150 CC LOGIC USB EXTCON support" - depends on I2C && GPIOLIB || COMPILE_TEST + depends on I2C && (GPIOLIB || COMPILE_TEST) select REGMAP_I2C help Say Y here to enable support for USB peripheral and USB host diff --git a/drivers/gpio/gpio-adnp.c b/drivers/gpio/gpio-adnp.c index 91b90c0cea73..12acdac85820 100644 --- a/drivers/gpio/gpio-adnp.c +++ b/drivers/gpio/gpio-adnp.c @@ -132,8 +132,10 @@ static int adnp_gpio_direction_input(struct gpio_chip *chip, unsigned offset) if (err < 0) goto out; - if (err & BIT(pos)) - err = -EACCES; + if (value & BIT(pos)) { + err = -EPERM; + goto out; + } err = 0; diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c index 854bce4fb9e7..217507002dbc 100644 --- a/drivers/gpio/gpio-aspeed.c +++ b/drivers/gpio/gpio-aspeed.c @@ -1224,6 +1224,8 @@ static int __init aspeed_gpio_probe(struct platform_device *pdev) gpio->offset_timer = devm_kzalloc(&pdev->dev, gpio->chip.ngpio, GFP_KERNEL); + if (!gpio->offset_timer) + return -ENOMEM; return aspeed_gpio_setup_irqs(gpio, pdev); } diff --git a/drivers/gpio/gpio-eic-sprd.c b/drivers/gpio/gpio-eic-sprd.c index f0223cee9774..77092268ee95 100644 --- a/drivers/gpio/gpio-eic-sprd.c +++ b/drivers/gpio/gpio-eic-sprd.c @@ -414,6 +414,7 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type) irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_EDGE_BOTH: + sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 1); irq_set_handler_locked(data, handle_edge_irq); break; diff --git a/drivers/gpio/gpio-exar.c b/drivers/gpio/gpio-exar.c index 0ecd2369c2ca..a09d2f9ebacc 100644 --- a/drivers/gpio/gpio-exar.c +++ b/drivers/gpio/gpio-exar.c @@ -148,6 +148,8 @@ static int gpio_exar_probe(struct platform_device *pdev) mutex_init(&exar_gpio->lock); index = ida_simple_get(&ida_index, 0, 0, GFP_KERNEL); + if (index < 0) + goto err_destroy; sprintf(exar_gpio->name, "exar_gpio%d", index); exar_gpio->gpio_chip.label = exar_gpio->name; diff --git a/drivers/gpio/gpio-mockup.c b/drivers/gpio/gpio-mockup.c index 154d959e8993..b6a4efce7c92 100644 --- a/drivers/gpio/gpio-mockup.c +++ b/drivers/gpio/gpio-mockup.c @@ -204,8 +204,8 @@ static ssize_t gpio_mockup_debugfs_read(struct file *file, struct gpio_mockup_chip *chip; struct seq_file *sfile; struct gpio_chip *gc; + int val, cnt; char buf[3]; - int val, rv; if (*ppos != 0) return 0; @@ -216,13 +216,9 @@ static ssize_t gpio_mockup_debugfs_read(struct file *file, gc = &chip->gc; val = gpio_mockup_get(gc, priv->offset); - snprintf(buf, sizeof(buf), "%d\n", val); + cnt = snprintf(buf, sizeof(buf), "%d\n", val); - rv = copy_to_user(usr_buf, buf, sizeof(buf)); - if (rv) - return rv; - - return sizeof(buf) - 1; + return simple_read_from_buffer(usr_buf, size, ppos, buf, cnt); } static ssize_t gpio_mockup_debugfs_write(struct file *file, diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index 8b9c3ab70f6e..6a3ec575a404 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -120,7 +120,8 @@ static void of_gpio_flags_quirks(struct device_node *np, * to determine if the flags should have inverted semantics. */ if (IS_ENABLED(CONFIG_SPI_MASTER) && - of_property_read_bool(np, "cs-gpios")) { + of_property_read_bool(np, "cs-gpios") && + !strcmp(propname, "cs-gpios")) { struct device_node *child; u32 cs; int ret; @@ -142,16 +143,16 @@ static void of_gpio_flags_quirks(struct device_node *np, * conflict and the "spi-cs-high" flag will * take precedence. */ - if (of_property_read_bool(np, "spi-cs-high")) { + if (of_property_read_bool(child, "spi-cs-high")) { if (*flags & OF_GPIO_ACTIVE_LOW) { pr_warn("%s GPIO handle specifies active low - ignored\n", - of_node_full_name(np)); + of_node_full_name(child)); *flags &= ~OF_GPIO_ACTIVE_LOW; } } else { if (!(*flags & OF_GPIO_ACTIVE_LOW)) pr_info("%s enforce active low on chipselect handle\n", - of_node_full_name(np)); + of_node_full_name(child)); *flags |= OF_GPIO_ACTIVE_LOW; } break; @@ -717,7 +718,13 @@ int of_gpiochip_add(struct gpio_chip *chip) of_node_get(chip->of_node); - return of_gpiochip_scan_gpios(chip); + status = of_gpiochip_scan_gpios(chip); + if (status) { + of_node_put(chip->of_node); + gpiochip_remove_pin_ranges(chip); + } + + return status; } void of_gpiochip_remove(struct gpio_chip *chip) diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 144af0733581..bca3e7740ef6 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1379,7 +1379,7 @@ int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data, status = gpiochip_add_irqchip(chip, lock_key, request_key); if (status) - goto err_remove_chip; + goto err_free_gpiochip_mask; status = of_gpiochip_add(chip); if (status) @@ -1387,7 +1387,7 @@ int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data, status = gpiochip_init_valid_mask(chip); if (status) - goto err_remove_chip; + goto err_remove_of_chip; for (i = 0; i < chip->ngpio; i++) { struct gpio_desc *desc = &gdev->descs[i]; @@ -1415,14 +1415,18 @@ int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data, if (gpiolib_initialized) { status = gpiochip_setup_dev(gdev); if (status) - goto err_remove_chip; + goto err_remove_acpi_chip; } return 0; -err_remove_chip: +err_remove_acpi_chip: acpi_gpiochip_remove(chip); +err_remove_of_chip: gpiochip_free_hogs(chip); of_gpiochip_remove(chip); +err_remove_chip: + gpiochip_irqchip_remove(chip); +err_free_gpiochip_mask: gpiochip_free_valid_mask(chip); err_remove_irqchip_mask: gpiochip_irqchip_free_valid_mask(chip); @@ -2776,7 +2780,7 @@ int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce) } config = pinconf_to_config_packed(PIN_CONFIG_INPUT_DEBOUNCE, debounce); - return gpio_set_config(chip, gpio_chip_hwgpio(desc), config); + return chip->set_config(chip, gpio_chip_hwgpio(desc), config); } EXPORT_SYMBOL_GPL(gpiod_set_debounce); @@ -2813,7 +2817,7 @@ int gpiod_set_transitory(struct gpio_desc *desc, bool transitory) packed = pinconf_to_config_packed(PIN_CONFIG_PERSIST_STATE, !transitory); gpio = gpio_chip_hwgpio(desc); - rc = gpio_set_config(chip, gpio, packed); + rc = chip->set_config(chip, gpio, packed); if (rc == -ENOTSUPP) { dev_dbg(&desc->gdev->dev, "Persistence not supported for GPIO %d\n", gpio); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 4f8fb4ecde34..79fb302fb954 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3165,6 +3165,7 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev) /* No need to recover an evicted BO */ if (shadow->tbo.mem.mem_type != TTM_PL_TT || + shadow->tbo.mem.start == AMDGPU_BO_INVALID_OFFSET || shadow->parent->tbo.mem.mem_type != TTM_PL_VRAM) continue; @@ -3173,11 +3174,16 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev) break; if (fence) { - r = dma_fence_wait_timeout(fence, false, tmo); + tmo = dma_fence_wait_timeout(fence, false, tmo); dma_fence_put(fence); fence = next; - if (r <= 0) + if (tmo == 0) { + r = -ETIMEDOUT; break; + } else if (tmo < 0) { + r = tmo; + break; + } } else { fence = next; } @@ -3188,8 +3194,8 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev) tmo = dma_fence_wait_timeout(fence, false, tmo); dma_fence_put(fence); - if (r <= 0 || tmo <= 0) { - DRM_ERROR("recover vram bo from shadow failed\n"); + if (r < 0 || tmo <= 0) { + DRM_ERROR("recover vram bo from shadow failed, r is %ld, tmo is %ld\n", r, tmo); return -EIO; } @@ -3625,6 +3631,7 @@ static void amdgpu_device_get_min_pci_speed_width(struct amdgpu_device *adev, struct pci_dev *pdev = adev->pdev; enum pci_bus_speed cur_speed; enum pcie_link_width cur_width; + u32 ret = 1; *speed = PCI_SPEED_UNKNOWN; *width = PCIE_LNK_WIDTH_UNKNOWN; @@ -3632,6 +3639,10 @@ static void amdgpu_device_get_min_pci_speed_width(struct amdgpu_device *adev, while (pdev) { cur_speed = pcie_get_speed_cap(pdev); cur_width = pcie_get_width_cap(pdev); + ret = pcie_bandwidth_available(adev->pdev, NULL, + NULL, &cur_width); + if (!ret) + cur_width = PCIE_LNK_WIDTH_RESRV; if (cur_speed != PCI_SPEED_UNKNOWN) { if (*speed == PCI_SPEED_UNKNOWN) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c index 0b8ef2d27d6b..fe393a46f881 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c @@ -35,6 +35,7 @@ #include "amdgpu_trace.h" #define AMDGPU_IB_TEST_TIMEOUT msecs_to_jiffies(1000) +#define AMDGPU_IB_TEST_GFX_XGMI_TIMEOUT msecs_to_jiffies(2000) /* * IB @@ -344,6 +345,8 @@ int amdgpu_ib_ring_tests(struct amdgpu_device *adev) * cost waiting for it coming back under RUNTIME only */ tmo_gfx = 8 * AMDGPU_IB_TEST_TIMEOUT; + } else if (adev->gmc.xgmi.hive_id) { + tmo_gfx = AMDGPU_IB_TEST_GFX_XGMI_TIMEOUT; } for (i = 0; i < adev->num_rings; ++i) { diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index d0309e8c9d12..a11db2b1a63f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -2405,8 +2405,6 @@ static int gfx_v9_0_rlc_resume(struct amdgpu_device *adev) /* disable CG */ WREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL, 0); - adev->gfx.rlc.funcs->reset(adev); - gfx_v9_0_init_pg(adev); if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) { diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c index d0d966d6080a..1696644ec022 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c @@ -182,6 +182,7 @@ static void mmhub_v1_0_init_cache_regs(struct amdgpu_device *adev) tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, L2_CACHE_BIGK_FRAGMENT_SIZE, 6); } + WREG32_SOC15(MMHUB, 0, mmVM_L2_CNTL3, tmp); tmp = mmVM_L2_CNTL4_DEFAULT; tmp = REG_SET_FIELD(tmp, VM_L2_CNTL4, VMC_TAP_PDE_REQUEST_PHYSICAL, 0); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 8be9677c0c07..cf9a49f49d3a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -320,6 +320,7 @@ static const struct kfd_deviceid supported_devices[] = { { 0x9876, &carrizo_device_info }, /* Carrizo */ { 0x9877, &carrizo_device_info }, /* Carrizo */ { 0x15DD, &raven_device_info }, /* Raven */ + { 0x15D8, &raven_device_info }, /* Raven */ #endif { 0x67A0, &hawaii_device_info }, /* Hawaii */ { 0x67A1, &hawaii_device_info }, /* Hawaii */ 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 fb27783d7a54..3082b55b1e77 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -4533,6 +4533,7 @@ static void handle_cursor_update(struct drm_plane *plane, amdgpu_crtc->cursor_width = plane->state->crtc_w; amdgpu_crtc->cursor_height = plane->state->crtc_h; + memset(&attributes, 0, sizeof(attributes)); attributes.address.high_part = upper_32_bits(address); attributes.address.low_part = lower_32_bits(address); attributes.width = plane->state->crtc_w; @@ -5429,9 +5430,11 @@ static void get_freesync_config_for_crtc( struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(new_con_state->base.connector); struct drm_display_mode *mode = &new_crtc_state->base.mode; + int vrefresh = drm_mode_vrefresh(mode); new_crtc_state->vrr_supported = new_con_state->freesync_capable && - aconnector->min_vfreq <= drm_mode_vrefresh(mode); + vrefresh >= aconnector->min_vfreq && + vrefresh <= aconnector->max_vfreq; if (new_crtc_state->vrr_supported) { new_crtc_state->stream->ignore_msa_timing_param = true; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index c68fbd55db3c..a6cda201c964 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -1377,6 +1377,11 @@ static enum surface_update_type det_surface_update(const struct dc *dc, return UPDATE_TYPE_FULL; } + if (u->surface->force_full_update) { + update_flags->bits.full_update = 1; + return UPDATE_TYPE_FULL; + } + type = get_plane_info_update_type(u); elevate_update_type(&overall_type, type); @@ -1802,6 +1807,14 @@ void dc_commit_updates_for_stream(struct dc *dc, } dc_resource_state_copy_construct(state, context); + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *new_pipe = &context->res_ctx.pipe_ctx[i]; + struct pipe_ctx *old_pipe = &dc->current_state->res_ctx.pipe_ctx[i]; + + if (new_pipe->plane_state && new_pipe->plane_state != old_pipe->plane_state) + new_pipe->plane_state->force_full_update = true; + } } @@ -1838,6 +1851,12 @@ void dc_commit_updates_for_stream(struct dc *dc, dc->current_state = context; dc_release_state(old); + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i]; + + if (pipe_ctx->plane_state && pipe_ctx->stream == stream) + pipe_ctx->plane_state->force_full_update = false; + } } /*let's use current_state to update watermark etc*/ if (update_type >= UPDATE_TYPE_FULL) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 4eba3c4800b6..ea18e9c2d8ce 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -2660,12 +2660,18 @@ void core_link_enable_stream( void core_link_disable_stream(struct pipe_ctx *pipe_ctx, int option) { struct dc *core_dc = pipe_ctx->stream->ctx->dc; + struct dc_stream_state *stream = pipe_ctx->stream; core_dc->hwss.blank_stream(pipe_ctx); if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) deallocate_mst_payload(pipe_ctx); + if (dc_is_hdmi_signal(pipe_ctx->stream->signal)) + dal_ddc_service_write_scdc_data( + stream->link->ddc, 0, + stream->timing.flags.LTE_340MCSC_SCRAMBLE); + core_dc->hwss.disable_stream(pipe_ctx, option); disable_link(pipe_ctx->stream->link, pipe_ctx->stream->signal); diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 1a7fd6aa77eb..0515095574e7 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -503,6 +503,9 @@ struct dc_plane_state { struct dc_plane_status status; struct dc_context *ctx; + /* HACK: Workaround for forcing full reprogramming under some conditions */ + bool force_full_update; + /* private to dc_surface.c */ enum dc_irq_source irq_source; struct kref refcount; diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c index 4febf4ef7240..4fe3664fb495 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c @@ -190,6 +190,12 @@ static void submit_channel_request( 1, 0); } + + REG_UPDATE(AUX_INTERRUPT_CONTROL, AUX_SW_DONE_ACK, 1); + + REG_WAIT(AUX_SW_STATUS, AUX_SW_DONE, 0, + 10, aux110->timeout_period/10); + /* set the delay and the number of bytes to write */ /* The length include @@ -242,9 +248,6 @@ static void submit_channel_request( } } - REG_UPDATE(AUX_INTERRUPT_CONTROL, AUX_SW_DONE_ACK, 1); - REG_WAIT(AUX_SW_STATUS, AUX_SW_DONE, 0, - 10, aux110->timeout_period/10); REG_UPDATE(AUX_SW_CONTROL, AUX_SW_GO, 1); } diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h index d27f22c05e4b..e28ed6a00ff4 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h @@ -71,11 +71,11 @@ enum { /* This is the timeout as defined in DP 1.2a, * at most within ~240usec. That means, * increasing this timeout will not affect normal operation, * and we'll timeout after - * SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD = 1600usec. + * SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD = 2400usec. * This timeout is especially important for - * resume from S3 and CTS. + * converters, resume from S3, and CTS. */ - SW_AUX_TIMEOUT_PERIOD_MULTIPLIER = 4 + SW_AUX_TIMEOUT_PERIOD_MULTIPLIER = 6 }; struct dce_aux { diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c index 683829466a44..0ba68d41b9c3 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c @@ -1150,28 +1150,9 @@ void hubp1_cursor_set_position( REG_UPDATE(CURSOR_CONTROL, CURSOR_ENABLE, cur_en); - //account for cases where we see negative offset relative to overlay plane - if (src_x_offset < 0 && src_y_offset < 0) { - REG_SET_2(CURSOR_POSITION, 0, - CURSOR_X_POSITION, 0, - CURSOR_Y_POSITION, 0); - x_hotspot -= src_x_offset; - y_hotspot -= src_y_offset; - } else if (src_x_offset < 0) { - REG_SET_2(CURSOR_POSITION, 0, - CURSOR_X_POSITION, 0, - CURSOR_Y_POSITION, pos->y); - x_hotspot -= src_x_offset; - } else if (src_y_offset < 0) { - REG_SET_2(CURSOR_POSITION, 0, + REG_SET_2(CURSOR_POSITION, 0, CURSOR_X_POSITION, pos->x, - CURSOR_Y_POSITION, 0); - y_hotspot -= src_y_offset; - } else { - REG_SET_2(CURSOR_POSITION, 0, - CURSOR_X_POSITION, pos->x, - CURSOR_Y_POSITION, pos->y); - } + CURSOR_Y_POSITION, pos->y); REG_SET_2(CURSOR_HOT_SPOT, 0, CURSOR_HOT_SPOT_X, x_hotspot, diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c index 9aa7bec1b5fe..23b5b94a4939 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c @@ -91,6 +91,12 @@ static void vega20_set_default_registry_data(struct pp_hwmgr *hwmgr) * MP0CLK DS */ data->registry_data.disallowed_features = 0xE0041C00; + /* ECC feature should be disabled on old SMUs */ + smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetSmuVersion); + hwmgr->smu_version = smum_get_argument(hwmgr); + if (hwmgr->smu_version < 0x282100) + data->registry_data.disallowed_features |= FEATURE_ECC_MASK; + data->registry_data.od_state_in_dc_support = 0; data->registry_data.thermal_support = 1; data->registry_data.skip_baco_hardware = 0; @@ -357,6 +363,7 @@ static void vega20_init_dpm_defaults(struct pp_hwmgr *hwmgr) data->smu_features[GNLD_DS_MP1CLK].smu_feature_id = FEATURE_DS_MP1CLK_BIT; data->smu_features[GNLD_DS_MP0CLK].smu_feature_id = FEATURE_DS_MP0CLK_BIT; data->smu_features[GNLD_XGMI].smu_feature_id = FEATURE_XGMI_BIT; + data->smu_features[GNLD_ECC].smu_feature_id = FEATURE_ECC_BIT; for (i = 0; i < GNLD_FEATURES_MAX; i++) { data->smu_features[i].smu_feature_bitmap = @@ -3020,7 +3027,8 @@ static int vega20_get_ppfeature_status(struct pp_hwmgr *hwmgr, char *buf) "FCLK_DS", "MP1CLK_DS", "MP0CLK_DS", - "XGMI"}; + "XGMI", + "ECC"}; static const char *output_title[] = { "FEATURES", "BITMASK", @@ -3462,6 +3470,7 @@ static int vega20_apply_clocks_adjust_rules(struct pp_hwmgr *hwmgr) struct vega20_single_dpm_table *dpm_table; bool vblank_too_short = false; bool disable_mclk_switching; + bool disable_fclk_switching; uint32_t i, latency; disable_mclk_switching = ((1 < hwmgr->display_config->num_display) && @@ -3537,13 +3546,20 @@ static int vega20_apply_clocks_adjust_rules(struct pp_hwmgr *hwmgr) if (hwmgr->display_config->nb_pstate_switch_disable) dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value; + if ((disable_mclk_switching && + (dpm_table->dpm_state.hard_min_level == dpm_table->dpm_levels[dpm_table->count - 1].value)) || + hwmgr->display_config->min_mem_set_clock / 100 >= dpm_table->dpm_levels[dpm_table->count - 1].value) + disable_fclk_switching = true; + else + disable_fclk_switching = false; + /* fclk */ dpm_table = &(data->dpm_table.fclk_table); dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[0].value; dpm_table->dpm_state.soft_max_level = VG20_CLOCK_MAX_DEFAULT; dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[0].value; dpm_table->dpm_state.hard_max_level = VG20_CLOCK_MAX_DEFAULT; - if (hwmgr->display_config->nb_pstate_switch_disable) + if (hwmgr->display_config->nb_pstate_switch_disable || disable_fclk_switching) dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value; /* vclk */ diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h index a5bc758ae097..ac2a3118a0ae 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h @@ -80,6 +80,7 @@ enum { GNLD_DS_MP1CLK, GNLD_DS_MP0CLK, GNLD_XGMI, + GNLD_ECC, GNLD_FEATURES_MAX }; diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if.h b/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if.h index 63d5cf691549..195c4ae67058 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if.h +++ b/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if.h @@ -99,7 +99,7 @@ #define FEATURE_DS_MP1CLK_BIT 30 #define FEATURE_DS_MP0CLK_BIT 31 #define FEATURE_XGMI_BIT 32 -#define FEATURE_SPARE_33_BIT 33 +#define FEATURE_ECC_BIT 33 #define FEATURE_SPARE_34_BIT 34 #define FEATURE_SPARE_35_BIT 35 #define FEATURE_SPARE_36_BIT 36 @@ -165,7 +165,8 @@ #define FEATURE_DS_FCLK_MASK (1 << FEATURE_DS_FCLK_BIT ) #define FEATURE_DS_MP1CLK_MASK (1 << FEATURE_DS_MP1CLK_BIT ) #define FEATURE_DS_MP0CLK_MASK (1 << FEATURE_DS_MP0CLK_BIT ) -#define FEATURE_XGMI_MASK (1 << FEATURE_XGMI_BIT ) +#define FEATURE_XGMI_MASK (1ULL << FEATURE_XGMI_BIT ) +#define FEATURE_ECC_MASK (1ULL << FEATURE_ECC_BIT ) #define DPM_OVERRIDE_DISABLE_SOCCLK_PID 0x00000001 #define DPM_OVERRIDE_DISABLE_UCLK_PID 0x00000002 diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c index a63e5f0dae56..ab7968c8f6a2 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c @@ -1037,6 +1037,35 @@ void dw_hdmi_phy_i2c_write(struct dw_hdmi *hdmi, unsigned short data, } EXPORT_SYMBOL_GPL(dw_hdmi_phy_i2c_write); +/* Filter out invalid setups to avoid configuring SCDC and scrambling */ +static bool dw_hdmi_support_scdc(struct dw_hdmi *hdmi) +{ + struct drm_display_info *display = &hdmi->connector.display_info; + + /* Completely disable SCDC support for older controllers */ + if (hdmi->version < 0x200a) + return false; + + /* Disable if no DDC bus */ + if (!hdmi->ddc) + return false; + + /* Disable if SCDC is not supported, or if an HF-VSDB block is absent */ + if (!display->hdmi.scdc.supported || + !display->hdmi.scdc.scrambling.supported) + return false; + + /* + * Disable if display only support low TMDS rates and scrambling + * for low rates is not supported either + */ + if (!display->hdmi.scdc.scrambling.low_rates && + display->max_tmds_clock <= 340000) + return false; + + return true; +} + /* * HDMI2.0 Specifies the following procedure for High TMDS Bit Rates: * - The Source shall suspend transmission of the TMDS clock and data @@ -1055,7 +1084,7 @@ void dw_hdmi_set_high_tmds_clock_ratio(struct dw_hdmi *hdmi) unsigned long mtmdsclock = hdmi->hdmi_data.video_mode.mtmdsclock; /* Control for TMDS Bit Period/TMDS Clock-Period Ratio */ - if (hdmi->connector.display_info.hdmi.scdc.supported) { + if (dw_hdmi_support_scdc(hdmi)) { if (mtmdsclock > HDMI14_MAX_TMDSCLK) drm_scdc_set_high_tmds_clock_ratio(hdmi->ddc, 1); else @@ -1579,8 +1608,9 @@ static void hdmi_av_composer(struct dw_hdmi *hdmi, /* Set up HDMI_FC_INVIDCONF */ inv_val = (hdmi->hdmi_data.hdcp_enable || - vmode->mtmdsclock > HDMI14_MAX_TMDSCLK || - hdmi_info->scdc.scrambling.low_rates ? + (dw_hdmi_support_scdc(hdmi) && + (vmode->mtmdsclock > HDMI14_MAX_TMDSCLK || + hdmi_info->scdc.scrambling.low_rates)) ? HDMI_FC_INVIDCONF_HDCP_KEEPOUT_ACTIVE : HDMI_FC_INVIDCONF_HDCP_KEEPOUT_INACTIVE); @@ -1646,7 +1676,7 @@ static void hdmi_av_composer(struct dw_hdmi *hdmi, } /* Scrambling Control */ - if (hdmi_info->scdc.supported) { + if (dw_hdmi_support_scdc(hdmi)) { if (vmode->mtmdsclock > HDMI14_MAX_TMDSCLK || hdmi_info->scdc.scrambling.low_rates) { /* @@ -1658,13 +1688,13 @@ static void hdmi_av_composer(struct dw_hdmi *hdmi, * Source Devices compliant shall set the * Source Version = 1. */ - drm_scdc_readb(&hdmi->i2c->adap, SCDC_SINK_VERSION, + drm_scdc_readb(hdmi->ddc, SCDC_SINK_VERSION, &bytes); - drm_scdc_writeb(&hdmi->i2c->adap, SCDC_SOURCE_VERSION, + drm_scdc_writeb(hdmi->ddc, SCDC_SOURCE_VERSION, min_t(u8, bytes, SCDC_MIN_SOURCE_VERSION)); /* Enabled Scrambling in the Sink */ - drm_scdc_set_scrambling(&hdmi->i2c->adap, 1); + drm_scdc_set_scrambling(hdmi->ddc, 1); /* * To activate the scrambler feature, you must ensure @@ -1680,7 +1710,7 @@ static void hdmi_av_composer(struct dw_hdmi *hdmi, hdmi_writeb(hdmi, 0, HDMI_FC_SCRAMBLER_CTRL); hdmi_writeb(hdmi, (u8)~HDMI_MC_SWRSTZ_TMDSSWRST_REQ, HDMI_MC_SWRSTZ); - drm_scdc_set_scrambling(&hdmi->i2c->adap, 0); + drm_scdc_set_scrambling(hdmi->ddc, 0); } } @@ -1774,6 +1804,8 @@ static void dw_hdmi_clear_overflow(struct dw_hdmi *hdmi) * iteration for others. * The Amlogic Meson GX SoCs (v2.01a) have been identified as needing * the workaround with a single iteration. + * The Rockchip RK3288 SoC (v2.00a) and RK3328/RK3399 SoCs (v2.11a) have + * been identified as needing the workaround with a single iteration. */ switch (hdmi->version) { @@ -1782,7 +1814,9 @@ static void dw_hdmi_clear_overflow(struct dw_hdmi *hdmi) break; case 0x131a: case 0x132a: + case 0x200a: case 0x201a: + case 0x211a: case 0x212a: count = 1; break; diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 40ac19848034..fbb76332cc9f 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -1034,7 +1034,7 @@ disable_outputs(struct drm_device *dev, struct drm_atomic_state *old_state) funcs->atomic_disable(crtc, old_crtc_state); else if (funcs->disable) funcs->disable(crtc); - else + else if (funcs->dpms) funcs->dpms(crtc, DRM_MODE_DPMS_OFF); if (!(dev->irq_enabled && dev->num_crtcs)) @@ -1277,10 +1277,9 @@ void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev, if (new_crtc_state->enable) { DRM_DEBUG_ATOMIC("enabling [CRTC:%d:%s]\n", crtc->base.id, crtc->name); - if (funcs->atomic_enable) funcs->atomic_enable(crtc, old_crtc_state); - else + else if (funcs->commit) funcs->commit(crtc); } } diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index 381581b01d48..05bbc2b622fc 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -376,11 +376,7 @@ void drm_dev_unplug(struct drm_device *dev) synchronize_srcu(&drm_unplug_srcu); drm_dev_unregister(dev); - - mutex_lock(&drm_global_mutex); - if (dev->open_count == 0) - drm_dev_put(dev); - mutex_unlock(&drm_global_mutex); + drm_dev_put(dev); } EXPORT_SYMBOL(drm_dev_unplug); diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 0e9349ff2d16..af2ab640cadb 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -1963,7 +1963,7 @@ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper, best_depth = fmt->depth; } } - if (sizes.surface_depth != best_depth) { + if (sizes.surface_depth != best_depth && best_depth) { DRM_INFO("requested bpp %d, scaled depth down to %d", sizes.surface_bpp, best_depth); sizes.surface_depth = best_depth; diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c index 83a5bbca6e7e..7caa3c7ed978 100644 --- a/drivers/gpu/drm/drm_file.c +++ b/drivers/gpu/drm/drm_file.c @@ -489,11 +489,9 @@ int drm_release(struct inode *inode, struct file *filp) drm_close_helper(filp); - if (!--dev->open_count) { + if (!--dev->open_count) drm_lastclose(dev); - if (drm_dev_is_unplugged(dev)) - drm_put_dev(dev); - } + mutex_unlock(&drm_global_mutex); drm_minor_release(minor); diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index 35b4ec3f7618..3592d04c33b2 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -1441,7 +1441,7 @@ static inline int cmd_address_audit(struct parser_exec_state *s, } if (index_mode) { - if (guest_gma >= I915_GTT_PAGE_SIZE / sizeof(u64)) { + if (guest_gma >= I915_GTT_PAGE_SIZE) { ret = -EFAULT; goto err; } diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c index 035479e273be..e3f9caa7839f 100644 --- a/drivers/gpu/drm/i915/gvt/display.c +++ b/drivers/gpu/drm/i915/gvt/display.c @@ -448,7 +448,7 @@ void intel_gvt_emulate_vblank(struct intel_gvt *gvt) /** * intel_vgpu_emulate_hotplug - trigger hotplug event for vGPU * @vgpu: a vGPU - * @conncted: link state + * @connected: link state * * This function is used to trigger hotplug interrupt for vGPU * diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c index 3e7e2b80c857..69a9a1b2ea4a 100644 --- a/drivers/gpu/drm/i915/gvt/dmabuf.c +++ b/drivers/gpu/drm/i915/gvt/dmabuf.c @@ -209,7 +209,7 @@ static int vgpu_get_plane_info(struct drm_device *dev, struct drm_i915_private *dev_priv = to_i915(dev); struct intel_vgpu_primary_plane_format p; struct intel_vgpu_cursor_plane_format c; - int ret; + int ret, tile_height = 1; if (plane_id == DRM_PLANE_TYPE_PRIMARY) { ret = intel_vgpu_decode_primary_plane(vgpu, &p); @@ -228,19 +228,19 @@ static int vgpu_get_plane_info(struct drm_device *dev, break; case PLANE_CTL_TILED_X: info->drm_format_mod = I915_FORMAT_MOD_X_TILED; + tile_height = 8; break; case PLANE_CTL_TILED_Y: info->drm_format_mod = I915_FORMAT_MOD_Y_TILED; + tile_height = 32; break; case PLANE_CTL_TILED_YF: info->drm_format_mod = I915_FORMAT_MOD_Yf_TILED; + tile_height = 32; break; default: gvt_vgpu_err("invalid tiling mode: %x\n", p.tiled); } - - info->size = (((p.stride * p.height * p.bpp) / 8) + - (PAGE_SIZE - 1)) >> PAGE_SHIFT; } else if (plane_id == DRM_PLANE_TYPE_CURSOR) { ret = intel_vgpu_decode_cursor_plane(vgpu, &c); if (ret) @@ -262,14 +262,13 @@ static int vgpu_get_plane_info(struct drm_device *dev, info->x_hot = UINT_MAX; info->y_hot = UINT_MAX; } - - info->size = (((info->stride * c.height * c.bpp) / 8) - + (PAGE_SIZE - 1)) >> PAGE_SHIFT; } else { gvt_vgpu_err("invalid plane id:%d\n", plane_id); return -EINVAL; } + info->size = (info->stride * roundup(info->height, tile_height) + + PAGE_SIZE - 1) >> PAGE_SHIFT; if (info->size == 0) { gvt_vgpu_err("fb size is zero\n"); return -EINVAL; diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index c7103dd2d8d5..9814773882ec 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -750,14 +750,20 @@ static void ppgtt_free_spt(struct intel_vgpu_ppgtt_spt *spt) static void ppgtt_free_all_spt(struct intel_vgpu *vgpu) { - struct intel_vgpu_ppgtt_spt *spt; + struct intel_vgpu_ppgtt_spt *spt, *spn; struct radix_tree_iter iter; - void **slot; + LIST_HEAD(all_spt); + void __rcu **slot; + rcu_read_lock(); radix_tree_for_each_slot(slot, &vgpu->gtt.spt_tree, &iter, 0) { spt = radix_tree_deref_slot(slot); - ppgtt_free_spt(spt); + list_move(&spt->post_shadow_list, &all_spt); } + rcu_read_unlock(); + + list_for_each_entry_safe(spt, spn, &all_spt, post_shadow_list) + ppgtt_free_spt(spt); } static int ppgtt_handle_guest_write_page_table_bytes( @@ -1882,7 +1888,11 @@ struct intel_vgpu_mm *intel_vgpu_create_ppgtt_mm(struct intel_vgpu *vgpu, } list_add_tail(&mm->ppgtt_mm.list, &vgpu->gtt.ppgtt_mm_list_head); + + mutex_lock(&gvt->gtt.ppgtt_mm_lock); list_add_tail(&mm->ppgtt_mm.lru_list, &gvt->gtt.ppgtt_mm_lru_list_head); + mutex_unlock(&gvt->gtt.ppgtt_mm_lock); + return mm; } @@ -1942,7 +1952,7 @@ void _intel_vgpu_mm_release(struct kref *mm_ref) */ void intel_vgpu_unpin_mm(struct intel_vgpu_mm *mm) { - atomic_dec(&mm->pincount); + atomic_dec_if_positive(&mm->pincount); } /** @@ -1967,9 +1977,10 @@ int intel_vgpu_pin_mm(struct intel_vgpu_mm *mm) if (ret) return ret; + mutex_lock(&mm->vgpu->gvt->gtt.ppgtt_mm_lock); list_move_tail(&mm->ppgtt_mm.lru_list, &mm->vgpu->gvt->gtt.ppgtt_mm_lru_list_head); - + mutex_unlock(&mm->vgpu->gvt->gtt.ppgtt_mm_lock); } return 0; @@ -1980,6 +1991,8 @@ static int reclaim_one_ppgtt_mm(struct intel_gvt *gvt) struct intel_vgpu_mm *mm; struct list_head *pos, *n; + mutex_lock(&gvt->gtt.ppgtt_mm_lock); + list_for_each_safe(pos, n, &gvt->gtt.ppgtt_mm_lru_list_head) { mm = container_of(pos, struct intel_vgpu_mm, ppgtt_mm.lru_list); @@ -1987,9 +2000,11 @@ static int reclaim_one_ppgtt_mm(struct intel_gvt *gvt) continue; list_del_init(&mm->ppgtt_mm.lru_list); + mutex_unlock(&gvt->gtt.ppgtt_mm_lock); invalidate_ppgtt_mm(mm); return 1; } + mutex_unlock(&gvt->gtt.ppgtt_mm_lock); return 0; } @@ -2659,6 +2674,7 @@ int intel_gvt_init_gtt(struct intel_gvt *gvt) } } INIT_LIST_HEAD(&gvt->gtt.ppgtt_mm_lru_list_head); + mutex_init(&gvt->gtt.ppgtt_mm_lock); return 0; } @@ -2699,7 +2715,9 @@ void intel_vgpu_invalidate_ppgtt(struct intel_vgpu *vgpu) list_for_each_safe(pos, n, &vgpu->gtt.ppgtt_mm_list_head) { mm = container_of(pos, struct intel_vgpu_mm, ppgtt_mm.list); if (mm->type == INTEL_GVT_MM_PPGTT) { + mutex_lock(&vgpu->gvt->gtt.ppgtt_mm_lock); list_del_init(&mm->ppgtt_mm.lru_list); + mutex_unlock(&vgpu->gvt->gtt.ppgtt_mm_lock); if (mm->ppgtt_mm.shadowed) invalidate_ppgtt_mm(mm); } diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h index d8cb04cc946d..edb610dc5d86 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.h +++ b/drivers/gpu/drm/i915/gvt/gtt.h @@ -88,6 +88,7 @@ struct intel_gvt_gtt { void (*mm_free_page_table)(struct intel_vgpu_mm *mm); struct list_head oos_page_use_list_head; struct list_head oos_page_free_list_head; + struct mutex ppgtt_mm_lock; struct list_head ppgtt_mm_lru_list_head; struct page *scratch_page; diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index d5fcc447d22f..a68addf95c23 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -905,7 +905,7 @@ static inline bool intel_vgpu_in_aperture(struct intel_vgpu *vgpu, u64 off) static int intel_vgpu_aperture_rw(struct intel_vgpu *vgpu, u64 off, void *buf, unsigned long count, bool is_write) { - void *aperture_va; + void __iomem *aperture_va; if (!intel_vgpu_in_aperture(vgpu, off) || !intel_vgpu_in_aperture(vgpu, off + count)) { @@ -920,9 +920,9 @@ static int intel_vgpu_aperture_rw(struct intel_vgpu *vgpu, u64 off, return -EIO; if (is_write) - memcpy(aperture_va + offset_in_page(off), buf, count); + memcpy_toio(aperture_va + offset_in_page(off), buf, count); else - memcpy(buf, aperture_va + offset_in_page(off), count); + memcpy_fromio(buf, aperture_va + offset_in_page(off), count); io_mapping_unmap(aperture_va); diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c index 7d84cfb9051a..7902fb162d09 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.c +++ b/drivers/gpu/drm/i915/gvt/mmio_context.c @@ -132,6 +132,7 @@ static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = { {RCS, GEN9_GAMT_ECO_REG_RW_IA, 0x0, false}, /* 0x4ab0 */ {RCS, GEN9_CSFE_CHICKEN1_RCS, 0xffff, false}, /* 0x20d4 */ + {RCS, _MMIO(0x20D8), 0xffff, true}, /* 0x20d8 */ {RCS, GEN8_GARBCNTL, 0x0, false}, /* 0xb004 */ {RCS, GEN7_FF_THREAD_MODE, 0x0, false}, /* 0x20a0 */ diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index 1bb8f936fdaa..05b953793316 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -346,7 +346,7 @@ static int set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload, int i = 0; if (mm->type != INTEL_GVT_MM_PPGTT || !mm->ppgtt_mm.shadowed) - return -1; + return -EINVAL; if (mm->ppgtt_mm.root_entry_type == GTT_TYPE_PPGTT_ROOT_L4_ENTRY) { px_dma(&ppgtt->pml4) = mm->ppgtt_mm.shadow_pdps[0]; @@ -410,12 +410,6 @@ int intel_gvt_scan_and_shadow_workload(struct intel_vgpu_workload *workload) if (workload->shadow) return 0; - ret = set_context_ppgtt_from_shadow(workload, shadow_ctx); - if (ret < 0) { - gvt_vgpu_err("workload shadow ppgtt isn't ready\n"); - return ret; - } - /* pin shadow context by gvt even the shadow context will be pinned * when i915 alloc request. That is because gvt will update the guest * context from shadow context when workload is completed, and at that @@ -678,6 +672,9 @@ static int dispatch_workload(struct intel_vgpu_workload *workload) { struct intel_vgpu *vgpu = workload->vgpu; struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; + struct intel_vgpu_submission *s = &vgpu->submission; + struct i915_gem_context *shadow_ctx = s->shadow_ctx; + struct i915_request *rq; int ring_id = workload->ring_id; int ret; @@ -687,6 +684,12 @@ static int dispatch_workload(struct intel_vgpu_workload *workload) mutex_lock(&vgpu->vgpu_lock); mutex_lock(&dev_priv->drm.struct_mutex); + ret = set_context_ppgtt_from_shadow(workload, shadow_ctx); + if (ret < 0) { + gvt_vgpu_err("workload shadow ppgtt isn't ready\n"); + goto err_req; + } + ret = intel_gvt_workload_req_alloc(workload); if (ret) goto err_req; @@ -703,6 +706,14 @@ static int dispatch_workload(struct intel_vgpu_workload *workload) ret = prepare_workload(workload); out: + if (ret) { + /* We might still need to add request with + * clean ctx to retire it properly.. + */ + rq = fetch_and_zero(&workload->req); + i915_request_put(rq); + } + if (!IS_ERR_OR_NULL(workload->req)) { gvt_dbg_sched("ring id %d submit workload to i915 %p\n", ring_id, workload->req); @@ -739,7 +750,8 @@ static struct intel_vgpu_workload *pick_next_workload( goto out; } - if (list_empty(workload_q_head(scheduler->current_vgpu, ring_id))) + if (!scheduler->current_vgpu->active || + list_empty(workload_q_head(scheduler->current_vgpu, ring_id))) goto out; /* @@ -1474,8 +1486,9 @@ intel_vgpu_create_workload(struct intel_vgpu *vgpu, int ring_id, intel_runtime_pm_put_unchecked(dev_priv); } - if (ret && (vgpu_is_vm_unhealthy(ret))) { - enter_failsafe_mode(vgpu, GVT_FAILSAFE_GUEST_ERR); + if (ret) { + if (vgpu_is_vm_unhealthy(ret)) + enter_failsafe_mode(vgpu, GVT_FAILSAFE_GUEST_ERR); intel_vgpu_destroy_workload(workload); return ERR_PTR(ret); } diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 0bd890c04fe4..f6f6e5b78e97 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -4830,7 +4830,10 @@ static int i915_dsc_fec_support_show(struct seq_file *m, void *data) ret = drm_modeset_lock(&dev->mode_config.connection_mutex, &ctx); if (ret) { - ret = -EINTR; + if (ret == -EDEADLK && !drm_modeset_backoff(&ctx)) { + try_again = true; + continue; + } break; } crtc = connector->state->crtc; diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 9adc7bb9e69c..a67a63b5aa84 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -2346,7 +2346,8 @@ static inline unsigned int i915_sg_segment_size(void) INTEL_DEVID(dev_priv) == 0x5915 || \ INTEL_DEVID(dev_priv) == 0x591E) #define IS_AML_ULX(dev_priv) (INTEL_DEVID(dev_priv) == 0x591C || \ - INTEL_DEVID(dev_priv) == 0x87C0) + INTEL_DEVID(dev_priv) == 0x87C0 || \ + INTEL_DEVID(dev_priv) == 0x87CA) #define IS_SKL_GT2(dev_priv) (IS_SKYLAKE(dev_priv) && \ INTEL_INFO(dev_priv)->gt == 2) #define IS_SKL_GT3(dev_priv) (IS_SKYLAKE(dev_priv) && \ diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 638a586469f9..047855dd8c6b 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -2863,7 +2863,7 @@ enum i915_power_well_id { #define GEN11_GT_VEBOX_VDBOX_DISABLE _MMIO(0x9140) #define GEN11_GT_VDBOX_DISABLE_MASK 0xff #define GEN11_GT_VEBOX_DISABLE_SHIFT 16 -#define GEN11_GT_VEBOX_DISABLE_MASK (0xff << GEN11_GT_VEBOX_DISABLE_SHIFT) +#define GEN11_GT_VEBOX_DISABLE_MASK (0x0f << GEN11_GT_VEBOX_DISABLE_SHIFT) #define GEN11_EU_DISABLE _MMIO(0x9134) #define GEN11_EU_DIS_MASK 0xFF @@ -9243,7 +9243,7 @@ enum skl_power_gate { #define TRANS_DDI_FUNC_CTL2(tran) _MMIO_TRANS2(tran, \ _TRANS_DDI_FUNC_CTL2_A) #define PORT_SYNC_MODE_ENABLE (1 << 4) -#define PORT_SYNC_MODE_MASTER_SELECT(x) ((x) < 0) +#define PORT_SYNC_MODE_MASTER_SELECT(x) ((x) << 0) #define PORT_SYNC_MODE_MASTER_SELECT_MASK (0x7 << 0) #define PORT_SYNC_MODE_MASTER_SELECT_SHIFT 0 diff --git a/drivers/gpu/drm/i915/icl_dsi.c b/drivers/gpu/drm/i915/icl_dsi.c index 73a7bee24a66..641e0778fa9c 100644 --- a/drivers/gpu/drm/i915/icl_dsi.c +++ b/drivers/gpu/drm/i915/icl_dsi.c @@ -323,6 +323,21 @@ static void gen11_dsi_program_esc_clk_div(struct intel_encoder *encoder) } } +static void get_dsi_io_power_domains(struct drm_i915_private *dev_priv, + struct intel_dsi *intel_dsi) +{ + enum port port; + + for_each_dsi_port(port, intel_dsi->ports) { + WARN_ON(intel_dsi->io_wakeref[port]); + intel_dsi->io_wakeref[port] = + intel_display_power_get(dev_priv, + port == PORT_A ? + POWER_DOMAIN_PORT_DDI_A_IO : + POWER_DOMAIN_PORT_DDI_B_IO); + } +} + static void gen11_dsi_enable_io_power(struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); @@ -336,13 +351,7 @@ static void gen11_dsi_enable_io_power(struct intel_encoder *encoder) I915_WRITE(ICL_DSI_IO_MODECTL(port), tmp); } - for_each_dsi_port(port, intel_dsi->ports) { - intel_dsi->io_wakeref[port] = - intel_display_power_get(dev_priv, - port == PORT_A ? - POWER_DOMAIN_PORT_DDI_A_IO : - POWER_DOMAIN_PORT_DDI_B_IO); - } + get_dsi_io_power_domains(dev_priv, intel_dsi); } static void gen11_dsi_power_up_lanes(struct intel_encoder *encoder) @@ -589,6 +598,12 @@ static void gen11_dsi_map_pll(struct intel_encoder *encoder, val |= DPCLKA_CFGCR0_DDI_CLK_SEL(pll->info->id, port); } I915_WRITE(DPCLKA_CFGCR0_ICL, val); + + for_each_dsi_port(port, intel_dsi->ports) { + val &= ~DPCLKA_CFGCR0_DDI_CLK_OFF(port); + } + I915_WRITE(DPCLKA_CFGCR0_ICL, val); + POSTING_READ(DPCLKA_CFGCR0_ICL); mutex_unlock(&dev_priv->dpll_lock); @@ -1117,7 +1132,7 @@ static void gen11_dsi_disable_port(struct intel_encoder *encoder) DRM_ERROR("DDI port:%c buffer not idle\n", port_name(port)); } - gen11_dsi_ungate_clocks(encoder); + gen11_dsi_gate_clocks(encoder); } static void gen11_dsi_disable_io_power(struct intel_encoder *encoder) @@ -1218,20 +1233,11 @@ static int gen11_dsi_compute_config(struct intel_encoder *encoder, return 0; } -static u64 gen11_dsi_get_power_domains(struct intel_encoder *encoder, - struct intel_crtc_state *crtc_state) +static void gen11_dsi_get_power_domains(struct intel_encoder *encoder, + struct intel_crtc_state *crtc_state) { - struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); - u64 domains = 0; - enum port port; - - for_each_dsi_port(port, intel_dsi->ports) - if (port == PORT_A) - domains |= BIT_ULL(POWER_DOMAIN_PORT_DDI_A_IO); - else - domains |= BIT_ULL(POWER_DOMAIN_PORT_DDI_B_IO); - - return domains; + get_dsi_io_power_domains(to_i915(encoder->base.dev), + enc_to_intel_dsi(&encoder->base)); } static bool gen11_dsi_get_hw_state(struct intel_encoder *encoder, diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 14d580cdefd3..98cea1f4b3bf 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -2075,12 +2075,11 @@ intel_ddi_main_link_aux_domain(struct intel_digital_port *dig_port) intel_aux_power_domain(dig_port); } -static u64 intel_ddi_get_power_domains(struct intel_encoder *encoder, - struct intel_crtc_state *crtc_state) +static void intel_ddi_get_power_domains(struct intel_encoder *encoder, + struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); struct intel_digital_port *dig_port; - u64 domains; /* * TODO: Add support for MST encoders. Atm, the following should never @@ -2088,10 +2087,10 @@ static u64 intel_ddi_get_power_domains(struct intel_encoder *encoder, * hook. */ if (WARN_ON(intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST))) - return 0; + return; dig_port = enc_to_dig_port(&encoder->base); - domains = BIT_ULL(dig_port->ddi_io_power_domain); + intel_display_power_get(dev_priv, dig_port->ddi_io_power_domain); /* * AUX power is only needed for (e)DP mode, and for HDMI mode on TC @@ -2099,15 +2098,15 @@ static u64 intel_ddi_get_power_domains(struct intel_encoder *encoder, */ if (intel_crtc_has_dp_encoder(crtc_state) || intel_port_is_tc(dev_priv, encoder->port)) - domains |= BIT_ULL(intel_ddi_main_link_aux_domain(dig_port)); + intel_display_power_get(dev_priv, + intel_ddi_main_link_aux_domain(dig_port)); /* * VDSC power is needed when DSC is enabled */ if (crtc_state->dsc_params.compression_enable) - domains |= BIT_ULL(intel_dsc_power_domain(crtc_state)); - - return domains; + intel_display_power_get(dev_priv, + intel_dsc_power_domain(crtc_state)); } void intel_ddi_enable_pipe_clock(const struct intel_crtc_state *crtc_state) @@ -2825,10 +2824,10 @@ void icl_sanitize_encoder_pll_mapping(struct intel_encoder *encoder) return; } /* - * DSI ports should have their DDI clock ungated when disabled - * and gated when enabled. + * For DSI we keep the ddi clocks gated + * except during enable/disable sequence. */ - ddi_clk_needed = !encoder->base.crtc; + ddi_clk_needed = false; } val = I915_READ(DPCLKA_CFGCR0_ICL); @@ -3863,14 +3862,16 @@ static int intel_ddi_compute_config(struct intel_encoder *encoder, ret = intel_hdmi_compute_config(encoder, pipe_config, conn_state); else ret = intel_dp_compute_config(encoder, pipe_config, conn_state); + if (ret) + return ret; - if (IS_GEN9_LP(dev_priv) && ret) + if (IS_GEN9_LP(dev_priv)) pipe_config->lane_lat_optim_mask = bxt_ddi_phy_calc_lane_lat_optim_mask(pipe_config->lane_count); intel_ddi_compute_min_voltage_level(dev_priv, pipe_config); - return ret; + return 0; } diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index ccb616351bba..421aac80a838 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -15986,8 +15986,6 @@ get_encoder_power_domains(struct drm_i915_private *dev_priv) struct intel_encoder *encoder; for_each_intel_encoder(&dev_priv->drm, encoder) { - u64 get_domains; - enum intel_display_power_domain domain; struct intel_crtc_state *crtc_state; if (!encoder->get_power_domains) @@ -16001,9 +15999,7 @@ get_encoder_power_domains(struct drm_i915_private *dev_priv) continue; crtc_state = to_intel_crtc_state(encoder->base.crtc->state); - get_domains = encoder->get_power_domains(encoder, crtc_state); - for_each_power_domain(domain, get_domains) - intel_display_power_get(dev_priv, domain); + encoder->get_power_domains(encoder, crtc_state); } } diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index cf709835fb9a..48da4a969a0a 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -1859,42 +1859,6 @@ intel_dp_compute_link_config_wide(struct intel_dp *intel_dp, return -EINVAL; } -/* Optimize link config in order: max bpp, min lanes, min clock */ -static int -intel_dp_compute_link_config_fast(struct intel_dp *intel_dp, - struct intel_crtc_state *pipe_config, - const struct link_config_limits *limits) -{ - struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode; - int bpp, clock, lane_count; - int mode_rate, link_clock, link_avail; - - for (bpp = limits->max_bpp; bpp >= limits->min_bpp; bpp -= 2 * 3) { - mode_rate = intel_dp_link_required(adjusted_mode->crtc_clock, - bpp); - - for (lane_count = limits->min_lane_count; - lane_count <= limits->max_lane_count; - lane_count <<= 1) { - for (clock = limits->min_clock; clock <= limits->max_clock; clock++) { - link_clock = intel_dp->common_rates[clock]; - link_avail = intel_dp_max_data_rate(link_clock, - lane_count); - - if (mode_rate <= link_avail) { - pipe_config->lane_count = lane_count; - pipe_config->pipe_bpp = bpp; - pipe_config->port_clock = link_clock; - - return 0; - } - } - } - } - - return -EINVAL; -} - static int intel_dp_dsc_compute_bpp(struct intel_dp *intel_dp, u8 dsc_max_bpc) { int i, num_bpc; @@ -1922,6 +1886,9 @@ static int intel_dp_dsc_compute_config(struct intel_dp *intel_dp, int pipe_bpp; int ret; + pipe_config->fec_enable = !intel_dp_is_edp(intel_dp) && + intel_dp_supports_fec(intel_dp, pipe_config); + if (!intel_dp_supports_dsc(intel_dp, pipe_config)) return -EINVAL; @@ -2031,15 +1998,13 @@ intel_dp_compute_link_config(struct intel_encoder *encoder, limits.min_bpp = 6 * 3; limits.max_bpp = intel_dp_compute_bpp(intel_dp, pipe_config); - if (intel_dp_is_edp(intel_dp) && intel_dp->edp_dpcd[0] < DP_EDP_14) { + if (intel_dp_is_edp(intel_dp)) { /* * Use the maximum clock and number of lanes the eDP panel - * advertizes being capable of. The eDP 1.3 and earlier panels - * are generally designed to support only a single clock and - * lane configuration, and typically these values correspond to - * the native resolution of the panel. With eDP 1.4 rate select - * and DSC, this is decreasingly the case, and we need to be - * able to select less than maximum link config. + * advertizes being capable of. The panels are generally + * designed to support only a single clock and lane + * configuration, and typically these values correspond to the + * native resolution of the panel. */ limits.min_lane_count = limits.max_lane_count; limits.min_clock = limits.max_clock; @@ -2053,22 +2018,11 @@ intel_dp_compute_link_config(struct intel_encoder *encoder, intel_dp->common_rates[limits.max_clock], limits.max_bpp, adjusted_mode->crtc_clock); - if (intel_dp_is_edp(intel_dp)) - /* - * Optimize for fast and narrow. eDP 1.3 section 3.3 and eDP 1.4 - * section A.1: "It is recommended that the minimum number of - * lanes be used, using the minimum link rate allowed for that - * lane configuration." - * - * Note that we use the max clock and lane count for eDP 1.3 and - * earlier, and fast vs. wide is irrelevant. - */ - ret = intel_dp_compute_link_config_fast(intel_dp, pipe_config, - &limits); - else - /* Optimize for slow and wide. */ - ret = intel_dp_compute_link_config_wide(intel_dp, pipe_config, - &limits); + /* + * Optimize for slow and wide. This is the place to add alternative + * optimization policy. + */ + ret = intel_dp_compute_link_config_wide(intel_dp, pipe_config, &limits); /* enable compression if the mode doesn't fit available BW */ DRM_DEBUG_KMS("Force DSC en = %d\n", intel_dp->force_dsc_en); @@ -2165,9 +2119,6 @@ intel_dp_compute_config(struct intel_encoder *encoder, if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK) return -EINVAL; - pipe_config->fec_enable = !intel_dp_is_edp(intel_dp) && - intel_dp_supports_fec(intel_dp, pipe_config); - ret = intel_dp_compute_link_config(encoder, pipe_config, conn_state); if (ret < 0) return ret; diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 15db41394b9e..d5660ac1b0d6 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -270,10 +270,12 @@ struct intel_encoder { * be set correctly before calling this function. */ void (*get_config)(struct intel_encoder *, struct intel_crtc_state *pipe_config); - /* Returns a mask of power domains that need to be referenced as part - * of the hardware state readout code. */ - u64 (*get_power_domains)(struct intel_encoder *encoder, - struct intel_crtc_state *crtc_state); + /* + * Acquires the power domains needed for an active encoder during + * hardware state readout. + */ + void (*get_power_domains)(struct intel_encoder *encoder, + struct intel_crtc_state *crtc_state); /* * Called during system suspend after all pending requests for the * encoder are flushed (for example for DP AUX transactions) and diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c index e8f694b57b8a..376ffe842e26 100644 --- a/drivers/gpu/drm/i915/intel_fbdev.c +++ b/drivers/gpu/drm/i915/intel_fbdev.c @@ -338,8 +338,8 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper, bool *enabled, int width, int height) { struct drm_i915_private *dev_priv = to_i915(fb_helper->dev); + unsigned long conn_configured, conn_seq, mask; unsigned int count = min(fb_helper->connector_count, BITS_PER_LONG); - unsigned long conn_configured, conn_seq; int i, j; bool *save_enabled; bool fallback = true, ret = true; @@ -357,9 +357,10 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper, drm_modeset_backoff(&ctx); memcpy(save_enabled, enabled, count); - conn_seq = GENMASK(count - 1, 0); + mask = GENMASK(count - 1, 0); conn_configured = 0; retry: + conn_seq = conn_configured; for (i = 0; i < count; i++) { struct drm_fb_helper_connector *fb_conn; struct drm_connector *connector; @@ -372,8 +373,7 @@ retry: if (conn_configured & BIT(i)) continue; - /* First pass, only consider tiled connectors */ - if (conn_seq == GENMASK(count - 1, 0) && !connector->has_tile) + if (conn_seq == 0 && !connector->has_tile) continue; if (connector->status == connector_status_connected) @@ -477,10 +477,8 @@ retry: conn_configured |= BIT(i); } - if (conn_configured != conn_seq) { /* repeat until no more are found */ - conn_seq = conn_configured; + if ((conn_configured & mask) != mask && conn_configured != conn_seq) goto retry; - } /* * If the BIOS didn't enable everything it could, fall back to have the diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c index 32dce7176f63..b9b0ea4e2404 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c @@ -455,7 +455,7 @@ static int igt_evict_contexts(void *arg) struct i915_gem_context *ctx; ctx = live_context(i915, file); - if (!ctx) + if (IS_ERR(ctx)) break; /* We will need some GGTT space for the rq's context */ diff --git a/drivers/gpu/drm/i915/vlv_dsi.c b/drivers/gpu/drm/i915/vlv_dsi.c index 6403728fe778..31c93c3ccd00 100644 --- a/drivers/gpu/drm/i915/vlv_dsi.c +++ b/drivers/gpu/drm/i915/vlv_dsi.c @@ -256,6 +256,28 @@ static void band_gap_reset(struct drm_i915_private *dev_priv) mutex_unlock(&dev_priv->sb_lock); } +static int bdw_get_pipemisc_bpp(struct intel_crtc *crtc) +{ + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + u32 tmp; + + tmp = I915_READ(PIPEMISC(crtc->pipe)); + + switch (tmp & PIPEMISC_DITHER_BPC_MASK) { + case PIPEMISC_DITHER_6_BPC: + return 18; + case PIPEMISC_DITHER_8_BPC: + return 24; + case PIPEMISC_DITHER_10_BPC: + return 30; + case PIPEMISC_DITHER_12_BPC: + return 36; + default: + MISSING_CASE(tmp); + return 0; + } +} + static int intel_dsi_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config, struct drm_connector_state *conn_state) @@ -1071,6 +1093,8 @@ static void bxt_dsi_get_pipe_config(struct intel_encoder *encoder, bpp = mipi_dsi_pixel_format_to_bpp( pixel_format_from_register_bits(fmt)); + pipe_config->pipe_bpp = bdw_get_pipemisc_bpp(crtc); + /* Enable Frame time stamo based scanline reporting */ adjusted_mode->private_flags |= I915_MODE_FLAG_GET_SCANLINE_FROM_TIMESTAMP; diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c index ec3602ebbc1c..54011df8c2e8 100644 --- a/drivers/gpu/drm/imx/ipuv3-crtc.c +++ b/drivers/gpu/drm/imx/ipuv3-crtc.c @@ -71,7 +71,7 @@ static void ipu_crtc_disable_planes(struct ipu_crtc *ipu_crtc, if (disable_partial) ipu_plane_disable(ipu_crtc->plane[1], true); if (disable_full) - ipu_plane_disable(ipu_crtc->plane[0], false); + ipu_plane_disable(ipu_crtc->plane[0], true); } static void ipu_crtc_atomic_disable(struct drm_crtc *crtc, diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c index 22e68a100e7b..5d333138f913 100644 --- a/drivers/gpu/drm/mediatek/mtk_dpi.c +++ b/drivers/gpu/drm/mediatek/mtk_dpi.c @@ -662,13 +662,11 @@ static unsigned int mt8173_calculate_factor(int clock) static unsigned int mt2701_calculate_factor(int clock) { if (clock <= 64000) - return 16; - else if (clock <= 128000) - return 8; - else if (clock <= 256000) return 4; - else + else if (clock <= 128000) return 2; + else + return 1; } static const struct mtk_dpi_conf mt8173_conf = { diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index cf59ea9bccfd..57ce4708ef1b 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -15,6 +15,7 @@ #include <drm/drmP.h> #include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> +#include <drm/drm_fb_helper.h> #include <drm/drm_gem.h> #include <drm/drm_gem_cma_helper.h> #include <drm/drm_of.h> @@ -341,6 +342,8 @@ static struct drm_driver mtk_drm_driver = { .gem_prime_get_sg_table = mtk_gem_prime_get_sg_table, .gem_prime_import_sg_table = mtk_gem_prime_import_sg_table, .gem_prime_mmap = mtk_drm_gem_mmap_buf, + .gem_prime_vmap = mtk_drm_gem_prime_vmap, + .gem_prime_vunmap = mtk_drm_gem_prime_vunmap, .fops = &mtk_drm_fops, .name = DRIVER_NAME, @@ -376,6 +379,10 @@ static int mtk_drm_bind(struct device *dev) if (ret < 0) goto err_deinit; + ret = drm_fbdev_generic_setup(drm, 32); + if (ret) + DRM_ERROR("Failed to initialize fbdev: %d\n", ret); + return 0; err_deinit: diff --git a/drivers/gpu/drm/mediatek/mtk_drm_gem.c b/drivers/gpu/drm/mediatek/mtk_drm_gem.c index 259b7b0de1d2..38483e9ee071 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_gem.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_gem.c @@ -241,3 +241,49 @@ err_gem_free: kfree(mtk_gem); return ERR_PTR(ret); } + +void *mtk_drm_gem_prime_vmap(struct drm_gem_object *obj) +{ + struct mtk_drm_gem_obj *mtk_gem = to_mtk_gem_obj(obj); + struct sg_table *sgt; + struct sg_page_iter iter; + unsigned int npages; + unsigned int i = 0; + + if (mtk_gem->kvaddr) + return mtk_gem->kvaddr; + + sgt = mtk_gem_prime_get_sg_table(obj); + if (IS_ERR(sgt)) + return NULL; + + npages = obj->size >> PAGE_SHIFT; + mtk_gem->pages = kcalloc(npages, sizeof(*mtk_gem->pages), GFP_KERNEL); + if (!mtk_gem->pages) + goto out; + + for_each_sg_page(sgt->sgl, &iter, sgt->orig_nents, 0) { + mtk_gem->pages[i++] = sg_page_iter_page(&iter); + if (i > npages) + break; + } + mtk_gem->kvaddr = vmap(mtk_gem->pages, npages, VM_MAP, + pgprot_writecombine(PAGE_KERNEL)); + +out: + kfree((void *)sgt); + + return mtk_gem->kvaddr; +} + +void mtk_drm_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr) +{ + struct mtk_drm_gem_obj *mtk_gem = to_mtk_gem_obj(obj); + + if (!mtk_gem->pages) + return; + + vunmap(vaddr); + mtk_gem->kvaddr = 0; + kfree((void *)mtk_gem->pages); +} diff --git a/drivers/gpu/drm/mediatek/mtk_drm_gem.h b/drivers/gpu/drm/mediatek/mtk_drm_gem.h index 534639b43a1c..c047a7ef294f 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_gem.h +++ b/drivers/gpu/drm/mediatek/mtk_drm_gem.h @@ -37,6 +37,7 @@ struct mtk_drm_gem_obj { dma_addr_t dma_addr; unsigned long dma_attrs; struct sg_table *sg; + struct page **pages; }; #define to_mtk_gem_obj(x) container_of(x, struct mtk_drm_gem_obj, base) @@ -52,5 +53,7 @@ int mtk_drm_gem_mmap_buf(struct drm_gem_object *obj, struct sg_table *mtk_gem_prime_get_sg_table(struct drm_gem_object *obj); struct drm_gem_object *mtk_gem_prime_import_sg_table(struct drm_device *dev, struct dma_buf_attachment *attach, struct sg_table *sg); +void *mtk_drm_gem_prime_vmap(struct drm_gem_object *obj); +void mtk_drm_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr); #endif diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c index 915cc84621ae..e04e6c293d39 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c @@ -1480,7 +1480,6 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi, if (IS_ERR(regmap)) ret = PTR_ERR(regmap); if (ret) { - ret = PTR_ERR(regmap); dev_err(dev, "Failed to get system configuration registers: %d\n", ret); @@ -1516,6 +1515,7 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi, of_node_put(remote); hdmi->ddc_adpt = of_find_i2c_adapter_by_node(i2c_np); + of_node_put(i2c_np); if (!hdmi->ddc_adpt) { dev_err(dev, "Failed to get ddc i2c adapter by node\n"); return -EINVAL; diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi_phy.c b/drivers/gpu/drm/mediatek/mtk_hdmi_phy.c index 4ef9c57ffd44..5223498502c4 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi_phy.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi_phy.c @@ -15,28 +15,6 @@ static const struct phy_ops mtk_hdmi_phy_dev_ops = { .owner = THIS_MODULE, }; -long mtk_hdmi_pll_round_rate(struct clk_hw *hw, unsigned long rate, - unsigned long *parent_rate) -{ - struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw); - - hdmi_phy->pll_rate = rate; - if (rate <= 74250000) - *parent_rate = rate; - else - *parent_rate = rate / 2; - - return rate; -} - -unsigned long mtk_hdmi_pll_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) -{ - struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw); - - return hdmi_phy->pll_rate; -} - void mtk_hdmi_phy_clear_bits(struct mtk_hdmi_phy *hdmi_phy, u32 offset, u32 bits) { @@ -110,13 +88,11 @@ mtk_hdmi_phy_dev_get_ops(const struct mtk_hdmi_phy *hdmi_phy) return NULL; } -static void mtk_hdmi_phy_clk_get_ops(struct mtk_hdmi_phy *hdmi_phy, - const struct clk_ops **ops) +static void mtk_hdmi_phy_clk_get_data(struct mtk_hdmi_phy *hdmi_phy, + struct clk_init_data *clk_init) { - if (hdmi_phy && hdmi_phy->conf && hdmi_phy->conf->hdmi_phy_clk_ops) - *ops = hdmi_phy->conf->hdmi_phy_clk_ops; - else - dev_err(hdmi_phy->dev, "Failed to get clk ops of phy\n"); + clk_init->flags = hdmi_phy->conf->flags; + clk_init->ops = hdmi_phy->conf->hdmi_phy_clk_ops; } static int mtk_hdmi_phy_probe(struct platform_device *pdev) @@ -129,7 +105,6 @@ static int mtk_hdmi_phy_probe(struct platform_device *pdev) struct clk_init_data clk_init = { .num_parents = 1, .parent_names = (const char * const *)&ref_clk_name, - .flags = CLK_SET_RATE_PARENT | CLK_SET_RATE_GATE, }; struct phy *phy; @@ -167,7 +142,7 @@ static int mtk_hdmi_phy_probe(struct platform_device *pdev) hdmi_phy->dev = dev; hdmi_phy->conf = (struct mtk_hdmi_phy_conf *)of_device_get_match_data(dev); - mtk_hdmi_phy_clk_get_ops(hdmi_phy, &clk_init.ops); + mtk_hdmi_phy_clk_get_data(hdmi_phy, &clk_init); hdmi_phy->pll_hw.init = &clk_init; hdmi_phy->pll = devm_clk_register(dev, &hdmi_phy->pll_hw); if (IS_ERR(hdmi_phy->pll)) { diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi_phy.h b/drivers/gpu/drm/mediatek/mtk_hdmi_phy.h index f39b1fc66612..2d8b3182470d 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi_phy.h +++ b/drivers/gpu/drm/mediatek/mtk_hdmi_phy.h @@ -21,6 +21,7 @@ struct mtk_hdmi_phy; struct mtk_hdmi_phy_conf { bool tz_disabled; + unsigned long flags; const struct clk_ops *hdmi_phy_clk_ops; void (*hdmi_phy_enable_tmds)(struct mtk_hdmi_phy *hdmi_phy); void (*hdmi_phy_disable_tmds)(struct mtk_hdmi_phy *hdmi_phy); @@ -48,10 +49,6 @@ void mtk_hdmi_phy_set_bits(struct mtk_hdmi_phy *hdmi_phy, u32 offset, void mtk_hdmi_phy_mask(struct mtk_hdmi_phy *hdmi_phy, u32 offset, u32 val, u32 mask); struct mtk_hdmi_phy *to_mtk_hdmi_phy(struct clk_hw *hw); -long mtk_hdmi_pll_round_rate(struct clk_hw *hw, unsigned long rate, - unsigned long *parent_rate); -unsigned long mtk_hdmi_pll_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate); extern struct platform_driver mtk_hdmi_phy_driver; extern struct mtk_hdmi_phy_conf mtk_hdmi_phy_8173_conf; diff --git a/drivers/gpu/drm/mediatek/mtk_mt2701_hdmi_phy.c b/drivers/gpu/drm/mediatek/mtk_mt2701_hdmi_phy.c index fcc42dc6ea7f..d3cc4022e988 100644 --- a/drivers/gpu/drm/mediatek/mtk_mt2701_hdmi_phy.c +++ b/drivers/gpu/drm/mediatek/mtk_mt2701_hdmi_phy.c @@ -79,7 +79,6 @@ static int mtk_hdmi_pll_prepare(struct clk_hw *hw) mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SLDO_MASK); usleep_range(80, 100); mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_MBIAS_LPF_EN); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_TX_POSDIV); mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SER_MASK); mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_PRED_MASK); mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_DRV_MASK); @@ -94,7 +93,6 @@ static void mtk_hdmi_pll_unprepare(struct clk_hw *hw) mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_DRV_MASK); mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_PRED_MASK); mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SER_MASK); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_TX_POSDIV); mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_MBIAS_LPF_EN); usleep_range(80, 100); mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SLDO_MASK); @@ -108,6 +106,12 @@ static void mtk_hdmi_pll_unprepare(struct clk_hw *hw) usleep_range(80, 100); } +static long mtk_hdmi_pll_round_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *parent_rate) +{ + return rate; +} + static int mtk_hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate, unsigned long parent_rate) { @@ -116,13 +120,14 @@ static int mtk_hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate, if (rate <= 64000000) pos_div = 3; - else if (rate <= 12800000) - pos_div = 1; + else if (rate <= 128000000) + pos_div = 2; else pos_div = 1; mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON6, RG_HTPLL_PREDIV_MASK); mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON6, RG_HTPLL_POSDIV_MASK); + mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_TX_POSDIV); mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON6, (0x1 << RG_HTPLL_IC), RG_HTPLL_IC_MASK); mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON6, (0x1 << RG_HTPLL_IR), @@ -154,6 +159,39 @@ static int mtk_hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate, return 0; } +static unsigned long mtk_hdmi_pll_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw); + unsigned long out_rate, val; + + val = (readl(hdmi_phy->regs + HDMI_CON6) + & RG_HTPLL_PREDIV_MASK) >> RG_HTPLL_PREDIV; + switch (val) { + case 0x00: + out_rate = parent_rate; + break; + case 0x01: + out_rate = parent_rate / 2; + break; + default: + out_rate = parent_rate / 4; + break; + } + + val = (readl(hdmi_phy->regs + HDMI_CON6) + & RG_HTPLL_FBKDIV_MASK) >> RG_HTPLL_FBKDIV; + out_rate *= (val + 1) * 2; + val = (readl(hdmi_phy->regs + HDMI_CON2) + & RG_HDMITX_TX_POSDIV_MASK); + out_rate >>= (val >> RG_HDMITX_TX_POSDIV); + + if (readl(hdmi_phy->regs + HDMI_CON2) & RG_HDMITX_EN_TX_POSDIV) + out_rate /= 5; + + return out_rate; +} + static const struct clk_ops mtk_hdmi_phy_pll_ops = { .prepare = mtk_hdmi_pll_prepare, .unprepare = mtk_hdmi_pll_unprepare, @@ -174,7 +212,6 @@ static void mtk_hdmi_phy_enable_tmds(struct mtk_hdmi_phy *hdmi_phy) mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SLDO_MASK); usleep_range(80, 100); mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_MBIAS_LPF_EN); - mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_TX_POSDIV); mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SER_MASK); mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_PRED_MASK); mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_DRV_MASK); @@ -186,7 +223,6 @@ static void mtk_hdmi_phy_disable_tmds(struct mtk_hdmi_phy *hdmi_phy) mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_DRV_MASK); mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_PRED_MASK); mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SER_MASK); - mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_TX_POSDIV); mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_MBIAS_LPF_EN); usleep_range(80, 100); mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SLDO_MASK); @@ -202,6 +238,7 @@ static void mtk_hdmi_phy_disable_tmds(struct mtk_hdmi_phy *hdmi_phy) struct mtk_hdmi_phy_conf mtk_hdmi_phy_2701_conf = { .tz_disabled = true, + .flags = CLK_SET_RATE_GATE, .hdmi_phy_clk_ops = &mtk_hdmi_phy_pll_ops, .hdmi_phy_enable_tmds = mtk_hdmi_phy_enable_tmds, .hdmi_phy_disable_tmds = mtk_hdmi_phy_disable_tmds, diff --git a/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c b/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c index ed5916b27658..47f8a2951682 100644 --- a/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c +++ b/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c @@ -199,6 +199,20 @@ static void mtk_hdmi_pll_unprepare(struct clk_hw *hw) usleep_range(100, 150); } +static long mtk_hdmi_pll_round_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *parent_rate) +{ + struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw); + + hdmi_phy->pll_rate = rate; + if (rate <= 74250000) + *parent_rate = rate; + else + *parent_rate = rate / 2; + + return rate; +} + static int mtk_hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate, unsigned long parent_rate) { @@ -285,6 +299,14 @@ static int mtk_hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate, return 0; } +static unsigned long mtk_hdmi_pll_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw); + + return hdmi_phy->pll_rate; +} + static const struct clk_ops mtk_hdmi_phy_pll_ops = { .prepare = mtk_hdmi_pll_prepare, .unprepare = mtk_hdmi_pll_unprepare, @@ -309,6 +331,7 @@ static void mtk_hdmi_phy_disable_tmds(struct mtk_hdmi_phy *hdmi_phy) } struct mtk_hdmi_phy_conf mtk_hdmi_phy_8173_conf = { + .flags = CLK_SET_RATE_PARENT | CLK_SET_RATE_GATE, .hdmi_phy_clk_ops = &mtk_hdmi_phy_pll_ops, .hdmi_phy_enable_tmds = mtk_hdmi_phy_enable_tmds, .hdmi_phy_disable_tmds = mtk_hdmi_phy_disable_tmds, diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c index 2281ed3eb774..8a4ebcb6405c 100644 --- a/drivers/gpu/drm/meson/meson_drv.c +++ b/drivers/gpu/drm/meson/meson_drv.c @@ -337,12 +337,14 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) ret = drm_dev_register(drm, 0); if (ret) - goto free_drm; + goto uninstall_irq; drm_fbdev_generic_setup(drm, 32); return 0; +uninstall_irq: + drm_irq_uninstall(drm); free_drm: drm_dev_put(drm); @@ -356,8 +358,8 @@ static int meson_drv_bind(struct device *dev) static void meson_drv_unbind(struct device *dev) { - struct drm_device *drm = dev_get_drvdata(dev); - struct meson_drm *priv = drm->dev_private; + struct meson_drm *priv = dev_get_drvdata(dev); + struct drm_device *drm = priv->drm; if (priv->canvas) { meson_canvas_free(priv->canvas, priv->canvas_id_osd1); @@ -367,6 +369,7 @@ static void meson_drv_unbind(struct device *dev) } drm_dev_unregister(drm); + drm_irq_uninstall(drm); drm_kms_helper_poll_fini(drm); drm_mode_config_cleanup(drm); drm_dev_put(drm); diff --git a/drivers/gpu/drm/meson/meson_dw_hdmi.c b/drivers/gpu/drm/meson/meson_dw_hdmi.c index e28814f4ea6c..563953ec6ad0 100644 --- a/drivers/gpu/drm/meson/meson_dw_hdmi.c +++ b/drivers/gpu/drm/meson/meson_dw_hdmi.c @@ -569,7 +569,8 @@ dw_hdmi_mode_valid(struct drm_connector *connector, DRM_DEBUG_DRIVER("Modeline " DRM_MODE_FMT "\n", DRM_MODE_ARG(mode)); /* If sink max TMDS clock, we reject the mode */ - if (mode->clock > connector->display_info.max_tmds_clock) + if (connector->display_info.max_tmds_clock && + mode->clock > connector->display_info.max_tmds_clock) return MODE_BAD; /* Check against non-VIC supported modes */ diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi4_cec.c b/drivers/gpu/drm/omapdrm/dss/hdmi4_cec.c index 340383150fb9..ebf9c96d43ee 100644 --- a/drivers/gpu/drm/omapdrm/dss/hdmi4_cec.c +++ b/drivers/gpu/drm/omapdrm/dss/hdmi4_cec.c @@ -175,6 +175,7 @@ static int hdmi_cec_adap_enable(struct cec_adapter *adap, bool enable) REG_FLD_MOD(core->base, HDMI_CORE_SYS_INTR_UNMASK4, 0, 3, 3); hdmi_wp_clear_irqenable(core->wp, HDMI_IRQ_CORE); hdmi_wp_set_irqstatus(core->wp, HDMI_IRQ_CORE); + REG_FLD_MOD(core->wp->base, HDMI_WP_CLK, 0, 5, 0); hdmi4_core_disable(core); return 0; } @@ -182,16 +183,24 @@ static int hdmi_cec_adap_enable(struct cec_adapter *adap, bool enable) if (err) return err; + /* + * Initialize CEC clock divider: CEC needs 2MHz clock hence + * set the divider to 24 to get 48/24=2MHz clock + */ + REG_FLD_MOD(core->wp->base, HDMI_WP_CLK, 0x18, 5, 0); + /* Clear TX FIFO */ if (!hdmi_cec_clear_tx_fifo(adap)) { pr_err("cec-%s: could not clear TX FIFO\n", adap->name); - return -EIO; + err = -EIO; + goto err_disable_clk; } /* Clear RX FIFO */ if (!hdmi_cec_clear_rx_fifo(adap)) { pr_err("cec-%s: could not clear RX FIFO\n", adap->name); - return -EIO; + err = -EIO; + goto err_disable_clk; } /* Clear CEC interrupts */ @@ -236,6 +245,12 @@ static int hdmi_cec_adap_enable(struct cec_adapter *adap, bool enable) hdmi_write_reg(core->base, HDMI_CEC_INT_STATUS_1, temp); } return 0; + +err_disable_clk: + REG_FLD_MOD(core->wp->base, HDMI_WP_CLK, 0, 5, 0); + hdmi4_core_disable(core); + + return err; } static int hdmi_cec_adap_log_addr(struct cec_adapter *adap, u8 log_addr) @@ -333,11 +348,8 @@ int hdmi4_cec_init(struct platform_device *pdev, struct hdmi_core_data *core, return ret; core->wp = wp; - /* - * Initialize CEC clock divider: CEC needs 2MHz clock hence - * set the devider to 24 to get 48/24=2MHz clock - */ - REG_FLD_MOD(core->wp->base, HDMI_WP_CLK, 0x18, 5, 0); + /* Disable clock initially, hdmi_cec_adap_enable() manages it */ + REG_FLD_MOD(core->wp->base, HDMI_WP_CLK, 0, 5, 0); ret = cec_register_adapter(core->adap, &pdev->dev); if (ret < 0) { diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c b/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c index 813ba42f2753..e384b95ad857 100644 --- a/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c +++ b/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c @@ -708,7 +708,7 @@ int hdmi4_audio_config(struct hdmi_core_data *core, struct hdmi_wp_data *wp, else acore.i2s_cfg.justification = HDMI_AUDIO_JUSTIFY_RIGHT; /* - * The I2S input word length is twice the lenght given in the IEC-60958 + * The I2S input word length is twice the length given in the IEC-60958 * status word. If the word size is greater than * 20 bits, increment by one. */ diff --git a/drivers/gpu/drm/qxl/qxl_drv.c b/drivers/gpu/drm/qxl/qxl_drv.c index 578d867a81d5..f33e349c4ec5 100644 --- a/drivers/gpu/drm/qxl/qxl_drv.c +++ b/drivers/gpu/drm/qxl/qxl_drv.c @@ -255,10 +255,14 @@ static struct drm_driver qxl_driver = { #if defined(CONFIG_DEBUG_FS) .debugfs_init = qxl_debugfs_init, #endif + .prime_handle_to_fd = drm_gem_prime_handle_to_fd, + .prime_fd_to_handle = drm_gem_prime_fd_to_handle, .gem_prime_export = drm_gem_prime_export, .gem_prime_import = drm_gem_prime_import, .gem_prime_pin = qxl_gem_prime_pin, .gem_prime_unpin = qxl_gem_prime_unpin, + .gem_prime_get_sg_table = qxl_gem_prime_get_sg_table, + .gem_prime_import_sg_table = qxl_gem_prime_import_sg_table, .gem_prime_vmap = qxl_gem_prime_vmap, .gem_prime_vunmap = qxl_gem_prime_vunmap, .gem_prime_mmap = qxl_gem_prime_mmap, diff --git a/drivers/gpu/drm/qxl/qxl_prime.c b/drivers/gpu/drm/qxl/qxl_prime.c index 8b448eca1cd9..114653b471c6 100644 --- a/drivers/gpu/drm/qxl/qxl_prime.c +++ b/drivers/gpu/drm/qxl/qxl_prime.c @@ -42,6 +42,18 @@ void qxl_gem_prime_unpin(struct drm_gem_object *obj) qxl_bo_unpin(bo); } +struct sg_table *qxl_gem_prime_get_sg_table(struct drm_gem_object *obj) +{ + return ERR_PTR(-ENOSYS); +} + +struct drm_gem_object *qxl_gem_prime_import_sg_table( + struct drm_device *dev, struct dma_buf_attachment *attach, + struct sg_table *table) +{ + return ERR_PTR(-ENOSYS); +} + void *qxl_gem_prime_vmap(struct drm_gem_object *obj) { struct qxl_bo *bo = gem_to_qxl_bo(obj); diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index c7d4c6073ea5..0d4ade9d4722 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -541,6 +541,18 @@ static void vop_core_clks_disable(struct vop *vop) clk_disable(vop->hclk); } +static void vop_win_disable(struct vop *vop, const struct vop_win_data *win) +{ + if (win->phy->scl && win->phy->scl->ext) { + VOP_SCL_SET_EXT(vop, win, yrgb_hor_scl_mode, SCALE_NONE); + VOP_SCL_SET_EXT(vop, win, yrgb_ver_scl_mode, SCALE_NONE); + VOP_SCL_SET_EXT(vop, win, cbcr_hor_scl_mode, SCALE_NONE); + VOP_SCL_SET_EXT(vop, win, cbcr_ver_scl_mode, SCALE_NONE); + } + + VOP_WIN_SET(vop, win, enable, 0); +} + static int vop_enable(struct drm_crtc *crtc) { struct vop *vop = to_vop(crtc); @@ -586,7 +598,7 @@ static int vop_enable(struct drm_crtc *crtc) struct vop_win *vop_win = &vop->win[i]; const struct vop_win_data *win = vop_win->data; - VOP_WIN_SET(vop, win, enable, 0); + vop_win_disable(vop, win); } spin_unlock(&vop->reg_lock); @@ -735,7 +747,7 @@ static void vop_plane_atomic_disable(struct drm_plane *plane, spin_lock(&vop->reg_lock); - VOP_WIN_SET(vop, win, enable, 0); + vop_win_disable(vop, win); spin_unlock(&vop->reg_lock); } @@ -1622,7 +1634,7 @@ static int vop_initial(struct vop *vop) int channel = i * 2 + 1; VOP_WIN_SET(vop, win, channel, (channel + 1) << 4 | channel); - VOP_WIN_SET(vop, win, enable, 0); + vop_win_disable(vop, win); VOP_WIN_SET(vop, win, gate, 1); } diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 19fc601c9eeb..a1bec2779e76 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -366,10 +366,9 @@ void drm_sched_increase_karma(struct drm_sched_job *bad) EXPORT_SYMBOL(drm_sched_increase_karma); /** - * drm_sched_hw_job_reset - stop the scheduler if it contains the bad job + * drm_sched_stop - stop the scheduler * * @sched: scheduler instance - * @bad: bad scheduler job * */ void drm_sched_stop(struct drm_gpu_scheduler *sched) diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c index 3ebd9f5e2719..29258b404e54 100644 --- a/drivers/gpu/drm/sun4i/sun4i_drv.c +++ b/drivers/gpu/drm/sun4i/sun4i_drv.c @@ -16,6 +16,7 @@ #include <linux/of_reserved_mem.h> #include <drm/drmP.h> +#include <drm/drm_atomic_helper.h> #include <drm/drm_fb_cma_helper.h> #include <drm/drm_fb_helper.h> #include <drm/drm_gem_cma_helper.h> @@ -85,6 +86,8 @@ static int sun4i_drv_bind(struct device *dev) ret = -ENOMEM; goto free_drm; } + + dev_set_drvdata(dev, drm); drm->dev_private = drv; INIT_LIST_HEAD(&drv->frontend_list); INIT_LIST_HEAD(&drv->engine_list); @@ -144,8 +147,12 @@ static void sun4i_drv_unbind(struct device *dev) drm_dev_unregister(drm); drm_kms_helper_poll_fini(drm); + drm_atomic_helper_shutdown(drm); drm_mode_config_cleanup(drm); + + component_unbind_all(dev, NULL); of_reserved_mem_device_release(dev); + drm_dev_put(drm); } @@ -395,6 +402,8 @@ static int sun4i_drv_probe(struct platform_device *pdev) static int sun4i_drv_remove(struct platform_device *pdev) { + component_master_del(&pdev->dev, &sun4i_drv_master_ops); + return 0; } diff --git a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c index dc47720c99ba..39d8509d96a0 100644 --- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c +++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c @@ -48,8 +48,13 @@ static enum drm_mode_status sun8i_dw_hdmi_mode_valid_h6(struct drm_connector *connector, const struct drm_display_mode *mode) { - /* This is max for HDMI 2.0b (4K@60Hz) */ - if (mode->clock > 594000) + /* + * Controller support maximum of 594 MHz, which correlates to + * 4K@60Hz 4:4:4 or RGB. However, for frequencies greater than + * 340 MHz scrambling has to be enabled. Because scrambling is + * not yet implemented, just limit to 340 MHz for now. + */ + if (mode->clock > 340000) return MODE_CLOCK_HIGH; return MODE_OK; diff --git a/drivers/gpu/drm/sun4i/sun8i_tcon_top.c b/drivers/gpu/drm/sun4i/sun8i_tcon_top.c index fc36e0c10a37..b1e7c76e9c17 100644 --- a/drivers/gpu/drm/sun4i/sun8i_tcon_top.c +++ b/drivers/gpu/drm/sun4i/sun8i_tcon_top.c @@ -227,7 +227,7 @@ static int sun8i_tcon_top_bind(struct device *dev, struct device *master, err_unregister_gates: for (i = 0; i < CLK_NUM; i++) - if (clk_data->hws[i]) + if (!IS_ERR_OR_NULL(clk_data->hws[i])) clk_hw_unregister_gate(clk_data->hws[i]); clk_disable_unprepare(tcon_top->bus); err_assert_reset: @@ -245,7 +245,8 @@ static void sun8i_tcon_top_unbind(struct device *dev, struct device *master, of_clk_del_provider(dev->of_node); for (i = 0; i < CLK_NUM; i++) - clk_hw_unregister_gate(clk_data->hws[i]); + if (clk_data->hws[i]) + clk_hw_unregister_gate(clk_data->hws[i]); clk_disable_unprepare(tcon_top->bus); reset_control_assert(tcon_top->rst); diff --git a/drivers/gpu/drm/tegra/hdmi.c b/drivers/gpu/drm/tegra/hdmi.c index 47c55974756d..d23c4bfde790 100644 --- a/drivers/gpu/drm/tegra/hdmi.c +++ b/drivers/gpu/drm/tegra/hdmi.c @@ -1260,9 +1260,15 @@ static void tegra_hdmi_encoder_enable(struct drm_encoder *encoder) hdmi->dvi = !tegra_output_is_hdmi(output); if (!hdmi->dvi) { - err = tegra_hdmi_setup_audio(hdmi); - if (err < 0) - hdmi->dvi = true; + /* + * Make sure that the audio format has been configured before + * enabling audio, otherwise we may try to divide by zero. + */ + if (hdmi->format.sample_rate > 0) { + err = tegra_hdmi_setup_audio(hdmi); + if (err < 0) + hdmi->dvi = true; + } } if (hdmi->config->has_hda) diff --git a/drivers/gpu/drm/tegra/hub.c b/drivers/gpu/drm/tegra/hub.c index ba9b3cfb8c3d..b3436c2aed68 100644 --- a/drivers/gpu/drm/tegra/hub.c +++ b/drivers/gpu/drm/tegra/hub.c @@ -378,14 +378,16 @@ static int tegra_shared_plane_atomic_check(struct drm_plane *plane, static void tegra_shared_plane_atomic_disable(struct drm_plane *plane, struct drm_plane_state *old_state) { - struct tegra_dc *dc = to_tegra_dc(old_state->crtc); struct tegra_plane *p = to_tegra_plane(plane); + struct tegra_dc *dc; u32 value; /* rien ne va plus */ if (!old_state || !old_state->crtc) return; + dc = to_tegra_dc(old_state->crtc); + /* * XXX Legacy helpers seem to sometimes call ->atomic_disable() even * on planes that are already disabled. Make sure we fallback to the diff --git a/drivers/gpu/drm/tegra/vic.c b/drivers/gpu/drm/tegra/vic.c index 39bfed9623de..982ce37ecde1 100644 --- a/drivers/gpu/drm/tegra/vic.c +++ b/drivers/gpu/drm/tegra/vic.c @@ -106,6 +106,7 @@ static int vic_boot(struct vic *vic) if (vic->booted) return 0; +#ifdef CONFIG_IOMMU_API if (vic->config->supports_sid) { struct iommu_fwspec *spec = dev_iommu_fwspec_get(vic->dev); u32 value; @@ -121,6 +122,7 @@ static int vic_boot(struct vic *vic) vic_writel(vic, value, VIC_THI_STREAMID1); } } +#endif /* setup clockgating registers */ vic_writel(vic, CG_IDLE_CG_DLY_CNT(4) | diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 3f56647cdb35..1a01669b159a 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -49,9 +49,8 @@ static void ttm_bo_global_kobj_release(struct kobject *kobj); * ttm_global_mutex - protecting the global BO state */ DEFINE_MUTEX(ttm_global_mutex); -struct ttm_bo_global ttm_bo_glob = { - .use_count = 0 -}; +unsigned ttm_bo_glob_use_count; +struct ttm_bo_global ttm_bo_glob; static struct attribute ttm_bo_count = { .name = "bo_count", @@ -876,8 +875,10 @@ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo, reservation_object_add_shared_fence(bo->resv, fence); ret = reservation_object_reserve_shared(bo->resv, 1); - if (unlikely(ret)) + if (unlikely(ret)) { + dma_fence_put(fence); return ret; + } dma_fence_put(bo->moving); bo->moving = fence; @@ -1529,12 +1530,13 @@ static void ttm_bo_global_release(void) struct ttm_bo_global *glob = &ttm_bo_glob; mutex_lock(&ttm_global_mutex); - if (--glob->use_count > 0) + if (--ttm_bo_glob_use_count > 0) goto out; kobject_del(&glob->kobj); kobject_put(&glob->kobj); ttm_mem_global_release(&ttm_mem_glob); + memset(glob, 0, sizeof(*glob)); out: mutex_unlock(&ttm_global_mutex); } @@ -1546,7 +1548,7 @@ static int ttm_bo_global_init(void) unsigned i; mutex_lock(&ttm_global_mutex); - if (++glob->use_count > 1) + if (++ttm_bo_glob_use_count > 1) goto out; ret = ttm_mem_global_init(&ttm_mem_glob); diff --git a/drivers/gpu/drm/ttm/ttm_memory.c b/drivers/gpu/drm/ttm/ttm_memory.c index f1567c353b54..9a0909decb36 100644 --- a/drivers/gpu/drm/ttm/ttm_memory.c +++ b/drivers/gpu/drm/ttm/ttm_memory.c @@ -461,8 +461,8 @@ out_no_zone: void ttm_mem_global_release(struct ttm_mem_global *glob) { - unsigned int i; struct ttm_mem_zone *zone; + unsigned int i; /* let the page allocator first stop the shrink work. */ ttm_page_alloc_fini(); @@ -475,9 +475,10 @@ void ttm_mem_global_release(struct ttm_mem_global *glob) zone = glob->zones[i]; kobject_del(&zone->kobj); kobject_put(&zone->kobj); - } + } kobject_del(&glob->kobj); kobject_put(&glob->kobj); + memset(glob, 0, sizeof(*glob)); } static void ttm_check_swapping(struct ttm_mem_global *glob) diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c index f841accc2c00..627f8dc91d0e 100644 --- a/drivers/gpu/drm/ttm/ttm_page_alloc.c +++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c @@ -730,9 +730,10 @@ static void ttm_put_pages(struct page **pages, unsigned npages, int flags, } #ifdef CONFIG_TRANSPARENT_HUGEPAGE - if (!(flags & TTM_PAGE_FLAG_DMA32)) { - for (j = 0; j < HPAGE_PMD_NR; ++j) - if (p++ != pages[i + j]) + if (!(flags & TTM_PAGE_FLAG_DMA32) && + (npages - i) >= HPAGE_PMD_NR) { + for (j = 1; j < HPAGE_PMD_NR; ++j) + if (++p != pages[i + j]) break; if (j == HPAGE_PMD_NR) @@ -759,15 +760,15 @@ static void ttm_put_pages(struct page **pages, unsigned npages, int flags, unsigned max_size, n2free; spin_lock_irqsave(&huge->lock, irq_flags); - while (i < npages) { + while ((npages - i) >= HPAGE_PMD_NR) { struct page *p = pages[i]; unsigned j; if (!p) break; - for (j = 0; j < HPAGE_PMD_NR; ++j) - if (p++ != pages[i + j]) + for (j = 1; j < HPAGE_PMD_NR; ++j) + if (++p != pages[i + j]) break; if (j != HPAGE_PMD_NR) diff --git a/drivers/gpu/drm/udl/udl_connector.c b/drivers/gpu/drm/udl/udl_connector.c index 66885c24590f..c1bd5e3d9e4a 100644 --- a/drivers/gpu/drm/udl/udl_connector.c +++ b/drivers/gpu/drm/udl/udl_connector.c @@ -18,18 +18,19 @@ #include "udl_connector.h" #include "udl_drv.h" -static bool udl_get_edid_block(struct udl_device *udl, int block_idx, - u8 *buff) +static int udl_get_edid_block(void *data, u8 *buf, unsigned int block, + size_t len) { int ret, i; u8 *read_buff; + struct udl_device *udl = data; read_buff = kmalloc(2, GFP_KERNEL); if (!read_buff) - return false; + return -1; - for (i = 0; i < EDID_LENGTH; i++) { - int bval = (i + block_idx * EDID_LENGTH) << 8; + for (i = 0; i < len; i++) { + int bval = (i + block * EDID_LENGTH) << 8; ret = usb_control_msg(udl->udev, usb_rcvctrlpipe(udl->udev, 0), (0x02), (0x80 | (0x02 << 5)), bval, @@ -37,60 +38,13 @@ static bool udl_get_edid_block(struct udl_device *udl, int block_idx, if (ret < 1) { DRM_ERROR("Read EDID byte %d failed err %x\n", i, ret); kfree(read_buff); - return false; + return -1; } - buff[i] = read_buff[1]; + buf[i] = read_buff[1]; } kfree(read_buff); - return true; -} - -static bool udl_get_edid(struct udl_device *udl, u8 **result_buff, - int *result_buff_size) -{ - int i, extensions; - u8 *block_buff = NULL, *buff_ptr; - - block_buff = kmalloc(EDID_LENGTH, GFP_KERNEL); - if (block_buff == NULL) - return false; - - if (udl_get_edid_block(udl, 0, block_buff) && - memchr_inv(block_buff, 0, EDID_LENGTH)) { - extensions = ((struct edid *)block_buff)->extensions; - if (extensions > 0) { - /* we have to read all extensions one by one */ - *result_buff_size = EDID_LENGTH * (extensions + 1); - *result_buff = kmalloc(*result_buff_size, GFP_KERNEL); - buff_ptr = *result_buff; - if (buff_ptr == NULL) { - kfree(block_buff); - return false; - } - memcpy(buff_ptr, block_buff, EDID_LENGTH); - kfree(block_buff); - buff_ptr += EDID_LENGTH; - for (i = 1; i < extensions; ++i) { - if (udl_get_edid_block(udl, i, buff_ptr)) { - buff_ptr += EDID_LENGTH; - } else { - kfree(*result_buff); - *result_buff = NULL; - return false; - } - } - return true; - } - /* we have only base edid block */ - *result_buff = block_buff; - *result_buff_size = EDID_LENGTH; - return true; - } - - kfree(block_buff); - - return false; + return 0; } static int udl_get_modes(struct drm_connector *connector) @@ -122,8 +76,6 @@ static enum drm_mode_status udl_mode_valid(struct drm_connector *connector, static enum drm_connector_status udl_detect(struct drm_connector *connector, bool force) { - u8 *edid_buff = NULL; - int edid_buff_size = 0; struct udl_device *udl = connector->dev->dev_private; struct udl_drm_connector *udl_connector = container_of(connector, @@ -136,12 +88,10 @@ udl_detect(struct drm_connector *connector, bool force) udl_connector->edid = NULL; } - - if (!udl_get_edid(udl, &edid_buff, &edid_buff_size)) + udl_connector->edid = drm_do_get_edid(connector, udl_get_edid_block, udl); + if (!udl_connector->edid) return connector_status_disconnected; - udl_connector->edid = (struct edid *)edid_buff; - return connector_status_connected; } diff --git a/drivers/gpu/drm/udl/udl_drv.c b/drivers/gpu/drm/udl/udl_drv.c index 22cd2d13e272..ff47f890e6ad 100644 --- a/drivers/gpu/drm/udl/udl_drv.c +++ b/drivers/gpu/drm/udl/udl_drv.c @@ -52,6 +52,7 @@ static struct drm_driver driver = { .driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_PRIME, .load = udl_driver_load, .unload = udl_driver_unload, + .release = udl_driver_release, /* gem hooks */ .gem_free_object_unlocked = udl_gem_free_object, diff --git a/drivers/gpu/drm/udl/udl_drv.h b/drivers/gpu/drm/udl/udl_drv.h index e9e9b1ff678e..4ae67d882eae 100644 --- a/drivers/gpu/drm/udl/udl_drv.h +++ b/drivers/gpu/drm/udl/udl_drv.h @@ -104,6 +104,7 @@ void udl_urb_completion(struct urb *urb); int udl_driver_load(struct drm_device *dev, unsigned long flags); void udl_driver_unload(struct drm_device *dev); +void udl_driver_release(struct drm_device *dev); int udl_fbdev_init(struct drm_device *dev); void udl_fbdev_cleanup(struct drm_device *dev); diff --git a/drivers/gpu/drm/udl/udl_main.c b/drivers/gpu/drm/udl/udl_main.c index 9086d0d1b880..1f8ef34ade24 100644 --- a/drivers/gpu/drm/udl/udl_main.c +++ b/drivers/gpu/drm/udl/udl_main.c @@ -379,6 +379,12 @@ void udl_driver_unload(struct drm_device *dev) udl_free_urb_list(dev); udl_fbdev_cleanup(dev); - udl_modeset_cleanup(dev); kfree(udl); } + +void udl_driver_release(struct drm_device *dev) +{ + udl_modeset_cleanup(dev); + drm_dev_fini(dev); + kfree(dev); +} diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c index 730008d3da76..1baa10e94484 100644 --- a/drivers/gpu/drm/vc4/vc4_crtc.c +++ b/drivers/gpu/drm/vc4/vc4_crtc.c @@ -1042,7 +1042,7 @@ static void vc4_crtc_reset(struct drm_crtc *crtc) { if (crtc->state) - __drm_atomic_helper_crtc_destroy_state(crtc->state); + vc4_crtc_destroy_state(crtc, crtc->state); crtc->state = kzalloc(sizeof(struct vc4_crtc_state), GFP_KERNEL); if (crtc->state) diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c index 5930facd6d2d..11a8f99ba18c 100644 --- a/drivers/gpu/drm/vgem/vgem_drv.c +++ b/drivers/gpu/drm/vgem/vgem_drv.c @@ -191,13 +191,9 @@ static struct drm_gem_object *vgem_gem_create(struct drm_device *dev, ret = drm_gem_handle_create(file, &obj->base, handle); drm_gem_object_put_unlocked(&obj->base); if (ret) - goto err; + return ERR_PTR(ret); return &obj->base; - -err: - __vgem_gem_destroy(obj); - return ERR_PTR(ret); } static int vgem_gem_dumb_create(struct drm_file *file, struct drm_device *dev, diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c index b996ac1d4fcc..af92964b6889 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.c +++ b/drivers/gpu/drm/virtio/virtgpu_drv.c @@ -205,10 +205,14 @@ static struct drm_driver driver = { #if defined(CONFIG_DEBUG_FS) .debugfs_init = virtio_gpu_debugfs_init, #endif + .prime_handle_to_fd = drm_gem_prime_handle_to_fd, + .prime_fd_to_handle = drm_gem_prime_fd_to_handle, .gem_prime_export = drm_gem_prime_export, .gem_prime_import = drm_gem_prime_import, .gem_prime_pin = virtgpu_gem_prime_pin, .gem_prime_unpin = virtgpu_gem_prime_unpin, + .gem_prime_get_sg_table = virtgpu_gem_prime_get_sg_table, + .gem_prime_import_sg_table = virtgpu_gem_prime_import_sg_table, .gem_prime_vmap = virtgpu_gem_prime_vmap, .gem_prime_vunmap = virtgpu_gem_prime_vunmap, .gem_prime_mmap = virtgpu_gem_prime_mmap, diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index 3238fdf58eb4..d577cb76f5ad 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -354,6 +354,10 @@ int virtio_gpu_object_wait(struct virtio_gpu_object *bo, bool no_wait); /* virtgpu_prime.c */ int virtgpu_gem_prime_pin(struct drm_gem_object *obj); void virtgpu_gem_prime_unpin(struct drm_gem_object *obj); +struct sg_table *virtgpu_gem_prime_get_sg_table(struct drm_gem_object *obj); +struct drm_gem_object *virtgpu_gem_prime_import_sg_table( + struct drm_device *dev, struct dma_buf_attachment *attach, + struct sg_table *sgt); void *virtgpu_gem_prime_vmap(struct drm_gem_object *obj); void virtgpu_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr); int virtgpu_gem_prime_mmap(struct drm_gem_object *obj, diff --git a/drivers/gpu/drm/virtio/virtgpu_prime.c b/drivers/gpu/drm/virtio/virtgpu_prime.c index c59ec34c80a5..eb51a78e1199 100644 --- a/drivers/gpu/drm/virtio/virtgpu_prime.c +++ b/drivers/gpu/drm/virtio/virtgpu_prime.c @@ -39,6 +39,18 @@ void virtgpu_gem_prime_unpin(struct drm_gem_object *obj) WARN_ONCE(1, "not implemented"); } +struct sg_table *virtgpu_gem_prime_get_sg_table(struct drm_gem_object *obj) +{ + return ERR_PTR(-ENODEV); +} + +struct drm_gem_object *virtgpu_gem_prime_import_sg_table( + struct drm_device *dev, struct dma_buf_attachment *attach, + struct sg_table *table) +{ + return ERR_PTR(-ENODEV); +} + void *virtgpu_gem_prime_vmap(struct drm_gem_object *obj) { struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(obj); diff --git a/drivers/gpu/drm/vkms/vkms_gem.c b/drivers/gpu/drm/vkms/vkms_gem.c index 138b0bb325cf..69048e73377d 100644 --- a/drivers/gpu/drm/vkms/vkms_gem.c +++ b/drivers/gpu/drm/vkms/vkms_gem.c @@ -111,11 +111,8 @@ struct drm_gem_object *vkms_gem_create(struct drm_device *dev, ret = drm_gem_handle_create(file, &obj->gem, handle); drm_gem_object_put_unlocked(&obj->gem); - if (ret) { - drm_gem_object_release(&obj->gem); - kfree(obj); + if (ret) return ERR_PTR(ret); - } return &obj->gem; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 6165fe2c4504..1bfa353d995c 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -546,29 +546,13 @@ static void vmw_get_initial_size(struct vmw_private *dev_priv) } /** - * vmw_assume_iommu - Figure out whether coherent dma-remapping might be - * taking place. - * @dev: Pointer to the struct drm_device. - * - * Return: true if iommu present, false otherwise. - */ -static bool vmw_assume_iommu(struct drm_device *dev) -{ - const struct dma_map_ops *ops = get_dma_ops(dev->dev); - - return !dma_is_direct(ops) && ops && - ops->map_page != dma_direct_map_page; -} - -/** * vmw_dma_select_mode - Determine how DMA mappings should be set up for this * system. * * @dev_priv: Pointer to a struct vmw_private * - * This functions tries to determine the IOMMU setup and what actions - * need to be taken by the driver to make system pages visible to the - * device. + * This functions tries to determine what actions need to be taken by the + * driver to make system pages visible to the device. * If this function decides that DMA is not possible, it returns -EINVAL. * The driver may then try to disable features of the device that require * DMA. @@ -578,23 +562,16 @@ static int vmw_dma_select_mode(struct vmw_private *dev_priv) static const char *names[vmw_dma_map_max] = { [vmw_dma_phys] = "Using physical TTM page addresses.", [vmw_dma_alloc_coherent] = "Using coherent TTM pages.", - [vmw_dma_map_populate] = "Keeping DMA mappings.", + [vmw_dma_map_populate] = "Caching DMA mappings.", [vmw_dma_map_bind] = "Giving up DMA mappings early."}; if (vmw_force_coherent) dev_priv->map_mode = vmw_dma_alloc_coherent; - else if (vmw_assume_iommu(dev_priv->dev)) - dev_priv->map_mode = vmw_dma_map_populate; - else if (!vmw_force_iommu) - dev_priv->map_mode = vmw_dma_phys; - else if (IS_ENABLED(CONFIG_SWIOTLB) && swiotlb_nr_tbl()) - dev_priv->map_mode = vmw_dma_alloc_coherent; + else if (vmw_restrict_iommu) + dev_priv->map_mode = vmw_dma_map_bind; else dev_priv->map_mode = vmw_dma_map_populate; - if (dev_priv->map_mode == vmw_dma_map_populate && vmw_restrict_iommu) - dev_priv->map_mode = vmw_dma_map_bind; - /* No TTM coherent page pool? FIXME: Ask TTM instead! */ if (!(IS_ENABLED(CONFIG_SWIOTLB) || IS_ENABLED(CONFIG_INTEL_IOMMU)) && (dev_priv->map_mode == vmw_dma_alloc_coherent)) diff --git a/drivers/gpu/host1x/hw/channel_hw.c b/drivers/gpu/host1x/hw/channel_hw.c index 27101c04a827..0c0eb43abf65 100644 --- a/drivers/gpu/host1x/hw/channel_hw.c +++ b/drivers/gpu/host1x/hw/channel_hw.c @@ -115,8 +115,12 @@ static inline void synchronize_syncpt_base(struct host1x_job *job) static void host1x_channel_set_streamid(struct host1x_channel *channel) { #if HOST1X_HW >= 6 + u32 sid = 0x7f; +#ifdef CONFIG_IOMMU_API struct iommu_fwspec *spec = dev_iommu_fwspec_get(channel->dev->parent); - u32 sid = spec ? spec->ids[0] & 0xffff : 0x7f; + if (spec) + sid = spec->ids[0] & 0xffff; +#endif host1x_ch_writel(channel, sid, HOST1X_CHANNEL_SMMU_STREAMID); #endif diff --git a/drivers/gpu/ipu-v3/ipu-dp.c b/drivers/gpu/ipu-v3/ipu-dp.c index 9b2b3fa479c4..5e44ff1f2085 100644 --- a/drivers/gpu/ipu-v3/ipu-dp.c +++ b/drivers/gpu/ipu-v3/ipu-dp.c @@ -195,7 +195,8 @@ int ipu_dp_setup_channel(struct ipu_dp *dp, ipu_dp_csc_init(flow, flow->foreground.in_cs, flow->out_cs, DP_COM_CONF_CSC_DEF_BOTH); } else { - if (flow->foreground.in_cs == flow->out_cs) + if (flow->foreground.in_cs == IPUV3_COLORSPACE_UNKNOWN || + flow->foreground.in_cs == flow->out_cs) /* * foreground identical to output, apply color * conversion on background @@ -261,6 +262,8 @@ void ipu_dp_disable_channel(struct ipu_dp *dp, bool sync) struct ipu_dp_priv *priv = flow->priv; u32 reg, csc; + dp->in_cs = IPUV3_COLORSPACE_UNKNOWN; + if (!dp->foreground) return; @@ -268,8 +271,9 @@ void ipu_dp_disable_channel(struct ipu_dp *dp, bool sync) reg = readl(flow->base + DP_COM_CONF); csc = reg & DP_COM_CONF_CSC_DEF_MASK; - if (csc == DP_COM_CONF_CSC_DEF_FG) - reg &= ~DP_COM_CONF_CSC_DEF_MASK; + reg &= ~DP_COM_CONF_CSC_DEF_MASK; + if (csc == DP_COM_CONF_CSC_DEF_BOTH || csc == DP_COM_CONF_CSC_DEF_BG) + reg |= DP_COM_CONF_CSC_DEF_BG; reg &= ~DP_COM_CONF_FG_EN; writel(reg, flow->base + DP_COM_CONF); @@ -347,6 +351,8 @@ int ipu_dp_init(struct ipu_soc *ipu, struct device *dev, unsigned long base) mutex_init(&priv->mutex); for (i = 0; i < IPUV3_NUM_FLOWS; i++) { + priv->flow[i].background.in_cs = IPUV3_COLORSPACE_UNKNOWN; + priv->flow[i].foreground.in_cs = IPUV3_COLORSPACE_UNKNOWN; priv->flow[i].foreground.foreground = true; priv->flow[i].base = priv->base + ipu_dp_flow_base[i]; priv->flow[i].priv = priv; diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig index 6ca8d322b487..4ca0cdfa6b33 100644 --- a/drivers/hid/Kconfig +++ b/drivers/hid/Kconfig @@ -150,6 +150,7 @@ config HID_ASUS tristate "Asus" depends on LEDS_CLASS depends on ASUS_WMI || ASUS_WMI=n + select POWER_SUPPLY ---help--- Support for Asus notebook built-in keyboard and touchpad via i2c, and the Asus Republic of Gamers laptop keyboard special keys. diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 9993b692598f..860e21ec6a49 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1301,10 +1301,10 @@ static u32 __extract(u8 *report, unsigned offset, int n) u32 hid_field_extract(const struct hid_device *hid, u8 *report, unsigned offset, unsigned n) { - if (n > 32) { - hid_warn(hid, "hid_field_extract() called with n (%d) > 32! (%s)\n", + if (n > 256) { + hid_warn(hid, "hid_field_extract() called with n (%d) > 256! (%s)\n", n, current->comm); - n = 32; + n = 256; } return __extract(report, offset, n); diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c index ac9fda1b5a72..1384e57182af 100644 --- a/drivers/hid/hid-debug.c +++ b/drivers/hid/hid-debug.c @@ -1060,10 +1060,15 @@ static int hid_debug_rdesc_show(struct seq_file *f, void *p) seq_printf(f, "\n\n"); /* dump parsed data and input mappings */ + if (down_interruptible(&hdev->driver_input_lock)) + return 0; + hid_dump_device(hdev, f); seq_printf(f, "\n"); hid_dump_input_mapping(hdev, f); + up(&hdev->driver_input_lock); + return 0; } diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index b6d93f4ad037..adce58f24f76 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -1083,6 +1083,7 @@ #define USB_DEVICE_ID_SYNAPTICS_HD 0x0ac3 #define USB_DEVICE_ID_SYNAPTICS_QUAD_HD 0x1ac3 #define USB_DEVICE_ID_SYNAPTICS_TP_V103 0x5710 +#define I2C_DEVICE_ID_SYNAPTICS_7E7E 0x7e7e #define USB_VENDOR_ID_TEXAS_INSTRUMENTS 0x2047 #define USB_DEVICE_ID_TEXAS_INSTRUMENTS_LENOVO_YOGA 0x0855 diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index b10b1922c5bd..b607286a0bc8 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -680,6 +680,14 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel break; } + if ((usage->hid & 0xf0) == 0xb0) { /* SC - Display */ + switch (usage->hid & 0xf) { + case 0x05: map_key_clear(KEY_SWITCHVIDEOMODE); break; + default: goto ignore; + } + break; + } + /* * Some lazy vendors declare 255 usages for System Control, * leading to the creation of ABS_X|Y axis and too many others. @@ -902,7 +910,7 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel case 0x06a: map_key_clear(KEY_GREEN); break; case 0x06b: map_key_clear(KEY_BLUE); break; case 0x06c: map_key_clear(KEY_YELLOW); break; - case 0x06d: map_key_clear(KEY_ZOOM); break; + case 0x06d: map_key_clear(KEY_ASPECT_RATIO); break; case 0x06f: map_key_clear(KEY_BRIGHTNESSUP); break; case 0x070: map_key_clear(KEY_BRIGHTNESSDOWN); break; @@ -911,6 +919,10 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel case 0x074: map_key_clear(KEY_BRIGHTNESS_MAX); break; case 0x075: map_key_clear(KEY_BRIGHTNESS_AUTO); break; + case 0x079: map_key_clear(KEY_KBDILLUMUP); break; + case 0x07a: map_key_clear(KEY_KBDILLUMDOWN); break; + case 0x07c: map_key_clear(KEY_KBDILLUMTOGGLE); break; + case 0x082: map_key_clear(KEY_VIDEO_NEXT); break; case 0x083: map_key_clear(KEY_LAST); break; case 0x084: map_key_clear(KEY_ENTER); break; @@ -998,6 +1010,7 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel case 0x1b8: map_key_clear(KEY_VIDEO); break; case 0x1bc: map_key_clear(KEY_MESSENGER); break; case 0x1bd: map_key_clear(KEY_INFO); break; + case 0x1cb: map_key_clear(KEY_ASSISTANT); break; case 0x201: map_key_clear(KEY_NEW); break; case 0x202: map_key_clear(KEY_OPEN); break; case 0x203: map_key_clear(KEY_CLOSE); break; @@ -1021,6 +1034,7 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel case 0x22d: map_key_clear(KEY_ZOOMIN); break; case 0x22e: map_key_clear(KEY_ZOOMOUT); break; case 0x22f: map_key_clear(KEY_ZOOMRESET); break; + case 0x232: map_key_clear(KEY_FULL_SCREEN); break; case 0x233: map_key_clear(KEY_SCROLLUP); break; case 0x234: map_key_clear(KEY_SCROLLDOWN); break; case 0x238: /* AC Pan */ @@ -1044,6 +1058,8 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel case 0x2cb: map_key_clear(KEY_KBDINPUTASSIST_ACCEPT); break; case 0x2cc: map_key_clear(KEY_KBDINPUTASSIST_CANCEL); break; + case 0x29f: map_key_clear(KEY_SCALE); break; + default: map_key_clear(KEY_UNKNOWN); } break; diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 15ed6177a7a3..199cc256e9d9 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -2111,6 +2111,13 @@ static int hidpp_ff_init(struct hidpp_device *hidpp, u8 feature_index) kfree(data); return -ENOMEM; } + data->wq = create_singlethread_workqueue("hidpp-ff-sendqueue"); + if (!data->wq) { + kfree(data->effect_ids); + kfree(data); + return -ENOMEM; + } + data->hidpp = hidpp; data->feature_index = feature_index; data->version = version; @@ -2155,7 +2162,6 @@ static int hidpp_ff_init(struct hidpp_device *hidpp, u8 feature_index) /* ignore boost value at response.fap.params[2] */ /* init the hardware command queue */ - data->wq = create_singlethread_workqueue("hidpp-ff-sendqueue"); atomic_set(&data->workqueue_size, 0); /* initialize with zero autocenter to get wheel in usable state */ @@ -2608,8 +2614,9 @@ static int m560_raw_event(struct hid_device *hdev, u8 *data, int size) input_report_rel(mydata->input, REL_Y, v); v = hid_snto32(data[6], 8); - hidpp_scroll_counter_handle_scroll( - &hidpp->vertical_wheel_counter, v); + if (v != 0) + hidpp_scroll_counter_handle_scroll( + &hidpp->vertical_wheel_counter, v); input_sync(mydata->input); } diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 953908f2267c..77ffba48cc73 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -715,7 +715,6 @@ static const struct hid_device_id hid_ignore_list[] = { { HID_USB_DEVICE(USB_VENDOR_ID_DEALEXTREAME, USB_DEVICE_ID_DEALEXTREAME_RADIO_SI4701) }, { HID_USB_DEVICE(USB_VENDOR_ID_DELORME, USB_DEVICE_ID_DELORME_EARTHMATE) }, { HID_USB_DEVICE(USB_VENDOR_ID_DELORME, USB_DEVICE_ID_DELORME_EM_LT20) }, - { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, 0x0400) }, { HID_USB_DEVICE(USB_VENDOR_ID_ESSENTIAL_REALITY, USB_DEVICE_ID_ESSENTIAL_REALITY_P5) }, { HID_USB_DEVICE(USB_VENDOR_ID_ETT, USB_DEVICE_ID_TC5UH) }, { HID_USB_DEVICE(USB_VENDOR_ID_ETT, USB_DEVICE_ID_TC4UM) }, @@ -855,7 +854,7 @@ static const struct hid_device_id hid_ignore_list[] = { { } }; -/** +/* * hid_mouse_ignore_list - mouse devices which should not be handled by the hid layer * * There are composite devices for which we want to ignore only a certain @@ -996,6 +995,10 @@ bool hid_ignore(struct hid_device *hdev) if (hdev->product == 0x0401 && strncmp(hdev->name, "ELAN0800", 8) != 0) return true; + /* Same with product id 0x0400 */ + if (hdev->product == 0x0400 && + strncmp(hdev->name, "QTEC0001", 8) != 0) + return true; break; } @@ -1042,7 +1045,7 @@ static struct hid_device_id *hid_exists_dquirk(const struct hid_device *hdev) } if (bl_entry != NULL) - dbg_hid("Found dynamic quirk 0x%lx for HID device 0x%hx:0x%hx\n", + dbg_hid("Found dynamic quirk 0x%lx for HID device 0x%04x:0x%04x\n", bl_entry->driver_data, bl_entry->vendor, bl_entry->product); @@ -1209,7 +1212,7 @@ static unsigned long hid_gets_squirk(const struct hid_device *hdev) quirks |= bl_entry->driver_data; if (quirks) - dbg_hid("Found squirk 0x%lx for HID device 0x%hx:0x%hx\n", + dbg_hid("Found squirk 0x%lx for HID device 0x%04x:0x%04x\n", quirks, hdev->vendor, hdev->product); return quirks; } diff --git a/drivers/hid/hid-steam.c b/drivers/hid/hid-steam.c index 8141cadfca0e..8dae0f9b819e 100644 --- a/drivers/hid/hid-steam.c +++ b/drivers/hid/hid-steam.c @@ -499,6 +499,7 @@ static void steam_battery_unregister(struct steam_device *steam) static int steam_register(struct steam_device *steam) { int ret; + bool client_opened; /* * This function can be called several times in a row with the @@ -511,9 +512,11 @@ static int steam_register(struct steam_device *steam) * Unlikely, but getting the serial could fail, and it is not so * important, so make up a serial number and go on. */ + mutex_lock(&steam->mutex); if (steam_get_serial(steam) < 0) strlcpy(steam->serial_no, "XXXXXXXXXX", sizeof(steam->serial_no)); + mutex_unlock(&steam->mutex); hid_info(steam->hdev, "Steam Controller '%s' connected", steam->serial_no); @@ -528,13 +531,15 @@ static int steam_register(struct steam_device *steam) } mutex_lock(&steam->mutex); - if (!steam->client_opened) { + client_opened = steam->client_opened; + if (!client_opened) steam_set_lizard_mode(steam, lizard_mode); + mutex_unlock(&steam->mutex); + + if (!client_opened) ret = steam_input_register(steam); - } else { + else ret = 0; - } - mutex_unlock(&steam->mutex); return ret; } @@ -630,14 +635,21 @@ static void steam_client_ll_close(struct hid_device *hdev) { struct steam_device *steam = hdev->driver_data; + unsigned long flags; + bool connected; + + spin_lock_irqsave(&steam->lock, flags); + connected = steam->connected; + spin_unlock_irqrestore(&steam->lock, flags); + mutex_lock(&steam->mutex); steam->client_opened = false; + if (connected) + steam_set_lizard_mode(steam, lizard_mode); mutex_unlock(&steam->mutex); - if (steam->connected) { - steam_set_lizard_mode(steam, lizard_mode); + if (connected) steam_input_register(steam); - } } static int steam_client_ll_raw_request(struct hid_device *hdev, diff --git a/drivers/hid/hid-uclogic-params.c b/drivers/hid/hid-uclogic-params.c index 7710d9f957da..0187c9f8fc22 100644 --- a/drivers/hid/hid-uclogic-params.c +++ b/drivers/hid/hid-uclogic-params.c @@ -735,10 +735,6 @@ static int uclogic_params_huion_init(struct uclogic_params *params, goto cleanup; } rc = usb_string(udev, 201, ver_ptr, ver_len); - if (ver_ptr == NULL) { - rc = -ENOMEM; - goto cleanup; - } if (rc == -EPIPE) { *ver_ptr = '\0'; } else if (rc < 0) { diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index 90164fed08d3..4d1f24ee249c 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -184,6 +184,8 @@ static const struct i2c_hid_quirks { I2C_HID_QUIRK_NO_RUNTIME_PM }, { USB_VENDOR_ID_ELAN, HID_ANY_ID, I2C_HID_QUIRK_BOGUS_IRQ }, + { USB_VENDOR_ID_SYNAPTICS, I2C_DEVICE_ID_SYNAPTICS_7E7E, + I2C_HID_QUIRK_NO_RUNTIME_PM }, { 0, 0 } }; diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index 6f929bfa9fcd..d0f1dfe2bcbb 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -1759,6 +1759,7 @@ config SENSORS_VT8231 config SENSORS_W83773G tristate "Nuvoton W83773G" depends on I2C + select REGMAP_I2C help If you say yes here you get support for the Nuvoton W83773G hardware monitoring chip. diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c index e4f9f7ce92fa..f9abeeeead9e 100644 --- a/drivers/hwmon/ntc_thermistor.c +++ b/drivers/hwmon/ntc_thermistor.c @@ -640,7 +640,7 @@ static const struct hwmon_channel_info ntc_chip = { }; static const u32 ntc_temp_config[] = { - HWMON_T_INPUT, HWMON_T_TYPE, + HWMON_T_INPUT | HWMON_T_TYPE, 0 }; diff --git a/drivers/hwmon/occ/common.c b/drivers/hwmon/occ/common.c index b91a80abf724..4679acb4918e 100644 --- a/drivers/hwmon/occ/common.c +++ b/drivers/hwmon/occ/common.c @@ -890,6 +890,8 @@ static int occ_setup_sensor_attrs(struct occ *occ) s++; } } + + s = (sensors->power.num_sensors * 4) + 1; } else { for (i = 0; i < sensors->power.num_sensors; ++i) { s = i + 1; @@ -918,11 +920,11 @@ static int occ_setup_sensor_attrs(struct occ *occ) show_power, NULL, 3, i); attr++; } - } - if (sensors->caps.num_sensors >= 1) { s = sensors->power.num_sensors + 1; + } + if (sensors->caps.num_sensors >= 1) { snprintf(attr->name, sizeof(attr->name), "power%d_label", s); attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_caps, NULL, 0, 0); diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index f2c681971201..f8979abb9a19 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -131,6 +131,7 @@ config I2C_I801 Cannon Lake (PCH) Cedar Fork (PCH) Ice Lake (PCH) + Comet Lake (PCH) This driver can also be built as a module. If so, the module will be called i2c-i801. diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c index bb8e3f149979..d464799e40a3 100644 --- a/drivers/i2c/busses/i2c-designware-master.c +++ b/drivers/i2c/busses/i2c-designware-master.c @@ -426,8 +426,7 @@ i2c_dw_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], int num) pm_runtime_get_sync(dev->dev); - if (dev->suspended) { - dev_err(dev->dev, "Error %s call while suspended\n", __func__); + if (dev_WARN_ONCE(dev->dev, dev->suspended, "Transfer while suspended\n")) { ret = -ESHUTDOWN; goto done_nolock; } diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index c91e145ef5a5..679c6c41f64b 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -71,6 +71,7 @@ * Cannon Lake-LP (PCH) 0x9da3 32 hard yes yes yes * Cedar Fork (PCH) 0x18df 32 hard yes yes yes * Ice Lake-LP (PCH) 0x34a3 32 hard yes yes yes + * Comet Lake (PCH) 0x02a3 32 hard yes yes yes * * Features supported by this driver: * Software PEC no @@ -240,6 +241,7 @@ #define PCI_DEVICE_ID_INTEL_LEWISBURG_SSKU_SMBUS 0xa223 #define PCI_DEVICE_ID_INTEL_KABYLAKE_PCH_H_SMBUS 0xa2a3 #define PCI_DEVICE_ID_INTEL_CANNONLAKE_H_SMBUS 0xa323 +#define PCI_DEVICE_ID_INTEL_COMETLAKE_SMBUS 0x02a3 struct i801_mux_config { char *gpio_chip; @@ -1038,6 +1040,7 @@ static const struct pci_device_id i801_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CANNONLAKE_H_SMBUS) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CANNONLAKE_LP_SMBUS) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICELAKE_LP_SMBUS) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_COMETLAKE_SMBUS) }, { 0, } }; @@ -1534,6 +1537,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) case PCI_DEVICE_ID_INTEL_DNV_SMBUS: case PCI_DEVICE_ID_INTEL_KABYLAKE_PCH_H_SMBUS: case PCI_DEVICE_ID_INTEL_ICELAKE_LP_SMBUS: + case PCI_DEVICE_ID_INTEL_COMETLAKE_SMBUS: priv->features |= FEATURE_I2C_BLOCK_READ; priv->features |= FEATURE_IRQ; priv->features |= FEATURE_SMBUS_PEC; diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index 42fed40198a0..fd70b110e8f4 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -515,9 +515,9 @@ static int i2c_imx_clk_notifier_call(struct notifier_block *nb, unsigned long action, void *data) { struct clk_notifier_data *ndata = data; - struct imx_i2c_struct *i2c_imx = container_of(&ndata->clk, + struct imx_i2c_struct *i2c_imx = container_of(nb, struct imx_i2c_struct, - clk); + clk_change_nb); if (action & POST_RATE_CHANGE) i2c_imx_set_clk(i2c_imx, ndata->new_rate); @@ -1169,11 +1169,13 @@ static int i2c_imx_probe(struct platform_device *pdev) /* Init DMA config if supported */ ret = i2c_imx_dma_request(i2c_imx, phy_addr); if (ret < 0) - goto clk_notifier_unregister; + goto del_adapter; dev_info(&i2c_imx->adapter.dev, "IMX I2C adapter registered\n"); return 0; /* Return OK */ +del_adapter: + i2c_del_adapter(&i2c_imx->adapter); clk_notifier_unregister: clk_notifier_unregister(i2c_imx->clk, &i2c_imx->clk_change_nb); rpm_disable: diff --git a/drivers/i2c/busses/i2c-synquacer.c b/drivers/i2c/busses/i2c-synquacer.c index d18b0941b71a..f14d4b3fab44 100644 --- a/drivers/i2c/busses/i2c-synquacer.c +++ b/drivers/i2c/busses/i2c-synquacer.c @@ -597,6 +597,8 @@ static int synquacer_i2c_probe(struct platform_device *pdev) i2c->adapter = synquacer_i2c_ops; i2c_set_adapdata(&i2c->adapter, i2c); i2c->adapter.dev.parent = &pdev->dev; + i2c->adapter.dev.of_node = pdev->dev.of_node; + ACPI_COMPANION_SET(&i2c->adapter.dev, ACPI_COMPANION(&pdev->dev)); i2c->adapter.nr = pdev->id; init_completion(&i2c->completion); diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 38af18645133..688aa3b5f3ac 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -185,7 +185,7 @@ static int i2c_generic_bus_free(struct i2c_adapter *adap) int i2c_generic_scl_recovery(struct i2c_adapter *adap) { struct i2c_bus_recovery_info *bri = adap->bus_recovery_info; - int i = 0, scl = 1, ret; + int i = 0, scl = 1, ret = 0; if (bri->prepare_recovery) bri->prepare_recovery(adap); @@ -327,6 +327,8 @@ static int i2c_device_probe(struct device *dev) if (client->flags & I2C_CLIENT_HOST_NOTIFY) { dev_dbg(dev, "Using Host Notify IRQ\n"); + /* Keep adapter active when Host Notify is required */ + pm_runtime_get_sync(&client->adapter->dev); irq = i2c_smbus_host_notify_to_irq(client); } else if (dev->of_node) { irq = of_irq_get_byname(dev->of_node, "irq"); @@ -431,6 +433,8 @@ static int i2c_device_remove(struct device *dev) device_init_wakeup(&client->dev, false); client->irq = client->init_irq; + if (client->flags & I2C_CLIENT_HOST_NOTIFY) + pm_runtime_put(&client->adapter->dev); return status; } diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c index 2dc628d4f1ae..1412abcff010 100644 --- a/drivers/i3c/master.c +++ b/drivers/i3c/master.c @@ -1980,7 +1980,6 @@ of_i3c_master_add_i3c_boardinfo(struct i3c_master_controller *master, { struct i3c_dev_boardinfo *boardinfo; struct device *dev = &master->dev; - struct i3c_device_info info = { }; enum i3c_addr_slot_status addrstatus; u32 init_dyn_addr = 0; @@ -2012,8 +2011,8 @@ of_i3c_master_add_i3c_boardinfo(struct i3c_master_controller *master, boardinfo->pid = ((u64)reg[1] << 32) | reg[2]; - if ((info.pid & GENMASK_ULL(63, 48)) || - I3C_PID_RND_LOWER_32BITS(info.pid)) + if ((boardinfo->pid & GENMASK_ULL(63, 48)) || + I3C_PID_RND_LOWER_32BITS(boardinfo->pid)) return -EINVAL; boardinfo->init_dyn_addr = init_dyn_addr; diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c index 59279224e07f..10c26ffaa8ef 100644 --- a/drivers/i3c/master/dw-i3c-master.c +++ b/drivers/i3c/master/dw-i3c-master.c @@ -300,7 +300,7 @@ to_dw_i3c_master(struct i3c_master_controller *master) static void dw_i3c_master_disable(struct dw_i3c_master *master) { - writel(readl(master->regs + DEVICE_CTRL) & DEV_CTRL_ENABLE, + writel(readl(master->regs + DEVICE_CTRL) & ~DEV_CTRL_ENABLE, master->regs + DEVICE_CTRL); } diff --git a/drivers/iio/accel/kxcjk-1013.c b/drivers/iio/accel/kxcjk-1013.c index 7096e577b23f..50f3ff386bea 100644 --- a/drivers/iio/accel/kxcjk-1013.c +++ b/drivers/iio/accel/kxcjk-1013.c @@ -1437,6 +1437,8 @@ static int kxcjk1013_resume(struct device *dev) mutex_lock(&data->mutex); ret = kxcjk1013_set_mode(data, OPERATION); + if (ret == 0) + ret = kxcjk1013_set_range(data, data->range); mutex_unlock(&data->mutex); return ret; diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c index ff5f2da2e1b1..54d9978b2740 100644 --- a/drivers/iio/adc/ad_sigma_delta.c +++ b/drivers/iio/adc/ad_sigma_delta.c @@ -121,6 +121,7 @@ static int ad_sd_read_reg_raw(struct ad_sigma_delta *sigma_delta, if (sigma_delta->info->has_registers) { data[0] = reg << sigma_delta->info->addr_shift; data[0] |= sigma_delta->info->read_mask; + data[0] |= sigma_delta->comm; spi_message_add_tail(&t[0], &m); } spi_message_add_tail(&t[1], &m); diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c index 75d2f73582a3..596841a3c4db 100644 --- a/drivers/iio/adc/at91_adc.c +++ b/drivers/iio/adc/at91_adc.c @@ -704,23 +704,29 @@ static int at91_adc_read_raw(struct iio_dev *idev, ret = wait_event_interruptible_timeout(st->wq_data_avail, st->done, msecs_to_jiffies(1000)); - if (ret == 0) - ret = -ETIMEDOUT; - if (ret < 0) { - mutex_unlock(&st->lock); - return ret; - } - - *val = st->last_value; + /* Disable interrupts, regardless if adc conversion was + * successful or not + */ at91_adc_writel(st, AT91_ADC_CHDR, AT91_ADC_CH(chan->channel)); at91_adc_writel(st, AT91_ADC_IDR, BIT(chan->channel)); - st->last_value = 0; - st->done = false; + if (ret > 0) { + /* a valid conversion took place */ + *val = st->last_value; + st->last_value = 0; + st->done = false; + ret = IIO_VAL_INT; + } else if (ret == 0) { + /* conversion timeout */ + dev_err(&idev->dev, "ADC Channel %d timeout.\n", + chan->channel); + ret = -ETIMEDOUT; + } + mutex_unlock(&st->lock); - return IIO_VAL_INT; + return ret; case IIO_CHAN_INFO_SCALE: *val = st->vref_mv; diff --git a/drivers/iio/adc/xilinx-xadc-core.c b/drivers/iio/adc/xilinx-xadc-core.c index b13c61539d46..6401ca7a9a20 100644 --- a/drivers/iio/adc/xilinx-xadc-core.c +++ b/drivers/iio/adc/xilinx-xadc-core.c @@ -1292,6 +1292,7 @@ static int xadc_probe(struct platform_device *pdev) err_free_irq: free_irq(xadc->irq, indio_dev); + cancel_delayed_work_sync(&xadc->zynq_unmask_work); err_clk_disable_unprepare: clk_disable_unprepare(xadc->clk); err_free_samplerate_trigger: @@ -1321,8 +1322,8 @@ static int xadc_remove(struct platform_device *pdev) iio_triggered_buffer_cleanup(indio_dev); } free_irq(xadc->irq, indio_dev); + cancel_delayed_work_sync(&xadc->zynq_unmask_work); clk_disable_unprepare(xadc->clk); - cancel_delayed_work(&xadc->zynq_unmask_work); kfree(xadc->data); kfree(indio_dev->channels); diff --git a/drivers/iio/chemical/Kconfig b/drivers/iio/chemical/Kconfig index d5d146e9e372..92c684d2b67e 100644 --- a/drivers/iio/chemical/Kconfig +++ b/drivers/iio/chemical/Kconfig @@ -64,6 +64,7 @@ config IAQCORE config PMS7003 tristate "Plantower PMS7003 particulate matter sensor" depends on SERIAL_DEV_BUS + select IIO_TRIGGERED_BUFFER help Say Y here to build support for the Plantower PMS7003 particulate matter sensor. @@ -71,6 +72,19 @@ config PMS7003 To compile this driver as a module, choose M here: the module will be called pms7003. +config SENSIRION_SGP30 + tristate "Sensirion SGPxx gas sensors" + depends on I2C + select CRC8 + help + Say Y here to build I2C interface support for the following + Sensirion SGP gas sensors: + * SGP30 gas sensor + * SGPC3 low power gas sensor + + To compile this driver as module, choose M here: the + module will be called sgp30. + config SPS30 tristate "SPS30 particulate matter sensor" depends on I2C diff --git a/drivers/iio/chemical/bme680.h b/drivers/iio/chemical/bme680.h index 0ae89b87e2d6..4edc5d21cb9f 100644 --- a/drivers/iio/chemical/bme680.h +++ b/drivers/iio/chemical/bme680.h @@ -2,11 +2,9 @@ #ifndef BME680_H_ #define BME680_H_ -#define BME680_REG_CHIP_I2C_ID 0xD0 -#define BME680_REG_CHIP_SPI_ID 0x50 +#define BME680_REG_CHIP_ID 0xD0 #define BME680_CHIP_ID_VAL 0x61 -#define BME680_REG_SOFT_RESET_I2C 0xE0 -#define BME680_REG_SOFT_RESET_SPI 0x60 +#define BME680_REG_SOFT_RESET 0xE0 #define BME680_CMD_SOFTRESET 0xB6 #define BME680_REG_STATUS 0x73 #define BME680_SPI_MEM_PAGE_BIT BIT(4) diff --git a/drivers/iio/chemical/bme680_core.c b/drivers/iio/chemical/bme680_core.c index 70c1fe4366f4..ccde4c65ff93 100644 --- a/drivers/iio/chemical/bme680_core.c +++ b/drivers/iio/chemical/bme680_core.c @@ -63,9 +63,23 @@ struct bme680_data { s32 t_fine; }; +static const struct regmap_range bme680_volatile_ranges[] = { + regmap_reg_range(BME680_REG_MEAS_STAT_0, BME680_REG_GAS_R_LSB), + regmap_reg_range(BME680_REG_STATUS, BME680_REG_STATUS), + regmap_reg_range(BME680_T2_LSB_REG, BME680_GH3_REG), +}; + +static const struct regmap_access_table bme680_volatile_table = { + .yes_ranges = bme680_volatile_ranges, + .n_yes_ranges = ARRAY_SIZE(bme680_volatile_ranges), +}; + const struct regmap_config bme680_regmap_config = { .reg_bits = 8, .val_bits = 8, + .max_register = 0xef, + .volatile_table = &bme680_volatile_table, + .cache_type = REGCACHE_RBTREE, }; EXPORT_SYMBOL(bme680_regmap_config); @@ -316,6 +330,10 @@ static s16 bme680_compensate_temp(struct bme680_data *data, s64 var1, var2, var3; s16 calc_temp; + /* If the calibration is invalid, attempt to reload it */ + if (!calib->par_t2) + bme680_read_calib(data, calib); + var1 = (adc_temp >> 3) - (calib->par_t1 << 1); var2 = (var1 * calib->par_t2) >> 11; var3 = ((var1 >> 1) * (var1 >> 1)) >> 12; @@ -583,8 +601,7 @@ static int bme680_gas_config(struct bme680_data *data) return ret; } -static int bme680_read_temp(struct bme680_data *data, - int *val, int *val2) +static int bme680_read_temp(struct bme680_data *data, int *val) { struct device *dev = regmap_get_device(data->regmap); int ret; @@ -617,10 +634,9 @@ static int bme680_read_temp(struct bme680_data *data, * compensate_press/compensate_humid to get compensated * pressure/humidity readings. */ - if (val && val2) { - *val = comp_temp; - *val2 = 100; - return IIO_VAL_FRACTIONAL; + if (val) { + *val = comp_temp * 10; /* Centidegrees to millidegrees */ + return IIO_VAL_INT; } return ret; @@ -635,7 +651,7 @@ static int bme680_read_press(struct bme680_data *data, s32 adc_press; /* Read and compensate temperature to get a reading of t_fine */ - ret = bme680_read_temp(data, NULL, NULL); + ret = bme680_read_temp(data, NULL); if (ret < 0) return ret; @@ -668,7 +684,7 @@ static int bme680_read_humid(struct bme680_data *data, u32 comp_humidity; /* Read and compensate temperature to get a reading of t_fine */ - ret = bme680_read_temp(data, NULL, NULL); + ret = bme680_read_temp(data, NULL); if (ret < 0) return ret; @@ -761,7 +777,7 @@ static int bme680_read_raw(struct iio_dev *indio_dev, case IIO_CHAN_INFO_PROCESSED: switch (chan->type) { case IIO_TEMP: - return bme680_read_temp(data, val, val2); + return bme680_read_temp(data, val); case IIO_PRESSURE: return bme680_read_press(data, val, val2); case IIO_HUMIDITYRELATIVE: @@ -867,8 +883,28 @@ int bme680_core_probe(struct device *dev, struct regmap *regmap, { struct iio_dev *indio_dev; struct bme680_data *data; + unsigned int val; int ret; + ret = regmap_write(regmap, BME680_REG_SOFT_RESET, + BME680_CMD_SOFTRESET); + if (ret < 0) { + dev_err(dev, "Failed to reset chip\n"); + return ret; + } + + ret = regmap_read(regmap, BME680_REG_CHIP_ID, &val); + if (ret < 0) { + dev_err(dev, "Error reading chip ID\n"); + return ret; + } + + if (val != BME680_CHIP_ID_VAL) { + dev_err(dev, "Wrong chip ID, got %x expected %x\n", + val, BME680_CHIP_ID_VAL); + return -ENODEV; + } + indio_dev = devm_iio_device_alloc(dev, sizeof(*data)); if (!indio_dev) return -ENOMEM; diff --git a/drivers/iio/chemical/bme680_i2c.c b/drivers/iio/chemical/bme680_i2c.c index b2f805b6b36a..de9c9e3d23ea 100644 --- a/drivers/iio/chemical/bme680_i2c.c +++ b/drivers/iio/chemical/bme680_i2c.c @@ -23,8 +23,6 @@ static int bme680_i2c_probe(struct i2c_client *client, { struct regmap *regmap; const char *name = NULL; - unsigned int val; - int ret; regmap = devm_regmap_init_i2c(client, &bme680_regmap_config); if (IS_ERR(regmap)) { @@ -33,25 +31,6 @@ static int bme680_i2c_probe(struct i2c_client *client, return PTR_ERR(regmap); } - ret = regmap_write(regmap, BME680_REG_SOFT_RESET_I2C, - BME680_CMD_SOFTRESET); - if (ret < 0) { - dev_err(&client->dev, "Failed to reset chip\n"); - return ret; - } - - ret = regmap_read(regmap, BME680_REG_CHIP_I2C_ID, &val); - if (ret < 0) { - dev_err(&client->dev, "Error reading I2C chip ID\n"); - return ret; - } - - if (val != BME680_CHIP_ID_VAL) { - dev_err(&client->dev, "Wrong chip ID, got %x expected %x\n", - val, BME680_CHIP_ID_VAL); - return -ENODEV; - } - if (id) name = id->name; diff --git a/drivers/iio/chemical/bme680_spi.c b/drivers/iio/chemical/bme680_spi.c index d0b7bdd3f066..3b838068a7e4 100644 --- a/drivers/iio/chemical/bme680_spi.c +++ b/drivers/iio/chemical/bme680_spi.c @@ -12,28 +12,93 @@ #include "bme680.h" +struct bme680_spi_bus_context { + struct spi_device *spi; + u8 current_page; +}; + +/* + * In SPI mode there are only 7 address bits, a "page" register determines + * which part of the 8-bit range is active. This function looks at the address + * and writes the page selection bit if needed + */ +static int bme680_regmap_spi_select_page( + struct bme680_spi_bus_context *ctx, u8 reg) +{ + struct spi_device *spi = ctx->spi; + int ret; + u8 buf[2]; + u8 page = (reg & 0x80) ? 0 : 1; /* Page "1" is low range */ + + if (page == ctx->current_page) + return 0; + + /* + * Data sheet claims we're only allowed to change bit 4, so we must do + * a read-modify-write on each and every page select + */ + buf[0] = BME680_REG_STATUS; + ret = spi_write_then_read(spi, buf, 1, buf + 1, 1); + if (ret < 0) { + dev_err(&spi->dev, "failed to set page %u\n", page); + return ret; + } + + buf[0] = BME680_REG_STATUS; + if (page) + buf[1] |= BME680_SPI_MEM_PAGE_BIT; + else + buf[1] &= ~BME680_SPI_MEM_PAGE_BIT; + + ret = spi_write(spi, buf, 2); + if (ret < 0) { + dev_err(&spi->dev, "failed to set page %u\n", page); + return ret; + } + + ctx->current_page = page; + + return 0; +} + static int bme680_regmap_spi_write(void *context, const void *data, size_t count) { - struct spi_device *spi = context; + struct bme680_spi_bus_context *ctx = context; + struct spi_device *spi = ctx->spi; + int ret; u8 buf[2]; memcpy(buf, data, 2); + + ret = bme680_regmap_spi_select_page(ctx, buf[0]); + if (ret) + return ret; + /* * The SPI register address (= full register address without bit 7) * and the write command (bit7 = RW = '0') */ buf[0] &= ~0x80; - return spi_write_then_read(spi, buf, 2, NULL, 0); + return spi_write(spi, buf, 2); } static int bme680_regmap_spi_read(void *context, const void *reg, size_t reg_size, void *val, size_t val_size) { - struct spi_device *spi = context; + struct bme680_spi_bus_context *ctx = context; + struct spi_device *spi = ctx->spi; + int ret; + u8 addr = *(const u8 *)reg; + + ret = bme680_regmap_spi_select_page(ctx, addr); + if (ret) + return ret; - return spi_write_then_read(spi, reg, reg_size, val, val_size); + addr |= 0x80; /* bit7 = RW = '1' */ + + return spi_write_then_read(spi, &addr, 1, val, val_size); } static struct regmap_bus bme680_regmap_bus = { @@ -46,8 +111,8 @@ static struct regmap_bus bme680_regmap_bus = { static int bme680_spi_probe(struct spi_device *spi) { const struct spi_device_id *id = spi_get_device_id(spi); + struct bme680_spi_bus_context *bus_context; struct regmap *regmap; - unsigned int val; int ret; spi->bits_per_word = 8; @@ -57,45 +122,21 @@ static int bme680_spi_probe(struct spi_device *spi) return ret; } + bus_context = devm_kzalloc(&spi->dev, sizeof(*bus_context), GFP_KERNEL); + if (!bus_context) + return -ENOMEM; + + bus_context->spi = spi; + bus_context->current_page = 0xff; /* Undefined on warm boot */ + regmap = devm_regmap_init(&spi->dev, &bme680_regmap_bus, - &spi->dev, &bme680_regmap_config); + bus_context, &bme680_regmap_config); if (IS_ERR(regmap)) { dev_err(&spi->dev, "Failed to register spi regmap %d\n", (int)PTR_ERR(regmap)); return PTR_ERR(regmap); } - ret = regmap_write(regmap, BME680_REG_SOFT_RESET_SPI, - BME680_CMD_SOFTRESET); - if (ret < 0) { - dev_err(&spi->dev, "Failed to reset chip\n"); - return ret; - } - - /* after power-on reset, Page 0(0x80-0xFF) of spi_mem_page is active */ - ret = regmap_read(regmap, BME680_REG_CHIP_SPI_ID, &val); - if (ret < 0) { - dev_err(&spi->dev, "Error reading SPI chip ID\n"); - return ret; - } - - if (val != BME680_CHIP_ID_VAL) { - dev_err(&spi->dev, "Wrong chip ID, got %x expected %x\n", - val, BME680_CHIP_ID_VAL); - return -ENODEV; - } - /* - * select Page 1 of spi_mem_page to enable access to - * to registers from address 0x00 to 0x7F. - */ - ret = regmap_write_bits(regmap, BME680_REG_STATUS, - BME680_SPI_MEM_PAGE_BIT, - BME680_SPI_MEM_PAGE_1_VAL); - if (ret < 0) { - dev_err(&spi->dev, "failed to set page 1 of spi_mem_page\n"); - return ret; - } - return bme680_core_probe(&spi->dev, regmap, id->name); } diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c index 89cb0066a6e0..8d76afb87d87 100644 --- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c +++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c @@ -103,9 +103,10 @@ static int cros_ec_sensors_read(struct iio_dev *indio_dev, * Do not use IIO_DEGREE_TO_RAD to avoid precision * loss. Round to the nearest integer. */ - *val = div_s64(val64 * 314159 + 9000000ULL, 1000); - *val2 = 18000 << (CROS_EC_SENSOR_BITS - 1); - ret = IIO_VAL_FRACTIONAL; + *val = 0; + *val2 = div_s64(val64 * 3141592653ULL, + 180 << (CROS_EC_SENSOR_BITS - 1)); + ret = IIO_VAL_INT_PLUS_NANO; break; case MOTIONSENSE_TYPE_MAG: /* diff --git a/drivers/iio/dac/mcp4725.c b/drivers/iio/dac/mcp4725.c index 6d71fd905e29..c701a45469f6 100644 --- a/drivers/iio/dac/mcp4725.c +++ b/drivers/iio/dac/mcp4725.c @@ -92,6 +92,7 @@ static ssize_t mcp4725_store_eeprom(struct device *dev, inoutbuf[0] = 0x60; /* write EEPROM */ inoutbuf[0] |= data->ref_mode << 3; + inoutbuf[0] |= data->powerdown ? ((data->powerdown_mode + 1) << 1) : 0; inoutbuf[1] = data->dac_value >> 4; inoutbuf[2] = (data->dac_value & 0xf) << 4; diff --git a/drivers/iio/gyro/bmg160_core.c b/drivers/iio/gyro/bmg160_core.c index 63ca31628a93..92c07ab826eb 100644 --- a/drivers/iio/gyro/bmg160_core.c +++ b/drivers/iio/gyro/bmg160_core.c @@ -582,11 +582,10 @@ static int bmg160_read_raw(struct iio_dev *indio_dev, case IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY: return bmg160_get_filter(data, val); case IIO_CHAN_INFO_SCALE: - *val = 0; switch (chan->type) { case IIO_TEMP: - *val2 = 500000; - return IIO_VAL_INT_PLUS_MICRO; + *val = 500; + return IIO_VAL_INT; case IIO_ANGL_VEL: { int i; @@ -594,6 +593,7 @@ static int bmg160_read_raw(struct iio_dev *indio_dev, for (i = 0; i < ARRAY_SIZE(bmg160_scale_table); ++i) { if (bmg160_scale_table[i].dps_range == data->dps_range) { + *val = 0; *val2 = bmg160_scale_table[i].scale; return IIO_VAL_INT_PLUS_MICRO; } diff --git a/drivers/iio/gyro/mpu3050-core.c b/drivers/iio/gyro/mpu3050-core.c index 77fac81a3adc..5ddebede31a6 100644 --- a/drivers/iio/gyro/mpu3050-core.c +++ b/drivers/iio/gyro/mpu3050-core.c @@ -29,7 +29,8 @@ #include "mpu3050.h" -#define MPU3050_CHIP_ID 0x69 +#define MPU3050_CHIP_ID 0x68 +#define MPU3050_CHIP_ID_MASK 0x7E /* * Register map: anything suffixed *_H is a big-endian high byte and always @@ -1176,8 +1177,9 @@ int mpu3050_common_probe(struct device *dev, goto err_power_down; } - if (val != MPU3050_CHIP_ID) { - dev_err(dev, "unsupported chip id %02x\n", (u8)val); + if ((val & MPU3050_CHIP_ID_MASK) != MPU3050_CHIP_ID) { + dev_err(dev, "unsupported chip id %02x\n", + (u8)(val & MPU3050_CHIP_ID_MASK)); ret = -ENODEV; goto err_power_down; } diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c index cd5bfe39591b..dadd921a4a30 100644 --- a/drivers/iio/industrialio-buffer.c +++ b/drivers/iio/industrialio-buffer.c @@ -320,9 +320,8 @@ static int iio_scan_mask_set(struct iio_dev *indio_dev, const unsigned long *mask; unsigned long *trialmask; - trialmask = kmalloc_array(BITS_TO_LONGS(indio_dev->masklength), - sizeof(*trialmask), - GFP_KERNEL); + trialmask = kcalloc(BITS_TO_LONGS(indio_dev->masklength), + sizeof(*trialmask), GFP_KERNEL); if (trialmask == NULL) return -ENOMEM; if (!indio_dev->masklength) { diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index 4700fd5d8c90..9c4d92115504 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -1743,10 +1743,10 @@ EXPORT_SYMBOL(__iio_device_register); **/ void iio_device_unregister(struct iio_dev *indio_dev) { - mutex_lock(&indio_dev->info_exist_lock); - cdev_device_del(&indio_dev->chrdev, &indio_dev->dev); + mutex_lock(&indio_dev->info_exist_lock); + iio_device_unregister_debugfs(indio_dev); iio_disable_all_buffers(indio_dev); diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h index ea0bc6885517..32cc8fe7902f 100644 --- a/drivers/infiniband/core/uverbs.h +++ b/drivers/infiniband/core/uverbs.h @@ -160,6 +160,7 @@ struct ib_uverbs_file { struct mutex umap_lock; struct list_head umaps; + struct page *disassociate_page; struct idr idr; /* spinlock protects write access to idr */ diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 70b7d80431a9..c489f545baae 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -208,6 +208,9 @@ void ib_uverbs_release_file(struct kref *ref) kref_put(&file->async_file->ref, ib_uverbs_release_async_event_file); put_device(&file->device->dev); + + if (file->disassociate_page) + __free_pages(file->disassociate_page, 0); kfree(file); } @@ -877,9 +880,50 @@ static void rdma_umap_close(struct vm_area_struct *vma) kfree(priv); } +/* + * Once the zap_vma_ptes has been called touches to the VMA will come here and + * we return a dummy writable zero page for all the pfns. + */ +static vm_fault_t rdma_umap_fault(struct vm_fault *vmf) +{ + struct ib_uverbs_file *ufile = vmf->vma->vm_file->private_data; + struct rdma_umap_priv *priv = vmf->vma->vm_private_data; + vm_fault_t ret = 0; + + if (!priv) + return VM_FAULT_SIGBUS; + + /* Read only pages can just use the system zero page. */ + if (!(vmf->vma->vm_flags & (VM_WRITE | VM_MAYWRITE))) { + vmf->page = ZERO_PAGE(vmf->address); + get_page(vmf->page); + return 0; + } + + mutex_lock(&ufile->umap_lock); + if (!ufile->disassociate_page) + ufile->disassociate_page = + alloc_pages(vmf->gfp_mask | __GFP_ZERO, 0); + + if (ufile->disassociate_page) { + /* + * This VMA is forced to always be shared so this doesn't have + * to worry about COW. + */ + vmf->page = ufile->disassociate_page; + get_page(vmf->page); + } else { + ret = VM_FAULT_SIGBUS; + } + mutex_unlock(&ufile->umap_lock); + + return ret; +} + static const struct vm_operations_struct rdma_umap_ops = { .open = rdma_umap_open, .close = rdma_umap_close, + .fault = rdma_umap_fault, }; static struct rdma_umap_priv *rdma_user_mmap_pre(struct ib_ucontext *ucontext, @@ -889,6 +933,9 @@ static struct rdma_umap_priv *rdma_user_mmap_pre(struct ib_ucontext *ucontext, struct ib_uverbs_file *ufile = ucontext->ufile; struct rdma_umap_priv *priv; + if (!(vma->vm_flags & VM_SHARED)) + return ERR_PTR(-EINVAL); + if (vma->vm_end - vma->vm_start != size) return ERR_PTR(-EINVAL); @@ -992,7 +1039,9 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile) * at a time to get the lock ordering right. Typically there * will only be one mm, so no big deal. */ - down_write(&mm->mmap_sem); + down_read(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto skip_mm; mutex_lock(&ufile->umap_lock); list_for_each_entry_safe (priv, next_priv, &ufile->umaps, list) { @@ -1004,10 +1053,10 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile) zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start); - vma->vm_flags &= ~(VM_SHARED | VM_MAYSHARE); } mutex_unlock(&ufile->umap_lock); - up_write(&mm->mmap_sem); + skip_mm: + up_read(&mm->mmap_sem); mmput(mm); } } diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 612f04190ed8..9784c6c0d2ec 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -13232,7 +13232,7 @@ static int set_up_context_variables(struct hfi1_devdata *dd) int total_contexts; int ret; unsigned ngroups; - int qos_rmt_count; + int rmt_count; int user_rmt_reduced; u32 n_usr_ctxts; u32 send_contexts = chip_send_contexts(dd); @@ -13294,10 +13294,20 @@ static int set_up_context_variables(struct hfi1_devdata *dd) n_usr_ctxts = rcv_contexts - total_contexts; } - /* each user context requires an entry in the RMT */ - qos_rmt_count = qos_rmt_entries(dd, NULL, NULL); - if (qos_rmt_count + n_usr_ctxts > NUM_MAP_ENTRIES) { - user_rmt_reduced = NUM_MAP_ENTRIES - qos_rmt_count; + /* + * The RMT entries are currently allocated as shown below: + * 1. QOS (0 to 128 entries); + * 2. FECN for PSM (num_user_contexts + num_vnic_contexts); + * 3. VNIC (num_vnic_contexts). + * It should be noted that PSM FECN oversubscribe num_vnic_contexts + * entries of RMT because both VNIC and PSM could allocate any receive + * context between dd->first_dyn_alloc_text and dd->num_rcv_contexts, + * and PSM FECN must reserve an RMT entry for each possible PSM receive + * context. + */ + rmt_count = qos_rmt_entries(dd, NULL, NULL) + (num_vnic_contexts * 2); + if (rmt_count + n_usr_ctxts > NUM_MAP_ENTRIES) { + user_rmt_reduced = NUM_MAP_ENTRIES - rmt_count; dd_dev_err(dd, "RMT size is reducing the number of user receive contexts from %u to %d\n", n_usr_ctxts, @@ -14285,9 +14295,11 @@ static void init_user_fecn_handling(struct hfi1_devdata *dd, u64 reg; int i, idx, regoff, regidx; u8 offset; + u32 total_cnt; /* there needs to be enough room in the map table */ - if (rmt->used + dd->num_user_contexts >= NUM_MAP_ENTRIES) { + total_cnt = dd->num_rcv_contexts - dd->first_dyn_alloc_ctxt; + if (rmt->used + total_cnt >= NUM_MAP_ENTRIES) { dd_dev_err(dd, "User FECN handling disabled - too many user contexts allocated\n"); return; } @@ -14341,7 +14353,7 @@ static void init_user_fecn_handling(struct hfi1_devdata *dd, /* add rule 1 */ add_rsm_rule(dd, RSM_INS_FECN, &rrd); - rmt->used += dd->num_user_contexts; + rmt->used += total_cnt; } /* Initialize RSM for VNIC */ diff --git a/drivers/infiniband/hw/hfi1/qp.c b/drivers/infiniband/hw/hfi1/qp.c index 9b643c2409cf..eba300330a02 100644 --- a/drivers/infiniband/hw/hfi1/qp.c +++ b/drivers/infiniband/hw/hfi1/qp.c @@ -898,7 +898,9 @@ void notify_error_qp(struct rvt_qp *qp) if (!list_empty(&priv->s_iowait.list) && !(qp->s_flags & RVT_S_BUSY) && !(priv->s_flags & RVT_S_BUSY)) { - qp->s_flags &= ~RVT_S_ANY_WAIT_IO; + qp->s_flags &= ~HFI1_S_ANY_WAIT_IO; + iowait_clear_flag(&priv->s_iowait, IOWAIT_PENDING_IB); + iowait_clear_flag(&priv->s_iowait, IOWAIT_PENDING_TID); list_del_init(&priv->s_iowait.list); priv->s_iowait.lock = NULL; rvt_put_qp(qp); diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c index e6726c1ab866..5991211d72bd 100644 --- a/drivers/infiniband/hw/hfi1/rc.c +++ b/drivers/infiniband/hw/hfi1/rc.c @@ -3088,7 +3088,7 @@ send_last: update_ack_queue(qp, next); } e = &qp->s_ack_queue[qp->r_head_ack_queue]; - if (e->opcode == OP(RDMA_READ_REQUEST) && e->rdma_sge.mr) { + if (e->rdma_sge.mr) { rvt_put_mr(e->rdma_sge.mr); e->rdma_sge.mr = NULL; } @@ -3166,7 +3166,7 @@ send_last: update_ack_queue(qp, next); } e = &qp->s_ack_queue[qp->r_head_ack_queue]; - if (e->opcode == OP(RDMA_READ_REQUEST) && e->rdma_sge.mr) { + if (e->rdma_sge.mr) { rvt_put_mr(e->rdma_sge.mr); e->rdma_sge.mr = NULL; } diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c index fdda33aca77f..43cbce7a19ea 100644 --- a/drivers/infiniband/hw/hfi1/tid_rdma.c +++ b/drivers/infiniband/hw/hfi1/tid_rdma.c @@ -5017,24 +5017,14 @@ int hfi1_make_tid_rdma_pkt(struct rvt_qp *qp, struct hfi1_pkt_state *ps) make_tid_rdma_ack(qp, ohdr, ps)) return 1; - if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_SEND_OK)) { - if (!(ib_rvt_state_ops[qp->state] & RVT_FLUSH_SEND)) - goto bail; - /* We are in the error state, flush the work request. */ - if (qp->s_last == READ_ONCE(qp->s_head)) - goto bail; - /* If DMAs are in progress, we can't flush immediately. */ - if (iowait_sdma_pending(&priv->s_iowait)) { - qp->s_flags |= RVT_S_WAIT_DMA; - goto bail; - } - clear_ahg(qp); - wqe = rvt_get_swqe_ptr(qp, qp->s_last); - hfi1_trdma_send_complete(qp, wqe, qp->s_last != qp->s_acked ? - IB_WC_SUCCESS : IB_WC_WR_FLUSH_ERR); - /* will get called again */ - goto done_free_tx; - } + /* + * Bail out if we can't send data. + * Be reminded that this check must been done after the call to + * make_tid_rdma_ack() because the responding QP could be in + * RTR state where it can send TID RDMA ACK, not TID RDMA WRITE DATA. + */ + if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_SEND_OK)) + goto bail; if (priv->s_flags & RVT_S_WAIT_ACK) goto bail; @@ -5144,11 +5134,6 @@ int hfi1_make_tid_rdma_pkt(struct rvt_qp *qp, struct hfi1_pkt_state *ps) hfi1_make_ruc_header(qp, ohdr, (opcode << 24), bth1, bth2, middle, ps); return 1; -done_free_tx: - hfi1_put_txreq(ps->s_txreq); - ps->s_txreq = NULL; - return 1; - bail: hfi1_put_txreq(ps->s_txreq); bail_no_tx: diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.c b/drivers/infiniband/hw/hns/hns_roce_hem.c index f1fec56f3ff4..8e29dbb5b5fb 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hem.c +++ b/drivers/infiniband/hw/hns/hns_roce_hem.c @@ -792,6 +792,8 @@ void *hns_roce_table_find(struct hns_roce_dev *hr_dev, idx_offset = (obj & (table->num_obj - 1)) % obj_per_chunk; dma_offset = offset = idx_offset * table->obj_size; } else { + u32 seg_size = 64; /* 8 bytes per BA and 8 BA per segment */ + hns_roce_calc_hem_mhop(hr_dev, table, &mhop_obj, &mhop); /* mtt mhop */ i = mhop.l0_idx; @@ -803,8 +805,8 @@ void *hns_roce_table_find(struct hns_roce_dev *hr_dev, hem_idx = i; hem = table->hem[hem_idx]; - dma_offset = offset = (obj & (table->num_obj - 1)) * - table->obj_size % mhop.bt_chunk_size; + dma_offset = offset = (obj & (table->num_obj - 1)) * seg_size % + mhop.bt_chunk_size; if (mhop.hop_num == 2) dma_offset = offset = 0; } diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c index b09f1cde2ff5..08be0e4eabcd 100644 --- a/drivers/infiniband/hw/hns/hns_roce_mr.c +++ b/drivers/infiniband/hw/hns/hns_roce_mr.c @@ -746,7 +746,6 @@ static int hns_roce_write_mtt_chunk(struct hns_roce_dev *hr_dev, struct hns_roce_hem_table *table; dma_addr_t dma_handle; __le64 *mtts; - u32 s = start_index * sizeof(u64); u32 bt_page_size; u32 i; @@ -780,7 +779,8 @@ static int hns_roce_write_mtt_chunk(struct hns_roce_dev *hr_dev, return -EINVAL; mtts = hns_roce_table_find(hr_dev, table, - mtt->first_seg + s / hr_dev->caps.mtt_entry_sz, + mtt->first_seg + + start_index / HNS_ROCE_MTT_ENTRY_PER_SEG, &dma_handle); if (!mtts) return -ENOMEM; diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c index 57c76eafef2f..60cf9f03e941 100644 --- a/drivers/infiniband/hw/hns/hns_roce_qp.c +++ b/drivers/infiniband/hw/hns/hns_roce_qp.c @@ -274,9 +274,6 @@ void hns_roce_qp_free(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp) wait_for_completion(&hr_qp->free); if ((hr_qp->ibqp.qp_type) != IB_QPT_GSI) { - if (hr_dev->caps.sccc_entry_sz) - hns_roce_table_put(hr_dev, &qp_table->sccc_table, - hr_qp->qpn); if (hr_dev->caps.trrl_entry_sz) hns_roce_table_put(hr_dev, &qp_table->trrl_table, hr_qp->qpn); @@ -536,7 +533,7 @@ static int hns_roce_set_kernel_sq_size(struct hns_roce_dev *hr_dev, static int hns_roce_qp_has_sq(struct ib_qp_init_attr *attr) { - if (attr->qp_type == IB_QPT_XRC_TGT) + if (attr->qp_type == IB_QPT_XRC_TGT || !attr->cap.max_send_wr) return 0; return 1; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 531ff20b32ad..d3dd290ae1b1 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -1119,6 +1119,8 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, if (MLX5_CAP_GEN(mdev, qp_packet_based)) resp.flags |= MLX5_IB_QUERY_DEV_RESP_PACKET_BASED_CREDIT_MODE; + + resp.flags |= MLX5_IB_QUERY_DEV_RESP_FLAGS_SCAT2CQE_DCT; } if (field_avail(typeof(resp), sw_parsing_caps, @@ -2066,6 +2068,7 @@ static int mlx5_ib_mmap_clock_info_page(struct mlx5_ib_dev *dev, if (vma->vm_flags & VM_WRITE) return -EPERM; + vma->vm_flags &= ~VM_MAYWRITE; if (!dev->mdev->clock_info_page) return -EOPNOTSUPP; @@ -2231,19 +2234,18 @@ static int mlx5_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vm if (vma->vm_flags & VM_WRITE) return -EPERM; + vma->vm_flags &= ~VM_MAYWRITE; /* Don't expose to user-space information it shouldn't have */ if (PAGE_SIZE > 4096) return -EOPNOTSUPP; - vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); pfn = (dev->mdev->iseg_base + offsetof(struct mlx5_init_seg, internal_timer_h)) >> PAGE_SHIFT; - if (io_remap_pfn_range(vma, vma->vm_start, pfn, - PAGE_SIZE, vma->vm_page_prot)) - return -EAGAIN; - break; + return rdma_user_mmap_io(&context->ibucontext, vma, pfn, + PAGE_SIZE, + pgprot_noncached(vma->vm_page_prot)); case MLX5_IB_MMAP_CLOCK_INFO: return mlx5_ib_mmap_clock_info_page(dev, vma, context); diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index c20bfc41ecf1..0aa10ebda5d9 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -585,7 +585,7 @@ static int pagefault_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr, struct ib_umem_odp *odp_mr = to_ib_umem_odp(mr->umem); bool downgrade = flags & MLX5_PF_FLAGS_DOWNGRADE; bool prefetch = flags & MLX5_PF_FLAGS_PREFETCH; - u64 access_mask = ODP_READ_ALLOWED_BIT; + u64 access_mask; u64 start_idx, page_mask; struct ib_umem_odp *odp; size_t size; @@ -607,6 +607,7 @@ next_mr: page_shift = mr->umem->page_shift; page_mask = ~(BIT(page_shift) - 1); start_idx = (io_virt - (mr->mmkey.iova & page_mask)) >> page_shift; + access_mask = ODP_READ_ALLOWED_BIT; if (prefetch && !downgrade && !mr->umem->writable) { /* prefetch with write-access must diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 7cd006da1dae..8870c350fda0 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -1818,13 +1818,16 @@ static void configure_responder_scat_cqe(struct ib_qp_init_attr *init_attr, rcqe_sz = mlx5_ib_get_cqe_size(init_attr->recv_cq); - if (rcqe_sz == 128) { - MLX5_SET(qpc, qpc, cs_res, MLX5_RES_SCAT_DATA64_CQE); + if (init_attr->qp_type == MLX5_IB_QPT_DCT) { + if (rcqe_sz == 128) + MLX5_SET(dctc, qpc, cs_res, MLX5_RES_SCAT_DATA64_CQE); + return; } - if (init_attr->qp_type != MLX5_IB_QPT_DCT) - MLX5_SET(qpc, qpc, cs_res, MLX5_RES_SCAT_DATA32_CQE); + MLX5_SET(qpc, qpc, cs_res, + rcqe_sz == 128 ? MLX5_RES_SCAT_DATA64_CQE : + MLX5_RES_SCAT_DATA32_CQE); } static void configure_requester_scat_cqe(struct mlx5_ib_dev *dev, diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c index 6d8b3e0de57a..ec41400fec0c 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c @@ -1131,6 +1131,8 @@ static void pvrdma_pci_remove(struct pci_dev *pdev) pvrdma_page_dir_cleanup(dev, &dev->cq_pdir); pvrdma_page_dir_cleanup(dev, &dev->async_pdir); pvrdma_free_slots(dev); + dma_free_coherent(&pdev->dev, sizeof(*dev->dsr), dev->dsr, + dev->dsrbase); iounmap(dev->regs); kfree(dev->sgid_tbl); diff --git a/drivers/infiniband/sw/rdmavt/mr.c b/drivers/infiniband/sw/rdmavt/mr.c index 728795043496..0bb6e39dd03a 100644 --- a/drivers/infiniband/sw/rdmavt/mr.c +++ b/drivers/infiniband/sw/rdmavt/mr.c @@ -608,11 +608,6 @@ static int rvt_set_page(struct ib_mr *ibmr, u64 addr) if (unlikely(mapped_segs == mr->mr.max_segs)) return -ENOMEM; - if (mr->mr.length == 0) { - mr->mr.user_base = addr; - mr->mr.iova = addr; - } - m = mapped_segs / RVT_SEGSZ; n = mapped_segs % RVT_SEGSZ; mr->mr.map[m]->segs[n].vaddr = (void *)addr; @@ -630,17 +625,24 @@ static int rvt_set_page(struct ib_mr *ibmr, u64 addr) * @sg_nents: number of entries in sg * @sg_offset: offset in bytes into sg * + * Overwrite rvt_mr length with mr length calculated by ib_sg_to_pages. + * * Return: number of sg elements mapped to the memory region */ int rvt_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset) { struct rvt_mr *mr = to_imr(ibmr); + int ret; mr->mr.length = 0; mr->mr.page_shift = PAGE_SHIFT; - return ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset, - rvt_set_page); + ret = ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset, rvt_set_page); + mr->mr.user_base = ibmr->iova; + mr->mr.iova = ibmr->iova; + mr->mr.offset = ibmr->iova - (u64)mr->mr.map[0]->segs[0].vaddr; + mr->mr.length = (size_t)ibmr->length; + return ret; } /** @@ -671,6 +673,7 @@ int rvt_fast_reg_mr(struct rvt_qp *qp, struct ib_mr *ibmr, u32 key, ibmr->rkey = key; mr->mr.lkey = key; mr->mr.access_flags = access; + mr->mr.iova = ibmr->iova; atomic_set(&mr->mr.lkey_invalid, 0); return 0; diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig index a878351f1643..52d7f55fca32 100644 --- a/drivers/input/keyboard/Kconfig +++ b/drivers/input/keyboard/Kconfig @@ -420,7 +420,7 @@ config KEYBOARD_MPR121 config KEYBOARD_SNVS_PWRKEY tristate "IMX SNVS Power Key Driver" - depends on SOC_IMX6SX || SOC_IMX7D + depends on ARCH_MXC || COMPILE_TEST depends on OF help This is the snvs powerkey driver for the Freescale i.MX application diff --git a/drivers/input/keyboard/snvs_pwrkey.c b/drivers/input/keyboard/snvs_pwrkey.c index effb63205d3d..4c67cf30a5d9 100644 --- a/drivers/input/keyboard/snvs_pwrkey.c +++ b/drivers/input/keyboard/snvs_pwrkey.c @@ -148,6 +148,9 @@ static int imx_snvs_pwrkey_probe(struct platform_device *pdev) return error; } + pdata->input = input; + platform_set_drvdata(pdev, pdata); + error = devm_request_irq(&pdev->dev, pdata->irq, imx_snvs_pwrkey_interrupt, 0, pdev->name, pdev); @@ -163,9 +166,6 @@ static int imx_snvs_pwrkey_probe(struct platform_device *pdev) return error; } - pdata->input = input; - platform_set_drvdata(pdev, pdata); - device_init_wakeup(&pdev->dev, pdata->wakeup); return 0; diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c index 628ef617bb2f..f9525d6f0bfe 100644 --- a/drivers/input/mouse/elan_i2c_core.c +++ b/drivers/input/mouse/elan_i2c_core.c @@ -1339,21 +1339,46 @@ static const struct acpi_device_id elan_acpi_id[] = { { "ELAN0600", 0 }, { "ELAN0601", 0 }, { "ELAN0602", 0 }, + { "ELAN0603", 0 }, + { "ELAN0604", 0 }, { "ELAN0605", 0 }, + { "ELAN0606", 0 }, + { "ELAN0607", 0 }, { "ELAN0608", 0 }, { "ELAN0609", 0 }, { "ELAN060B", 0 }, { "ELAN060C", 0 }, + { "ELAN060F", 0 }, + { "ELAN0610", 0 }, { "ELAN0611", 0 }, { "ELAN0612", 0 }, + { "ELAN0615", 0 }, + { "ELAN0616", 0 }, { "ELAN0617", 0 }, { "ELAN0618", 0 }, + { "ELAN0619", 0 }, + { "ELAN061A", 0 }, + { "ELAN061B", 0 }, { "ELAN061C", 0 }, { "ELAN061D", 0 }, { "ELAN061E", 0 }, + { "ELAN061F", 0 }, { "ELAN0620", 0 }, { "ELAN0621", 0 }, { "ELAN0622", 0 }, + { "ELAN0623", 0 }, + { "ELAN0624", 0 }, + { "ELAN0625", 0 }, + { "ELAN0626", 0 }, + { "ELAN0627", 0 }, + { "ELAN0628", 0 }, + { "ELAN0629", 0 }, + { "ELAN062A", 0 }, + { "ELAN062B", 0 }, + { "ELAN062C", 0 }, + { "ELAN062D", 0 }, + { "ELAN0631", 0 }, + { "ELAN0632", 0 }, { "ELAN1000", 0 }, { } }; diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c index fc3ab93b7aea..7fb358f96195 100644 --- a/drivers/input/rmi4/rmi_driver.c +++ b/drivers/input/rmi4/rmi_driver.c @@ -860,7 +860,7 @@ static int rmi_create_function(struct rmi_device *rmi_dev, error = rmi_register_function(fn); if (error) - goto err_put_fn; + return error; if (pdt->function_number == 0x01) data->f01_container = fn; @@ -870,10 +870,6 @@ static int rmi_create_function(struct rmi_device *rmi_dev, list_add_tail(&fn->node, &data->function_list); return RMI_SCAN_CONTINUE; - -err_put_fn: - put_device(&fn->dev); - return error; } void rmi_enable_irq(struct rmi_device *rmi_dev, bool clear_wake) diff --git a/drivers/input/rmi4/rmi_f11.c b/drivers/input/rmi4/rmi_f11.c index df64d6aed4f7..93901ebd122a 100644 --- a/drivers/input/rmi4/rmi_f11.c +++ b/drivers/input/rmi4/rmi_f11.c @@ -1230,7 +1230,7 @@ static int rmi_f11_initialize(struct rmi_function *fn) } rc = f11_write_control_regs(fn, &f11->sens_query, - &f11->dev_controls, fn->fd.query_base_addr); + &f11->dev_controls, fn->fd.control_base_addr); if (rc) dev_warn(&fn->dev, "Failed to write control registers\n"); diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 21cb088d6687..f7cdd2ab7f11 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -3169,21 +3169,24 @@ static void amd_iommu_get_resv_regions(struct device *dev, return; list_for_each_entry(entry, &amd_iommu_unity_map, list) { + int type, prot = 0; size_t length; - int prot = 0; if (devid < entry->devid_start || devid > entry->devid_end) continue; + type = IOMMU_RESV_DIRECT; length = entry->address_end - entry->address_start; if (entry->prot & IOMMU_PROT_IR) prot |= IOMMU_READ; if (entry->prot & IOMMU_PROT_IW) prot |= IOMMU_WRITE; + if (entry->prot & IOMMU_UNITY_MAP_FLAG_EXCL_RANGE) + /* Exclusion range */ + type = IOMMU_RESV_RESERVED; region = iommu_alloc_resv_region(entry->address_start, - length, prot, - IOMMU_RESV_DIRECT); + length, prot, type); if (!region) { dev_err(dev, "Out of memory allocating dm-regions\n"); return; diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index f773792d77fd..ff40ba758cf3 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -359,7 +359,7 @@ static void iommu_write_l2(struct amd_iommu *iommu, u8 address, u32 val) static void iommu_set_exclusion_range(struct amd_iommu *iommu) { u64 start = iommu->exclusion_start & PAGE_MASK; - u64 limit = (start + iommu->exclusion_length) & PAGE_MASK; + u64 limit = (start + iommu->exclusion_length - 1) & PAGE_MASK; u64 entry; if (!iommu->exclusion_start) @@ -2013,6 +2013,9 @@ static int __init init_unity_map_range(struct ivmd_header *m) if (e == NULL) return -ENOMEM; + if (m->flags & IVMD_FLAG_EXCL_RANGE) + init_exclusion_range(m); + switch (m->type) { default: kfree(e); @@ -2059,9 +2062,7 @@ static int __init init_memory_definitions(struct acpi_table_header *table) while (p < end) { m = (struct ivmd_header *)p; - if (m->flags & IVMD_FLAG_EXCL_RANGE) - init_exclusion_range(m); - else if (m->flags & IVMD_FLAG_UNITY_MAP) + if (m->flags & (IVMD_FLAG_UNITY_MAP | IVMD_FLAG_EXCL_RANGE)) init_unity_map_range(m); p += m->length; diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index eae0741f72dc..87965e4d9647 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -374,6 +374,8 @@ #define IOMMU_PROT_IR 0x01 #define IOMMU_PROT_IW 0x02 +#define IOMMU_UNITY_MAP_FLAG_EXCL_RANGE (1 << 2) + /* IOMMU capabilities */ #define IOMMU_CAP_IOTLB 24 #define IOMMU_CAP_NPCACHE 26 diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index f101afc315ab..9a8a8870e267 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -160,6 +160,14 @@ #define ARM_V7S_TCR_PD1 BIT(5) +#ifdef CONFIG_ZONE_DMA32 +#define ARM_V7S_TABLE_GFP_DMA GFP_DMA32 +#define ARM_V7S_TABLE_SLAB_FLAGS SLAB_CACHE_DMA32 +#else +#define ARM_V7S_TABLE_GFP_DMA GFP_DMA +#define ARM_V7S_TABLE_SLAB_FLAGS SLAB_CACHE_DMA +#endif + typedef u32 arm_v7s_iopte; static bool selftest_running; @@ -197,13 +205,16 @@ static void *__arm_v7s_alloc_table(int lvl, gfp_t gfp, void *table = NULL; if (lvl == 1) - table = (void *)__get_dma_pages(__GFP_ZERO, get_order(size)); + table = (void *)__get_free_pages( + __GFP_ZERO | ARM_V7S_TABLE_GFP_DMA, get_order(size)); else if (lvl == 2) - table = kmem_cache_zalloc(data->l2_tables, gfp | GFP_DMA); + table = kmem_cache_zalloc(data->l2_tables, gfp); phys = virt_to_phys(table); - if (phys != (arm_v7s_iopte)phys) + if (phys != (arm_v7s_iopte)phys) { /* Doesn't fit in PTE */ + dev_err(dev, "Page table does not fit in PTE: %pa", &phys); goto out_free; + } if (table && !(cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA)) { dma = dma_map_single(dev, table, size, DMA_TO_DEVICE); if (dma_mapping_error(dev, dma)) @@ -733,7 +744,7 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg, data->l2_tables = kmem_cache_create("io-pgtable_armv7s_l2", ARM_V7S_TABLE_SIZE(2), ARM_V7S_TABLE_SIZE(2), - SLAB_CACHE_DMA, NULL); + ARM_V7S_TABLE_SLAB_FLAGS, NULL); if (!data->l2_tables) goto out_free_data; diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 33a982e33716..109de67d5d72 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1105,10 +1105,12 @@ struct iommu_group *iommu_group_get_for_dev(struct device *dev) dom = __iommu_domain_alloc(dev->bus, iommu_def_domain_type); if (!dom && iommu_def_domain_type != IOMMU_DOMAIN_DMA) { - dev_warn(dev, - "failed to allocate default IOMMU domain of type %u; falling back to IOMMU_DOMAIN_DMA", - iommu_def_domain_type); dom = __iommu_domain_alloc(dev->bus, IOMMU_DOMAIN_DMA); + if (dom) { + dev_warn(dev, + "failed to allocate default IOMMU domain of type %u; falling back to IOMMU_DOMAIN_DMA", + iommu_def_domain_type); + } } group->default_domain = dom; diff --git a/drivers/irqchip/irq-ath79-misc.c b/drivers/irqchip/irq-ath79-misc.c index aa7290784636..0390603170b4 100644 --- a/drivers/irqchip/irq-ath79-misc.c +++ b/drivers/irqchip/irq-ath79-misc.c @@ -22,6 +22,15 @@ #define AR71XX_RESET_REG_MISC_INT_ENABLE 4 #define ATH79_MISC_IRQ_COUNT 32 +#define ATH79_MISC_PERF_IRQ 5 + +static int ath79_perfcount_irq; + +int get_c0_perfcount_int(void) +{ + return ath79_perfcount_irq; +} +EXPORT_SYMBOL_GPL(get_c0_perfcount_int); static void ath79_misc_irq_handler(struct irq_desc *desc) { @@ -113,6 +122,8 @@ static void __init ath79_misc_intc_domain_init( { void __iomem *base = domain->host_data; + ath79_perfcount_irq = irq_create_mapping(domain, ATH79_MISC_PERF_IRQ); + /* Disable and clear all interrupts */ __raw_writel(0, base + AR71XX_RESET_REG_MISC_INT_ENABLE); __raw_writel(0, base + AR71XX_RESET_REG_MISC_INT_STATUS); diff --git a/drivers/irqchip/irq-ls1x.c b/drivers/irqchip/irq-ls1x.c index 86b72fbd3b45..353111a10413 100644 --- a/drivers/irqchip/irq-ls1x.c +++ b/drivers/irqchip/irq-ls1x.c @@ -130,6 +130,7 @@ static int __init ls1x_intc_of_init(struct device_node *node, NULL); if (!priv->domain) { pr_err("ls1x-irq: cannot add IRQ domain\n"); + err = -ENOMEM; goto out_iounmap; } diff --git a/drivers/isdn/hardware/mISDN/hfcmulti.c b/drivers/isdn/hardware/mISDN/hfcmulti.c index 4d85645c87f7..0928fd1f0e0c 100644 --- a/drivers/isdn/hardware/mISDN/hfcmulti.c +++ b/drivers/isdn/hardware/mISDN/hfcmulti.c @@ -4365,7 +4365,8 @@ setup_pci(struct hfc_multi *hc, struct pci_dev *pdev, if (m->clock2) test_and_set_bit(HFC_CHIP_CLOCK2, &hc->chip); - if (ent->device == 0xB410) { + if (ent->vendor == PCI_VENDOR_ID_DIGIUM && + ent->device == PCI_DEVICE_ID_DIGIUM_HFC4S) { test_and_set_bit(HFC_CHIP_B410P, &hc->chip); test_and_set_bit(HFC_CHIP_PCM_MASTER, &hc->chip); test_and_clear_bit(HFC_CHIP_PCM_SLAVE, &hc->chip); diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c index 4ab8b1b6608f..a14e35d40538 100644 --- a/drivers/isdn/mISDN/socket.c +++ b/drivers/isdn/mISDN/socket.c @@ -710,10 +710,10 @@ base_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) struct sock *sk = sock->sk; int err = 0; - if (!maddr || maddr->family != AF_ISDN) + if (addr_len < sizeof(struct sockaddr_mISDN)) return -EINVAL; - if (addr_len < sizeof(struct sockaddr_mISDN)) + if (!maddr || maddr->family != AF_ISDN) return -EINVAL; lock_sock(sk); diff --git a/drivers/leds/leds-pca9532.c b/drivers/leds/leds-pca9532.c index 7fea18b0c15d..7cb4d685a1f1 100644 --- a/drivers/leds/leds-pca9532.c +++ b/drivers/leds/leds-pca9532.c @@ -513,6 +513,7 @@ static int pca9532_probe(struct i2c_client *client, const struct i2c_device_id *id) { int devid; + const struct of_device_id *of_id; struct pca9532_data *data = i2c_get_clientdata(client); struct pca9532_platform_data *pca9532_pdata = dev_get_platdata(&client->dev); @@ -528,8 +529,11 @@ static int pca9532_probe(struct i2c_client *client, dev_err(&client->dev, "no platform data\n"); return -EINVAL; } - devid = (int)(uintptr_t)of_match_device( - of_pca9532_leds_match, &client->dev)->data; + of_id = of_match_device(of_pca9532_leds_match, + &client->dev); + if (unlikely(!of_id)) + return -EINVAL; + devid = (int)(uintptr_t) of_id->data; } else { devid = id->driver_data; } diff --git a/drivers/leds/trigger/ledtrig-netdev.c b/drivers/leds/trigger/ledtrig-netdev.c index 3dd3ed46d473..136f86a1627d 100644 --- a/drivers/leds/trigger/ledtrig-netdev.c +++ b/drivers/leds/trigger/ledtrig-netdev.c @@ -122,7 +122,8 @@ static ssize_t device_name_store(struct device *dev, trigger_data->net_dev = NULL; } - strncpy(trigger_data->device_name, buf, size); + memcpy(trigger_data->device_name, buf, size); + trigger_data->device_name[size] = 0; if (size > 0 && trigger_data->device_name[size - 1] == '\n') trigger_data->device_name[size - 1] = 0; @@ -301,11 +302,11 @@ static int netdev_trig_notify(struct notifier_block *nb, container_of(nb, struct led_netdev_data, notifier); if (evt != NETDEV_UP && evt != NETDEV_DOWN && evt != NETDEV_CHANGE - && evt != NETDEV_REGISTER && evt != NETDEV_UNREGISTER - && evt != NETDEV_CHANGENAME) + && evt != NETDEV_REGISTER && evt != NETDEV_UNREGISTER) return NOTIFY_DONE; - if (strcmp(dev->name, trigger_data->device_name)) + if (!(dev == trigger_data->net_dev || + (evt == NETDEV_REGISTER && !strcmp(dev->name, trigger_data->device_name)))) return NOTIFY_DONE; cancel_delayed_work_sync(&trigger_data->work); @@ -320,12 +321,9 @@ static int netdev_trig_notify(struct notifier_block *nb, dev_hold(dev); trigger_data->net_dev = dev; break; - case NETDEV_CHANGENAME: case NETDEV_UNREGISTER: - if (trigger_data->net_dev) { - dev_put(trigger_data->net_dev); - trigger_data->net_dev = NULL; - } + dev_put(trigger_data->net_dev); + trigger_data->net_dev = NULL; break; case NETDEV_UP: case NETDEV_CHANGE: diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c index 3789185144da..0b7d5fb4548d 100644 --- a/drivers/lightnvm/pblk-read.c +++ b/drivers/lightnvm/pblk-read.c @@ -231,14 +231,14 @@ static void pblk_end_partial_read(struct nvm_rq *rqd) struct pblk_sec_meta *meta; struct bio *new_bio = rqd->bio; struct bio *bio = pr_ctx->orig_bio; - struct bio_vec src_bv, dst_bv; void *meta_list = rqd->meta_list; - int bio_init_idx = pr_ctx->bio_init_idx; unsigned long *read_bitmap = pr_ctx->bitmap; + struct bvec_iter orig_iter = BVEC_ITER_ALL_INIT; + struct bvec_iter new_iter = BVEC_ITER_ALL_INIT; int nr_secs = pr_ctx->orig_nr_secs; int nr_holes = nr_secs - bitmap_weight(read_bitmap, nr_secs); void *src_p, *dst_p; - int hole, i; + int bit, i; if (unlikely(nr_holes == 1)) { struct ppa_addr ppa; @@ -257,33 +257,39 @@ static void pblk_end_partial_read(struct nvm_rq *rqd) /* Fill the holes in the original bio */ i = 0; - hole = find_first_zero_bit(read_bitmap, nr_secs); - do { - struct pblk_line *line; + for (bit = 0; bit < nr_secs; bit++) { + if (!test_bit(bit, read_bitmap)) { + struct bio_vec dst_bv, src_bv; + struct pblk_line *line; - line = pblk_ppa_to_line(pblk, rqd->ppa_list[i]); - kref_put(&line->ref, pblk_line_put); + line = pblk_ppa_to_line(pblk, rqd->ppa_list[i]); + kref_put(&line->ref, pblk_line_put); - meta = pblk_get_meta(pblk, meta_list, hole); - meta->lba = cpu_to_le64(pr_ctx->lba_list_media[i]); + meta = pblk_get_meta(pblk, meta_list, bit); + meta->lba = cpu_to_le64(pr_ctx->lba_list_media[i]); - src_bv = new_bio->bi_io_vec[i++]; - dst_bv = bio->bi_io_vec[bio_init_idx + hole]; + dst_bv = bio_iter_iovec(bio, orig_iter); + src_bv = bio_iter_iovec(new_bio, new_iter); - src_p = kmap_atomic(src_bv.bv_page); - dst_p = kmap_atomic(dst_bv.bv_page); + src_p = kmap_atomic(src_bv.bv_page); + dst_p = kmap_atomic(dst_bv.bv_page); - memcpy(dst_p + dst_bv.bv_offset, - src_p + src_bv.bv_offset, - PBLK_EXPOSED_PAGE_SIZE); + memcpy(dst_p + dst_bv.bv_offset, + src_p + src_bv.bv_offset, + PBLK_EXPOSED_PAGE_SIZE); - kunmap_atomic(src_p); - kunmap_atomic(dst_p); + kunmap_atomic(src_p); + kunmap_atomic(dst_p); - mempool_free(src_bv.bv_page, &pblk->page_bio_pool); + flush_dcache_page(dst_bv.bv_page); + mempool_free(src_bv.bv_page, &pblk->page_bio_pool); - hole = find_next_zero_bit(read_bitmap, nr_secs, hole + 1); - } while (hole < nr_secs); + bio_advance_iter(new_bio, &new_iter, + PBLK_EXPOSED_PAGE_SIZE); + i++; + } + bio_advance_iter(bio, &orig_iter, PBLK_EXPOSED_PAGE_SIZE); + } bio_put(new_bio); kfree(pr_ctx); diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index 95c6d86ab5e8..c4ef1fceead6 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -115,6 +115,7 @@ struct mapped_device { struct srcu_struct io_barrier; }; +void disable_discard(struct mapped_device *md); void disable_write_same(struct mapped_device *md); void disable_write_zeroes(struct mapped_device *md); diff --git a/drivers/md/dm-init.c b/drivers/md/dm-init.c index b53f30f16b4d..4b76f84424c3 100644 --- a/drivers/md/dm-init.c +++ b/drivers/md/dm-init.c @@ -36,7 +36,7 @@ struct dm_device { struct list_head list; }; -const char *dm_allowed_targets[] __initconst = { +const char * const dm_allowed_targets[] __initconst = { "crypt", "delay", "linear", diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index d57d997a52c8..7c678f50aaa3 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -913,7 +913,7 @@ static void copy_from_journal(struct dm_integrity_c *ic, unsigned section, unsig static bool ranges_overlap(struct dm_integrity_range *range1, struct dm_integrity_range *range2) { return range1->logical_sector < range2->logical_sector + range2->n_sectors && - range2->logical_sector + range2->n_sectors > range2->logical_sector; + range1->logical_sector + range1->n_sectors > range2->logical_sector; } static bool add_new_range(struct dm_integrity_c *ic, struct dm_integrity_range *new_range, bool check_waiting) @@ -959,8 +959,6 @@ static void remove_range_unlocked(struct dm_integrity_c *ic, struct dm_integrity struct dm_integrity_range *last_range = list_first_entry(&ic->wait_list, struct dm_integrity_range, wait_entry); struct task_struct *last_range_task; - if (!ranges_overlap(range, last_range)) - break; last_range_task = last_range->task; list_del(&last_range->wait_entry); if (!add_new_range(ic, last_range, false)) { @@ -3185,7 +3183,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv) journal_watermark = val; else if (sscanf(opt_string, "commit_time:%u%c", &val, &dummy) == 1) sync_msec = val; - else if (!memcmp(opt_string, "meta_device:", strlen("meta_device:"))) { + else if (!strncmp(opt_string, "meta_device:", strlen("meta_device:"))) { if (ic->meta_dev) { dm_put_device(ti, ic->meta_dev); ic->meta_dev = NULL; @@ -3204,17 +3202,17 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv) goto bad; } ic->sectors_per_block = val >> SECTOR_SHIFT; - } else if (!memcmp(opt_string, "internal_hash:", strlen("internal_hash:"))) { + } else if (!strncmp(opt_string, "internal_hash:", strlen("internal_hash:"))) { r = get_alg_and_key(opt_string, &ic->internal_hash_alg, &ti->error, "Invalid internal_hash argument"); if (r) goto bad; - } else if (!memcmp(opt_string, "journal_crypt:", strlen("journal_crypt:"))) { + } else if (!strncmp(opt_string, "journal_crypt:", strlen("journal_crypt:"))) { r = get_alg_and_key(opt_string, &ic->journal_crypt_alg, &ti->error, "Invalid journal_crypt argument"); if (r) goto bad; - } else if (!memcmp(opt_string, "journal_mac:", strlen("journal_mac:"))) { + } else if (!strncmp(opt_string, "journal_mac:", strlen("journal_mac:"))) { r = get_alg_and_key(opt_string, &ic->journal_mac_alg, &ti->error, "Invalid journal_mac argument"); if (r) @@ -3616,7 +3614,7 @@ static struct target_type integrity_target = { .io_hints = dm_integrity_io_hints, }; -int __init dm_integrity_init(void) +static int __init dm_integrity_init(void) { int r; @@ -3635,7 +3633,7 @@ int __init dm_integrity_init(void) return r; } -void dm_integrity_exit(void) +static void __exit dm_integrity_exit(void) { dm_unregister_target(&integrity_target); kmem_cache_destroy(journal_io_cache); diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index 09773636602d..b66745bd08bb 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -222,11 +222,14 @@ static void dm_done(struct request *clone, blk_status_t error, bool mapped) } if (unlikely(error == BLK_STS_TARGET)) { - if (req_op(clone) == REQ_OP_WRITE_SAME && - !clone->q->limits.max_write_same_sectors) + if (req_op(clone) == REQ_OP_DISCARD && + !clone->q->limits.max_discard_sectors) + disable_discard(tio->md); + else if (req_op(clone) == REQ_OP_WRITE_SAME && + !clone->q->limits.max_write_same_sectors) disable_write_same(tio->md); - if (req_op(clone) == REQ_OP_WRITE_ZEROES && - !clone->q->limits.max_write_zeroes_sectors) + else if (req_op(clone) == REQ_OP_WRITE_ZEROES && + !clone->q->limits.max_write_zeroes_sectors) disable_write_zeroes(tio->md); } diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index ba9481f1bf3c..cde3b49b2a91 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1844,6 +1844,36 @@ static bool dm_table_supports_secure_erase(struct dm_table *t) return true; } +static int device_requires_stable_pages(struct dm_target *ti, + struct dm_dev *dev, sector_t start, + sector_t len, void *data) +{ + struct request_queue *q = bdev_get_queue(dev->bdev); + + return q && bdi_cap_stable_pages_required(q->backing_dev_info); +} + +/* + * If any underlying device requires stable pages, a table must require + * them as well. Only targets that support iterate_devices are considered: + * don't want error, zero, etc to require stable pages. + */ +static bool dm_table_requires_stable_pages(struct dm_table *t) +{ + struct dm_target *ti; + unsigned i; + + for (i = 0; i < dm_table_get_num_targets(t); i++) { + ti = dm_table_get_target(t, i); + + if (ti->type->iterate_devices && + ti->type->iterate_devices(ti, device_requires_stable_pages, NULL)) + return true; + } + + return false; +} + void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, struct queue_limits *limits) { @@ -1897,6 +1927,15 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, dm_table_verify_integrity(t); /* + * Some devices don't use blk_integrity but still want stable pages + * because they do their own checksumming. + */ + if (dm_table_requires_stable_pages(t)) + q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES; + else + q->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES; + + /* * Determine whether or not this queue's I/O timings contribute * to the entropy pool, Only request-based targets use this. * Clear QUEUE_FLAG_ADD_RANDOM if any underlying device does not diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 68d24056d0b1..043f0761e4a0 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -945,6 +945,15 @@ static void dec_pending(struct dm_io *io, blk_status_t error) } } +void disable_discard(struct mapped_device *md) +{ + struct queue_limits *limits = dm_get_queue_limits(md); + + /* device doesn't really support DISCARD, disable it */ + limits->max_discard_sectors = 0; + blk_queue_flag_clear(QUEUE_FLAG_DISCARD, md->queue); +} + void disable_write_same(struct mapped_device *md) { struct queue_limits *limits = dm_get_queue_limits(md); @@ -970,11 +979,14 @@ static void clone_endio(struct bio *bio) dm_endio_fn endio = tio->ti->type->end_io; if (unlikely(error == BLK_STS_TARGET) && md->type != DM_TYPE_NVME_BIO_BASED) { - if (bio_op(bio) == REQ_OP_WRITE_SAME && - !bio->bi_disk->queue->limits.max_write_same_sectors) + if (bio_op(bio) == REQ_OP_DISCARD && + !bio->bi_disk->queue->limits.max_discard_sectors) + disable_discard(md); + else if (bio_op(bio) == REQ_OP_WRITE_SAME && + !bio->bi_disk->queue->limits.max_write_same_sectors) disable_write_same(md); - if (bio_op(bio) == REQ_OP_WRITE_ZEROES && - !bio->bi_disk->queue->limits.max_write_zeroes_sectors) + else if (bio_op(bio) == REQ_OP_WRITE_ZEROES && + !bio->bi_disk->queue->limits.max_write_zeroes_sectors) disable_write_zeroes(md); } @@ -1042,15 +1054,7 @@ int dm_set_target_max_io_len(struct dm_target *ti, sector_t len) return -EINVAL; } - /* - * BIO based queue uses its own splitting. When multipage bvecs - * is switched on, size of the incoming bio may be too big to - * be handled in some targets, such as crypt. - * - * When these targets are ready for the big bio, we can remove - * the limit. - */ - ti->max_io_len = min_t(uint32_t, len, BIO_MAX_PAGES * PAGE_SIZE); + ti->max_io_len = (uint32_t) len; return 0; } diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index 0ce2d8dfc5f1..26ad6468d13a 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -1246,7 +1246,7 @@ config MFD_STA2X11 config MFD_SUN6I_PRCM bool "Allwinner A31 PRCM controller" - depends on ARCH_SUNXI + depends on ARCH_SUNXI || COMPILE_TEST select MFD_CORE help Support for the PRCM (Power/Reset/Clock Management) unit available diff --git a/drivers/mfd/sprd-sc27xx-spi.c b/drivers/mfd/sprd-sc27xx-spi.c index 69df27769c21..43ac71691fe4 100644 --- a/drivers/mfd/sprd-sc27xx-spi.c +++ b/drivers/mfd/sprd-sc27xx-spi.c @@ -53,67 +53,67 @@ static const struct sprd_pmic_data sc2731_data = { static const struct mfd_cell sprd_pmic_devs[] = { { .name = "sc27xx-wdt", - .of_compatible = "sprd,sc27xx-wdt", + .of_compatible = "sprd,sc2731-wdt", }, { .name = "sc27xx-rtc", - .of_compatible = "sprd,sc27xx-rtc", + .of_compatible = "sprd,sc2731-rtc", }, { .name = "sc27xx-charger", - .of_compatible = "sprd,sc27xx-charger", + .of_compatible = "sprd,sc2731-charger", }, { .name = "sc27xx-chg-timer", - .of_compatible = "sprd,sc27xx-chg-timer", + .of_compatible = "sprd,sc2731-chg-timer", }, { .name = "sc27xx-fast-chg", - .of_compatible = "sprd,sc27xx-fast-chg", + .of_compatible = "sprd,sc2731-fast-chg", }, { .name = "sc27xx-chg-wdt", - .of_compatible = "sprd,sc27xx-chg-wdt", + .of_compatible = "sprd,sc2731-chg-wdt", }, { .name = "sc27xx-typec", - .of_compatible = "sprd,sc27xx-typec", + .of_compatible = "sprd,sc2731-typec", }, { .name = "sc27xx-flash", - .of_compatible = "sprd,sc27xx-flash", + .of_compatible = "sprd,sc2731-flash", }, { .name = "sc27xx-eic", - .of_compatible = "sprd,sc27xx-eic", + .of_compatible = "sprd,sc2731-eic", }, { .name = "sc27xx-efuse", - .of_compatible = "sprd,sc27xx-efuse", + .of_compatible = "sprd,sc2731-efuse", }, { .name = "sc27xx-thermal", - .of_compatible = "sprd,sc27xx-thermal", + .of_compatible = "sprd,sc2731-thermal", }, { .name = "sc27xx-adc", - .of_compatible = "sprd,sc27xx-adc", + .of_compatible = "sprd,sc2731-adc", }, { .name = "sc27xx-audio-codec", - .of_compatible = "sprd,sc27xx-audio-codec", + .of_compatible = "sprd,sc2731-audio-codec", }, { .name = "sc27xx-regulator", - .of_compatible = "sprd,sc27xx-regulator", + .of_compatible = "sprd,sc2731-regulator", }, { .name = "sc27xx-vibrator", - .of_compatible = "sprd,sc27xx-vibrator", + .of_compatible = "sprd,sc2731-vibrator", }, { .name = "sc27xx-keypad-led", - .of_compatible = "sprd,sc27xx-keypad-led", + .of_compatible = "sprd,sc2731-keypad-led", }, { .name = "sc27xx-bltc", - .of_compatible = "sprd,sc27xx-bltc", + .of_compatible = "sprd,sc2731-bltc", }, { .name = "sc27xx-fgu", - .of_compatible = "sprd,sc27xx-fgu", + .of_compatible = "sprd,sc2731-fgu", }, { .name = "sc27xx-7sreset", - .of_compatible = "sprd,sc27xx-7sreset", + .of_compatible = "sprd,sc2731-7sreset", }, { .name = "sc27xx-poweroff", - .of_compatible = "sprd,sc27xx-poweroff", + .of_compatible = "sprd,sc2731-poweroff", }, { .name = "sc27xx-syscon", - .of_compatible = "sprd,sc27xx-syscon", + .of_compatible = "sprd,sc2731-syscon", }, }; diff --git a/drivers/mfd/twl-core.c b/drivers/mfd/twl-core.c index 299016bc46d9..104477b512a2 100644 --- a/drivers/mfd/twl-core.c +++ b/drivers/mfd/twl-core.c @@ -1245,6 +1245,28 @@ free: return status; } +static int __maybe_unused twl_suspend(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev); + + if (client->irq) + disable_irq(client->irq); + + return 0; +} + +static int __maybe_unused twl_resume(struct device *dev) +{ + struct i2c_client *client = to_i2c_client(dev); + + if (client->irq) + enable_irq(client->irq); + + return 0; +} + +static SIMPLE_DEV_PM_OPS(twl_dev_pm_ops, twl_suspend, twl_resume); + static const struct i2c_device_id twl_ids[] = { { "twl4030", TWL4030_VAUX2 }, /* "Triton 2" */ { "twl5030", 0 }, /* T2 updated */ @@ -1262,6 +1284,7 @@ static const struct i2c_device_id twl_ids[] = { /* One Client Driver , 4 Clients */ static struct i2c_driver twl_driver = { .driver.name = DRIVER_NAME, + .driver.pm = &twl_dev_pm_ops, .id_table = twl_ids, .probe = twl_probe, .remove = twl_remove, diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index 39f832d27288..36d0d5c9cfba 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -1184,6 +1184,7 @@ static int fastrpc_cb_probe(struct platform_device *pdev) struct fastrpc_session_ctx *sess; struct device *dev = &pdev->dev; int i, sessions = 0; + int rc; cctx = dev_get_drvdata(dev->parent); if (!cctx) @@ -1213,7 +1214,11 @@ static int fastrpc_cb_probe(struct platform_device *pdev) } cctx->sesscount++; spin_unlock(&cctx->lock); - dma_set_mask(dev, DMA_BIT_MASK(32)); + rc = dma_set_mask(dev, DMA_BIT_MASK(32)); + if (rc) { + dev_err(dev, "32-bit DMA enable failed\n"); + return rc; + } return 0; } diff --git a/drivers/misc/habanalabs/command_submission.c b/drivers/misc/habanalabs/command_submission.c index 3525236ed8d9..19c84214a7ea 100644 --- a/drivers/misc/habanalabs/command_submission.c +++ b/drivers/misc/habanalabs/command_submission.c @@ -179,6 +179,12 @@ static void cs_do_release(struct kref *ref) /* We also need to update CI for internal queues */ if (cs->submitted) { + int cs_cnt = atomic_dec_return(&hdev->cs_active_cnt); + + WARN_ONCE((cs_cnt < 0), + "hl%d: error in CS active cnt %d\n", + hdev->id, cs_cnt); + hl_int_hw_queue_update_ci(cs); spin_lock(&hdev->hw_queues_mirror_lock); diff --git a/drivers/misc/habanalabs/debugfs.c b/drivers/misc/habanalabs/debugfs.c index a53c12aff6ad..974a87789bd8 100644 --- a/drivers/misc/habanalabs/debugfs.c +++ b/drivers/misc/habanalabs/debugfs.c @@ -232,6 +232,7 @@ static int vm_show(struct seq_file *s, void *data) struct hl_vm_phys_pg_pack *phys_pg_pack = NULL; enum vm_type_t *vm_type; bool once = true; + u64 j; int i; if (!dev_entry->hdev->mmu_enable) @@ -260,7 +261,7 @@ static int vm_show(struct seq_file *s, void *data) } else { phys_pg_pack = hnode->ptr; seq_printf(s, - " 0x%-14llx %-10u %-4u\n", + " 0x%-14llx %-10llu %-4u\n", hnode->vaddr, phys_pg_pack->total_size, phys_pg_pack->handle); } @@ -282,9 +283,9 @@ static int vm_show(struct seq_file *s, void *data) phys_pg_pack->page_size); seq_puts(s, " physical address\n"); seq_puts(s, "---------------------\n"); - for (i = 0 ; i < phys_pg_pack->npages ; i++) { + for (j = 0 ; j < phys_pg_pack->npages ; j++) { seq_printf(s, " 0x%-14llx\n", - phys_pg_pack->pages[i]); + phys_pg_pack->pages[j]); } } spin_unlock(&vm->idr_lock); diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c index de46aa6ed154..77d51be66c7e 100644 --- a/drivers/misc/habanalabs/device.c +++ b/drivers/misc/habanalabs/device.c @@ -11,6 +11,8 @@ #include <linux/sched/signal.h> #include <linux/hwmon.h> +#define HL_PLDM_PENDING_RESET_PER_SEC (HL_PENDING_RESET_PER_SEC * 10) + bool hl_device_disabled_or_in_reset(struct hl_device *hdev) { if ((hdev->disabled) || (atomic_read(&hdev->in_reset))) @@ -216,6 +218,7 @@ static int device_early_init(struct hl_device *hdev) spin_lock_init(&hdev->hw_queues_mirror_lock); atomic_set(&hdev->in_reset, 0); atomic_set(&hdev->fd_open_cnt, 0); + atomic_set(&hdev->cs_active_cnt, 0); return 0; @@ -413,6 +416,27 @@ int hl_device_suspend(struct hl_device *hdev) pci_save_state(hdev->pdev); + /* Block future CS/VM/JOB completion operations */ + rc = atomic_cmpxchg(&hdev->in_reset, 0, 1); + if (rc) { + dev_err(hdev->dev, "Can't suspend while in reset\n"); + return -EIO; + } + + /* This blocks all other stuff that is not blocked by in_reset */ + hdev->disabled = true; + + /* + * Flush anyone that is inside the critical section of enqueue + * jobs to the H/W + */ + hdev->asic_funcs->hw_queues_lock(hdev); + hdev->asic_funcs->hw_queues_unlock(hdev); + + /* Flush processes that are sending message to CPU */ + mutex_lock(&hdev->send_cpu_message_lock); + mutex_unlock(&hdev->send_cpu_message_lock); + rc = hdev->asic_funcs->suspend(hdev); if (rc) dev_err(hdev->dev, @@ -440,21 +464,38 @@ int hl_device_resume(struct hl_device *hdev) pci_set_power_state(hdev->pdev, PCI_D0); pci_restore_state(hdev->pdev); - rc = pci_enable_device(hdev->pdev); + rc = pci_enable_device_mem(hdev->pdev); if (rc) { dev_err(hdev->dev, "Failed to enable PCI device in resume\n"); return rc; } + pci_set_master(hdev->pdev); + rc = hdev->asic_funcs->resume(hdev); if (rc) { - dev_err(hdev->dev, - "Failed to enable PCI access from device CPU\n"); - return rc; + dev_err(hdev->dev, "Failed to resume device after suspend\n"); + goto disable_device; + } + + + hdev->disabled = false; + atomic_set(&hdev->in_reset, 0); + + rc = hl_device_reset(hdev, true, false); + if (rc) { + dev_err(hdev->dev, "Failed to reset device during resume\n"); + goto disable_device; } return 0; + +disable_device: + pci_clear_master(hdev->pdev); + pci_disable_device(hdev->pdev); + + return rc; } static void hl_device_hard_reset_pending(struct work_struct *work) @@ -462,9 +503,16 @@ static void hl_device_hard_reset_pending(struct work_struct *work) struct hl_device_reset_work *device_reset_work = container_of(work, struct hl_device_reset_work, reset_work); struct hl_device *hdev = device_reset_work->hdev; - u16 pending_cnt = HL_PENDING_RESET_PER_SEC; + u16 pending_total, pending_cnt; struct task_struct *task = NULL; + if (hdev->pldm) + pending_total = HL_PLDM_PENDING_RESET_PER_SEC; + else + pending_total = HL_PENDING_RESET_PER_SEC; + + pending_cnt = pending_total; + /* Flush all processes that are inside hl_open */ mutex_lock(&hdev->fd_open_cnt_lock); @@ -489,6 +537,19 @@ static void hl_device_hard_reset_pending(struct work_struct *work) } } + pending_cnt = pending_total; + + while ((atomic_read(&hdev->fd_open_cnt)) && (pending_cnt)) { + + pending_cnt--; + + ssleep(1); + } + + if (atomic_read(&hdev->fd_open_cnt)) + dev_crit(hdev->dev, + "Going to hard reset with open user contexts\n"); + mutex_unlock(&hdev->fd_open_cnt_lock); hl_device_reset(hdev, true, true); diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 238dd57c541b..3c509e19d69d 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -1201,15 +1201,6 @@ static int goya_stop_external_queues(struct hl_device *hdev) return retval; } -static void goya_resume_external_queues(struct hl_device *hdev) -{ - WREG32(mmDMA_QM_0_GLBL_CFG1, 0); - WREG32(mmDMA_QM_1_GLBL_CFG1, 0); - WREG32(mmDMA_QM_2_GLBL_CFG1, 0); - WREG32(mmDMA_QM_3_GLBL_CFG1, 0); - WREG32(mmDMA_QM_4_GLBL_CFG1, 0); -} - /* * goya_init_cpu_queues - Initialize PQ/CQ/EQ of CPU * @@ -1697,12 +1688,11 @@ static void goya_init_golden_registers(struct hl_device *hdev) /* * Workaround for H2 #HW-23 bug - * Set DMA max outstanding read requests to 240 on DMA CH 1. Set it - * to 16 on KMD DMA - * We need to limit only these DMAs because the user can only read + * Set DMA max outstanding read requests to 240 on DMA CH 1. + * This limitation is still large enough to not affect Gen4 bandwidth. + * We need to only limit that DMA channel because the user can only read * from Host using DMA CH 1 */ - WREG32(mmDMA_CH_0_CFG0, 0x0fff0010); WREG32(mmDMA_CH_1_CFG0, 0x0fff00F0); goya->hw_cap_initialized |= HW_CAP_GOLDEN; @@ -2178,36 +2168,6 @@ static int goya_stop_internal_queues(struct hl_device *hdev) return retval; } -static void goya_resume_internal_queues(struct hl_device *hdev) -{ - WREG32(mmMME_QM_GLBL_CFG1, 0); - WREG32(mmMME_CMDQ_GLBL_CFG1, 0); - - WREG32(mmTPC0_QM_GLBL_CFG1, 0); - WREG32(mmTPC0_CMDQ_GLBL_CFG1, 0); - - WREG32(mmTPC1_QM_GLBL_CFG1, 0); - WREG32(mmTPC1_CMDQ_GLBL_CFG1, 0); - - WREG32(mmTPC2_QM_GLBL_CFG1, 0); - WREG32(mmTPC2_CMDQ_GLBL_CFG1, 0); - - WREG32(mmTPC3_QM_GLBL_CFG1, 0); - WREG32(mmTPC3_CMDQ_GLBL_CFG1, 0); - - WREG32(mmTPC4_QM_GLBL_CFG1, 0); - WREG32(mmTPC4_CMDQ_GLBL_CFG1, 0); - - WREG32(mmTPC5_QM_GLBL_CFG1, 0); - WREG32(mmTPC5_CMDQ_GLBL_CFG1, 0); - - WREG32(mmTPC6_QM_GLBL_CFG1, 0); - WREG32(mmTPC6_CMDQ_GLBL_CFG1, 0); - - WREG32(mmTPC7_QM_GLBL_CFG1, 0); - WREG32(mmTPC7_CMDQ_GLBL_CFG1, 0); -} - static void goya_dma_stall(struct hl_device *hdev) { WREG32(mmDMA_QM_0_GLBL_CFG1, 1 << DMA_QM_0_GLBL_CFG1_DMA_STOP_SHIFT); @@ -2905,20 +2865,6 @@ int goya_suspend(struct hl_device *hdev) { int rc; - rc = goya_stop_internal_queues(hdev); - - if (rc) { - dev_err(hdev->dev, "failed to stop internal queues\n"); - return rc; - } - - rc = goya_stop_external_queues(hdev); - - if (rc) { - dev_err(hdev->dev, "failed to stop external queues\n"); - return rc; - } - rc = goya_send_pci_access_msg(hdev, ARMCP_PACKET_DISABLE_PCI_ACCESS); if (rc) dev_err(hdev->dev, "Failed to disable PCI access from CPU\n"); @@ -2928,15 +2874,7 @@ int goya_suspend(struct hl_device *hdev) int goya_resume(struct hl_device *hdev) { - int rc; - - goya_resume_external_queues(hdev); - goya_resume_internal_queues(hdev); - - rc = goya_send_pci_access_msg(hdev, ARMCP_PACKET_ENABLE_PCI_ACCESS); - if (rc) - dev_err(hdev->dev, "Failed to enable PCI access from CPU\n"); - return rc; + return goya_init_iatu(hdev); } static int goya_cb_mmap(struct hl_device *hdev, struct vm_area_struct *vma, @@ -3070,7 +3008,7 @@ void *goya_get_int_queue_base(struct hl_device *hdev, u32 queue_id, *dma_handle = hdev->asic_prop.sram_base_address; - base = hdev->pcie_bar[SRAM_CFG_BAR_ID]; + base = (void *) hdev->pcie_bar[SRAM_CFG_BAR_ID]; switch (queue_id) { case GOYA_QUEUE_ID_MME: @@ -3754,7 +3692,7 @@ static int goya_validate_dma_pkt_mmu(struct hl_device *hdev, * WA for HW-23. * We can't allow user to read from Host using QMANs other than 1. */ - if (parser->hw_queue_id > GOYA_QUEUE_ID_DMA_1 && + if (parser->hw_queue_id != GOYA_QUEUE_ID_DMA_1 && hl_mem_area_inside_range(le64_to_cpu(user_dma_pkt->src_addr), le32_to_cpu(user_dma_pkt->tsize), hdev->asic_prop.va_space_host_start_address, diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h index a7c95e9f9b9a..a8ee52c880cd 100644 --- a/drivers/misc/habanalabs/habanalabs.h +++ b/drivers/misc/habanalabs/habanalabs.h @@ -793,11 +793,11 @@ struct hl_vm_hash_node { * struct hl_vm_phys_pg_pack - physical page pack. * @vm_type: describes the type of the virtual area descriptor. * @pages: the physical page array. + * @npages: num physical pages in the pack. + * @total_size: total size of all the pages in this list. * @mapping_cnt: number of shared mappings. * @asid: the context related to this list. - * @npages: num physical pages in the pack. * @page_size: size of each page in the pack. - * @total_size: total size of all the pages in this list. * @flags: HL_MEM_* flags related to this list. * @handle: the provided handle related to this list. * @offset: offset from the first page. @@ -807,11 +807,11 @@ struct hl_vm_hash_node { struct hl_vm_phys_pg_pack { enum vm_type_t vm_type; /* must be first */ u64 *pages; + u64 npages; + u64 total_size; atomic_t mapping_cnt; u32 asid; - u32 npages; u32 page_size; - u32 total_size; u32 flags; u32 handle; u32 offset; @@ -1056,13 +1056,15 @@ struct hl_device_reset_work { * @cb_pool_lock: protects the CB pool. * @user_ctx: current user context executing. * @dram_used_mem: current DRAM memory consumption. - * @in_reset: is device in reset flow. - * @curr_pll_profile: current PLL profile. - * @fd_open_cnt: number of open user processes. * @timeout_jiffies: device CS timeout value. * @max_power: the max power of the device, as configured by the sysadmin. This * value is saved so in case of hard-reset, KMD will restore this * value and update the F/W after the re-initialization + * @in_reset: is device in reset flow. + * @curr_pll_profile: current PLL profile. + * @fd_open_cnt: number of open user processes. + * @cs_active_cnt: number of active command submissions on this device (active + * means already in H/W queues) * @major: habanalabs KMD major. * @high_pll: high PLL profile frequency. * @soft_reset_cnt: number of soft reset since KMD loading. @@ -1128,11 +1130,12 @@ struct hl_device { struct hl_ctx *user_ctx; atomic64_t dram_used_mem; + u64 timeout_jiffies; + u64 max_power; atomic_t in_reset; atomic_t curr_pll_profile; atomic_t fd_open_cnt; - u64 timeout_jiffies; - u64 max_power; + atomic_t cs_active_cnt; u32 major; u32 high_pll; u32 soft_reset_cnt; diff --git a/drivers/misc/habanalabs/hw_queue.c b/drivers/misc/habanalabs/hw_queue.c index 67bece26417c..ef3bb6951360 100644 --- a/drivers/misc/habanalabs/hw_queue.c +++ b/drivers/misc/habanalabs/hw_queue.c @@ -370,12 +370,13 @@ int hl_hw_queue_schedule_cs(struct hl_cs *cs) spin_unlock(&hdev->hw_queues_mirror_lock); } - list_for_each_entry_safe(job, tmp, &cs->job_list, cs_node) { + atomic_inc(&hdev->cs_active_cnt); + + list_for_each_entry_safe(job, tmp, &cs->job_list, cs_node) if (job->ext_queue) ext_hw_queue_schedule_job(job); else int_hw_queue_schedule_job(job); - } cs->submitted = true; diff --git a/drivers/misc/habanalabs/memory.c b/drivers/misc/habanalabs/memory.c index 3a12fd1a5274..ce1fda40a8b8 100644 --- a/drivers/misc/habanalabs/memory.c +++ b/drivers/misc/habanalabs/memory.c @@ -56,9 +56,9 @@ static int alloc_device_memory(struct hl_ctx *ctx, struct hl_mem_in *args, struct hl_device *hdev = ctx->hdev; struct hl_vm *vm = &hdev->vm; struct hl_vm_phys_pg_pack *phys_pg_pack; - u64 paddr = 0; - u32 total_size, num_pgs, num_curr_pgs, page_size, page_shift; - int handle, rc, i; + u64 paddr = 0, total_size, num_pgs, i; + u32 num_curr_pgs, page_size, page_shift; + int handle, rc; bool contiguous; num_curr_pgs = 0; @@ -73,7 +73,7 @@ static int alloc_device_memory(struct hl_ctx *ctx, struct hl_mem_in *args, paddr = (u64) gen_pool_alloc(vm->dram_pg_pool, total_size); if (!paddr) { dev_err(hdev->dev, - "failed to allocate %u huge contiguous pages\n", + "failed to allocate %llu huge contiguous pages\n", num_pgs); return -ENOMEM; } @@ -93,7 +93,7 @@ static int alloc_device_memory(struct hl_ctx *ctx, struct hl_mem_in *args, phys_pg_pack->flags = args->flags; phys_pg_pack->contiguous = contiguous; - phys_pg_pack->pages = kcalloc(num_pgs, sizeof(u64), GFP_KERNEL); + phys_pg_pack->pages = kvmalloc_array(num_pgs, sizeof(u64), GFP_KERNEL); if (!phys_pg_pack->pages) { rc = -ENOMEM; goto pages_arr_err; @@ -148,7 +148,7 @@ page_err: gen_pool_free(vm->dram_pg_pool, phys_pg_pack->pages[i], page_size); - kfree(phys_pg_pack->pages); + kvfree(phys_pg_pack->pages); pages_arr_err: kfree(phys_pg_pack); pages_pack_err: @@ -267,7 +267,7 @@ static void free_phys_pg_pack(struct hl_device *hdev, struct hl_vm_phys_pg_pack *phys_pg_pack) { struct hl_vm *vm = &hdev->vm; - int i; + u64 i; if (!phys_pg_pack->created_from_userptr) { if (phys_pg_pack->contiguous) { @@ -288,7 +288,7 @@ static void free_phys_pg_pack(struct hl_device *hdev, } } - kfree(phys_pg_pack->pages); + kvfree(phys_pg_pack->pages); kfree(phys_pg_pack); } @@ -519,7 +519,7 @@ static inline int add_va_block(struct hl_device *hdev, * - Return the start address of the virtual block */ static u64 get_va_block(struct hl_device *hdev, - struct hl_va_range *va_range, u32 size, u64 hint_addr, + struct hl_va_range *va_range, u64 size, u64 hint_addr, bool is_userptr) { struct hl_vm_va_block *va_block, *new_va_block = NULL; @@ -577,7 +577,8 @@ static u64 get_va_block(struct hl_device *hdev, } if (!new_va_block) { - dev_err(hdev->dev, "no available va block for size %u\n", size); + dev_err(hdev->dev, "no available va block for size %llu\n", + size); goto out; } @@ -648,8 +649,8 @@ static int init_phys_pg_pack_from_userptr(struct hl_ctx *ctx, struct hl_vm_phys_pg_pack *phys_pg_pack; struct scatterlist *sg; dma_addr_t dma_addr; - u64 page_mask; - u32 npages, total_npages, page_size = PAGE_SIZE; + u64 page_mask, total_npages; + u32 npages, page_size = PAGE_SIZE; bool first = true, is_huge_page_opt = true; int rc, i, j; @@ -691,7 +692,8 @@ static int init_phys_pg_pack_from_userptr(struct hl_ctx *ctx, page_mask = ~(((u64) page_size) - 1); - phys_pg_pack->pages = kcalloc(total_npages, sizeof(u64), GFP_KERNEL); + phys_pg_pack->pages = kvmalloc_array(total_npages, sizeof(u64), + GFP_KERNEL); if (!phys_pg_pack->pages) { rc = -ENOMEM; goto page_pack_arr_mem_err; @@ -750,9 +752,9 @@ static int map_phys_page_pack(struct hl_ctx *ctx, u64 vaddr, struct hl_vm_phys_pg_pack *phys_pg_pack) { struct hl_device *hdev = ctx->hdev; - u64 next_vaddr = vaddr, paddr; + u64 next_vaddr = vaddr, paddr, mapped_pg_cnt = 0, i; u32 page_size = phys_pg_pack->page_size; - int i, rc = 0, mapped_pg_cnt = 0; + int rc = 0; for (i = 0 ; i < phys_pg_pack->npages ; i++) { paddr = phys_pg_pack->pages[i]; @@ -764,7 +766,7 @@ static int map_phys_page_pack(struct hl_ctx *ctx, u64 vaddr, rc = hl_mmu_map(ctx, next_vaddr, paddr, page_size); if (rc) { dev_err(hdev->dev, - "map failed for handle %u, npages: %d, mapped: %d", + "map failed for handle %u, npages: %llu, mapped: %llu", phys_pg_pack->handle, phys_pg_pack->npages, mapped_pg_cnt); goto err; @@ -985,10 +987,10 @@ static int unmap_device_va(struct hl_ctx *ctx, u64 vaddr) struct hl_vm_hash_node *hnode = NULL; struct hl_userptr *userptr = NULL; enum vm_type_t *vm_type; - u64 next_vaddr; + u64 next_vaddr, i; u32 page_size; bool is_userptr; - int i, rc; + int rc; /* protect from double entrance */ mutex_lock(&ctx->mem_hash_lock); diff --git a/drivers/misc/habanalabs/mmu.c b/drivers/misc/habanalabs/mmu.c index 2f2e99cb2743..3a5a2cec8305 100644 --- a/drivers/misc/habanalabs/mmu.c +++ b/drivers/misc/habanalabs/mmu.c @@ -832,7 +832,7 @@ err: int hl_mmu_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr, u32 page_size) { struct hl_device *hdev = ctx->hdev; - u64 real_virt_addr; + u64 real_virt_addr, real_phys_addr; u32 real_page_size, npages; int i, rc, mapped_cnt = 0; @@ -857,14 +857,16 @@ int hl_mmu_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr, u32 page_size) npages = page_size / real_page_size; real_virt_addr = virt_addr; + real_phys_addr = phys_addr; for (i = 0 ; i < npages ; i++) { - rc = _hl_mmu_map(ctx, real_virt_addr, phys_addr, + rc = _hl_mmu_map(ctx, real_virt_addr, real_phys_addr, real_page_size); if (rc) goto err; real_virt_addr += real_page_size; + real_phys_addr += real_page_size; mapped_cnt++; } diff --git a/drivers/mmc/host/alcor.c b/drivers/mmc/host/alcor.c index 82a97866e0cf..7c8f203f9a24 100644 --- a/drivers/mmc/host/alcor.c +++ b/drivers/mmc/host/alcor.c @@ -48,7 +48,6 @@ struct alcor_sdmmc_host { struct mmc_command *cmd; struct mmc_data *data; unsigned int dma_on:1; - unsigned int early_data:1; struct mutex cmd_mutex; @@ -144,8 +143,7 @@ static void alcor_data_set_dma(struct alcor_sdmmc_host *host) host->sg_count--; } -static void alcor_trigger_data_transfer(struct alcor_sdmmc_host *host, - bool early) +static void alcor_trigger_data_transfer(struct alcor_sdmmc_host *host) { struct alcor_pci_priv *priv = host->alcor_pci; struct mmc_data *data = host->data; @@ -155,13 +153,6 @@ static void alcor_trigger_data_transfer(struct alcor_sdmmc_host *host, ctrl |= AU6601_DATA_WRITE; if (data->host_cookie == COOKIE_MAPPED) { - if (host->early_data) { - host->early_data = false; - return; - } - - host->early_data = early; - alcor_data_set_dma(host); ctrl |= AU6601_DATA_DMA_MODE; host->dma_on = 1; @@ -231,6 +222,7 @@ static void alcor_prepare_sg_miter(struct alcor_sdmmc_host *host) static void alcor_prepare_data(struct alcor_sdmmc_host *host, struct mmc_command *cmd) { + struct alcor_pci_priv *priv = host->alcor_pci; struct mmc_data *data = cmd->data; if (!data) @@ -248,7 +240,7 @@ static void alcor_prepare_data(struct alcor_sdmmc_host *host, if (data->host_cookie != COOKIE_MAPPED) alcor_prepare_sg_miter(host); - alcor_trigger_data_transfer(host, true); + alcor_write8(priv, 0, AU6601_DATA_XFER_CTRL); } static void alcor_send_cmd(struct alcor_sdmmc_host *host, @@ -435,7 +427,7 @@ static int alcor_cmd_irq_done(struct alcor_sdmmc_host *host, u32 intmask) if (!host->data) return false; - alcor_trigger_data_transfer(host, false); + alcor_trigger_data_transfer(host); host->cmd = NULL; return true; } @@ -456,7 +448,7 @@ static void alcor_cmd_irq_thread(struct alcor_sdmmc_host *host, u32 intmask) if (!host->data) alcor_request_complete(host, 1); else - alcor_trigger_data_transfer(host, false); + alcor_trigger_data_transfer(host); host->cmd = NULL; } @@ -487,15 +479,9 @@ static int alcor_data_irq_done(struct alcor_sdmmc_host *host, u32 intmask) break; case AU6601_INT_READ_BUF_RDY: alcor_trf_block_pio(host, true); - if (!host->blocks) - break; - alcor_trigger_data_transfer(host, false); return 1; case AU6601_INT_WRITE_BUF_RDY: alcor_trf_block_pio(host, false); - if (!host->blocks) - break; - alcor_trigger_data_transfer(host, false); return 1; case AU6601_INT_DMA_END: if (!host->sg_count) @@ -508,8 +494,14 @@ static int alcor_data_irq_done(struct alcor_sdmmc_host *host, u32 intmask) break; } - if (intmask & AU6601_INT_DATA_END) - return 0; + if (intmask & AU6601_INT_DATA_END) { + if (!host->dma_on && host->blocks) { + alcor_trigger_data_transfer(host); + return 1; + } else { + return 0; + } + } return 1; } diff --git a/drivers/mmc/host/sdhci-omap.c b/drivers/mmc/host/sdhci-omap.c index 5bbed477c9b1..9f20fff9781b 100644 --- a/drivers/mmc/host/sdhci-omap.c +++ b/drivers/mmc/host/sdhci-omap.c @@ -797,6 +797,43 @@ void sdhci_omap_reset(struct sdhci_host *host, u8 mask) sdhci_reset(host, mask); } +#define CMD_ERR_MASK (SDHCI_INT_CRC | SDHCI_INT_END_BIT | SDHCI_INT_INDEX |\ + SDHCI_INT_TIMEOUT) +#define CMD_MASK (CMD_ERR_MASK | SDHCI_INT_RESPONSE) + +static u32 sdhci_omap_irq(struct sdhci_host *host, u32 intmask) +{ + struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + struct sdhci_omap_host *omap_host = sdhci_pltfm_priv(pltfm_host); + + if (omap_host->is_tuning && host->cmd && !host->data_early && + (intmask & CMD_ERR_MASK)) { + + /* + * Since we are not resetting data lines during tuning + * operation, data error or data complete interrupts + * might still arrive. Mark this request as a failure + * but still wait for the data interrupt + */ + if (intmask & SDHCI_INT_TIMEOUT) + host->cmd->error = -ETIMEDOUT; + else + host->cmd->error = -EILSEQ; + + host->cmd = NULL; + + /* + * Sometimes command error interrupts and command complete + * interrupt will arrive together. Clear all command related + * interrupts here. + */ + sdhci_writel(host, intmask & CMD_MASK, SDHCI_INT_STATUS); + intmask &= ~CMD_MASK; + } + + return intmask; +} + static struct sdhci_ops sdhci_omap_ops = { .set_clock = sdhci_omap_set_clock, .set_power = sdhci_omap_set_power, @@ -807,6 +844,7 @@ static struct sdhci_ops sdhci_omap_ops = { .platform_send_init_74_clocks = sdhci_omap_init_74_clocks, .reset = sdhci_omap_reset, .set_uhs_signaling = sdhci_omap_set_uhs_signaling, + .irq = sdhci_omap_irq, }; static int sdhci_omap_set_capabilities(struct sdhci_omap_host *omap_host) diff --git a/drivers/mtd/chips/cfi_cmdset_0002.c b/drivers/mtd/chips/cfi_cmdset_0002.c index 72428b6bfc47..7b7286b4d81e 100644 --- a/drivers/mtd/chips/cfi_cmdset_0002.c +++ b/drivers/mtd/chips/cfi_cmdset_0002.c @@ -1876,7 +1876,11 @@ static int __xipram do_write_buffer(struct map_info *map, struct flchip *chip, continue; } - if (time_after(jiffies, timeo) && !chip_ready(map, adr)) + /* + * We check "time_after" and "!chip_good" before checking "chip_good" to avoid + * the failure due to scheduling. + */ + if (time_after(jiffies, timeo) && !chip_good(map, adr, datum)) break; if (chip_good(map, adr, datum)) { diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c index f38e5c1b87e4..d984538980e2 100644 --- a/drivers/mtd/nand/raw/marvell_nand.c +++ b/drivers/mtd/nand/raw/marvell_nand.c @@ -722,12 +722,6 @@ static void marvell_nfc_select_target(struct nand_chip *chip, struct marvell_nfc *nfc = to_marvell_nfc(chip->controller); u32 ndcr_generic; - if (chip == nfc->selected_chip && die_nr == marvell_nand->selected_die) - return; - - writel_relaxed(marvell_nand->ndtr0, nfc->regs + NDTR0); - writel_relaxed(marvell_nand->ndtr1, nfc->regs + NDTR1); - /* * Reset the NDCR register to a clean state for this particular chip, * also clear ND_RUN bit. @@ -739,6 +733,12 @@ static void marvell_nfc_select_target(struct nand_chip *chip, /* Also reset the interrupt status register */ marvell_nfc_clear_int(nfc, NDCR_ALL_INT); + if (chip == nfc->selected_chip && die_nr == marvell_nand->selected_die) + return; + + writel_relaxed(marvell_nand->ndtr0, nfc->regs + NDTR0); + writel_relaxed(marvell_nand->ndtr1, nfc->regs + NDTR1); + nfc->selected_chip = chip; marvell_nand->selected_die = die_nr; } diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 5e4ca082cfcd..7a96d168efc4 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -216,8 +216,8 @@ config GENEVE config GTP tristate "GPRS Tunneling Protocol datapath (GTP-U)" - depends on INET && NET_UDP_TUNNEL - select NET_IP_TUNNEL + depends on INET + select NET_UDP_TUNNEL ---help--- This allows one to create gtp virtual interfaces that provide the GPRS Tunneling Protocol datapath (GTP-U). This tunneling protocol diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index b59708c35faf..ee610721098e 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3213,8 +3213,12 @@ static int bond_netdev_event(struct notifier_block *this, return NOTIFY_DONE; if (event_dev->flags & IFF_MASTER) { + int ret; + netdev_dbg(event_dev, "IFF_MASTER\n"); - return bond_master_netdev_event(event, event_dev); + ret = bond_master_netdev_event(event, event_dev); + if (ret != NOTIFY_DONE) + return ret; } if (event_dev->flags & IFF_SLAVE) { diff --git a/drivers/net/bonding/bond_sysfs_slave.c b/drivers/net/bonding/bond_sysfs_slave.c index 2f120b2ffef0..4985268e2273 100644 --- a/drivers/net/bonding/bond_sysfs_slave.c +++ b/drivers/net/bonding/bond_sysfs_slave.c @@ -55,7 +55,9 @@ static SLAVE_ATTR_RO(link_failure_count); static ssize_t perm_hwaddr_show(struct slave *slave, char *buf) { - return sprintf(buf, "%pM\n", slave->perm_hwaddr); + return sprintf(buf, "%*phC\n", + slave->dev->addr_len, + slave->perm_hwaddr); } static SLAVE_ATTR_RO(perm_hwaddr); diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c index e6234d209787..4212bc4a5f31 100644 --- a/drivers/net/dsa/bcm_sf2_cfp.c +++ b/drivers/net/dsa/bcm_sf2_cfp.c @@ -886,6 +886,9 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port, fs->m_ext.data[1])) return -EINVAL; + if (fs->location != RX_CLS_LOC_ANY && fs->location >= CFP_NUM_RULES) + return -EINVAL; + if (fs->location != RX_CLS_LOC_ANY && test_bit(fs->location, priv->cfp.used)) return -EBUSY; @@ -974,6 +977,9 @@ static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port, u32 loc) struct cfp_rule *rule; int ret; + if (loc >= CFP_NUM_RULES) + return -EINVAL; + /* Refuse deleting unused rules, and those that are not unique since * that could leave IPv6 rules with one of the chained rule in the * table. diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c index dce84a2a65c7..c44b2822e4dd 100644 --- a/drivers/net/dsa/mv88e6xxx/port.c +++ b/drivers/net/dsa/mv88e6xxx/port.c @@ -427,18 +427,22 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port, return 0; lane = mv88e6390x_serdes_get_lane(chip, port); - if (lane < 0) + if (lane < 0 && lane != -ENODEV) return lane; - if (chip->ports[port].serdes_irq) { - err = mv88e6390_serdes_irq_disable(chip, port, lane); + if (lane >= 0) { + if (chip->ports[port].serdes_irq) { + err = mv88e6390_serdes_irq_disable(chip, port, lane); + if (err) + return err; + } + + err = mv88e6390x_serdes_power(chip, port, false); if (err) return err; } - err = mv88e6390x_serdes_power(chip, port, false); - if (err) - return err; + chip->ports[port].cmode = 0; if (cmode) { err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_STS, ®); @@ -452,6 +456,12 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port, if (err) return err; + chip->ports[port].cmode = cmode; + + lane = mv88e6390x_serdes_get_lane(chip, port); + if (lane < 0) + return lane; + err = mv88e6390x_serdes_power(chip, port, true); if (err) return err; @@ -463,8 +473,6 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port, } } - chip->ports[port].cmode = cmode; - return 0; } diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index 576b37d12a63..c4fa400efdcc 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -481,6 +481,155 @@ qca8k_port_set_status(struct qca8k_priv *priv, int port, int enable) qca8k_reg_clear(priv, QCA8K_REG_PORT_STATUS(port), mask); } +static u32 +qca8k_port_to_phy(int port) +{ + /* From Andrew Lunn: + * Port 0 has no internal phy. + * Port 1 has an internal PHY at MDIO address 0. + * Port 2 has an internal PHY at MDIO address 1. + * ... + * Port 5 has an internal PHY at MDIO address 4. + * Port 6 has no internal PHY. + */ + + return port - 1; +} + +static int +qca8k_mdio_write(struct qca8k_priv *priv, int port, u32 regnum, u16 data) +{ + u32 phy, val; + + if (regnum >= QCA8K_MDIO_MASTER_MAX_REG) + return -EINVAL; + + /* callee is responsible for not passing bad ports, + * but we still would like to make spills impossible. + */ + phy = qca8k_port_to_phy(port) % PHY_MAX_ADDR; + val = QCA8K_MDIO_MASTER_BUSY | QCA8K_MDIO_MASTER_EN | + QCA8K_MDIO_MASTER_WRITE | QCA8K_MDIO_MASTER_PHY_ADDR(phy) | + QCA8K_MDIO_MASTER_REG_ADDR(regnum) | + QCA8K_MDIO_MASTER_DATA(data); + + qca8k_write(priv, QCA8K_MDIO_MASTER_CTRL, val); + + return qca8k_busy_wait(priv, QCA8K_MDIO_MASTER_CTRL, + QCA8K_MDIO_MASTER_BUSY); +} + +static int +qca8k_mdio_read(struct qca8k_priv *priv, int port, u32 regnum) +{ + u32 phy, val; + + if (regnum >= QCA8K_MDIO_MASTER_MAX_REG) + return -EINVAL; + + /* callee is responsible for not passing bad ports, + * but we still would like to make spills impossible. + */ + phy = qca8k_port_to_phy(port) % PHY_MAX_ADDR; + val = QCA8K_MDIO_MASTER_BUSY | QCA8K_MDIO_MASTER_EN | + QCA8K_MDIO_MASTER_READ | QCA8K_MDIO_MASTER_PHY_ADDR(phy) | + QCA8K_MDIO_MASTER_REG_ADDR(regnum); + + qca8k_write(priv, QCA8K_MDIO_MASTER_CTRL, val); + + if (qca8k_busy_wait(priv, QCA8K_MDIO_MASTER_CTRL, + QCA8K_MDIO_MASTER_BUSY)) + return -ETIMEDOUT; + + val = (qca8k_read(priv, QCA8K_MDIO_MASTER_CTRL) & + QCA8K_MDIO_MASTER_DATA_MASK); + + return val; +} + +static int +qca8k_phy_write(struct dsa_switch *ds, int port, int regnum, u16 data) +{ + struct qca8k_priv *priv = ds->priv; + + return qca8k_mdio_write(priv, port, regnum, data); +} + +static int +qca8k_phy_read(struct dsa_switch *ds, int port, int regnum) +{ + struct qca8k_priv *priv = ds->priv; + int ret; + + ret = qca8k_mdio_read(priv, port, regnum); + + if (ret < 0) + return 0xffff; + + return ret; +} + +static int +qca8k_setup_mdio_bus(struct qca8k_priv *priv) +{ + u32 internal_mdio_mask = 0, external_mdio_mask = 0, reg; + struct device_node *ports, *port; + int err; + + ports = of_get_child_by_name(priv->dev->of_node, "ports"); + if (!ports) + return -EINVAL; + + for_each_available_child_of_node(ports, port) { + err = of_property_read_u32(port, "reg", ®); + if (err) + return err; + + if (!dsa_is_user_port(priv->ds, reg)) + continue; + + if (of_property_read_bool(port, "phy-handle")) + external_mdio_mask |= BIT(reg); + else + internal_mdio_mask |= BIT(reg); + } + + if (!external_mdio_mask && !internal_mdio_mask) { + dev_err(priv->dev, "no PHYs are defined.\n"); + return -EINVAL; + } + + /* The QCA8K_MDIO_MASTER_EN Bit, which grants access to PHYs through + * the MDIO_MASTER register also _disconnects_ the external MDC + * passthrough to the internal PHYs. It's not possible to use both + * configurations at the same time! + * + * Because this came up during the review process: + * If the external mdio-bus driver is capable magically disabling + * the QCA8K_MDIO_MASTER_EN and mutex/spin-locking out the qca8k's + * accessors for the time being, it would be possible to pull this + * off. + */ + if (!!external_mdio_mask && !!internal_mdio_mask) { + dev_err(priv->dev, "either internal or external mdio bus configuration is supported.\n"); + return -EINVAL; + } + + if (external_mdio_mask) { + /* Make sure to disable the internal mdio bus in cases + * a dt-overlay and driver reload changed the configuration + */ + + qca8k_reg_clear(priv, QCA8K_MDIO_MASTER_CTRL, + QCA8K_MDIO_MASTER_EN); + return 0; + } + + priv->ops.phy_read = qca8k_phy_read; + priv->ops.phy_write = qca8k_phy_write; + return 0; +} + static int qca8k_setup(struct dsa_switch *ds) { @@ -502,6 +651,10 @@ qca8k_setup(struct dsa_switch *ds) if (IS_ERR(priv->regmap)) pr_warn("regmap initialization failed"); + ret = qca8k_setup_mdio_bus(priv); + if (ret) + return ret; + /* Initialize CPU port pad mode (xMII type, delays...) */ phy_mode = of_get_phy_mode(ds->ports[QCA8K_CPU_PORT].dn); if (phy_mode < 0) { @@ -624,22 +777,6 @@ qca8k_adjust_link(struct dsa_switch *ds, int port, struct phy_device *phy) qca8k_port_set_status(priv, port, 1); } -static int -qca8k_phy_read(struct dsa_switch *ds, int phy, int regnum) -{ - struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv; - - return mdiobus_read(priv->bus, phy, regnum); -} - -static int -qca8k_phy_write(struct dsa_switch *ds, int phy, int regnum, u16 val) -{ - struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv; - - return mdiobus_write(priv->bus, phy, regnum, val); -} - static void qca8k_get_strings(struct dsa_switch *ds, int port, u32 stringset, uint8_t *data) { @@ -879,8 +1016,6 @@ static const struct dsa_switch_ops qca8k_switch_ops = { .setup = qca8k_setup, .adjust_link = qca8k_adjust_link, .get_strings = qca8k_get_strings, - .phy_read = qca8k_phy_read, - .phy_write = qca8k_phy_write, .get_ethtool_stats = qca8k_get_ethtool_stats, .get_sset_count = qca8k_get_sset_count, .get_mac_eee = qca8k_get_mac_eee, @@ -923,7 +1058,8 @@ qca8k_sw_probe(struct mdio_device *mdiodev) return -ENOMEM; priv->ds->priv = priv; - priv->ds->ops = &qca8k_switch_ops; + priv->ops = qca8k_switch_ops; + priv->ds->ops = &priv->ops; mutex_init(&priv->reg_mutex); dev_set_drvdata(&mdiodev->dev, priv); diff --git a/drivers/net/dsa/qca8k.h b/drivers/net/dsa/qca8k.h index d146e54c8a6c..249fd62268e5 100644 --- a/drivers/net/dsa/qca8k.h +++ b/drivers/net/dsa/qca8k.h @@ -49,6 +49,18 @@ #define QCA8K_MIB_FLUSH BIT(24) #define QCA8K_MIB_CPU_KEEP BIT(20) #define QCA8K_MIB_BUSY BIT(17) +#define QCA8K_MDIO_MASTER_CTRL 0x3c +#define QCA8K_MDIO_MASTER_BUSY BIT(31) +#define QCA8K_MDIO_MASTER_EN BIT(30) +#define QCA8K_MDIO_MASTER_READ BIT(27) +#define QCA8K_MDIO_MASTER_WRITE 0 +#define QCA8K_MDIO_MASTER_SUP_PRE BIT(26) +#define QCA8K_MDIO_MASTER_PHY_ADDR(x) ((x) << 21) +#define QCA8K_MDIO_MASTER_REG_ADDR(x) ((x) << 16) +#define QCA8K_MDIO_MASTER_DATA(x) (x) +#define QCA8K_MDIO_MASTER_DATA_MASK GENMASK(15, 0) +#define QCA8K_MDIO_MASTER_MAX_PORTS 5 +#define QCA8K_MDIO_MASTER_MAX_REG 32 #define QCA8K_GOL_MAC_ADDR0 0x60 #define QCA8K_GOL_MAC_ADDR1 0x64 #define QCA8K_REG_PORT_STATUS(_i) (0x07c + (_i) * 4) @@ -169,6 +181,7 @@ struct qca8k_priv { struct dsa_switch *ds; struct mutex reg_mutex; struct device *dev; + struct dsa_switch_ops ops; }; struct qca8k_mib_desc { diff --git a/drivers/net/ethernet/3com/3c515.c b/drivers/net/ethernet/3com/3c515.c index 808abb6b3671..b15752267c8d 100644 --- a/drivers/net/ethernet/3com/3c515.c +++ b/drivers/net/ethernet/3com/3c515.c @@ -1521,7 +1521,7 @@ static void update_stats(int ioaddr, struct net_device *dev) static void set_rx_mode(struct net_device *dev) { int ioaddr = dev->base_addr; - short new_mode; + unsigned short new_mode; if (dev->flags & IFF_PROMISC) { if (corkscrew_debug > 3) diff --git a/drivers/net/ethernet/8390/mac8390.c b/drivers/net/ethernet/8390/mac8390.c index 342ae08ec3c2..d60a86aa8aa8 100644 --- a/drivers/net/ethernet/8390/mac8390.c +++ b/drivers/net/ethernet/8390/mac8390.c @@ -153,8 +153,6 @@ static void dayna_block_input(struct net_device *dev, int count, static void dayna_block_output(struct net_device *dev, int count, const unsigned char *buf, int start_page); -#define memcmp_withio(a, b, c) memcmp((a), (void *)(b), (c)) - /* Slow Sane (16-bit chunk memory read/write) Cabletron uses this */ static void slow_sane_get_8390_hdr(struct net_device *dev, struct e8390_pkt_hdr *hdr, int ring_page); @@ -233,19 +231,26 @@ static enum mac8390_type mac8390_ident(struct nubus_rsrc *fres) static enum mac8390_access mac8390_testio(unsigned long membase) { - unsigned long outdata = 0xA5A0B5B0; - unsigned long indata = 0x00000000; + u32 outdata = 0xA5A0B5B0; + u32 indata = 0; + /* Try writing 32 bits */ - memcpy_toio((void __iomem *)membase, &outdata, 4); - /* Now compare them */ - if (memcmp_withio(&outdata, membase, 4) == 0) + nubus_writel(outdata, membase); + /* Now read it back */ + indata = nubus_readl(membase); + if (outdata == indata) return ACCESS_32; + + outdata = 0xC5C0D5D0; + indata = 0; + /* Write 16 bit output */ word_memcpy_tocard(membase, &outdata, 4); /* Now read it back */ word_memcpy_fromcard(&indata, membase, 4); if (outdata == indata) return ACCESS_16; + return ACCESS_UNKNOWN; } diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 74550ccc7a20..e2ffb159cbe2 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -186,11 +186,12 @@ static void aq_rx_checksum(struct aq_ring_s *self, } if (buff->is_ip_cso) { __skb_incr_checksum_unnecessary(skb); - if (buff->is_udp_cso || buff->is_tcp_cso) - __skb_incr_checksum_unnecessary(skb); } else { skb->ip_summed = CHECKSUM_NONE; } + + if (buff->is_udp_cso || buff->is_tcp_cso) + __skb_incr_checksum_unnecessary(skb); } #define AQ_SKB_ALIGN SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c index 9e07b469066a..156fbc5601ca 100644 --- a/drivers/net/ethernet/atheros/atlx/atl1.c +++ b/drivers/net/ethernet/atheros/atlx/atl1.c @@ -1721,7 +1721,7 @@ static void atl1_inc_smb(struct atl1_adapter *adapter) adapter->soft_stats.scc += smb->tx_1_col; adapter->soft_stats.mcc += smb->tx_2_col; adapter->soft_stats.latecol += smb->tx_late_col; - adapter->soft_stats.tx_underun += smb->tx_underrun; + adapter->soft_stats.tx_underrun += smb->tx_underrun; adapter->soft_stats.tx_trunc += smb->tx_trunc; adapter->soft_stats.tx_pause += smb->tx_pause; @@ -3179,7 +3179,7 @@ static struct atl1_stats atl1_gstrings_stats[] = { {"tx_deferred_ok", ATL1_STAT(soft_stats.deffer)}, {"tx_single_coll_ok", ATL1_STAT(soft_stats.scc)}, {"tx_multi_coll_ok", ATL1_STAT(soft_stats.mcc)}, - {"tx_underun", ATL1_STAT(soft_stats.tx_underun)}, + {"tx_underrun", ATL1_STAT(soft_stats.tx_underrun)}, {"tx_trunc", ATL1_STAT(soft_stats.tx_trunc)}, {"tx_pause", ATL1_STAT(soft_stats.tx_pause)}, {"rx_pause", ATL1_STAT(soft_stats.rx_pause)}, diff --git a/drivers/net/ethernet/atheros/atlx/atl1.h b/drivers/net/ethernet/atheros/atlx/atl1.h index 34a58cd846a0..eacff19ea05b 100644 --- a/drivers/net/ethernet/atheros/atlx/atl1.h +++ b/drivers/net/ethernet/atheros/atlx/atl1.h @@ -681,7 +681,7 @@ struct atl1_sft_stats { u64 scc; /* packets TX after a single collision */ u64 mcc; /* packets TX after multiple collisions */ u64 latecol; /* TX packets w/ late collisions */ - u64 tx_underun; /* TX packets aborted due to TX FIFO underrun + u64 tx_underrun; /* TX packets aborted due to TX FIFO underrun * or TRD FIFO underrun */ u64 tx_trunc; /* TX packets truncated due to size > MTU */ u64 rx_pause; /* num Pause packets received. */ diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c index d99317b3d891..98da0fa27192 100644 --- a/drivers/net/ethernet/atheros/atlx/atl2.c +++ b/drivers/net/ethernet/atheros/atlx/atl2.c @@ -553,7 +553,7 @@ static void atl2_intr_tx(struct atl2_adapter *adapter) netdev->stats.tx_aborted_errors++; if (txs->late_col) netdev->stats.tx_window_errors++; - if (txs->underun) + if (txs->underrun) netdev->stats.tx_fifo_errors++; } while (1); diff --git a/drivers/net/ethernet/atheros/atlx/atl2.h b/drivers/net/ethernet/atheros/atlx/atl2.h index c64a6bdfa7ae..25ec84cb4853 100644 --- a/drivers/net/ethernet/atheros/atlx/atl2.h +++ b/drivers/net/ethernet/atheros/atlx/atl2.h @@ -260,7 +260,7 @@ struct tx_pkt_status { unsigned multi_col:1; unsigned late_col:1; unsigned abort_col:1; - unsigned underun:1; /* current packet is aborted + unsigned underrun:1; /* current packet is aborted * due to txram underrun */ unsigned:3; /* reserved */ unsigned update:1; /* always 1'b1 in tx_status_buf */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c index a9bdc21873d3..10ff37d6dc78 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c @@ -957,7 +957,7 @@ int bnx2x_vfpf_update_vlan(struct bnx2x *bp, u16 vid, u8 vf_qid, bool add) bnx2x_sample_bulletin(bp); if (bp->shadow_bulletin.content.valid_bitmap & 1 << VLAN_VALID) { - BNX2X_ERR("Hypervisor will dicline the request, avoiding\n"); + BNX2X_ERR("Hypervisor will decline the request, avoiding\n"); rc = -EINVAL; goto out; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 0bb9d7b3a2b6..52ade133b57c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1133,6 +1133,8 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, tpa_info = &rxr->rx_tpa[agg_id]; if (unlikely(cons != rxr->rx_next_cons)) { + netdev_warn(bp->dev, "TPA cons %x != expected cons %x\n", + cons, rxr->rx_next_cons); bnxt_sched_reset(bp, rxr); return; } @@ -1585,15 +1587,17 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, } cons = rxcmp->rx_cmp_opaque; - rx_buf = &rxr->rx_buf_ring[cons]; - data = rx_buf->data; - data_ptr = rx_buf->data_ptr; if (unlikely(cons != rxr->rx_next_cons)) { int rc1 = bnxt_discard_rx(bp, cpr, raw_cons, rxcmp); + netdev_warn(bp->dev, "RX cons %x != expected cons %x\n", + cons, rxr->rx_next_cons); bnxt_sched_reset(bp, rxr); return rc1; } + rx_buf = &rxr->rx_buf_ring[cons]; + data = rx_buf->data; + data_ptr = rx_buf->data_ptr; prefetch(data_ptr); misc = le32_to_cpu(rxcmp->rx_cmp_misc_v1); @@ -1610,12 +1614,18 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, rx_buf->data = NULL; if (rxcmp1->rx_cmp_cfa_code_errors_v2 & RX_CMP_L2_ERRORS) { + u32 rx_err = le32_to_cpu(rxcmp1->rx_cmp_cfa_code_errors_v2); + bnxt_reuse_rx_data(rxr, cons, data); if (agg_bufs) bnxt_reuse_rx_agg_bufs(cpr, cp_cons, agg_bufs); rc = -EIO; - goto next_rx; + if (rx_err & RX_CMPL_ERRORS_BUFFER_ERROR_MASK) { + netdev_warn(bp->dev, "RX buffer error %x\n", rx_err); + bnxt_sched_reset(bp, rxr); + } + goto next_rx_no_len; } len = le32_to_cpu(rxcmp->rx_cmp_len_flags_type) >> RX_CMP_LEN_SHIFT; @@ -1696,12 +1706,13 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, rc = 1; next_rx: - rxr->rx_prod = NEXT_RX(prod); - rxr->rx_next_cons = NEXT_RX(cons); - cpr->rx_packets += 1; cpr->rx_bytes += len; +next_rx_no_len: + rxr->rx_prod = NEXT_RX(prod); + rxr->rx_next_cons = NEXT_RX(cons); + next_rx_no_prod_no_len: *raw_cons = tmp_raw_cons; @@ -5125,10 +5136,10 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path) for (i = 0; i < bp->tx_nr_rings; i++) { struct bnxt_tx_ring_info *txr = &bp->tx_ring[i]; struct bnxt_ring_struct *ring = &txr->tx_ring_struct; - u32 cmpl_ring_id; - cmpl_ring_id = bnxt_cp_ring_for_tx(bp, txr); if (ring->fw_ring_id != INVALID_HW_RING_ID) { + u32 cmpl_ring_id = bnxt_cp_ring_for_tx(bp, txr); + hwrm_ring_free_send_msg(bp, ring, RING_FREE_REQ_RING_TYPE_TX, close_path ? cmpl_ring_id : @@ -5141,10 +5152,10 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path) struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; struct bnxt_ring_struct *ring = &rxr->rx_ring_struct; u32 grp_idx = rxr->bnapi->index; - u32 cmpl_ring_id; - cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr); if (ring->fw_ring_id != INVALID_HW_RING_ID) { + u32 cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr); + hwrm_ring_free_send_msg(bp, ring, RING_FREE_REQ_RING_TYPE_RX, close_path ? cmpl_ring_id : @@ -5163,10 +5174,10 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path) struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; struct bnxt_ring_struct *ring = &rxr->rx_agg_ring_struct; u32 grp_idx = rxr->bnapi->index; - u32 cmpl_ring_id; - cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr); if (ring->fw_ring_id != INVALID_HW_RING_ID) { + u32 cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr); + hwrm_ring_free_send_msg(bp, ring, type, close_path ? cmpl_ring_id : INVALID_HW_RING_ID); @@ -5305,17 +5316,16 @@ __bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, struct hwrm_func_cfg_input *req, req->num_tx_rings = cpu_to_le16(tx_rings); if (BNXT_NEW_RM(bp)) { enables |= rx_rings ? FUNC_CFG_REQ_ENABLES_NUM_RX_RINGS : 0; + enables |= stats ? FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0; if (bp->flags & BNXT_FLAG_CHIP_P5) { enables |= cp_rings ? FUNC_CFG_REQ_ENABLES_NUM_MSIX : 0; enables |= tx_rings + ring_grps ? - FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS | - FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0; + FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0; enables |= rx_rings ? FUNC_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS : 0; } else { enables |= cp_rings ? - FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS | - FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0; + FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0; enables |= ring_grps ? FUNC_CFG_REQ_ENABLES_NUM_HW_RING_GRPS | FUNC_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS : 0; @@ -5355,14 +5365,13 @@ __bnxt_hwrm_reserve_vf_rings(struct bnxt *bp, enables |= tx_rings ? FUNC_VF_CFG_REQ_ENABLES_NUM_TX_RINGS : 0; enables |= rx_rings ? FUNC_VF_CFG_REQ_ENABLES_NUM_RX_RINGS | FUNC_VF_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS : 0; + enables |= stats ? FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0; if (bp->flags & BNXT_FLAG_CHIP_P5) { enables |= tx_rings + ring_grps ? - FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS | - FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0; + FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0; } else { enables |= cp_rings ? - FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS | - FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0; + FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0; enables |= ring_grps ? FUNC_VF_CFG_REQ_ENABLES_NUM_HW_RING_GRPS : 0; } @@ -6743,6 +6752,7 @@ static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp) struct hwrm_queue_pri2cos_qcfg_input req2 = {0}; struct hwrm_port_qstats_ext_input req = {0}; struct bnxt_pf_info *pf = &bp->pf; + u32 tx_stat_size; int rc; if (!(bp->flags & BNXT_FLAG_PORT_STATS_EXT)) @@ -6752,13 +6762,16 @@ static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp) req.port_id = cpu_to_le16(pf->port_id); req.rx_stat_size = cpu_to_le16(sizeof(struct rx_port_stats_ext)); req.rx_stat_host_addr = cpu_to_le64(bp->hw_rx_port_stats_ext_map); - req.tx_stat_size = cpu_to_le16(sizeof(struct tx_port_stats_ext)); + tx_stat_size = bp->hw_tx_port_stats_ext ? + sizeof(*bp->hw_tx_port_stats_ext) : 0; + req.tx_stat_size = cpu_to_le16(tx_stat_size); req.tx_stat_host_addr = cpu_to_le64(bp->hw_tx_port_stats_ext_map); mutex_lock(&bp->hwrm_cmd_lock); rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (!rc) { bp->fw_rx_stats_ext_size = le16_to_cpu(resp->rx_stat_size) / 8; - bp->fw_tx_stats_ext_size = le16_to_cpu(resp->tx_stat_size) / 8; + bp->fw_tx_stats_ext_size = tx_stat_size ? + le16_to_cpu(resp->tx_stat_size) / 8 : 0; } else { bp->fw_rx_stats_ext_size = 0; bp->fw_tx_stats_ext_size = 0; @@ -8951,8 +8964,15 @@ static int bnxt_cfg_rx_mode(struct bnxt *bp) skip_uc: rc = bnxt_hwrm_cfa_l2_set_rx_mask(bp, 0); + if (rc && vnic->mc_list_count) { + netdev_info(bp->dev, "Failed setting MC filters rc: %d, turning on ALL_MCAST mode\n", + rc); + vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST; + vnic->mc_list_count = 0; + rc = bnxt_hwrm_cfa_l2_set_rx_mask(bp, 0); + } if (rc) - netdev_err(bp->dev, "HWRM cfa l2 rx mask failure rc: %x\n", + netdev_err(bp->dev, "HWRM cfa l2 rx mask failure rc: %d\n", rc); return rc; @@ -10675,6 +10695,7 @@ init_err_cleanup_tc: bnxt_clear_int_mode(bp); init_err_pci_clean: + bnxt_free_hwrm_short_cmd_req(bp); bnxt_free_hwrm_resources(bp); bnxt_free_ctx_mem(bp); kfree(bp->ctx); diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 328373e0578f..060a6f386104 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -4283,7 +4283,7 @@ static void tg3_power_down(struct tg3 *tp) pci_set_power_state(tp->pdev, PCI_D3hot); } -static void tg3_aux_stat_to_speed_duplex(struct tg3 *tp, u32 val, u16 *speed, u8 *duplex) +static void tg3_aux_stat_to_speed_duplex(struct tg3 *tp, u32 val, u32 *speed, u8 *duplex) { switch (val & MII_TG3_AUX_STAT_SPDMASK) { case MII_TG3_AUX_STAT_10HALF: @@ -4787,7 +4787,7 @@ static int tg3_setup_copper_phy(struct tg3 *tp, bool force_reset) bool current_link_up; u32 bmsr, val; u32 lcl_adv, rmt_adv; - u16 current_speed; + u32 current_speed; u8 current_duplex; int i, err; @@ -5719,7 +5719,7 @@ out: static int tg3_setup_fiber_phy(struct tg3 *tp, bool force_reset) { u32 orig_pause_cfg; - u16 orig_active_speed; + u32 orig_active_speed; u8 orig_active_duplex; u32 mac_status; bool current_link_up; @@ -5823,7 +5823,7 @@ static int tg3_setup_fiber_mii_phy(struct tg3 *tp, bool force_reset) { int err = 0; u32 bmsr, bmcr; - u16 current_speed = SPEED_UNKNOWN; + u32 current_speed = SPEED_UNKNOWN; u8 current_duplex = DUPLEX_UNKNOWN; bool current_link_up = false; u32 local_adv, remote_adv, sgsr; diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h index a772a33b685c..6953d0546acb 100644 --- a/drivers/net/ethernet/broadcom/tg3.h +++ b/drivers/net/ethernet/broadcom/tg3.h @@ -2873,7 +2873,7 @@ struct tg3_tx_ring_info { struct tg3_link_config { /* Describes what we're trying to get. */ u32 advertising; - u16 speed; + u32 speed; u8 duplex; u8 autoneg; u8 flowctrl; @@ -2882,7 +2882,7 @@ struct tg3_link_config { u8 active_flowctrl; u8 active_duplex; - u16 active_speed; + u32 active_speed; u32 rmt_adv; }; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index ad099fd01b45..3da2795e2486 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -898,7 +898,9 @@ static void macb_tx_interrupt(struct macb_queue *queue) /* First, update TX stats if needed */ if (skb) { - if (gem_ptp_do_txstamp(queue, skb, desc) == 0) { + if (unlikely(skb_shinfo(skb)->tx_flags & + SKBTX_HW_TSTAMP) && + gem_ptp_do_txstamp(queue, skb, desc) == 0) { /* skb now belongs to timestamp buffer * and will be removed later */ @@ -3370,14 +3372,20 @@ static int macb_clk_init(struct platform_device *pdev, struct clk **pclk, *hclk = devm_clk_get(&pdev->dev, "hclk"); } - if (IS_ERR(*pclk)) { + if (IS_ERR_OR_NULL(*pclk)) { err = PTR_ERR(*pclk); + if (!err) + err = -ENODEV; + dev_err(&pdev->dev, "failed to get macb_clk (%u)\n", err); return err; } - if (IS_ERR(*hclk)) { + if (IS_ERR_OR_NULL(*hclk)) { err = PTR_ERR(*hclk); + if (!err) + err = -ENODEV; + dev_err(&pdev->dev, "failed to get hclk (%u)\n", err); return err; } diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index aa2be4807191..c032bef1b776 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -32,6 +32,13 @@ #define DRV_NAME "nicvf" #define DRV_VERSION "1.0" +/* NOTE: Packets bigger than 1530 are split across multiple pages and XDP needs + * the buffer to be contiguous. Allow XDP to be set up only if we don't exceed + * this value, keeping headroom for the 14 byte Ethernet header and two + * VLAN tags (for QinQ) + */ +#define MAX_XDP_MTU (1530 - ETH_HLEN - VLAN_HLEN * 2) + /* Supported devices */ static const struct pci_device_id nicvf_id_table[] = { { PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, @@ -1328,10 +1335,11 @@ int nicvf_stop(struct net_device *netdev) struct nicvf_cq_poll *cq_poll = NULL; union nic_mbx mbx = {}; - cancel_delayed_work_sync(&nic->link_change_work); - /* wait till all queued set_rx_mode tasks completes */ - drain_workqueue(nic->nicvf_rx_mode_wq); + if (nic->nicvf_rx_mode_wq) { + cancel_delayed_work_sync(&nic->link_change_work); + drain_workqueue(nic->nicvf_rx_mode_wq); + } mbx.msg.msg = NIC_MBOX_MSG_SHUTDOWN; nicvf_send_msg_to_pf(nic, &mbx); @@ -1452,7 +1460,8 @@ int nicvf_open(struct net_device *netdev) struct nicvf_cq_poll *cq_poll = NULL; /* wait till all queued set_rx_mode tasks completes if any */ - drain_workqueue(nic->nicvf_rx_mode_wq); + if (nic->nicvf_rx_mode_wq) + drain_workqueue(nic->nicvf_rx_mode_wq); netif_carrier_off(netdev); @@ -1550,10 +1559,12 @@ int nicvf_open(struct net_device *netdev) /* Send VF config done msg to PF */ nicvf_send_cfg_done(nic); - INIT_DELAYED_WORK(&nic->link_change_work, - nicvf_link_status_check_task); - queue_delayed_work(nic->nicvf_rx_mode_wq, - &nic->link_change_work, 0); + if (nic->nicvf_rx_mode_wq) { + INIT_DELAYED_WORK(&nic->link_change_work, + nicvf_link_status_check_task); + queue_delayed_work(nic->nicvf_rx_mode_wq, + &nic->link_change_work, 0); + } return 0; cleanup: @@ -1578,6 +1589,15 @@ static int nicvf_change_mtu(struct net_device *netdev, int new_mtu) struct nicvf *nic = netdev_priv(netdev); int orig_mtu = netdev->mtu; + /* For now just support only the usual MTU sized frames, + * plus some headroom for VLAN, QinQ. + */ + if (nic->xdp_prog && new_mtu > MAX_XDP_MTU) { + netdev_warn(netdev, "Jumbo frames not yet supported with XDP, current MTU %d.\n", + netdev->mtu); + return -EINVAL; + } + netdev->mtu = new_mtu; if (!netif_running(netdev)) @@ -1826,8 +1846,10 @@ static int nicvf_xdp_setup(struct nicvf *nic, struct bpf_prog *prog) bool bpf_attached = false; int ret = 0; - /* For now just support only the usual MTU sized frames */ - if (prog && (dev->mtu > 1500)) { + /* For now just support only the usual MTU sized frames, + * plus some headroom for VLAN, QinQ. + */ + if (prog && dev->mtu > MAX_XDP_MTU) { netdev_warn(dev, "Jumbo frames not yet supported with XDP, current MTU %d.\n", dev->mtu); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c index 5b4d3badcb73..e246f9733bb8 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c @@ -105,20 +105,19 @@ static inline struct pgcache *nicvf_alloc_page(struct nicvf *nic, /* Check if page can be recycled */ if (page) { ref_count = page_ref_count(page); - /* Check if this page has been used once i.e 'put_page' - * called after packet transmission i.e internal ref_count - * and page's ref_count are equal i.e page can be recycled. + /* This page can be recycled if internal ref_count and page's + * ref_count are equal, indicating that the page has been used + * once for packet transmission. For non-XDP mode, internal + * ref_count is always '1'. */ - if (rbdr->is_xdp && (ref_count == pgcache->ref_count)) - pgcache->ref_count--; - else - page = NULL; - - /* In non-XDP mode, page's ref_count needs to be '1' for it - * to be recycled. - */ - if (!rbdr->is_xdp && (ref_count != 1)) + if (rbdr->is_xdp) { + if (ref_count == pgcache->ref_count) + pgcache->ref_count--; + else + page = NULL; + } else if (ref_count != 1) { page = NULL; + } } if (!page) { @@ -365,11 +364,10 @@ static void nicvf_free_rbdr(struct nicvf *nic, struct rbdr *rbdr) while (head < rbdr->pgcnt) { pgcache = &rbdr->pgcache[head]; if (pgcache->page && page_ref_count(pgcache->page) != 0) { - if (!rbdr->is_xdp) { - put_page(pgcache->page); - continue; + if (rbdr->is_xdp) { + page_ref_sub(pgcache->page, + pgcache->ref_count - 1); } - page_ref_sub(pgcache->page, pgcache->ref_count - 1); put_page(pgcache->page); } head++; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index 3130b43bba52..02959035ed3f 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -2620,7 +2620,7 @@ static inline struct port_info *ethqset2pinfo(struct adapter *adap, int qset) } /* should never happen! */ - BUG_ON(1); + BUG(); return NULL; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index 88773ca58e6b..b3da81e90132 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -476,7 +476,7 @@ static inline int get_buf_size(struct adapter *adapter, break; default: - BUG_ON(1); + BUG(); } return buf_size; diff --git a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c index 74849be5f004..e2919005ead3 100644 --- a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c +++ b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c @@ -354,7 +354,10 @@ static struct cxgbi_ppm_pool *ppm_alloc_cpu_pool(unsigned int *total, ppmax = max; /* pool size must be multiple of unsigned long */ - bmap = BITS_TO_LONGS(ppmax); + bmap = ppmax / BITS_PER_TYPE(unsigned long); + if (!bmap) + return NULL; + ppmax = (bmap * sizeof(unsigned long)) << 3; alloc_sz = sizeof(*pools) + sizeof(unsigned long) * bmap; @@ -402,6 +405,10 @@ int cxgbi_ppm_init(void **ppm_pp, struct net_device *ndev, if (reserve_factor) { ppmax_pool = ppmax / reserve_factor; pool = ppm_alloc_cpu_pool(&ppmax_pool, &pool_index_max); + if (!pool) { + ppmax_pool = 0; + reserve_factor = 0; + } pr_debug("%s: ppmax %u, cpu total %u, per cpu %u.\n", ndev->name, ppmax, ppmax_pool, pool_index_max); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 2ba49e959c3f..dc339dc1adb2 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -815,6 +815,14 @@ static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev) */ queue_mapping = skb_get_queue_mapping(skb); fq = &priv->fq[queue_mapping]; + + fd_len = dpaa2_fd_get_len(&fd); + nq = netdev_get_tx_queue(net_dev, queue_mapping); + netdev_tx_sent_queue(nq, fd_len); + + /* Everything that happens after this enqueues might race with + * the Tx confirmation callback for this frame + */ for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) { err = priv->enqueue(priv, fq, &fd, 0); if (err != -EBUSY) @@ -825,13 +833,10 @@ static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev) percpu_stats->tx_errors++; /* Clean up everything, including freeing the skb */ free_tx_fd(priv, fq, &fd, false); + netdev_tx_completed_queue(nq, 1, fd_len); } else { - fd_len = dpaa2_fd_get_len(&fd); percpu_stats->tx_packets++; percpu_stats->tx_bytes += fd_len; - - nq = netdev_get_tx_queue(net_dev, queue_mapping); - netdev_tx_sent_queue(nq, fd_len); } return NETDEV_TX_OK; @@ -1817,7 +1822,7 @@ static int dpaa2_eth_xdp_xmit_frame(struct net_device *net_dev, dpaa2_fd_set_format(&fd, dpaa2_fd_single); dpaa2_fd_set_ctrl(&fd, FD_CTRL_PTA); - fq = &priv->fq[smp_processor_id()]; + fq = &priv->fq[smp_processor_id() % dpaa2_eth_queue_count(priv)]; for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) { err = priv->enqueue(priv, fq, &fd, 0); if (err != -EBUSY) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 697c2427f2b7..a96ad20ee484 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1840,13 +1840,9 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable) int ret; if (enable) { - ret = clk_prepare_enable(fep->clk_ahb); - if (ret) - return ret; - ret = clk_prepare_enable(fep->clk_enet_out); if (ret) - goto failed_clk_enet_out; + return ret; if (fep->clk_ptp) { mutex_lock(&fep->ptp_clk_mutex); @@ -1866,7 +1862,6 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable) phy_reset_after_clk_enable(ndev->phydev); } else { - clk_disable_unprepare(fep->clk_ahb); clk_disable_unprepare(fep->clk_enet_out); if (fep->clk_ptp) { mutex_lock(&fep->ptp_clk_mutex); @@ -1885,8 +1880,6 @@ failed_clk_ref: failed_clk_ptp: if (fep->clk_enet_out) clk_disable_unprepare(fep->clk_enet_out); -failed_clk_enet_out: - clk_disable_unprepare(fep->clk_ahb); return ret; } @@ -3470,6 +3463,9 @@ fec_probe(struct platform_device *pdev) ret = clk_prepare_enable(fep->clk_ipg); if (ret) goto failed_clk_ipg; + ret = clk_prepare_enable(fep->clk_ahb); + if (ret) + goto failed_clk_ahb; fep->reg_phy = devm_regulator_get_optional(&pdev->dev, "phy"); if (!IS_ERR(fep->reg_phy)) { @@ -3563,6 +3559,9 @@ failed_reset: pm_runtime_put(&pdev->dev); pm_runtime_disable(&pdev->dev); failed_regulator: + clk_disable_unprepare(fep->clk_ahb); +failed_clk_ahb: + clk_disable_unprepare(fep->clk_ipg); failed_clk_ipg: fec_enet_clk_enable(ndev, false); failed_clk: @@ -3686,6 +3685,7 @@ static int __maybe_unused fec_runtime_suspend(struct device *dev) struct net_device *ndev = dev_get_drvdata(dev); struct fec_enet_private *fep = netdev_priv(ndev); + clk_disable_unprepare(fep->clk_ahb); clk_disable_unprepare(fep->clk_ipg); return 0; @@ -3695,8 +3695,20 @@ static int __maybe_unused fec_runtime_resume(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); struct fec_enet_private *fep = netdev_priv(ndev); + int ret; - return clk_prepare_enable(fep->clk_ipg); + ret = clk_prepare_enable(fep->clk_ahb); + if (ret) + return ret; + ret = clk_prepare_enable(fep->clk_ipg); + if (ret) + goto failed_clk_ipg; + + return 0; + +failed_clk_ipg: + clk_disable_unprepare(fep->clk_ahb); + return ret; } static const struct dev_pm_ops fec_pm_ops = { diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c index 79d03f8ee7b1..c7fa97a7e1f4 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.c +++ b/drivers/net/ethernet/hisilicon/hns/hnae.c @@ -150,7 +150,6 @@ out_buffer_fail: /* free desc along with its attached buffer */ static void hnae_free_desc(struct hnae_ring *ring) { - hnae_free_buffers(ring); dma_unmap_single(ring_to_dev(ring), ring->desc_dma_addr, ring->desc_num * sizeof(ring->desc[0]), ring_to_dma_dir(ring)); @@ -183,6 +182,9 @@ static int hnae_alloc_desc(struct hnae_ring *ring) /* fini ring, also free the buffer for the ring */ static void hnae_fini_ring(struct hnae_ring *ring) { + if (is_rx_ring(ring)) + hnae_free_buffers(ring); + hnae_free_desc(ring); kfree(ring->desc_cb); ring->desc_cb = NULL; diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h index 08a750fb60c4..d6fb83437230 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.h +++ b/drivers/net/ethernet/hisilicon/hns/hnae.h @@ -357,7 +357,7 @@ struct hnae_buf_ops { }; struct hnae_queue { - void __iomem *io_base; + u8 __iomem *io_base; phys_addr_t phy_base; struct hnae_ae_dev *dev; /* the device who use this queue */ struct hnae_ring rx_ring ____cacheline_internodealigned_in_smp; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c index a97228c93831..6c0507921623 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c @@ -370,7 +370,7 @@ int hns_mac_clr_multicast(struct hns_mac_cb *mac_cb, int vfn) static void hns_mac_param_get(struct mac_params *param, struct hns_mac_cb *mac_cb) { - param->vaddr = (void *)mac_cb->vaddr; + param->vaddr = mac_cb->vaddr; param->mac_mode = hns_get_enet_interface(mac_cb); ether_addr_copy(param->addr, mac_cb->addr_entry_idx[0].addr); param->mac_id = mac_cb->mac_id; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h index fbc75341bef7..22589799f1a5 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h @@ -187,7 +187,7 @@ struct mac_statistics { /*mac para struct ,mac get param from nic or dsaf when initialize*/ struct mac_params { char addr[ETH_ALEN]; - void *vaddr; /*virtual address*/ + u8 __iomem *vaddr; /*virtual address*/ struct device *dev; u8 mac_id; /**< Ethernet operation mode (MAC-PHY interface and speed) */ @@ -402,7 +402,7 @@ struct mac_driver { enum mac_mode mac_mode; u8 mac_id; struct hns_mac_cb *mac_cb; - void __iomem *io_base; + u8 __iomem *io_base; unsigned int mac_en_flg;/*you'd better don't enable mac twice*/ unsigned int virt_dev_num; struct device *dev; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index ac55db065f16..61eea6ac846f 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -1602,8 +1602,6 @@ static void hns_dsaf_set_mac_key( DSAF_TBL_TCAM_KEY_VLAN_S, vlan_id); dsaf_set_field(mac_key->low.bits.port_vlan, DSAF_TBL_TCAM_KEY_PORT_M, DSAF_TBL_TCAM_KEY_PORT_S, port); - - mac_key->low.bits.port_vlan = le16_to_cpu(mac_key->low.bits.port_vlan); } /** @@ -1663,8 +1661,8 @@ int hns_dsaf_set_mac_uc_entry( /* default config dvc to 0 */ mac_data.tbl_ucast_dvc = 0; mac_data.tbl_ucast_out_port = mac_entry->port_num; - tcam_data.tbl_tcam_data_high = cpu_to_le32(mac_key.high.val); - tcam_data.tbl_tcam_data_low = cpu_to_le32(mac_key.low.val); + tcam_data.tbl_tcam_data_high = mac_key.high.val; + tcam_data.tbl_tcam_data_low = mac_key.low.val; hns_dsaf_tcam_uc_cfg(dsaf_dev, entry_index, &tcam_data, &mac_data); @@ -1786,9 +1784,6 @@ int hns_dsaf_add_mac_mc_port(struct dsaf_device *dsaf_dev, 0xff, mc_mask); - mask_key.high.val = le32_to_cpu(mask_key.high.val); - mask_key.low.val = le32_to_cpu(mask_key.low.val); - pmask_key = (struct dsaf_tbl_tcam_data *)(&mask_key); } @@ -1840,8 +1835,8 @@ int hns_dsaf_add_mac_mc_port(struct dsaf_device *dsaf_dev, dsaf_dev->ae_dev.name, mac_key.high.val, mac_key.low.val, entry_index); - tcam_data.tbl_tcam_data_high = cpu_to_le32(mac_key.high.val); - tcam_data.tbl_tcam_data_low = cpu_to_le32(mac_key.low.val); + tcam_data.tbl_tcam_data_high = mac_key.high.val; + tcam_data.tbl_tcam_data_low = mac_key.low.val; /* config mc entry with mask */ hns_dsaf_tcam_mc_cfg(dsaf_dev, entry_index, &tcam_data, @@ -1956,9 +1951,6 @@ int hns_dsaf_del_mac_mc_port(struct dsaf_device *dsaf_dev, /* config key mask */ hns_dsaf_set_mac_key(dsaf_dev, &mask_key, 0x00, 0xff, mc_mask); - mask_key.high.val = le32_to_cpu(mask_key.high.val); - mask_key.low.val = le32_to_cpu(mask_key.low.val); - pmask_key = (struct dsaf_tbl_tcam_data *)(&mask_key); } @@ -2012,8 +2004,8 @@ int hns_dsaf_del_mac_mc_port(struct dsaf_device *dsaf_dev, soft_mac_entry += entry_index; soft_mac_entry->index = DSAF_INVALID_ENTRY_IDX; } else { /* not zero, just del port, update */ - tcam_data.tbl_tcam_data_high = cpu_to_le32(mac_key.high.val); - tcam_data.tbl_tcam_data_low = cpu_to_le32(mac_key.low.val); + tcam_data.tbl_tcam_data_high = mac_key.high.val; + tcam_data.tbl_tcam_data_low = mac_key.low.val; hns_dsaf_tcam_mc_cfg(dsaf_dev, entry_index, &tcam_data, @@ -2750,6 +2742,17 @@ int hns_dsaf_get_regs_count(void) return DSAF_DUMP_REGS_NUM; } +static int hns_dsaf_get_port_id(u8 port) +{ + if (port < DSAF_SERVICE_NW_NUM) + return port; + + if (port >= DSAF_BASE_INNER_PORT_NUM) + return port - DSAF_BASE_INNER_PORT_NUM + DSAF_SERVICE_NW_NUM; + + return -EINVAL; +} + static void set_promisc_tcam_enable(struct dsaf_device *dsaf_dev, u32 port) { struct dsaf_tbl_tcam_ucast_cfg tbl_tcam_ucast = {0, 1, 0, 0, 0x80}; @@ -2815,23 +2818,33 @@ static void set_promisc_tcam_enable(struct dsaf_device *dsaf_dev, u32 port) memset(&temp_key, 0x0, sizeof(temp_key)); mask_entry.addr[0] = 0x01; hns_dsaf_set_mac_key(dsaf_dev, &mask_key, mask_entry.in_vlan_id, - port, mask_entry.addr); + 0xf, mask_entry.addr); tbl_tcam_mcast.tbl_mcast_item_vld = 1; tbl_tcam_mcast.tbl_mcast_old_en = 0; - if (port < DSAF_SERVICE_NW_NUM) { - mskid = port; - } else if (port >= DSAF_BASE_INNER_PORT_NUM) { - mskid = port - DSAF_BASE_INNER_PORT_NUM + DSAF_SERVICE_NW_NUM; - } else { + /* set MAC port to handle multicast */ + mskid = hns_dsaf_get_port_id(port); + if (mskid == -EINVAL) { dev_err(dsaf_dev->dev, "%s,pnum(%d)error,key(%#x:%#x)\n", dsaf_dev->ae_dev.name, port, mask_key.high.val, mask_key.low.val); return; } + dsaf_set_bit(tbl_tcam_mcast.tbl_mcast_port_msk[mskid / 32], + mskid % 32, 1); + /* set pool bit map to handle multicast */ + mskid = hns_dsaf_get_port_id(port_num); + if (mskid == -EINVAL) { + dev_err(dsaf_dev->dev, + "%s, pool bit map pnum(%d)error,key(%#x:%#x)\n", + dsaf_dev->ae_dev.name, port_num, + mask_key.high.val, mask_key.low.val); + return; + } dsaf_set_bit(tbl_tcam_mcast.tbl_mcast_port_msk[mskid / 32], mskid % 32, 1); + memcpy(&temp_key, &mask_key, sizeof(mask_key)); hns_dsaf_tcam_mc_cfg_vague(dsaf_dev, entry_index, &tbl_tcam_data_mc, (struct dsaf_tbl_tcam_data *)(&mask_key), diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h index 0e1cd99831a6..76cc8887e1a8 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h @@ -467,4 +467,6 @@ int hns_dsaf_clr_mac_mc_port(struct dsaf_device *dsaf_dev, u8 mac_id, u8 port_num); int hns_dsaf_wait_pkt_clean(struct dsaf_device *dsaf_dev, int port); +int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset); + #endif /* __HNS_DSAF_MAIN_H__ */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c index 16294cd3c954..19b94879691f 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c @@ -670,7 +670,7 @@ static int hns_mac_config_sds_loopback(struct hns_mac_cb *mac_cb, bool en) dsaf_set_field(origin, 1ull << 10, 10, en); dsaf_write_syscon(mac_cb->serdes_ctrl, reg_offset, origin); } else { - u8 *base_addr = (u8 *)mac_cb->serdes_vaddr + + u8 __iomem *base_addr = mac_cb->serdes_vaddr + (mac_cb->mac_id <= 3 ? 0x00280000 : 0x00200000); dsaf_set_reg_field(base_addr, reg_offset, 1ull << 10, 10, en); } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c index 3d07c8a7639d..17c019106e6e 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c @@ -61,7 +61,7 @@ void hns_ppe_set_indir_table(struct hns_ppe_cb *ppe_cb, } } -static void __iomem * +static u8 __iomem * hns_ppe_common_get_ioaddr(struct ppe_common_cb *ppe_common) { return ppe_common->dsaf_dev->ppe_base + PPE_COMMON_REG_OFFSET; @@ -111,8 +111,8 @@ hns_ppe_common_free_cfg(struct dsaf_device *dsaf_dev, u32 comm_index) dsaf_dev->ppe_common[comm_index] = NULL; } -static void __iomem *hns_ppe_get_iobase(struct ppe_common_cb *ppe_common, - int ppe_idx) +static u8 __iomem *hns_ppe_get_iobase(struct ppe_common_cb *ppe_common, + int ppe_idx) { return ppe_common->dsaf_dev->ppe_base + ppe_idx * PPE_REG_OFFSET; } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h index f670e63a5a01..110c6e8222c7 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h @@ -80,7 +80,7 @@ struct hns_ppe_cb { struct hns_ppe_hw_stats hw_stats; u8 index; /* index in a ppe common device */ - void __iomem *io_base; + u8 __iomem *io_base; int virq; u32 rss_indir_table[HNS_PPEV2_RSS_IND_TBL_SIZE]; /*shadow indir tab */ u32 rss_key[HNS_PPEV2_RSS_KEY_NUM]; /* rss hash key */ @@ -89,7 +89,7 @@ struct hns_ppe_cb { struct ppe_common_cb { struct device *dev; struct dsaf_device *dsaf_dev; - void __iomem *io_base; + u8 __iomem *io_base; enum ppe_common_mode ppe_mode; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c index 6bf346c11b25..ac3518ca4d7b 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c @@ -458,7 +458,7 @@ static void hns_rcb_ring_get_cfg(struct hnae_queue *q, int ring_type) mdnum_ppkt = HNS_RCB_RING_MAX_BD_PER_PKT; } else { ring = &q->tx_ring; - ring->io_base = (u8 __iomem *)ring_pair_cb->q.io_base + + ring->io_base = ring_pair_cb->q.io_base + HNS_RCB_TX_REG_OFFSET; irq_idx = HNS_RCB_IRQ_IDX_TX; mdnum_ppkt = is_ver1 ? HNS_RCB_RING_MAX_TXBD_PER_PKT : @@ -764,7 +764,7 @@ static int hns_rcb_get_ring_num(struct dsaf_device *dsaf_dev) } } -static void __iomem *hns_rcb_common_get_vaddr(struct rcb_common_cb *rcb_common) +static u8 __iomem *hns_rcb_common_get_vaddr(struct rcb_common_cb *rcb_common) { struct dsaf_device *dsaf_dev = rcb_common->dsaf_dev; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h index b9733b0b8482..b9e7f11f0896 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h @@ -1018,7 +1018,7 @@ #define XGMAC_PAUSE_CTL_RSP_MODE_B 2 #define XGMAC_PAUSE_CTL_TX_XOFF_B 3 -static inline void dsaf_write_reg(void __iomem *base, u32 reg, u32 value) +static inline void dsaf_write_reg(u8 __iomem *base, u32 reg, u32 value) { writel(value, base + reg); } @@ -1053,7 +1053,7 @@ static inline int dsaf_read_syscon(struct regmap *base, u32 reg, u32 *val) #define dsaf_set_bit(origin, shift, val) \ dsaf_set_field((origin), (1ull << (shift)), (shift), (val)) -static inline void dsaf_set_reg_field(void __iomem *base, u32 reg, u32 mask, +static inline void dsaf_set_reg_field(u8 __iomem *base, u32 reg, u32 mask, u32 shift, u32 val) { u32 origin = dsaf_read_reg(base, reg); @@ -1073,7 +1073,7 @@ static inline void dsaf_set_reg_field(void __iomem *base, u32 reg, u32 mask, #define dsaf_get_bit(origin, shift) \ dsaf_get_field((origin), (1ull << (shift)), (shift)) -static inline u32 dsaf_get_reg_field(void __iomem *base, u32 reg, u32 mask, +static inline u32 dsaf_get_reg_field(u8 __iomem *base, u32 reg, u32 mask, u32 shift) { u32 origin; @@ -1089,11 +1089,11 @@ static inline u32 dsaf_get_reg_field(void __iomem *base, u32 reg, u32 mask, dsaf_get_reg_field((dev)->io_base, (reg), (1ull << (bit)), (bit)) #define dsaf_write_b(addr, data)\ - writeb((data), (__iomem unsigned char *)(addr)) + writeb((data), (__iomem u8 *)(addr)) #define dsaf_read_b(addr)\ - readb((__iomem unsigned char *)(addr)) + readb((__iomem u8 *)(addr)) #define hns_mac_reg_read64(drv, offset) \ - readq((__iomem void *)(((u8 *)(drv)->io_base + 0xc00 + (offset)))) + readq((__iomem void *)(((drv)->io_base + 0xc00 + (offset)))) #endif /* _DSAF_REG_H */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c index ba4316910dea..a60f207768fc 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c @@ -129,7 +129,7 @@ static void hns_xgmac_lf_rf_control_init(struct mac_driver *mac_drv) dsaf_set_bit(val, XGMAC_UNIDIR_EN_B, 0); dsaf_set_bit(val, XGMAC_RF_TX_EN_B, 1); dsaf_set_field(val, XGMAC_LF_RF_INSERT_M, XGMAC_LF_RF_INSERT_S, 0); - dsaf_write_reg(mac_drv, XGMAC_MAC_TX_LF_RF_CONTROL_REG, val); + dsaf_write_dev(mac_drv, XGMAC_MAC_TX_LF_RF_CONTROL_REG, val); } /** diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 60e7d7ae3787..4cd86ba1f050 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -29,9 +29,6 @@ #define SERVICE_TIMER_HZ (1 * HZ) -#define NIC_TX_CLEAN_MAX_NUM 256 -#define NIC_RX_CLEAN_MAX_NUM 64 - #define RCB_IRQ_NOT_INITED 0 #define RCB_IRQ_INITED 1 #define HNS_BUFFER_SIZE_2048 2048 @@ -376,8 +373,6 @@ netdev_tx_t hns_nic_net_xmit_hw(struct net_device *ndev, wmb(); /* commit all data before submit */ assert(skb->queue_mapping < priv->ae_handle->q_num); hnae_queue_xmit(priv->ae_handle->qs[skb->queue_mapping], buf_num); - ring->stats.tx_pkts++; - ring->stats.tx_bytes += skb->len; return NETDEV_TX_OK; @@ -999,6 +994,9 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data, /* issue prefetch for next Tx descriptor */ prefetch(&ring->desc_cb[ring->next_to_clean]); } + /* update tx ring statistics. */ + ring->stats.tx_pkts += pkts; + ring->stats.tx_bytes += bytes; NETIF_TX_UNLOCK(ring); @@ -2152,7 +2150,7 @@ static int hns_nic_init_ring_data(struct hns_nic_priv *priv) hns_nic_tx_fini_pro_v2; netif_napi_add(priv->netdev, &rd->napi, - hns_nic_common_poll, NIC_TX_CLEAN_MAX_NUM); + hns_nic_common_poll, NAPI_POLL_WEIGHT); rd->ring->irq_init_flag = RCB_IRQ_NOT_INITED; } for (i = h->q_num; i < h->q_num * 2; i++) { @@ -2165,7 +2163,7 @@ static int hns_nic_init_ring_data(struct hns_nic_priv *priv) hns_nic_rx_fini_pro_v2; netif_napi_add(priv->netdev, &rd->napi, - hns_nic_common_poll, NIC_RX_CLEAN_MAX_NUM); + hns_nic_common_poll, NAPI_POLL_WEIGHT); rd->ring->irq_init_flag = RCB_IRQ_NOT_INITED; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 1c1f17ec6be2..162cb9afa0e7 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -22,6 +22,7 @@ #include "hns3_enet.h" #define hns3_set_field(origin, shift, val) ((origin) |= ((val) << (shift))) +#define hns3_tx_bd_count(S) DIV_ROUND_UP(S, HNS3_MAX_BD_SIZE) static void hns3_clear_all_ring(struct hnae3_handle *h); static void hns3_force_clear_all_rx_ring(struct hnae3_handle *h); @@ -1079,7 +1080,7 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv, desc_cb->length = size; - frag_buf_num = (size + HNS3_MAX_BD_SIZE - 1) >> HNS3_MAX_BD_SIZE_OFFSET; + frag_buf_num = hns3_tx_bd_count(size); sizeoflast = size & HNS3_TX_LAST_SIZE_M; sizeoflast = sizeoflast ? sizeoflast : HNS3_MAX_BD_SIZE; @@ -1124,14 +1125,13 @@ static int hns3_nic_maybe_stop_tso(struct sk_buff **out_skb, int *bnum, int i; size = skb_headlen(skb); - buf_num = (size + HNS3_MAX_BD_SIZE - 1) >> HNS3_MAX_BD_SIZE_OFFSET; + buf_num = hns3_tx_bd_count(size); frag_num = skb_shinfo(skb)->nr_frags; for (i = 0; i < frag_num; i++) { frag = &skb_shinfo(skb)->frags[i]; size = skb_frag_size(frag); - bdnum_for_frag = (size + HNS3_MAX_BD_SIZE - 1) >> - HNS3_MAX_BD_SIZE_OFFSET; + bdnum_for_frag = hns3_tx_bd_count(size); if (unlikely(bdnum_for_frag > HNS3_MAX_BD_PER_FRAG)) return -ENOMEM; @@ -1139,8 +1139,7 @@ static int hns3_nic_maybe_stop_tso(struct sk_buff **out_skb, int *bnum, } if (unlikely(buf_num > HNS3_MAX_BD_PER_FRAG)) { - buf_num = (skb->len + HNS3_MAX_BD_SIZE - 1) >> - HNS3_MAX_BD_SIZE_OFFSET; + buf_num = hns3_tx_bd_count(skb->len); if (ring_space(ring) < buf_num) return -EBUSY; /* manual split the send packet */ @@ -1169,7 +1168,7 @@ static int hns3_nic_maybe_stop_tx(struct sk_buff **out_skb, int *bnum, buf_num = skb_shinfo(skb)->nr_frags + 1; if (unlikely(buf_num > HNS3_MAX_BD_PER_FRAG)) { - buf_num = (skb->len + HNS3_MAX_BD_SIZE - 1) / HNS3_MAX_BD_SIZE; + buf_num = hns3_tx_bd_count(skb->len); if (ring_space(ring) < buf_num) return -EBUSY; /* manual split the send packet */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index 1db0bd41d209..75669cd0c311 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -193,7 +193,6 @@ enum hns3_nic_state { #define HNS3_VECTOR_INITED 1 #define HNS3_MAX_BD_SIZE 65535 -#define HNS3_MAX_BD_SIZE_OFFSET 16 #define HNS3_MAX_BD_PER_FRAG 8 #define HNS3_MAX_BD_PER_PKT MAX_SKB_FRAGS diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile index fffe8c1c45d3..0fb61d440d3b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile @@ -3,7 +3,7 @@ # Makefile for the HISILICON network device drivers. # -ccflags-y := -Idrivers/net/ethernet/hisilicon/hns3 +ccflags-y := -I $(srctree)/drivers/net/ethernet/hisilicon/hns3 obj-$(CONFIG_HNS3_HCLGE) += hclge.o hclge-objs = hclge_main.o hclge_cmd.o hclge_mdio.o hclge_tm.o hclge_mbx.o hclge_err.o hclge_debugfs.o diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile b/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile index fb93bbd35845..6193f8fa7cf3 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile @@ -3,7 +3,7 @@ # Makefile for the HISILICON network device drivers. # -ccflags-y := -Idrivers/net/ethernet/hisilicon/hns3 +ccflags-y := -I $(srctree)/drivers/net/ethernet/hisilicon/hns3 obj-$(CONFIG_HNS3_HCLGEVF) += hclgevf.o hclgevf-objs = hclgevf_main.o hclgevf_cmd.o hclgevf_mbx.o
\ No newline at end of file diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c index baf5cc251f32..8b8a7d00e8e0 100644 --- a/drivers/net/ethernet/hisilicon/hns_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns_mdio.c @@ -39,7 +39,7 @@ struct hns_mdio_sc_reg { }; struct hns_mdio_device { - void *vbase; /* mdio reg base address */ + u8 __iomem *vbase; /* mdio reg base address */ struct regmap *subctrl_vbase; struct hns_mdio_sc_reg sc_reg; }; @@ -96,21 +96,17 @@ enum mdio_c45_op_seq { #define MDIO_SC_CLK_ST 0x531C #define MDIO_SC_RESET_ST 0x5A1C -static void mdio_write_reg(void *base, u32 reg, u32 value) +static void mdio_write_reg(u8 __iomem *base, u32 reg, u32 value) { - u8 __iomem *reg_addr = (u8 __iomem *)base; - - writel_relaxed(value, reg_addr + reg); + writel_relaxed(value, base + reg); } #define MDIO_WRITE_REG(a, reg, value) \ mdio_write_reg((a)->vbase, (reg), (value)) -static u32 mdio_read_reg(void *base, u32 reg) +static u32 mdio_read_reg(u8 __iomem *base, u32 reg) { - u8 __iomem *reg_addr = (u8 __iomem *)base; - - return readl_relaxed(reg_addr + reg); + return readl_relaxed(base + reg); } #define mdio_set_field(origin, mask, shift, val) \ @@ -121,7 +117,7 @@ static u32 mdio_read_reg(void *base, u32 reg) #define mdio_get_field(origin, mask, shift) (((origin) >> (shift)) & (mask)) -static void mdio_set_reg_field(void *base, u32 reg, u32 mask, u32 shift, +static void mdio_set_reg_field(u8 __iomem *base, u32 reg, u32 mask, u32 shift, u32 val) { u32 origin = mdio_read_reg(base, reg); @@ -133,7 +129,7 @@ static void mdio_set_reg_field(void *base, u32 reg, u32 mask, u32 shift, #define MDIO_SET_REG_FIELD(dev, reg, mask, shift, val) \ mdio_set_reg_field((dev)->vbase, (reg), (mask), (shift), (val)) -static u32 mdio_get_reg_field(void *base, u32 reg, u32 mask, u32 shift) +static u32 mdio_get_reg_field(u8 __iomem *base, u32 reg, u32 mask, u32 shift) { u32 origin; diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c index 3baabdc89726..90b62c1412c8 100644 --- a/drivers/net/ethernet/ibm/ehea/ehea_main.c +++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c @@ -3160,6 +3160,7 @@ static ssize_t ehea_probe_port(struct device *dev, if (ehea_add_adapter_mr(adapter)) { pr_err("creating MR failed\n"); + of_node_put(eth_dn); return -EIO; } diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 5ecbb1adcf3b..3dfb2d131eb7 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1885,6 +1885,7 @@ static int do_hard_reset(struct ibmvnic_adapter *adapter, */ adapter->state = VNIC_PROBED; + reinit_completion(&adapter->init_done); rc = init_crq_queue(adapter); if (rc) { netdev_err(adapter->netdev, @@ -3761,6 +3762,7 @@ static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter) { struct device *dev = &adapter->vdev->dev; struct ibmvnic_query_ip_offload_buffer *buf = &adapter->ip_offload_buf; + netdev_features_t old_hw_features = 0; union ibmvnic_crq crq; int i; @@ -3836,24 +3838,41 @@ static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter) adapter->ip_offload_ctrl.large_rx_ipv4 = 0; adapter->ip_offload_ctrl.large_rx_ipv6 = 0; - adapter->netdev->features = NETIF_F_SG | NETIF_F_GSO; + if (adapter->state != VNIC_PROBING) { + old_hw_features = adapter->netdev->hw_features; + adapter->netdev->hw_features = 0; + } + + adapter->netdev->hw_features = NETIF_F_SG | NETIF_F_GSO | NETIF_F_GRO; if (buf->tcp_ipv4_chksum || buf->udp_ipv4_chksum) - adapter->netdev->features |= NETIF_F_IP_CSUM; + adapter->netdev->hw_features |= NETIF_F_IP_CSUM; if (buf->tcp_ipv6_chksum || buf->udp_ipv6_chksum) - adapter->netdev->features |= NETIF_F_IPV6_CSUM; + adapter->netdev->hw_features |= NETIF_F_IPV6_CSUM; if ((adapter->netdev->features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM))) - adapter->netdev->features |= NETIF_F_RXCSUM; + adapter->netdev->hw_features |= NETIF_F_RXCSUM; if (buf->large_tx_ipv4) - adapter->netdev->features |= NETIF_F_TSO; + adapter->netdev->hw_features |= NETIF_F_TSO; if (buf->large_tx_ipv6) - adapter->netdev->features |= NETIF_F_TSO6; + adapter->netdev->hw_features |= NETIF_F_TSO6; + + if (adapter->state == VNIC_PROBING) { + adapter->netdev->features |= adapter->netdev->hw_features; + } else if (old_hw_features != adapter->netdev->hw_features) { + netdev_features_t tmp = 0; - adapter->netdev->hw_features |= adapter->netdev->features; + /* disable features no longer supported */ + adapter->netdev->features &= adapter->netdev->hw_features; + /* turn on features now supported if previously enabled */ + tmp = (old_hw_features ^ adapter->netdev->hw_features) & + adapter->netdev->hw_features; + adapter->netdev->features |= + tmp & adapter->netdev->wanted_features; + } memset(&crq, 0, sizeof(crq)); crq.control_ip_offload.first = IBMVNIC_CRQ_CMD; @@ -4625,7 +4644,7 @@ static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter) old_num_rx_queues = adapter->req_rx_queues; old_num_tx_queues = adapter->req_tx_queues; - init_completion(&adapter->init_done); + reinit_completion(&adapter->init_done); adapter->init_done_rc = 0; ibmvnic_send_crq_init(adapter); if (!wait_for_completion_timeout(&adapter->init_done, timeout)) { @@ -4680,7 +4699,6 @@ static int ibmvnic_init(struct ibmvnic_adapter *adapter) adapter->from_passive_init = false; - init_completion(&adapter->init_done); adapter->init_done_rc = 0; ibmvnic_send_crq_init(adapter); if (!wait_for_completion_timeout(&adapter->init_done, timeout)) { @@ -4759,6 +4777,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) INIT_WORK(&adapter->ibmvnic_reset, __ibmvnic_reset); INIT_LIST_HEAD(&adapter->rwi_list); spin_lock_init(&adapter->rwi_lock); + init_completion(&adapter->init_done); adapter->resetting = false; adapter->mac_change_pending = false; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 5a0419421511..ecef949f3baa 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -41,6 +41,8 @@ static int __init fm10k_init_module(void) /* create driver workqueue */ fm10k_workqueue = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0, fm10k_driver_name); + if (!fm10k_workqueue) + return -ENOMEM; fm10k_dbg_init(); diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index d684998ba2b0..d3cc3427caad 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -790,6 +790,8 @@ struct i40e_vsi { /* VSI specific handlers */ irqreturn_t (*irq_handler)(int irq, void *data); + + unsigned long *af_xdp_zc_qps; /* tracks AF_XDP ZC enabled qps */ } ____cacheline_internodealigned_in_smp; struct i40e_netdev_priv { @@ -1096,20 +1098,6 @@ static inline bool i40e_enabled_xdp_vsi(struct i40e_vsi *vsi) return !!vsi->xdp_prog; } -static inline struct xdp_umem *i40e_xsk_umem(struct i40e_ring *ring) -{ - bool xdp_on = i40e_enabled_xdp_vsi(ring->vsi); - int qid = ring->queue_index; - - if (ring_is_xdp(ring)) - qid -= ring->vsi->alloc_queue_pairs; - - if (!xdp_on) - return NULL; - - return xdp_get_umem_from_qid(ring->vsi->netdev, qid); -} - int i40e_create_queue_channel(struct i40e_vsi *vsi, struct i40e_channel *ch); int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate); int i40e_add_del_cloud_filter(struct i40e_vsi *vsi, diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 4c885801fa26..7874d0ec7fb0 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -2573,8 +2573,7 @@ static int i40e_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) return -EOPNOTSUPP; /* only magic packet is supported */ - if (wol->wolopts && (wol->wolopts != WAKE_MAGIC) - | (wol->wolopts != WAKE_FILTER)) + if (wol->wolopts & ~WAKE_MAGIC) return -EOPNOTSUPP; /* is this a new value? */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index da62218eb70a..b1c265012c8a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -3064,6 +3064,26 @@ static void i40e_config_xps_tx_ring(struct i40e_ring *ring) } /** + * i40e_xsk_umem - Retrieve the AF_XDP ZC if XDP and ZC is enabled + * @ring: The Tx or Rx ring + * + * Returns the UMEM or NULL. + **/ +static struct xdp_umem *i40e_xsk_umem(struct i40e_ring *ring) +{ + bool xdp_on = i40e_enabled_xdp_vsi(ring->vsi); + int qid = ring->queue_index; + + if (ring_is_xdp(ring)) + qid -= ring->vsi->alloc_queue_pairs; + + if (!xdp_on || !test_bit(qid, ring->vsi->af_xdp_zc_qps)) + return NULL; + + return xdp_get_umem_from_qid(ring->vsi->netdev, qid); +} + +/** * i40e_configure_tx_ring - Configure a transmit ring context and rest * @ring: The Tx ring to configure * @@ -10064,6 +10084,12 @@ static int i40e_vsi_mem_alloc(struct i40e_pf *pf, enum i40e_vsi_type type) hash_init(vsi->mac_filter_hash); vsi->irqs_ready = false; + if (type == I40E_VSI_MAIN) { + vsi->af_xdp_zc_qps = bitmap_zalloc(pf->num_lan_qps, GFP_KERNEL); + if (!vsi->af_xdp_zc_qps) + goto err_rings; + } + ret = i40e_set_num_rings_in_vsi(vsi); if (ret) goto err_rings; @@ -10082,6 +10108,7 @@ static int i40e_vsi_mem_alloc(struct i40e_pf *pf, enum i40e_vsi_type type) goto unlock_pf; err_rings: + bitmap_free(vsi->af_xdp_zc_qps); pf->next_vsi = i - 1; kfree(vsi); unlock_pf: @@ -10162,6 +10189,7 @@ static int i40e_vsi_clear(struct i40e_vsi *vsi) i40e_put_lump(pf->qp_pile, vsi->base_queue, vsi->idx); i40e_put_lump(pf->irq_pile, vsi->base_vector, vsi->idx); + bitmap_free(vsi->af_xdp_zc_qps); i40e_vsi_free_arrays(vsi, true); i40e_clear_rss_config_user(vsi); diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index 5fb4353c742b..31575c0bb884 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -146,12 +146,13 @@ static int i40e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) static int i40e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) { struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps); - struct timespec64 now; + struct timespec64 now, then; + then = ns_to_timespec64(delta); mutex_lock(&pf->tmreg_lock); i40e_ptp_read(pf, &now, NULL); - timespec64_add_ns(&now, delta); + now = timespec64_add(now, then); i40e_ptp_write(pf, (const struct timespec64 *)&now); mutex_unlock(&pf->tmreg_lock); diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index b5c182e688e3..1b17486543ac 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -102,6 +102,8 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem, if (err) return err; + set_bit(qid, vsi->af_xdp_zc_qps); + if_running = netif_running(vsi->netdev) && i40e_enabled_xdp_vsi(vsi); if (if_running) { @@ -148,6 +150,7 @@ static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid) return err; } + clear_bit(qid, vsi->af_xdp_zc_qps); i40e_xsk_umem_dma_unmap(vsi, umem); if (if_running) { diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h index 01fcfc6f3415..d2e2c50ce257 100644 --- a/drivers/net/ethernet/intel/igb/e1000_defines.h +++ b/drivers/net/ethernet/intel/igb/e1000_defines.h @@ -194,6 +194,8 @@ /* enable link status from external LINK_0 and LINK_1 pins */ #define E1000_CTRL_SWDPIN0 0x00040000 /* SWDPIN 0 value */ #define E1000_CTRL_SWDPIN1 0x00080000 /* SWDPIN 1 value */ +#define E1000_CTRL_ADVD3WUC 0x00100000 /* D3 WUC */ +#define E1000_CTRL_EN_PHY_PWR_MGMT 0x00200000 /* PHY PM enable */ #define E1000_CTRL_SDP0_DIR 0x00400000 /* SDP0 Data direction */ #define E1000_CTRL_SDP1_DIR 0x00800000 /* SDP1 Data direction */ #define E1000_CTRL_RST 0x04000000 /* Global reset */ diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 69b230c53fed..3269d8e94744 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -8740,9 +8740,7 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake, struct e1000_hw *hw = &adapter->hw; u32 ctrl, rctl, status; u32 wufc = runtime ? E1000_WUFC_LNKC : adapter->wol; -#ifdef CONFIG_PM - int retval = 0; -#endif + bool wake; rtnl_lock(); netif_device_detach(netdev); @@ -8755,14 +8753,6 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake, igb_clear_interrupt_scheme(adapter); rtnl_unlock(); -#ifdef CONFIG_PM - if (!runtime) { - retval = pci_save_state(pdev); - if (retval) - return retval; - } -#endif - status = rd32(E1000_STATUS); if (status & E1000_STATUS_LU) wufc &= ~E1000_WUFC_LNKC; @@ -8779,10 +8769,6 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake, } ctrl = rd32(E1000_CTRL); - /* advertise wake from D3Cold */ - #define E1000_CTRL_ADVD3WUC 0x00100000 - /* phy power management enable */ - #define E1000_CTRL_EN_PHY_PWR_MGMT 0x00200000 ctrl |= E1000_CTRL_ADVD3WUC; wr32(E1000_CTRL, ctrl); @@ -8796,12 +8782,15 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake, wr32(E1000_WUFC, 0); } - *enable_wake = wufc || adapter->en_mng_pt; - if (!*enable_wake) + wake = wufc || adapter->en_mng_pt; + if (!wake) igb_power_down_link(adapter); else igb_power_up_link(adapter); + if (enable_wake) + *enable_wake = wake; + /* Release control of h/w to f/w. If f/w is AMT enabled, this * would have already happened in close and is redundant. */ @@ -8844,22 +8833,7 @@ static void igb_deliver_wake_packet(struct net_device *netdev) static int __maybe_unused igb_suspend(struct device *dev) { - int retval; - bool wake; - struct pci_dev *pdev = to_pci_dev(dev); - - retval = __igb_shutdown(pdev, &wake, 0); - if (retval) - return retval; - - if (wake) { - pci_prepare_to_sleep(pdev); - } else { - pci_wake_from_d3(pdev, false); - pci_set_power_state(pdev, PCI_D3hot); - } - - return 0; + return __igb_shutdown(to_pci_dev(dev), NULL, 0); } static int __maybe_unused igb_resume(struct device *dev) @@ -8930,22 +8904,7 @@ static int __maybe_unused igb_runtime_idle(struct device *dev) static int __maybe_unused igb_runtime_suspend(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - int retval; - bool wake; - - retval = __igb_shutdown(pdev, &wake, 1); - if (retval) - return retval; - - if (wake) { - pci_prepare_to_sleep(pdev); - } else { - pci_wake_from_d3(pdev, false); - pci_set_power_state(pdev, PCI_D3hot); - } - - return 0; + return __igb_shutdown(to_pci_dev(dev), NULL, 1); } static int __maybe_unused igb_runtime_resume(struct device *dev) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c index cc4907f9ff02..2fb97967961c 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c @@ -905,13 +905,12 @@ s32 ixgbe_mii_bus_init(struct ixgbe_hw *hw) struct pci_dev *pdev = adapter->pdev; struct device *dev = &adapter->netdev->dev; struct mii_bus *bus; + int err = -ENODEV; - adapter->mii_bus = devm_mdiobus_alloc(dev); - if (!adapter->mii_bus) + bus = devm_mdiobus_alloc(dev); + if (!bus) return -ENOMEM; - bus = adapter->mii_bus; - switch (hw->device_id) { /* C3000 SoCs */ case IXGBE_DEV_ID_X550EM_A_KR: @@ -949,12 +948,15 @@ s32 ixgbe_mii_bus_init(struct ixgbe_hw *hw) */ hw->phy.mdio.mode_support = MDIO_SUPPORTS_C45 | MDIO_SUPPORTS_C22; - return mdiobus_register(bus); + err = mdiobus_register(bus); + if (!err) { + adapter->mii_bus = bus; + return 0; + } ixgbe_no_mii_bus: devm_mdiobus_free(dev, bus); - adapter->mii_bus = NULL; - return -ENODEV; + return err; } /** diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 71c65cc17904..d3eaf2ceaa39 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -858,6 +858,7 @@ void mlx5e_close_channels(struct mlx5e_channels *chs); * switching channels */ typedef int (*mlx5e_fp_hw_modify)(struct mlx5e_priv *priv); +int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv); int mlx5e_safe_switch_channels(struct mlx5e_priv *priv, struct mlx5e_channels *new_chs, mlx5e_fp_hw_modify hw_modify); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c index 122927f3a600..d5e5afbdca6d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c @@ -96,9 +96,6 @@ int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext, if (!eproto) return -EINVAL; - if (ext != MLX5_CAP_PCAM_FEATURE(dev, ptys_extended_ethernet)) - return -EOPNOTSUPP; - err = mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_EN, port); if (err) return err; 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 eac245a93f91..4ab0d030b544 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c @@ -122,7 +122,9 @@ out: return err; } -/* xoff = ((301+2.16 * len [m]) * speed [Gbps] + 2.72 MTU [B]) */ +/* xoff = ((301+2.16 * len [m]) * speed [Gbps] + 2.72 MTU [B]) + * minimum speed value is 40Gbps + */ static u32 calculate_xoff(struct mlx5e_priv *priv, unsigned int mtu) { u32 speed; @@ -130,10 +132,9 @@ static u32 calculate_xoff(struct mlx5e_priv *priv, unsigned int mtu) int err; err = mlx5e_port_linkspeed(priv->mdev, &speed); - if (err) { - mlx5_core_warn(priv->mdev, "cannot get port speed\n"); - return 0; - } + if (err) + speed = SPEED_40000; + speed = max_t(u32, speed, SPEED_40000); xoff = (301 + 216 * priv->dcbx.cable_len / 100) * speed / 1000 + 272 * mtu / 100; @@ -142,7 +143,7 @@ static u32 calculate_xoff(struct mlx5e_priv *priv, unsigned int mtu) } static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer, - u32 xoff, unsigned int mtu) + u32 xoff, unsigned int max_mtu) { int i; @@ -154,11 +155,12 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer, } if (port_buffer->buffer[i].size < - (xoff + mtu + (1 << MLX5E_BUFFER_CELL_SHIFT))) + (xoff + max_mtu + (1 << MLX5E_BUFFER_CELL_SHIFT))) return -ENOMEM; port_buffer->buffer[i].xoff = port_buffer->buffer[i].size - xoff; - port_buffer->buffer[i].xon = port_buffer->buffer[i].xoff - mtu; + port_buffer->buffer[i].xon = + port_buffer->buffer[i].xoff - max_mtu; } return 0; @@ -166,7 +168,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer, /** * update_buffer_lossy() - * mtu: device's MTU + * max_mtu: netdev's max_mtu * pfc_en: <input> current pfc configuration * buffer: <input> current prio to buffer mapping * xoff: <input> xoff value @@ -183,7 +185,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer, * Return 0 if no error. * Set change to true if buffer configuration is modified. */ -static int update_buffer_lossy(unsigned int mtu, +static int update_buffer_lossy(unsigned int max_mtu, u8 pfc_en, u8 *buffer, u32 xoff, struct mlx5e_port_buffer *port_buffer, bool *change) @@ -220,7 +222,7 @@ static int update_buffer_lossy(unsigned int mtu, } if (changed) { - err = update_xoff_threshold(port_buffer, xoff, mtu); + err = update_xoff_threshold(port_buffer, xoff, max_mtu); if (err) return err; @@ -230,6 +232,7 @@ static int update_buffer_lossy(unsigned int mtu, return 0; } +#define MINIMUM_MAX_MTU 9216 int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, u32 change, unsigned int mtu, struct ieee_pfc *pfc, @@ -241,12 +244,14 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, bool update_prio2buffer = false; u8 buffer[MLX5E_MAX_PRIORITY]; bool update_buffer = false; + unsigned int max_mtu; u32 total_used = 0; u8 curr_pfc_en; int err; int i; mlx5e_dbg(HW, priv, "%s: change=%x\n", __func__, change); + max_mtu = max_t(unsigned int, priv->netdev->max_mtu, MINIMUM_MAX_MTU); err = mlx5e_port_query_buffer(priv, &port_buffer); if (err) @@ -254,7 +259,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, if (change & MLX5E_PORT_BUFFER_CABLE_LEN) { update_buffer = true; - err = update_xoff_threshold(&port_buffer, xoff, mtu); + err = update_xoff_threshold(&port_buffer, xoff, max_mtu); if (err) return err; } @@ -264,7 +269,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, if (err) return err; - err = update_buffer_lossy(mtu, pfc->pfc_en, buffer, xoff, + err = update_buffer_lossy(max_mtu, pfc->pfc_en, buffer, xoff, &port_buffer, &update_buffer); if (err) return err; @@ -276,8 +281,8 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, if (err) return err; - err = update_buffer_lossy(mtu, curr_pfc_en, prio2buffer, xoff, - &port_buffer, &update_buffer); + err = update_buffer_lossy(max_mtu, curr_pfc_en, prio2buffer, + xoff, &port_buffer, &update_buffer); if (err) return err; } @@ -301,7 +306,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, return -EINVAL; update_buffer = true; - err = update_xoff_threshold(&port_buffer, xoff, mtu); + err = update_xoff_threshold(&port_buffer, xoff, max_mtu); if (err) return err; } @@ -309,7 +314,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, /* Need to update buffer configuration if xoff value is changed */ if (!update_buffer && xoff != priv->dcbx.xoff) { update_buffer = true; - err = update_xoff_threshold(&port_buffer, xoff, mtu); + err = update_xoff_threshold(&port_buffer, xoff, max_mtu); if (err) return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index 9d38e62cdf24..476dd97f7f2f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -186,12 +186,17 @@ static int mlx5e_tx_reporter_recover_from_ctx(struct mlx5e_tx_err_ctx *err_ctx) static int mlx5e_tx_reporter_recover_all(struct mlx5e_priv *priv) { - int err; + int err = 0; rtnl_lock(); mutex_lock(&priv->state_lock); - mlx5e_close_locked(priv->netdev); - err = mlx5e_open_locked(priv->netdev); + + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) + goto out; + + err = mlx5e_safe_reopen_channels(priv); + +out: mutex_unlock(&priv->state_lock); rtnl_unlock(); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index fa2a3c444cdc..eec07b34b4ad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -39,6 +39,10 @@ static int get_route_and_out_devs(struct mlx5e_priv *priv, return -EOPNOTSUPP; } + if (!(mlx5e_eswitch_rep(*out_dev) && + mlx5e_is_uplink_rep(netdev_priv(*out_dev)))) + return -EOPNOTSUPP; + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 03b2a9f9c589..cad34d6f5f45 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -33,6 +33,26 @@ #include <linux/bpf_trace.h> #include "en/xdp.h" +int mlx5e_xdp_max_mtu(struct mlx5e_params *params) +{ + int hr = NET_IP_ALIGN + XDP_PACKET_HEADROOM; + + /* Let S := SKB_DATA_ALIGN(sizeof(struct skb_shared_info)). + * The condition checked in mlx5e_rx_is_linear_skb is: + * SKB_DATA_ALIGN(sw_mtu + hard_mtu + hr) + S <= PAGE_SIZE (1) + * (Note that hw_mtu == sw_mtu + hard_mtu.) + * What is returned from this function is: + * max_mtu = PAGE_SIZE - S - hr - hard_mtu (2) + * After assigning sw_mtu := max_mtu, the left side of (1) turns to + * SKB_DATA_ALIGN(PAGE_SIZE - S) + S, which is equal to PAGE_SIZE, + * because both PAGE_SIZE and S are already aligned. Any number greater + * than max_mtu would make the left side of (1) greater than PAGE_SIZE, + * so max_mtu is the maximum MTU allowed. + */ + + return MLX5E_HW2SW_MTU(params, SKB_MAX_HEAD(hr)); +} + static inline bool mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_dma_info *di, struct xdp_buff *xdp) @@ -304,9 +324,9 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq) mlx5e_xdpi_fifo_pop(xdpi_fifo); if (is_redirect) { - xdp_return_frame(xdpi.xdpf); dma_unmap_single(sq->pdev, xdpi.dma_addr, xdpi.xdpf->len, DMA_TO_DEVICE); + xdp_return_frame(xdpi.xdpf); } else { /* Recycle RX page */ mlx5e_page_release(rq, &xdpi.di, true); @@ -345,9 +365,9 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq) mlx5e_xdpi_fifo_pop(xdpi_fifo); if (is_redirect) { - xdp_return_frame(xdpi.xdpf); dma_unmap_single(sq->pdev, xdpi.dma_addr, xdpi.xdpf->len, DMA_TO_DEVICE); + xdp_return_frame(xdpi.xdpf); } else { /* Recycle RX page */ mlx5e_page_release(rq, &xdpi.di, false); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h index ee27a7c8cd87..553956cadc8a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h @@ -34,13 +34,12 @@ #include "en.h" -#define MLX5E_XDP_MAX_MTU ((int)(PAGE_SIZE - \ - MLX5_SKB_FRAG_SZ(XDP_PACKET_HEADROOM))) #define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN) #define MLX5E_XDP_TX_EMPTY_DS_COUNT \ (sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS) #define MLX5E_XDP_TX_DS_COUNT (MLX5E_XDP_TX_EMPTY_DS_COUNT + 1 /* SG DS */) +int mlx5e_xdp_max_mtu(struct mlx5e_params *params); bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, void *va, u16 *rx_headroom, u32 *len); bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index 3078491cc0d0..1539cf3de5dc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -45,7 +45,9 @@ int mlx5e_create_tir(struct mlx5_core_dev *mdev, if (err) return err; + mutex_lock(&mdev->mlx5e_res.td.list_lock); list_add(&tir->list, &mdev->mlx5e_res.td.tirs_list); + mutex_unlock(&mdev->mlx5e_res.td.list_lock); return 0; } @@ -53,8 +55,10 @@ int mlx5e_create_tir(struct mlx5_core_dev *mdev, void mlx5e_destroy_tir(struct mlx5_core_dev *mdev, struct mlx5e_tir *tir) { + mutex_lock(&mdev->mlx5e_res.td.list_lock); mlx5_core_destroy_tir(mdev, tir->tirn); list_del(&tir->list); + mutex_unlock(&mdev->mlx5e_res.td.list_lock); } static int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, @@ -114,6 +118,7 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev) } INIT_LIST_HEAD(&mdev->mlx5e_res.td.tirs_list); + mutex_init(&mdev->mlx5e_res.td.list_lock); return 0; @@ -141,15 +146,17 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb) { struct mlx5_core_dev *mdev = priv->mdev; struct mlx5e_tir *tir; - int err = -ENOMEM; + int err = 0; u32 tirn = 0; int inlen; void *in; inlen = MLX5_ST_SZ_BYTES(modify_tir_in); in = kvzalloc(inlen, GFP_KERNEL); - if (!in) + if (!in) { + err = -ENOMEM; goto out; + } if (enable_uc_lb) MLX5_SET(modify_tir_in, in, ctx.self_lb_block, @@ -157,6 +164,7 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb) MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1); + mutex_lock(&mdev->mlx5e_res.td.list_lock); list_for_each_entry(tir, &mdev->mlx5e_res.td.tirs_list, list) { tirn = tir->tirn; err = mlx5_core_modify_tir(mdev, tirn, in, inlen); @@ -168,6 +176,7 @@ out: kvfree(in); if (err) netdev_err(priv->netdev, "refresh tir(0x%x) failed, %d\n", tirn, err); + mutex_unlock(&mdev->mlx5e_res.td.list_lock); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index a0987cc5fe4a..78dc8fe2a83c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -603,16 +603,18 @@ static void ptys2ethtool_supported_link(struct mlx5_core_dev *mdev, __ETHTOOL_LINK_MODE_MASK_NBITS); } -static void ptys2ethtool_adver_link(struct mlx5_core_dev *mdev, - unsigned long *advertising_modes, - u32 eth_proto_cap) +static void ptys2ethtool_adver_link(unsigned long *advertising_modes, + u32 eth_proto_cap, bool ext) { unsigned long proto_cap = eth_proto_cap; struct ptys2ethtool_config *table; u32 max_size; int proto; - mlx5e_ethtool_get_speed_arr(mdev, &table, &max_size); + table = ext ? ptys2ext_ethtool_table : ptys2legacy_ethtool_table; + max_size = ext ? ARRAY_SIZE(ptys2ext_ethtool_table) : + ARRAY_SIZE(ptys2legacy_ethtool_table); + for_each_set_bit(proto, &proto_cap, max_size) bitmap_or(advertising_modes, advertising_modes, table[proto].advertised, @@ -794,12 +796,12 @@ static void get_supported(struct mlx5_core_dev *mdev, u32 eth_proto_cap, ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Pause); } -static void get_advertising(struct mlx5_core_dev *mdev, u32 eth_proto_cap, - u8 tx_pause, u8 rx_pause, - struct ethtool_link_ksettings *link_ksettings) +static void get_advertising(u32 eth_proto_cap, u8 tx_pause, u8 rx_pause, + struct ethtool_link_ksettings *link_ksettings, + bool ext) { unsigned long *advertising = link_ksettings->link_modes.advertising; - ptys2ethtool_adver_link(mdev, advertising, eth_proto_cap); + ptys2ethtool_adver_link(advertising, eth_proto_cap, ext); if (rx_pause) ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Pause); @@ -854,8 +856,9 @@ static void get_lp_advertising(struct mlx5_core_dev *mdev, u32 eth_proto_lp, struct ethtool_link_ksettings *link_ksettings) { unsigned long *lp_advertising = link_ksettings->link_modes.lp_advertising; + bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); - ptys2ethtool_adver_link(mdev, lp_advertising, eth_proto_lp); + ptys2ethtool_adver_link(lp_advertising, eth_proto_lp, ext); } int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv, @@ -872,6 +875,7 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv, u8 an_disable_admin; u8 an_status; u8 connector_type; + bool admin_ext; bool ext; int err; @@ -886,6 +890,19 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv, eth_proto_capability); eth_proto_admin = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, eth_proto_admin); + /* Fields: eth_proto_admin and ext_eth_proto_admin are + * mutually exclusive. Hence try reading legacy advertising + * when extended advertising is zero. + * admin_ext indicates how eth_proto_admin should be + * interpreted + */ + admin_ext = ext; + if (ext && !eth_proto_admin) { + eth_proto_admin = MLX5_GET_ETH_PROTO(ptys_reg, out, false, + eth_proto_admin); + admin_ext = false; + } + eth_proto_oper = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, eth_proto_oper); eth_proto_lp = MLX5_GET(ptys_reg, out, eth_proto_lp_advertise); @@ -899,7 +916,8 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv, ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising); get_supported(mdev, eth_proto_cap, link_ksettings); - get_advertising(mdev, eth_proto_admin, tx_pause, rx_pause, link_ksettings); + get_advertising(eth_proto_admin, tx_pause, rx_pause, link_ksettings, + admin_ext); get_speed_duplex(priv->netdev, eth_proto_oper, link_ksettings); eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap; @@ -997,19 +1015,17 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, #define MLX5E_PTYS_EXT ((1ULL << ETHTOOL_LINK_MODE_50000baseKR_Full_BIT) - 1) - ext_requested = (link_ksettings->link_modes.advertising[0] > - MLX5E_PTYS_EXT); + ext_requested = !!(link_ksettings->link_modes.advertising[0] > + MLX5E_PTYS_EXT || + link_ksettings->link_modes.advertising[1]); ext_supported = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); - - /*when ptys_extended_ethernet is set legacy link modes are deprecated */ - if (ext_requested != ext_supported) - return -EPROTONOSUPPORT; + ext_requested &= ext_supported; speed = link_ksettings->base.speed; ethtool2ptys_adver_func = ext_requested ? mlx5e_ethtool2ptys_ext_adver_link : mlx5e_ethtool2ptys_adver_link; - err = mlx5_port_query_eth_proto(mdev, 1, ext_supported, &eproto); + err = mlx5_port_query_eth_proto(mdev, 1, ext_requested, &eproto); if (err) { netdev_err(priv->netdev, "%s: query port eth proto failed: %d\n", __func__, err); @@ -1037,7 +1053,7 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, if (!an_changes && link_modes == eproto.admin) goto out; - mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext_supported); + mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext_requested); mlx5_toggle_port_link(mdev); out: @@ -1570,7 +1586,7 @@ static int mlx5e_get_module_info(struct net_device *netdev, break; case MLX5_MODULE_ID_SFP: modinfo->type = ETH_MODULE_SFF_8472; - modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; + modinfo->eeprom_len = MLX5_EEPROM_PAGE_LENGTH; break; default: netdev_err(priv->netdev, "%s: cable type not recognized:0x%x\n", @@ -1752,7 +1768,8 @@ static int set_pflag_rx_no_csum_complete(struct net_device *netdev, bool enable) struct mlx5e_channel *c; int i; - if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) + if (!test_bit(MLX5E_STATE_OPENED, &priv->state) || + priv->channels.params.xdp_prog) return 0; for (i = 0; i < channels->num; i++) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index b5fdbd3190d9..46157e2a1e5a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -951,7 +951,11 @@ static int mlx5e_open_rq(struct mlx5e_channel *c, if (params->rx_dim_enabled) __set_bit(MLX5E_RQ_STATE_AM, &c->rq.state); - if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE)) + /* We disable csum_complete when XDP is enabled since + * XDP programs might manipulate packets which will render + * skb->checksum incorrect. + */ + if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE) || c->xdp) __set_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &c->rq.state); return 0; @@ -2937,6 +2941,14 @@ int mlx5e_safe_switch_channels(struct mlx5e_priv *priv, return 0; } +int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv) +{ + struct mlx5e_channels new_channels = {}; + + new_channels.params = priv->channels.params; + return mlx5e_safe_switch_channels(priv, &new_channels, NULL); +} + void mlx5e_timestamp_init(struct mlx5e_priv *priv) { priv->tstamp.tx_type = HWTSTAMP_TX_OFF; @@ -3765,7 +3777,7 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu, if (params->xdp_prog && !mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) { netdev_err(netdev, "MTU(%d) > %d is not allowed while XDP enabled\n", - new_mtu, MLX5E_XDP_MAX_MTU); + new_mtu, mlx5e_xdp_max_mtu(params)); err = -EINVAL; goto out; } @@ -4161,11 +4173,10 @@ static void mlx5e_tx_timeout_work(struct work_struct *work) if (!report_failed) goto unlock; - mlx5e_close_locked(priv->netdev); - err = mlx5e_open_locked(priv->netdev); + err = mlx5e_safe_reopen_channels(priv); if (err) netdev_err(priv->netdev, - "mlx5e_open_locked failed recovering from a tx_timeout, err(%d).\n", + "mlx5e_safe_reopen_channels failed recovering from a tx_timeout, err(%d).\n", err); unlock: @@ -4201,7 +4212,8 @@ static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog) if (!mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) { netdev_warn(netdev, "XDP is not allowed with MTU(%d) > %d\n", - new_channels.params.sw_mtu, MLX5E_XDP_MAX_MTU); + new_channels.params.sw_mtu, + mlx5e_xdp_max_mtu(&new_channels.params)); return -EINVAL; } @@ -4553,7 +4565,7 @@ void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params, { enum mlx5e_traffic_types tt; - rss_params->hfunc = ETH_RSS_HASH_XOR; + rss_params->hfunc = ETH_RSS_HASH_TOP; netdev_rss_key_fill(rss_params->toeplitz_hash_key, sizeof(rss_params->toeplitz_hash_key)); mlx5e_build_default_indir_rqt(rss_params->indirection_rqt, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 3dde5c7e0739..c3b3002ff62f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -692,7 +692,14 @@ static inline bool is_last_ethertype_ip(struct sk_buff *skb, int *network_depth, { *proto = ((struct ethhdr *)skb->data)->h_proto; *proto = __vlan_get_protocol(skb, *proto, network_depth); - return (*proto == htons(ETH_P_IP) || *proto == htons(ETH_P_IPV6)); + + if (*proto == htons(ETH_P_IP)) + return pskb_may_pull(skb, *network_depth + sizeof(struct iphdr)); + + if (*proto == htons(ETH_P_IPV6)) + return pskb_may_pull(skb, *network_depth + sizeof(struct ipv6hdr)); + + return false; } static inline void mlx5e_enable_ecn(struct mlx5e_rq *rq, struct sk_buff *skb) @@ -712,17 +719,6 @@ static inline void mlx5e_enable_ecn(struct mlx5e_rq *rq, struct sk_buff *skb) rq->stats->ecn_mark += !!rc; } -static u32 mlx5e_get_fcs(const struct sk_buff *skb) -{ - const void *fcs_bytes; - u32 _fcs_bytes; - - fcs_bytes = skb_header_pointer(skb, skb->len - ETH_FCS_LEN, - ETH_FCS_LEN, &_fcs_bytes); - - return __get_unaligned_cpu32(fcs_bytes); -} - static u8 get_ip_proto(struct sk_buff *skb, int network_depth, __be16 proto) { void *ip_p = skb->data + network_depth; @@ -733,6 +729,68 @@ static u8 get_ip_proto(struct sk_buff *skb, int network_depth, __be16 proto) #define short_frame(size) ((size) <= ETH_ZLEN + ETH_FCS_LEN) +#define MAX_PADDING 8 + +static void +tail_padding_csum_slow(struct sk_buff *skb, int offset, int len, + struct mlx5e_rq_stats *stats) +{ + stats->csum_complete_tail_slow++; + skb->csum = csum_block_add(skb->csum, + skb_checksum(skb, offset, len, 0), + offset); +} + +static void +tail_padding_csum(struct sk_buff *skb, int offset, + struct mlx5e_rq_stats *stats) +{ + u8 tail_padding[MAX_PADDING]; + int len = skb->len - offset; + void *tail; + + if (unlikely(len > MAX_PADDING)) { + tail_padding_csum_slow(skb, offset, len, stats); + return; + } + + tail = skb_header_pointer(skb, offset, len, tail_padding); + if (unlikely(!tail)) { + tail_padding_csum_slow(skb, offset, len, stats); + return; + } + + stats->csum_complete_tail++; + skb->csum = csum_block_add(skb->csum, csum_partial(tail, len, 0), offset); +} + +static void +mlx5e_skb_padding_csum(struct sk_buff *skb, int network_depth, __be16 proto, + struct mlx5e_rq_stats *stats) +{ + struct ipv6hdr *ip6; + struct iphdr *ip4; + int pkt_len; + + switch (proto) { + case htons(ETH_P_IP): + ip4 = (struct iphdr *)(skb->data + network_depth); + pkt_len = network_depth + ntohs(ip4->tot_len); + break; + case htons(ETH_P_IPV6): + ip6 = (struct ipv6hdr *)(skb->data + network_depth); + pkt_len = network_depth + sizeof(*ip6) + ntohs(ip6->payload_len); + break; + default: + return; + } + + if (likely(pkt_len >= skb->len)) + return; + + tail_padding_csum(skb, pkt_len, stats); +} + static inline void mlx5e_handle_csum(struct net_device *netdev, struct mlx5_cqe64 *cqe, struct mlx5e_rq *rq, @@ -752,7 +810,8 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, return; } - if (unlikely(test_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &rq->state))) + /* True when explicitly set via priv flag, or XDP prog is loaded */ + if (test_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &rq->state)) goto csum_unnecessary; /* CQE csum doesn't cover padding octets in short ethernet @@ -780,18 +839,15 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, skb->csum = csum_partial(skb->data + ETH_HLEN, network_depth - ETH_HLEN, skb->csum); - if (unlikely(netdev->features & NETIF_F_RXFCS)) - skb->csum = csum_block_add(skb->csum, - (__force __wsum)mlx5e_get_fcs(skb), - skb->len - ETH_FCS_LEN); + + mlx5e_skb_padding_csum(skb, network_depth, proto, stats); stats->csum_complete++; return; } csum_unnecessary: if (likely((cqe->hds_ip_ext & CQE_L3_OK) && - ((cqe->hds_ip_ext & CQE_L4_OK) || - (get_cqe_l4_hdr_type(cqe) == CQE_L4_HDR_TYPE_NONE)))) { + (cqe->hds_ip_ext & CQE_L4_OK))) { skb->ip_summed = CHECKSUM_UNNECESSARY; if (cqe_is_tunneled(cqe)) { skb->csum_level = 1; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 1a78e05cbba8..b75aa8b8bf04 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -59,6 +59,8 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_none) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete_tail) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete_tail_slow) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary_inner) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_drop) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_redirect) }, @@ -151,6 +153,8 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->rx_removed_vlan_packets += rq_stats->removed_vlan_packets; s->rx_csum_none += rq_stats->csum_none; s->rx_csum_complete += rq_stats->csum_complete; + s->rx_csum_complete_tail += rq_stats->csum_complete_tail; + s->rx_csum_complete_tail_slow += rq_stats->csum_complete_tail_slow; s->rx_csum_unnecessary += rq_stats->csum_unnecessary; s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner; s->rx_xdp_drop += rq_stats->xdp_drop; @@ -1190,6 +1194,8 @@ static const struct counter_desc rq_stats_desc[] = { { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, packets) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, bytes) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete_tail) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete_tail_slow) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary_inner) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) }, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 4640d4f986f8..16c3b785f282 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -71,6 +71,8 @@ struct mlx5e_sw_stats { u64 rx_csum_unnecessary; u64 rx_csum_none; u64 rx_csum_complete; + u64 rx_csum_complete_tail; + u64 rx_csum_complete_tail_slow; u64 rx_csum_unnecessary_inner; u64 rx_xdp_drop; u64 rx_xdp_redirect; @@ -181,6 +183,8 @@ struct mlx5e_rq_stats { u64 packets; u64 bytes; u64 csum_complete; + u64 csum_complete_tail; + u64 csum_complete_tail_slow; u64 csum_unnecessary; u64 csum_unnecessary_inner; u64 csum_none; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index b4967a0ff8c7..d75dc44eb2ff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -2158,6 +2158,52 @@ static bool csum_offload_supported(struct mlx5e_priv *priv, return true; } +struct ip_ttl_word { + __u8 ttl; + __u8 protocol; + __sum16 check; +}; + +struct ipv6_hoplimit_word { + __be16 payload_len; + __u8 nexthdr; + __u8 hop_limit; +}; + +static bool is_action_keys_supported(const struct flow_action_entry *act) +{ + u32 mask, offset; + u8 htype; + + htype = act->mangle.htype; + offset = act->mangle.offset; + mask = ~act->mangle.mask; + /* For IPv4 & IPv6 header check 4 byte word, + * to determine that modified fields + * are NOT ttl & hop_limit only. + */ + if (htype == FLOW_ACT_MANGLE_HDR_TYPE_IP4) { + struct ip_ttl_word *ttl_word = + (struct ip_ttl_word *)&mask; + + if (offset != offsetof(struct iphdr, ttl) || + ttl_word->protocol || + ttl_word->check) { + return true; + } + } else if (htype == FLOW_ACT_MANGLE_HDR_TYPE_IP6) { + struct ipv6_hoplimit_word *hoplimit_word = + (struct ipv6_hoplimit_word *)&mask; + + if (offset != offsetof(struct ipv6hdr, payload_len) || + hoplimit_word->payload_len || + hoplimit_word->nexthdr) { + return true; + } + } + return false; +} + static bool modify_header_match_supported(struct mlx5_flow_spec *spec, struct flow_action *flow_action, u32 actions, @@ -2165,9 +2211,9 @@ static bool modify_header_match_supported(struct mlx5_flow_spec *spec, { const struct flow_action_entry *act; bool modify_ip_header; - u8 htype, ip_proto; void *headers_v; u16 ethertype; + u8 ip_proto; int i; if (actions & MLX5_FLOW_CONTEXT_ACTION_DECAP) @@ -2187,9 +2233,7 @@ static bool modify_header_match_supported(struct mlx5_flow_spec *spec, act->id != FLOW_ACTION_ADD) continue; - htype = act->mangle.htype; - if (htype == FLOW_ACT_MANGLE_HDR_TYPE_IP4 || - htype == FLOW_ACT_MANGLE_HDR_TYPE_IP6) { + if (is_action_keys_supported(act)) { modify_ip_header = true; break; } @@ -2340,15 +2384,22 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, return 0; } -static inline int cmp_encap_info(struct ip_tunnel_key *a, - struct ip_tunnel_key *b) +struct encap_key { + struct ip_tunnel_key *ip_tun_key; + int tunnel_type; +}; + +static inline int cmp_encap_info(struct encap_key *a, + struct encap_key *b) { - return memcmp(a, b, sizeof(*a)); + return memcmp(a->ip_tun_key, b->ip_tun_key, sizeof(*a->ip_tun_key)) || + a->tunnel_type != b->tunnel_type; } -static inline int hash_encap_info(struct ip_tunnel_key *key) +static inline int hash_encap_info(struct encap_key *key) { - return jhash(key, sizeof(*key), 0); + return jhash(key->ip_tun_key, sizeof(*key->ip_tun_key), + key->tunnel_type); } @@ -2379,7 +2430,7 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, struct mlx5_esw_flow_attr *attr = flow->esw_attr; struct mlx5e_tc_flow_parse_attr *parse_attr; struct ip_tunnel_info *tun_info; - struct ip_tunnel_key *key; + struct encap_key key, e_key; struct mlx5e_encap_entry *e; unsigned short family; uintptr_t hash_key; @@ -2389,13 +2440,16 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, parse_attr = attr->parse_attr; tun_info = &parse_attr->tun_info[out_index]; family = ip_tunnel_info_af(tun_info); - key = &tun_info->key; + key.ip_tun_key = &tun_info->key; + key.tunnel_type = mlx5e_tc_tun_get_type(mirred_dev); - hash_key = hash_encap_info(key); + hash_key = hash_encap_info(&key); hash_for_each_possible_rcu(esw->offloads.encap_tbl, e, encap_hlist, hash_key) { - if (!cmp_encap_info(&e->tun_info.key, key)) { + e_key.ip_tun_key = &e->tun_info.key; + e_key.tunnel_type = e->tunnel_type; + if (!cmp_encap_info(&e_key, &key)) { found = true; break; } @@ -2657,7 +2711,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, if (hdrs[TCA_PEDIT_KEY_EX_CMD_SET].pedits || hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].pedits) { - err = alloc_tc_pedit_action(priv, MLX5_FLOW_NAMESPACE_KERNEL, + err = alloc_tc_pedit_action(priv, MLX5_FLOW_NAMESPACE_FDB, parse_attr, hdrs, extack); 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 ecd2c747f726..8a67fd197b79 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -105,8 +105,7 @@ 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); - if (vport) - MLX5_SET(modify_nic_vport_context_in, in, other_vport, 1); + 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); @@ -134,8 +133,7 @@ static int modify_esw_vport_context_cmd(struct mlx5_core_dev *dev, u16 vport, MLX5_SET(modify_esw_vport_context_in, in, opcode, MLX5_CMD_OP_MODIFY_ESW_VPORT_CONTEXT); MLX5_SET(modify_esw_vport_context_in, in, vport_number, vport); - if (vport) - MLX5_SET(modify_esw_vport_context_in, in, other_vport, 1); + MLX5_SET(modify_esw_vport_context_in, in, other_vport, 1); return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); } @@ -431,6 +429,8 @@ static int esw_create_legacy_table(struct mlx5_eswitch *esw) { int err; + memset(&esw->fdb_table.legacy, 0, sizeof(struct legacy_fdb)); + err = esw_create_legacy_vepa_table(esw); if (err) return err; @@ -2157,6 +2157,7 @@ static int _mlx5_eswitch_set_vepa_locked(struct mlx5_eswitch *esw, /* Star rule to forward all traffic to uplink vport */ memset(spec, 0, sizeof(*spec)); + memset(&dest, 0, sizeof(dest)); dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT; dest.vport.num = MLX5_VPORT_UPLINK; flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index f2260391be5b..9b2d78ee22b8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1611,6 +1611,7 @@ static int esw_offloads_steering_init(struct mlx5_eswitch *esw, int nvports) { int err; + memset(&esw->fdb_table.offloads, 0, sizeof(struct offloads_fdb)); mutex_init(&esw->fdb_table.offloads.fdb_prio_lock); err = esw_create_offloads_fdb_tables(esw, nvports); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c index 5cf5f2a9d51f..22a2ef111514 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c @@ -148,14 +148,16 @@ static int mlx5_fpga_tls_alloc_swid(struct idr *idr, spinlock_t *idr_spinlock, return ret; } -static void mlx5_fpga_tls_release_swid(struct idr *idr, - spinlock_t *idr_spinlock, u32 swid) +static void *mlx5_fpga_tls_release_swid(struct idr *idr, + spinlock_t *idr_spinlock, u32 swid) { unsigned long flags; + void *ptr; spin_lock_irqsave(idr_spinlock, flags); - idr_remove(idr, swid); + ptr = idr_remove(idr, swid); spin_unlock_irqrestore(idr_spinlock, flags); + return ptr; } static void mlx_tls_kfree_complete(struct mlx5_fpga_conn *conn, @@ -165,20 +167,12 @@ static void mlx_tls_kfree_complete(struct mlx5_fpga_conn *conn, kfree(buf); } -struct mlx5_teardown_stream_context { - struct mlx5_fpga_tls_command_context cmd; - u32 swid; -}; - static void mlx5_fpga_tls_teardown_completion(struct mlx5_fpga_conn *conn, struct mlx5_fpga_device *fdev, struct mlx5_fpga_tls_command_context *cmd, struct mlx5_fpga_dma_buf *resp) { - struct mlx5_teardown_stream_context *ctx = - container_of(cmd, struct mlx5_teardown_stream_context, cmd); - if (resp) { u32 syndrome = MLX5_GET(tls_resp, resp->sg[0].data, syndrome); @@ -186,14 +180,6 @@ mlx5_fpga_tls_teardown_completion(struct mlx5_fpga_conn *conn, mlx5_fpga_err(fdev, "Teardown stream failed with syndrome = %d", syndrome); - else if (MLX5_GET(tls_cmd, cmd->buf.sg[0].data, direction_sx)) - mlx5_fpga_tls_release_swid(&fdev->tls->tx_idr, - &fdev->tls->tx_idr_spinlock, - ctx->swid); - else - mlx5_fpga_tls_release_swid(&fdev->tls->rx_idr, - &fdev->tls->rx_idr_spinlock, - ctx->swid); } mlx5_fpga_tls_put_command_ctx(cmd); } @@ -225,8 +211,14 @@ int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq, rcu_read_lock(); flow = idr_find(&mdev->fpga->tls->rx_idr, ntohl(handle)); - rcu_read_unlock(); + if (unlikely(!flow)) { + rcu_read_unlock(); + WARN_ONCE(1, "Received NULL pointer for handle\n"); + kfree(buf); + return -EINVAL; + } mlx5_fpga_tls_flow_to_cmd(flow, cmd); + rcu_read_unlock(); MLX5_SET(tls_cmd, cmd, swid, ntohl(handle)); MLX5_SET64(tls_cmd, cmd, tls_rcd_sn, be64_to_cpu(rcd_sn)); @@ -238,6 +230,8 @@ int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq, buf->complete = mlx_tls_kfree_complete; ret = mlx5_fpga_sbu_conn_sendmsg(mdev->fpga->tls->conn, buf); + if (ret < 0) + kfree(buf); return ret; } @@ -245,7 +239,7 @@ int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq, static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev, void *flow, u32 swid, gfp_t flags) { - struct mlx5_teardown_stream_context *ctx; + struct mlx5_fpga_tls_command_context *ctx; struct mlx5_fpga_dma_buf *buf; void *cmd; @@ -253,7 +247,7 @@ static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev, if (!ctx) return; - buf = &ctx->cmd.buf; + buf = &ctx->buf; cmd = (ctx + 1); MLX5_SET(tls_cmd, cmd, command_type, CMD_TEARDOWN_STREAM); MLX5_SET(tls_cmd, cmd, swid, swid); @@ -264,8 +258,7 @@ static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev, buf->sg[0].data = cmd; buf->sg[0].size = MLX5_TLS_COMMAND_SIZE; - ctx->swid = swid; - mlx5_fpga_tls_cmd_send(mdev->fpga, &ctx->cmd, + mlx5_fpga_tls_cmd_send(mdev->fpga, ctx, mlx5_fpga_tls_teardown_completion); } @@ -275,13 +268,14 @@ void mlx5_fpga_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid, struct mlx5_fpga_tls *tls = mdev->fpga->tls; void *flow; - rcu_read_lock(); if (direction_sx) - flow = idr_find(&tls->tx_idr, swid); + flow = mlx5_fpga_tls_release_swid(&tls->tx_idr, + &tls->tx_idr_spinlock, + swid); else - flow = idr_find(&tls->rx_idr, swid); - - rcu_read_unlock(); + flow = mlx5_fpga_tls_release_swid(&tls->rx_idr, + &tls->rx_idr_spinlock, + swid); if (!flow) { mlx5_fpga_err(mdev->fpga, "No flow information for swid %u\n", @@ -289,6 +283,7 @@ void mlx5_fpga_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid, return; } + synchronize_rcu(); /* before kfree(flow) */ mlx5_fpga_tls_send_teardown_cmd(mdev, flow, swid, flags); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 70cc906a102b..76716419370d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -164,26 +164,6 @@ static struct mlx5_profile profile[] = { .size = 8, .limit = 4 }, - .mr_cache[16] = { - .size = 8, - .limit = 4 - }, - .mr_cache[17] = { - .size = 8, - .limit = 4 - }, - .mr_cache[18] = { - .size = 8, - .limit = 4 - }, - .mr_cache[19] = { - .size = 4, - .limit = 2 - }, - .mr_cache[20] = { - .size = 4, - .limit = 2 - }, }, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 21b7f05b16a5..361468e0435d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -317,10 +317,6 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev, size -= offset + size - MLX5_EEPROM_PAGE_LENGTH; i2c_addr = MLX5_I2C_ADDR_LOW; - if (offset >= MLX5_EEPROM_PAGE_LENGTH) { - i2c_addr = MLX5_I2C_ADDR_HIGH; - offset -= MLX5_EEPROM_PAGE_LENGTH; - } MLX5_SET(mcia_reg, in, l, 0); MLX5_SET(mcia_reg, in, module, module_num); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index d23d53c0e284..f26a4ca29363 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -568,7 +568,7 @@ static int mlxsw_emad_init(struct mlxsw_core *mlxsw_core) if (!(mlxsw_core->bus->features & MLXSW_BUS_F_TXRX)) return 0; - emad_wq = alloc_workqueue("mlxsw_core_emad", WQ_MEM_RECLAIM, 0); + emad_wq = alloc_workqueue("mlxsw_core_emad", 0, 0); if (!emad_wq) return -ENOMEM; mlxsw_core->emad_wq = emad_wq; @@ -1958,10 +1958,10 @@ static int __init mlxsw_core_module_init(void) { int err; - mlxsw_wq = alloc_workqueue(mlxsw_core_driver_name, WQ_MEM_RECLAIM, 0); + mlxsw_wq = alloc_workqueue(mlxsw_core_driver_name, 0, 0); if (!mlxsw_wq) return -ENOMEM; - mlxsw_owq = alloc_ordered_workqueue("%s_ordered", WQ_MEM_RECLAIM, + mlxsw_owq = alloc_ordered_workqueue("%s_ordered", 0, mlxsw_core_driver_name); if (!mlxsw_owq) { err = -ENOMEM; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.c b/drivers/net/ethernet/mellanox/mlxsw/core_env.c index 7a15e932ed2f..c1c1965d7acc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_env.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.c @@ -113,7 +113,7 @@ int mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, int module, return 0; default: /* Do not consider thresholds for zero temperature. */ - if (!MLXSW_REG_MTMP_TEMP_TO_MC(module_temp)) { + if (MLXSW_REG_MTMP_TEMP_TO_MC(module_temp) == 0) { *temp = 0; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h index ffee38e36ce8..8648ca171254 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h +++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h @@ -27,7 +27,7 @@ #define MLXSW_PCI_SW_RESET 0xF0010 #define MLXSW_PCI_SW_RESET_RST_BIT BIT(0) -#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS 13000 +#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS 20000 #define MLXSW_PCI_SW_RESET_WAIT_MSECS 100 #define MLXSW_PCI_FW_READY 0xA1844 #define MLXSW_PCI_FW_READY_MASK 0xFFFF diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 9eb63300c1d3..6b8aa3761899 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -3126,11 +3126,11 @@ mlxsw_sp_port_set_link_ksettings(struct net_device *dev, if (err) return err; + mlxsw_sp_port->link.autoneg = autoneg; + if (!netif_running(dev)) return 0; - mlxsw_sp_port->link.autoneg = autoneg; - mlxsw_sp_port_admin_status_set(mlxsw_sp_port, false); mlxsw_sp_port_admin_status_set(mlxsw_sp_port, true); @@ -3316,7 +3316,7 @@ static int mlxsw_sp_port_ets_init(struct mlxsw_sp_port *mlxsw_sp_port) err = mlxsw_sp_port_ets_set(mlxsw_sp_port, MLXSW_REG_QEEC_HIERARCY_TC, i + 8, i, - false, 0); + true, 100); if (err) return err; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index 9a79b5e11597..d633bef5f105 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -70,6 +70,7 @@ static const struct mlxsw_sp_sb_pool_des mlxsw_sp2_sb_pool_dess[] = { {MLXSW_REG_SBXX_DIR_EGRESS, 1}, {MLXSW_REG_SBXX_DIR_EGRESS, 2}, {MLXSW_REG_SBXX_DIR_EGRESS, 3}, + {MLXSW_REG_SBXX_DIR_EGRESS, 15}, }; #define MLXSW_SP_SB_ING_TC_COUNT 8 @@ -428,6 +429,7 @@ static const struct mlxsw_sp_sb_pr mlxsw_sp2_sb_prs[] = { MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0), MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0), + MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, MLXSW_SP_SB_INFI), }; static int mlxsw_sp_sb_prs_init(struct mlxsw_sp *mlxsw_sp, @@ -517,14 +519,14 @@ static const struct mlxsw_sp_sb_cm mlxsw_sp2_sb_cms_egress[] = { MLXSW_SP_SB_CM(0, 7, 4), MLXSW_SP_SB_CM(0, 7, 4), MLXSW_SP_SB_CM(0, 7, 4), - MLXSW_SP_SB_CM(0, 7, 4), - MLXSW_SP_SB_CM(0, 7, 4), - MLXSW_SP_SB_CM(0, 7, 4), - MLXSW_SP_SB_CM(0, 7, 4), - MLXSW_SP_SB_CM(0, 7, 4), - MLXSW_SP_SB_CM(0, 7, 4), - MLXSW_SP_SB_CM(0, 7, 4), - MLXSW_SP_SB_CM(0, 7, 4), + MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8), + MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8), + MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8), + MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8), + MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8), + MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8), + MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8), + MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8), MLXSW_SP_SB_CM(1, 0xff, 4), }; @@ -671,6 +673,7 @@ static const struct mlxsw_sp_sb_pm mlxsw_sp2_sb_pms[] = { MLXSW_SP_SB_PM(0, 0), MLXSW_SP_SB_PM(0, 0), MLXSW_SP_SB_PM(0, 0), + MLXSW_SP_SB_PM(10000, 90000), }; static int mlxsw_sp_port_sb_pms_init(struct mlxsw_sp_port *mlxsw_sp_port) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 52fed8c7bf1e..902e766a8ed3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -6781,7 +6781,7 @@ static int mlxsw_sp_router_port_check_rif_addr(struct mlxsw_sp *mlxsw_sp, /* A RIF is not created for macvlan netdevs. Their MAC is used to * populate the FDB */ - if (netif_is_macvlan(dev)) + if (netif_is_macvlan(dev) || netif_is_l3_master(dev)) return 0; for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index f6ce386c3036..50111f228d77 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -1630,7 +1630,7 @@ static int mlxsw_sp_port_mdb_add(struct mlxsw_sp_port *mlxsw_sp_port, u16 fid_index; int err = 0; - if (switchdev_trans_ph_prepare(trans)) + if (switchdev_trans_ph_commit(trans)) return 0; bridge_port = mlxsw_sp_bridge_port_find(mlxsw_sp->bridge, orig_dev); diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c index bd6e9014bc74..7849119d407a 100644 --- a/drivers/net/ethernet/micrel/ks8851.c +++ b/drivers/net/ethernet/micrel/ks8851.c @@ -142,6 +142,12 @@ struct ks8851_net { static int msg_enable; +/* SPI frame opcodes */ +#define KS_SPIOP_RD (0x00) +#define KS_SPIOP_WR (0x40) +#define KS_SPIOP_RXFIFO (0x80) +#define KS_SPIOP_TXFIFO (0xC0) + /* shift for byte-enable data */ #define BYTE_EN(_x) ((_x) << 2) @@ -535,9 +541,8 @@ static void ks8851_rx_pkts(struct ks8851_net *ks) /* set dma read address */ ks8851_wrreg16(ks, KS_RXFDPR, RXFDPR_RXFPAI | 0x00); - /* start the packet dma process, and set auto-dequeue rx */ - ks8851_wrreg16(ks, KS_RXQCR, - ks->rc_rxqcr | RXQCR_SDA | RXQCR_ADRFE); + /* start DMA access */ + ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA); if (rxlen > 4) { unsigned int rxalign; @@ -568,7 +573,8 @@ static void ks8851_rx_pkts(struct ks8851_net *ks) } } - ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr); + /* end DMA access and dequeue packet */ + ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_RRXEF); } } @@ -785,6 +791,15 @@ static void ks8851_tx_work(struct work_struct *work) static int ks8851_net_open(struct net_device *dev) { struct ks8851_net *ks = netdev_priv(dev); + int ret; + + ret = request_threaded_irq(dev->irq, NULL, ks8851_irq, + IRQF_TRIGGER_LOW | IRQF_ONESHOT, + dev->name, ks); + if (ret < 0) { + netdev_err(dev, "failed to get irq\n"); + return ret; + } /* lock the card, even if we may not actually be doing anything * else at the moment */ @@ -849,6 +864,7 @@ static int ks8851_net_open(struct net_device *dev) netif_dbg(ks, ifup, ks->netdev, "network device up\n"); mutex_unlock(&ks->lock); + mii_check_link(&ks->mii); return 0; } @@ -899,6 +915,8 @@ static int ks8851_net_stop(struct net_device *dev) dev_kfree_skb(txb); } + free_irq(dev->irq, ks); + return 0; } @@ -1508,6 +1526,7 @@ static int ks8851_probe(struct spi_device *spi) spi_set_drvdata(spi, ks); + netif_carrier_off(ks->netdev); ndev->if_port = IF_PORT_100BASET; ndev->netdev_ops = &ks8851_netdev_ops; ndev->irq = spi->irq; @@ -1529,14 +1548,6 @@ static int ks8851_probe(struct spi_device *spi) ks8851_read_selftest(ks); ks8851_init_mac(ks); - ret = request_threaded_irq(spi->irq, NULL, ks8851_irq, - IRQF_TRIGGER_LOW | IRQF_ONESHOT, - ndev->name, ks); - if (ret < 0) { - dev_err(&spi->dev, "failed to get irq\n"); - goto err_irq; - } - ret = register_netdev(ndev); if (ret) { dev_err(&spi->dev, "failed to register network device\n"); @@ -1549,14 +1560,10 @@ static int ks8851_probe(struct spi_device *spi) return 0; - err_netdev: - free_irq(ndev->irq, ks); - -err_irq: +err_id: if (gpio_is_valid(gpio)) gpio_set_value(gpio, 0); -err_id: regulator_disable(ks->vdd_reg); err_reg: regulator_disable(ks->vdd_io); @@ -1574,7 +1581,6 @@ static int ks8851_remove(struct spi_device *spi) dev_info(&spi->dev, "remove\n"); unregister_netdev(priv->netdev); - free_irq(spi->irq, priv); if (gpio_is_valid(priv->gpio)) gpio_set_value(priv->gpio, 0); regulator_disable(priv->vdd_reg); diff --git a/drivers/net/ethernet/micrel/ks8851.h b/drivers/net/ethernet/micrel/ks8851.h index 852256ef1f22..23da1e3ee429 100644 --- a/drivers/net/ethernet/micrel/ks8851.h +++ b/drivers/net/ethernet/micrel/ks8851.h @@ -11,9 +11,15 @@ */ #define KS_CCR 0x08 +#define CCR_LE (1 << 10) /* KSZ8851-16MLL */ #define CCR_EEPROM (1 << 9) -#define CCR_SPI (1 << 8) -#define CCR_32PIN (1 << 0) +#define CCR_SPI (1 << 8) /* KSZ8851SNL */ +#define CCR_8BIT (1 << 7) /* KSZ8851-16MLL */ +#define CCR_16BIT (1 << 6) /* KSZ8851-16MLL */ +#define CCR_32BIT (1 << 5) /* KSZ8851-16MLL */ +#define CCR_SHARED (1 << 4) /* KSZ8851-16MLL */ +#define CCR_48PIN (1 << 1) /* KSZ8851-16MLL */ +#define CCR_32PIN (1 << 0) /* KSZ8851SNL */ /* MAC address registers */ #define KS_MAR(_m) (0x15 - (_m)) @@ -112,13 +118,13 @@ #define RXCR1_RXE (1 << 0) #define KS_RXCR2 0x76 -#define RXCR2_SRDBL_MASK (0x7 << 5) -#define RXCR2_SRDBL_SHIFT (5) -#define RXCR2_SRDBL_4B (0x0 << 5) -#define RXCR2_SRDBL_8B (0x1 << 5) -#define RXCR2_SRDBL_16B (0x2 << 5) -#define RXCR2_SRDBL_32B (0x3 << 5) -#define RXCR2_SRDBL_FRAME (0x4 << 5) +#define RXCR2_SRDBL_MASK (0x7 << 5) /* KSZ8851SNL */ +#define RXCR2_SRDBL_SHIFT (5) /* KSZ8851SNL */ +#define RXCR2_SRDBL_4B (0x0 << 5) /* KSZ8851SNL */ +#define RXCR2_SRDBL_8B (0x1 << 5) /* KSZ8851SNL */ +#define RXCR2_SRDBL_16B (0x2 << 5) /* KSZ8851SNL */ +#define RXCR2_SRDBL_32B (0x3 << 5) /* KSZ8851SNL */ +#define RXCR2_SRDBL_FRAME (0x4 << 5) /* KSZ8851SNL */ #define RXCR2_IUFFP (1 << 4) #define RXCR2_RXIUFCEZ (1 << 3) #define RXCR2_UDPLFE (1 << 2) @@ -143,8 +149,10 @@ #define RXFSHR_RXCE (1 << 0) #define KS_RXFHBCR 0x7E +#define RXFHBCR_CNT_MASK (0xfff << 0) + #define KS_TXQCR 0x80 -#define TXQCR_AETFE (1 << 2) +#define TXQCR_AETFE (1 << 2) /* KSZ8851SNL */ #define TXQCR_TXQMAM (1 << 1) #define TXQCR_METFE (1 << 0) @@ -167,6 +175,10 @@ #define KS_RXFDPR 0x86 #define RXFDPR_RXFPAI (1 << 14) +#define RXFDPR_WST (1 << 12) /* KSZ8851-16MLL */ +#define RXFDPR_EMS (1 << 11) /* KSZ8851-16MLL */ +#define RXFDPR_RXFP_MASK (0x7ff << 0) +#define RXFDPR_RXFP_SHIFT (0) #define KS_RXDTTR 0x8C #define KS_RXDBCTR 0x8E @@ -184,7 +196,7 @@ #define IRQ_RXMPDI (1 << 4) #define IRQ_LDI (1 << 3) #define IRQ_EDI (1 << 2) -#define IRQ_SPIBEI (1 << 1) +#define IRQ_SPIBEI (1 << 1) /* KSZ8851SNL */ #define IRQ_DEDI (1 << 0) #define KS_RXFCTR 0x9C @@ -257,42 +269,37 @@ #define KS_P1ANLPR 0xEE #define KS_P1SCLMD 0xF4 -#define P1SCLMD_LEDOFF (1 << 15) -#define P1SCLMD_TXIDS (1 << 14) -#define P1SCLMD_RESTARTAN (1 << 13) -#define P1SCLMD_DISAUTOMDIX (1 << 10) -#define P1SCLMD_FORCEMDIX (1 << 9) -#define P1SCLMD_AUTONEGEN (1 << 7) -#define P1SCLMD_FORCE100 (1 << 6) -#define P1SCLMD_FORCEFDX (1 << 5) -#define P1SCLMD_ADV_FLOW (1 << 4) -#define P1SCLMD_ADV_100BT_FDX (1 << 3) -#define P1SCLMD_ADV_100BT_HDX (1 << 2) -#define P1SCLMD_ADV_10BT_FDX (1 << 1) -#define P1SCLMD_ADV_10BT_HDX (1 << 0) #define KS_P1CR 0xF6 -#define P1CR_HP_MDIX (1 << 15) -#define P1CR_REV_POL (1 << 13) -#define P1CR_OP_100M (1 << 10) -#define P1CR_OP_FDX (1 << 9) -#define P1CR_OP_MDI (1 << 7) -#define P1CR_AN_DONE (1 << 6) -#define P1CR_LINK_GOOD (1 << 5) -#define P1CR_PNTR_FLOW (1 << 4) -#define P1CR_PNTR_100BT_FDX (1 << 3) -#define P1CR_PNTR_100BT_HDX (1 << 2) -#define P1CR_PNTR_10BT_FDX (1 << 1) -#define P1CR_PNTR_10BT_HDX (1 << 0) +#define P1CR_LEDOFF (1 << 15) +#define P1CR_TXIDS (1 << 14) +#define P1CR_RESTARTAN (1 << 13) +#define P1CR_DISAUTOMDIX (1 << 10) +#define P1CR_FORCEMDIX (1 << 9) +#define P1CR_AUTONEGEN (1 << 7) +#define P1CR_FORCE100 (1 << 6) +#define P1CR_FORCEFDX (1 << 5) +#define P1CR_ADV_FLOW (1 << 4) +#define P1CR_ADV_100BT_FDX (1 << 3) +#define P1CR_ADV_100BT_HDX (1 << 2) +#define P1CR_ADV_10BT_FDX (1 << 1) +#define P1CR_ADV_10BT_HDX (1 << 0) + +#define KS_P1SR 0xF8 +#define P1SR_HP_MDIX (1 << 15) +#define P1SR_REV_POL (1 << 13) +#define P1SR_OP_100M (1 << 10) +#define P1SR_OP_FDX (1 << 9) +#define P1SR_OP_MDI (1 << 7) +#define P1SR_AN_DONE (1 << 6) +#define P1SR_LINK_GOOD (1 << 5) +#define P1SR_PNTR_FLOW (1 << 4) +#define P1SR_PNTR_100BT_FDX (1 << 3) +#define P1SR_PNTR_100BT_HDX (1 << 2) +#define P1SR_PNTR_10BT_FDX (1 << 1) +#define P1SR_PNTR_10BT_HDX (1 << 0) /* TX Frame control */ - #define TXFR_TXIC (1 << 15) #define TXFR_TXFID_MASK (0x3f << 0) #define TXFR_TXFID_SHIFT (0) - -/* SPI frame opcodes */ -#define KS_SPIOP_RD (0x00) -#define KS_SPIOP_WR (0x40) -#define KS_SPIOP_RXFIFO (0x80) -#define KS_SPIOP_TXFIFO (0xC0) diff --git a/drivers/net/ethernet/micrel/ks8851_mll.c b/drivers/net/ethernet/micrel/ks8851_mll.c index 35f8c9ef204d..c946841c0a06 100644 --- a/drivers/net/ethernet/micrel/ks8851_mll.c +++ b/drivers/net/ethernet/micrel/ks8851_mll.c @@ -40,6 +40,8 @@ #include <linux/of_device.h> #include <linux/of_net.h> +#include "ks8851.h" + #define DRV_NAME "ks8851_mll" static u8 KS_DEFAULT_MAC_ADDRESS[] = { 0x00, 0x10, 0xA1, 0x86, 0x95, 0x11 }; @@ -48,319 +50,10 @@ static u8 KS_DEFAULT_MAC_ADDRESS[] = { 0x00, 0x10, 0xA1, 0x86, 0x95, 0x11 }; #define TX_BUF_SIZE 2000 #define RX_BUF_SIZE 2000 -#define KS_CCR 0x08 -#define CCR_EEPROM (1 << 9) -#define CCR_SPI (1 << 8) -#define CCR_8BIT (1 << 7) -#define CCR_16BIT (1 << 6) -#define CCR_32BIT (1 << 5) -#define CCR_SHARED (1 << 4) -#define CCR_32PIN (1 << 0) - -/* MAC address registers */ -#define KS_MARL 0x10 -#define KS_MARM 0x12 -#define KS_MARH 0x14 - -#define KS_OBCR 0x20 -#define OBCR_ODS_16MA (1 << 6) - -#define KS_EEPCR 0x22 -#define EEPCR_EESA (1 << 4) -#define EEPCR_EESB (1 << 3) -#define EEPCR_EEDO (1 << 2) -#define EEPCR_EESCK (1 << 1) -#define EEPCR_EECS (1 << 0) - -#define KS_MBIR 0x24 -#define MBIR_TXMBF (1 << 12) -#define MBIR_TXMBFA (1 << 11) -#define MBIR_RXMBF (1 << 4) -#define MBIR_RXMBFA (1 << 3) - -#define KS_GRR 0x26 -#define GRR_QMU (1 << 1) -#define GRR_GSR (1 << 0) - -#define KS_WFCR 0x2A -#define WFCR_MPRXE (1 << 7) -#define WFCR_WF3E (1 << 3) -#define WFCR_WF2E (1 << 2) -#define WFCR_WF1E (1 << 1) -#define WFCR_WF0E (1 << 0) - -#define KS_WF0CRC0 0x30 -#define KS_WF0CRC1 0x32 -#define KS_WF0BM0 0x34 -#define KS_WF0BM1 0x36 -#define KS_WF0BM2 0x38 -#define KS_WF0BM3 0x3A - -#define KS_WF1CRC0 0x40 -#define KS_WF1CRC1 0x42 -#define KS_WF1BM0 0x44 -#define KS_WF1BM1 0x46 -#define KS_WF1BM2 0x48 -#define KS_WF1BM3 0x4A - -#define KS_WF2CRC0 0x50 -#define KS_WF2CRC1 0x52 -#define KS_WF2BM0 0x54 -#define KS_WF2BM1 0x56 -#define KS_WF2BM2 0x58 -#define KS_WF2BM3 0x5A - -#define KS_WF3CRC0 0x60 -#define KS_WF3CRC1 0x62 -#define KS_WF3BM0 0x64 -#define KS_WF3BM1 0x66 -#define KS_WF3BM2 0x68 -#define KS_WF3BM3 0x6A - -#define KS_TXCR 0x70 -#define TXCR_TCGICMP (1 << 8) -#define TXCR_TCGUDP (1 << 7) -#define TXCR_TCGTCP (1 << 6) -#define TXCR_TCGIP (1 << 5) -#define TXCR_FTXQ (1 << 4) -#define TXCR_TXFCE (1 << 3) -#define TXCR_TXPE (1 << 2) -#define TXCR_TXCRC (1 << 1) -#define TXCR_TXE (1 << 0) - -#define KS_TXSR 0x72 -#define TXSR_TXLC (1 << 13) -#define TXSR_TXMC (1 << 12) -#define TXSR_TXFID_MASK (0x3f << 0) -#define TXSR_TXFID_SHIFT (0) -#define TXSR_TXFID_GET(_v) (((_v) >> 0) & 0x3f) - - -#define KS_RXCR1 0x74 -#define RXCR1_FRXQ (1 << 15) -#define RXCR1_RXUDPFCC (1 << 14) -#define RXCR1_RXTCPFCC (1 << 13) -#define RXCR1_RXIPFCC (1 << 12) -#define RXCR1_RXPAFMA (1 << 11) -#define RXCR1_RXFCE (1 << 10) -#define RXCR1_RXEFE (1 << 9) -#define RXCR1_RXMAFMA (1 << 8) -#define RXCR1_RXBE (1 << 7) -#define RXCR1_RXME (1 << 6) -#define RXCR1_RXUE (1 << 5) -#define RXCR1_RXAE (1 << 4) -#define RXCR1_RXINVF (1 << 1) -#define RXCR1_RXE (1 << 0) #define RXCR1_FILTER_MASK (RXCR1_RXINVF | RXCR1_RXAE | \ RXCR1_RXMAFMA | RXCR1_RXPAFMA) - -#define KS_RXCR2 0x76 -#define RXCR2_SRDBL_MASK (0x7 << 5) -#define RXCR2_SRDBL_SHIFT (5) -#define RXCR2_SRDBL_4B (0x0 << 5) -#define RXCR2_SRDBL_8B (0x1 << 5) -#define RXCR2_SRDBL_16B (0x2 << 5) -#define RXCR2_SRDBL_32B (0x3 << 5) -/* #define RXCR2_SRDBL_FRAME (0x4 << 5) */ -#define RXCR2_IUFFP (1 << 4) -#define RXCR2_RXIUFCEZ (1 << 3) -#define RXCR2_UDPLFE (1 << 2) -#define RXCR2_RXICMPFCC (1 << 1) -#define RXCR2_RXSAF (1 << 0) - -#define KS_TXMIR 0x78 - -#define KS_RXFHSR 0x7C -#define RXFSHR_RXFV (1 << 15) -#define RXFSHR_RXICMPFCS (1 << 13) -#define RXFSHR_RXIPFCS (1 << 12) -#define RXFSHR_RXTCPFCS (1 << 11) -#define RXFSHR_RXUDPFCS (1 << 10) -#define RXFSHR_RXBF (1 << 7) -#define RXFSHR_RXMF (1 << 6) -#define RXFSHR_RXUF (1 << 5) -#define RXFSHR_RXMR (1 << 4) -#define RXFSHR_RXFT (1 << 3) -#define RXFSHR_RXFTL (1 << 2) -#define RXFSHR_RXRF (1 << 1) -#define RXFSHR_RXCE (1 << 0) -#define RXFSHR_ERR (RXFSHR_RXCE | RXFSHR_RXRF |\ - RXFSHR_RXFTL | RXFSHR_RXMR |\ - RXFSHR_RXICMPFCS | RXFSHR_RXIPFCS |\ - RXFSHR_RXTCPFCS) -#define KS_RXFHBCR 0x7E -#define RXFHBCR_CNT_MASK 0x0FFF - -#define KS_TXQCR 0x80 -#define TXQCR_AETFE (1 << 2) -#define TXQCR_TXQMAM (1 << 1) -#define TXQCR_METFE (1 << 0) - -#define KS_RXQCR 0x82 -#define RXQCR_RXDTTS (1 << 12) -#define RXQCR_RXDBCTS (1 << 11) -#define RXQCR_RXFCTS (1 << 10) -#define RXQCR_RXIPHTOE (1 << 9) -#define RXQCR_RXDTTE (1 << 7) -#define RXQCR_RXDBCTE (1 << 6) -#define RXQCR_RXFCTE (1 << 5) -#define RXQCR_ADRFE (1 << 4) -#define RXQCR_SDA (1 << 3) -#define RXQCR_RRXEF (1 << 0) #define RXQCR_CMD_CNTL (RXQCR_RXFCTE|RXQCR_ADRFE) -#define KS_TXFDPR 0x84 -#define TXFDPR_TXFPAI (1 << 14) -#define TXFDPR_TXFP_MASK (0x7ff << 0) -#define TXFDPR_TXFP_SHIFT (0) - -#define KS_RXFDPR 0x86 -#define RXFDPR_RXFPAI (1 << 14) - -#define KS_RXDTTR 0x8C -#define KS_RXDBCTR 0x8E - -#define KS_IER 0x90 -#define KS_ISR 0x92 -#define IRQ_LCI (1 << 15) -#define IRQ_TXI (1 << 14) -#define IRQ_RXI (1 << 13) -#define IRQ_RXOI (1 << 11) -#define IRQ_TXPSI (1 << 9) -#define IRQ_RXPSI (1 << 8) -#define IRQ_TXSAI (1 << 6) -#define IRQ_RXWFDI (1 << 5) -#define IRQ_RXMPDI (1 << 4) -#define IRQ_LDI (1 << 3) -#define IRQ_EDI (1 << 2) -#define IRQ_SPIBEI (1 << 1) -#define IRQ_DEDI (1 << 0) - -#define KS_RXFCTR 0x9C -#define RXFCTR_THRESHOLD_MASK 0x00FF - -#define KS_RXFC 0x9D -#define RXFCTR_RXFC_MASK (0xff << 8) -#define RXFCTR_RXFC_SHIFT (8) -#define RXFCTR_RXFC_GET(_v) (((_v) >> 8) & 0xff) -#define RXFCTR_RXFCT_MASK (0xff << 0) -#define RXFCTR_RXFCT_SHIFT (0) - -#define KS_TXNTFSR 0x9E - -#define KS_MAHTR0 0xA0 -#define KS_MAHTR1 0xA2 -#define KS_MAHTR2 0xA4 -#define KS_MAHTR3 0xA6 - -#define KS_FCLWR 0xB0 -#define KS_FCHWR 0xB2 -#define KS_FCOWR 0xB4 - -#define KS_CIDER 0xC0 -#define CIDER_ID 0x8870 -#define CIDER_REV_MASK (0x7 << 1) -#define CIDER_REV_SHIFT (1) -#define CIDER_REV_GET(_v) (((_v) >> 1) & 0x7) - -#define KS_CGCR 0xC6 -#define KS_IACR 0xC8 -#define IACR_RDEN (1 << 12) -#define IACR_TSEL_MASK (0x3 << 10) -#define IACR_TSEL_SHIFT (10) -#define IACR_TSEL_MIB (0x3 << 10) -#define IACR_ADDR_MASK (0x1f << 0) -#define IACR_ADDR_SHIFT (0) - -#define KS_IADLR 0xD0 -#define KS_IAHDR 0xD2 - -#define KS_PMECR 0xD4 -#define PMECR_PME_DELAY (1 << 14) -#define PMECR_PME_POL (1 << 12) -#define PMECR_WOL_WAKEUP (1 << 11) -#define PMECR_WOL_MAGICPKT (1 << 10) -#define PMECR_WOL_LINKUP (1 << 9) -#define PMECR_WOL_ENERGY (1 << 8) -#define PMECR_AUTO_WAKE_EN (1 << 7) -#define PMECR_WAKEUP_NORMAL (1 << 6) -#define PMECR_WKEVT_MASK (0xf << 2) -#define PMECR_WKEVT_SHIFT (2) -#define PMECR_WKEVT_GET(_v) (((_v) >> 2) & 0xf) -#define PMECR_WKEVT_ENERGY (0x1 << 2) -#define PMECR_WKEVT_LINK (0x2 << 2) -#define PMECR_WKEVT_MAGICPKT (0x4 << 2) -#define PMECR_WKEVT_FRAME (0x8 << 2) -#define PMECR_PM_MASK (0x3 << 0) -#define PMECR_PM_SHIFT (0) -#define PMECR_PM_NORMAL (0x0 << 0) -#define PMECR_PM_ENERGY (0x1 << 0) -#define PMECR_PM_SOFTDOWN (0x2 << 0) -#define PMECR_PM_POWERSAVE (0x3 << 0) - -/* Standard MII PHY data */ -#define KS_P1MBCR 0xE4 -#define P1MBCR_FORCE_FDX (1 << 8) - -#define KS_P1MBSR 0xE6 -#define P1MBSR_AN_COMPLETE (1 << 5) -#define P1MBSR_AN_CAPABLE (1 << 3) -#define P1MBSR_LINK_UP (1 << 2) - -#define KS_PHY1ILR 0xE8 -#define KS_PHY1IHR 0xEA -#define KS_P1ANAR 0xEC -#define KS_P1ANLPR 0xEE - -#define KS_P1SCLMD 0xF4 -#define P1SCLMD_LEDOFF (1 << 15) -#define P1SCLMD_TXIDS (1 << 14) -#define P1SCLMD_RESTARTAN (1 << 13) -#define P1SCLMD_DISAUTOMDIX (1 << 10) -#define P1SCLMD_FORCEMDIX (1 << 9) -#define P1SCLMD_AUTONEGEN (1 << 7) -#define P1SCLMD_FORCE100 (1 << 6) -#define P1SCLMD_FORCEFDX (1 << 5) -#define P1SCLMD_ADV_FLOW (1 << 4) -#define P1SCLMD_ADV_100BT_FDX (1 << 3) -#define P1SCLMD_ADV_100BT_HDX (1 << 2) -#define P1SCLMD_ADV_10BT_FDX (1 << 1) -#define P1SCLMD_ADV_10BT_HDX (1 << 0) - -#define KS_P1CR 0xF6 -#define P1CR_HP_MDIX (1 << 15) -#define P1CR_REV_POL (1 << 13) -#define P1CR_OP_100M (1 << 10) -#define P1CR_OP_FDX (1 << 9) -#define P1CR_OP_MDI (1 << 7) -#define P1CR_AN_DONE (1 << 6) -#define P1CR_LINK_GOOD (1 << 5) -#define P1CR_PNTR_FLOW (1 << 4) -#define P1CR_PNTR_100BT_FDX (1 << 3) -#define P1CR_PNTR_100BT_HDX (1 << 2) -#define P1CR_PNTR_10BT_FDX (1 << 1) -#define P1CR_PNTR_10BT_HDX (1 << 0) - -/* TX Frame control */ - -#define TXFR_TXIC (1 << 15) -#define TXFR_TXFID_MASK (0x3f << 0) -#define TXFR_TXFID_SHIFT (0) - -#define KS_P1SR 0xF8 -#define P1SR_HP_MDIX (1 << 15) -#define P1SR_REV_POL (1 << 13) -#define P1SR_OP_100M (1 << 10) -#define P1SR_OP_FDX (1 << 9) -#define P1SR_OP_MDI (1 << 7) -#define P1SR_AN_DONE (1 << 6) -#define P1SR_LINK_GOOD (1 << 5) -#define P1SR_PNTR_FLOW (1 << 4) -#define P1SR_PNTR_100BT_FDX (1 << 3) -#define P1SR_PNTR_100BT_HDX (1 << 2) -#define P1SR_PNTR_10BT_FDX (1 << 1) -#define P1SR_PNTR_10BT_HDX (1 << 0) - #define ENUM_BUS_NONE 0 #define ENUM_BUS_8BIT 1 #define ENUM_BUS_16BIT 2 @@ -1475,7 +1168,7 @@ static void ks_setup(struct ks_net *ks) ks_wrreg16(ks, KS_RXFDPR, RXFDPR_RXFPAI); /* Setup Receive Frame Threshold - 1 frame (RXFCTFC) */ - ks_wrreg16(ks, KS_RXFCTR, 1 & RXFCTR_THRESHOLD_MASK); + ks_wrreg16(ks, KS_RXFCTR, 1 & RXFCTR_RXFCT_MASK); /* Setup RxQ Command Control (RXQCR) */ ks->rc_rxqcr = RXQCR_CMD_CNTL; @@ -1488,7 +1181,7 @@ static void ks_setup(struct ks_net *ks) */ w = ks_rdreg16(ks, KS_P1MBCR); - w &= ~P1MBCR_FORCE_FDX; + w &= ~BMCR_FULLDPLX; ks_wrreg16(ks, KS_P1MBCR, w); w = TXCR_TXFCE | TXCR_TXPE | TXCR_TXCRC | TXCR_TCGIP; @@ -1629,7 +1322,7 @@ static int ks8851_probe(struct platform_device *pdev) ks_setup_int(ks); data = ks_rdreg16(ks, KS_OBCR); - ks_wrreg16(ks, KS_OBCR, data | OBCR_ODS_16MA); + ks_wrreg16(ks, KS_OBCR, data | OBCR_ODS_16mA); /* overwriting the default MAC address */ if (pdev->dev.of_node) { diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index a1d0d6e42533..d715ef4fc92f 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -613,7 +613,7 @@ static int ocelot_mact_mc_add(struct ocelot_port *port, struct netdev_hw_addr *hw_addr) { struct ocelot *ocelot = port->ocelot; - struct netdev_hw_addr *ha = kzalloc(sizeof(*ha), GFP_KERNEL); + struct netdev_hw_addr *ha = kzalloc(sizeof(*ha), GFP_ATOMIC); if (!ha) return -ENOMEM; @@ -959,10 +959,8 @@ static void ocelot_get_strings(struct net_device *netdev, u32 sset, u8 *data) ETH_GSTRING_LEN); } -static void ocelot_check_stats(struct work_struct *work) +static void ocelot_update_stats(struct ocelot *ocelot) { - struct delayed_work *del_work = to_delayed_work(work); - struct ocelot *ocelot = container_of(del_work, struct ocelot, stats_work); int i, j; mutex_lock(&ocelot->stats_lock); @@ -986,11 +984,19 @@ static void ocelot_check_stats(struct work_struct *work) } } - cancel_delayed_work(&ocelot->stats_work); + mutex_unlock(&ocelot->stats_lock); +} + +static void ocelot_check_stats_work(struct work_struct *work) +{ + struct delayed_work *del_work = to_delayed_work(work); + struct ocelot *ocelot = container_of(del_work, struct ocelot, + stats_work); + + ocelot_update_stats(ocelot); + queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work, OCELOT_STATS_CHECK_DELAY); - - mutex_unlock(&ocelot->stats_lock); } static void ocelot_get_ethtool_stats(struct net_device *dev, @@ -1001,7 +1007,7 @@ static void ocelot_get_ethtool_stats(struct net_device *dev, int i; /* check and update now */ - ocelot_check_stats(&ocelot->stats_work.work); + ocelot_update_stats(ocelot); /* Copy all counters */ for (i = 0; i < ocelot->num_stats; i++) @@ -1809,7 +1815,7 @@ int ocelot_init(struct ocelot *ocelot) ANA_CPUQ_8021_CFG_CPUQ_BPDU_VAL(6), ANA_CPUQ_8021_CFG, i); - INIT_DELAYED_WORK(&ocelot->stats_work, ocelot_check_stats); + INIT_DELAYED_WORK(&ocelot->stats_work, ocelot_check_stats_work); queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work, OCELOT_STATS_CHECK_DELAY); return 0; diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.c b/drivers/net/ethernet/neterion/vxge/vxge-config.c index 7cde387e5ec6..51cd57ab3d95 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-config.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-config.c @@ -2366,6 +2366,7 @@ static void *__vxge_hw_blockpool_malloc(struct __vxge_hw_device *devh, u32 size, dma_object->addr))) { vxge_os_dma_free(devh->pdev, memblock, &dma_object->acc_handle); + memblock = NULL; goto exit; } diff --git a/drivers/net/ethernet/netronome/nfp/abm/cls.c b/drivers/net/ethernet/netronome/nfp/abm/cls.c index 9852080cf454..ff3913085665 100644 --- a/drivers/net/ethernet/netronome/nfp/abm/cls.c +++ b/drivers/net/ethernet/netronome/nfp/abm/cls.c @@ -39,7 +39,7 @@ nfp_abm_u32_check_knode(struct nfp_abm *abm, struct tc_cls_u32_knode *knode, } if (knode->sel->off || knode->sel->offshift || knode->sel->offmask || knode->sel->offoff || knode->fshift) { - NL_SET_ERR_MSG_MOD(extack, "variable offseting not supported"); + NL_SET_ERR_MSG_MOD(extack, "variable offsetting not supported"); return false; } if (knode->sel->hoff || knode->sel->hmask) { @@ -78,7 +78,7 @@ nfp_abm_u32_check_knode(struct nfp_abm *abm, struct tc_cls_u32_knode *knode, k = &knode->sel->keys[0]; if (k->offmask) { - NL_SET_ERR_MSG_MOD(extack, "offset mask - variable offseting not supported"); + NL_SET_ERR_MSG_MOD(extack, "offset mask - variable offsetting not supported"); return false; } if (k->off) { diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c index eeda4ed98333..e336f6ee94f5 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/action.c +++ b/drivers/net/ethernet/netronome/nfp/flower/action.c @@ -48,8 +48,7 @@ nfp_fl_push_vlan(struct nfp_fl_push_vlan *push_vlan, tmp_push_vlan_tci = FIELD_PREP(NFP_FL_PUSH_VLAN_PRIO, act->vlan.prio) | - FIELD_PREP(NFP_FL_PUSH_VLAN_VID, act->vlan.vid) | - NFP_FL_PUSH_VLAN_CFI; + FIELD_PREP(NFP_FL_PUSH_VLAN_VID, act->vlan.vid); push_vlan->vlan_tci = cpu_to_be16(tmp_push_vlan_tci); } diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h index 4fcaf11ed56e..0ed51e79db00 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h @@ -26,7 +26,7 @@ #define NFP_FLOWER_LAYER2_GENEVE_OP BIT(6) #define NFP_FLOWER_MASK_VLAN_PRIO GENMASK(15, 13) -#define NFP_FLOWER_MASK_VLAN_CFI BIT(12) +#define NFP_FLOWER_MASK_VLAN_PRESENT BIT(12) #define NFP_FLOWER_MASK_VLAN_VID GENMASK(11, 0) #define NFP_FLOWER_MASK_MPLS_LB GENMASK(31, 12) @@ -82,7 +82,6 @@ #define NFP_FL_OUT_FLAGS_TYPE_IDX GENMASK(2, 0) #define NFP_FL_PUSH_VLAN_PRIO GENMASK(15, 13) -#define NFP_FL_PUSH_VLAN_CFI BIT(12) #define NFP_FL_PUSH_VLAN_VID GENMASK(11, 0) #define IPV6_FLOW_LABEL_MASK cpu_to_be32(0x000fffff) diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c index e03c8ef2c28c..9b8b843d0340 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/match.c +++ b/drivers/net/ethernet/netronome/nfp/flower/match.c @@ -30,20 +30,19 @@ nfp_flower_compile_meta_tci(struct nfp_flower_meta_tci *ext, flow_rule_match_vlan(rule, &match); /* Populate the tci field. */ - if (match.key->vlan_id || match.key->vlan_priority) { - tmp_tci = FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO, - match.key->vlan_priority) | - FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID, - match.key->vlan_id) | - NFP_FLOWER_MASK_VLAN_CFI; - ext->tci = cpu_to_be16(tmp_tci); - tmp_tci = FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO, - match.mask->vlan_priority) | - FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID, - match.mask->vlan_id) | - NFP_FLOWER_MASK_VLAN_CFI; - msk->tci = cpu_to_be16(tmp_tci); - } + tmp_tci = NFP_FLOWER_MASK_VLAN_PRESENT; + tmp_tci |= FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO, + match.key->vlan_priority) | + FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID, + match.key->vlan_id); + ext->tci = cpu_to_be16(tmp_tci); + + tmp_tci = NFP_FLOWER_MASK_VLAN_PRESENT; + tmp_tci |= FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO, + match.mask->vlan_priority) | + FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID, + match.mask->vlan_id); + msk->tci = cpu_to_be16(tmp_tci); } } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c index d2c803bb4e56..94d228c04496 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c @@ -195,7 +195,7 @@ static netdev_tx_t nfp_repr_xmit(struct sk_buff *skb, struct net_device *netdev) ret = dev_queue_xmit(skb); nfp_repr_inc_tx_stats(netdev, len, ret); - return ret; + return NETDEV_TX_OK; } static int nfp_repr_stop(struct net_device *netdev) @@ -383,7 +383,7 @@ int nfp_repr_init(struct nfp_app *app, struct net_device *netdev, netdev->features &= ~(NETIF_F_TSO | NETIF_F_TSO6); netdev->gso_max_segs = NFP_NET_LSO_MAX_SEGS; - netdev->priv_flags |= IFF_NO_QUEUE; + netdev->priv_flags |= IFF_NO_QUEUE | IFF_DISABLE_NETPOLL; netdev->features |= NETIF_F_LLTX; if (nfp_app_has_tc(app)) { diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index 43a57ec296fd..127c89b22ef0 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -431,12 +431,16 @@ struct qed_qm_info { u8 num_pf_rls; }; +#define QED_OVERFLOW_BIT 1 + struct qed_db_recovery_info { struct list_head list; /* Lock to protect the doorbell recovery mechanism list */ spinlock_t lock; + bool dorq_attn; u32 db_recovery_counter; + unsigned long overflow; }; struct storm_stats { @@ -920,8 +924,7 @@ u16 qed_get_cm_pq_idx_llt_mtc(struct qed_hwfn *p_hwfn, u8 tc); /* doorbell recovery mechanism */ void qed_db_recovery_dp(struct qed_hwfn *p_hwfn); -void qed_db_recovery_execute(struct qed_hwfn *p_hwfn, - enum qed_db_rec_exec db_exec); +void qed_db_recovery_execute(struct qed_hwfn *p_hwfn); bool qed_edpm_enabled(struct qed_hwfn *p_hwfn); /* Other Linux specific common definitions */ diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 9df8c4b3b54e..866cdc86a3f2 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -102,11 +102,15 @@ static void qed_db_recovery_dp_entry(struct qed_hwfn *p_hwfn, /* Doorbell address sanity (address within doorbell bar range) */ static bool qed_db_rec_sanity(struct qed_dev *cdev, - void __iomem *db_addr, void *db_data) + void __iomem *db_addr, + enum qed_db_rec_width db_width, + void *db_data) { + u32 width = (db_width == DB_REC_WIDTH_32B) ? 32 : 64; + /* Make sure doorbell address is within the doorbell bar */ if (db_addr < cdev->doorbells || - (u8 __iomem *)db_addr > + (u8 __iomem *)db_addr + width > (u8 __iomem *)cdev->doorbells + cdev->db_size) { WARN(true, "Illegal doorbell address: %p. Legal range for doorbell addresses is [%p..%p]\n", @@ -159,7 +163,7 @@ int qed_db_recovery_add(struct qed_dev *cdev, } /* Sanitize doorbell address */ - if (!qed_db_rec_sanity(cdev, db_addr, db_data)) + if (!qed_db_rec_sanity(cdev, db_addr, db_width, db_data)) return -EINVAL; /* Obtain hwfn from doorbell address */ @@ -205,10 +209,6 @@ int qed_db_recovery_del(struct qed_dev *cdev, return 0; } - /* Sanitize doorbell address */ - if (!qed_db_rec_sanity(cdev, db_addr, db_data)) - return -EINVAL; - /* Obtain hwfn from doorbell address */ p_hwfn = qed_db_rec_find_hwfn(cdev, db_addr); @@ -300,31 +300,24 @@ void qed_db_recovery_dp(struct qed_hwfn *p_hwfn) /* Ring the doorbell of a single doorbell recovery entry */ static void qed_db_recovery_ring(struct qed_hwfn *p_hwfn, - struct qed_db_recovery_entry *db_entry, - enum qed_db_rec_exec db_exec) -{ - if (db_exec != DB_REC_ONCE) { - /* Print according to width */ - if (db_entry->db_width == DB_REC_WIDTH_32B) { - DP_VERBOSE(p_hwfn, QED_MSG_SPQ, - "%s doorbell address %p data %x\n", - db_exec == DB_REC_DRY_RUN ? - "would have rung" : "ringing", - db_entry->db_addr, - *(u32 *)db_entry->db_data); - } else { - DP_VERBOSE(p_hwfn, QED_MSG_SPQ, - "%s doorbell address %p data %llx\n", - db_exec == DB_REC_DRY_RUN ? - "would have rung" : "ringing", - db_entry->db_addr, - *(u64 *)(db_entry->db_data)); - } + struct qed_db_recovery_entry *db_entry) +{ + /* Print according to width */ + if (db_entry->db_width == DB_REC_WIDTH_32B) { + DP_VERBOSE(p_hwfn, QED_MSG_SPQ, + "ringing doorbell address %p data %x\n", + db_entry->db_addr, + *(u32 *)db_entry->db_data); + } else { + DP_VERBOSE(p_hwfn, QED_MSG_SPQ, + "ringing doorbell address %p data %llx\n", + db_entry->db_addr, + *(u64 *)(db_entry->db_data)); } /* Sanity */ if (!qed_db_rec_sanity(p_hwfn->cdev, db_entry->db_addr, - db_entry->db_data)) + db_entry->db_width, db_entry->db_data)) return; /* Flush the write combined buffer. Since there are multiple doorbelling @@ -334,14 +327,12 @@ static void qed_db_recovery_ring(struct qed_hwfn *p_hwfn, wmb(); /* Ring the doorbell */ - if (db_exec == DB_REC_REAL_DEAL || db_exec == DB_REC_ONCE) { - if (db_entry->db_width == DB_REC_WIDTH_32B) - DIRECT_REG_WR(db_entry->db_addr, - *(u32 *)(db_entry->db_data)); - else - DIRECT_REG_WR64(db_entry->db_addr, - *(u64 *)(db_entry->db_data)); - } + if (db_entry->db_width == DB_REC_WIDTH_32B) + DIRECT_REG_WR(db_entry->db_addr, + *(u32 *)(db_entry->db_data)); + else + DIRECT_REG_WR64(db_entry->db_addr, + *(u64 *)(db_entry->db_data)); /* Flush the write combined buffer. Next doorbell may come from a * different entity to the same address... @@ -350,29 +341,21 @@ static void qed_db_recovery_ring(struct qed_hwfn *p_hwfn, } /* Traverse the doorbell recovery entry list and ring all the doorbells */ -void qed_db_recovery_execute(struct qed_hwfn *p_hwfn, - enum qed_db_rec_exec db_exec) +void qed_db_recovery_execute(struct qed_hwfn *p_hwfn) { struct qed_db_recovery_entry *db_entry = NULL; - if (db_exec != DB_REC_ONCE) { - DP_NOTICE(p_hwfn, - "Executing doorbell recovery. Counter was %d\n", - p_hwfn->db_recovery_info.db_recovery_counter); + DP_NOTICE(p_hwfn, "Executing doorbell recovery. Counter was %d\n", + p_hwfn->db_recovery_info.db_recovery_counter); - /* Track amount of times recovery was executed */ - p_hwfn->db_recovery_info.db_recovery_counter++; - } + /* Track amount of times recovery was executed */ + p_hwfn->db_recovery_info.db_recovery_counter++; /* Protect the list */ spin_lock_bh(&p_hwfn->db_recovery_info.lock); list_for_each_entry(db_entry, - &p_hwfn->db_recovery_info.list, list_entry) { - qed_db_recovery_ring(p_hwfn, db_entry, db_exec); - if (db_exec == DB_REC_ONCE) - break; - } - + &p_hwfn->db_recovery_info.list, list_entry) + qed_db_recovery_ring(p_hwfn, db_entry); spin_unlock_bh(&p_hwfn->db_recovery_info.lock); } diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c index e23980e301b6..8848d5bed6e5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.c +++ b/drivers/net/ethernet/qlogic/qed/qed_int.c @@ -378,6 +378,9 @@ static int qed_db_rec_flush_queue(struct qed_hwfn *p_hwfn, u32 count = QED_DB_REC_COUNT; u32 usage = 1; + /* Flush any pending (e)dpms as they may never arrive */ + qed_wr(p_hwfn, p_ptt, DORQ_REG_DPM_FORCE_ABORT, 0x1); + /* wait for usage to zero or count to run out. This is necessary since * EDPM doorbell transactions can take multiple 64b cycles, and as such * can "split" over the pci. Possibly, the doorbell drop can happen with @@ -406,51 +409,74 @@ static int qed_db_rec_flush_queue(struct qed_hwfn *p_hwfn, int qed_db_rec_handler(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) { - u32 overflow; + u32 attn_ovfl, cur_ovfl; int rc; - overflow = qed_rd(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY); - DP_NOTICE(p_hwfn, "PF Overflow sticky 0x%x\n", overflow); - if (!overflow) { - qed_db_recovery_execute(p_hwfn, DB_REC_ONCE); + attn_ovfl = test_and_clear_bit(QED_OVERFLOW_BIT, + &p_hwfn->db_recovery_info.overflow); + cur_ovfl = qed_rd(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY); + if (!cur_ovfl && !attn_ovfl) return 0; - } - if (qed_edpm_enabled(p_hwfn)) { + DP_NOTICE(p_hwfn, "PF Overflow sticky: attn %u current %u\n", + attn_ovfl, cur_ovfl); + + if (cur_ovfl && !p_hwfn->db_bar_no_edpm) { rc = qed_db_rec_flush_queue(p_hwfn, p_ptt); if (rc) return rc; } - /* Flush any pending (e)dpm as they may never arrive */ - qed_wr(p_hwfn, p_ptt, DORQ_REG_DPM_FORCE_ABORT, 0x1); - /* Release overflow sticky indication (stop silently dropping everything) */ qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY, 0x0); /* Repeat all last doorbells (doorbell drop recovery) */ - qed_db_recovery_execute(p_hwfn, DB_REC_REAL_DEAL); + qed_db_recovery_execute(p_hwfn); return 0; } -static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn) +static void qed_dorq_attn_overflow(struct qed_hwfn *p_hwfn) { - u32 int_sts, first_drop_reason, details, address, all_drops_reason; struct qed_ptt *p_ptt = p_hwfn->p_dpc_ptt; + u32 overflow; int rc; - int_sts = qed_rd(p_hwfn, p_ptt, DORQ_REG_INT_STS); - DP_NOTICE(p_hwfn->cdev, "DORQ attention. int_sts was %x\n", int_sts); + overflow = qed_rd(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY); + if (!overflow) + goto out; + + /* Run PF doorbell recovery in next periodic handler */ + set_bit(QED_OVERFLOW_BIT, &p_hwfn->db_recovery_info.overflow); + + if (!p_hwfn->db_bar_no_edpm) { + rc = qed_db_rec_flush_queue(p_hwfn, p_ptt); + if (rc) + goto out; + } + + qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY, 0x0); +out: + /* Schedule the handler even if overflow was not detected */ + qed_periodic_db_rec_start(p_hwfn); +} + +static int qed_dorq_attn_int_sts(struct qed_hwfn *p_hwfn) +{ + u32 int_sts, first_drop_reason, details, address, all_drops_reason; + struct qed_ptt *p_ptt = p_hwfn->p_dpc_ptt; /* int_sts may be zero since all PFs were interrupted for doorbell * overflow but another one already handled it. Can abort here. If * This PF also requires overflow recovery we will be interrupted again. * The masked almost full indication may also be set. Ignoring. */ + int_sts = qed_rd(p_hwfn, p_ptt, DORQ_REG_INT_STS); if (!(int_sts & ~DORQ_REG_INT_STS_DORQ_FIFO_AFULL)) return 0; + DP_NOTICE(p_hwfn->cdev, "DORQ attention. int_sts was %x\n", int_sts); + /* check if db_drop or overflow happened */ if (int_sts & (DORQ_REG_INT_STS_DB_DROP | DORQ_REG_INT_STS_DORQ_FIFO_OVFL_ERR)) { @@ -477,11 +503,6 @@ static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn) GET_FIELD(details, QED_DORQ_ATTENTION_SIZE) * 4, first_drop_reason, all_drops_reason); - rc = qed_db_rec_handler(p_hwfn, p_ptt); - qed_periodic_db_rec_start(p_hwfn); - if (rc) - return rc; - /* Clear the doorbell drop details and prepare for next drop */ qed_wr(p_hwfn, p_ptt, DORQ_REG_DB_DROP_DETAILS_REL, 0); @@ -507,6 +528,25 @@ static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn) return -EINVAL; } +static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn) +{ + p_hwfn->db_recovery_info.dorq_attn = true; + qed_dorq_attn_overflow(p_hwfn); + + return qed_dorq_attn_int_sts(p_hwfn); +} + +static void qed_dorq_attn_handler(struct qed_hwfn *p_hwfn) +{ + if (p_hwfn->db_recovery_info.dorq_attn) + goto out; + + /* Call DORQ callback if the attention was missed */ + qed_dorq_attn_cb(p_hwfn); +out: + p_hwfn->db_recovery_info.dorq_attn = false; +} + /* Instead of major changes to the data-structure, we have a some 'special' * identifiers for sources that changed meaning between adapters. */ @@ -1080,6 +1120,9 @@ static int qed_int_deassertion(struct qed_hwfn *p_hwfn, } } + /* Handle missed DORQ attention */ + qed_dorq_attn_handler(p_hwfn); + /* Clear IGU indication for the deasserted bits */ DIRECT_REG_WR((u8 __iomem *)p_hwfn->regview + GTT_BAR0_MAP_REG_IGU_CMD + diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.h b/drivers/net/ethernet/qlogic/qed/qed_int.h index 1f356ed4f761..d473b522afc5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.h +++ b/drivers/net/ethernet/qlogic/qed/qed_int.h @@ -192,8 +192,8 @@ void qed_int_disable_post_isr_release(struct qed_dev *cdev); /** * @brief - Doorbell Recovery handler. - * Run DB_REAL_DEAL doorbell recovery in case of PF overflow - * (and flush DORQ if needed), otherwise run DB_REC_ONCE. + * Run doorbell recovery in case of PF overflow (and flush DORQ if + * needed). * * @param p_hwfn * @param p_ptt diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index f164d4acebcb..6de23b56b294 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -970,7 +970,7 @@ static void qed_update_pf_params(struct qed_dev *cdev, } } -#define QED_PERIODIC_DB_REC_COUNT 100 +#define QED_PERIODIC_DB_REC_COUNT 10 #define QED_PERIODIC_DB_REC_INTERVAL_MS 100 #define QED_PERIODIC_DB_REC_INTERVAL \ msecs_to_jiffies(QED_PERIODIC_DB_REC_INTERVAL_MS) diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index 9faaa6df78ed..2f318aaf2b05 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -1591,7 +1591,7 @@ static void qed_iov_vf_mbx_acquire(struct qed_hwfn *p_hwfn, p_vfdev->eth_fp_hsi_minor = ETH_HSI_VER_NO_PKT_LEN_TUNN; } else { DP_INFO(p_hwfn, - "VF[%d] needs fastpath HSI %02x.%02x, which is incompatible with loaded FW's faspath HSI %02x.%02x\n", + "VF[%d] needs fastpath HSI %02x.%02x, which is incompatible with loaded FW's fastpath HSI %02x.%02x\n", vf->abs_vf_id, req->vfdev_info.eth_fp_hsi_major, req->vfdev_info.eth_fp_hsi_minor, diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c index 5f3f42a25361..bddb2b5982dc 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.c @@ -490,18 +490,17 @@ int qede_ptp_enable(struct qede_dev *edev, bool init_tc) ptp->clock = ptp_clock_register(&ptp->clock_info, &edev->pdev->dev); if (IS_ERR(ptp->clock)) { - rc = -EINVAL; DP_ERR(edev, "PTP clock registration failed\n"); + qede_ptp_disable(edev); + rc = -EINVAL; goto err2; } return 0; -err2: - qede_ptp_disable(edev); - ptp->clock = NULL; err1: kfree(ptp); +err2: edev->ptp = NULL; return rc; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h index 0c443ea98479..374a4d4371f9 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h @@ -497,7 +497,7 @@ struct qlcnic_hardware_context { u16 board_type; u16 supported_type; - u16 link_speed; + u32 link_speed; u16 link_duplex; u16 link_autoneg; u16 module_type; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c index 3b0adda7cc9c..a4cd6f2cfb86 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c @@ -1048,6 +1048,8 @@ int qlcnic_do_lb_test(struct qlcnic_adapter *adapter, u8 mode) for (i = 0; i < QLCNIC_NUM_ILB_PKT; i++) { skb = netdev_alloc_skb(adapter->netdev, QLCNIC_ILB_PKT_SIZE); + if (!skb) + break; qlcnic_create_loopback_buff(skb->data, adapter->mac_addr); skb_put(skb, QLCNIC_ILB_PKT_SIZE); adapter->ahw->diag_cnt = 0; diff --git a/drivers/net/ethernet/realtek/atp.c b/drivers/net/ethernet/realtek/atp.c index cfb67b746595..58e0ca9093d3 100644 --- a/drivers/net/ethernet/realtek/atp.c +++ b/drivers/net/ethernet/realtek/atp.c @@ -482,7 +482,7 @@ static void hardware_init(struct net_device *dev) write_reg_high(ioaddr, IMR, ISRh_RxErr); lp->tx_unit_busy = 0; - lp->pac_cnt_in_tx_buf = 0; + lp->pac_cnt_in_tx_buf = 0; lp->saved_tx_size = 0; } diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index c29dde064078..ed651dde6ef9 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -28,6 +28,7 @@ #include <linux/pm_runtime.h> #include <linux/firmware.h> #include <linux/prefetch.h> +#include <linux/pci-aspm.h> #include <linux/ipv6.h> #include <net/ip6_checksum.h> @@ -678,6 +679,7 @@ struct rtl8169_private { struct work_struct work; } wk; + unsigned irq_enabled:1; unsigned supports_gmii:1; dma_addr_t counters_phys_addr; struct rtl8169_counters *counters; @@ -1293,6 +1295,7 @@ static void rtl_ack_events(struct rtl8169_private *tp, u16 bits) static void rtl_irq_disable(struct rtl8169_private *tp) { RTL_W16(tp, IntrMask, 0); + tp->irq_enabled = 0; } #define RTL_EVENT_NAPI_RX (RxOK | RxErr) @@ -1301,6 +1304,7 @@ static void rtl_irq_disable(struct rtl8169_private *tp) static void rtl_irq_enable(struct rtl8169_private *tp) { + tp->irq_enabled = 1; RTL_W16(tp, IntrMask, tp->irq_mask); } @@ -5457,7 +5461,7 @@ static void rtl_hw_start_8168(struct rtl8169_private *tp) tp->cp_cmd |= PktCntrDisable | INTT_1; RTL_W16(tp, CPlusCmd, tp->cp_cmd); - RTL_W16(tp, IntrMitigate, 0x5151); + RTL_W16(tp, IntrMitigate, 0x5100); /* Work around for RxFIFO overflow. */ if (tp->mac_version == RTL_GIGA_MAC_VER_11) { @@ -6520,9 +6524,8 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance) { struct rtl8169_private *tp = dev_instance; u16 status = RTL_R16(tp, IntrStatus); - u16 irq_mask = RTL_R16(tp, IntrMask); - if (status == 0xffff || !(status & irq_mask)) + if (!tp->irq_enabled || status == 0xffff || !(status & tp->irq_mask)) return IRQ_NONE; if (unlikely(status & SYSErr)) { @@ -6540,7 +6543,7 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance) set_bit(RTL_FLAG_TASK_RESET_PENDING, tp->wk.flags); } - if (status & RTL_EVENT_NAPI) { + if (status & (RTL_EVENT_NAPI | LinkChg)) { rtl_irq_disable(tp); napi_schedule_irqoff(&tp->napi); } @@ -7350,6 +7353,11 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (rc) return rc; + /* Disable ASPM completely as that cause random device stop working + * problems as well as full system hangs for some PCIe devices users. + */ + pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1); + /* enable device (incl. PCI PM wakeup and hotplug setup) */ rc = pcim_enable_device(pdev); if (rc < 0) { diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c index 6073387511f8..67f9bb6e941b 100644 --- a/drivers/net/ethernet/sis/sis900.c +++ b/drivers/net/ethernet/sis/sis900.c @@ -730,10 +730,10 @@ static u16 sis900_default_phy(struct net_device * net_dev) status = mdio_read(net_dev, phy->phy_addr, MII_STATUS); /* Link ON & Not select default PHY & not ghost PHY */ - if ((status & MII_STAT_LINK) && !default_phy && - (phy->phy_types != UNKNOWN)) - default_phy = phy; - else { + if ((status & MII_STAT_LINK) && !default_phy && + (phy->phy_types != UNKNOWN)) { + default_phy = phy; + } else { status = mdio_read(net_dev, phy->phy_addr, MII_CONTROL); mdio_write(net_dev, phy->phy_addr, MII_CONTROL, status | MII_CNTL_AUTO | MII_CNTL_ISOLATE); @@ -741,7 +741,7 @@ static u16 sis900_default_phy(struct net_device * net_dev) phy_home = phy; else if(phy->phy_types == LAN) phy_lan = phy; - } + } } if (!default_phy && phy_home) diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index a18149720aa2..cba5881b2746 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -673,7 +673,8 @@ static void netsec_process_tx(struct netsec_priv *priv) } static void *netsec_alloc_rx_data(struct netsec_priv *priv, - dma_addr_t *dma_handle, u16 *desc_len) + dma_addr_t *dma_handle, u16 *desc_len, + bool napi) { size_t total_len = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); size_t payload_len = NETSEC_RX_BUF_SZ; @@ -682,7 +683,7 @@ static void *netsec_alloc_rx_data(struct netsec_priv *priv, total_len += SKB_DATA_ALIGN(payload_len + NETSEC_SKB_PAD); - buf = napi_alloc_frag(total_len); + buf = napi ? napi_alloc_frag(total_len) : netdev_alloc_frag(total_len); if (!buf) return NULL; @@ -765,7 +766,8 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget) /* allocate a fresh buffer and map it to the hardware. * This will eventually replace the old buffer in the hardware */ - buf_addr = netsec_alloc_rx_data(priv, &dma_handle, &desc_len); + buf_addr = netsec_alloc_rx_data(priv, &dma_handle, &desc_len, + true); if (unlikely(!buf_addr)) break; @@ -1069,7 +1071,8 @@ static int netsec_setup_rx_dring(struct netsec_priv *priv) void *buf; u16 len; - buf = netsec_alloc_rx_data(priv, &dma_handle, &len); + buf = netsec_alloc_rx_data(priv, &dma_handle, &len, + false); if (!buf) { netsec_uninit_pkt_dring(priv, NETSEC_RING_RX); goto err_out; diff --git a/drivers/net/ethernet/stmicro/stmmac/descs_com.h b/drivers/net/ethernet/stmicro/stmmac/descs_com.h index 40d6356a7e73..3dfb07a78952 100644 --- a/drivers/net/ethernet/stmicro/stmmac/descs_com.h +++ b/drivers/net/ethernet/stmicro/stmmac/descs_com.h @@ -29,11 +29,13 @@ /* Specific functions used for Ring mode */ /* Enhanced descriptors */ -static inline void ehn_desc_rx_set_on_ring(struct dma_desc *p, int end) +static inline void ehn_desc_rx_set_on_ring(struct dma_desc *p, int end, + int bfsize) { - p->des1 |= cpu_to_le32((BUF_SIZE_8KiB - << ERDES1_BUFFER2_SIZE_SHIFT) - & ERDES1_BUFFER2_SIZE_MASK); + if (bfsize == BUF_SIZE_16KiB) + p->des1 |= cpu_to_le32((BUF_SIZE_8KiB + << ERDES1_BUFFER2_SIZE_SHIFT) + & ERDES1_BUFFER2_SIZE_MASK); if (end) p->des1 |= cpu_to_le32(ERDES1_END_RING); @@ -59,11 +61,15 @@ static inline void enh_set_tx_desc_len_on_ring(struct dma_desc *p, int len) } /* Normal descriptors */ -static inline void ndesc_rx_set_on_ring(struct dma_desc *p, int end) +static inline void ndesc_rx_set_on_ring(struct dma_desc *p, int end, int bfsize) { - p->des1 |= cpu_to_le32(((BUF_SIZE_2KiB - 1) - << RDES1_BUFFER2_SIZE_SHIFT) - & RDES1_BUFFER2_SIZE_MASK); + if (bfsize >= BUF_SIZE_2KiB) { + int bfsize2; + + bfsize2 = min(bfsize - BUF_SIZE_2KiB + 1, BUF_SIZE_2KiB - 1); + p->des1 |= cpu_to_le32((bfsize2 << RDES1_BUFFER2_SIZE_SHIFT) + & RDES1_BUFFER2_SIZE_MASK); + } if (end) p->des1 |= cpu_to_le32(RDES1_END_RING); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c index 062a600fa5a7..21428537e231 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c @@ -333,6 +333,9 @@ static int stm32mp1_parse_data(struct stm32_dwmac *dwmac, */ dwmac->irq_pwr_wakeup = platform_get_irq_byname(pdev, "stm32_pwr_wakeup"); + if (dwmac->irq_pwr_wakeup == -EPROBE_DEFER) + return -EPROBE_DEFER; + if (!dwmac->clk_eth_ck && dwmac->irq_pwr_wakeup >= 0) { err = device_init_wakeup(&pdev->dev, true); if (err) { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c index 7fbb6a4dbf51..e061e9f5fad7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c @@ -296,7 +296,7 @@ exit: } static void dwmac4_rd_init_rx_desc(struct dma_desc *p, int disable_rx_ic, - int mode, int end) + int mode, int end, int bfsize) { dwmac4_set_rx_owner(p, disable_rx_ic); } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c index 1d858fdec997..98fa471da7c0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c @@ -123,7 +123,7 @@ static int dwxgmac2_get_rx_timestamp_status(void *desc, void *next_desc, } static void dwxgmac2_init_rx_desc(struct dma_desc *p, int disable_rx_ic, - int mode, int end) + int mode, int end, int bfsize) { dwxgmac2_set_rx_owner(p, disable_rx_ic); } diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c index 5ef91a790f9d..5202d6ad7919 100644 --- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c +++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c @@ -201,6 +201,11 @@ static int enh_desc_get_rx_status(void *data, struct stmmac_extra_stats *x, if (unlikely(rdes0 & RDES0_OWN)) return dma_own; + if (unlikely(!(rdes0 & RDES0_LAST_DESCRIPTOR))) { + stats->rx_length_errors++; + return discard_frame; + } + if (unlikely(rdes0 & RDES0_ERROR_SUMMARY)) { if (unlikely(rdes0 & RDES0_DESCRIPTOR_ERROR)) { x->rx_desc++; @@ -231,9 +236,10 @@ static int enh_desc_get_rx_status(void *data, struct stmmac_extra_stats *x, * It doesn't match with the information reported into the databook. * At any rate, we need to understand if the CSUM hw computation is ok * and report this info to the upper layers. */ - ret = enh_desc_coe_rdes0(!!(rdes0 & RDES0_IPC_CSUM_ERROR), - !!(rdes0 & RDES0_FRAME_TYPE), - !!(rdes0 & ERDES0_RX_MAC_ADDR)); + if (likely(ret == good_frame)) + ret = enh_desc_coe_rdes0(!!(rdes0 & RDES0_IPC_CSUM_ERROR), + !!(rdes0 & RDES0_FRAME_TYPE), + !!(rdes0 & ERDES0_RX_MAC_ADDR)); if (unlikely(rdes0 & RDES0_DRIBBLING)) x->dribbling_bit++; @@ -259,15 +265,19 @@ static int enh_desc_get_rx_status(void *data, struct stmmac_extra_stats *x, } static void enh_desc_init_rx_desc(struct dma_desc *p, int disable_rx_ic, - int mode, int end) + int mode, int end, int bfsize) { + int bfsize1; + p->des0 |= cpu_to_le32(RDES0_OWN); - p->des1 |= cpu_to_le32(BUF_SIZE_8KiB & ERDES1_BUFFER1_SIZE_MASK); + + bfsize1 = min(bfsize, BUF_SIZE_8KiB); + p->des1 |= cpu_to_le32(bfsize1 & ERDES1_BUFFER1_SIZE_MASK); if (mode == STMMAC_CHAIN_MODE) ehn_desc_rx_set_on_chain(p); else - ehn_desc_rx_set_on_ring(p, end); + ehn_desc_rx_set_on_ring(p, end, bfsize); if (disable_rx_ic) p->des1 |= cpu_to_le32(ERDES1_DISABLE_IC); diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index 92b8944f26e3..5bb00234d961 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -33,7 +33,7 @@ struct dma_extended_desc; struct stmmac_desc_ops { /* DMA RX descriptor ring initialization */ void (*init_rx_desc)(struct dma_desc *p, int disable_rx_ic, int mode, - int end); + int end, int bfsize); /* DMA TX descriptor ring initialization */ void (*init_tx_desc)(struct dma_desc *p, int mode, int end); /* Invoked by the xmit function to prepare the tx descriptor */ diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c index de65bb29feba..6d690678c20e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c +++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c @@ -91,8 +91,6 @@ static int ndesc_get_rx_status(void *data, struct stmmac_extra_stats *x, return dma_own; if (unlikely(!(rdes0 & RDES0_LAST_DESCRIPTOR))) { - pr_warn("%s: Oversized frame spanned multiple buffers\n", - __func__); stats->rx_length_errors++; return discard_frame; } @@ -135,15 +133,19 @@ static int ndesc_get_rx_status(void *data, struct stmmac_extra_stats *x, } static void ndesc_init_rx_desc(struct dma_desc *p, int disable_rx_ic, int mode, - int end) + int end, int bfsize) { + int bfsize1; + p->des0 |= cpu_to_le32(RDES0_OWN); - p->des1 |= cpu_to_le32((BUF_SIZE_2KiB - 1) & RDES1_BUFFER1_SIZE_MASK); + + bfsize1 = min(bfsize, BUF_SIZE_2KiB - 1); + p->des1 |= cpu_to_le32(bfsize1 & RDES1_BUFFER1_SIZE_MASK); if (mode == STMMAC_CHAIN_MODE) ndesc_rx_set_on_chain(p, end); else - ndesc_rx_set_on_ring(p, end); + ndesc_rx_set_on_ring(p, end, bfsize); if (disable_rx_ic) p->des1 |= cpu_to_le32(RDES1_DISABLE_IC); diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c index d8c5bc412219..4d9bcb4d0378 100644 --- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c +++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c @@ -59,7 +59,7 @@ static int jumbo_frm(void *p, struct sk_buff *skb, int csum) desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB); stmmac_prepare_tx_desc(priv, desc, 1, bmax, csum, - STMMAC_RING_MODE, 1, false, skb->len); + STMMAC_RING_MODE, 0, false, skb->len); tx_q->tx_skbuff[entry] = NULL; entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE); @@ -79,7 +79,8 @@ static int jumbo_frm(void *p, struct sk_buff *skb, int csum) desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB); stmmac_prepare_tx_desc(priv, desc, 0, len, csum, - STMMAC_RING_MODE, 1, true, skb->len); + STMMAC_RING_MODE, 1, !skb_is_nonlinear(skb), + skb->len); } else { des2 = dma_map_single(priv->device, skb->data, nopaged_len, DMA_TO_DEVICE); @@ -91,7 +92,8 @@ static int jumbo_frm(void *p, struct sk_buff *skb, int csum) tx_q->tx_skbuff_dma[entry].is_jumbo = true; desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB); stmmac_prepare_tx_desc(priv, desc, 1, nopaged_len, csum, - STMMAC_RING_MODE, 1, true, skb->len); + STMMAC_RING_MODE, 0, !skb_is_nonlinear(skb), + skb->len); } tx_q->cur_tx = entry; @@ -111,10 +113,11 @@ static unsigned int is_jumbo_frm(int len, int enh_desc) static void refill_desc3(void *priv_ptr, struct dma_desc *p) { - struct stmmac_priv *priv = (struct stmmac_priv *)priv_ptr; + struct stmmac_rx_queue *rx_q = priv_ptr; + struct stmmac_priv *priv = rx_q->priv_data; /* Fill DES3 in case of RING mode */ - if (priv->dma_buf_sz >= BUF_SIZE_8KiB) + if (priv->dma_buf_sz == BUF_SIZE_16KiB) p->des3 = cpu_to_le32(le32_to_cpu(p->des2) + BUF_SIZE_8KiB); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 97c5e1aad88f..48712437d0da 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1136,11 +1136,13 @@ static void stmmac_clear_rx_descriptors(struct stmmac_priv *priv, u32 queue) if (priv->extend_desc) stmmac_init_rx_desc(priv, &rx_q->dma_erx[i].basic, priv->use_riwt, priv->mode, - (i == DMA_RX_SIZE - 1)); + (i == DMA_RX_SIZE - 1), + priv->dma_buf_sz); else stmmac_init_rx_desc(priv, &rx_q->dma_rx[i], priv->use_riwt, priv->mode, - (i == DMA_RX_SIZE - 1)); + (i == DMA_RX_SIZE - 1), + priv->dma_buf_sz); } /** @@ -2614,8 +2616,6 @@ static int stmmac_open(struct net_device *dev) u32 chan; int ret; - stmmac_check_ether_addr(priv); - if (priv->hw->pcs != STMMAC_PCS_RGMII && priv->hw->pcs != STMMAC_PCS_TBI && priv->hw->pcs != STMMAC_PCS_RTBI) { @@ -3216,14 +3216,16 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) stmmac_prepare_tx_desc(priv, first, 1, nopaged_len, csum_insertion, priv->mode, 1, last_segment, skb->len); - - /* The own bit must be the latest setting done when prepare the - * descriptor and then barrier is needed to make sure that - * all is coherent before granting the DMA engine. - */ - wmb(); + } else { + stmmac_set_tx_owner(priv, first); } + /* The own bit must be the latest setting done when prepare the + * descriptor and then barrier is needed to make sure that + * all is coherent before granting the DMA engine. + */ + wmb(); + netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len); stmmac_enable_dma_transmission(priv, priv->ioaddr); @@ -3350,9 +3352,8 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) { struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; struct stmmac_channel *ch = &priv->channel[queue]; - unsigned int entry = rx_q->cur_rx; + unsigned int next_entry = rx_q->cur_rx; int coe = priv->hw->rx_csum; - unsigned int next_entry; unsigned int count = 0; bool xmac; @@ -3370,10 +3371,12 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) stmmac_display_ring(priv, rx_head, DMA_RX_SIZE, true); } while (count < limit) { - int status; + int entry, status; struct dma_desc *p; struct dma_desc *np; + entry = next_entry; + if (priv->extend_desc) p = (struct dma_desc *)(rx_q->dma_erx + entry); else @@ -3429,11 +3432,12 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) * ignored */ if (frame_len > priv->dma_buf_sz) { - netdev_err(priv->dev, - "len %d larger than size (%d)\n", - frame_len, priv->dma_buf_sz); + if (net_ratelimit()) + netdev_err(priv->dev, + "len %d larger than size (%d)\n", + frame_len, priv->dma_buf_sz); priv->dev->stats.rx_length_errors++; - break; + continue; } /* ACS is set; GMAC core strips PAD/FCS for IEEE 802.3 @@ -3468,7 +3472,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) dev_warn(priv->device, "packet dropped\n"); priv->dev->stats.rx_dropped++; - break; + continue; } dma_sync_single_for_cpu(priv->device, @@ -3488,11 +3492,12 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) } else { skb = rx_q->rx_skbuff[entry]; if (unlikely(!skb)) { - netdev_err(priv->dev, - "%s: Inconsistent Rx chain\n", - priv->dev->name); + if (net_ratelimit()) + netdev_err(priv->dev, + "%s: Inconsistent Rx chain\n", + priv->dev->name); priv->dev->stats.rx_dropped++; - break; + continue; } prefetch(skb->data - NET_IP_ALIGN); rx_q->rx_skbuff[entry] = NULL; @@ -3527,7 +3532,6 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) priv->dev->stats.rx_packets++; priv->dev->stats.rx_bytes += frame_len; } - entry = next_entry; } stmmac_rx_refill(priv, queue); @@ -4297,6 +4301,8 @@ int stmmac_dvr_probe(struct device *device, if (ret) goto error_hw_init; + stmmac_check_ether_addr(priv); + /* Configure real RX and TX queues */ netif_set_real_num_rx_queues(ndev, priv->plat->rx_queues_to_use); netif_set_real_num_tx_queues(ndev, priv->plat->tx_queues_to_use); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index d819e8eaba12..26db6aa002d1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -159,6 +159,12 @@ static const struct dmi_system_id quark_pci_dmi[] = { }, .driver_data = (void *)&galileo_stmmac_dmi_data, }, + /* + * There are 2 types of SIMATIC IOT2000: IOT2020 and IOT2040. + * The asset tag "6ES7647-0AA00-0YA2" is only for IOT2020 which + * has only one pci network device while other asset tags are + * for IOT2040 which has two. + */ { .matches = { DMI_EXACT_MATCH(DMI_BOARD_NAME, "SIMATIC IOT2000"), @@ -170,8 +176,6 @@ static const struct dmi_system_id quark_pci_dmi[] = { { .matches = { DMI_EXACT_MATCH(DMI_BOARD_NAME, "SIMATIC IOT2000"), - DMI_EXACT_MATCH(DMI_BOARD_ASSET_TAG, - "6ES7647-0AA00-1YA2"), }, .driver_data = (void *)&iot2040_stmmac_dmi_data, }, diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c index 5174d318901e..0a920c5936b2 100644 --- a/drivers/net/ethernet/ti/netcp_ethss.c +++ b/drivers/net/ethernet/ti/netcp_ethss.c @@ -3657,12 +3657,16 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, ret = netcp_txpipe_init(&gbe_dev->tx_pipe, netcp_device, gbe_dev->dma_chan_name, gbe_dev->tx_queue_id); - if (ret) + if (ret) { + of_node_put(interfaces); return ret; + } ret = netcp_txpipe_open(&gbe_dev->tx_pipe); - if (ret) + if (ret) { + of_node_put(interfaces); return ret; + } /* Create network interfaces */ INIT_LIST_HEAD(&gbe_dev->gbe_intf_head); diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index ec7e7ec24ff9..4041c75997ba 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -1575,12 +1575,14 @@ static int axienet_probe(struct platform_device *pdev) ret = of_address_to_resource(np, 0, &dmares); if (ret) { dev_err(&pdev->dev, "unable to get DMA resource\n"); + of_node_put(np); goto free_netdev; } lp->dma_regs = devm_ioremap_resource(&pdev->dev, &dmares); if (IS_ERR(lp->dma_regs)) { dev_err(&pdev->dev, "could not map DMA regs\n"); ret = PTR_ERR(lp->dma_regs); + of_node_put(np); goto free_netdev; } lp->rx_irq = irq_of_parse_and_map(np, 1); diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index e859ae2e42d5..49f41b64077b 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -987,6 +987,7 @@ struct netvsc_device { wait_queue_head_t wait_drain; bool destroy; + bool tx_disable; /* if true, do not wake up queue again */ /* Receive buffer allocated by us but manages by NetVSP */ void *recv_buf; diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 813d195bbd57..e0dce373cdd9 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -110,6 +110,7 @@ static struct netvsc_device *alloc_net_device(void) init_waitqueue_head(&net_device->wait_drain); net_device->destroy = false; + net_device->tx_disable = false; net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT; net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT; @@ -719,7 +720,7 @@ static void netvsc_send_tx_complete(struct net_device *ndev, } else { struct netdev_queue *txq = netdev_get_tx_queue(ndev, q_idx); - if (netif_tx_queue_stopped(txq) && + if (netif_tx_queue_stopped(txq) && !net_device->tx_disable && (hv_get_avail_to_write_percent(&channel->outbound) > RING_AVAIL_PERCENT_HIWATER || queue_sends < 1)) { netif_tx_wake_queue(txq); @@ -874,7 +875,8 @@ static inline int netvsc_send_pkt( } else if (ret == -EAGAIN) { netif_tx_stop_queue(txq); ndev_ctx->eth_stats.stop_queue++; - if (atomic_read(&nvchan->queue_sends) < 1) { + if (atomic_read(&nvchan->queue_sends) < 1 && + !net_device->tx_disable) { netif_tx_wake_queue(txq); ndev_ctx->eth_stats.wake_queue++; ret = -ENOSPC; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index cf4897043e83..b20fb0fb595b 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -109,6 +109,15 @@ static void netvsc_set_rx_mode(struct net_device *net) rcu_read_unlock(); } +static void netvsc_tx_enable(struct netvsc_device *nvscdev, + struct net_device *ndev) +{ + nvscdev->tx_disable = false; + virt_wmb(); /* ensure queue wake up mechanism is on */ + + netif_tx_wake_all_queues(ndev); +} + static int netvsc_open(struct net_device *net) { struct net_device_context *ndev_ctx = netdev_priv(net); @@ -129,7 +138,7 @@ static int netvsc_open(struct net_device *net) rdev = nvdev->extension; if (!rdev->link_state) { netif_carrier_on(net); - netif_tx_wake_all_queues(net); + netvsc_tx_enable(nvdev, net); } if (vf_netdev) { @@ -184,6 +193,17 @@ static int netvsc_wait_until_empty(struct netvsc_device *nvdev) } } +static void netvsc_tx_disable(struct netvsc_device *nvscdev, + struct net_device *ndev) +{ + if (nvscdev) { + nvscdev->tx_disable = true; + virt_wmb(); /* ensure txq will not wake up after stop */ + } + + netif_tx_disable(ndev); +} + static int netvsc_close(struct net_device *net) { struct net_device_context *net_device_ctx = netdev_priv(net); @@ -192,7 +212,7 @@ static int netvsc_close(struct net_device *net) struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev); int ret; - netif_tx_disable(net); + netvsc_tx_disable(nvdev, net); /* No need to close rndis filter if it is removed already */ if (!nvdev) @@ -920,7 +940,7 @@ static int netvsc_detach(struct net_device *ndev, /* If device was up (receiving) then shutdown */ if (netif_running(ndev)) { - netif_tx_disable(ndev); + netvsc_tx_disable(nvdev, ndev); ret = rndis_filter_close(nvdev); if (ret) { @@ -1908,7 +1928,7 @@ static void netvsc_link_change(struct work_struct *w) if (rdev->link_state) { rdev->link_state = false; netif_carrier_on(net); - netif_tx_wake_all_queues(net); + netvsc_tx_enable(net_device, net); } else { notify = true; } @@ -1918,7 +1938,7 @@ static void netvsc_link_change(struct work_struct *w) if (!rdev->link_state) { rdev->link_state = true; netif_carrier_off(net); - netif_tx_stop_all_queues(net); + netvsc_tx_disable(net_device, net); } kfree(event); break; @@ -1927,7 +1947,7 @@ static void netvsc_link_change(struct work_struct *w) if (!rdev->link_state) { rdev->link_state = true; netif_carrier_off(net); - netif_tx_stop_all_queues(net); + netvsc_tx_disable(net_device, net); event->event = RNDIS_STATUS_MEDIA_CONNECT; spin_lock_irqsave(&ndev_ctx->lock, flags); list_add(&event->list, &ndev_ctx->reconfig_events); diff --git a/drivers/net/ieee802154/adf7242.c b/drivers/net/ieee802154/adf7242.c index cd1d8faccca5..cd6b95e673a5 100644 --- a/drivers/net/ieee802154/adf7242.c +++ b/drivers/net/ieee802154/adf7242.c @@ -1268,6 +1268,10 @@ static int adf7242_probe(struct spi_device *spi) INIT_DELAYED_WORK(&lp->work, adf7242_rx_cal_work); lp->wqueue = alloc_ordered_workqueue(dev_name(&spi->dev), WQ_MEM_RECLAIM); + if (unlikely(!lp->wqueue)) { + ret = -ENOMEM; + goto err_hw_init; + } ret = adf7242_hw_init(lp); if (ret) diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c index b6743f03dce0..3b88846de31b 100644 --- a/drivers/net/ieee802154/mac802154_hwsim.c +++ b/drivers/net/ieee802154/mac802154_hwsim.c @@ -324,7 +324,7 @@ static int hwsim_get_radio_nl(struct sk_buff *msg, struct genl_info *info) goto out_err; } - genlmsg_reply(skb, info); + res = genlmsg_reply(skb, info); break; } diff --git a/drivers/net/ieee802154/mcr20a.c b/drivers/net/ieee802154/mcr20a.c index c589f5ae75bb..8bb53ec8d9cf 100644 --- a/drivers/net/ieee802154/mcr20a.c +++ b/drivers/net/ieee802154/mcr20a.c @@ -533,6 +533,8 @@ mcr20a_start(struct ieee802154_hw *hw) dev_dbg(printdev(lp), "no slotted operation\n"); ret = regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL1, DAR_PHY_CTRL1_SLOTTED, 0x0); + if (ret < 0) + return ret; /* enable irq */ enable_irq(lp->spi->irq); @@ -540,11 +542,15 @@ mcr20a_start(struct ieee802154_hw *hw) /* Unmask SEQ interrupt */ ret = regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL2, DAR_PHY_CTRL2_SEQMSK, 0x0); + if (ret < 0) + return ret; /* Start the RX sequence */ dev_dbg(printdev(lp), "start the RX sequence\n"); ret = regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL1, DAR_PHY_CTRL1_XCVSEQ_MASK, MCR20A_XCVSEQ_RX); + if (ret < 0) + return ret; return 0; } diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 071869db44cf..520657945b82 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -7,6 +7,8 @@ menuconfig MDIO_DEVICE help MDIO devices and driver infrastructure code. +if MDIO_DEVICE + config MDIO_BUS tristate default m if PHYLIB=m @@ -179,6 +181,7 @@ config MDIO_XGENE APM X-Gene SoC's. endif +endif config PHYLINK tristate diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index 9605d4fe540b..cb86a3e90c7d 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -323,6 +323,19 @@ static int bcm54xx_config_init(struct phy_device *phydev) bcm54xx_phydsp_config(phydev); + /* Encode link speed into LED1 and LED3 pair (green/amber). + * Also flash these two LEDs on activity. This means configuring + * them for MULTICOLOR and encoding link/activity into them. + */ + 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 = BCM_LED_MULTICOLOR_IN_PHASE | + BCM5482_SHD_LEDS1_LED1(BCM_LED_MULTICOLOR_LINK_ACT) | + BCM5482_SHD_LEDS1_LED3(BCM_LED_MULTICOLOR_LINK_ACT); + bcm_phy_write_exp(phydev, BCM_EXP_MULTICOLOR, val); + return 0; } diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c index bbd8c22067f3..97d45bd5b38e 100644 --- a/drivers/net/phy/dp83822.c +++ b/drivers/net/phy/dp83822.c @@ -15,6 +15,8 @@ #include <linux/netdevice.h> #define DP83822_PHY_ID 0x2000a240 +#define DP83825I_PHY_ID 0x2000a150 + #define DP83822_DEVADDR 0x1f #define MII_DP83822_PHYSCR 0x11 @@ -304,26 +306,30 @@ static int dp83822_resume(struct phy_device *phydev) return 0; } +#define DP83822_PHY_DRIVER(_id, _name) \ + { \ + PHY_ID_MATCH_MODEL(_id), \ + .name = (_name), \ + .features = PHY_BASIC_FEATURES, \ + .soft_reset = dp83822_phy_reset, \ + .config_init = dp83822_config_init, \ + .get_wol = dp83822_get_wol, \ + .set_wol = dp83822_set_wol, \ + .ack_interrupt = dp83822_ack_interrupt, \ + .config_intr = dp83822_config_intr, \ + .suspend = dp83822_suspend, \ + .resume = dp83822_resume, \ + } + static struct phy_driver dp83822_driver[] = { - { - .phy_id = DP83822_PHY_ID, - .phy_id_mask = 0xfffffff0, - .name = "TI DP83822", - .features = PHY_BASIC_FEATURES, - .config_init = dp83822_config_init, - .soft_reset = dp83822_phy_reset, - .get_wol = dp83822_get_wol, - .set_wol = dp83822_set_wol, - .ack_interrupt = dp83822_ack_interrupt, - .config_intr = dp83822_config_intr, - .suspend = dp83822_suspend, - .resume = dp83822_resume, - }, + DP83822_PHY_DRIVER(DP83822_PHY_ID, "TI DP83822"), + DP83822_PHY_DRIVER(DP83825I_PHY_ID, "TI DP83825I"), }; module_phy_driver(dp83822_driver); static struct mdio_device_id __maybe_unused dp83822_tbl[] = { { DP83822_PHY_ID, 0xfffffff0 }, + { DP83825I_PHY_ID, 0xfffffff0 }, { }, }; MODULE_DEVICE_TABLE(mdio, dp83822_tbl); diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 3ccba37bd6dd..f76c4048b978 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -1489,9 +1489,10 @@ static int marvell_get_sset_count(struct phy_device *phydev) static void marvell_get_strings(struct phy_device *phydev, u8 *data) { + int count = marvell_get_sset_count(phydev); int i; - for (i = 0; i < ARRAY_SIZE(marvell_hw_stats); i++) { + for (i = 0; i < count; i++) { strlcpy(data + i * ETH_GSTRING_LEN, marvell_hw_stats[i].string, ETH_GSTRING_LEN); } @@ -1519,9 +1520,10 @@ static u64 marvell_get_stat(struct phy_device *phydev, int i) static void marvell_get_stats(struct phy_device *phydev, struct ethtool_stats *stats, u64 *data) { + int count = marvell_get_sset_count(phydev); int i; - for (i = 0; i < ARRAY_SIZE(marvell_hw_stats); i++) + for (i = 0; i < count; i++) data[i] = marvell_get_stat(phydev, i); } diff --git a/drivers/net/phy/meson-gxl.c b/drivers/net/phy/meson-gxl.c index a238388eb1a5..0eec2913c289 100644 --- a/drivers/net/phy/meson-gxl.c +++ b/drivers/net/phy/meson-gxl.c @@ -201,6 +201,7 @@ static int meson_gxl_ack_interrupt(struct phy_device *phydev) static int meson_gxl_config_intr(struct phy_device *phydev) { u16 val; + int ret; if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { val = INTSRC_ANEG_PR @@ -213,6 +214,11 @@ static int meson_gxl_config_intr(struct phy_device *phydev) val = 0; } + /* Ack any pending IRQ */ + ret = meson_gxl_ack_interrupt(phydev); + if (ret) + return ret; + return phy_write(phydev, INTSRC_MASK, val); } diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 49fdd1ee798e..77068c545de0 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1831,7 +1831,7 @@ int genphy_soft_reset(struct phy_device *phydev) { int ret; - ret = phy_write(phydev, MII_BMCR, BMCR_RESET); + ret = phy_set_bits(phydev, MII_BMCR, BMCR_RESET); if (ret < 0) return ret; diff --git a/drivers/net/phy/spi_ks8995.c b/drivers/net/phy/spi_ks8995.c index 92b64e254b44..7475cef17cf7 100644 --- a/drivers/net/phy/spi_ks8995.c +++ b/drivers/net/phy/spi_ks8995.c @@ -159,6 +159,14 @@ static const struct spi_device_id ks8995_id[] = { }; MODULE_DEVICE_TABLE(spi, ks8995_id); +static const struct of_device_id ks8895_spi_of_match[] = { + { .compatible = "micrel,ks8995" }, + { .compatible = "micrel,ksz8864" }, + { .compatible = "micrel,ksz8795" }, + { }, + }; +MODULE_DEVICE_TABLE(of, ks8895_spi_of_match); + static inline u8 get_chip_id(u8 val) { return (val >> ID1_CHIPID_S) & ID1_CHIPID_M; @@ -526,6 +534,7 @@ static int ks8995_remove(struct spi_device *spi) static struct spi_driver ks8995_driver = { .driver = { .name = "spi-ks8995", + .of_match_table = of_match_ptr(ks8895_spi_of_match), }, .probe = ks8995_probe, .remove = ks8995_remove, diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c index f4e93f5fc204..ea90db3c7705 100644 --- a/drivers/net/slip/slhc.c +++ b/drivers/net/slip/slhc.c @@ -153,7 +153,7 @@ out_fail: void slhc_free(struct slcompress *comp) { - if ( comp == NULLSLCOMPR ) + if ( IS_ERR_OR_NULL(comp) ) return; if ( comp->tstate != NULLSLSTATE ) diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 6ed96fdfd96d..16963f7a88f7 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1156,6 +1156,13 @@ static int team_port_add(struct team *team, struct net_device *port_dev, return -EINVAL; } + if (netdev_has_upper_dev(dev, port_dev)) { + NL_SET_ERR_MSG(extack, "Device is already an upper device of the team interface"); + netdev_err(dev, "Device %s is already an upper device of the team interface\n", + portname); + return -EBUSY; + } + if (port_dev->features & NETIF_F_VLAN_CHALLENGED && vlan_uses_dev(dev)) { NL_SET_ERR_MSG(extack, "Device is VLAN challenged and team device has VLAN set up"); @@ -1246,6 +1253,23 @@ static int team_port_add(struct team *team, struct net_device *port_dev, goto err_option_port_add; } + /* set promiscuity level to new slave */ + if (dev->flags & IFF_PROMISC) { + err = dev_set_promiscuity(port_dev, 1); + if (err) + goto err_set_slave_promisc; + } + + /* set allmulti level to new slave */ + if (dev->flags & IFF_ALLMULTI) { + err = dev_set_allmulti(port_dev, 1); + if (err) { + if (dev->flags & IFF_PROMISC) + dev_set_promiscuity(port_dev, -1); + goto err_set_slave_promisc; + } + } + netif_addr_lock_bh(dev); dev_uc_sync_multiple(port_dev, dev); dev_mc_sync_multiple(port_dev, dev); @@ -1262,6 +1286,9 @@ static int team_port_add(struct team *team, struct net_device *port_dev, return 0; +err_set_slave_promisc: + __team_option_inst_del_port(team, port); + err_option_port_add: team_upper_dev_unlink(team, port); @@ -1307,6 +1334,12 @@ static int team_port_del(struct team *team, struct net_device *port_dev) team_port_disable(team, port); list_del_rcu(&port->list); + + if (dev->flags & IFF_PROMISC) + dev_set_promiscuity(port_dev, -1); + if (dev->flags & IFF_ALLMULTI) + dev_set_allmulti(port_dev, -1); + team_upper_dev_unlink(team, port); netdev_rx_handler_unregister(port_dev); team_port_disable_netpoll(port); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 1d68921723dc..e9ca1c088d0b 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1763,9 +1763,6 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, int skb_xdp = 1; bool frags = tun_napi_frags_enabled(tfile); - if (!(tun->dev->flags & IFF_UP)) - return -EIO; - if (!(tun->flags & IFF_NO_PI)) { if (len < sizeof(pi)) return -EINVAL; @@ -1867,6 +1864,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, err = skb_copy_datagram_from_iter(skb, 0, from, len); if (err) { + err = -EFAULT; +drop: this_cpu_inc(tun->pcpu_stats->rx_dropped); kfree_skb(skb); if (frags) { @@ -1874,7 +1873,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, mutex_unlock(&tfile->napi_mutex); } - return -EFAULT; + return err; } } @@ -1958,6 +1957,13 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, !tfile->detached) rxhash = __skb_get_hash_symmetric(skb); + rcu_read_lock(); + if (unlikely(!(tun->dev->flags & IFF_UP))) { + err = -EIO; + rcu_read_unlock(); + goto drop; + } + if (frags) { /* Exercise flow dissector code path. */ u32 headlen = eth_get_headlen(skb->data, skb_headlen(skb)); @@ -1965,6 +1971,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, if (unlikely(headlen > skb_headlen(skb))) { this_cpu_inc(tun->pcpu_stats->rx_dropped); napi_free_frags(&tfile->napi); + rcu_read_unlock(); mutex_unlock(&tfile->napi_mutex); WARN_ON(1); return -ENOMEM; @@ -1992,6 +1999,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, } else { netif_rx_ni(skb); } + rcu_read_unlock(); stats = get_cpu_ptr(tun->pcpu_stats); u64_stats_update_begin(&stats->syncp); diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c index 820a2fe7d027..aff995be2a31 100644 --- a/drivers/net/usb/aqc111.c +++ b/drivers/net/usb/aqc111.c @@ -1301,6 +1301,20 @@ static const struct driver_info trendnet_info = { .tx_fixup = aqc111_tx_fixup, }; +static const struct driver_info qnap_info = { + .description = "QNAP QNA-UC5G1T USB to 5GbE Adapter", + .bind = aqc111_bind, + .unbind = aqc111_unbind, + .status = aqc111_status, + .link_reset = aqc111_link_reset, + .reset = aqc111_reset, + .stop = aqc111_stop, + .flags = FLAG_ETHER | FLAG_FRAMING_AX | + FLAG_AVOID_UNLINK_URBS | FLAG_MULTI_PACKET, + .rx_fixup = aqc111_rx_fixup, + .tx_fixup = aqc111_tx_fixup, +}; + static int aqc111_suspend(struct usb_interface *intf, pm_message_t message) { struct usbnet *dev = usb_get_intfdata(intf); @@ -1455,6 +1469,7 @@ static const struct usb_device_id products[] = { {AQC111_USB_ETH_DEV(0x0b95, 0x2790, asix111_info)}, {AQC111_USB_ETH_DEV(0x0b95, 0x2791, asix112_info)}, {AQC111_USB_ETH_DEV(0x20f4, 0xe05a, trendnet_info)}, + {AQC111_USB_ETH_DEV(0x1c04, 0x0015, qnap_info)}, { },/* END */ }; MODULE_DEVICE_TABLE(usb, products); diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 5512a1038721..3e9b2c319e45 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -851,6 +851,14 @@ static const struct usb_device_id products[] = { .driver_info = 0, }, +/* QNAP QNA-UC5G1T USB to 5GbE Adapter (based on AQC111U) */ +{ + USB_DEVICE_AND_INTERFACE_INFO(0x1c04, 0x0015, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, + USB_CDC_PROTO_NONE), + .driver_info = 0, +}, + /* WHITELIST!!! * * CDC Ether uses two interfaces, not necessarily consecutive. diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 74bebbdb4b15..679e404a5224 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1122,9 +1122,16 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x0846, 0x68d3, 8)}, /* Netgear Aircard 779S */ {QMI_FIXED_INTF(0x12d1, 0x140c, 1)}, /* Huawei E173 */ {QMI_FIXED_INTF(0x12d1, 0x14ac, 1)}, /* Huawei E1820 */ + {QMI_FIXED_INTF(0x1435, 0x0918, 3)}, /* Wistron NeWeb D16Q1 */ + {QMI_FIXED_INTF(0x1435, 0x0918, 4)}, /* Wistron NeWeb D16Q1 */ + {QMI_FIXED_INTF(0x1435, 0x0918, 5)}, /* Wistron NeWeb D16Q1 */ + {QMI_FIXED_INTF(0x1435, 0x3185, 4)}, /* Wistron NeWeb M18Q5 */ + {QMI_FIXED_INTF(0x1435, 0xd111, 4)}, /* M9615A DM11-1 D51QC */ {QMI_FIXED_INTF(0x1435, 0xd181, 3)}, /* Wistron NeWeb D18Q1 */ {QMI_FIXED_INTF(0x1435, 0xd181, 4)}, /* Wistron NeWeb D18Q1 */ {QMI_FIXED_INTF(0x1435, 0xd181, 5)}, /* Wistron NeWeb D18Q1 */ + {QMI_FIXED_INTF(0x1435, 0xd182, 4)}, /* Wistron NeWeb D18 */ + {QMI_FIXED_INTF(0x1435, 0xd182, 5)}, /* Wistron NeWeb D18 */ {QMI_FIXED_INTF(0x1435, 0xd191, 4)}, /* Wistron NeWeb D19Q1 */ {QMI_QUIRK_SET_DTR(0x1508, 0x1001, 4)}, /* Fibocom NL668 series */ {QMI_FIXED_INTF(0x16d8, 0x6003, 0)}, /* CMOTech 6003 */ @@ -1180,6 +1187,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x19d2, 0x0265, 4)}, /* ONDA MT8205 4G LTE */ {QMI_FIXED_INTF(0x19d2, 0x0284, 4)}, /* ZTE MF880 */ {QMI_FIXED_INTF(0x19d2, 0x0326, 4)}, /* ZTE MF821D */ + {QMI_FIXED_INTF(0x19d2, 0x0396, 3)}, /* ZTE ZM8620 */ {QMI_FIXED_INTF(0x19d2, 0x0412, 4)}, /* Telewell TW-LTE 4G */ {QMI_FIXED_INTF(0x19d2, 0x1008, 4)}, /* ZTE (Vodafone) K3570-Z */ {QMI_FIXED_INTF(0x19d2, 0x1010, 4)}, /* ZTE (Vodafone) K3571-Z */ @@ -1200,9 +1208,12 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x19d2, 0x1425, 2)}, {QMI_FIXED_INTF(0x19d2, 0x1426, 2)}, /* ZTE MF91 */ {QMI_FIXED_INTF(0x19d2, 0x1428, 2)}, /* Telewell TW-LTE 4G v2 */ + {QMI_FIXED_INTF(0x19d2, 0x1432, 3)}, /* ZTE ME3620 */ {QMI_FIXED_INTF(0x19d2, 0x2002, 4)}, /* ZTE (Vodafone) K3765-Z */ + {QMI_FIXED_INTF(0x2001, 0x7e16, 3)}, /* D-Link DWM-221 */ {QMI_FIXED_INTF(0x2001, 0x7e19, 4)}, /* D-Link DWM-221 B1 */ {QMI_FIXED_INTF(0x2001, 0x7e35, 4)}, /* D-Link DWM-222 */ + {QMI_FIXED_INTF(0x2020, 0x2031, 4)}, /* Olicard 600 */ {QMI_FIXED_INTF(0x2020, 0x2033, 4)}, /* BroadMobi BM806U */ {QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)}, /* Sierra Wireless MC7700 */ {QMI_FIXED_INTF(0x114f, 0x68a2, 8)}, /* Sierra Wireless MC7750 */ diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 7c1430ed0244..9ee4d7402ca2 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -875,6 +875,7 @@ static const struct net_device_ops vrf_netdev_ops = { .ndo_init = vrf_dev_init, .ndo_uninit = vrf_dev_uninit, .ndo_start_xmit = vrf_xmit, + .ndo_set_mac_address = eth_mac_addr, .ndo_get_stats64 = vrf_get_stats64, .ndo_add_slave = vrf_add_slave, .ndo_del_slave = vrf_del_slave, @@ -1273,9 +1274,15 @@ static void vrf_setup(struct net_device *dev) /* default to no qdisc; user can add if desired */ dev->priv_flags |= IFF_NO_QUEUE; + dev->priv_flags |= IFF_NO_RX_HANDLER; + dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; - dev->min_mtu = 0; - dev->max_mtu = 0; + /* VRF devices do not care about MTU, but if the MTU is set + * too low then the ipv4 and ipv6 protocols are disabled + * which breaks networking. + */ + dev->min_mtu = IPV6_MIN_MTU; + dev->max_mtu = ETH_MAX_MTU; } static int vrf_validate(struct nlattr *tb[], struct nlattr *data[], diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 077f1b9f2761..d76dfed8d9bb 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -4335,10 +4335,8 @@ static void vxlan_destroy_tunnels(struct net *net, struct list_head *head) /* If vxlan->dev is in the same netns, it has already been added * to the list by the previous loop. */ - if (!net_eq(dev_net(vxlan->dev), net)) { - gro_cells_destroy(&vxlan->gro_cells); + if (!net_eq(dev_net(vxlan->dev), net)) unregister_netdevice_queue(vxlan->dev, head); - } } for (h = 0; h < PORT_HASH_SIZE; ++h) diff --git a/drivers/net/wireless/ath/ath10k/ce.c b/drivers/net/wireless/ath/ath10k/ce.c index 24b983edb357..eca87f7c5b6c 100644 --- a/drivers/net/wireless/ath/ath10k/ce.c +++ b/drivers/net/wireless/ath/ath10k/ce.c @@ -1855,7 +1855,7 @@ void ath10k_ce_dump_registers(struct ath10k *ar, struct ath10k_ce_crash_data ce_data; u32 addr, id; - lockdep_assert_held(&ar->data_lock); + lockdep_assert_held(&ar->dump_mutex); ath10k_err(ar, "Copy Engine register dump:\n"); diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c index 835b8de92d55..aff585658fc0 100644 --- a/drivers/net/wireless/ath/ath10k/core.c +++ b/drivers/net/wireless/ath/ath10k/core.c @@ -3119,6 +3119,7 @@ struct ath10k *ath10k_core_create(size_t priv_size, struct device *dev, goto err_free_wq; mutex_init(&ar->conf_mutex); + mutex_init(&ar->dump_mutex); spin_lock_init(&ar->data_lock); INIT_LIST_HEAD(&ar->peers); diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h index e08a17b01e03..e35aae5146f1 100644 --- a/drivers/net/wireless/ath/ath10k/core.h +++ b/drivers/net/wireless/ath/ath10k/core.h @@ -1063,6 +1063,9 @@ struct ath10k { /* prevents concurrent FW reconfiguration */ struct mutex conf_mutex; + /* protects coredump data */ + struct mutex dump_mutex; + /* protects shared structure data */ spinlock_t data_lock; diff --git a/drivers/net/wireless/ath/ath10k/coredump.c b/drivers/net/wireless/ath/ath10k/coredump.c index 33838d9c1cb6..45a355fb62b9 100644 --- a/drivers/net/wireless/ath/ath10k/coredump.c +++ b/drivers/net/wireless/ath/ath10k/coredump.c @@ -1102,7 +1102,7 @@ struct ath10k_fw_crash_data *ath10k_coredump_new(struct ath10k *ar) { struct ath10k_fw_crash_data *crash_data = ar->coredump.fw_crash_data; - lockdep_assert_held(&ar->data_lock); + lockdep_assert_held(&ar->dump_mutex); if (ath10k_coredump_mask == 0) /* coredump disabled */ @@ -1146,7 +1146,7 @@ static struct ath10k_dump_file_data *ath10k_coredump_build(struct ath10k *ar) if (!buf) return NULL; - spin_lock_bh(&ar->data_lock); + mutex_lock(&ar->dump_mutex); dump_data = (struct ath10k_dump_file_data *)(buf); strlcpy(dump_data->df_magic, "ATH10K-FW-DUMP", @@ -1213,7 +1213,7 @@ static struct ath10k_dump_file_data *ath10k_coredump_build(struct ath10k *ar) sofar += sizeof(*dump_tlv) + crash_data->ramdump_buf_len; } - spin_unlock_bh(&ar->data_lock); + mutex_unlock(&ar->dump_mutex); return dump_data; } diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c index a20ea270d519..1acc622d2183 100644 --- a/drivers/net/wireless/ath/ath10k/htt_rx.c +++ b/drivers/net/wireless/ath/ath10k/htt_rx.c @@ -2728,7 +2728,7 @@ static void ath10k_htt_rx_tx_fetch_ind(struct ath10k *ar, struct sk_buff *skb) num_msdus++; num_bytes += ret; } - ieee80211_return_txq(hw, txq); + ieee80211_return_txq(hw, txq, false); ieee80211_txq_schedule_end(hw, txq->ac); record->num_msdus = cpu_to_le16(num_msdus); diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c index b73c23d4ce86..9c703d287333 100644 --- a/drivers/net/wireless/ath/ath10k/mac.c +++ b/drivers/net/wireless/ath/ath10k/mac.c @@ -4089,7 +4089,7 @@ static int ath10k_mac_schedule_txq(struct ieee80211_hw *hw, u32 ac) if (ret < 0) break; } - ieee80211_return_txq(hw, txq); + ieee80211_return_txq(hw, txq, false); ath10k_htt_tx_txq_update(hw, txq); if (ret == -EBUSY) break; @@ -4374,7 +4374,7 @@ static void ath10k_mac_op_wake_tx_queue(struct ieee80211_hw *hw, if (ret < 0) break; } - ieee80211_return_txq(hw, txq); + ieee80211_return_txq(hw, txq, false); ath10k_htt_tx_txq_update(hw, txq); out: ieee80211_txq_schedule_end(hw, ac); @@ -5774,7 +5774,7 @@ static void ath10k_bss_info_changed(struct ieee80211_hw *hw, } if (changed & BSS_CHANGED_MCAST_RATE && - !WARN_ON(ath10k_mac_vif_chan(arvif->vif, &def))) { + !ath10k_mac_vif_chan(arvif->vif, &def)) { band = def.chan->band; rateidx = vif->bss_conf.mcast_rate[band] - 1; @@ -5812,7 +5812,7 @@ static void ath10k_bss_info_changed(struct ieee80211_hw *hw, } if (changed & BSS_CHANGED_BASIC_RATES) { - if (WARN_ON(ath10k_mac_vif_chan(vif, &def))) { + if (ath10k_mac_vif_chan(vif, &def)) { mutex_unlock(&ar->conf_mutex); return; } diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c index 271f92c24d44..2c27f407a851 100644 --- a/drivers/net/wireless/ath/ath10k/pci.c +++ b/drivers/net/wireless/ath/ath10k/pci.c @@ -1441,7 +1441,7 @@ static void ath10k_pci_dump_registers(struct ath10k *ar, __le32 reg_dump_values[REG_DUMP_COUNT_QCA988X] = {}; int i, ret; - lockdep_assert_held(&ar->data_lock); + lockdep_assert_held(&ar->dump_mutex); ret = ath10k_pci_diag_read_hi(ar, ®_dump_values[0], hi_failure_state, @@ -1656,7 +1656,7 @@ static void ath10k_pci_dump_memory(struct ath10k *ar, int ret, i; u8 *buf; - lockdep_assert_held(&ar->data_lock); + lockdep_assert_held(&ar->dump_mutex); if (!crash_data) return; @@ -1734,14 +1734,19 @@ static void ath10k_pci_dump_memory(struct ath10k *ar, } } -static void ath10k_pci_fw_crashed_dump(struct ath10k *ar) +static void ath10k_pci_fw_dump_work(struct work_struct *work) { + struct ath10k_pci *ar_pci = container_of(work, struct ath10k_pci, + dump_work); struct ath10k_fw_crash_data *crash_data; + struct ath10k *ar = ar_pci->ar; char guid[UUID_STRING_LEN + 1]; - spin_lock_bh(&ar->data_lock); + mutex_lock(&ar->dump_mutex); + spin_lock_bh(&ar->data_lock); ar->stats.fw_crash_counter++; + spin_unlock_bh(&ar->data_lock); crash_data = ath10k_coredump_new(ar); @@ -1756,11 +1761,18 @@ static void ath10k_pci_fw_crashed_dump(struct ath10k *ar) ath10k_ce_dump_registers(ar, crash_data); ath10k_pci_dump_memory(ar, crash_data); - spin_unlock_bh(&ar->data_lock); + mutex_unlock(&ar->dump_mutex); queue_work(ar->workqueue, &ar->restart_work); } +static void ath10k_pci_fw_crashed_dump(struct ath10k *ar) +{ + struct ath10k_pci *ar_pci = ath10k_pci_priv(ar); + + queue_work(ar->workqueue, &ar_pci->dump_work); +} + void ath10k_pci_hif_send_complete_check(struct ath10k *ar, u8 pipe, int force) { @@ -3442,6 +3454,8 @@ int ath10k_pci_setup_resource(struct ath10k *ar) spin_lock_init(&ar_pci->ps_lock); mutex_init(&ar_pci->ce_diag_mutex); + INIT_WORK(&ar_pci->dump_work, ath10k_pci_fw_dump_work); + timer_setup(&ar_pci->rx_post_retry, ath10k_pci_rx_replenish_retry, 0); if (QCA_REV_6174(ar) || QCA_REV_9377(ar)) diff --git a/drivers/net/wireless/ath/ath10k/pci.h b/drivers/net/wireless/ath/ath10k/pci.h index 3773c79f322f..4455ed6c5275 100644 --- a/drivers/net/wireless/ath/ath10k/pci.h +++ b/drivers/net/wireless/ath/ath10k/pci.h @@ -121,6 +121,8 @@ struct ath10k_pci { /* For protecting ce_diag */ struct mutex ce_diag_mutex; + struct work_struct dump_work; + struct ath10k_ce ce; struct timer_list rx_post_retry; diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c index 773d428ff1b0..b17e1ca40995 100644 --- a/drivers/net/wireless/ath/ath9k/xmit.c +++ b/drivers/net/wireless/ath/ath9k/xmit.c @@ -1938,12 +1938,15 @@ void ath_txq_schedule(struct ath_softc *sc, struct ath_txq *txq) goto out; while ((queue = ieee80211_next_txq(hw, txq->mac80211_qnum))) { + bool force; + tid = (struct ath_atx_tid *)queue->drv_priv; ret = ath_tx_sched_aggr(sc, txq, tid); ath_dbg(common, QUEUE, "ath_tx_sched_aggr returned %d\n", ret); - ieee80211_return_txq(hw, queue); + force = !skb_queue_empty(&tid->retry_q); + ieee80211_return_txq(hw, queue, force); } out: diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c index fdc56f821b5a..0a87d87fbb4f 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c @@ -82,6 +82,7 @@ #define IWL_22000_HR_A0_FW_PRE "iwlwifi-QuQnj-a0-hr-a0-" #define IWL_22000_SU_Z0_FW_PRE "iwlwifi-su-z0-" #define IWL_QU_B_JF_B_FW_PRE "iwlwifi-Qu-b0-jf-b0-" +#define IWL_QUZ_A_HR_B_FW_PRE "iwlwifi-QuZ-a0-hr-b0-" #define IWL_QNJ_B_JF_B_FW_PRE "iwlwifi-QuQnj-b0-jf-b0-" #define IWL_CC_A_FW_PRE "iwlwifi-cc-a0-" #define IWL_22000_SO_A_JF_B_FW_PRE "iwlwifi-so-a0-jf-b0-" @@ -105,8 +106,8 @@ IWL_22000_HR_A0_FW_PRE __stringify(api) ".ucode" #define IWL_22000_SU_Z0_MODULE_FIRMWARE(api) \ IWL_22000_SU_Z0_FW_PRE __stringify(api) ".ucode" -#define IWL_QU_B_JF_B_MODULE_FIRMWARE(api) \ - IWL_QU_B_JF_B_FW_PRE __stringify(api) ".ucode" +#define IWL_QUZ_A_HR_B_MODULE_FIRMWARE(api) \ + IWL_QUZ_A_HR_B_FW_PRE __stringify(api) ".ucode" #define IWL_QU_B_JF_B_MODULE_FIRMWARE(api) \ IWL_QU_B_JF_B_FW_PRE __stringify(api) ".ucode" #define IWL_QNJ_B_JF_B_MODULE_FIRMWARE(api) \ @@ -200,7 +201,7 @@ static const struct iwl_ht_params iwl_22000_ht_params = { #define IWL_DEVICE_AX210 \ IWL_DEVICE_AX200_COMMON, \ .device_family = IWL_DEVICE_FAMILY_AX210, \ - .base_params = &iwl_22000_base_params, \ + .base_params = &iwl_22560_base_params, \ .csr = &iwl_csr_v1, \ .min_txq_size = 128 @@ -235,8 +236,20 @@ const struct iwl_cfg iwl_ax101_cfg_qu_hr = { .max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT, }; -const struct iwl_cfg iwl22260_2ax_cfg = { - .name = "Intel(R) Wireless-AX 22260", +const struct iwl_cfg iwl_ax101_cfg_quz_hr = { + .name = "Intel(R) Wi-Fi 6 AX101", + .fw_name_pre = IWL_QUZ_A_HR_B_FW_PRE, + IWL_DEVICE_22500, + /* + * This device doesn't support receiving BlockAck with a large bitmap + * so we need to restrict the size of transmitted aggregation to the + * HT size; mac80211 would otherwise pick the HE max (256) by default. + */ + .max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT, +}; + +const struct iwl_cfg iwl_ax200_cfg_cc = { + .name = "Intel(R) Wi-Fi 6 AX200 160MHz", .fw_name_pre = IWL_CC_A_FW_PRE, IWL_DEVICE_22500, /* @@ -249,7 +262,7 @@ const struct iwl_cfg iwl22260_2ax_cfg = { }; const struct iwl_cfg killer1650x_2ax_cfg = { - .name = "Killer(R) Wireless-AX 1650x Wireless Network Adapter (200NGW)", + .name = "Killer(R) Wi-Fi 6 AX1650x 160MHz Wireless Network Adapter (200NGW)", .fw_name_pre = IWL_CC_A_FW_PRE, IWL_DEVICE_22500, /* @@ -262,7 +275,7 @@ const struct iwl_cfg killer1650x_2ax_cfg = { }; const struct iwl_cfg killer1650w_2ax_cfg = { - .name = "Killer(R) Wireless-AX 1650w Wireless Network Adapter (200D2W)", + .name = "Killer(R) Wi-Fi 6 AX1650w 160MHz Wireless Network Adapter (200D2W)", .fw_name_pre = IWL_CC_A_FW_PRE, IWL_DEVICE_22500, /* @@ -328,7 +341,7 @@ const struct iwl_cfg killer1550s_2ac_cfg_qu_b0_jf_b0 = { }; const struct iwl_cfg killer1650s_2ax_cfg_qu_b0_hr_b0 = { - .name = "Killer(R) Wireless-AX 1650i Wireless Network Adapter (22560NGW)", + .name = "Killer(R) Wi-Fi 6 AX1650i 160MHz Wireless Network Adapter (201NGW)", .fw_name_pre = IWL_22000_QU_B_HR_B_FW_PRE, IWL_DEVICE_22500, /* @@ -340,7 +353,7 @@ const struct iwl_cfg killer1650s_2ax_cfg_qu_b0_hr_b0 = { }; const struct iwl_cfg killer1650i_2ax_cfg_qu_b0_hr_b0 = { - .name = "Killer(R) Wireless-AX 1650s Wireless Network Adapter (22560D2W)", + .name = "Killer(R) Wi-Fi 6 AX1650s 160MHz Wireless Network Adapter (201D2W)", .fw_name_pre = IWL_22000_QU_B_HR_B_FW_PRE, IWL_DEVICE_22500, /* @@ -444,6 +457,7 @@ MODULE_FIRMWARE(IWL_22000_HR_B_QNJ_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_22000_HR_A0_QNJ_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_22000_SU_Z0_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_QU_B_JF_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); +MODULE_FIRMWARE(IWL_QUZ_A_HR_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_QNJ_B_JF_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_CC_A_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_22000_SO_A_JF_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/5000.c b/drivers/net/wireless/intel/iwlwifi/cfg/5000.c index 575a7022d045..3846064d51a5 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/5000.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/5000.c @@ -1,7 +1,7 @@ /****************************************************************************** * * Copyright(c) 2007 - 2014 Intel Corporation. All rights reserved. - * Copyright(c) 2018 Intel Corporation + * Copyright(c) 2018 - 2019 Intel Corporation * * This program is free software; you can redistribute it and/or modify it * under the terms of version 2 of the GNU General Public License as @@ -136,6 +136,7 @@ const struct iwl_cfg iwl5350_agn_cfg = { .ht_params = &iwl5000_ht_params, .led_mode = IWL_LED_BLINK, .internal_wimax_coex = true, + .csr = &iwl_csr_v1, }; #define IWL_DEVICE_5150 \ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c index f119c49cd39c..d7380016f1c0 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c @@ -1614,6 +1614,7 @@ iwl_dump_ini_mem(struct iwl_fw_runtime *fwrt, if (!range) { IWL_ERR(fwrt, "Failed to fill region header: id=%d, type=%d\n", le32_to_cpu(reg->region_id), type); + memset(*data, 0, le32_to_cpu((*data)->len)); return; } @@ -1623,6 +1624,7 @@ iwl_dump_ini_mem(struct iwl_fw_runtime *fwrt, if (range_size < 0) { IWL_ERR(fwrt, "Failed to dump region: id=%d, type=%d\n", le32_to_cpu(reg->region_id), type); + memset(*data, 0, le32_to_cpu((*data)->len)); return; } range = range + range_size; @@ -1807,12 +1809,12 @@ _iwl_fw_error_ini_dump(struct iwl_fw_runtime *fwrt, trigger = fwrt->dump.active_trigs[id].trig; - size = sizeof(*dump_file); - size += iwl_fw_ini_get_trigger_len(fwrt, trigger); - + size = iwl_fw_ini_get_trigger_len(fwrt, trigger); if (!size) return NULL; + size += sizeof(*dump_file); + dump_file = vzalloc(size); if (!dump_file) return NULL; @@ -1942,14 +1944,10 @@ int iwl_fw_dbg_error_collect(struct iwl_fw_runtime *fwrt, iwl_dump_error_desc->len = 0; ret = iwl_fw_dbg_collect_desc(fwrt, iwl_dump_error_desc, false, 0); - if (ret) { + if (ret) kfree(iwl_dump_error_desc); - } else { - set_bit(STATUS_FW_WAIT_DUMP, &fwrt->trans->status); - - /* trigger nmi to halt the fw */ - iwl_force_nmi(fwrt->trans); - } + else + iwl_trans_sync_nmi(fwrt->trans); return ret; } @@ -2489,22 +2487,6 @@ IWL_EXPORT_SYMBOL(iwl_fw_dbg_apply_point); void iwl_fwrt_stop_device(struct iwl_fw_runtime *fwrt) { - /* if the wait event timeout elapses instead of wake up then - * the driver did not receive NMI interrupt and can not assume the FW - * is halted - */ - int ret = wait_event_timeout(fwrt->trans->fw_halt_waitq, - !test_bit(STATUS_FW_WAIT_DUMP, - &fwrt->trans->status), - msecs_to_jiffies(2000)); - if (!ret) { - /* failed to receive NMI interrupt, assuming the FW is stuck */ - set_bit(STATUS_FW_ERROR, &fwrt->trans->status); - - clear_bit(STATUS_FW_WAIT_DUMP, &fwrt->trans->status); - } - - /* Assuming the op mode mutex is held at this point */ iwl_fw_dbg_collect_sync(fwrt); iwl_trans_stop_device(fwrt->trans); diff --git a/drivers/net/wireless/intel/iwlwifi/fw/file.h b/drivers/net/wireless/intel/iwlwifi/fw/file.h index 641c95d03b15..e06407dc088b 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/file.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/file.h @@ -93,7 +93,7 @@ struct iwl_ucode_header { } u; }; -#define IWL_UCODE_INI_TLV_GROUP BIT(24) +#define IWL_UCODE_INI_TLV_GROUP 0x1000000 /* * new TLV uCode file layout @@ -148,11 +148,14 @@ enum iwl_ucode_tlv_type { IWL_UCODE_TLV_UMAC_DEBUG_ADDRS = 54, IWL_UCODE_TLV_LMAC_DEBUG_ADDRS = 55, IWL_UCODE_TLV_FW_RECOVERY_INFO = 57, - IWL_UCODE_TLV_TYPE_BUFFER_ALLOCATION = IWL_UCODE_INI_TLV_GROUP | 0x1, - IWL_UCODE_TLV_TYPE_HCMD = IWL_UCODE_INI_TLV_GROUP | 0x2, - IWL_UCODE_TLV_TYPE_REGIONS = IWL_UCODE_INI_TLV_GROUP | 0x3, - IWL_UCODE_TLV_TYPE_TRIGGERS = IWL_UCODE_INI_TLV_GROUP | 0x4, - IWL_UCODE_TLV_TYPE_DEBUG_FLOW = IWL_UCODE_INI_TLV_GROUP | 0x5, + + IWL_UCODE_TLV_TYPE_BUFFER_ALLOCATION = IWL_UCODE_INI_TLV_GROUP + 0x1, + IWL_UCODE_TLV_DEBUG_BASE = IWL_UCODE_TLV_TYPE_BUFFER_ALLOCATION, + IWL_UCODE_TLV_TYPE_HCMD = IWL_UCODE_INI_TLV_GROUP + 0x2, + IWL_UCODE_TLV_TYPE_REGIONS = IWL_UCODE_INI_TLV_GROUP + 0x3, + IWL_UCODE_TLV_TYPE_TRIGGERS = IWL_UCODE_INI_TLV_GROUP + 0x4, + IWL_UCODE_TLV_TYPE_DEBUG_FLOW = IWL_UCODE_INI_TLV_GROUP + 0x5, + IWL_UCODE_TLV_DEBUG_MAX = IWL_UCODE_TLV_TYPE_DEBUG_FLOW, /* TLVs 0x1000-0x2000 are for internal driver usage */ IWL_UCODE_TLV_FW_DBG_DUMP_LST = 0x1000, diff --git a/drivers/net/wireless/intel/iwlwifi/fw/init.c b/drivers/net/wireless/intel/iwlwifi/fw/init.c index 7adf4e4e841a..12310e3d2fc5 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/init.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/init.c @@ -76,7 +76,6 @@ void iwl_fw_runtime_init(struct iwl_fw_runtime *fwrt, struct iwl_trans *trans, fwrt->ops_ctx = ops_ctx; INIT_DELAYED_WORK(&fwrt->dump.wk, iwl_fw_error_dump_wk); iwl_fwrt_dbgfs_register(fwrt, dbgfs_dir); - init_waitqueue_head(&fwrt->trans->fw_halt_waitq); } IWL_EXPORT_SYMBOL(iwl_fw_runtime_init); diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h index f5f87773667b..93070848280a 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h @@ -549,8 +549,9 @@ extern const struct iwl_cfg iwl22000_2ac_cfg_hr; extern const struct iwl_cfg iwl22000_2ac_cfg_hr_cdb; extern const struct iwl_cfg iwl22000_2ac_cfg_jf; extern const struct iwl_cfg iwl_ax101_cfg_qu_hr; +extern const struct iwl_cfg iwl_ax101_cfg_quz_hr; extern const struct iwl_cfg iwl22000_2ax_cfg_hr; -extern const struct iwl_cfg iwl22260_2ax_cfg; +extern const struct iwl_cfg iwl_ax200_cfg_cc; extern const struct iwl_cfg killer1650s_2ax_cfg_qu_b0_hr_b0; extern const struct iwl_cfg killer1650i_2ax_cfg_qu_b0_hr_b0; extern const struct iwl_cfg killer1650x_2ax_cfg; diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h index aea6d03e545a..e539bc94eff7 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h @@ -327,6 +327,7 @@ enum { #define CSR_HW_REV_TYPE_NONE (0x00001F0) #define CSR_HW_REV_TYPE_QNJ (0x0000360) #define CSR_HW_REV_TYPE_QNJ_B0 (0x0000364) +#define CSR_HW_REV_TYPE_QUZ (0x0000354) #define CSR_HW_REV_TYPE_HR_CDB (0x0000340) #define CSR_HW_REV_TYPE_SO (0x0000370) #define CSR_HW_REV_TYPE_TY (0x0000420) diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c index 5798f434f68f..c7070760a10a 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c @@ -126,7 +126,8 @@ void iwl_alloc_dbg_tlv(struct iwl_trans *trans, size_t len, const u8 *data, len -= ALIGN(tlv_len, 4); data += sizeof(*tlv) + ALIGN(tlv_len, 4); - if (!(tlv_type & IWL_UCODE_INI_TLV_GROUP)) + if (tlv_type < IWL_UCODE_TLV_DEBUG_BASE || + tlv_type > IWL_UCODE_TLV_DEBUG_MAX) continue; hdr = (void *)&tlv->data[0]; diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h index bbebbf3efd57..d8690acee40c 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h @@ -338,7 +338,6 @@ enum iwl_d3_status { * are sent * @STATUS_TRANS_IDLE: the trans is idle - general commands are not to be sent * @STATUS_TRANS_DEAD: trans is dead - avoid any read/write operation - * @STATUS_FW_WAIT_DUMP: if set, wait until cleared before collecting dump */ enum iwl_trans_status { STATUS_SYNC_HCMD_ACTIVE, @@ -351,7 +350,6 @@ enum iwl_trans_status { STATUS_TRANS_GOING_IDLE, STATUS_TRANS_IDLE, STATUS_TRANS_DEAD, - STATUS_FW_WAIT_DUMP, }; static inline int @@ -618,6 +616,7 @@ struct iwl_trans_ops { struct iwl_trans_dump_data *(*dump_data)(struct iwl_trans *trans, u32 dump_mask); void (*debugfs_cleanup)(struct iwl_trans *trans); + void (*sync_nmi)(struct iwl_trans *trans); }; /** @@ -831,7 +830,6 @@ struct iwl_trans { u32 lmac_error_event_table[2]; u32 umac_error_event_table; unsigned int error_event_table_tlv_status; - wait_queue_head_t fw_halt_waitq; /* pointer to trans specific struct */ /*Ensure that this pointer will always be aligned to sizeof pointer */ @@ -1239,10 +1237,12 @@ static inline void iwl_trans_fw_error(struct iwl_trans *trans) /* prevent double restarts due to the same erroneous FW */ if (!test_and_set_bit(STATUS_FW_ERROR, &trans->status)) iwl_op_mode_nic_error(trans->op_mode); +} - if (test_and_clear_bit(STATUS_FW_WAIT_DUMP, &trans->status)) - wake_up(&trans->fw_halt_waitq); - +static inline void iwl_trans_sync_nmi(struct iwl_trans *trans) +{ + if (trans->ops->sync_nmi) + trans->ops->sync_nmi(trans); } /***************************************************** diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c index 2453ceabf00d..6925527d8457 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c @@ -774,8 +774,7 @@ void iwl_mvm_vif_dbgfs_register(struct iwl_mvm *mvm, struct ieee80211_vif *vif) return; mvmvif->dbgfs_dir = debugfs_create_dir("iwlmvm", dbgfs_dir); - - if (!mvmvif->dbgfs_dir) { + if (IS_ERR_OR_NULL(mvmvif->dbgfs_dir)) { IWL_ERR(mvm, "Failed to create debugfs directory under %pd\n", dbgfs_dir); return; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c index e9822a3ec373..94132cfd1f56 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c @@ -460,9 +460,7 @@ static int iwl_mvm_ftm_range_resp_valid(struct iwl_mvm *mvm, u8 request_id, static void iwl_mvm_debug_range_resp(struct iwl_mvm *mvm, u8 index, struct cfg80211_pmsr_result *res) { - s64 rtt_avg = res->ftm.rtt_avg * 100; - - do_div(rtt_avg, 6666); + s64 rtt_avg = div_s64(res->ftm.rtt_avg * 100, 6666); IWL_DEBUG_INFO(mvm, "entry %d\n", index); IWL_DEBUG_INFO(mvm, "\tstatus: %d\n", res->status); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index 00a47f6f1d81..ab68b5d53ec9 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -1121,7 +1121,9 @@ int iwl_mvm_up(struct iwl_mvm *mvm) ret = iwl_mvm_load_rt_fw(mvm); if (ret) { IWL_ERR(mvm, "Failed to start RT ucode: %d\n", ret); - iwl_fw_dbg_error_collect(&mvm->fwrt, FW_DBG_TRIGGER_DRIVER); + if (ret != -ERFKILL) + iwl_fw_dbg_error_collect(&mvm->fwrt, + FW_DBG_TRIGGER_DRIVER); goto error; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 3a92c09d4692..6a3b11dd2edf 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -2714,9 +2714,6 @@ static void iwl_mvm_stop_ap_ibss(struct ieee80211_hw *hw, iwl_mvm_mac_ctxt_remove(mvm, vif); - kfree(mvmvif->ap_wep_key); - mvmvif->ap_wep_key = NULL; - mutex_unlock(&mvm->mutex); } @@ -3183,24 +3180,7 @@ static int iwl_mvm_mac_sta_state(struct ieee80211_hw *hw, ret = iwl_mvm_update_sta(mvm, vif, sta); } else if (old_state == IEEE80211_STA_ASSOC && new_state == IEEE80211_STA_AUTHORIZED) { - /* if wep is used, need to set the key for the station now */ - if (vif->type == NL80211_IFTYPE_AP && mvmvif->ap_wep_key) { - mvm_sta->wep_key = - kmemdup(mvmvif->ap_wep_key, - sizeof(*mvmvif->ap_wep_key) + - mvmvif->ap_wep_key->keylen, - GFP_KERNEL); - if (!mvm_sta->wep_key) { - ret = -ENOMEM; - goto out_unlock; - } - - ret = iwl_mvm_set_sta_key(mvm, vif, sta, - mvm_sta->wep_key, - STA_KEY_IDX_INVALID); - } else { - ret = 0; - } + ret = 0; /* we don't support TDLS during DCM */ if (iwl_mvm_phy_ctx_count(mvm) > 1) @@ -3242,17 +3222,6 @@ static int iwl_mvm_mac_sta_state(struct ieee80211_hw *hw, NL80211_TDLS_DISABLE_LINK); } - /* Remove STA key if this is an AP using WEP */ - if (vif->type == NL80211_IFTYPE_AP && mvmvif->ap_wep_key) { - int rm_ret = iwl_mvm_remove_sta_key(mvm, vif, sta, - mvm_sta->wep_key); - - if (!ret) - ret = rm_ret; - kfree(mvm_sta->wep_key); - mvm_sta->wep_key = NULL; - } - if (unlikely(ret && test_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, &mvm->status))) @@ -3289,6 +3258,13 @@ static void iwl_mvm_sta_rc_update(struct ieee80211_hw *hw, struct ieee80211_sta *sta, u32 changed) { struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw); + struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); + + if (changed & (IEEE80211_RC_BW_CHANGED | + IEEE80211_RC_SUPP_RATES_CHANGED | + IEEE80211_RC_NSS_CHANGED)) + iwl_mvm_rs_rate_init(mvm, sta, mvmvif->phy_ctxt->channel->band, + true); if (vif->type == NL80211_IFTYPE_STATION && changed & IEEE80211_RC_NSS_CHANGED) @@ -3439,20 +3415,12 @@ static int iwl_mvm_mac_set_key(struct ieee80211_hw *hw, break; case WLAN_CIPHER_SUITE_WEP40: case WLAN_CIPHER_SUITE_WEP104: - if (vif->type == NL80211_IFTYPE_AP) { - struct iwl_mvm_vif *mvmvif = - iwl_mvm_vif_from_mac80211(vif); - - mvmvif->ap_wep_key = kmemdup(key, - sizeof(*key) + key->keylen, - GFP_KERNEL); - if (!mvmvif->ap_wep_key) - return -ENOMEM; - } - - if (vif->type != NL80211_IFTYPE_STATION) - return 0; - break; + if (vif->type == NL80211_IFTYPE_STATION) + break; + if (iwl_mvm_has_new_tx_api(mvm)) + return -EOPNOTSUPP; + /* support HW crypto on TX */ + return 0; default: /* currently FW supports only one optional cipher scheme */ if (hw->n_cipher_schemes && @@ -3540,12 +3508,17 @@ static int iwl_mvm_mac_set_key(struct ieee80211_hw *hw, ret = iwl_mvm_set_sta_key(mvm, vif, sta, key, key_offset); if (ret) { IWL_WARN(mvm, "set key failed\n"); + key->hw_key_idx = STA_KEY_IDX_INVALID; /* * can't add key for RX, but we don't need it - * in the device for TX so still return 0 + * in the device for TX so still return 0, + * unless we have new TX API where we cannot + * put key material into the TX_CMD */ - key->hw_key_idx = STA_KEY_IDX_INVALID; - ret = 0; + if (iwl_mvm_has_new_tx_api(mvm)) + ret = -EOPNOTSUPP; + else + ret = 0; } break; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index bca6f6b536d9..a50dc53df086 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -498,7 +498,6 @@ struct iwl_mvm_vif { netdev_features_t features; struct iwl_probe_resp_data __rcu *probe_resp_data; - struct ieee80211_key_conf *ap_wep_key; }; static inline struct iwl_mvm_vif * diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c index ba27dce4c2bb..13681b03c10e 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c @@ -834,7 +834,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg, mutex_lock(&mvm->mutex); iwl_mvm_ref(mvm, IWL_MVM_REF_INIT_UCODE); err = iwl_run_init_mvm_ucode(mvm, true); - if (err) + if (err && err != -ERFKILL) iwl_fw_dbg_error_collect(&mvm->fwrt, FW_DBG_TRIGGER_DRIVER); if (!iwlmvm_mod_params.init_dbg || !err) iwl_mvm_stop_device(mvm); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index 1e03acf30762..b516fd1867ec 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -169,9 +169,9 @@ static inline int iwl_mvm_check_pn(struct iwl_mvm *mvm, struct sk_buff *skb, } /* iwl_mvm_create_skb Adds the rxb to a new skb */ -static void iwl_mvm_create_skb(struct sk_buff *skb, struct ieee80211_hdr *hdr, - u16 len, u8 crypt_len, - struct iwl_rx_cmd_buffer *rxb) +static int iwl_mvm_create_skb(struct iwl_mvm *mvm, struct sk_buff *skb, + struct ieee80211_hdr *hdr, u16 len, u8 crypt_len, + struct iwl_rx_cmd_buffer *rxb) { struct iwl_rx_packet *pkt = rxb_addr(rxb); struct iwl_rx_mpdu_desc *desc = (void *)pkt->data; @@ -204,6 +204,20 @@ static void iwl_mvm_create_skb(struct sk_buff *skb, struct ieee80211_hdr *hdr, * present before copying packet data. */ hdrlen += crypt_len; + + if (WARN_ONCE(headlen < hdrlen, + "invalid packet lengths (hdrlen=%d, len=%d, crypt_len=%d)\n", + hdrlen, len, crypt_len)) { + /* + * We warn and trace because we want to be able to see + * it in trace-cmd as well. + */ + IWL_DEBUG_RX(mvm, + "invalid packet lengths (hdrlen=%d, len=%d, crypt_len=%d)\n", + hdrlen, len, crypt_len); + return -EINVAL; + } + skb_put_data(skb, hdr, hdrlen); skb_put_data(skb, (u8 *)hdr + hdrlen + pad_len, headlen - hdrlen); @@ -216,6 +230,8 @@ static void iwl_mvm_create_skb(struct sk_buff *skb, struct ieee80211_hdr *hdr, skb_add_rx_frag(skb, 0, rxb_steal_page(rxb), offset, fraglen, rxb->truesize); } + + return 0; } static void iwl_mvm_add_rtap_sniffer_config(struct iwl_mvm *mvm, @@ -1671,7 +1687,11 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi, rx_status->boottime_ns = ktime_get_boot_ns(); } - iwl_mvm_create_skb(skb, hdr, len, crypt_len, rxb); + if (iwl_mvm_create_skb(mvm, skb, hdr, len, crypt_len, rxb)) { + kfree_skb(skb); + goto out; + } + if (!iwl_mvm_reorder(mvm, napi, queue, sta, skb, desc)) iwl_mvm_pass_packet_to_mac80211(mvm, napi, skb, queue, sta, csi); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index 498c315291cf..98d123dd7177 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -8,7 +8,7 @@ * Copyright(c) 2012 - 2015 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH - * Copyright(c) 2018 Intel Corporation + * Copyright(c) 2018 - 2019 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -31,7 +31,7 @@ * Copyright(c) 2012 - 2015 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH - * Copyright(c) 2018 Intel Corporation + * Copyright(c) 2018 - 2019 Intel Corporation * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -1399,7 +1399,9 @@ void iwl_mvm_add_new_dqa_stream_wk(struct work_struct *wk) iwl_mvm_sta_alloc_queue(mvm, txq->sta, txq->ac, tid); list_del_init(&mvmtxq->list); + local_bh_disable(); iwl_mvm_mac_itxq_xmit(mvm->hw, txq); + local_bh_enable(); } mutex_unlock(&mvm->mutex); @@ -2333,21 +2335,6 @@ int iwl_mvm_add_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif) iwl_mvm_enable_txq(mvm, NULL, mvmvif->cab_queue, 0, &cfg, timeout); - if (mvmvif->ap_wep_key) { - u8 key_offset = iwl_mvm_set_fw_key_idx(mvm); - - __set_bit(key_offset, mvm->fw_key_table); - - if (key_offset == STA_KEY_IDX_INVALID) - return -ENOSPC; - - ret = iwl_mvm_send_sta_key(mvm, mvmvif->mcast_sta.sta_id, - mvmvif->ap_wep_key, true, 0, NULL, 0, - key_offset, 0); - if (ret) - return ret; - } - return 0; } @@ -2419,28 +2406,6 @@ int iwl_mvm_rm_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif) iwl_mvm_disable_txq(mvm, NULL, mvmvif->cab_queue, 0, 0); - if (mvmvif->ap_wep_key) { - int i; - - if (!__test_and_clear_bit(mvmvif->ap_wep_key->hw_key_idx, - mvm->fw_key_table)) { - IWL_ERR(mvm, "offset %d not used in fw key table.\n", - mvmvif->ap_wep_key->hw_key_idx); - return -ENOENT; - } - - /* track which key was deleted last */ - for (i = 0; i < STA_KEY_MAX_NUM; i++) { - if (mvm->fw_key_deleted[i] < U8_MAX) - mvm->fw_key_deleted[i]++; - } - mvm->fw_key_deleted[mvmvif->ap_wep_key->hw_key_idx] = 0; - ret = __iwl_mvm_remove_sta_key(mvm, mvmvif->mcast_sta.sta_id, - mvmvif->ap_wep_key, true); - if (ret) - return ret; - } - ret = iwl_mvm_rm_sta_common(mvm, mvmvif->mcast_sta.sta_id); if (ret) IWL_WARN(mvm, "Failed sending remove station\n"); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h index 79700c7310a1..b4d4071b865d 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h @@ -8,7 +8,7 @@ * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH * Copyright(c) 2015 - 2016 Intel Deutschland GmbH - * Copyright(c) 2018 Intel Corporation + * Copyright(c) 2018 - 2019 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -31,7 +31,7 @@ * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH * Copyright(c) 2015 - 2016 Intel Deutschland GmbH - * Copyright(c) 2018 Intel Corporation + * Copyright(c) 2018 - 2019 Intel Corporation * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -394,7 +394,6 @@ struct iwl_mvm_rxq_dup_data { * the BA window. To be used for UAPSD only. * @ptk_pn: per-queue PTK PN data structures * @dup_data: per queue duplicate packet detection data - * @wep_key: used in AP mode. Is a duplicate of the WEP key. * @deferred_traffic_tid_map: indication bitmap of deferred traffic per-TID * @tx_ant: the index of the antenna to use for data tx to this station. Only * used during connection establishment (e.g. for the 4 way handshake @@ -426,8 +425,6 @@ struct iwl_mvm_sta { struct iwl_mvm_key_pn __rcu *ptk_pn[4]; struct iwl_mvm_rxq_dup_data *dup_data; - struct ieee80211_key_conf *wep_key; - u8 reserved_queue; /* Temporary, until the new TLC will control the Tx protection */ diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 2b94e4cef56c..9f1af8da9dc1 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -953,14 +953,15 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0xA0F0, 0x1652, killer1650i_2ax_cfg_qu_b0_hr_b0)}, {IWL_PCI_DEVICE(0xA0F0, 0x4070, iwl_ax101_cfg_qu_hr)}, - {IWL_PCI_DEVICE(0x2723, 0x0080, iwl22260_2ax_cfg)}, - {IWL_PCI_DEVICE(0x2723, 0x0084, iwl22260_2ax_cfg)}, - {IWL_PCI_DEVICE(0x2723, 0x0088, iwl22260_2ax_cfg)}, - {IWL_PCI_DEVICE(0x2723, 0x008C, iwl22260_2ax_cfg)}, + {IWL_PCI_DEVICE(0x2723, 0x0080, iwl_ax200_cfg_cc)}, + {IWL_PCI_DEVICE(0x2723, 0x0084, iwl_ax200_cfg_cc)}, + {IWL_PCI_DEVICE(0x2723, 0x0088, iwl_ax200_cfg_cc)}, + {IWL_PCI_DEVICE(0x2723, 0x008C, iwl_ax200_cfg_cc)}, {IWL_PCI_DEVICE(0x2723, 0x1653, killer1650w_2ax_cfg)}, {IWL_PCI_DEVICE(0x2723, 0x1654, killer1650x_2ax_cfg)}, - {IWL_PCI_DEVICE(0x2723, 0x4080, iwl22260_2ax_cfg)}, - {IWL_PCI_DEVICE(0x2723, 0x4088, iwl22260_2ax_cfg)}, + {IWL_PCI_DEVICE(0x2723, 0x2080, iwl_ax200_cfg_cc)}, + {IWL_PCI_DEVICE(0x2723, 0x4080, iwl_ax200_cfg_cc)}, + {IWL_PCI_DEVICE(0x2723, 0x4088, iwl_ax200_cfg_cc)}, {IWL_PCI_DEVICE(0x1a56, 0x1653, killer1650w_2ax_cfg)}, {IWL_PCI_DEVICE(0x1a56, 0x1654, killer1650x_2ax_cfg)}, diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h index bf8b61a476c5..59213164f35e 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h +++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h @@ -1043,7 +1043,7 @@ static inline bool iwl_pcie_dbg_on(struct iwl_trans *trans) void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state); void iwl_trans_pcie_dump_regs(struct iwl_trans *trans); -void iwl_trans_sync_nmi(struct iwl_trans *trans); +void iwl_trans_pcie_sync_nmi(struct iwl_trans *trans); #ifdef CONFIG_IWLWIFI_DEBUGFS int iwl_trans_pcie_dbgfs_register(struct iwl_trans *trans); diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c index fe8269d023de..c4375b868901 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@ -3318,7 +3318,8 @@ static void iwl_trans_pcie_resume(struct iwl_trans *trans) .unref = iwl_trans_pcie_unref, \ .dump_data = iwl_trans_pcie_dump_data, \ .d3_suspend = iwl_trans_pcie_d3_suspend, \ - .d3_resume = iwl_trans_pcie_d3_resume + .d3_resume = iwl_trans_pcie_d3_resume, \ + .sync_nmi = iwl_trans_pcie_sync_nmi #ifdef CONFIG_PM_SLEEP #define IWL_TRANS_PM_OPS \ @@ -3542,6 +3543,10 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev, } } else if (cfg == &iwl_ax101_cfg_qu_hr) { if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) == + CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR) && + trans->hw_rev == CSR_HW_REV_TYPE_QNJ_B0) { + trans->cfg = &iwl22000_2ax_cfg_qnj_hr_b0; + } else if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) == CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR)) { trans->cfg = &iwl_ax101_cfg_qu_hr; } else if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) == @@ -3560,7 +3565,7 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev, } } else if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) == CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR) && - (trans->cfg != &iwl22260_2ax_cfg || + (trans->cfg != &iwl_ax200_cfg_cc || trans->hw_rev == CSR_HW_REV_TYPE_QNJ_B0)) { u32 hw_status; @@ -3637,22 +3642,29 @@ out_no_pci: return ERR_PTR(ret); } -void iwl_trans_sync_nmi(struct iwl_trans *trans) +void iwl_trans_pcie_sync_nmi(struct iwl_trans *trans) { + struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); unsigned long timeout = jiffies + IWL_TRANS_NMI_TIMEOUT; + u32 inta_addr, sw_err_bit; + + if (trans_pcie->msix_enabled) { + inta_addr = CSR_MSIX_HW_INT_CAUSES_AD; + sw_err_bit = MSIX_HW_INT_CAUSES_REG_SW_ERR; + } else { + inta_addr = CSR_INT; + sw_err_bit = CSR_INT_BIT_SW_ERR; + } iwl_disable_interrupts(trans); iwl_force_nmi(trans); while (time_after(timeout, jiffies)) { - u32 inta_hw = iwl_read32(trans, - CSR_MSIX_HW_INT_CAUSES_AD); + u32 inta_hw = iwl_read32(trans, inta_addr); /* Error detected by uCode */ - if (inta_hw & MSIX_HW_INT_CAUSES_REG_SW_ERR) { + if (inta_hw & sw_err_bit) { /* Clear causes register */ - iwl_write32(trans, CSR_MSIX_HW_INT_CAUSES_AD, - inta_hw & - MSIX_HW_INT_CAUSES_REG_SW_ERR); + iwl_write32(trans, inta_addr, inta_hw & sw_err_bit); break; } diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c index 88530d9f4a54..38d110338987 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c @@ -965,7 +965,7 @@ static int iwl_pcie_gen2_send_hcmd_sync(struct iwl_trans *trans, cmd_str); ret = -ETIMEDOUT; - iwl_trans_sync_nmi(trans); + iwl_trans_pcie_sync_nmi(trans); goto cancel; } diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c index 9fbd37d23e85..7be73e2c4681 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c @@ -1960,7 +1960,7 @@ static int iwl_pcie_send_hcmd_sync(struct iwl_trans *trans, iwl_get_cmd_string(trans, cmd->id)); ret = -ETIMEDOUT; - iwl_trans_sync_nmi(trans); + iwl_trans_pcie_sync_nmi(trans); goto cancel; } diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 0838af04d681..524eb5805995 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -2644,7 +2644,7 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, enum nl80211_band band; const struct ieee80211_ops *ops = &mac80211_hwsim_ops; struct net *net; - int idx; + int idx, i; int n_limits = 0; if (WARN_ON(param->channels > 1 && !param->use_chanctx)) @@ -2768,12 +2768,23 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, goto failed_hw; } + data->if_combination.max_interfaces = 0; + for (i = 0; i < n_limits; i++) + data->if_combination.max_interfaces += + data->if_limits[i].max; + data->if_combination.n_limits = n_limits; - data->if_combination.max_interfaces = 2048; data->if_combination.limits = data->if_limits; - hw->wiphy->iface_combinations = &data->if_combination; - hw->wiphy->n_iface_combinations = 1; + /* + * If we actually were asked to support combinations, + * advertise them - if there's only a single thing like + * only IBSS then don't advertise it as combinations. + */ + if (data->if_combination.max_interfaces > 1) { + hw->wiphy->iface_combinations = &data->if_combination; + hw->wiphy->n_iface_combinations = 1; + } if (param->ciphers) { memcpy(data->ciphers, param->ciphers, diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.c b/drivers/net/wireless/marvell/mwifiex/sdio.c index a85648342d15..d5a70340a945 100644 --- a/drivers/net/wireless/marvell/mwifiex/sdio.c +++ b/drivers/net/wireless/marvell/mwifiex/sdio.c @@ -181,7 +181,7 @@ static int mwifiex_sdio_resume(struct device *dev) adapter = card->adapter; - if (test_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags)) { + if (!test_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags)) { mwifiex_dbg(adapter, WARN, "device already resumed\n"); return 0; diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c index 6eedc0ec7661..76629b98c78d 100644 --- a/drivers/net/wireless/mediatek/mt76/dma.c +++ b/drivers/net/wireless/mediatek/mt76/dma.c @@ -130,6 +130,8 @@ mt76_dma_tx_cleanup_idx(struct mt76_dev *dev, struct mt76_queue *q, int idx, static void mt76_dma_sync_idx(struct mt76_dev *dev, struct mt76_queue *q) { + iowrite32(q->desc_dma, &q->regs->desc_base); + iowrite32(q->ndesc, &q->regs->ring_size); q->head = ioread32(&q->regs->dma_idx); q->tail = q->head; iowrite32(q->head, &q->regs->cpu_idx); @@ -180,7 +182,10 @@ mt76_dma_tx_cleanup(struct mt76_dev *dev, enum mt76_txq_id qid, bool flush) else mt76_dma_sync_idx(dev, q); - wake = wake && qid < IEEE80211_NUM_ACS && q->queued < q->ndesc - 8; + wake = wake && q->stopped && + qid < IEEE80211_NUM_ACS && q->queued < q->ndesc - 8; + if (wake) + q->stopped = false; if (!q->queued) wake_up(&dev->tx_wait); diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c index a033745adb2f..316167404729 100644 --- a/drivers/net/wireless/mediatek/mt76/mac80211.c +++ b/drivers/net/wireless/mediatek/mt76/mac80211.c @@ -679,19 +679,15 @@ out: return ret; } -static void -mt76_sta_remove(struct mt76_dev *dev, struct ieee80211_vif *vif, - struct ieee80211_sta *sta) +void __mt76_sta_remove(struct mt76_dev *dev, struct ieee80211_vif *vif, + struct ieee80211_sta *sta) { struct mt76_wcid *wcid = (struct mt76_wcid *)sta->drv_priv; - int idx = wcid->idx; - int i; + int i, idx = wcid->idx; rcu_assign_pointer(dev->wcid[idx], NULL); synchronize_rcu(); - mutex_lock(&dev->mutex); - if (dev->drv->sta_remove) dev->drv->sta_remove(dev, vif, sta); @@ -699,7 +695,15 @@ mt76_sta_remove(struct mt76_dev *dev, struct ieee80211_vif *vif, for (i = 0; i < ARRAY_SIZE(sta->txq); i++) mt76_txq_remove(dev, sta->txq[i]); mt76_wcid_free(dev->wcid_mask, idx); +} +EXPORT_SYMBOL_GPL(__mt76_sta_remove); +static void +mt76_sta_remove(struct mt76_dev *dev, struct ieee80211_vif *vif, + struct ieee80211_sta *sta) +{ + mutex_lock(&dev->mutex); + __mt76_sta_remove(dev, vif, sta); mutex_unlock(&dev->mutex); } diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h index 5dfb0601f101..bcbfd3c4a44b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76.h +++ b/drivers/net/wireless/mediatek/mt76/mt76.h @@ -126,6 +126,7 @@ struct mt76_queue { int ndesc; int queued; int buf_size; + bool stopped; u8 buf_offset; u8 hw_idx; @@ -143,6 +144,7 @@ struct mt76_mcu_ops { const struct mt76_reg_pair *rp, int len); int (*mcu_rd_rp)(struct mt76_dev *dev, u32 base, struct mt76_reg_pair *rp, int len); + int (*mcu_restart)(struct mt76_dev *dev); }; struct mt76_queue_ops { @@ -693,6 +695,8 @@ int mt76_sta_state(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, enum ieee80211_sta_state old_state, enum ieee80211_sta_state new_state); +void __mt76_sta_remove(struct mt76_dev *dev, struct ieee80211_vif *vif, + struct ieee80211_sta *sta); struct ieee80211_sta *mt76_rx_convert(struct sk_buff *skb); diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/beacon.c b/drivers/net/wireless/mediatek/mt76/mt7603/beacon.c index afcd86f735b4..4dcb465095d1 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/beacon.c +++ b/drivers/net/wireless/mediatek/mt76/mt7603/beacon.c @@ -135,8 +135,7 @@ void mt7603_pre_tbtt_tasklet(unsigned long arg) out: mt76_queue_tx_cleanup(dev, MT_TXQ_BEACON, false); - if (dev->mt76.q_tx[MT_TXQ_BEACON].queued > - __sw_hweight8(dev->beacon_mask)) + if (dev->mt76.q_tx[MT_TXQ_BEACON].queued > hweight8(dev->beacon_mask)) dev->beacon_check++; } diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/dma.c b/drivers/net/wireless/mediatek/mt76/mt7603/dma.c index d69e82c66ab2..b3ae0aaea62a 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/dma.c +++ b/drivers/net/wireless/mediatek/mt76/mt7603/dma.c @@ -27,12 +27,16 @@ static void mt7603_rx_loopback_skb(struct mt7603_dev *dev, struct sk_buff *skb) { __le32 *txd = (__le32 *)skb->data; + struct ieee80211_hdr *hdr; + struct ieee80211_sta *sta; struct mt7603_sta *msta; struct mt76_wcid *wcid; + void *priv; int idx; u32 val; + u8 tid; - if (skb->len < sizeof(MT_TXD_SIZE) + sizeof(struct ieee80211_hdr)) + if (skb->len < MT_TXD_SIZE + sizeof(struct ieee80211_hdr)) goto free; val = le32_to_cpu(txd[1]); @@ -46,10 +50,19 @@ mt7603_rx_loopback_skb(struct mt7603_dev *dev, struct sk_buff *skb) if (!wcid) goto free; - msta = container_of(wcid, struct mt7603_sta, wcid); + priv = msta = container_of(wcid, struct mt7603_sta, wcid); val = le32_to_cpu(txd[0]); skb_set_queue_mapping(skb, FIELD_GET(MT_TXD0_Q_IDX, val)); + val &= ~(MT_TXD0_P_IDX | MT_TXD0_Q_IDX); + val |= FIELD_PREP(MT_TXD0_Q_IDX, MT_TX_HW_QUEUE_MGMT); + txd[0] = cpu_to_le32(val); + + sta = container_of(priv, struct ieee80211_sta, drv_priv); + hdr = (struct ieee80211_hdr *) &skb->data[MT_TXD_SIZE]; + tid = *ieee80211_get_qos_ctl(hdr) & IEEE80211_QOS_CTL_TID_MASK; + ieee80211_sta_set_buffered(sta, tid, true); + spin_lock_bh(&dev->ps_lock); __skb_queue_tail(&msta->psq, skb); if (skb_queue_len(&msta->psq) >= 64) { diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/init.c b/drivers/net/wireless/mediatek/mt76/mt7603/init.c index 15cc8f33b34d..3af45949e868 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7603/init.c @@ -112,7 +112,7 @@ static void mt7603_phy_init(struct mt7603_dev *dev) { int rx_chains = dev->mt76.antenna_mask; - int tx_chains = __sw_hweight8(rx_chains) - 1; + int tx_chains = hweight8(rx_chains) - 1; mt76_rmw(dev, MT_WF_RMAC_RMCR, (MT_WF_RMAC_RMCR_SMPS_MODE | @@ -510,6 +510,8 @@ int mt7603_register_device(struct mt7603_dev *dev) bus_ops->rmw = mt7603_rmw; dev->mt76.bus = bus_ops; + spin_lock_init(&dev->ps_lock); + INIT_DELAYED_WORK(&dev->mac_work, mt7603_mac_work); tasklet_init(&dev->pre_tbtt_tasklet, mt7603_pre_tbtt_tasklet, (unsigned long)dev); diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c index 0a0115861b51..5abc02b57818 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c @@ -343,7 +343,7 @@ void mt7603_mac_rx_ba_reset(struct mt7603_dev *dev, void *addr, u8 tid) MT_BA_CONTROL_1_RESET)); } -void mt7603_mac_tx_ba_reset(struct mt7603_dev *dev, int wcid, int tid, int ssn, +void mt7603_mac_tx_ba_reset(struct mt7603_dev *dev, int wcid, int tid, int ba_size) { u32 addr = mt7603_wtbl2_addr(wcid); @@ -358,43 +358,6 @@ void mt7603_mac_tx_ba_reset(struct mt7603_dev *dev, int wcid, int tid, int ssn, mt76_clear(dev, addr + (15 * 4), tid_mask); return; } - mt76_poll(dev, MT_WTBL_UPDATE, MT_WTBL_UPDATE_BUSY, 0, 5000); - - mt7603_mac_stop(dev); - switch (tid) { - case 0: - mt76_rmw_field(dev, addr + (2 * 4), MT_WTBL2_W2_TID0_SN, ssn); - break; - case 1: - mt76_rmw_field(dev, addr + (2 * 4), MT_WTBL2_W2_TID1_SN, ssn); - break; - case 2: - mt76_rmw_field(dev, addr + (2 * 4), MT_WTBL2_W2_TID2_SN_LO, - ssn); - mt76_rmw_field(dev, addr + (3 * 4), MT_WTBL2_W3_TID2_SN_HI, - ssn >> 8); - break; - case 3: - mt76_rmw_field(dev, addr + (3 * 4), MT_WTBL2_W3_TID3_SN, ssn); - break; - case 4: - mt76_rmw_field(dev, addr + (3 * 4), MT_WTBL2_W3_TID4_SN, ssn); - break; - case 5: - mt76_rmw_field(dev, addr + (3 * 4), MT_WTBL2_W3_TID5_SN_LO, - ssn); - mt76_rmw_field(dev, addr + (4 * 4), MT_WTBL2_W4_TID5_SN_HI, - ssn >> 4); - break; - case 6: - mt76_rmw_field(dev, addr + (4 * 4), MT_WTBL2_W4_TID6_SN, ssn); - break; - case 7: - mt76_rmw_field(dev, addr + (4 * 4), MT_WTBL2_W4_TID7_SN, ssn); - break; - } - mt7603_wtbl_update(dev, wcid, MT_WTBL_UPDATE_WTBL2); - mt7603_mac_start(dev); for (i = 7; i > 0; i--) { if (ba_size >= MT_AGG_SIZE_LIMIT(i)) @@ -827,6 +790,7 @@ mt7603_mac_write_txwi(struct mt7603_dev *dev, __le32 *txwi, struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_tx_rate *rate = &info->control.rates[0]; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; + struct ieee80211_bar *bar = (struct ieee80211_bar *)skb->data; struct ieee80211_vif *vif = info->control.vif; struct mt7603_vif *mvif; int wlan_idx; @@ -834,6 +798,7 @@ mt7603_mac_write_txwi(struct mt7603_dev *dev, __le32 *txwi, int tx_count = 8; u8 frame_type, frame_subtype; u16 fc = le16_to_cpu(hdr->frame_control); + u16 seqno = 0; u8 vif_idx = 0; u32 val; u8 bw; @@ -919,7 +884,17 @@ mt7603_mac_write_txwi(struct mt7603_dev *dev, __le32 *txwi, tx_count = 0x1f; val = FIELD_PREP(MT_TXD3_REM_TX_COUNT, tx_count) | - FIELD_PREP(MT_TXD3_SEQ, le16_to_cpu(hdr->seq_ctrl)); + MT_TXD3_SN_VALID; + + if (ieee80211_is_data_qos(hdr->frame_control)) + seqno = le16_to_cpu(hdr->seq_ctrl); + else if (ieee80211_is_back_req(hdr->frame_control)) + seqno = le16_to_cpu(bar->start_seq_num); + else + val &= ~MT_TXD3_SN_VALID; + + val |= FIELD_PREP(MT_TXD3_SEQ, seqno >> 4); + txwi[3] = cpu_to_le32(val); if (key) { @@ -1072,7 +1047,7 @@ out: case MT_PHY_TYPE_HT: final_rate_flags |= IEEE80211_TX_RC_MCS; final_rate &= GENMASK(5, 0); - if (i > 15) + if (final_rate > 15) return false; break; default: diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/main.c b/drivers/net/wireless/mediatek/mt76/mt7603/main.c index b10775ed92e6..a3c4ef198bfe 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7603/main.c @@ -5,6 +5,7 @@ #include <linux/pci.h> #include <linux/module.h> #include "mt7603.h" +#include "mac.h" #include "eeprom.h" static int @@ -371,7 +372,7 @@ mt7603_sta_ps(struct mt76_dev *mdev, struct ieee80211_sta *sta, bool ps) struct mt7603_sta *msta = (struct mt7603_sta *)sta->drv_priv; struct sk_buff_head list; - mt76_stop_tx_queues(&dev->mt76, sta, false); + mt76_stop_tx_queues(&dev->mt76, sta, true); mt7603_wtbl_set_ps(dev, msta, ps); if (ps) return; @@ -386,6 +387,15 @@ mt7603_sta_ps(struct mt76_dev *mdev, struct ieee80211_sta *sta, bool ps) } static void +mt7603_ps_set_more_data(struct sk_buff *skb) +{ + struct ieee80211_hdr *hdr; + + hdr = (struct ieee80211_hdr *) &skb->data[MT_TXD_SIZE]; + hdr->frame_control |= cpu_to_le16(IEEE80211_FCTL_MOREDATA); +} + +static void mt7603_release_buffered_frames(struct ieee80211_hw *hw, struct ieee80211_sta *sta, u16 tids, int nframes, @@ -399,6 +409,8 @@ mt7603_release_buffered_frames(struct ieee80211_hw *hw, __skb_queue_head_init(&list); + mt7603_wtbl_set_ps(dev, msta, false); + spin_lock_bh(&dev->ps_lock); skb_queue_walk_safe(&msta->psq, skb, tmp) { if (!nframes) @@ -409,11 +421,15 @@ mt7603_release_buffered_frames(struct ieee80211_hw *hw, skb_set_queue_mapping(skb, MT_TXQ_PSD); __skb_unlink(skb, &msta->psq); + mt7603_ps_set_more_data(skb); __skb_queue_tail(&list, skb); nframes--; } spin_unlock_bh(&dev->ps_lock); + if (!skb_queue_empty(&list)) + ieee80211_sta_eosp(sta); + mt7603_ps_tx_list(dev, &list); if (nframes) @@ -568,13 +584,13 @@ mt7603_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, case IEEE80211_AMPDU_TX_OPERATIONAL: mtxq->aggr = true; mtxq->send_bar = false; - mt7603_mac_tx_ba_reset(dev, msta->wcid.idx, tid, *ssn, ba_size); + mt7603_mac_tx_ba_reset(dev, msta->wcid.idx, tid, ba_size); break; case IEEE80211_AMPDU_TX_STOP_FLUSH: case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT: mtxq->aggr = false; ieee80211_send_bar(vif, sta->addr, tid, mtxq->agg_ssn); - mt7603_mac_tx_ba_reset(dev, msta->wcid.idx, tid, *ssn, -1); + mt7603_mac_tx_ba_reset(dev, msta->wcid.idx, tid, -1); break; case IEEE80211_AMPDU_TX_START: mtxq->agg_ssn = *ssn << 4; @@ -582,7 +598,7 @@ mt7603_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, break; case IEEE80211_AMPDU_TX_STOP_CONT: mtxq->aggr = false; - mt7603_mac_tx_ba_reset(dev, msta->wcid.idx, tid, *ssn, -1); + mt7603_mac_tx_ba_reset(dev, msta->wcid.idx, tid, -1); ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid); break; } diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7603/mcu.c index 4b0713f1fd5e..d06905ea8cc6 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7603/mcu.c @@ -433,7 +433,7 @@ int mt7603_mcu_set_channel(struct mt7603_dev *dev) { struct cfg80211_chan_def *chandef = &dev->mt76.chandef; struct ieee80211_hw *hw = mt76_hw(dev); - int n_chains = __sw_hweight8(dev->mt76.antenna_mask); + int n_chains = hweight8(dev->mt76.antenna_mask); struct { u8 control_chan; u8 center_chan; diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h b/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h index 79f332429432..6049f3b7c8fe 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h +++ b/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h @@ -200,7 +200,7 @@ void mt7603_beacon_set_timer(struct mt7603_dev *dev, int idx, int intval); int mt7603_mac_fill_rx(struct mt7603_dev *dev, struct sk_buff *skb); void mt7603_mac_add_txs(struct mt7603_dev *dev, void *data); void mt7603_mac_rx_ba_reset(struct mt7603_dev *dev, void *addr, u8 tid); -void mt7603_mac_tx_ba_reset(struct mt7603_dev *dev, int wcid, int tid, int ssn, +void mt7603_mac_tx_ba_reset(struct mt7603_dev *dev, int wcid, int tid, int ba_size); void mt7603_pse_client_reset(struct mt7603_dev *dev); diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/soc.c b/drivers/net/wireless/mediatek/mt76/mt7603/soc.c index e13fea80d970..b920be1f5718 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/soc.c +++ b/drivers/net/wireless/mediatek/mt76/mt7603/soc.c @@ -23,9 +23,9 @@ mt76_wmac_probe(struct platform_device *pdev) } mem_base = devm_ioremap_resource(&pdev->dev, res); - if (!mem_base) { + if (IS_ERR(mem_base)) { dev_err(&pdev->dev, "Failed to get memory resource\n"); - return -EINVAL; + return PTR_ERR(mem_base); } mdev = mt76_alloc_device(&pdev->dev, sizeof(*dev), &mt7603_ops, diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h b/drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h index 0290ba5869a5..736f81752b5b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h @@ -46,7 +46,7 @@ static const struct mt76_reg_pair common_mac_reg_table[] = { { MT_MM20_PROT_CFG, 0x01742004 }, { MT_MM40_PROT_CFG, 0x03f42084 }, { MT_TXOP_CTRL_CFG, 0x0000583f }, - { MT_TX_RTS_CFG, 0x00092b20 }, + { MT_TX_RTS_CFG, 0x00ffff20 }, { MT_EXP_ACK_TIME, 0x002400ca }, { MT_TXOP_HLDR_ET, 0x00000002 }, { MT_XIFS_TIME_CFG, 0x33a41010 }, diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c index 91718647da02..e5a06f74a6f7 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c @@ -229,7 +229,7 @@ static int mt76x0u_probe(struct usb_interface *usb_intf, struct usb_device *usb_dev = interface_to_usbdev(usb_intf); struct mt76x02_dev *dev; struct mt76_dev *mdev; - u32 asic_rev, mac_rev; + u32 mac_rev; int ret; mdev = mt76_alloc_device(&usb_intf->dev, sizeof(*dev), &mt76x0u_ops, @@ -262,10 +262,14 @@ static int mt76x0u_probe(struct usb_interface *usb_intf, goto err; } - asic_rev = mt76_rr(dev, MT_ASIC_VERSION); + mdev->rev = mt76_rr(dev, MT_ASIC_VERSION); mac_rev = mt76_rr(dev, MT_MAC_CSR0); dev_info(mdev->dev, "ASIC revision: %08x MAC revision: %08x\n", - asic_rev, mac_rev); + mdev->rev, mac_rev); + if (!is_mt76x0(dev)) { + ret = -ENODEV; + goto err; + } /* Note: vendor driver skips this check for MT76X0U */ if (!(mt76_rr(dev, MT_EFUSE_CTRL) & MT_EFUSE_CTRL_SEL)) diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02.h b/drivers/net/wireless/mediatek/mt76/mt76x02.h index 6915cce5def9..07061eb4d1e1 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02.h +++ b/drivers/net/wireless/mediatek/mt76/mt76x02.h @@ -51,6 +51,7 @@ struct mt76x02_calibration { u16 false_cca; s8 avg_rssi_all; s8 agc_gain_adjust; + s8 agc_lowest_gain; s8 low_gain; s8 temp_vco; @@ -114,8 +115,11 @@ struct mt76x02_dev { struct mt76x02_dfs_pattern_detector dfs_pd; /* edcca monitor */ + unsigned long ed_trigger_timeout; bool ed_tx_blocked; bool ed_monitor; + u8 ed_monitor_enabled; + u8 ed_monitor_learning; u8 ed_trigger; u8 ed_silent; ktime_t ed_time; @@ -188,6 +192,13 @@ void mt76x02_mac_start(struct mt76x02_dev *dev); void mt76x02_init_debugfs(struct mt76x02_dev *dev); +static inline bool is_mt76x0(struct mt76x02_dev *dev) +{ + return mt76_chip(&dev->mt76) == 0x7610 || + mt76_chip(&dev->mt76) == 0x7630 || + mt76_chip(&dev->mt76) == 0x7650; +} + static inline bool is_mt76x2(struct mt76x02_dev *dev) { return mt76_chip(&dev->mt76) == 0x7612 || diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_debugfs.c b/drivers/net/wireless/mediatek/mt76/mt76x02_debugfs.c index 7580c5c986ff..b1d6fd4861e3 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_debugfs.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_debugfs.c @@ -116,6 +116,32 @@ static int read_agc(struct seq_file *file, void *data) return 0; } +static int +mt76_edcca_set(void *data, u64 val) +{ + struct mt76x02_dev *dev = data; + enum nl80211_dfs_regions region = dev->dfs_pd.region; + + dev->ed_monitor_enabled = !!val; + dev->ed_monitor = dev->ed_monitor_enabled && + region == NL80211_DFS_ETSI; + mt76x02_edcca_init(dev, true); + + return 0; +} + +static int +mt76_edcca_get(void *data, u64 *val) +{ + struct mt76x02_dev *dev = data; + + *val = dev->ed_monitor_enabled; + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(fops_edcca, mt76_edcca_get, mt76_edcca_set, + "%lld\n"); + void mt76x02_init_debugfs(struct mt76x02_dev *dev) { struct dentry *dir; @@ -127,6 +153,7 @@ void mt76x02_init_debugfs(struct mt76x02_dev *dev) debugfs_create_u8("temperature", 0400, dir, &dev->cal.temp); debugfs_create_bool("tpc", 0600, dir, &dev->enable_tpc); + debugfs_create_file("edcca", 0400, dir, dev, &fops_edcca); debugfs_create_file("ampdu_stat", 0400, dir, dev, &fops_ampdu_stat); debugfs_create_file("dfs_stats", 0400, dir, dev, &fops_dfs_stat); debugfs_create_devm_seqfile(dev->mt76.dev, "txpower", dir, diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c b/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c index e4649103efd4..17d12d212d1b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c @@ -885,7 +885,8 @@ mt76x02_dfs_set_domain(struct mt76x02_dev *dev, if (dfs_pd->region != region) { tasklet_disable(&dfs_pd->dfs_tasklet); - dev->ed_monitor = region == NL80211_DFS_ETSI; + dev->ed_monitor = dev->ed_monitor_enabled && + region == NL80211_DFS_ETSI; mt76x02_edcca_init(dev, true); dfs_pd->region = region; diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c index 91ff6598eccf..4fe5a83ca5a4 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c @@ -67,12 +67,39 @@ int mt76x02_mac_shared_key_setup(struct mt76x02_dev *dev, u8 vif_idx, } EXPORT_SYMBOL_GPL(mt76x02_mac_shared_key_setup); +void mt76x02_mac_wcid_sync_pn(struct mt76x02_dev *dev, u8 idx, + struct ieee80211_key_conf *key) +{ + enum mt76x02_cipher_type cipher; + u8 key_data[32]; + u32 iv, eiv; + u64 pn; + + cipher = mt76x02_mac_get_key_info(key, key_data); + iv = mt76_rr(dev, MT_WCID_IV(idx)); + eiv = mt76_rr(dev, MT_WCID_IV(idx) + 4); + + pn = (u64)eiv << 16; + if (cipher == MT_CIPHER_TKIP) { + pn |= (iv >> 16) & 0xff; + pn |= (iv & 0xff) << 8; + } else if (cipher >= MT_CIPHER_AES_CCMP) { + pn |= iv & 0xffff; + } else { + return; + } + + atomic64_set(&key->tx_pn, pn); +} + + int mt76x02_mac_wcid_set_key(struct mt76x02_dev *dev, u8 idx, struct ieee80211_key_conf *key) { enum mt76x02_cipher_type cipher; u8 key_data[32]; u8 iv_data[8]; + u64 pn; cipher = mt76x02_mac_get_key_info(key, key_data); if (cipher == MT_CIPHER_NONE && key) @@ -85,9 +112,22 @@ int mt76x02_mac_wcid_set_key(struct mt76x02_dev *dev, u8 idx, if (key) { mt76_rmw_field(dev, MT_WCID_ATTR(idx), MT_WCID_ATTR_PAIRWISE, !!(key->flags & IEEE80211_KEY_FLAG_PAIRWISE)); + + pn = atomic64_read(&key->tx_pn); + iv_data[3] = key->keyidx << 6; - if (cipher >= MT_CIPHER_TKIP) + if (cipher >= MT_CIPHER_TKIP) { iv_data[3] |= 0x20; + put_unaligned_le32(pn >> 16, &iv_data[4]); + } + + if (cipher == MT_CIPHER_TKIP) { + iv_data[0] = (pn >> 8) & 0xff; + iv_data[1] = (iv_data[0] | 0x20) & 0x7f; + iv_data[2] = pn & 0xff; + } else if (cipher >= MT_CIPHER_AES_CCMP) { + put_unaligned_le16((pn & 0xffff), &iv_data[0]); + } } mt76_wr_copy(dev, MT_WCID_IV(idx), iv_data, sizeof(iv_data)); @@ -426,7 +466,6 @@ void mt76x02_send_tx_status(struct mt76x02_dev *dev, return; rcu_read_lock(); - mt76_tx_status_lock(mdev, &list); if (stat->wcid < ARRAY_SIZE(dev->mt76.wcid)) wcid = rcu_dereference(dev->mt76.wcid[stat->wcid]); @@ -439,6 +478,8 @@ void mt76x02_send_tx_status(struct mt76x02_dev *dev, drv_priv); } + mt76_tx_status_lock(mdev, &list); + if (wcid) { if (stat->pktid >= MT_PACKET_ID_FIRST) status.skb = mt76_tx_status_skb_get(mdev, wcid, @@ -458,7 +499,9 @@ void mt76x02_send_tx_status(struct mt76x02_dev *dev, if (*update == 0 && stat_val == stat_cache && stat->wcid == msta->status.wcid && msta->n_frames < 32) { msta->n_frames++; - goto out; + mt76_tx_status_unlock(mdev, &list); + rcu_read_unlock(); + return; } mt76x02_mac_fill_tx_status(dev, status.info, &msta->status, @@ -474,11 +517,10 @@ void mt76x02_send_tx_status(struct mt76x02_dev *dev, if (status.skb) mt76_tx_status_skb_done(mdev, status.skb, &list); - else - ieee80211_tx_status_ext(mt76_hw(dev), &status); - -out: mt76_tx_status_unlock(mdev, &list); + + if (!status.skb) + ieee80211_tx_status_ext(mt76_hw(dev), &status); rcu_read_unlock(); } @@ -920,6 +962,7 @@ void mt76x02_edcca_init(struct mt76x02_dev *dev, bool enable) } } mt76x02_edcca_tx_enable(dev, true); + dev->ed_monitor_learning = true; /* clear previous CCA timer value */ mt76_rr(dev, MT_ED_CCA_TIMER); @@ -929,6 +972,10 @@ EXPORT_SYMBOL_GPL(mt76x02_edcca_init); #define MT_EDCCA_TH 92 #define MT_EDCCA_BLOCK_TH 2 +#define MT_EDCCA_LEARN_TH 50 +#define MT_EDCCA_LEARN_CCA 180 +#define MT_EDCCA_LEARN_TIMEOUT (20 * HZ) + static void mt76x02_edcca_check(struct mt76x02_dev *dev) { ktime_t cur_time; @@ -951,11 +998,23 @@ static void mt76x02_edcca_check(struct mt76x02_dev *dev) dev->ed_trigger = 0; } - if (dev->ed_trigger > MT_EDCCA_BLOCK_TH && - !dev->ed_tx_blocked) + if (dev->cal.agc_lowest_gain && + dev->cal.false_cca > MT_EDCCA_LEARN_CCA && + dev->ed_trigger > MT_EDCCA_LEARN_TH) { + dev->ed_monitor_learning = false; + dev->ed_trigger_timeout = jiffies + 20 * HZ; + } else if (!dev->ed_monitor_learning && + time_is_after_jiffies(dev->ed_trigger_timeout)) { + dev->ed_monitor_learning = true; + mt76x02_edcca_tx_enable(dev, true); + } + + if (dev->ed_monitor_learning) + return; + + if (dev->ed_trigger > MT_EDCCA_BLOCK_TH && !dev->ed_tx_blocked) mt76x02_edcca_tx_enable(dev, false); - else if (dev->ed_silent > MT_EDCCA_BLOCK_TH && - dev->ed_tx_blocked) + else if (dev->ed_silent > MT_EDCCA_BLOCK_TH && dev->ed_tx_blocked) mt76x02_edcca_tx_enable(dev, true); } diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h index 6b1f25d2f64c..caeeef96c42f 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h @@ -177,6 +177,8 @@ int mt76x02_mac_shared_key_setup(struct mt76x02_dev *dev, u8 vif_idx, u8 key_idx, struct ieee80211_key_conf *key); int mt76x02_mac_wcid_set_key(struct mt76x02_dev *dev, u8 idx, struct ieee80211_key_conf *key); +void mt76x02_mac_wcid_sync_pn(struct mt76x02_dev *dev, u8 idx, + struct ieee80211_key_conf *key); void mt76x02_mac_wcid_setup(struct mt76x02_dev *dev, u8 idx, u8 vif_idx, u8 *mac); void mt76x02_mac_wcid_set_drop(struct mt76x02_dev *dev, u8 idx, bool drop); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c index 1229f19f2b02..daaed1220147 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c @@ -19,6 +19,7 @@ #include <linux/irq.h> #include "mt76x02.h" +#include "mt76x02_mcu.h" #include "mt76x02_trace.h" struct beacon_bc_data { @@ -418,9 +419,66 @@ static bool mt76x02_tx_hang(struct mt76x02_dev *dev) return i < 4; } +static void mt76x02_key_sync(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + struct ieee80211_key_conf *key, void *data) +{ + struct mt76x02_dev *dev = hw->priv; + struct mt76_wcid *wcid; + + if (!sta) + return; + + wcid = (struct mt76_wcid *) sta->drv_priv; + + if (wcid->hw_key_idx != key->keyidx || wcid->sw_iv) + return; + + mt76x02_mac_wcid_sync_pn(dev, wcid->idx, key); +} + +static void mt76x02_reset_state(struct mt76x02_dev *dev) +{ + int i; + + lockdep_assert_held(&dev->mt76.mutex); + + clear_bit(MT76_STATE_RUNNING, &dev->mt76.state); + + rcu_read_lock(); + ieee80211_iter_keys_rcu(dev->mt76.hw, NULL, mt76x02_key_sync, NULL); + rcu_read_unlock(); + + for (i = 0; i < ARRAY_SIZE(dev->mt76.wcid); i++) { + struct ieee80211_sta *sta; + struct ieee80211_vif *vif; + struct mt76x02_sta *msta; + struct mt76_wcid *wcid; + void *priv; + + wcid = rcu_dereference_protected(dev->mt76.wcid[i], + lockdep_is_held(&dev->mt76.mutex)); + if (!wcid) + continue; + + priv = msta = container_of(wcid, struct mt76x02_sta, wcid); + sta = container_of(priv, struct ieee80211_sta, drv_priv); + + priv = msta->vif; + vif = container_of(priv, struct ieee80211_vif, drv_priv); + + __mt76_sta_remove(&dev->mt76, vif, sta); + memset(msta, 0, sizeof(*msta)); + } + + dev->vif_mask = 0; + dev->beacon_mask = 0; +} + static void mt76x02_watchdog_reset(struct mt76x02_dev *dev) { u32 mask = dev->mt76.mmio.irqmask; + bool restart = dev->mt76.mcu_ops->mcu_restart; int i; ieee80211_stop_queues(dev->mt76.hw); @@ -434,6 +492,9 @@ static void mt76x02_watchdog_reset(struct mt76x02_dev *dev) mutex_lock(&dev->mt76.mutex); + if (restart) + mt76x02_reset_state(dev); + if (dev->beacon_mask) mt76_clear(dev, MT_BEACON_TIME_CFG, MT_BEACON_TIME_CFG_BEACON_TX | @@ -452,20 +513,21 @@ static void mt76x02_watchdog_reset(struct mt76x02_dev *dev) /* let fw reset DMA */ mt76_set(dev, 0x734, 0x3); + if (restart) + dev->mt76.mcu_ops->mcu_restart(&dev->mt76); + for (i = 0; i < ARRAY_SIZE(dev->mt76.q_tx); i++) mt76_queue_tx_cleanup(dev, i, true); for (i = 0; i < ARRAY_SIZE(dev->mt76.q_rx); i++) mt76_queue_rx_reset(dev, i); - mt76_wr(dev, MT_MAC_SYS_CTRL, - MT_MAC_SYS_CTRL_ENABLE_TX | MT_MAC_SYS_CTRL_ENABLE_RX); - mt76_set(dev, MT_WPDMA_GLO_CFG, - MT_WPDMA_GLO_CFG_TX_DMA_EN | MT_WPDMA_GLO_CFG_RX_DMA_EN); + mt76x02_mac_start(dev); + if (dev->ed_monitor) mt76_set(dev, MT_TXOP_CTRL_CFG, MT_TXOP_ED_CCA_EN); - if (dev->beacon_mask) + if (dev->beacon_mask && !restart) mt76_set(dev, MT_BEACON_TIME_CFG, MT_BEACON_TIME_CFG_BEACON_TX | MT_BEACON_TIME_CFG_TBTT_EN); @@ -486,9 +548,13 @@ static void mt76x02_watchdog_reset(struct mt76x02_dev *dev) napi_schedule(&dev->mt76.napi[i]); } - ieee80211_wake_queues(dev->mt76.hw); - - mt76_txq_schedule_all(&dev->mt76); + if (restart) { + mt76x02_mcu_function_select(dev, Q_SELECT, 1); + ieee80211_restart_hw(dev->mt76.hw); + } else { + ieee80211_wake_queues(dev->mt76.hw); + mt76_txq_schedule_all(&dev->mt76); + } } static void mt76x02_check_tx_hang(struct mt76x02_dev *dev) diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_phy.c b/drivers/net/wireless/mediatek/mt76/mt76x02_phy.c index a020c757ba5c..a54b63a96eae 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_phy.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_phy.c @@ -194,6 +194,8 @@ bool mt76x02_phy_adjust_vga_gain(struct mt76x02_dev *dev) ret = true; } + dev->cal.agc_lowest_gain = dev->cal.agc_gain_adjust >= limit; + return ret; } EXPORT_SYMBOL_GPL(mt76x02_phy_adjust_vga_gain); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c index 43f07461c8d3..6fb52b596d42 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c @@ -85,8 +85,9 @@ int mt76x02u_tx_prepare_skb(struct mt76_dev *mdev, void *data, mt76x02_insert_hdr_pad(skb); - txwi = skb_push(skb, sizeof(struct mt76x02_txwi)); + txwi = (struct mt76x02_txwi *)(skb->data - sizeof(struct mt76x02_txwi)); mt76x02_mac_write_txwi(dev, txwi, skb, wcid, sta, len); + skb_push(skb, sizeof(struct mt76x02_txwi)); pid = mt76_tx_status_skb_add(mdev, wcid, skb); txwi->pktid = pid; diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c index a48c261b0c63..cd072ac614f7 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c @@ -237,6 +237,8 @@ int mt76x02_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif, struct mt76x02_vif *mvif = (struct mt76x02_vif *)vif->drv_priv; int idx = 0; + memset(msta, 0, sizeof(*msta)); + idx = mt76_wcid_alloc(dev->mt76.wcid_mask, ARRAY_SIZE(dev->mt76.wcid)); if (idx < 0) return -ENOSPC; @@ -274,6 +276,8 @@ mt76x02_vif_init(struct mt76x02_dev *dev, struct ieee80211_vif *vif, struct mt76x02_vif *mvif = (struct mt76x02_vif *)vif->drv_priv; struct mt76_txq *mtxq; + memset(mvif, 0, sizeof(*mvif)); + mvif->idx = idx; mvif->group_wcid.idx = MT_VIF_WCID(idx); mvif->group_wcid.hw_key_idx = -1; @@ -289,6 +293,12 @@ mt76x02_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) struct mt76x02_dev *dev = hw->priv; unsigned int idx = 0; + /* Allow to change address in HW if we create first interface. */ + if (!dev->vif_mask && + (((vif->addr[0] ^ dev->mt76.macaddr[0]) & ~GENMASK(4, 1)) || + memcmp(vif->addr + 1, dev->mt76.macaddr + 1, ETH_ALEN - 1))) + mt76x02_mac_setaddr(dev, vif->addr); + if (vif->addr[0] & BIT(1)) idx = 1 + (((dev->mt76.macaddr[0] ^ vif->addr[0]) >> 2) & 7); @@ -311,10 +321,6 @@ mt76x02_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) if (dev->vif_mask & BIT(idx)) return -EBUSY; - /* Allow to change address in HW if we create first interface. */ - if (!dev->vif_mask && !ether_addr_equal(dev->mt76.macaddr, vif->addr)) - mt76x02_mac_setaddr(dev, vif->addr); - dev->vif_mask |= BIT(idx); mt76x02_vif_init(dev, vif, idx); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/init.c index f8534362e2c8..a30ef2c5a9db 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/init.c @@ -106,7 +106,7 @@ void mt76_write_mac_initvals(struct mt76x02_dev *dev) { MT_TX_SW_CFG1, 0x00010000 }, { MT_TX_SW_CFG2, 0x00000000 }, { MT_TXOP_CTRL_CFG, 0x0400583f }, - { MT_TX_RTS_CFG, 0x00100020 }, + { MT_TX_RTS_CFG, 0x00ffff20 }, { MT_TX_TIMEOUT_CFG, 0x000a2290 }, { MT_TX_RETRY_CFG, 0x47f01f0f }, { MT_EXP_ACK_TIME, 0x002c00dc }, diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h index 6c619f1c65c9..d7abe3d73bad 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h @@ -71,6 +71,7 @@ int mt76x2_mcu_load_cr(struct mt76x02_dev *dev, u8 type, u8 temp_level, void mt76x2_cleanup(struct mt76x02_dev *dev); +int mt76x2_mac_reset(struct mt76x02_dev *dev, bool hard); void mt76x2_reset_wlan(struct mt76x02_dev *dev, bool enable); void mt76x2_init_txpower(struct mt76x02_dev *dev, struct ieee80211_supported_band *sband); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c index 984d9c4c2e1a..d3927a13e92e 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c @@ -77,7 +77,7 @@ mt76x2_fixup_xtal(struct mt76x02_dev *dev) } } -static int mt76x2_mac_reset(struct mt76x02_dev *dev, bool hard) +int mt76x2_mac_reset(struct mt76x02_dev *dev, bool hard) { const u8 *macaddr = dev->mt76.macaddr; u32 val; diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mcu.c index 03e24ae7f66c..605dc66ae83b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mcu.c @@ -165,9 +165,30 @@ error: return -ENOENT; } +static int +mt76pci_mcu_restart(struct mt76_dev *mdev) +{ + struct mt76x02_dev *dev; + int ret; + + dev = container_of(mdev, struct mt76x02_dev, mt76); + + mt76x02_mcu_cleanup(dev); + mt76x2_mac_reset(dev, true); + + ret = mt76pci_load_firmware(dev); + if (ret) + return ret; + + mt76_wr(dev, MT_WPDMA_RST_IDX, ~0); + + return 0; +} + int mt76x2_mcu_init(struct mt76x02_dev *dev) { static const struct mt76_mcu_ops mt76x2_mcu_ops = { + .mcu_restart = mt76pci_mcu_restart, .mcu_send_msg = mt76x02_mcu_msg_send, }; int ret; diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c index 1848e8ab2e21..769a9b972044 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c @@ -260,10 +260,15 @@ mt76x2_phy_set_gain_val(struct mt76x02_dev *dev) gain_val[0] = dev->cal.agc_gain_cur[0] - dev->cal.agc_gain_adjust; gain_val[1] = dev->cal.agc_gain_cur[1] - dev->cal.agc_gain_adjust; - if (dev->mt76.chandef.width >= NL80211_CHAN_WIDTH_40) + val = 0x1836 << 16; + if (!mt76x2_has_ext_lna(dev) && + dev->mt76.chandef.width >= NL80211_CHAN_WIDTH_40) val = 0x1e42 << 16; - else - val = 0x1836 << 16; + + if (mt76x2_has_ext_lna(dev) && + dev->mt76.chandef.chan->band == NL80211_BAND_2GHZ && + dev->mt76.chandef.width < NL80211_CHAN_WIDTH_40) + val = 0x0f36 << 16; val |= 0xf8; @@ -280,6 +285,7 @@ void mt76x2_phy_update_channel_gain(struct mt76x02_dev *dev) { u8 *gain = dev->cal.agc_gain_init; u8 low_gain_delta, gain_delta; + u32 agc_35, agc_37; bool gain_change; int low_gain; u32 val; @@ -318,6 +324,16 @@ void mt76x2_phy_update_channel_gain(struct mt76x02_dev *dev) else low_gain_delta = 14; + agc_37 = 0x2121262c; + if (dev->mt76.chandef.chan->band == NL80211_BAND_2GHZ) + agc_35 = 0x11111516; + else if (low_gain == 2) + agc_35 = agc_37 = 0x08080808; + else if (dev->mt76.chandef.width == NL80211_CHAN_WIDTH_80) + agc_35 = 0x10101014; + else + agc_35 = 0x11111116; + if (low_gain == 2) { mt76_wr(dev, MT_BBP(RXO, 18), 0xf000a990); mt76_wr(dev, MT_BBP(AGC, 35), 0x08080808); @@ -326,15 +342,13 @@ void mt76x2_phy_update_channel_gain(struct mt76x02_dev *dev) dev->cal.agc_gain_adjust = 0; } else { mt76_wr(dev, MT_BBP(RXO, 18), 0xf000a991); - if (dev->mt76.chandef.width == NL80211_CHAN_WIDTH_80) - mt76_wr(dev, MT_BBP(AGC, 35), 0x10101014); - else - mt76_wr(dev, MT_BBP(AGC, 35), 0x11111116); - mt76_wr(dev, MT_BBP(AGC, 37), 0x2121262C); gain_delta = 0; dev->cal.agc_gain_adjust = low_gain_delta; } + mt76_wr(dev, MT_BBP(AGC, 35), agc_35); + mt76_wr(dev, MT_BBP(AGC, 37), agc_37); + dev->cal.agc_gain_cur[0] = gain[0] - gain_delta; dev->cal.agc_gain_cur[1] = gain[1] - gain_delta; mt76x2_phy_set_gain_val(dev); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c index ddb6b2c48e01..ac0f13d46299 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c @@ -21,11 +21,10 @@ #include "mt76x2u.h" static const struct usb_device_id mt76x2u_device_table[] = { - { USB_DEVICE(0x0e8d, 0x7612) }, /* Alfa AWUS036ACM */ { USB_DEVICE(0x0b05, 0x1833) }, /* Asus USB-AC54 */ { USB_DEVICE(0x0b05, 0x17eb) }, /* Asus USB-AC55 */ { USB_DEVICE(0x0b05, 0x180b) }, /* Asus USB-N53 B1 */ - { USB_DEVICE(0x0e8d, 0x7612) }, /* Aukey USB-AC1200 */ + { USB_DEVICE(0x0e8d, 0x7612) }, /* Aukey USBAC1200 - Alfa AWUS036ACM */ { USB_DEVICE(0x057c, 0x8503) }, /* Avm FRITZ!WLAN AC860 */ { USB_DEVICE(0x7392, 0xb711) }, /* Edimax EW 7722 UAC */ { USB_DEVICE(0x0846, 0x9053) }, /* Netgear A6210 */ @@ -66,6 +65,10 @@ static int mt76x2u_probe(struct usb_interface *intf, mdev->rev = mt76_rr(dev, MT_ASIC_VERSION); dev_info(mdev->dev, "ASIC revision: %08x\n", mdev->rev); + if (!is_mt76x2(dev)) { + err = -ENODEV; + goto err; + } err = mt76x2u_register_device(dev); if (err < 0) diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mac.c index 5e84b4535cb1..3b82345756ea 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mac.c @@ -93,7 +93,6 @@ int mt76x2u_mac_reset(struct mt76x02_dev *dev) mt76_wr(dev, MT_TX_LINK_CFG, 0x1020); mt76_wr(dev, MT_AUTO_RSP_CFG, 0x13); mt76_wr(dev, MT_MAX_LEN_CFG, 0x2f00); - mt76_wr(dev, MT_TX_RTS_CFG, 0x92b20); mt76_wr(dev, MT_WMM_AIFSN, 0x2273); mt76_wr(dev, MT_WMM_CWMIN, 0x2344); diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c index 5a349fe3e576..2585df512335 100644 --- a/drivers/net/wireless/mediatek/mt76/tx.c +++ b/drivers/net/wireless/mediatek/mt76/tx.c @@ -289,8 +289,11 @@ mt76_tx(struct mt76_dev *dev, struct ieee80211_sta *sta, dev->queue_ops->tx_queue_skb(dev, q, skb, wcid, sta); dev->queue_ops->kick(dev, q); - if (q->queued > q->ndesc - 8) + if (q->queued > q->ndesc - 8 && !q->stopped) { ieee80211_stop_queue(dev->hw, skb_get_queue_mapping(skb)); + q->stopped = true; + } + spin_unlock_bh(&q->lock); } EXPORT_SYMBOL_GPL(mt76_tx); @@ -374,7 +377,10 @@ mt76_release_buffered_frames(struct ieee80211_hw *hw, struct ieee80211_sta *sta, if (last_skb) { mt76_queue_ps_skb(dev, sta, last_skb, true); dev->queue_ops->kick(dev, hwq); + } else { + ieee80211_sta_eosp(sta); } + spin_unlock_bh(&hwq->lock); } EXPORT_SYMBOL_GPL(mt76_release_buffered_frames); @@ -577,6 +583,9 @@ void mt76_wake_tx_queue(struct ieee80211_hw *hw, struct ieee80211_txq *txq) struct mt76_txq *mtxq = (struct mt76_txq *) txq->drv_priv; struct mt76_queue *hwq = mtxq->hwq; + if (!test_bit(MT76_STATE_RUNNING, &dev->state)) + return; + spin_lock_bh(&hwq->lock); if (list_empty(&mtxq->list)) list_add_tail(&mtxq->list, &hwq->swq); diff --git a/drivers/net/wireless/mediatek/mt76/usb.c b/drivers/net/wireless/mediatek/mt76/usb.c index ae6ada370597..4c1abd492405 100644 --- a/drivers/net/wireless/mediatek/mt76/usb.c +++ b/drivers/net/wireless/mediatek/mt76/usb.c @@ -655,7 +655,11 @@ static void mt76u_tx_tasklet(unsigned long data) spin_lock_bh(&q->lock); } mt76_txq_schedule(dev, q); - wake = i < IEEE80211_NUM_ACS && q->queued < q->ndesc - 8; + + wake = q->stopped && q->queued < q->ndesc - 8; + if (wake) + q->stopped = false; + if (!q->queued) wake_up(&dev->tx_wait); diff --git a/drivers/net/wireless/mediatek/mt7601u/usb.c b/drivers/net/wireless/mediatek/mt7601u/usb.c index d8b7863f7926..6ae7f14dc9bf 100644 --- a/drivers/net/wireless/mediatek/mt7601u/usb.c +++ b/drivers/net/wireless/mediatek/mt7601u/usb.c @@ -303,6 +303,10 @@ static int mt7601u_probe(struct usb_interface *usb_intf, mac_rev = mt7601u_rr(dev, MT_MAC_CSR0); dev_info(dev->dev, "ASIC revision: %08x MAC revision: %08x\n", asic_rev, mac_rev); + if ((asic_rev >> 16) != 0x7601) { + ret = -ENODEV; + goto err; + } /* Note: vendor driver skips this check for MT7601U */ if (!(mt7601u_rr(dev, MT_EFUSE_CTRL) & MT_EFUSE_CTRL_SEL)) diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00.h b/drivers/net/wireless/ralink/rt2x00/rt2x00.h index 4b1744e9fb78..50b92ca92bd7 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00.h +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00.h @@ -673,7 +673,6 @@ enum rt2x00_state_flags { CONFIG_CHANNEL_HT40, CONFIG_POWERSAVING, CONFIG_HT_DISABLED, - CONFIG_QOS_DISABLED, CONFIG_MONITORING, /* diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c index 2825560e2424..e8462f25d252 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c @@ -642,19 +642,9 @@ void rt2x00mac_bss_info_changed(struct ieee80211_hw *hw, rt2x00dev->intf_associated--; rt2x00leds_led_assoc(rt2x00dev, !!rt2x00dev->intf_associated); - - clear_bit(CONFIG_QOS_DISABLED, &rt2x00dev->flags); } /* - * Check for access point which do not support 802.11e . We have to - * generate data frames sequence number in S/W for such AP, because - * of H/W bug. - */ - if (changes & BSS_CHANGED_QOS && !bss_conf->qos) - set_bit(CONFIG_QOS_DISABLED, &rt2x00dev->flags); - - /* * When the erp information has changed, we should perform * additional configuration steps. For all other changes we are done. */ diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c b/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c index 92ddc19e7bf7..4834b4eb0206 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c @@ -201,15 +201,18 @@ static void rt2x00queue_create_tx_descriptor_seq(struct rt2x00_dev *rt2x00dev, if (!rt2x00_has_cap_flag(rt2x00dev, REQUIRE_SW_SEQNO)) { /* * rt2800 has a H/W (or F/W) bug, device incorrectly increase - * seqno on retransmited data (non-QOS) frames. To workaround - * the problem let's generate seqno in software if QOS is - * disabled. + * seqno on retransmitted data (non-QOS) and management frames. + * To workaround the problem let's generate seqno in software. + * Except for beacons which are transmitted periodically by H/W + * hence hardware has to assign seqno for them. */ - if (test_bit(CONFIG_QOS_DISABLED, &rt2x00dev->flags)) - __clear_bit(ENTRY_TXD_GENERATE_SEQ, &txdesc->flags); - else + if (ieee80211_is_beacon(hdr->frame_control)) { + __set_bit(ENTRY_TXD_GENERATE_SEQ, &txdesc->flags); /* H/W will generate sequence number */ return; + } + + __clear_bit(ENTRY_TXD_GENERATE_SEQ, &txdesc->flags); } /* diff --git a/drivers/nfc/st95hf/core.c b/drivers/nfc/st95hf/core.c index 2b26f762fbc3..01acb6e53365 100644 --- a/drivers/nfc/st95hf/core.c +++ b/drivers/nfc/st95hf/core.c @@ -1074,6 +1074,12 @@ static const struct spi_device_id st95hf_id[] = { }; MODULE_DEVICE_TABLE(spi, st95hf_id); +static const struct of_device_id st95hf_spi_of_match[] = { + { .compatible = "st,st95hf" }, + { }, +}; +MODULE_DEVICE_TABLE(of, st95hf_spi_of_match); + static int st95hf_probe(struct spi_device *nfc_spi_dev) { int ret; @@ -1260,6 +1266,7 @@ static struct spi_driver st95hf_driver = { .driver = { .name = "st95hf", .owner = THIS_MODULE, + .of_match_table = of_match_ptr(st95hf_spi_of_match), }, .id_table = st95hf_id, .probe = st95hf_probe, diff --git a/drivers/nvdimm/btt_devs.c b/drivers/nvdimm/btt_devs.c index b72a303176c7..9486acc08402 100644 --- a/drivers/nvdimm/btt_devs.c +++ b/drivers/nvdimm/btt_devs.c @@ -198,14 +198,15 @@ static struct device *__nd_btt_create(struct nd_region *nd_region, return NULL; nd_btt->id = ida_simple_get(&nd_region->btt_ida, 0, 0, GFP_KERNEL); - if (nd_btt->id < 0) { - kfree(nd_btt); - return NULL; - } + if (nd_btt->id < 0) + goto out_nd_btt; nd_btt->lbasize = lbasize; - if (uuid) + if (uuid) { uuid = kmemdup(uuid, 16, GFP_KERNEL); + if (!uuid) + goto out_put_id; + } nd_btt->uuid = uuid; dev = &nd_btt->dev; dev_set_name(dev, "btt%d.%d", nd_region->id, nd_btt->id); @@ -220,6 +221,13 @@ static struct device *__nd_btt_create(struct nd_region *nd_region, return NULL; } return dev; + +out_put_id: + ida_simple_remove(&nd_region->btt_ida, nd_btt->id); + +out_nd_btt: + kfree(nd_btt); + return NULL; } struct device *nd_btt_create(struct nd_region *nd_region) diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index 7849bf1812c4..f293556cbbf6 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -2249,9 +2249,12 @@ static struct device *create_namespace_blk(struct nd_region *nd_region, if (!nsblk->uuid) goto blk_err; memcpy(name, nd_label->name, NSLABEL_NAME_LEN); - if (name[0]) + if (name[0]) { nsblk->alt_name = kmemdup(name, NSLABEL_NAME_LEN, GFP_KERNEL); + if (!nsblk->alt_name) + goto blk_err; + } res = nsblk_add_resource(nd_region, ndd, nsblk, __le64_to_cpu(nd_label->dpa)); if (!res) diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index bc2f700feef8..0279eb1da3ef 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -113,13 +113,13 @@ static void write_pmem(void *pmem_addr, struct page *page, while (len) { mem = kmap_atomic(page); - chunk = min_t(unsigned int, len, PAGE_SIZE); + chunk = min_t(unsigned int, len, PAGE_SIZE - off); memcpy_flushcache(pmem_addr, mem + off, chunk); kunmap_atomic(mem); len -= chunk; off = 0; page++; - pmem_addr += PAGE_SIZE; + pmem_addr += chunk; } } @@ -132,7 +132,7 @@ static blk_status_t read_pmem(struct page *page, unsigned int off, while (len) { mem = kmap_atomic(page); - chunk = min_t(unsigned int, len, PAGE_SIZE); + chunk = min_t(unsigned int, len, PAGE_SIZE - off); rem = memcpy_mcsafe(mem + off, pmem_addr, chunk); kunmap_atomic(mem); if (rem) @@ -140,7 +140,7 @@ static blk_status_t read_pmem(struct page *page, unsigned int off, len -= chunk; off = 0; page++; - pmem_addr += PAGE_SIZE; + pmem_addr += chunk; } return BLK_STS_OK; } diff --git a/drivers/nvdimm/security.c b/drivers/nvdimm/security.c index f8bb746a549f..a570f2263a42 100644 --- a/drivers/nvdimm/security.c +++ b/drivers/nvdimm/security.c @@ -22,6 +22,8 @@ static bool key_revalidate = true; module_param(key_revalidate, bool, 0444); MODULE_PARM_DESC(key_revalidate, "Require key validation at init."); +static const char zero_key[NVDIMM_PASSPHRASE_LEN]; + static void *key_data(struct key *key) { struct encrypted_key_payload *epayload = dereference_key_locked(key); @@ -75,6 +77,16 @@ static struct key *nvdimm_request_key(struct nvdimm *nvdimm) return key; } +static const void *nvdimm_get_key_payload(struct nvdimm *nvdimm, + struct key **key) +{ + *key = nvdimm_request_key(nvdimm); + if (!*key) + return zero_key; + + return key_data(*key); +} + static struct key *nvdimm_lookup_user_key(struct nvdimm *nvdimm, key_serial_t id, int subclass) { @@ -105,36 +117,57 @@ static struct key *nvdimm_lookup_user_key(struct nvdimm *nvdimm, return key; } -static struct key *nvdimm_key_revalidate(struct nvdimm *nvdimm) +static const void *nvdimm_get_user_key_payload(struct nvdimm *nvdimm, + key_serial_t id, int subclass, struct key **key) +{ + *key = NULL; + if (id == 0) { + if (subclass == NVDIMM_BASE_KEY) + return zero_key; + else + return NULL; + } + + *key = nvdimm_lookup_user_key(nvdimm, id, subclass); + if (!*key) + return NULL; + + return key_data(*key); +} + + +static int nvdimm_key_revalidate(struct nvdimm *nvdimm) { struct key *key; int rc; + const void *data; if (!nvdimm->sec.ops->change_key) - return NULL; + return -EOPNOTSUPP; - key = nvdimm_request_key(nvdimm); - if (!key) - return NULL; + data = nvdimm_get_key_payload(nvdimm, &key); /* * Send the same key to the hardware as new and old key to * verify that the key is good. */ - rc = nvdimm->sec.ops->change_key(nvdimm, key_data(key), - key_data(key), NVDIMM_USER); + rc = nvdimm->sec.ops->change_key(nvdimm, data, data, NVDIMM_USER); if (rc < 0) { nvdimm_put_key(key); - key = NULL; + return rc; } - return key; + + nvdimm_put_key(key); + nvdimm->sec.state = nvdimm_security_state(nvdimm, NVDIMM_USER); + return 0; } static int __nvdimm_security_unlock(struct nvdimm *nvdimm) { struct device *dev = &nvdimm->dev; struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev); - struct key *key = NULL; + struct key *key; + const void *data; int rc; /* The bus lock should be held at the top level of the call stack */ @@ -160,16 +193,11 @@ static int __nvdimm_security_unlock(struct nvdimm *nvdimm) if (!key_revalidate) return 0; - key = nvdimm_key_revalidate(nvdimm); - if (!key) - return nvdimm_security_freeze(nvdimm); + return nvdimm_key_revalidate(nvdimm); } else - key = nvdimm_request_key(nvdimm); + data = nvdimm_get_key_payload(nvdimm, &key); - if (!key) - return -ENOKEY; - - rc = nvdimm->sec.ops->unlock(nvdimm, key_data(key)); + rc = nvdimm->sec.ops->unlock(nvdimm, data); dev_dbg(dev, "key: %d unlock: %s\n", key_serial(key), rc == 0 ? "success" : "fail"); @@ -195,6 +223,7 @@ int nvdimm_security_disable(struct nvdimm *nvdimm, unsigned int keyid) struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev); struct key *key; int rc; + const void *data; /* The bus lock should be held at the top level of the call stack */ lockdep_assert_held(&nvdimm_bus->reconfig_mutex); @@ -214,11 +243,12 @@ int nvdimm_security_disable(struct nvdimm *nvdimm, unsigned int keyid) return -EBUSY; } - key = nvdimm_lookup_user_key(nvdimm, keyid, NVDIMM_BASE_KEY); - if (!key) + data = nvdimm_get_user_key_payload(nvdimm, keyid, + NVDIMM_BASE_KEY, &key); + if (!data) return -ENOKEY; - rc = nvdimm->sec.ops->disable(nvdimm, key_data(key)); + rc = nvdimm->sec.ops->disable(nvdimm, data); dev_dbg(dev, "key: %d disable: %s\n", key_serial(key), rc == 0 ? "success" : "fail"); @@ -235,6 +265,7 @@ int nvdimm_security_update(struct nvdimm *nvdimm, unsigned int keyid, struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev); struct key *key, *newkey; int rc; + const void *data, *newdata; /* The bus lock should be held at the top level of the call stack */ lockdep_assert_held(&nvdimm_bus->reconfig_mutex); @@ -249,22 +280,19 @@ int nvdimm_security_update(struct nvdimm *nvdimm, unsigned int keyid, return -EIO; } - if (keyid == 0) - key = NULL; - else { - key = nvdimm_lookup_user_key(nvdimm, keyid, NVDIMM_BASE_KEY); - if (!key) - return -ENOKEY; - } + data = nvdimm_get_user_key_payload(nvdimm, keyid, + NVDIMM_BASE_KEY, &key); + if (!data) + return -ENOKEY; - newkey = nvdimm_lookup_user_key(nvdimm, new_keyid, NVDIMM_NEW_KEY); - if (!newkey) { + newdata = nvdimm_get_user_key_payload(nvdimm, new_keyid, + NVDIMM_NEW_KEY, &newkey); + if (!newdata) { nvdimm_put_key(key); return -ENOKEY; } - rc = nvdimm->sec.ops->change_key(nvdimm, key ? key_data(key) : NULL, - key_data(newkey), pass_type); + rc = nvdimm->sec.ops->change_key(nvdimm, data, newdata, pass_type); dev_dbg(dev, "key: %d %d update%s: %s\n", key_serial(key), key_serial(newkey), pass_type == NVDIMM_MASTER ? "(master)" : "(user)", @@ -286,8 +314,9 @@ int nvdimm_security_erase(struct nvdimm *nvdimm, unsigned int keyid, { struct device *dev = &nvdimm->dev; struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev); - struct key *key; + struct key *key = NULL; int rc; + const void *data; /* The bus lock should be held at the top level of the call stack */ lockdep_assert_held(&nvdimm_bus->reconfig_mutex); @@ -319,11 +348,12 @@ int nvdimm_security_erase(struct nvdimm *nvdimm, unsigned int keyid, return -EOPNOTSUPP; } - key = nvdimm_lookup_user_key(nvdimm, keyid, NVDIMM_BASE_KEY); - if (!key) + data = nvdimm_get_user_key_payload(nvdimm, keyid, + NVDIMM_BASE_KEY, &key); + if (!data) return -ENOKEY; - rc = nvdimm->sec.ops->erase(nvdimm, key_data(key), pass_type); + rc = nvdimm->sec.ops->erase(nvdimm, data, pass_type); dev_dbg(dev, "key: %d erase%s: %s\n", key_serial(key), pass_type == NVDIMM_MASTER ? "(master)" : "(user)", rc == 0 ? "success" : "fail"); @@ -337,8 +367,9 @@ int nvdimm_security_overwrite(struct nvdimm *nvdimm, unsigned int keyid) { struct device *dev = &nvdimm->dev; struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev); - struct key *key; + struct key *key = NULL; int rc; + const void *data; /* The bus lock should be held at the top level of the call stack */ lockdep_assert_held(&nvdimm_bus->reconfig_mutex); @@ -368,15 +399,12 @@ int nvdimm_security_overwrite(struct nvdimm *nvdimm, unsigned int keyid) return -EBUSY; } - if (keyid == 0) - key = NULL; - else { - key = nvdimm_lookup_user_key(nvdimm, keyid, NVDIMM_BASE_KEY); - if (!key) - return -ENOKEY; - } + data = nvdimm_get_user_key_payload(nvdimm, keyid, + NVDIMM_BASE_KEY, &key); + if (!data) + return -ENOKEY; - rc = nvdimm->sec.ops->overwrite(nvdimm, key ? key_data(key) : NULL); + rc = nvdimm->sec.ops->overwrite(nvdimm, data); dev_dbg(dev, "key: %d overwrite submission: %s\n", key_serial(key), rc == 0 ? "success" : "fail"); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 470601980794..2c43e12b70af 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -288,7 +288,7 @@ bool nvme_cancel_request(struct request *req, void *data, bool reserved) "Cancelling I/O %d", req->tag); nvme_req(req)->status = NVME_SC_ABORT_REQ; - blk_mq_complete_request(req); + blk_mq_complete_request_sync(req); return true; } EXPORT_SYMBOL_GPL(nvme_cancel_request); diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index f3b9d91ba0df..6d8451356eac 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1845,7 +1845,7 @@ nvme_fc_init_queue(struct nvme_fc_ctrl *ctrl, int idx) memset(queue, 0, sizeof(*queue)); queue->ctrl = ctrl; queue->qnum = idx; - atomic_set(&queue->csn, 1); + atomic_set(&queue->csn, 0); queue->dev = ctrl->dev; if (idx > 0) @@ -1887,7 +1887,7 @@ nvme_fc_free_queue(struct nvme_fc_queue *queue) */ queue->connection_id = 0; - atomic_set(&queue->csn, 1); + atomic_set(&queue->csn, 0); } static void @@ -2183,7 +2183,6 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue, { struct nvme_fc_cmd_iu *cmdiu = &op->cmd_iu; struct nvme_command *sqe = &cmdiu->sqe; - u32 csn; int ret, opstate; /* @@ -2198,8 +2197,6 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue, /* format the FC-NVME CMD IU and fcp_req */ cmdiu->connection_id = cpu_to_be64(queue->connection_id); - csn = atomic_inc_return(&queue->csn); - cmdiu->csn = cpu_to_be32(csn); cmdiu->data_len = cpu_to_be32(data_len); switch (io_dir) { case NVMEFC_FCP_WRITE: @@ -2257,11 +2254,24 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue, if (!(op->flags & FCOP_FLAGS_AEN)) blk_mq_start_request(op->rq); + cmdiu->csn = cpu_to_be32(atomic_inc_return(&queue->csn)); ret = ctrl->lport->ops->fcp_io(&ctrl->lport->localport, &ctrl->rport->remoteport, queue->lldd_handle, &op->fcp_req); if (ret) { + /* + * If the lld fails to send the command is there an issue with + * the csn value? If the command that fails is the Connect, + * no - as the connection won't be live. If it is a command + * post-connect, it's possible a gap in csn may be created. + * Does this matter? As Linux initiators don't send fused + * commands, no. The gap would exist, but as there's nothing + * that depends on csn order to be delivered on the target + * side, it shouldn't hurt. It would be difficult for a + * target to even detect the csn gap as it has no idea when the + * cmd with the csn was supposed to arrive. + */ opstate = atomic_xchg(&op->state, FCPOP_STATE_COMPLETE); __nvme_fc_fcpop_chk_teardowns(ctrl, op, opstate); diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 2839bb70badf..f0716f6ce41f 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -404,15 +404,12 @@ static inline bool nvme_state_is_live(enum nvme_ana_state state) static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc, struct nvme_ns *ns) { - enum nvme_ana_state old; - mutex_lock(&ns->head->lock); - old = ns->ana_state; ns->ana_grpid = le32_to_cpu(desc->grpid); ns->ana_state = desc->state; clear_bit(NVME_NS_ANA_PENDING, &ns->flags); - if (nvme_state_is_live(ns->ana_state) && !nvme_state_is_live(old)) + if (nvme_state_is_live(ns->ana_state)) nvme_mpath_set_live(ns); mutex_unlock(&ns->head->lock); } diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index e7e08889865e..68c49dd67210 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -627,7 +627,7 @@ static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb, return ret; } -static inline void nvme_tcp_end_request(struct request *rq, __le16 status) +static inline void nvme_tcp_end_request(struct request *rq, u16 status) { union nvme_result res = {}; diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 76250181fee0..9f72d515fc4b 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -24,6 +24,11 @@ u32 nvmet_get_log_page_len(struct nvme_command *cmd) return len; } +u64 nvmet_get_log_page_offset(struct nvme_command *cmd) +{ + return le64_to_cpu(cmd->get_log_page.lpo); +} + static void nvmet_execute_get_log_page_noop(struct nvmet_req *req) { nvmet_req_complete(req, nvmet_zero_sgl(req, 0, req->data_len)); diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 2d73b66e3686..b3e765a95af8 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -509,7 +509,7 @@ int nvmet_ns_enable(struct nvmet_ns *ns) ret = nvmet_p2pmem_ns_enable(ns); if (ret) - goto out_unlock; + goto out_dev_disable; list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) nvmet_p2pmem_ns_add_p2p(ctrl, ns); @@ -550,7 +550,7 @@ out_unlock: out_dev_put: list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) pci_dev_put(radix_tree_delete(&ctrl->p2p_ns_map, ns->nsid)); - +out_dev_disable: nvmet_ns_dev_disable(ns); goto out_unlock; } diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c index c872b47a88f3..33ed95e72d6b 100644 --- a/drivers/nvme/target/discovery.c +++ b/drivers/nvme/target/discovery.c @@ -131,54 +131,76 @@ static void nvmet_set_disc_traddr(struct nvmet_req *req, struct nvmet_port *port memcpy(traddr, port->disc_addr.traddr, NVMF_TRADDR_SIZE); } +static size_t discovery_log_entries(struct nvmet_req *req) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + struct nvmet_subsys_link *p; + struct nvmet_port *r; + size_t entries = 0; + + list_for_each_entry(p, &req->port->subsystems, entry) { + if (!nvmet_host_allowed(p->subsys, ctrl->hostnqn)) + continue; + entries++; + } + list_for_each_entry(r, &req->port->referrals, entry) + entries++; + return entries; +} + static void nvmet_execute_get_disc_log_page(struct nvmet_req *req) { const int entry_size = sizeof(struct nvmf_disc_rsp_page_entry); struct nvmet_ctrl *ctrl = req->sq->ctrl; struct nvmf_disc_rsp_page_hdr *hdr; + u64 offset = nvmet_get_log_page_offset(req->cmd); size_t data_len = nvmet_get_log_page_len(req->cmd); - size_t alloc_len = max(data_len, sizeof(*hdr)); - int residual_len = data_len - sizeof(*hdr); + size_t alloc_len; struct nvmet_subsys_link *p; struct nvmet_port *r; u32 numrec = 0; u16 status = 0; + void *buffer; + + /* Spec requires dword aligned offsets */ + if (offset & 0x3) { + status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + goto out; + } /* * Make sure we're passing at least a buffer of response header size. * If host provided data len is less than the header size, only the * number of bytes requested by host will be sent to host. */ - hdr = kzalloc(alloc_len, GFP_KERNEL); - if (!hdr) { + down_read(&nvmet_config_sem); + alloc_len = sizeof(*hdr) + entry_size * discovery_log_entries(req); + buffer = kzalloc(alloc_len, GFP_KERNEL); + if (!buffer) { + up_read(&nvmet_config_sem); status = NVME_SC_INTERNAL; goto out; } - down_read(&nvmet_config_sem); + hdr = buffer; list_for_each_entry(p, &req->port->subsystems, entry) { + char traddr[NVMF_TRADDR_SIZE]; + if (!nvmet_host_allowed(p->subsys, ctrl->hostnqn)) continue; - if (residual_len >= entry_size) { - char traddr[NVMF_TRADDR_SIZE]; - - nvmet_set_disc_traddr(req, req->port, traddr); - nvmet_format_discovery_entry(hdr, req->port, - p->subsys->subsysnqn, traddr, - NVME_NQN_NVME, numrec); - residual_len -= entry_size; - } + + nvmet_set_disc_traddr(req, req->port, traddr); + nvmet_format_discovery_entry(hdr, req->port, + p->subsys->subsysnqn, traddr, + NVME_NQN_NVME, numrec); numrec++; } list_for_each_entry(r, &req->port->referrals, entry) { - if (residual_len >= entry_size) { - nvmet_format_discovery_entry(hdr, r, - NVME_DISC_SUBSYS_NAME, - r->disc_addr.traddr, - NVME_NQN_DISC, numrec); - residual_len -= entry_size; - } + nvmet_format_discovery_entry(hdr, r, + NVME_DISC_SUBSYS_NAME, + r->disc_addr.traddr, + NVME_NQN_DISC, numrec); numrec++; } @@ -190,8 +212,8 @@ static void nvmet_execute_get_disc_log_page(struct nvmet_req *req) up_read(&nvmet_config_sem); - status = nvmet_copy_to_sgl(req, 0, hdr, data_len); - kfree(hdr); + status = nvmet_copy_to_sgl(req, 0, buffer + offset, data_len); + kfree(buffer); out: nvmet_req_complete(req, status); } diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c index 3e43212d3c1c..bc6ebb51b0bf 100644 --- a/drivers/nvme/target/io-cmd-file.c +++ b/drivers/nvme/target/io-cmd-file.c @@ -75,11 +75,11 @@ err: return ret; } -static void nvmet_file_init_bvec(struct bio_vec *bv, struct sg_page_iter *iter) +static void nvmet_file_init_bvec(struct bio_vec *bv, struct scatterlist *sg) { - bv->bv_page = sg_page_iter_page(iter); - bv->bv_offset = iter->sg->offset; - bv->bv_len = PAGE_SIZE - iter->sg->offset; + bv->bv_page = sg_page(sg); + bv->bv_offset = sg->offset; + bv->bv_len = sg->length; } static ssize_t nvmet_file_submit_bvec(struct nvmet_req *req, loff_t pos, @@ -128,14 +128,14 @@ static void nvmet_file_io_done(struct kiocb *iocb, long ret, long ret2) static bool nvmet_file_execute_io(struct nvmet_req *req, int ki_flags) { - ssize_t nr_bvec = DIV_ROUND_UP(req->data_len, PAGE_SIZE); - struct sg_page_iter sg_pg_iter; + ssize_t nr_bvec = req->sg_cnt; unsigned long bv_cnt = 0; bool is_sync = false; size_t len = 0, total_len = 0; ssize_t ret = 0; loff_t pos; - + int i; + struct scatterlist *sg; if (req->f.mpool_alloc && nr_bvec > NVMET_MAX_MPOOL_BVEC) is_sync = true; @@ -147,8 +147,8 @@ static bool nvmet_file_execute_io(struct nvmet_req *req, int ki_flags) } memset(&req->f.iocb, 0, sizeof(struct kiocb)); - for_each_sg_page(req->sg, &sg_pg_iter, req->sg_cnt, 0) { - nvmet_file_init_bvec(&req->f.bvec[bv_cnt], &sg_pg_iter); + for_each_sg(req->sg, sg, req->sg_cnt, i) { + nvmet_file_init_bvec(&req->f.bvec[bv_cnt], sg); len += req->f.bvec[bv_cnt].bv_len; total_len += req->f.bvec[bv_cnt].bv_len; bv_cnt++; @@ -225,7 +225,7 @@ static void nvmet_file_submit_buffered_io(struct nvmet_req *req) static void nvmet_file_execute_rw(struct nvmet_req *req) { - ssize_t nr_bvec = DIV_ROUND_UP(req->data_len, PAGE_SIZE); + ssize_t nr_bvec = req->sg_cnt; if (!req->sg_cnt || !nr_bvec) { nvmet_req_complete(req, 0); diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 51e49efd7849..1653d19b187f 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -428,6 +428,7 @@ u16 nvmet_copy_from_sgl(struct nvmet_req *req, off_t off, void *buf, u16 nvmet_zero_sgl(struct nvmet_req *req, off_t off, size_t len); u32 nvmet_get_log_page_len(struct nvme_command *cmd); +u64 nvmet_get_log_page_offset(struct nvme_command *cmd); extern struct list_head *nvmet_ports; void nvmet_port_disc_changed(struct nvmet_port *port, diff --git a/drivers/of/of_net.c b/drivers/of/of_net.c index 810ab0fbcccb..d820f3edd431 100644 --- a/drivers/of/of_net.c +++ b/drivers/of/of_net.c @@ -7,7 +7,6 @@ */ #include <linux/etherdevice.h> #include <linux/kernel.h> -#include <linux/nvmem-consumer.h> #include <linux/of_net.h> #include <linux/phy.h> #include <linux/export.h> diff --git a/drivers/parisc/iosapic.c b/drivers/parisc/iosapic.c index 1be571c20062..6bad04cbb1d3 100644 --- a/drivers/parisc/iosapic.c +++ b/drivers/parisc/iosapic.c @@ -157,8 +157,12 @@ #define DBG_IRT(x...) #endif +#ifdef CONFIG_64BIT +#define COMPARE_IRTE_ADDR(irte, hpa) ((irte)->dest_iosapic_addr == (hpa)) +#else #define COMPARE_IRTE_ADDR(irte, hpa) \ - ((irte)->dest_iosapic_addr == F_EXTEND(hpa)) + ((irte)->dest_iosapic_addr == ((hpa) | 0xffffffff00000000ULL)) +#endif #define IOSAPIC_REG_SELECT 0x00 #define IOSAPIC_REG_WINDOW 0x10 diff --git a/drivers/parport/daisy.c b/drivers/parport/daisy.c index 56dd83a45e55..5484a46dafda 100644 --- a/drivers/parport/daisy.c +++ b/drivers/parport/daisy.c @@ -213,12 +213,10 @@ void parport_daisy_fini(struct parport *port) struct pardevice *parport_open(int devnum, const char *name) { struct daisydev *p = topology; - struct pardev_cb par_cb; struct parport *port; struct pardevice *dev; int daisy; - memset(&par_cb, 0, sizeof(par_cb)); spin_lock(&topology_lock); while (p && p->devnum != devnum) p = p->next; @@ -232,7 +230,7 @@ struct pardevice *parport_open(int devnum, const char *name) port = parport_get_port(p->port); spin_unlock(&topology_lock); - dev = parport_register_dev_model(port, name, &par_cb, devnum); + dev = parport_register_device(port, name, NULL, NULL, NULL, 0, NULL); parport_put_port(port); if (!dev) return NULL; @@ -482,31 +480,3 @@ static int assign_addrs(struct parport *port) kfree(deviceid); return detected; } - -static int daisy_drv_probe(struct pardevice *par_dev) -{ - struct device_driver *drv = par_dev->dev.driver; - - if (strcmp(drv->name, "daisy_drv")) - return -ENODEV; - if (strcmp(par_dev->name, daisy_dev_name)) - return -ENODEV; - - return 0; -} - -static struct parport_driver daisy_driver = { - .name = "daisy_drv", - .probe = daisy_drv_probe, - .devmodel = true, -}; - -int daisy_drv_init(void) -{ - return parport_register_driver(&daisy_driver); -} - -void daisy_drv_exit(void) -{ - parport_unregister_driver(&daisy_driver); -} diff --git a/drivers/parport/probe.c b/drivers/parport/probe.c index e5e6a463a941..e035174ba205 100644 --- a/drivers/parport/probe.c +++ b/drivers/parport/probe.c @@ -257,7 +257,7 @@ static ssize_t parport_read_device_id (struct parport *port, char *buffer, ssize_t parport_device_id (int devnum, char *buffer, size_t count) { ssize_t retval = -ENXIO; - struct pardevice *dev = parport_open(devnum, daisy_dev_name); + struct pardevice *dev = parport_open (devnum, "Device ID probe"); if (!dev) return -ENXIO; diff --git a/drivers/parport/share.c b/drivers/parport/share.c index 0171b8dbcdcd..5dc53d420ca8 100644 --- a/drivers/parport/share.c +++ b/drivers/parport/share.c @@ -137,19 +137,11 @@ static struct bus_type parport_bus_type = { int parport_bus_init(void) { - int retval; - - retval = bus_register(&parport_bus_type); - if (retval) - return retval; - daisy_drv_init(); - - return 0; + return bus_register(&parport_bus_type); } void parport_bus_exit(void) { - daisy_drv_exit(); bus_unregister(&parport_bus_type); } diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c index 3f3df4c29f6e..905282a8ddaa 100644 --- a/drivers/pci/hotplug/pciehp_ctrl.c +++ b/drivers/pci/hotplug/pciehp_ctrl.c @@ -115,6 +115,10 @@ static void remove_board(struct controller *ctrl, bool safe_removal) * removed from the slot/adapter. */ msleep(1000); + + /* Ignore link or presence changes caused by power off */ + atomic_and(~(PCI_EXP_SLTSTA_DLLSC | PCI_EXP_SLTSTA_PDC), + &ctrl->pending_events); } /* turn off Green LED */ diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 7c1b362f599a..766f5779db92 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -6262,8 +6262,7 @@ static int __init pci_setup(char *str) } else if (!strncmp(str, "pcie_scan_all", 13)) { pci_add_flags(PCI_SCAN_ALL_PCIE_DEVS); } else if (!strncmp(str, "disable_acs_redir=", 18)) { - disable_acs_redir_param = - kstrdup(str + 18, GFP_KERNEL); + disable_acs_redir_param = str + 18; } else { printk(KERN_ERR "PCI: Unknown option `%s'\n", str); @@ -6274,3 +6273,19 @@ static int __init pci_setup(char *str) return 0; } early_param("pci", pci_setup); + +/* + * 'disable_acs_redir_param' is initialized in pci_setup(), above, to point + * to data in the __initdata section which will be freed after the init + * sequence is complete. We can't allocate memory in pci_setup() because some + * architectures do not have any memory allocation service available during + * an early_param() call. So we allocate memory and copy the variable here + * before the init section is freed. + */ +static int __init pci_realloc_setup_params(void) +{ + disable_acs_redir_param = kstrdup(disable_acs_redir_param, GFP_KERNEL); + + return 0; +} +pure_initcall(pci_realloc_setup_params); diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 224d88634115..d994839a3e24 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -273,6 +273,7 @@ enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev); u32 pcie_bandwidth_capable(struct pci_dev *dev, enum pci_bus_speed *speed, enum pcie_link_width *width); void __pcie_print_link_status(struct pci_dev *dev, bool verbose); +void pcie_report_downtraining(struct pci_dev *dev); /* Single Root I/O Virtualization */ struct pci_sriov { diff --git a/drivers/pci/pcie/Kconfig b/drivers/pci/pcie/Kconfig index 5cbdbca904ac..362eb8cfa53b 100644 --- a/drivers/pci/pcie/Kconfig +++ b/drivers/pci/pcie/Kconfig @@ -142,3 +142,11 @@ config PCIE_PTM This is only useful if you have devices that support PTM, but it is safe to enable even if you don't. + +config PCIE_BW + bool "PCI Express Bandwidth Change Notification" + depends on PCIEPORTBUS + help + This enables PCI Express Bandwidth Change Notification. If + you know link width or rate changes occur only to correct + unreliable links, you may answer Y. diff --git a/drivers/pci/pcie/Makefile b/drivers/pci/pcie/Makefile index f1d7bc1e5efa..efb9d2e71e9e 100644 --- a/drivers/pci/pcie/Makefile +++ b/drivers/pci/pcie/Makefile @@ -3,7 +3,6 @@ # Makefile for PCI Express features and port driver pcieportdrv-y := portdrv_core.o portdrv_pci.o err.o -pcieportdrv-y += bw_notification.o obj-$(CONFIG_PCIEPORTBUS) += pcieportdrv.o @@ -13,3 +12,4 @@ obj-$(CONFIG_PCIEAER_INJECT) += aer_inject.o obj-$(CONFIG_PCIE_PME) += pme.o obj-$(CONFIG_PCIE_DPC) += dpc.o obj-$(CONFIG_PCIE_PTM) += ptm.o +obj-$(CONFIG_PCIE_BW) += bw_notification.o diff --git a/drivers/pci/pcie/bw_notification.c b/drivers/pci/pcie/bw_notification.c index d2eae3b7cc0f..4fa9e3523ee1 100644 --- a/drivers/pci/pcie/bw_notification.c +++ b/drivers/pci/pcie/bw_notification.c @@ -30,6 +30,8 @@ static void pcie_enable_link_bandwidth_notification(struct pci_dev *dev) { u16 lnk_ctl; + pcie_capability_write_word(dev, PCI_EXP_LNKSTA, PCI_EXP_LNKSTA_LBMS); + pcie_capability_read_word(dev, PCI_EXP_LNKCTL, &lnk_ctl); lnk_ctl |= PCI_EXP_LNKCTL_LBMIE; pcie_capability_write_word(dev, PCI_EXP_LNKCTL, lnk_ctl); @@ -44,11 +46,10 @@ static void pcie_disable_link_bandwidth_notification(struct pci_dev *dev) pcie_capability_write_word(dev, PCI_EXP_LNKCTL, lnk_ctl); } -static irqreturn_t pcie_bw_notification_handler(int irq, void *context) +static irqreturn_t pcie_bw_notification_irq(int irq, void *context) { struct pcie_device *srv = context; struct pci_dev *port = srv->port; - struct pci_dev *dev; u16 link_status, events; int ret; @@ -58,17 +59,26 @@ static irqreturn_t pcie_bw_notification_handler(int irq, void *context) if (ret != PCIBIOS_SUCCESSFUL || !events) return IRQ_NONE; + pcie_capability_write_word(port, PCI_EXP_LNKSTA, events); + pcie_update_link_speed(port->subordinate, link_status); + return IRQ_WAKE_THREAD; +} + +static irqreturn_t pcie_bw_notification_handler(int irq, void *context) +{ + struct pcie_device *srv = context; + struct pci_dev *port = srv->port; + struct pci_dev *dev; + /* * Print status from downstream devices, not this root port or * downstream switch port. */ down_read(&pci_bus_sem); list_for_each_entry(dev, &port->subordinate->devices, bus_list) - __pcie_print_link_status(dev, false); + pcie_report_downtraining(dev); up_read(&pci_bus_sem); - pcie_update_link_speed(port->subordinate, link_status); - pcie_capability_write_word(port, PCI_EXP_LNKSTA, events); return IRQ_HANDLED; } @@ -80,7 +90,8 @@ static int pcie_bandwidth_notification_probe(struct pcie_device *srv) if (!pcie_link_bandwidth_notification_supported(srv->port)) return -ENODEV; - ret = request_threaded_irq(srv->irq, NULL, pcie_bw_notification_handler, + ret = request_threaded_irq(srv->irq, pcie_bw_notification_irq, + pcie_bw_notification_handler, IRQF_SHARED, "PCIe BW notif", srv); if (ret) return ret; diff --git a/drivers/pci/pcie/portdrv.h b/drivers/pci/pcie/portdrv.h index 1d50dc58ac40..944827a8c7d3 100644 --- a/drivers/pci/pcie/portdrv.h +++ b/drivers/pci/pcie/portdrv.h @@ -49,7 +49,11 @@ int pcie_dpc_init(void); static inline int pcie_dpc_init(void) { return 0; } #endif +#ifdef CONFIG_PCIE_BW int pcie_bandwidth_notification_init(void); +#else +static inline int pcie_bandwidth_notification_init(void) { return 0; } +#endif /* Port Type */ #define PCIE_ANY_PORT (~0) diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c index 7d04f9d087a6..1b330129089f 100644 --- a/drivers/pci/pcie/portdrv_core.c +++ b/drivers/pci/pcie/portdrv_core.c @@ -55,7 +55,8 @@ static int pcie_message_numbers(struct pci_dev *dev, int mask, * 7.8.2, 7.10.10, 7.31.2. */ - if (mask & (PCIE_PORT_SERVICE_PME | PCIE_PORT_SERVICE_HP)) { + if (mask & (PCIE_PORT_SERVICE_PME | PCIE_PORT_SERVICE_HP | + PCIE_PORT_SERVICE_BWNOTIF)) { pcie_capability_read_word(dev, PCI_EXP_FLAGS, ®16); *pme = (reg16 & PCI_EXP_FLAGS_IRQ) >> 9; nvec = *pme + 1; diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 2ec0df04e0dc..7e12d0163863 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2388,7 +2388,7 @@ static struct pci_dev *pci_scan_device(struct pci_bus *bus, int devfn) return dev; } -static void pcie_report_downtraining(struct pci_dev *dev) +void pcie_report_downtraining(struct pci_dev *dev) { if (!pci_is_pcie(dev)) return; diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index a59ad09ce911..a077f67fe1da 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -3877,6 +3877,8 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9128, /* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c14 */ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9130, quirk_dma_func1_alias); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9170, + quirk_dma_func1_alias); /* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c47 + c57 */ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9172, quirk_dma_func1_alias); diff --git a/drivers/phy/allwinner/phy-sun4i-usb.c b/drivers/phy/allwinner/phy-sun4i-usb.c index 5163097b43df..4bbd9ede38c8 100644 --- a/drivers/phy/allwinner/phy-sun4i-usb.c +++ b/drivers/phy/allwinner/phy-sun4i-usb.c @@ -485,8 +485,11 @@ static int sun4i_usb_phy_set_mode(struct phy *_phy, struct sun4i_usb_phy_data *data = to_sun4i_usb_phy_data(phy); int new_mode; - if (phy->index != 0) + if (phy->index != 0) { + if (mode == PHY_MODE_USB_HOST) + return 0; return -EINVAL; + } switch (mode) { case PHY_MODE_USB_HOST: diff --git a/drivers/platform/x86/pmc_atom.c b/drivers/platform/x86/pmc_atom.c index 8f018b3f3cd4..c7039f52ad51 100644 --- a/drivers/platform/x86/pmc_atom.c +++ b/drivers/platform/x86/pmc_atom.c @@ -17,6 +17,7 @@ #include <linux/debugfs.h> #include <linux/device.h> +#include <linux/dmi.h> #include <linux/init.h> #include <linux/io.h> #include <linux/platform_data/x86/clk-pmc-atom.h> @@ -391,11 +392,27 @@ static int pmc_dbgfs_register(struct pmc_dev *pmc) } #endif /* CONFIG_DEBUG_FS */ +/* + * Some systems need one or more of their pmc_plt_clks to be + * marked as critical. + */ +static const struct dmi_system_id critclk_systems[] = { + { + .ident = "MPL CEC1x", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "MPL AG"), + DMI_MATCH(DMI_PRODUCT_NAME, "CEC10 Family"), + }, + }, + { /*sentinel*/ } +}; + static int pmc_setup_clks(struct pci_dev *pdev, void __iomem *pmc_regmap, const struct pmc_data *pmc_data) { struct platform_device *clkdev; struct pmc_clk_data *clk_data; + const struct dmi_system_id *d = dmi_first_match(critclk_systems); clk_data = kzalloc(sizeof(*clk_data), GFP_KERNEL); if (!clk_data) @@ -403,6 +420,10 @@ static int pmc_setup_clks(struct pci_dev *pdev, void __iomem *pmc_regmap, clk_data->base = pmc_regmap; /* offset is added by client */ clk_data->clks = pmc_data->clks; + if (d) { + clk_data->critical = true; + pr_info("%s critclks quirk enabled\n", d->ident); + } clkdev = platform_device_register_data(&pdev->dev, "clk-pmc-atom", PLATFORM_DEVID_NONE, diff --git a/drivers/power/supply/cpcap-battery.c b/drivers/power/supply/cpcap-battery.c index 08d5037fd052..6887870ba32c 100644 --- a/drivers/power/supply/cpcap-battery.c +++ b/drivers/power/supply/cpcap-battery.c @@ -221,6 +221,9 @@ static int cpcap_battery_cc_raw_div(struct cpcap_battery_ddata *ddata, int avg_current; u32 cc_lsb; + if (!divider) + return 0; + sample &= 0xffffff; /* 24-bits, unsigned */ offset &= 0x7ff; /* 10-bits, signed */ diff --git a/drivers/power/supply/goldfish_battery.c b/drivers/power/supply/goldfish_battery.c index ad969d9fc981..c2644a9fe80f 100644 --- a/drivers/power/supply/goldfish_battery.c +++ b/drivers/power/supply/goldfish_battery.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL +// SPDX-License-Identifier: GPL-2.0 /* * Power supply driver for the goldfish emulator * diff --git a/drivers/power/supply/power_supply_sysfs.c b/drivers/power/supply/power_supply_sysfs.c index dce24f596160..5358a80d854f 100644 --- a/drivers/power/supply/power_supply_sysfs.c +++ b/drivers/power/supply/power_supply_sysfs.c @@ -383,15 +383,11 @@ int power_supply_uevent(struct device *dev, struct kobj_uevent_env *env) char *prop_buf; char *attrname; - dev_dbg(dev, "uevent\n"); - if (!psy || !psy->desc) { dev_dbg(dev, "No power supply yet\n"); return ret; } - dev_dbg(dev, "POWER_SUPPLY_NAME=%s\n", psy->desc->name); - ret = add_uevent_var(env, "POWER_SUPPLY_NAME=%s", psy->desc->name); if (ret) return ret; @@ -427,8 +423,6 @@ int power_supply_uevent(struct device *dev, struct kobj_uevent_env *env) goto out; } - dev_dbg(dev, "prop %s=%s\n", attrname, prop_buf); - ret = add_uevent_var(env, "POWER_SUPPLY_%s=%s", attrname, prop_buf); kfree(attrname); if (ret) diff --git a/drivers/reset/reset-meson-audio-arb.c b/drivers/reset/reset-meson-audio-arb.c index 91751617b37a..c53a2185a039 100644 --- a/drivers/reset/reset-meson-audio-arb.c +++ b/drivers/reset/reset-meson-audio-arb.c @@ -130,6 +130,7 @@ static int meson_audio_arb_probe(struct platform_device *pdev) arb->rstc.nr_resets = ARRAY_SIZE(axg_audio_arb_reset_bits); arb->rstc.ops = &meson_audio_arb_rstc_ops; arb->rstc.of_node = dev->of_node; + arb->rstc.owner = THIS_MODULE; /* * Enable general : diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index a71734c41693..f933c06bff4f 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -667,9 +667,9 @@ config RTC_DRV_S5M will be called rtc-s5m. config RTC_DRV_SD3078 - tristate "ZXW Crystal SD3078" + tristate "ZXW Shenzhen whwave SD3078" help - If you say yes here you get support for the ZXW Crystal + If you say yes here you get support for the ZXW Shenzhen whwave SD3078 RTC chips. This driver can also be built as a module. If so, the module diff --git a/drivers/rtc/rtc-cros-ec.c b/drivers/rtc/rtc-cros-ec.c index e5444296075e..4d6bf9304ceb 100644 --- a/drivers/rtc/rtc-cros-ec.c +++ b/drivers/rtc/rtc-cros-ec.c @@ -298,7 +298,7 @@ static int cros_ec_rtc_suspend(struct device *dev) struct cros_ec_rtc *cros_ec_rtc = dev_get_drvdata(&pdev->dev); if (device_may_wakeup(dev)) - enable_irq_wake(cros_ec_rtc->cros_ec->irq); + return enable_irq_wake(cros_ec_rtc->cros_ec->irq); return 0; } @@ -309,7 +309,7 @@ static int cros_ec_rtc_resume(struct device *dev) struct cros_ec_rtc *cros_ec_rtc = dev_get_drvdata(&pdev->dev); if (device_may_wakeup(dev)) - disable_irq_wake(cros_ec_rtc->cros_ec->irq); + return disable_irq_wake(cros_ec_rtc->cros_ec->irq); return 0; } diff --git a/drivers/rtc/rtc-da9063.c b/drivers/rtc/rtc-da9063.c index b4e054c64bad..69b54e5556c0 100644 --- a/drivers/rtc/rtc-da9063.c +++ b/drivers/rtc/rtc-da9063.c @@ -480,6 +480,13 @@ static int da9063_rtc_probe(struct platform_device *pdev) da9063_data_to_tm(data, &rtc->alarm_time, rtc); rtc->rtc_sync = false; + /* + * TODO: some models have alarms on a minute boundary but still support + * real hardware interrupts. Add this once the core supports it. + */ + if (config->rtc_data_start != RTC_SEC) + rtc->rtc_dev->uie_unsupported = 1; + irq_alarm = platform_get_irq_byname(pdev, "ALARM"); ret = devm_request_threaded_irq(&pdev->dev, irq_alarm, NULL, da9063_alarm_event, diff --git a/drivers/rtc/rtc-sh.c b/drivers/rtc/rtc-sh.c index d417b203cbc5..1d3de2a3d1a4 100644 --- a/drivers/rtc/rtc-sh.c +++ b/drivers/rtc/rtc-sh.c @@ -374,7 +374,7 @@ static int sh_rtc_set_time(struct device *dev, struct rtc_time *tm) static inline int sh_rtc_read_alarm_value(struct sh_rtc *rtc, int reg_off) { unsigned int byte; - int value = 0xff; /* return 0xff for ignored values */ + int value = -1; /* return -1 for ignored values */ byte = readb(rtc->regbase + reg_off); if (byte & AR_ENB) { diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 6e294b4d3635..f89f9d02e788 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -2004,14 +2004,14 @@ static int dasd_eckd_end_analysis(struct dasd_block *block) blk_per_trk = recs_per_track(&private->rdc_data, 0, block->bp_block); raw: - block->blocks = (private->real_cyl * + block->blocks = ((unsigned long) private->real_cyl * private->rdc_data.trk_per_cyl * blk_per_trk); dev_info(&device->cdev->dev, - "DASD with %d KB/block, %d KB total size, %d KB/track, " + "DASD with %u KB/block, %lu KB total size, %u KB/track, " "%s\n", (block->bp_block >> 10), - ((private->real_cyl * + (((unsigned long) private->real_cyl * private->rdc_data.trk_per_cyl * blk_per_trk * (block->bp_block >> 9)) >> 1), ((blk_per_trk * block->bp_block) >> 10), diff --git a/drivers/s390/char/con3270.c b/drivers/s390/char/con3270.c index fd2146bcc0ad..e17364e13d2f 100644 --- a/drivers/s390/char/con3270.c +++ b/drivers/s390/char/con3270.c @@ -629,7 +629,7 @@ con3270_init(void) (void (*)(unsigned long)) con3270_read_tasklet, (unsigned long) condev->read); - raw3270_add_view(&condev->view, &con3270_fn, 1); + raw3270_add_view(&condev->view, &con3270_fn, 1, RAW3270_VIEW_LOCK_IRQ); INIT_LIST_HEAD(&condev->freemem); for (i = 0; i < CON3270_STRING_PAGES; i++) { diff --git a/drivers/s390/char/fs3270.c b/drivers/s390/char/fs3270.c index 8f3a2eeb28dc..8b48ba9c598e 100644 --- a/drivers/s390/char/fs3270.c +++ b/drivers/s390/char/fs3270.c @@ -463,7 +463,8 @@ fs3270_open(struct inode *inode, struct file *filp) init_waitqueue_head(&fp->wait); fp->fs_pid = get_pid(task_pid(current)); - rc = raw3270_add_view(&fp->view, &fs3270_fn, minor); + rc = raw3270_add_view(&fp->view, &fs3270_fn, minor, + RAW3270_VIEW_LOCK_BH); if (rc) { fs3270_free_view(&fp->view); goto out; diff --git a/drivers/s390/char/raw3270.c b/drivers/s390/char/raw3270.c index f8cd2935fbfd..63a41b168761 100644 --- a/drivers/s390/char/raw3270.c +++ b/drivers/s390/char/raw3270.c @@ -920,7 +920,7 @@ raw3270_deactivate_view(struct raw3270_view *view) * Add view to device with minor "minor". */ int -raw3270_add_view(struct raw3270_view *view, struct raw3270_fn *fn, int minor) +raw3270_add_view(struct raw3270_view *view, struct raw3270_fn *fn, int minor, int subclass) { unsigned long flags; struct raw3270 *rp; @@ -942,6 +942,7 @@ raw3270_add_view(struct raw3270_view *view, struct raw3270_fn *fn, int minor) view->cols = rp->cols; view->ascebc = rp->ascebc; spin_lock_init(&view->lock); + lockdep_set_subclass(&view->lock, subclass); list_add(&view->list, &rp->view_list); rc = 0; spin_unlock_irqrestore(get_ccwdev_lock(rp->cdev), flags); diff --git a/drivers/s390/char/raw3270.h b/drivers/s390/char/raw3270.h index 114ca7cbf889..3afaa35f7351 100644 --- a/drivers/s390/char/raw3270.h +++ b/drivers/s390/char/raw3270.h @@ -150,6 +150,8 @@ struct raw3270_fn { struct raw3270_view { struct list_head list; spinlock_t lock; +#define RAW3270_VIEW_LOCK_IRQ 0 +#define RAW3270_VIEW_LOCK_BH 1 atomic_t ref_count; struct raw3270 *dev; struct raw3270_fn *fn; @@ -158,7 +160,7 @@ struct raw3270_view { unsigned char *ascebc; /* ascii -> ebcdic table */ }; -int raw3270_add_view(struct raw3270_view *, struct raw3270_fn *, int); +int raw3270_add_view(struct raw3270_view *, struct raw3270_fn *, int, int); int raw3270_activate_view(struct raw3270_view *); void raw3270_del_view(struct raw3270_view *); void raw3270_deactivate_view(struct raw3270_view *); diff --git a/drivers/s390/char/tty3270.c b/drivers/s390/char/tty3270.c index 2b0c36c2c568..98d7fc152e32 100644 --- a/drivers/s390/char/tty3270.c +++ b/drivers/s390/char/tty3270.c @@ -980,7 +980,8 @@ static int tty3270_install(struct tty_driver *driver, struct tty_struct *tty) return PTR_ERR(tp); rc = raw3270_add_view(&tp->view, &tty3270_fn, - tty->index + RAW3270_FIRSTMINOR); + tty->index + RAW3270_FIRSTMINOR, + RAW3270_VIEW_LOCK_BH); if (rc) { tty3270_free_view(tp); return rc; diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c index 4159c63a5fd2..a835b31aad99 100644 --- a/drivers/s390/cio/chsc.c +++ b/drivers/s390/cio/chsc.c @@ -24,6 +24,7 @@ #include <asm/crw.h> #include <asm/isc.h> #include <asm/ebcdic.h> +#include <asm/ap.h> #include "css.h" #include "cio.h" @@ -586,6 +587,15 @@ static void chsc_process_sei_scm_avail(struct chsc_sei_nt0_area *sei_area) " failed (rc=%d).\n", ret); } +static void chsc_process_sei_ap_cfg_chg(struct chsc_sei_nt0_area *sei_area) +{ + CIO_CRW_EVENT(3, "chsc: ap config changed\n"); + if (sei_area->rs != 5) + return; + + ap_bus_cfg_chg(); +} + static void chsc_process_sei_nt2(struct chsc_sei_nt2_area *sei_area) { switch (sei_area->cc) { @@ -612,6 +622,9 @@ static void chsc_process_sei_nt0(struct chsc_sei_nt0_area *sei_area) case 2: /* i/o resource accessibility */ chsc_process_sei_res_acc(sei_area); break; + case 3: /* ap config changed */ + chsc_process_sei_ap_cfg_chg(sei_area); + break; case 7: /* channel-path-availability information */ chsc_process_sei_chp_avail(sei_area); break; diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c index a10cec0e86eb..0b3b9de45c60 100644 --- a/drivers/s390/cio/vfio_ccw_drv.c +++ b/drivers/s390/cio/vfio_ccw_drv.c @@ -72,20 +72,24 @@ static void vfio_ccw_sch_io_todo(struct work_struct *work) { struct vfio_ccw_private *private; struct irb *irb; + bool is_final; private = container_of(work, struct vfio_ccw_private, io_work); irb = &private->irb; + is_final = !(scsw_actl(&irb->scsw) & + (SCSW_ACTL_DEVACT | SCSW_ACTL_SCHACT)); if (scsw_is_solicited(&irb->scsw)) { cp_update_scsw(&private->cp, &irb->scsw); - cp_free(&private->cp); + if (is_final) + cp_free(&private->cp); } memcpy(private->io_region->irb_area, irb, sizeof(*irb)); if (private->io_trigger) eventfd_signal(private->io_trigger, 1); - if (private->mdev) + if (private->mdev && is_final) private->state = VFIO_CCW_STATE_IDLE; } diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index e15816ff1265..1546389d71db 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -810,11 +810,18 @@ static int ap_device_remove(struct device *dev) struct ap_device *ap_dev = to_ap_dev(dev); struct ap_driver *ap_drv = ap_dev->drv; + /* prepare ap queue device removal */ if (is_queue_dev(dev)) - ap_queue_remove(to_ap_queue(dev)); + ap_queue_prepare_remove(to_ap_queue(dev)); + + /* driver's chance to clean up gracefully */ if (ap_drv->remove) ap_drv->remove(ap_dev); + /* now do the ap queue device remove */ + if (is_queue_dev(dev)) + ap_queue_remove(to_ap_queue(dev)); + /* Remove queue/card from list of active queues/cards */ spin_lock_bh(&ap_list_lock); if (is_card_dev(dev)) @@ -861,6 +868,16 @@ void ap_bus_force_rescan(void) EXPORT_SYMBOL(ap_bus_force_rescan); /* +* A config change has happened, force an ap bus rescan. +*/ +void ap_bus_cfg_chg(void) +{ + AP_DBF(DBF_INFO, "%s config change, forcing bus rescan\n", __func__); + + ap_bus_force_rescan(); +} + +/* * hex2bitmap() - parse hex mask string and set bitmap. * Valid strings are "0x012345678" with at least one valid hex number. * Rest of the bitmap to the right is padded with 0. No spaces allowed diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h index d0059eae5d94..15a98a673c5c 100644 --- a/drivers/s390/crypto/ap_bus.h +++ b/drivers/s390/crypto/ap_bus.h @@ -91,6 +91,7 @@ enum ap_state { AP_STATE_WORKING, AP_STATE_QUEUE_FULL, AP_STATE_SUSPEND_WAIT, + AP_STATE_REMOVE, /* about to be removed from driver */ AP_STATE_UNBOUND, /* momentary not bound to a driver */ AP_STATE_BORKED, /* broken */ NR_AP_STATES @@ -252,6 +253,7 @@ void ap_bus_force_rescan(void); void ap_queue_init_reply(struct ap_queue *aq, struct ap_message *ap_msg); struct ap_queue *ap_queue_create(ap_qid_t qid, int device_type); +void ap_queue_prepare_remove(struct ap_queue *aq); void ap_queue_remove(struct ap_queue *aq); void ap_queue_suspend(struct ap_device *ap_dev); void ap_queue_resume(struct ap_device *ap_dev); diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index ba261210c6da..5ea83dc4f1d7 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -420,6 +420,10 @@ static ap_func_t *ap_jumptable[NR_AP_STATES][NR_AP_EVENTS] = { [AP_EVENT_POLL] = ap_sm_suspend_read, [AP_EVENT_TIMEOUT] = ap_sm_nop, }, + [AP_STATE_REMOVE] = { + [AP_EVENT_POLL] = ap_sm_nop, + [AP_EVENT_TIMEOUT] = ap_sm_nop, + }, [AP_STATE_UNBOUND] = { [AP_EVENT_POLL] = ap_sm_nop, [AP_EVENT_TIMEOUT] = ap_sm_nop, @@ -740,18 +744,31 @@ void ap_flush_queue(struct ap_queue *aq) } EXPORT_SYMBOL(ap_flush_queue); -void ap_queue_remove(struct ap_queue *aq) +void ap_queue_prepare_remove(struct ap_queue *aq) { - ap_flush_queue(aq); + spin_lock_bh(&aq->lock); + /* flush queue */ + __ap_flush_queue(aq); + /* set REMOVE state to prevent new messages are queued in */ + aq->state = AP_STATE_REMOVE; + spin_unlock_bh(&aq->lock); del_timer_sync(&aq->timeout); +} - /* reset with zero, also clears irq registration */ +void ap_queue_remove(struct ap_queue *aq) +{ + /* + * all messages have been flushed and the state is + * AP_STATE_REMOVE. Now reset with zero which also + * clears the irq registration and move the state + * to AP_STATE_UNBOUND to signal that this queue + * is not used by any driver currently. + */ spin_lock_bh(&aq->lock); ap_zapq(aq->qid); aq->state = AP_STATE_UNBOUND; spin_unlock_bh(&aq->lock); } -EXPORT_SYMBOL(ap_queue_remove); void ap_queue_reinit_state(struct ap_queue *aq) { @@ -760,4 +777,3 @@ void ap_queue_reinit_state(struct ap_queue *aq) ap_wait(ap_sm_event(aq, AP_EVENT_POLL)); spin_unlock_bh(&aq->lock); } -EXPORT_SYMBOL(ap_queue_reinit_state); diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index 3e85d665c572..45eb0c14b880 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -51,7 +51,8 @@ static debug_info_t *debug_info; static void __init pkey_debug_init(void) { - debug_info = debug_register("pkey", 1, 1, 4 * sizeof(long)); + /* 5 arguments per dbf entry (including the format string ptr) */ + debug_info = debug_register("pkey", 1, 1, 5 * sizeof(long)); debug_register_view(debug_info, &debug_sprintf_view); debug_set_level(debug_info, 3); } diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index eb93c2d27d0a..689c2af7026a 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -586,6 +586,7 @@ static inline bool zcrypt_check_queue(struct ap_perms *perms, int queue) static inline struct zcrypt_queue *zcrypt_pick_queue(struct zcrypt_card *zc, struct zcrypt_queue *zq, + struct module **pmod, unsigned int weight) { if (!zq || !try_module_get(zq->queue->ap_dev.drv->driver.owner)) @@ -595,15 +596,15 @@ static inline struct zcrypt_queue *zcrypt_pick_queue(struct zcrypt_card *zc, atomic_add(weight, &zc->load); atomic_add(weight, &zq->load); zq->request_count++; + *pmod = zq->queue->ap_dev.drv->driver.owner; return zq; } static inline void zcrypt_drop_queue(struct zcrypt_card *zc, struct zcrypt_queue *zq, + struct module *mod, unsigned int weight) { - struct module *mod = zq->queue->ap_dev.drv->driver.owner; - zq->request_count--; atomic_sub(weight, &zc->load); atomic_sub(weight, &zq->load); @@ -653,6 +654,7 @@ static long zcrypt_rsa_modexpo(struct ap_perms *perms, unsigned int weight, pref_weight; unsigned int func_code; int qid = 0, rc = -ENODEV; + struct module *mod; trace_s390_zcrypt_req(mex, TP_ICARSAMODEXPO); @@ -706,7 +708,7 @@ static long zcrypt_rsa_modexpo(struct ap_perms *perms, pref_weight = weight; } } - pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, weight); + pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, weight); spin_unlock(&zcrypt_list_lock); if (!pref_zq) { @@ -718,7 +720,7 @@ static long zcrypt_rsa_modexpo(struct ap_perms *perms, rc = pref_zq->ops->rsa_modexpo(pref_zq, mex); spin_lock(&zcrypt_list_lock); - zcrypt_drop_queue(pref_zc, pref_zq, weight); + zcrypt_drop_queue(pref_zc, pref_zq, mod, weight); spin_unlock(&zcrypt_list_lock); out: @@ -735,6 +737,7 @@ static long zcrypt_rsa_crt(struct ap_perms *perms, unsigned int weight, pref_weight; unsigned int func_code; int qid = 0, rc = -ENODEV; + struct module *mod; trace_s390_zcrypt_req(crt, TP_ICARSACRT); @@ -788,7 +791,7 @@ static long zcrypt_rsa_crt(struct ap_perms *perms, pref_weight = weight; } } - pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, weight); + pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, weight); spin_unlock(&zcrypt_list_lock); if (!pref_zq) { @@ -800,7 +803,7 @@ static long zcrypt_rsa_crt(struct ap_perms *perms, rc = pref_zq->ops->rsa_modexpo_crt(pref_zq, crt); spin_lock(&zcrypt_list_lock); - zcrypt_drop_queue(pref_zc, pref_zq, weight); + zcrypt_drop_queue(pref_zc, pref_zq, mod, weight); spin_unlock(&zcrypt_list_lock); out: @@ -819,6 +822,7 @@ static long _zcrypt_send_cprb(struct ap_perms *perms, unsigned int func_code; unsigned short *domain; int qid = 0, rc = -ENODEV; + struct module *mod; trace_s390_zcrypt_req(xcRB, TB_ZSECSENDCPRB); @@ -865,7 +869,7 @@ static long _zcrypt_send_cprb(struct ap_perms *perms, pref_weight = weight; } } - pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, weight); + pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, weight); spin_unlock(&zcrypt_list_lock); if (!pref_zq) { @@ -881,7 +885,7 @@ static long _zcrypt_send_cprb(struct ap_perms *perms, rc = pref_zq->ops->send_cprb(pref_zq, xcRB, &ap_msg); spin_lock(&zcrypt_list_lock); - zcrypt_drop_queue(pref_zc, pref_zq, weight); + zcrypt_drop_queue(pref_zc, pref_zq, mod, weight); spin_unlock(&zcrypt_list_lock); out: @@ -932,6 +936,7 @@ static long zcrypt_send_ep11_cprb(struct ap_perms *perms, unsigned int func_code; struct ap_message ap_msg; int qid = 0, rc = -ENODEV; + struct module *mod; trace_s390_zcrypt_req(xcrb, TP_ZSENDEP11CPRB); @@ -1000,7 +1005,7 @@ static long zcrypt_send_ep11_cprb(struct ap_perms *perms, pref_weight = weight; } } - pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, weight); + pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, weight); spin_unlock(&zcrypt_list_lock); if (!pref_zq) { @@ -1012,7 +1017,7 @@ static long zcrypt_send_ep11_cprb(struct ap_perms *perms, rc = pref_zq->ops->send_ep11_cprb(pref_zq, xcrb, &ap_msg); spin_lock(&zcrypt_list_lock); - zcrypt_drop_queue(pref_zc, pref_zq, weight); + zcrypt_drop_queue(pref_zc, pref_zq, mod, weight); spin_unlock(&zcrypt_list_lock); out_free: @@ -1033,6 +1038,7 @@ static long zcrypt_rng(char *buffer) struct ap_message ap_msg; unsigned int domain; int qid = 0, rc = -ENODEV; + struct module *mod; trace_s390_zcrypt_req(buffer, TP_HWRNGCPRB); @@ -1064,7 +1070,7 @@ static long zcrypt_rng(char *buffer) pref_weight = weight; } } - pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, weight); + pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, weight); spin_unlock(&zcrypt_list_lock); if (!pref_zq) { @@ -1076,7 +1082,7 @@ static long zcrypt_rng(char *buffer) rc = pref_zq->ops->rng(pref_zq, buffer, &ap_msg); spin_lock(&zcrypt_list_lock); - zcrypt_drop_queue(pref_zc, pref_zq, weight); + zcrypt_drop_queue(pref_zc, pref_zq, mod, weight); spin_unlock(&zcrypt_list_lock); out: diff --git a/drivers/s390/net/ctcm_main.c b/drivers/s390/net/ctcm_main.c index 7617d21cb296..f63c5c871d3d 100644 --- a/drivers/s390/net/ctcm_main.c +++ b/drivers/s390/net/ctcm_main.c @@ -1595,6 +1595,7 @@ static int ctcm_new_device(struct ccwgroup_device *cgdev) if (priv->channel[direction] == NULL) { if (direction == CTCM_WRITE) channel_free(priv->channel[CTCM_READ]); + result = -ENODEV; goto out_dev; } priv->channel[direction]->netdev = dev; diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 197b0f5b63e7..44bd6f04c145 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -1150,13 +1150,16 @@ static void qeth_notify_skbs(struct qeth_qdio_out_q *q, static void qeth_release_skbs(struct qeth_qdio_out_buffer *buf) { + struct sk_buff *skb; + /* release may never happen from within CQ tasklet scope */ WARN_ON_ONCE(atomic_read(&buf->state) == QETH_QDIO_BUF_IN_CQ); if (atomic_read(&buf->state) == QETH_QDIO_BUF_PENDING) qeth_notify_skbs(buf->q, buf, TX_NOTIFY_GENERALERROR); - __skb_queue_purge(&buf->skb_list); + while ((skb = __skb_dequeue(&buf->skb_list)) != NULL) + consume_skb(skb); } static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue, diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 8efb2e8ff8f4..c3067fd3bd9e 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -629,8 +629,7 @@ static netdev_tx_t qeth_l2_hard_start_xmit(struct sk_buff *skb, } /* else fall through */ QETH_TXQ_STAT_INC(queue, tx_dropped); - QETH_TXQ_STAT_INC(queue, tx_errors); - dev_kfree_skb_any(skb); + kfree_skb(skb); netif_wake_queue(dev); return NETDEV_TX_OK; } @@ -645,6 +644,8 @@ static int qeth_l2_probe_device(struct ccwgroup_device *gdev) struct qeth_card *card = dev_get_drvdata(&gdev->dev); int rc; + qeth_l2_vnicc_set_defaults(card); + if (gdev->dev.type == &qeth_generic_devtype) { rc = qeth_l2_create_device_attributes(&gdev->dev); if (rc) @@ -652,8 +653,6 @@ static int qeth_l2_probe_device(struct ccwgroup_device *gdev) } hash_init(card->mac_htable); - card->info.hwtrap = 0; - qeth_l2_vnicc_set_defaults(card); return 0; } diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 7e68d9d16859..53712cf26406 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -2096,8 +2096,7 @@ static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb, tx_drop: QETH_TXQ_STAT_INC(queue, tx_dropped); - QETH_TXQ_STAT_INC(queue, tx_errors); - dev_kfree_skb_any(skb); + kfree_skb(skb); netif_wake_queue(dev); return NETDEV_TX_OK; } @@ -2253,14 +2252,15 @@ static int qeth_l3_probe_device(struct ccwgroup_device *gdev) struct qeth_card *card = dev_get_drvdata(&gdev->dev); int rc; + hash_init(card->ip_htable); + if (gdev->dev.type == &qeth_generic_devtype) { rc = qeth_l3_create_device_attributes(&gdev->dev); if (rc) return rc; } - hash_init(card->ip_htable); + hash_init(card->ip_mc_htable); - card->info.hwtrap = 0; return 0; } diff --git a/drivers/s390/scsi/zfcp_erp.c b/drivers/s390/scsi/zfcp_erp.c index 744a64680d5b..e8fc28dba8df 100644 --- a/drivers/s390/scsi/zfcp_erp.c +++ b/drivers/s390/scsi/zfcp_erp.c @@ -624,6 +624,20 @@ static void zfcp_erp_strategy_memwait(struct zfcp_erp_action *erp_action) add_timer(&erp_action->timer); } +void zfcp_erp_port_forced_reopen_all(struct zfcp_adapter *adapter, + int clear, char *dbftag) +{ + unsigned long flags; + struct zfcp_port *port; + + write_lock_irqsave(&adapter->erp_lock, flags); + read_lock(&adapter->port_list_lock); + list_for_each_entry(port, &adapter->port_list, list) + _zfcp_erp_port_forced_reopen(port, clear, dbftag); + read_unlock(&adapter->port_list_lock); + write_unlock_irqrestore(&adapter->erp_lock, flags); +} + static void _zfcp_erp_port_reopen_all(struct zfcp_adapter *adapter, int clear, char *dbftag) { @@ -1341,6 +1355,9 @@ static void zfcp_erp_try_rport_unblock(struct zfcp_port *port) struct zfcp_scsi_dev *zsdev = sdev_to_zfcp(sdev); int lun_status; + if (sdev->sdev_state == SDEV_DEL || + sdev->sdev_state == SDEV_CANCEL) + continue; if (zsdev->port != port) continue; /* LUN under port of interest */ diff --git a/drivers/s390/scsi/zfcp_ext.h b/drivers/s390/scsi/zfcp_ext.h index 3fce47b0b21b..c6acca521ffe 100644 --- a/drivers/s390/scsi/zfcp_ext.h +++ b/drivers/s390/scsi/zfcp_ext.h @@ -70,6 +70,8 @@ extern void zfcp_erp_port_reopen(struct zfcp_port *port, int clear, char *dbftag); extern void zfcp_erp_port_shutdown(struct zfcp_port *, int, char *); extern void zfcp_erp_port_forced_reopen(struct zfcp_port *, int, char *); +extern void zfcp_erp_port_forced_reopen_all(struct zfcp_adapter *adapter, + int clear, char *dbftag); extern void zfcp_erp_set_lun_status(struct scsi_device *, u32); extern void zfcp_erp_clear_lun_status(struct scsi_device *, u32); extern void zfcp_erp_lun_reopen(struct scsi_device *, int, char *); diff --git a/drivers/s390/scsi/zfcp_fc.c b/drivers/s390/scsi/zfcp_fc.c index db00b5e3abbe..33eddb02ee30 100644 --- a/drivers/s390/scsi/zfcp_fc.c +++ b/drivers/s390/scsi/zfcp_fc.c @@ -239,10 +239,6 @@ static void _zfcp_fc_incoming_rscn(struct zfcp_fsf_req *fsf_req, u32 range, list_for_each_entry(port, &adapter->port_list, list) { if ((port->d_id & range) == (ntoh24(page->rscn_fid) & range)) zfcp_fc_test_link(port); - if (!port->d_id) - zfcp_erp_port_reopen(port, - ZFCP_STATUS_COMMON_ERP_FAILED, - "fcrscn1"); } read_unlock_irqrestore(&adapter->port_list_lock, flags); } @@ -250,6 +246,7 @@ static void _zfcp_fc_incoming_rscn(struct zfcp_fsf_req *fsf_req, u32 range, static void zfcp_fc_incoming_rscn(struct zfcp_fsf_req *fsf_req) { struct fsf_status_read_buffer *status_buffer = (void *)fsf_req->data; + struct zfcp_adapter *adapter = fsf_req->adapter; struct fc_els_rscn *head; struct fc_els_rscn_page *page; u16 i; @@ -263,6 +260,22 @@ static void zfcp_fc_incoming_rscn(struct zfcp_fsf_req *fsf_req) no_entries = be16_to_cpu(head->rscn_plen) / sizeof(struct fc_els_rscn_page); + if (no_entries > 1) { + /* handle failed ports */ + unsigned long flags; + struct zfcp_port *port; + + read_lock_irqsave(&adapter->port_list_lock, flags); + list_for_each_entry(port, &adapter->port_list, list) { + if (port->d_id) + continue; + zfcp_erp_port_reopen(port, + ZFCP_STATUS_COMMON_ERP_FAILED, + "fcrscn1"); + } + read_unlock_irqrestore(&adapter->port_list_lock, flags); + } + for (i = 1; i < no_entries; i++) { /* skip head and start with 1st element */ page++; diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c index f4f6a07c5222..221d0dfb8493 100644 --- a/drivers/s390/scsi/zfcp_scsi.c +++ b/drivers/s390/scsi/zfcp_scsi.c @@ -368,6 +368,10 @@ static int zfcp_scsi_eh_host_reset_handler(struct scsi_cmnd *scpnt) struct zfcp_adapter *adapter = zfcp_sdev->port->adapter; int ret = SUCCESS, fc_ret; + if (!(adapter->connection_features & FSF_FEATURE_NPIV_MODE)) { + zfcp_erp_port_forced_reopen_all(adapter, 0, "schrh_p"); + zfcp_erp_wait(adapter); + } zfcp_erp_adapter_reopen(adapter, 0, "schrh_1"); zfcp_erp_wait(adapter); fc_ret = fc_block_scsi_eh(scpnt); diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h index 1df5171594b8..11fb68d7e60d 100644 --- a/drivers/scsi/aacraid/aacraid.h +++ b/drivers/scsi/aacraid/aacraid.h @@ -2640,9 +2640,14 @@ static inline unsigned int cap_to_cyls(sector_t capacity, unsigned divisor) return capacity; } +static inline int aac_pci_offline(struct aac_dev *dev) +{ + return pci_channel_offline(dev->pdev) || dev->handle_pci_error; +} + static inline int aac_adapter_check_health(struct aac_dev *dev) { - if (unlikely(pci_channel_offline(dev->pdev))) + if (unlikely(aac_pci_offline(dev))) return -1; return (dev)->a_ops.adapter_check_health(dev); diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c index e67e032936ef..78430a7b294c 100644 --- a/drivers/scsi/aacraid/commsup.c +++ b/drivers/scsi/aacraid/commsup.c @@ -672,7 +672,7 @@ int aac_fib_send(u16 command, struct fib *fibptr, unsigned long size, return -ETIMEDOUT; } - if (unlikely(pci_channel_offline(dev->pdev))) + if (unlikely(aac_pci_offline(dev))) return -EFAULT; if ((blink = aac_adapter_check_health(dev)) > 0) { @@ -772,7 +772,7 @@ int aac_hba_send(u8 command, struct fib *fibptr, fib_callback callback, spin_unlock_irqrestore(&fibptr->event_lock, flags); - if (unlikely(pci_channel_offline(dev->pdev))) + if (unlikely(aac_pci_offline(dev))) return -EFAULT; fibptr->flags |= FIB_CONTEXT_FLAG_WAIT; diff --git a/drivers/scsi/aic7xxx/aic7770_osm.c b/drivers/scsi/aic7xxx/aic7770_osm.c index 3d401d02c019..bdd177e3d762 100644 --- a/drivers/scsi/aic7xxx/aic7770_osm.c +++ b/drivers/scsi/aic7xxx/aic7770_osm.c @@ -91,6 +91,7 @@ aic7770_probe(struct device *dev) ahc = ahc_alloc(&aic7xxx_driver_template, name); if (ahc == NULL) return (ENOMEM); + ahc->dev = dev; error = aic7770_config(ahc, aic7770_ident_table + edev->id.driver_data, eisaBase); if (error != 0) { diff --git a/drivers/scsi/aic7xxx/aic7xxx.h b/drivers/scsi/aic7xxx/aic7xxx.h index 5614921b4041..88b90f9806c9 100644 --- a/drivers/scsi/aic7xxx/aic7xxx.h +++ b/drivers/scsi/aic7xxx/aic7xxx.h @@ -943,6 +943,7 @@ struct ahc_softc { * Platform specific device information. */ ahc_dev_softc_t dev_softc; + struct device *dev; /* * Bus specific device information. diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm.c b/drivers/scsi/aic7xxx/aic7xxx_osm.c index 3c9c17450bb3..d5c4a0d23706 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_osm.c +++ b/drivers/scsi/aic7xxx/aic7xxx_osm.c @@ -860,8 +860,8 @@ int ahc_dmamem_alloc(struct ahc_softc *ahc, bus_dma_tag_t dmat, void** vaddr, int flags, bus_dmamap_t *mapp) { - *vaddr = pci_alloc_consistent(ahc->dev_softc, - dmat->maxsize, mapp); + /* XXX: check if we really need the GFP_ATOMIC and unwind this mess! */ + *vaddr = dma_alloc_coherent(ahc->dev, dmat->maxsize, mapp, GFP_ATOMIC); if (*vaddr == NULL) return ENOMEM; return 0; @@ -871,8 +871,7 @@ void ahc_dmamem_free(struct ahc_softc *ahc, bus_dma_tag_t dmat, void* vaddr, bus_dmamap_t map) { - pci_free_consistent(ahc->dev_softc, dmat->maxsize, - vaddr, map); + dma_free_coherent(ahc->dev, dmat->maxsize, vaddr, map); } int @@ -1123,8 +1122,7 @@ ahc_linux_register_host(struct ahc_softc *ahc, struct scsi_host_template *templa host->transportt = ahc_linux_transport_template; - retval = scsi_add_host(host, - (ahc->dev_softc ? &ahc->dev_softc->dev : NULL)); + retval = scsi_add_host(host, ahc->dev); if (retval) { printk(KERN_WARNING "aic7xxx: scsi_add_host failed\n"); scsi_host_put(host); diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm_pci.c b/drivers/scsi/aic7xxx/aic7xxx_osm_pci.c index 0fc14dac7070..717d8d1082ce 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_osm_pci.c +++ b/drivers/scsi/aic7xxx/aic7xxx_osm_pci.c @@ -250,6 +250,7 @@ ahc_linux_pci_dev_probe(struct pci_dev *pdev, const struct pci_device_id *ent) } } ahc->dev_softc = pci; + ahc->dev = &pci->dev; error = ahc_pci_config(ahc, entry); if (error != 0) { ahc_free(ahc); diff --git a/drivers/scsi/csiostor/csio_scsi.c b/drivers/scsi/csiostor/csio_scsi.c index 462560b2855e..469d0bc9f5fe 100644 --- a/drivers/scsi/csiostor/csio_scsi.c +++ b/drivers/scsi/csiostor/csio_scsi.c @@ -1713,8 +1713,11 @@ csio_scsi_err_handler(struct csio_hw *hw, struct csio_ioreq *req) } out: - if (req->nsge > 0) + if (req->nsge > 0) { scsi_dma_unmap(cmnd); + if (req->dcopy && (host_status == DID_OK)) + host_status = csio_scsi_copy_to_sgl(hw, req); + } cmnd->result = (((host_status) << 16) | scsi_status); cmnd->scsi_done(cmnd); diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index dbaa4f131433..3ad997ac3510 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -139,6 +139,7 @@ static const struct { { IBMVFC_FC_FAILURE, IBMVFC_VENDOR_SPECIFIC, DID_ERROR, 1, 1, "vendor specific" }, { IBMVFC_FC_SCSI_ERROR, 0, DID_OK, 1, 0, "SCSI error" }, + { IBMVFC_FC_SCSI_ERROR, IBMVFC_COMMAND_FAILED, DID_ERROR, 0, 1, "PRLI to device failed." }, }; static void ibmvfc_npiv_login(struct ibmvfc_host *); @@ -1494,9 +1495,9 @@ static void ibmvfc_log_error(struct ibmvfc_event *evt) if (rsp->flags & FCP_RSP_LEN_VALID) rsp_code = rsp->data.info.rsp_code; - scmd_printk(KERN_ERR, cmnd, "Command (%02X) failed: %s (%x:%x) " + scmd_printk(KERN_ERR, cmnd, "Command (%02X) : %s (%x:%x) " "flags: %x fcp_rsp: %x, resid=%d, scsi_status: %x\n", - cmnd->cmnd[0], err, vfc_cmd->status, vfc_cmd->error, + cmnd->cmnd[0], err, be16_to_cpu(vfc_cmd->status), be16_to_cpu(vfc_cmd->error), rsp->flags, rsp_code, scsi_get_resid(cmnd), rsp->scsi_status); } @@ -2022,7 +2023,7 @@ static int ibmvfc_reset_device(struct scsi_device *sdev, int type, char *desc) sdev_printk(KERN_ERR, sdev, "%s reset failed: %s (%x:%x) " "flags: %x fcp_rsp: %x, scsi_status: %x\n", desc, ibmvfc_get_cmd_error(be16_to_cpu(rsp_iu.cmd.status), be16_to_cpu(rsp_iu.cmd.error)), - rsp_iu.cmd.status, rsp_iu.cmd.error, fc_rsp->flags, rsp_code, + be16_to_cpu(rsp_iu.cmd.status), be16_to_cpu(rsp_iu.cmd.error), fc_rsp->flags, rsp_code, fc_rsp->scsi_status); rsp_rc = -EIO; } else @@ -2381,7 +2382,7 @@ static int ibmvfc_abort_task_set(struct scsi_device *sdev) sdev_printk(KERN_ERR, sdev, "Abort failed: %s (%x:%x) " "flags: %x fcp_rsp: %x, scsi_status: %x\n", ibmvfc_get_cmd_error(be16_to_cpu(rsp_iu.cmd.status), be16_to_cpu(rsp_iu.cmd.error)), - rsp_iu.cmd.status, rsp_iu.cmd.error, fc_rsp->flags, rsp_code, + be16_to_cpu(rsp_iu.cmd.status), be16_to_cpu(rsp_iu.cmd.error), fc_rsp->flags, rsp_code, fc_rsp->scsi_status); rsp_rc = -EIO; } else @@ -2755,16 +2756,18 @@ static void ibmvfc_handle_crq(struct ibmvfc_crq *crq, struct ibmvfc_host *vhost) ibmvfc_set_host_action(vhost, IBMVFC_HOST_ACTION_NONE); if (crq->format == IBMVFC_PARTITION_MIGRATED) { /* We need to re-setup the interpartition connection */ - dev_info(vhost->dev, "Re-enabling adapter\n"); + dev_info(vhost->dev, "Partition migrated, Re-enabling adapter\n"); vhost->client_migrated = 1; ibmvfc_purge_requests(vhost, DID_REQUEUE); ibmvfc_link_down(vhost, IBMVFC_LINK_DOWN); ibmvfc_set_host_action(vhost, IBMVFC_HOST_ACTION_REENABLE); - } else { - dev_err(vhost->dev, "Virtual adapter failed (rc=%d)\n", crq->format); + } else if (crq->format == IBMVFC_PARTNER_FAILED || crq->format == IBMVFC_PARTNER_DEREGISTER) { + dev_err(vhost->dev, "Host partner adapter deregistered or failed (rc=%d)\n", crq->format); ibmvfc_purge_requests(vhost, DID_ERROR); ibmvfc_link_down(vhost, IBMVFC_LINK_DOWN); ibmvfc_set_host_action(vhost, IBMVFC_HOST_ACTION_RESET); + } else { + dev_err(vhost->dev, "Received unknown transport event from partner (rc=%d)\n", crq->format); } return; case IBMVFC_CRQ_CMD_RSP: @@ -3348,7 +3351,7 @@ static void ibmvfc_tgt_prli_done(struct ibmvfc_event *evt) tgt_log(tgt, level, "Process Login failed: %s (%x:%x) rc=0x%02X\n", ibmvfc_get_cmd_error(be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)), - rsp->status, rsp->error, status); + be16_to_cpu(rsp->status), be16_to_cpu(rsp->error), status); break; } @@ -3446,9 +3449,10 @@ static void ibmvfc_tgt_plogi_done(struct ibmvfc_event *evt) ibmvfc_set_tgt_action(tgt, IBMVFC_TGT_ACTION_DEL_RPORT); tgt_log(tgt, level, "Port Login failed: %s (%x:%x) %s (%x) %s (%x) rc=0x%02X\n", - ibmvfc_get_cmd_error(be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)), rsp->status, rsp->error, - ibmvfc_get_fc_type(be16_to_cpu(rsp->fc_type)), rsp->fc_type, - ibmvfc_get_ls_explain(be16_to_cpu(rsp->fc_explain)), rsp->fc_explain, status); + ibmvfc_get_cmd_error(be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)), + be16_to_cpu(rsp->status), be16_to_cpu(rsp->error), + ibmvfc_get_fc_type(be16_to_cpu(rsp->fc_type)), be16_to_cpu(rsp->fc_type), + ibmvfc_get_ls_explain(be16_to_cpu(rsp->fc_explain)), be16_to_cpu(rsp->fc_explain), status); break; } @@ -3619,7 +3623,7 @@ static void ibmvfc_tgt_adisc_done(struct ibmvfc_event *evt) fc_explain = (be32_to_cpu(mad->fc_iu.response[1]) & 0x0000ff00) >> 8; tgt_info(tgt, "ADISC failed: %s (%x:%x) %s (%x) %s (%x) rc=0x%02X\n", ibmvfc_get_cmd_error(be16_to_cpu(mad->iu.status), be16_to_cpu(mad->iu.error)), - mad->iu.status, mad->iu.error, + be16_to_cpu(mad->iu.status), be16_to_cpu(mad->iu.error), ibmvfc_get_fc_type(fc_reason), fc_reason, ibmvfc_get_ls_explain(fc_explain), fc_explain, status); break; @@ -3831,9 +3835,10 @@ static void ibmvfc_tgt_query_target_done(struct ibmvfc_event *evt) tgt_log(tgt, level, "Query Target failed: %s (%x:%x) %s (%x) %s (%x) rc=0x%02X\n", ibmvfc_get_cmd_error(be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)), - rsp->status, rsp->error, ibmvfc_get_fc_type(be16_to_cpu(rsp->fc_type)), - rsp->fc_type, ibmvfc_get_gs_explain(be16_to_cpu(rsp->fc_explain)), - rsp->fc_explain, status); + be16_to_cpu(rsp->status), be16_to_cpu(rsp->error), + ibmvfc_get_fc_type(be16_to_cpu(rsp->fc_type)), be16_to_cpu(rsp->fc_type), + ibmvfc_get_gs_explain(be16_to_cpu(rsp->fc_explain)), be16_to_cpu(rsp->fc_explain), + status); break; } @@ -3959,7 +3964,7 @@ static void ibmvfc_discover_targets_done(struct ibmvfc_event *evt) level += ibmvfc_retry_host_init(vhost); ibmvfc_log(vhost, level, "Discover Targets failed: %s (%x:%x)\n", ibmvfc_get_cmd_error(be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)), - rsp->status, rsp->error); + be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)); break; case IBMVFC_MAD_DRIVER_FAILED: break; @@ -4024,7 +4029,7 @@ static void ibmvfc_npiv_login_done(struct ibmvfc_event *evt) ibmvfc_link_down(vhost, IBMVFC_LINK_DEAD); ibmvfc_log(vhost, level, "NPIV Login failed: %s (%x:%x)\n", ibmvfc_get_cmd_error(be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)), - rsp->status, rsp->error); + be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)); ibmvfc_free_event(evt); return; case IBMVFC_MAD_CRQ_ERROR: diff --git a/drivers/scsi/ibmvscsi/ibmvfc.h b/drivers/scsi/ibmvscsi/ibmvfc.h index b81a53c4a9a8..459cc288ba1d 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.h +++ b/drivers/scsi/ibmvscsi/ibmvfc.h @@ -78,9 +78,14 @@ enum ibmvfc_crq_valid { IBMVFC_CRQ_XPORT_EVENT = 0xFF, }; -enum ibmvfc_crq_format { +enum ibmvfc_crq_init_msg { IBMVFC_CRQ_INIT = 0x01, IBMVFC_CRQ_INIT_COMPLETE = 0x02, +}; + +enum ibmvfc_crq_xport_evts { + IBMVFC_PARTNER_FAILED = 0x01, + IBMVFC_PARTNER_DEREGISTER = 0x02, IBMVFC_PARTITION_MIGRATED = 0x06, }; diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c index dfba4921b265..5bf61431434b 100644 --- a/drivers/scsi/libfc/fc_rport.c +++ b/drivers/scsi/libfc/fc_rport.c @@ -2162,7 +2162,6 @@ static void fc_rport_recv_logo_req(struct fc_lport *lport, struct fc_frame *fp) FC_RPORT_DBG(rdata, "Received LOGO request while in state %s\n", fc_rport_state(rdata)); - rdata->flags &= ~FC_RP_STARTED; fc_rport_enter_delete(rdata, RPORT_EV_STOP); mutex_unlock(&rdata->rp_mutex); kref_put(&rdata->kref, fc_rport_destroy); diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index c98f264f1d83..a497b2c0cb79 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -3878,10 +3878,9 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn, * wake up the thread. */ spin_lock(&lpfc_cmd->buf_lock); - if (unlikely(lpfc_cmd->cur_iocbq.iocb_flag & LPFC_DRIVER_ABORTED)) { - lpfc_cmd->cur_iocbq.iocb_flag &= ~LPFC_DRIVER_ABORTED; - if (lpfc_cmd->waitq) - wake_up(lpfc_cmd->waitq); + lpfc_cmd->cur_iocbq.iocb_flag &= ~LPFC_DRIVER_ABORTED; + if (lpfc_cmd->waitq) { + wake_up(lpfc_cmd->waitq); lpfc_cmd->waitq = NULL; } spin_unlock(&lpfc_cmd->buf_lock); diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index e57774472e75..1d8c584ec1e9 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -3281,12 +3281,18 @@ mpt3sas_base_free_smid(struct MPT3SAS_ADAPTER *ioc, u16 smid) if (smid < ioc->hi_priority_smid) { struct scsiio_tracker *st; + void *request; st = _get_st_from_smid(ioc, smid); if (!st) { _base_recovery_check(ioc); return; } + + /* Clear MPI request frame */ + request = mpt3sas_base_get_msg_frame(ioc, smid); + memset(request, 0, ioc->request_sz); + mpt3sas_base_clear_st(ioc, st); _base_recovery_check(ioc); return; diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 8bb5b8f9f4d2..1ccfbc7eebe0 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -1462,11 +1462,23 @@ mpt3sas_scsih_scsi_lookup_get(struct MPT3SAS_ADAPTER *ioc, u16 smid) { struct scsi_cmnd *scmd = NULL; struct scsiio_tracker *st; + Mpi25SCSIIORequest_t *mpi_request; if (smid > 0 && smid <= ioc->scsiio_depth - INTERNAL_SCSIIO_CMDS_COUNT) { u32 unique_tag = smid - 1; + mpi_request = mpt3sas_base_get_msg_frame(ioc, smid); + + /* + * If SCSI IO request is outstanding at driver level then + * DevHandle filed must be non-zero. If DevHandle is zero + * then it means that this smid is free at driver level, + * so return NULL. + */ + if (!mpi_request->DevHandle) + return scmd; + scmd = scsi_host_find_tag(ioc->shost, unique_tag); if (scmd) { st = scsi_cmd_priv(scmd); diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index e74a62448ba4..e5db9a9954dc 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -1392,10 +1392,8 @@ static void qedi_free_nvm_iscsi_cfg(struct qedi_ctx *qedi) static int qedi_alloc_nvm_iscsi_cfg(struct qedi_ctx *qedi) { - struct qedi_nvm_iscsi_image nvm_image; - qedi->iscsi_image = dma_alloc_coherent(&qedi->pdev->dev, - sizeof(nvm_image), + sizeof(struct qedi_nvm_iscsi_image), &qedi->nvm_buf_dma, GFP_KERNEL); if (!qedi->iscsi_image) { QEDI_ERR(&qedi->dbg_ctx, "Could not allocate NVM BUF.\n"); @@ -2236,14 +2234,13 @@ static void qedi_boot_release(void *data) static int qedi_get_boot_info(struct qedi_ctx *qedi) { int ret = 1; - struct qedi_nvm_iscsi_image nvm_image; QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO, "Get NVM iSCSI CFG image\n"); ret = qedi_ops->common->nvm_get_image(qedi->cdev, QED_NVM_IMAGE_ISCSI_CFG, (char *)qedi->iscsi_image, - sizeof(nvm_image)); + sizeof(struct qedi_nvm_iscsi_image)); if (ret) QEDI_ERR(&qedi->dbg_ctx, "Could not get NVM image. ret = %d\n", ret); diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c index 16a18d5d856f..6e4f4931ae17 100644 --- a/drivers/scsi/qla4xxx/ql4_os.c +++ b/drivers/scsi/qla4xxx/ql4_os.c @@ -3203,6 +3203,8 @@ static int qla4xxx_conn_bind(struct iscsi_cls_session *cls_session, if (iscsi_conn_bind(cls_session, cls_conn, is_leading)) return -EINVAL; ep = iscsi_lookup_endpoint(transport_fd); + if (!ep) + return -EINVAL; conn = cls_conn->dd_data; qla_conn = conn->dd_data; qla_conn->qla_ep = ep->dd_data; diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c index c4cbfd07b916..a08ff3bd6310 100644 --- a/drivers/scsi/scsi_devinfo.c +++ b/drivers/scsi/scsi_devinfo.c @@ -238,6 +238,7 @@ static struct { {"NETAPP", "Universal Xport", "*", BLIST_NO_ULD_ATTACH}, {"LSI", "Universal Xport", "*", BLIST_NO_ULD_ATTACH}, {"ENGENIO", "Universal Xport", "*", BLIST_NO_ULD_ATTACH}, + {"LENOVO", "Universal Xport", "*", BLIST_NO_ULD_ATTACH}, {"SMSC", "USB 2 HS-CF", NULL, BLIST_SPARSELUN | BLIST_INQUIRY_36}, {"SONY", "CD-ROM CDU-8001", NULL, BLIST_BORKEN}, {"SONY", "TSL", NULL, BLIST_FORCELUN}, /* DDS3 & DDS4 autoloaders */ diff --git a/drivers/scsi/scsi_dh.c b/drivers/scsi/scsi_dh.c index 5a58cbf3a75d..c14006ac98f9 100644 --- a/drivers/scsi/scsi_dh.c +++ b/drivers/scsi/scsi_dh.c @@ -75,6 +75,7 @@ static const struct scsi_dh_blist scsi_dh_blist[] = { {"NETAPP", "INF-01-00", "rdac", }, {"LSI", "INF-01-00", "rdac", }, {"ENGENIO", "INF-01-00", "rdac", }, + {"LENOVO", "DE_Series", "rdac", }, {NULL, NULL, NULL }, }; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 601b9f1de267..07dfc17d4824 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1706,8 +1706,12 @@ out_put_budget: ret = BLK_STS_DEV_RESOURCE; break; default: + if (unlikely(!scsi_device_online(sdev))) + scsi_req(req)->result = DID_NO_CONNECT << 16; + else + scsi_req(req)->result = DID_ERROR << 16; /* - * Make sure to release all allocated ressources when + * Make sure to release all allocated resources when * we hit an error, as we will never see this command * again. */ diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 6a9040faed00..3b119ca0cc0c 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -771,6 +771,12 @@ store_state_field(struct device *dev, struct device_attribute *attr, mutex_lock(&sdev->state_mutex); ret = scsi_device_set_state(sdev, state); + /* + * If the device state changes to SDEV_RUNNING, we need to run + * the queue to avoid I/O hang. + */ + if (ret == 0 && state == SDEV_RUNNING) + blk_mq_run_hw_queues(sdev->request_queue, true); mutex_unlock(&sdev->state_mutex); return ret == 0 ? count : -EINVAL; diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 251db30d0882..2b2bc4b49d78 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1415,11 +1415,6 @@ static void sd_release(struct gendisk *disk, fmode_t mode) scsi_set_medium_removal(sdev, SCSI_REMOVAL_ALLOW); } - /* - * XXX and what if there are packets in flight and this close() - * XXX is followed by a "rmmod sd_mod"? - */ - scsi_disk_put(sdkp); } @@ -3076,6 +3071,9 @@ static bool sd_validate_opt_xfer_size(struct scsi_disk *sdkp, unsigned int opt_xfer_bytes = logical_to_bytes(sdp, sdkp->opt_xfer_blocks); + if (sdkp->opt_xfer_blocks == 0) + return false; + if (sdkp->opt_xfer_blocks > dev_max) { sd_first_printk(KERN_WARNING, sdkp, "Optimal transfer size %u logical blocks " \ @@ -3505,9 +3503,21 @@ static void scsi_disk_release(struct device *dev) { struct scsi_disk *sdkp = to_scsi_disk(dev); struct gendisk *disk = sdkp->disk; - + struct request_queue *q = disk->queue; + ida_free(&sd_index_ida, sdkp->index); + /* + * Wait until all requests that are in progress have completed. + * This is necessary to avoid that e.g. scsi_end_request() crashes + * due to clearing the disk->private_data pointer. Wait from inside + * scsi_disk_release() instead of from sd_release() to avoid that + * freezing and unfreezing the request queue affects user space I/O + * in case multiple processes open a /dev/sd... node concurrently. + */ + blk_mq_freeze_queue(q); + blk_mq_unfreeze_queue(q); + disk->private_data = NULL; put_disk(disk); put_device(&sdkp->device->sdev_gendev); diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 84380bae20f1..8472de1007ff 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -385,7 +385,7 @@ enum storvsc_request_type { * This is the end of Protocol specific defines. */ -static int storvsc_ringbuffer_size = (256 * PAGE_SIZE); +static int storvsc_ringbuffer_size = (128 * 1024); static u32 max_outstanding_req_per_channel; static int storvsc_vcpus_per_sub_channel = 4; @@ -668,13 +668,22 @@ static void handle_multichannel_storage(struct hv_device *device, int max_chns) { struct device *dev = &device->device; struct storvsc_device *stor_device; - int num_cpus = num_online_cpus(); int num_sc; struct storvsc_cmd_request *request; struct vstor_packet *vstor_packet; int ret, t; - num_sc = ((max_chns > num_cpus) ? num_cpus : max_chns); + /* + * If the number of CPUs is artificially restricted, such as + * with maxcpus=1 on the kernel boot line, Hyper-V could offer + * sub-channels >= the number of CPUs. These sub-channels + * should not be created. The primary channel is already created + * and assigned to one CPU, so check against # CPUs - 1. + */ + num_sc = min((int)(num_online_cpus() - 1), max_chns); + if (!num_sc) + return; + stor_device = get_out_stor_device(device); if (!stor_device) return; diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 8af01777d09c..f8cb7c23305b 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -793,6 +793,7 @@ static int virtscsi_probe(struct virtio_device *vdev) /* We need to know how many queues before we allocate. */ num_queues = virtscsi_config_get(vdev, num_queues) ? : 1; + num_queues = min_t(unsigned int, nr_cpu_ids, num_queues); num_targets = virtscsi_config_get(vdev, max_target) + 1; diff --git a/drivers/soc/bcm/bcm2835-power.c b/drivers/soc/bcm/bcm2835-power.c index 9351349cf0a9..1e0041ec8132 100644 --- a/drivers/soc/bcm/bcm2835-power.c +++ b/drivers/soc/bcm/bcm2835-power.c @@ -150,7 +150,12 @@ struct bcm2835_power { static int bcm2835_asb_enable(struct bcm2835_power *power, u32 reg) { - u64 start = ktime_get_ns(); + u64 start; + + if (!reg) + return 0; + + start = ktime_get_ns(); /* Enable the module's async AXI bridges. */ ASB_WRITE(reg, ASB_READ(reg) & ~ASB_REQ_STOP); @@ -165,7 +170,12 @@ static int bcm2835_asb_enable(struct bcm2835_power *power, u32 reg) static int bcm2835_asb_disable(struct bcm2835_power *power, u32 reg) { - u64 start = ktime_get_ns(); + u64 start; + + if (!reg) + return 0; + + start = ktime_get_ns(); /* Enable the module's async AXI bridges. */ ASB_WRITE(reg, ASB_READ(reg) | ASB_REQ_STOP); @@ -475,7 +485,7 @@ static int bcm2835_power_pd_power_off(struct generic_pm_domain *domain) } } -static void +static int bcm2835_init_power_domain(struct bcm2835_power *power, int pd_xlate_index, const char *name) { @@ -483,6 +493,17 @@ bcm2835_init_power_domain(struct bcm2835_power *power, struct bcm2835_power_domain *dom = &power->domains[pd_xlate_index]; dom->clk = devm_clk_get(dev->parent, name); + if (IS_ERR(dom->clk)) { + int ret = PTR_ERR(dom->clk); + + if (ret == -EPROBE_DEFER) + return ret; + + /* Some domains don't have a clk, so make sure that we + * don't deref an error pointer later. + */ + dom->clk = NULL; + } dom->base.name = name; dom->base.power_on = bcm2835_power_pd_power_on; @@ -495,6 +516,8 @@ bcm2835_init_power_domain(struct bcm2835_power *power, pm_genpd_init(&dom->base, NULL, true); power->pd_xlate.domains[pd_xlate_index] = &dom->base; + + return 0; } /** bcm2835_reset_reset - Resets a block that has a reset line in the @@ -592,7 +615,7 @@ static int bcm2835_power_probe(struct platform_device *pdev) { BCM2835_POWER_DOMAIN_IMAGE_PERI, BCM2835_POWER_DOMAIN_CAM0 }, { BCM2835_POWER_DOMAIN_IMAGE_PERI, BCM2835_POWER_DOMAIN_CAM1 }, }; - int ret, i; + int ret = 0, i; u32 id; power = devm_kzalloc(dev, sizeof(*power), GFP_KERNEL); @@ -619,8 +642,11 @@ static int bcm2835_power_probe(struct platform_device *pdev) power->pd_xlate.num_domains = ARRAY_SIZE(power_domain_names); - for (i = 0; i < ARRAY_SIZE(power_domain_names); i++) - bcm2835_init_power_domain(power, i, power_domain_names[i]); + for (i = 0; i < ARRAY_SIZE(power_domain_names); i++) { + ret = bcm2835_init_power_domain(power, i, power_domain_names[i]); + if (ret) + goto fail; + } for (i = 0; i < ARRAY_SIZE(domain_deps); i++) { pm_genpd_add_subdomain(&power->domains[domain_deps[i].parent].base, @@ -634,12 +660,21 @@ static int bcm2835_power_probe(struct platform_device *pdev) ret = devm_reset_controller_register(dev, &power->reset); if (ret) - return ret; + goto fail; of_genpd_add_provider_onecell(dev->parent->of_node, &power->pd_xlate); dev_info(dev, "Broadcom BCM2835 power domains driver"); return 0; + +fail: + for (i = 0; i < ARRAY_SIZE(power_domain_names); i++) { + struct generic_pm_domain *dom = &power->domains[i].base; + + if (dom->name) + pm_genpd_remove(dom); + } + return ret; } static int bcm2835_power_remove(struct platform_device *pdev) diff --git a/drivers/staging/Kconfig b/drivers/staging/Kconfig index c0901b96cfe4..62951e836cbc 100644 --- a/drivers/staging/Kconfig +++ b/drivers/staging/Kconfig @@ -114,8 +114,6 @@ source "drivers/staging/ralink-gdma/Kconfig" source "drivers/staging/mt7621-mmc/Kconfig" -source "drivers/staging/mt7621-eth/Kconfig" - source "drivers/staging/mt7621-dts/Kconfig" source "drivers/staging/gasket/Kconfig" diff --git a/drivers/staging/Makefile b/drivers/staging/Makefile index 57c6bce13ff4..d1b17ddcd354 100644 --- a/drivers/staging/Makefile +++ b/drivers/staging/Makefile @@ -47,7 +47,6 @@ obj-$(CONFIG_SPI_MT7621) += mt7621-spi/ obj-$(CONFIG_SOC_MT7621) += mt7621-dma/ obj-$(CONFIG_DMA_RALINK) += ralink-gdma/ obj-$(CONFIG_MTK_MMC) += mt7621-mmc/ -obj-$(CONFIG_NET_MEDIATEK_SOC_STAGING) += mt7621-eth/ obj-$(CONFIG_SOC_MT7621) += mt7621-dts/ obj-$(CONFIG_STAGING_GASKET_FRAMEWORK) += gasket/ obj-$(CONFIG_XIL_AXIS_FIFO) += axis-fifo/ diff --git a/drivers/staging/axis-fifo/Kconfig b/drivers/staging/axis-fifo/Kconfig index 687537203d9c..d9725888af6f 100644 --- a/drivers/staging/axis-fifo/Kconfig +++ b/drivers/staging/axis-fifo/Kconfig @@ -3,6 +3,7 @@ # config XIL_AXIS_FIFO tristate "Xilinx AXI-Stream FIFO IP core driver" + depends on OF default n help This adds support for the Xilinx AXI-Stream diff --git a/drivers/staging/comedi/comedidev.h b/drivers/staging/comedi/comedidev.h index a7d569cfca5d..0dff1ac057cd 100644 --- a/drivers/staging/comedi/comedidev.h +++ b/drivers/staging/comedi/comedidev.h @@ -1001,6 +1001,8 @@ int comedi_dio_insn_config(struct comedi_device *dev, unsigned int mask); unsigned int comedi_dio_update_state(struct comedi_subdevice *s, unsigned int *data); +unsigned int comedi_bytes_per_scan_cmd(struct comedi_subdevice *s, + struct comedi_cmd *cmd); unsigned int comedi_bytes_per_scan(struct comedi_subdevice *s); unsigned int comedi_nscans_left(struct comedi_subdevice *s, unsigned int nscans); diff --git a/drivers/staging/comedi/drivers.c b/drivers/staging/comedi/drivers.c index eefa62f42c0f..5a32b8fc000e 100644 --- a/drivers/staging/comedi/drivers.c +++ b/drivers/staging/comedi/drivers.c @@ -394,11 +394,13 @@ unsigned int comedi_dio_update_state(struct comedi_subdevice *s, EXPORT_SYMBOL_GPL(comedi_dio_update_state); /** - * comedi_bytes_per_scan() - Get length of asynchronous command "scan" in bytes + * comedi_bytes_per_scan_cmd() - Get length of asynchronous command "scan" in + * bytes * @s: COMEDI subdevice. + * @cmd: COMEDI command. * * Determines the overall scan length according to the subdevice type and the - * number of channels in the scan. + * number of channels in the scan for the specified command. * * For digital input, output or input/output subdevices, samples for * multiple channels are assumed to be packed into one or more unsigned @@ -408,9 +410,9 @@ EXPORT_SYMBOL_GPL(comedi_dio_update_state); * * Returns the overall scan length in bytes. */ -unsigned int comedi_bytes_per_scan(struct comedi_subdevice *s) +unsigned int comedi_bytes_per_scan_cmd(struct comedi_subdevice *s, + struct comedi_cmd *cmd) { - struct comedi_cmd *cmd = &s->async->cmd; unsigned int num_samples; unsigned int bits_per_sample; @@ -427,6 +429,29 @@ unsigned int comedi_bytes_per_scan(struct comedi_subdevice *s) } return comedi_samples_to_bytes(s, num_samples); } +EXPORT_SYMBOL_GPL(comedi_bytes_per_scan_cmd); + +/** + * comedi_bytes_per_scan() - Get length of asynchronous command "scan" in bytes + * @s: COMEDI subdevice. + * + * Determines the overall scan length according to the subdevice type and the + * number of channels in the scan for the current command. + * + * For digital input, output or input/output subdevices, samples for + * multiple channels are assumed to be packed into one or more unsigned + * short or unsigned int values according to the subdevice's %SDF_LSAMPL + * flag. For other types of subdevice, samples are assumed to occupy a + * whole unsigned short or unsigned int according to the %SDF_LSAMPL flag. + * + * Returns the overall scan length in bytes. + */ +unsigned int comedi_bytes_per_scan(struct comedi_subdevice *s) +{ + struct comedi_cmd *cmd = &s->async->cmd; + + return comedi_bytes_per_scan_cmd(s, cmd); +} EXPORT_SYMBOL_GPL(comedi_bytes_per_scan); static unsigned int __comedi_nscans_left(struct comedi_subdevice *s, diff --git a/drivers/staging/comedi/drivers/ni_mio_common.c b/drivers/staging/comedi/drivers/ni_mio_common.c index 5edf59ac6706..b04dad8c7092 100644 --- a/drivers/staging/comedi/drivers/ni_mio_common.c +++ b/drivers/staging/comedi/drivers/ni_mio_common.c @@ -3545,6 +3545,7 @@ static int ni_cdio_cmdtest(struct comedi_device *dev, struct comedi_subdevice *s, struct comedi_cmd *cmd) { struct ni_private *devpriv = dev->private; + unsigned int bytes_per_scan; int err = 0; /* Step 1 : check if triggers are trivially valid */ @@ -3579,9 +3580,12 @@ static int ni_cdio_cmdtest(struct comedi_device *dev, err |= comedi_check_trigger_arg_is(&cmd->convert_arg, 0); err |= comedi_check_trigger_arg_is(&cmd->scan_end_arg, cmd->chanlist_len); - err |= comedi_check_trigger_arg_max(&cmd->stop_arg, - s->async->prealloc_bufsz / - comedi_bytes_per_scan(s)); + bytes_per_scan = comedi_bytes_per_scan_cmd(s, cmd); + if (bytes_per_scan) { + err |= comedi_check_trigger_arg_max(&cmd->stop_arg, + s->async->prealloc_bufsz / + bytes_per_scan); + } if (err) return 3; diff --git a/drivers/staging/comedi/drivers/ni_usb6501.c b/drivers/staging/comedi/drivers/ni_usb6501.c index 808ed92ed66f..1bb1cb651349 100644 --- a/drivers/staging/comedi/drivers/ni_usb6501.c +++ b/drivers/staging/comedi/drivers/ni_usb6501.c @@ -463,10 +463,8 @@ static int ni6501_alloc_usb_buffers(struct comedi_device *dev) size = usb_endpoint_maxp(devpriv->ep_tx); devpriv->usb_tx_buf = kzalloc(size, GFP_KERNEL); - if (!devpriv->usb_tx_buf) { - kfree(devpriv->usb_rx_buf); + if (!devpriv->usb_tx_buf) return -ENOMEM; - } return 0; } @@ -518,6 +516,9 @@ static int ni6501_auto_attach(struct comedi_device *dev, if (!devpriv) return -ENOMEM; + mutex_init(&devpriv->mut); + usb_set_intfdata(intf, devpriv); + ret = ni6501_find_endpoints(dev); if (ret) return ret; @@ -526,9 +527,6 @@ static int ni6501_auto_attach(struct comedi_device *dev, if (ret) return ret; - mutex_init(&devpriv->mut); - usb_set_intfdata(intf, devpriv); - ret = comedi_alloc_subdevices(dev, 2); if (ret) return ret; diff --git a/drivers/staging/comedi/drivers/vmk80xx.c b/drivers/staging/comedi/drivers/vmk80xx.c index 6234b649d887..65dc6c51037e 100644 --- a/drivers/staging/comedi/drivers/vmk80xx.c +++ b/drivers/staging/comedi/drivers/vmk80xx.c @@ -682,10 +682,8 @@ static int vmk80xx_alloc_usb_buffers(struct comedi_device *dev) size = usb_endpoint_maxp(devpriv->ep_tx); devpriv->usb_tx_buf = kzalloc(size, GFP_KERNEL); - if (!devpriv->usb_tx_buf) { - kfree(devpriv->usb_rx_buf); + if (!devpriv->usb_tx_buf) return -ENOMEM; - } return 0; } @@ -800,6 +798,8 @@ static int vmk80xx_auto_attach(struct comedi_device *dev, devpriv->model = board->model; + sema_init(&devpriv->limit_sem, 8); + ret = vmk80xx_find_usb_endpoints(dev); if (ret) return ret; @@ -808,8 +808,6 @@ static int vmk80xx_auto_attach(struct comedi_device *dev, if (ret) return ret; - sema_init(&devpriv->limit_sem, 8); - usb_set_intfdata(intf, devpriv); if (devpriv->model == VMK8055_MODEL) diff --git a/drivers/staging/erofs/data.c b/drivers/staging/erofs/data.c index 526e0dbea5b5..81af768e7248 100644 --- a/drivers/staging/erofs/data.c +++ b/drivers/staging/erofs/data.c @@ -298,7 +298,7 @@ submit_bio_retry: *last_block = current_block; /* shift in advance in case of it followed by too many gaps */ - if (unlikely(bio->bi_vcnt >= bio->bi_max_vecs)) { + if (bio->bi_iter.bi_size >= bio->bi_max_vecs * PAGE_SIZE) { /* err should reassign to 0 after submitting */ err = 0; goto submit_bio_out; diff --git a/drivers/staging/erofs/dir.c b/drivers/staging/erofs/dir.c index 829f7b12e0dc..9bbc68729c11 100644 --- a/drivers/staging/erofs/dir.c +++ b/drivers/staging/erofs/dir.c @@ -23,6 +23,21 @@ static const unsigned char erofs_filetype_table[EROFS_FT_MAX] = { [EROFS_FT_SYMLINK] = DT_LNK, }; +static void debug_one_dentry(unsigned char d_type, const char *de_name, + unsigned int de_namelen) +{ +#ifdef CONFIG_EROFS_FS_DEBUG + /* since the on-disk name could not have the trailing '\0' */ + unsigned char dbg_namebuf[EROFS_NAME_LEN + 1]; + + memcpy(dbg_namebuf, de_name, de_namelen); + dbg_namebuf[de_namelen] = '\0'; + + debugln("found dirent %s de_len %u d_type %d", dbg_namebuf, + de_namelen, d_type); +#endif +} + static int erofs_fill_dentries(struct dir_context *ctx, void *dentry_blk, unsigned int *ofs, unsigned int nameoff, unsigned int maxsize) @@ -33,14 +48,10 @@ static int erofs_fill_dentries(struct dir_context *ctx, de = dentry_blk + *ofs; while (de < end) { const char *de_name; - int de_namelen; + unsigned int de_namelen; unsigned char d_type; -#ifdef CONFIG_EROFS_FS_DEBUG - unsigned int dbg_namelen; - unsigned char dbg_namebuf[EROFS_NAME_LEN]; -#endif - if (unlikely(de->file_type < EROFS_FT_MAX)) + if (de->file_type < EROFS_FT_MAX) d_type = erofs_filetype_table[de->file_type]; else d_type = DT_UNKNOWN; @@ -48,26 +59,20 @@ static int erofs_fill_dentries(struct dir_context *ctx, nameoff = le16_to_cpu(de->nameoff); de_name = (char *)dentry_blk + nameoff; - de_namelen = unlikely(de + 1 >= end) ? - /* last directory entry */ - strnlen(de_name, maxsize - nameoff) : - le16_to_cpu(de[1].nameoff) - nameoff; + /* the last dirent in the block? */ + if (de + 1 >= end) + de_namelen = strnlen(de_name, maxsize - nameoff); + else + de_namelen = le16_to_cpu(de[1].nameoff) - nameoff; /* a corrupted entry is found */ - if (unlikely(de_namelen < 0)) { + if (unlikely(nameoff + de_namelen > maxsize || + de_namelen > EROFS_NAME_LEN)) { DBG_BUGON(1); return -EIO; } -#ifdef CONFIG_EROFS_FS_DEBUG - dbg_namelen = min(EROFS_NAME_LEN - 1, de_namelen); - memcpy(dbg_namebuf, de_name, dbg_namelen); - dbg_namebuf[dbg_namelen] = '\0'; - - debugln("%s, found de_name %s de_len %d d_type %d", __func__, - dbg_namebuf, de_namelen, d_type); -#endif - + debug_one_dentry(d_type, de_name, de_namelen); if (!dir_emit(ctx, de_name, de_namelen, le64_to_cpu(de->nid), d_type)) /* stopped by some reason */ diff --git a/drivers/staging/erofs/unzip_vle.c b/drivers/staging/erofs/unzip_vle.c index 8715bc50e09c..31eef8395774 100644 --- a/drivers/staging/erofs/unzip_vle.c +++ b/drivers/staging/erofs/unzip_vle.c @@ -972,6 +972,7 @@ repeat: overlapped = false; compressed_pages = grp->compressed_pages; + err = 0; for (i = 0; i < clusterpages; ++i) { unsigned int pagenr; @@ -981,26 +982,39 @@ repeat: DBG_BUGON(!page); DBG_BUGON(!page->mapping); - if (z_erofs_is_stagingpage(page)) - continue; + if (!z_erofs_is_stagingpage(page)) { #ifdef EROFS_FS_HAS_MANAGED_CACHE - if (page->mapping == MNGD_MAPPING(sbi)) { - DBG_BUGON(!PageUptodate(page)); - continue; - } + if (page->mapping == MNGD_MAPPING(sbi)) { + if (unlikely(!PageUptodate(page))) + err = -EIO; + continue; + } #endif - /* only non-head page could be reused as a compressed page */ - pagenr = z_erofs_onlinepage_index(page); + /* + * only if non-head page can be selected + * for inplace decompression + */ + pagenr = z_erofs_onlinepage_index(page); - DBG_BUGON(pagenr >= nr_pages); - DBG_BUGON(pages[pagenr]); - ++sparsemem_pages; - pages[pagenr] = page; + DBG_BUGON(pagenr >= nr_pages); + DBG_BUGON(pages[pagenr]); + ++sparsemem_pages; + pages[pagenr] = page; - overlapped = true; + overlapped = true; + } + + /* PG_error needs checking for inplaced and staging pages */ + if (unlikely(PageError(page))) { + DBG_BUGON(PageUptodate(page)); + err = -EIO; + } } + if (unlikely(err)) + goto out; + llen = (nr_pages << PAGE_SHIFT) - work->pageofs; if (z_erofs_vle_workgrp_fmt(grp) == Z_EROFS_VLE_WORKGRP_FMT_PLAIN) { @@ -1029,6 +1043,10 @@ repeat: skip_allocpage: vout = erofs_vmap(pages, nr_pages); + if (!vout) { + err = -ENOMEM; + goto out; + } err = z_erofs_vle_unzip_vmap(compressed_pages, clusterpages, vout, llen, work->pageofs, overlapped); @@ -1194,6 +1212,7 @@ repeat: if (page->mapping == mc) { WRITE_ONCE(grp->compressed_pages[nr], page); + ClearPageError(page); if (!PagePrivate(page)) { /* * impossible to be !PagePrivate(page) for diff --git a/drivers/staging/erofs/unzip_vle_lz4.c b/drivers/staging/erofs/unzip_vle_lz4.c index 48b263a2731a..0daac9b984a8 100644 --- a/drivers/staging/erofs/unzip_vle_lz4.c +++ b/drivers/staging/erofs/unzip_vle_lz4.c @@ -136,10 +136,13 @@ int z_erofs_vle_unzip_fast_percpu(struct page **compressed_pages, nr_pages = DIV_ROUND_UP(outlen + pageofs, PAGE_SIZE); - if (clusterpages == 1) + if (clusterpages == 1) { vin = kmap_atomic(compressed_pages[0]); - else + } else { vin = erofs_vmap(compressed_pages, clusterpages); + if (!vin) + return -ENOMEM; + } preempt_disable(); vout = erofs_pcpubuf[smp_processor_id()].data; diff --git a/drivers/staging/iio/adc/ad7192.c b/drivers/staging/iio/adc/ad7192.c index acdbc07fd259..2fc8bc22b57b 100644 --- a/drivers/staging/iio/adc/ad7192.c +++ b/drivers/staging/iio/adc/ad7192.c @@ -109,10 +109,10 @@ #define AD7192_CH_AIN3 BIT(6) /* AIN3 - AINCOM */ #define AD7192_CH_AIN4 BIT(7) /* AIN4 - AINCOM */ -#define AD7193_CH_AIN1P_AIN2M 0x000 /* AIN1(+) - AIN2(-) */ -#define AD7193_CH_AIN3P_AIN4M 0x001 /* AIN3(+) - AIN4(-) */ -#define AD7193_CH_AIN5P_AIN6M 0x002 /* AIN5(+) - AIN6(-) */ -#define AD7193_CH_AIN7P_AIN8M 0x004 /* AIN7(+) - AIN8(-) */ +#define AD7193_CH_AIN1P_AIN2M 0x001 /* AIN1(+) - AIN2(-) */ +#define AD7193_CH_AIN3P_AIN4M 0x002 /* AIN3(+) - AIN4(-) */ +#define AD7193_CH_AIN5P_AIN6M 0x004 /* AIN5(+) - AIN6(-) */ +#define AD7193_CH_AIN7P_AIN8M 0x008 /* AIN7(+) - AIN8(-) */ #define AD7193_CH_TEMP 0x100 /* Temp senseor */ #define AD7193_CH_AIN2P_AIN2M 0x200 /* AIN2(+) - AIN2(-) */ #define AD7193_CH_AIN1 0x401 /* AIN1 - AINCOM */ diff --git a/drivers/staging/iio/meter/ade7854.c b/drivers/staging/iio/meter/ade7854.c index 029c3bf42d4d..07774c000c5a 100644 --- a/drivers/staging/iio/meter/ade7854.c +++ b/drivers/staging/iio/meter/ade7854.c @@ -269,7 +269,7 @@ static IIO_DEV_ATTR_VPEAK(0644, static IIO_DEV_ATTR_IPEAK(0644, ade7854_read_32bit, ade7854_write_32bit, - ADE7854_VPEAK); + ADE7854_IPEAK); static IIO_DEV_ATTR_APHCAL(0644, ade7854_read_16bit, ade7854_write_16bit, diff --git a/drivers/staging/most/core.c b/drivers/staging/most/core.c index 18936cdb1083..956daf8c3bd2 100644 --- a/drivers/staging/most/core.c +++ b/drivers/staging/most/core.c @@ -1431,7 +1431,7 @@ int most_register_interface(struct most_interface *iface) INIT_LIST_HEAD(&iface->p->channel_list); iface->p->dev_id = id; - snprintf(iface->p->name, STRING_SIZE, "mdev%d", id); + strcpy(iface->p->name, iface->description); iface->dev.init_name = iface->p->name; iface->dev.bus = &mc.bus; iface->dev.parent = &mc.dev; diff --git a/drivers/staging/mt7621-dts/gbpc1.dts b/drivers/staging/mt7621-dts/gbpc1.dts index b73385540216..250c15ace2a7 100644 --- a/drivers/staging/mt7621-dts/gbpc1.dts +++ b/drivers/staging/mt7621-dts/gbpc1.dts @@ -117,22 +117,6 @@ status = "okay"; }; -ðernet { - //mtd-mac-address = <&factory 0xe000>; - gmac1: mac@0 { - compatible = "mediatek,eth-mac"; - reg = <0>; - phy-handle = <&phy1>; - }; - - mdio-bus { - phy1: ethernet-phy@1 { - reg = <1>; - phy-mode = "rgmii"; - }; - }; -}; - &pinctrl { state_default: pinctrl0 { gpio { @@ -141,3 +125,16 @@ }; }; }; + +&switch0 { + ports { + port@0 { + label = "ethblack"; + status = "ok"; + }; + port@4 { + label = "ethblue"; + status = "ok"; + }; + }; +}; diff --git a/drivers/staging/mt7621-dts/mt7621.dtsi b/drivers/staging/mt7621-dts/mt7621.dtsi index 6aff3680ce4b..17020e24abd2 100644 --- a/drivers/staging/mt7621-dts/mt7621.dtsi +++ b/drivers/staging/mt7621-dts/mt7621.dtsi @@ -372,16 +372,83 @@ mediatek,ethsys = <ðsys>; - mediatek,switch = <&gsw>; + gmac0: mac@0 { + compatible = "mediatek,eth-mac"; + reg = <0>; + phy-mode = "rgmii"; + fixed-link { + speed = <1000>; + full-duplex; + pause; + }; + }; + gmac1: mac@1 { + compatible = "mediatek,eth-mac"; + reg = <1>; + status = "off"; + phy-mode = "rgmii"; + phy-handle = <&phy5>; + }; mdio-bus { #address-cells = <1>; #size-cells = <0>; - phy1f: ethernet-phy@1f { - reg = <0x1f>; + phy5: ethernet-phy@5 { + reg = <5>; phy-mode = "rgmii"; }; + + switch0: switch0@0 { + compatible = "mediatek,mt7621"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0>; + mediatek,mcm; + resets = <&rstctrl 2>; + reset-names = "mcm"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + reg = <0>; + port@0 { + status = "off"; + reg = <0>; + label = "lan0"; + }; + port@1 { + status = "off"; + reg = <1>; + label = "lan1"; + }; + port@2 { + status = "off"; + reg = <2>; + label = "lan2"; + }; + port@3 { + status = "off"; + reg = <3>; + label = "lan3"; + }; + port@4 { + status = "off"; + reg = <4>; + label = "lan4"; + }; + port@6 { + reg = <6>; + label = "cpu"; + ethernet = <&gmac0>; + phy-mode = "trgmii"; + fixed-link { + speed = <1000>; + full-duplex; + }; + }; + }; + }; }; }; diff --git a/drivers/staging/mt7621-eth/Documentation/devicetree/bindings/net/mediatek-net-gsw.txt b/drivers/staging/mt7621-eth/Documentation/devicetree/bindings/net/mediatek-net-gsw.txt deleted file mode 100644 index 596b38552697..000000000000 --- a/drivers/staging/mt7621-eth/Documentation/devicetree/bindings/net/mediatek-net-gsw.txt +++ /dev/null @@ -1,48 +0,0 @@ -Mediatek Gigabit Switch -======================= - -The mediatek gigabit switch can be found on Mediatek SoCs. - -Required properties: -- compatible: Should be "mediatek,mt7620-gsw", "mediatek,mt7621-gsw", - "mediatek,mt7623-gsw" -- reg: Address and length of the register set for the device -- interrupts: Should contain the gigabit switches interrupt - - -Additional required properties for ARM based SoCs: -- mediatek,reset-pin: phandle describing the reset GPIO -- clocks: the clocks used by the switch -- clock-names: the names of the clocks listed in the clocks property - these should be "trgpll", "esw", "gp2", "gp1" -- mt7530-supply: the phandle of the regulator used to power the switch -- mediatek,pctl-regmap: phandle to the port control regmap. this is used to - setup the drive current - - -Optional properties: -- interrupt-parent: Should be the phandle for the interrupt controller - that services interrupts for this device - -Example: - -gsw: switch@1b100000 { - compatible = "mediatek,mt7623-gsw"; - reg = <0 0x1b110000 0 0x300000>; - - interrupt-parent = <&pio>; - interrupts = <168 IRQ_TYPE_EDGE_RISING>; - - clocks = <&apmixedsys CLK_APMIXED_TRGPLL>, - <ðsys CLK_ETHSYS_ESW>, - <ðsys CLK_ETHSYS_GP2>, - <ðsys CLK_ETHSYS_GP1>; - clock-names = "trgpll", "esw", "gp2", "gp1"; - - mt7530-supply = <&mt6323_vpa_reg>; - - mediatek,pctl-regmap = <&syscfg_pctl_a>; - mediatek,reset-pin = <&pio 15 0>; - - status = "okay"; -}; diff --git a/drivers/staging/mt7621-eth/Kconfig b/drivers/staging/mt7621-eth/Kconfig deleted file mode 100644 index 44ea86c7a96c..000000000000 --- a/drivers/staging/mt7621-eth/Kconfig +++ /dev/null @@ -1,39 +0,0 @@ -config NET_VENDOR_MEDIATEK_STAGING - bool "MediaTek ethernet driver - staging version" - depends on RALINK - ---help--- - If you have an MT7621 Mediatek SoC with ethernet, say Y. - -if NET_VENDOR_MEDIATEK_STAGING -choice - prompt "MAC type" - -config NET_MEDIATEK_MT7621 - bool "MT7621" - depends on MIPS && SOC_MT7621 - -endchoice - -config NET_MEDIATEK_SOC_STAGING - tristate "MediaTek SoC Gigabit Ethernet support" - depends on NET_VENDOR_MEDIATEK_STAGING - select PHYLIB - ---help--- - This driver supports the gigabit ethernet MACs in the - MediaTek SoC family. - -config NET_MEDIATEK_MDIO - def_bool NET_MEDIATEK_SOC_STAGING - depends on NET_MEDIATEK_MT7621 - select PHYLIB - -config NET_MEDIATEK_MDIO_MT7620 - def_bool NET_MEDIATEK_SOC_STAGING - depends on NET_MEDIATEK_MT7621 - select NET_MEDIATEK_MDIO - -config NET_MEDIATEK_GSW_MT7621 - def_tristate NET_MEDIATEK_SOC_STAGING - depends on NET_MEDIATEK_MT7621 - -endif #NET_VENDOR_MEDIATEK_STAGING diff --git a/drivers/staging/mt7621-eth/Makefile b/drivers/staging/mt7621-eth/Makefile deleted file mode 100644 index 018bcc3596b3..000000000000 --- a/drivers/staging/mt7621-eth/Makefile +++ /dev/null @@ -1,14 +0,0 @@ -# -# Makefile for the Ralink SoCs built-in ethernet macs -# - -mtk-eth-soc-y += mtk_eth_soc.o ethtool.o - -mtk-eth-soc-$(CONFIG_NET_MEDIATEK_MDIO) += mdio.o -mtk-eth-soc-$(CONFIG_NET_MEDIATEK_MDIO_MT7620) += mdio_mt7620.o - -mtk-eth-soc-$(CONFIG_NET_MEDIATEK_MT7621) += soc_mt7621.o - -obj-$(CONFIG_NET_MEDIATEK_GSW_MT7621) += gsw_mt7621.o - -obj-$(CONFIG_NET_MEDIATEK_SOC_STAGING) += mtk-eth-soc.o diff --git a/drivers/staging/mt7621-eth/TODO b/drivers/staging/mt7621-eth/TODO deleted file mode 100644 index f9e47d4b4cd4..000000000000 --- a/drivers/staging/mt7621-eth/TODO +++ /dev/null @@ -1,13 +0,0 @@ - -- verify devicetree documentation is consistent with code -- fix ethtool - currently doesn't return valid data. -- general code review and clean up -- add support for second MAC on mt7621 -- convert gsw code to use switchdev interfaces -- md7620_mmi_write etc should probably be wrapped - in a regmap abstraction. -- Get soc_mt7621 to work with QDMA TX if possible. -- Ensure phys are correctly configured when a cable - is plugged in. - -Cc: NeilBrown <neil@brown.name> diff --git a/drivers/staging/mt7621-eth/ethtool.c b/drivers/staging/mt7621-eth/ethtool.c deleted file mode 100644 index 8c4228e2c987..000000000000 --- a/drivers/staging/mt7621-eth/ethtool.c +++ /dev/null @@ -1,250 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org> - * Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org> - * Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com> - */ - -#include "mtk_eth_soc.h" -#include "ethtool.h" - -struct mtk_stat { - char name[ETH_GSTRING_LEN]; - unsigned int idx; -}; - -#define MTK_HW_STAT(stat) { \ - .name = #stat, \ - .idx = offsetof(struct mtk_hw_stats, stat) / sizeof(u64) \ -} - -static const struct mtk_stat mtk_ethtool_hw_stats[] = { - MTK_HW_STAT(tx_bytes), - MTK_HW_STAT(tx_packets), - MTK_HW_STAT(tx_skip), - MTK_HW_STAT(tx_collisions), - MTK_HW_STAT(rx_bytes), - MTK_HW_STAT(rx_packets), - MTK_HW_STAT(rx_overflow), - MTK_HW_STAT(rx_fcs_errors), - MTK_HW_STAT(rx_short_errors), - MTK_HW_STAT(rx_long_errors), - MTK_HW_STAT(rx_checksum_errors), - MTK_HW_STAT(rx_flow_control_packets), -}; - -#define MTK_HW_STATS_LEN ARRAY_SIZE(mtk_ethtool_hw_stats) - -static int mtk_get_link_ksettings(struct net_device *dev, - struct ethtool_link_ksettings *cmd) -{ - struct mtk_mac *mac = netdev_priv(dev); - int err; - - if (!mac->phy_dev) - return -ENODEV; - - if (mac->phy_flags == MTK_PHY_FLAG_ATTACH) { - err = phy_read_status(mac->phy_dev); - if (err) - return -ENODEV; - } - - phy_ethtool_ksettings_get(mac->phy_dev, cmd); - return 0; -} - -static int mtk_set_link_ksettings(struct net_device *dev, - const struct ethtool_link_ksettings *cmd) -{ - struct mtk_mac *mac = netdev_priv(dev); - - if (!mac->phy_dev) - return -ENODEV; - - if (cmd->base.phy_address != mac->phy_dev->mdio.addr) { - if (mac->hw->phy->phy_node[cmd->base.phy_address]) { - mac->phy_dev = mac->hw->phy->phy[cmd->base.phy_address]; - mac->phy_flags = MTK_PHY_FLAG_PORT; - } else if (mac->hw->mii_bus) { - mac->phy_dev = mdiobus_get_phy(mac->hw->mii_bus, - cmd->base.phy_address); - if (!mac->phy_dev) - return -ENODEV; - mac->phy_flags = MTK_PHY_FLAG_ATTACH; - } else { - return -ENODEV; - } - } - - return phy_ethtool_ksettings_set(mac->phy_dev, cmd); -} - -static void mtk_get_drvinfo(struct net_device *dev, - struct ethtool_drvinfo *info) -{ - struct mtk_mac *mac = netdev_priv(dev); - struct mtk_soc_data *soc = mac->hw->soc; - - strlcpy(info->driver, mac->hw->dev->driver->name, sizeof(info->driver)); - strlcpy(info->bus_info, dev_name(mac->hw->dev), sizeof(info->bus_info)); - - if (soc->reg_table[MTK_REG_MTK_COUNTER_BASE]) - info->n_stats = MTK_HW_STATS_LEN; -} - -static u32 mtk_get_msglevel(struct net_device *dev) -{ - struct mtk_mac *mac = netdev_priv(dev); - - return mac->hw->msg_enable; -} - -static void mtk_set_msglevel(struct net_device *dev, u32 value) -{ - struct mtk_mac *mac = netdev_priv(dev); - - mac->hw->msg_enable = value; -} - -static int mtk_nway_reset(struct net_device *dev) -{ - struct mtk_mac *mac = netdev_priv(dev); - - if (!mac->phy_dev) - return -EOPNOTSUPP; - - return genphy_restart_aneg(mac->phy_dev); -} - -static u32 mtk_get_link(struct net_device *dev) -{ - struct mtk_mac *mac = netdev_priv(dev); - int err; - - if (!mac->phy_dev) - goto out_get_link; - - if (mac->phy_flags == MTK_PHY_FLAG_ATTACH) { - err = genphy_update_link(mac->phy_dev); - if (err) - goto out_get_link; - } - - return mac->phy_dev->link; - -out_get_link: - return ethtool_op_get_link(dev); -} - -static int mtk_set_ringparam(struct net_device *dev, - struct ethtool_ringparam *ring) -{ - struct mtk_mac *mac = netdev_priv(dev); - - if ((ring->tx_pending < 2) || - (ring->rx_pending < 2) || - (ring->rx_pending > mac->hw->soc->dma_ring_size) || - (ring->tx_pending > mac->hw->soc->dma_ring_size)) - return -EINVAL; - - dev->netdev_ops->ndo_stop(dev); - - mac->hw->tx_ring.tx_ring_size = BIT(fls(ring->tx_pending) - 1); - mac->hw->rx_ring[0].rx_ring_size = BIT(fls(ring->rx_pending) - 1); - - return dev->netdev_ops->ndo_open(dev); -} - -static void mtk_get_ringparam(struct net_device *dev, - struct ethtool_ringparam *ring) -{ - struct mtk_mac *mac = netdev_priv(dev); - - ring->rx_max_pending = mac->hw->soc->dma_ring_size; - ring->tx_max_pending = mac->hw->soc->dma_ring_size; - ring->rx_pending = mac->hw->rx_ring[0].rx_ring_size; - ring->tx_pending = mac->hw->tx_ring.tx_ring_size; -} - -static void mtk_get_strings(struct net_device *dev, u32 stringset, u8 *data) -{ - int i; - - switch (stringset) { - case ETH_SS_STATS: - for (i = 0; i < MTK_HW_STATS_LEN; i++) { - memcpy(data, mtk_ethtool_hw_stats[i].name, - ETH_GSTRING_LEN); - data += ETH_GSTRING_LEN; - } - break; - } -} - -static int mtk_get_sset_count(struct net_device *dev, int sset) -{ - switch (sset) { - case ETH_SS_STATS: - return MTK_HW_STATS_LEN; - default: - return -EOPNOTSUPP; - } -} - -static void mtk_get_ethtool_stats(struct net_device *dev, - struct ethtool_stats *stats, u64 *data) -{ - struct mtk_mac *mac = netdev_priv(dev); - struct mtk_hw_stats *hwstats = mac->hw_stats; - unsigned int start; - int i; - - if (netif_running(dev) && netif_device_present(dev)) { - if (spin_trylock(&hwstats->stats_lock)) { - mtk_stats_update_mac(mac); - spin_unlock(&hwstats->stats_lock); - } - } - - do { - start = u64_stats_fetch_begin_irq(&hwstats->syncp); - for (i = 0; i < MTK_HW_STATS_LEN; i++) - data[i] = ((u64 *)hwstats)[mtk_ethtool_hw_stats[i].idx]; - - } while (u64_stats_fetch_retry_irq(&hwstats->syncp, start)); -} - -static struct ethtool_ops mtk_ethtool_ops = { - .get_link_ksettings = mtk_get_link_ksettings, - .set_link_ksettings = mtk_set_link_ksettings, - .get_drvinfo = mtk_get_drvinfo, - .get_msglevel = mtk_get_msglevel, - .set_msglevel = mtk_set_msglevel, - .nway_reset = mtk_nway_reset, - .get_link = mtk_get_link, - .set_ringparam = mtk_set_ringparam, - .get_ringparam = mtk_get_ringparam, -}; - -void mtk_set_ethtool_ops(struct net_device *netdev) -{ - struct mtk_mac *mac = netdev_priv(netdev); - struct mtk_soc_data *soc = mac->hw->soc; - - if (soc->reg_table[MTK_REG_MTK_COUNTER_BASE]) { - mtk_ethtool_ops.get_strings = mtk_get_strings; - mtk_ethtool_ops.get_sset_count = mtk_get_sset_count; - mtk_ethtool_ops.get_ethtool_stats = mtk_get_ethtool_stats; - } - - netdev->ethtool_ops = &mtk_ethtool_ops; -} diff --git a/drivers/staging/mt7621-eth/ethtool.h b/drivers/staging/mt7621-eth/ethtool.h deleted file mode 100644 index 0071469aea6c..000000000000 --- a/drivers/staging/mt7621-eth/ethtool.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org> - * Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org> - * Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com> - */ - -#ifndef MTK_ETHTOOL_H -#define MTK_ETHTOOL_H - -#include <linux/ethtool.h> - -void mtk_set_ethtool_ops(struct net_device *netdev); - -#endif /* MTK_ETHTOOL_H */ diff --git a/drivers/staging/mt7621-eth/gsw_mt7620.h b/drivers/staging/mt7621-eth/gsw_mt7620.h deleted file mode 100644 index 70f7e5481952..000000000000 --- a/drivers/staging/mt7621-eth/gsw_mt7620.h +++ /dev/null @@ -1,277 +0,0 @@ -/* This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org> - * Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org> - * Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com> - */ - -#ifndef _RALINK_GSW_MT7620_H__ -#define _RALINK_GSW_MT7620_H__ - -#define GSW_REG_PHY_TIMEOUT (5 * HZ) - -#define MT7620_GSW_REG_PIAC 0x0004 - -#define GSW_NUM_VLANS 16 -#define GSW_NUM_VIDS 4096 -#define GSW_NUM_PORTS 7 -#define GSW_PORT6 6 - -#define GSW_MDIO_ACCESS BIT(31) -#define GSW_MDIO_READ BIT(19) -#define GSW_MDIO_WRITE BIT(18) -#define GSW_MDIO_START BIT(16) -#define GSW_MDIO_ADDR_SHIFT 20 -#define GSW_MDIO_REG_SHIFT 25 - -#define GSW_REG_PORT_PMCR(x) (0x3000 + (x * 0x100)) -#define GSW_REG_PORT_STATUS(x) (0x3008 + (x * 0x100)) -#define GSW_REG_SMACCR0 0x3fE4 -#define GSW_REG_SMACCR1 0x3fE8 -#define GSW_REG_CKGCR 0x3ff0 - -#define GSW_REG_IMR 0x7008 -#define GSW_REG_ISR 0x700c -#define GSW_REG_GPC1 0x7014 - -#define SYSC_REG_CHIP_REV_ID 0x0c -#define SYSC_REG_CFG 0x10 -#define SYSC_REG_CFG1 0x14 -#define RST_CTRL_MCM BIT(2) -#define SYSC_PAD_RGMII2_MDIO 0x58 -#define SYSC_GPIO_MODE 0x60 - -#define PORT_IRQ_ST_CHG 0x7f - -#define MT7621_ESW_PHY_POLLING 0x0000 -#define MT7620_ESW_PHY_POLLING 0x7000 - -#define PMCR_IPG BIT(18) -#define PMCR_MAC_MODE BIT(16) -#define PMCR_FORCE BIT(15) -#define PMCR_TX_EN BIT(14) -#define PMCR_RX_EN BIT(13) -#define PMCR_BACKOFF BIT(9) -#define PMCR_BACKPRES BIT(8) -#define PMCR_RX_FC BIT(5) -#define PMCR_TX_FC BIT(4) -#define PMCR_SPEED(_x) (_x << 2) -#define PMCR_DUPLEX BIT(1) -#define PMCR_LINK BIT(0) - -#define PHY_AN_EN BIT(31) -#define PHY_PRE_EN BIT(30) -#define PMY_MDC_CONF(_x) ((_x & 0x3f) << 24) - -/* ethernet subsystem config register */ -#define ETHSYS_SYSCFG0 0x14 -/* ethernet subsystem clock register */ -#define ETHSYS_CLKCFG0 0x2c -#define ETHSYS_TRGMII_CLK_SEL362_5 BIT(11) - -/* p5 RGMII wrapper TX clock control register */ -#define MT7530_P5RGMIITXCR 0x7b04 -/* p5 RGMII wrapper RX clock control register */ -#define MT7530_P5RGMIIRXCR 0x7b00 -/* TRGMII TDX ODT registers */ -#define MT7530_TRGMII_TD0_ODT 0x7a54 -#define MT7530_TRGMII_TD1_ODT 0x7a5c -#define MT7530_TRGMII_TD2_ODT 0x7a64 -#define MT7530_TRGMII_TD3_ODT 0x7a6c -#define MT7530_TRGMII_TD4_ODT 0x7a74 -#define MT7530_TRGMII_TD5_ODT 0x7a7c -/* TRGMII TCK ctrl register */ -#define MT7530_TRGMII_TCK_CTRL 0x7a78 -/* TRGMII Tx ctrl register */ -#define MT7530_TRGMII_TXCTRL 0x7a40 -/* port 6 extended control register */ -#define MT7530_P6ECR 0x7830 -/* IO driver control register */ -#define MT7530_IO_DRV_CR 0x7810 -/* top signal control register */ -#define MT7530_TOP_SIG_CTRL 0x7808 -/* modified hwtrap register */ -#define MT7530_MHWTRAP 0x7804 -/* hwtrap status register */ -#define MT7530_HWTRAP 0x7800 -/* status interrupt register */ -#define MT7530_SYS_INT_STS 0x700c -/* system nterrupt register */ -#define MT7530_SYS_INT_EN 0x7008 -/* system control register */ -#define MT7530_SYS_CTRL 0x7000 -/* port MAC status register */ -#define MT7530_PMSR_P(x) (0x3008 + (x * 0x100)) -/* port MAC control register */ -#define MT7530_PMCR_P(x) (0x3000 + (x * 0x100)) - -#define MT7621_XTAL_SHIFT 6 -#define MT7621_XTAL_MASK 0x7 -#define MT7621_XTAL_25 6 -#define MT7621_XTAL_40 3 -#define MT7621_MDIO_DRV_MASK (3 << 4) -#define MT7621_GE1_MODE_MASK (3 << 12) - -#define TRGMII_TXCTRL_TXC_INV BIT(30) -#define P6ECR_INTF_MODE_RGMII BIT(1) -#define P5RGMIIRXCR_C_ALIGN BIT(8) -#define P5RGMIIRXCR_DELAY_2 BIT(1) -#define P5RGMIITXCR_DELAY_2 (BIT(8) | BIT(2)) - -/* TOP_SIG_CTRL bits */ -#define TOP_SIG_CTRL_NORMAL (BIT(17) | BIT(16)) - -/* MHWTRAP bits */ -#define MHWTRAP_MANUAL BIT(16) -#define MHWTRAP_P5_MAC_SEL BIT(13) -#define MHWTRAP_P6_DIS BIT(8) -#define MHWTRAP_P5_RGMII_MODE BIT(7) -#define MHWTRAP_P5_DIS BIT(6) -#define MHWTRAP_PHY_ACCESS BIT(5) - -/* HWTRAP bits */ -#define HWTRAP_XTAL_SHIFT 9 -#define HWTRAP_XTAL_MASK 0x3 - -/* SYS_CTRL bits */ -#define SYS_CTRL_SW_RST BIT(1) -#define SYS_CTRL_REG_RST BIT(0) - -/* PMCR bits */ -#define PMCR_IFG_XMIT_96 BIT(18) -#define PMCR_MAC_MODE BIT(16) -#define PMCR_FORCE_MODE BIT(15) -#define PMCR_TX_EN BIT(14) -#define PMCR_RX_EN BIT(13) -#define PMCR_BACK_PRES_EN BIT(9) -#define PMCR_BACKOFF_EN BIT(8) -#define PMCR_TX_FC_EN BIT(5) -#define PMCR_RX_FC_EN BIT(4) -#define PMCR_FORCE_SPEED_1000 BIT(3) -#define PMCR_FORCE_FDX BIT(1) -#define PMCR_FORCE_LNK BIT(0) -#define PMCR_FIXED_LINK (PMCR_IFG_XMIT_96 | PMCR_MAC_MODE | \ - PMCR_FORCE_MODE | PMCR_TX_EN | PMCR_RX_EN | \ - PMCR_BACK_PRES_EN | PMCR_BACKOFF_EN | \ - PMCR_FORCE_SPEED_1000 | PMCR_FORCE_FDX | \ - PMCR_FORCE_LNK) - -#define PMCR_FIXED_LINK_FC (PMCR_FIXED_LINK | \ - PMCR_TX_FC_EN | PMCR_RX_FC_EN) - -/* TRGMII control registers */ -#define GSW_INTF_MODE 0x390 -#define GSW_TRGMII_TD0_ODT 0x354 -#define GSW_TRGMII_TD1_ODT 0x35c -#define GSW_TRGMII_TD2_ODT 0x364 -#define GSW_TRGMII_TD3_ODT 0x36c -#define GSW_TRGMII_TXCTL_ODT 0x374 -#define GSW_TRGMII_TCK_ODT 0x37c -#define GSW_TRGMII_RCK_CTRL 0x300 - -#define INTF_MODE_TRGMII BIT(1) -#define TRGMII_RCK_CTRL_RX_RST BIT(31) - -/* Mac control registers */ -#define MTK_MAC_P2_MCR 0x200 -#define MTK_MAC_P1_MCR 0x100 - -#define MAC_MCR_MAX_RX_2K BIT(29) -#define MAC_MCR_IPG_CFG (BIT(18) | BIT(16)) -#define MAC_MCR_FORCE_MODE BIT(15) -#define MAC_MCR_TX_EN BIT(14) -#define MAC_MCR_RX_EN BIT(13) -#define MAC_MCR_BACKOFF_EN BIT(9) -#define MAC_MCR_BACKPR_EN BIT(8) -#define MAC_MCR_FORCE_RX_FC BIT(5) -#define MAC_MCR_FORCE_TX_FC BIT(4) -#define MAC_MCR_SPEED_1000 BIT(3) -#define MAC_MCR_FORCE_DPX BIT(1) -#define MAC_MCR_FORCE_LINK BIT(0) -#define MAC_MCR_FIXED_LINK (MAC_MCR_MAX_RX_2K | MAC_MCR_IPG_CFG | \ - MAC_MCR_FORCE_MODE | MAC_MCR_TX_EN | \ - MAC_MCR_RX_EN | MAC_MCR_BACKOFF_EN | \ - MAC_MCR_BACKPR_EN | MAC_MCR_FORCE_RX_FC | \ - MAC_MCR_FORCE_TX_FC | MAC_MCR_SPEED_1000 | \ - MAC_MCR_FORCE_DPX | MAC_MCR_FORCE_LINK) -#define MAC_MCR_FIXED_LINK_FC (MAC_MCR_MAX_RX_2K | MAC_MCR_IPG_CFG | \ - MAC_MCR_FIXED_LINK) - -/* possible XTAL speed */ -#define MT7623_XTAL_40 0 -#define MT7623_XTAL_20 1 -#define MT7623_XTAL_25 3 - -/* GPIO port control registers */ -#define GPIO_OD33_CTRL8 0x4c0 -#define GPIO_BIAS_CTRL 0xed0 -#define GPIO_DRV_SEL10 0xf00 - -/* on MT7620 the functio of port 4 can be software configured */ -enum { - PORT4_EPHY = 0, - PORT4_EXT, -}; - -/* struct mt7620_gsw - the structure that holds the SoC specific data - * @dev: The Device struct - * @base: The base address - * @piac_offset: The PIAC base may change depending on SoC - * @irq: The IRQ we are using - * @port4: The port4 mode on MT7620 - * @autopoll: Is MDIO autopolling enabled - * @ethsys: The ethsys register map - * @pctl: The pin control register map - * @clk_gsw: The switch clock - * @clk_gp1: The gmac1 clock - * @clk_gp2: The gmac2 clock - * @clk_trgpll: The trgmii pll clock - */ -struct mt7620_gsw { - struct device *dev; - void __iomem *base; - u32 piac_offset; - int irq; - int port4; - unsigned long int autopoll; - - struct regmap *ethsys; - struct regmap *pctl; - - struct clk *clk_gsw; - struct clk *clk_gp1; - struct clk *clk_gp2; - struct clk *clk_trgpll; -}; - -/* switch register I/O wrappers */ -void mtk_switch_w32(struct mt7620_gsw *gsw, u32 val, unsigned int reg); -u32 mtk_switch_r32(struct mt7620_gsw *gsw, unsigned int reg); - -/* the callback used by the driver core to bringup the switch */ -int mtk_gsw_init(struct mtk_eth *eth); - -/* MDIO access wrappers */ -int mt7620_mdio_write(struct mii_bus *bus, int phy_addr, int phy_reg, u16 val); -int mt7620_mdio_read(struct mii_bus *bus, int phy_addr, int phy_reg); -void mt7620_mdio_link_adjust(struct mtk_eth *eth, int port); -int mt7620_has_carrier(struct mtk_eth *eth); -void mt7620_print_link_state(struct mtk_eth *eth, int port, int link, - int speed, int duplex); -void mt7530_mdio_w32(struct mt7620_gsw *gsw, u32 reg, u32 val); -u32 mt7530_mdio_r32(struct mt7620_gsw *gsw, u32 reg); -void mt7530_mdio_m32(struct mt7620_gsw *gsw, u32 mask, u32 set, u32 reg); - -u32 _mt7620_mii_write(struct mt7620_gsw *gsw, u32 phy_addr, - u32 phy_register, u32 write_data); -u32 _mt7620_mii_read(struct mt7620_gsw *gsw, int phy_addr, int phy_reg); -void mt7620_handle_carrier(struct mtk_eth *eth); - -#endif diff --git a/drivers/staging/mt7621-eth/gsw_mt7621.c b/drivers/staging/mt7621-eth/gsw_mt7621.c deleted file mode 100644 index 53767b17bad9..000000000000 --- a/drivers/staging/mt7621-eth/gsw_mt7621.c +++ /dev/null @@ -1,297 +0,0 @@ -/* This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org> - * Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org> - * Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com> - */ - -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/platform_device.h> -#include <linux/of_device.h> -#include <linux/of_irq.h> - -#include <ralink_regs.h> - -#include "mtk_eth_soc.h" -#include "gsw_mt7620.h" - -void mtk_switch_w32(struct mt7620_gsw *gsw, u32 val, unsigned int reg) -{ - iowrite32(val, gsw->base + reg); -} -EXPORT_SYMBOL_GPL(mtk_switch_w32); - -u32 mtk_switch_r32(struct mt7620_gsw *gsw, unsigned int reg) -{ - return ioread32(gsw->base + reg); -} -EXPORT_SYMBOL_GPL(mtk_switch_r32); - -static irqreturn_t gsw_interrupt_mt7621(int irq, void *_eth) -{ - struct mtk_eth *eth = (struct mtk_eth *)_eth; - struct mt7620_gsw *gsw = (struct mt7620_gsw *)eth->sw_priv; - u32 reg, i; - - reg = mt7530_mdio_r32(gsw, MT7530_SYS_INT_STS); - - for (i = 0; i < 5; i++) { - unsigned int link; - - if ((reg & BIT(i)) == 0) - continue; - - link = mt7530_mdio_r32(gsw, MT7530_PMSR_P(i)) & 0x1; - - if (link == eth->link[i]) - continue; - - eth->link[i] = link; - if (link) - netdev_info(*eth->netdev, - "port %d link up\n", i); - else - netdev_info(*eth->netdev, - "port %d link down\n", i); - } - - mt7530_mdio_w32(gsw, MT7530_SYS_INT_STS, 0x1f); - - return IRQ_HANDLED; -} - -static void mt7621_hw_init(struct mtk_eth *eth, struct mt7620_gsw *gsw, - struct device_node *np) -{ - u32 i; - u32 val; - - /* hardware reset the switch */ - mtk_reset(eth, RST_CTRL_MCM); - mdelay(10); - - /* reduce RGMII2 PAD driving strength */ - rt_sysc_m32(MT7621_MDIO_DRV_MASK, 0, SYSC_PAD_RGMII2_MDIO); - - /* gpio mux - RGMII1=Normal mode */ - rt_sysc_m32(BIT(14), 0, SYSC_GPIO_MODE); - - /* set GMAC1 RGMII mode */ - rt_sysc_m32(MT7621_GE1_MODE_MASK, 0, SYSC_REG_CFG1); - - /* enable MDIO to control MT7530 */ - rt_sysc_m32(3 << 12, 0, SYSC_GPIO_MODE); - - /* turn off all PHYs */ - for (i = 0; i <= 4; i++) { - val = _mt7620_mii_read(gsw, i, 0x0); - val |= BIT(11); - _mt7620_mii_write(gsw, i, 0x0, val); - } - - /* reset the switch */ - mt7530_mdio_w32(gsw, MT7530_SYS_CTRL, - SYS_CTRL_SW_RST | SYS_CTRL_REG_RST); - usleep_range(10, 20); - - if ((rt_sysc_r32(SYSC_REG_CHIP_REV_ID) & 0xFFFF) == 0x0101) { - /* GE1, Force 1000M/FD, FC ON, MAX_RX_LENGTH 1536 */ - mtk_switch_w32(gsw, MAC_MCR_FIXED_LINK, MTK_MAC_P2_MCR); - mt7530_mdio_w32(gsw, MT7530_PMCR_P(6), PMCR_FIXED_LINK); - } else { - /* GE1, Force 1000M/FD, FC ON, MAX_RX_LENGTH 1536 */ - mtk_switch_w32(gsw, MAC_MCR_FIXED_LINK_FC, MTK_MAC_P1_MCR); - mt7530_mdio_w32(gsw, MT7530_PMCR_P(6), PMCR_FIXED_LINK_FC); - } - - /* GE2, Link down */ - mtk_switch_w32(gsw, MAC_MCR_FORCE_MODE, MTK_MAC_P2_MCR); - - /* Enable Port 6, P5 as GMAC5, P5 disable */ - val = mt7530_mdio_r32(gsw, MT7530_MHWTRAP); - /* Enable Port 6 */ - val &= ~MHWTRAP_P6_DIS; - /* Disable Port 5 */ - val |= MHWTRAP_P5_DIS; - /* manual override of HW-Trap */ - val |= MHWTRAP_MANUAL; - mt7530_mdio_w32(gsw, MT7530_MHWTRAP, val); - - val = rt_sysc_r32(SYSC_REG_CFG); - val = (val >> MT7621_XTAL_SHIFT) & MT7621_XTAL_MASK; - if (val < MT7621_XTAL_25 && val >= MT7621_XTAL_40) { - /* 40Mhz */ - - /* disable MT7530 core clock */ - _mt7620_mii_write(gsw, 0, 13, 0x1f); - _mt7620_mii_write(gsw, 0, 14, 0x410); - _mt7620_mii_write(gsw, 0, 13, 0x401f); - _mt7620_mii_write(gsw, 0, 14, 0x0); - - /* disable MT7530 PLL */ - _mt7620_mii_write(gsw, 0, 13, 0x1f); - _mt7620_mii_write(gsw, 0, 14, 0x40d); - _mt7620_mii_write(gsw, 0, 13, 0x401f); - _mt7620_mii_write(gsw, 0, 14, 0x2020); - - /* for MT7530 core clock = 500Mhz */ - _mt7620_mii_write(gsw, 0, 13, 0x1f); - _mt7620_mii_write(gsw, 0, 14, 0x40e); - _mt7620_mii_write(gsw, 0, 13, 0x401f); - _mt7620_mii_write(gsw, 0, 14, 0x119); - - /* enable MT7530 PLL */ - _mt7620_mii_write(gsw, 0, 13, 0x1f); - _mt7620_mii_write(gsw, 0, 14, 0x40d); - _mt7620_mii_write(gsw, 0, 13, 0x401f); - _mt7620_mii_write(gsw, 0, 14, 0x2820); - - usleep_range(20, 40); - - /* enable MT7530 core clock */ - _mt7620_mii_write(gsw, 0, 13, 0x1f); - _mt7620_mii_write(gsw, 0, 14, 0x410); - _mt7620_mii_write(gsw, 0, 13, 0x401f); - } - - /* RGMII */ - _mt7620_mii_write(gsw, 0, 14, 0x1); - - /* set MT7530 central align */ - mt7530_mdio_m32(gsw, BIT(0), P6ECR_INTF_MODE_RGMII, MT7530_P6ECR); - mt7530_mdio_m32(gsw, TRGMII_TXCTRL_TXC_INV, 0, - MT7530_TRGMII_TXCTRL); - mt7530_mdio_w32(gsw, MT7530_TRGMII_TCK_CTRL, 0x855); - - /* delay setting for 10/1000M */ - mt7530_mdio_w32(gsw, MT7530_P5RGMIIRXCR, - P5RGMIIRXCR_C_ALIGN | P5RGMIIRXCR_DELAY_2); - mt7530_mdio_w32(gsw, MT7530_P5RGMIITXCR, 0x14); - - /* lower Tx Driving*/ - mt7530_mdio_w32(gsw, MT7530_TRGMII_TD0_ODT, 0x44); - mt7530_mdio_w32(gsw, MT7530_TRGMII_TD1_ODT, 0x44); - mt7530_mdio_w32(gsw, MT7530_TRGMII_TD2_ODT, 0x44); - mt7530_mdio_w32(gsw, MT7530_TRGMII_TD3_ODT, 0x44); - mt7530_mdio_w32(gsw, MT7530_TRGMII_TD4_ODT, 0x44); - mt7530_mdio_w32(gsw, MT7530_TRGMII_TD5_ODT, 0x44); - - /* turn on all PHYs */ - for (i = 0; i <= 4; i++) { - val = _mt7620_mii_read(gsw, i, 0); - val &= ~BIT(11); - _mt7620_mii_write(gsw, i, 0, val); - } - -#define MT7530_NUM_PORTS 8 -#define REG_ESW_PORT_PCR(x) (0x2004 | ((x) << 8)) -#define REG_ESW_PORT_PVC(x) (0x2010 | ((x) << 8)) -#define REG_ESW_PORT_PPBV1(x) (0x2014 | ((x) << 8)) -#define MT7530_CPU_PORT 6 - - /* This is copied from mt7530_apply_config in libreCMC driver */ - { - int i; - - for (i = 0; i < MT7530_NUM_PORTS; i++) - mt7530_mdio_w32(gsw, REG_ESW_PORT_PCR(i), 0x00400000); - - mt7530_mdio_w32(gsw, REG_ESW_PORT_PCR(MT7530_CPU_PORT), - 0x00ff0000); - - for (i = 0; i < MT7530_NUM_PORTS; i++) - mt7530_mdio_w32(gsw, REG_ESW_PORT_PVC(i), 0x810000c0); - } - - /* enable irq */ - mt7530_mdio_m32(gsw, 0, 3 << 16, MT7530_TOP_SIG_CTRL); - mt7530_mdio_w32(gsw, MT7530_SYS_INT_EN, 0x1f); -} - -static const struct of_device_id mediatek_gsw_match[] = { - { .compatible = "mediatek,mt7621-gsw" }, - {}, -}; -MODULE_DEVICE_TABLE(of, mediatek_gsw_match); - -int mtk_gsw_init(struct mtk_eth *eth) -{ - struct device_node *np = eth->switch_np; - struct platform_device *pdev = of_find_device_by_node(np); - struct mt7620_gsw *gsw; - - if (!pdev) - return -ENODEV; - - if (!of_device_is_compatible(np, mediatek_gsw_match->compatible)) - return -EINVAL; - - gsw = platform_get_drvdata(pdev); - eth->sw_priv = gsw; - - if (!gsw->irq) - return -EINVAL; - - request_irq(gsw->irq, gsw_interrupt_mt7621, 0, - "gsw", eth); - disable_irq(gsw->irq); - - mt7621_hw_init(eth, gsw, np); - - enable_irq(gsw->irq); - - return 0; -} -EXPORT_SYMBOL_GPL(mtk_gsw_init); - -static int mt7621_gsw_probe(struct platform_device *pdev) -{ - struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - struct mt7620_gsw *gsw; - - gsw = devm_kzalloc(&pdev->dev, sizeof(struct mt7620_gsw), GFP_KERNEL); - if (!gsw) - return -ENOMEM; - - gsw->base = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(gsw->base)) - return PTR_ERR(gsw->base); - - gsw->dev = &pdev->dev; - gsw->irq = irq_of_parse_and_map(pdev->dev.of_node, 0); - - platform_set_drvdata(pdev, gsw); - - return 0; -} - -static int mt7621_gsw_remove(struct platform_device *pdev) -{ - platform_set_drvdata(pdev, NULL); - - return 0; -} - -static struct platform_driver gsw_driver = { - .probe = mt7621_gsw_probe, - .remove = mt7621_gsw_remove, - .driver = { - .name = "mt7621-gsw", - .of_match_table = mediatek_gsw_match, - }, -}; - -module_platform_driver(gsw_driver); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("John Crispin <blogic@openwrt.org>"); -MODULE_DESCRIPTION("GBit switch driver for Mediatek MT7621 SoC"); diff --git a/drivers/staging/mt7621-eth/mdio.c b/drivers/staging/mt7621-eth/mdio.c deleted file mode 100644 index 5fea6a447eed..000000000000 --- a/drivers/staging/mt7621-eth/mdio.c +++ /dev/null @@ -1,275 +0,0 @@ -/* This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License - * - * Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org> - * Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org> - * Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com> - */ - -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/phy.h> -#include <linux/of_net.h> -#include <linux/of_mdio.h> - -#include "mtk_eth_soc.h" -#include "mdio.h" - -static int mtk_mdio_reset(struct mii_bus *bus) -{ - /* TODO */ - return 0; -} - -static void mtk_phy_link_adjust(struct net_device *dev) -{ - struct mtk_eth *eth = netdev_priv(dev); - unsigned long flags; - int i; - - spin_lock_irqsave(ð->phy->lock, flags); - for (i = 0; i < 8; i++) { - if (eth->phy->phy_node[i]) { - struct phy_device *phydev = eth->phy->phy[i]; - int status_change = 0; - - if (phydev->link) - if (eth->phy->duplex[i] != phydev->duplex || - eth->phy->speed[i] != phydev->speed) - status_change = 1; - - if (phydev->link != eth->link[i]) - status_change = 1; - - switch (phydev->speed) { - case SPEED_1000: - case SPEED_100: - case SPEED_10: - eth->link[i] = phydev->link; - eth->phy->duplex[i] = phydev->duplex; - eth->phy->speed[i] = phydev->speed; - - if (status_change && - eth->soc->mdio_adjust_link) - eth->soc->mdio_adjust_link(eth, i); - break; - } - } - } - spin_unlock_irqrestore(ð->phy->lock, flags); -} - -int mtk_connect_phy_node(struct mtk_eth *eth, struct mtk_mac *mac, - struct device_node *phy_node) -{ - const __be32 *_port = NULL; - struct phy_device *phydev; - int phy_mode, port; - - _port = of_get_property(phy_node, "reg", NULL); - - if (!_port || (be32_to_cpu(*_port) >= 0x20)) { - pr_err("%pOFn: invalid port id\n", phy_node); - return -EINVAL; - } - port = be32_to_cpu(*_port); - phy_mode = of_get_phy_mode(phy_node); - if (phy_mode < 0) { - dev_err(eth->dev, "incorrect phy-mode %d\n", phy_mode); - eth->phy->phy_node[port] = NULL; - return -EINVAL; - } - - phydev = of_phy_connect(eth->netdev[mac->id], phy_node, - mtk_phy_link_adjust, 0, phy_mode); - if (!phydev) { - dev_err(eth->dev, "could not connect to PHY\n"); - eth->phy->phy_node[port] = NULL; - return -ENODEV; - } - - phydev->supported &= PHY_1000BT_FEATURES; - phydev->advertising = phydev->supported; - - dev_info(eth->dev, - "connected port %d to PHY at %s [uid=%08x, driver=%s]\n", - port, phydev_name(phydev), phydev->phy_id, - phydev->drv->name); - - eth->phy->phy[port] = phydev; - eth->link[port] = 0; - - return 0; -} - -static void phy_init(struct mtk_eth *eth, struct mtk_mac *mac, - struct phy_device *phy) -{ - phy_attach(eth->netdev[mac->id], phydev_name(phy), - PHY_INTERFACE_MODE_MII); - - phy->autoneg = AUTONEG_ENABLE; - phy->speed = 0; - phy->duplex = 0; - phy_set_max_speed(phy, SPEED_100); - phy->advertising = phy->supported | ADVERTISED_Autoneg; - - phy_start_aneg(phy); -} - -static int mtk_phy_connect(struct mtk_mac *mac) -{ - struct mtk_eth *eth = mac->hw; - int i; - - for (i = 0; i < 8; i++) { - if (eth->phy->phy_node[i]) { - if (!mac->phy_dev) { - mac->phy_dev = eth->phy->phy[i]; - mac->phy_flags = MTK_PHY_FLAG_PORT; - } - } else if (eth->mii_bus) { - struct phy_device *phy; - - phy = mdiobus_get_phy(eth->mii_bus, i); - if (phy) { - phy_init(eth, mac, phy); - if (!mac->phy_dev) { - mac->phy_dev = phy; - mac->phy_flags = MTK_PHY_FLAG_ATTACH; - } - } - } - } - - return 0; -} - -static void mtk_phy_disconnect(struct mtk_mac *mac) -{ - struct mtk_eth *eth = mac->hw; - unsigned long flags; - int i; - - for (i = 0; i < 8; i++) - if (eth->phy->phy_fixed[i]) { - spin_lock_irqsave(ð->phy->lock, flags); - eth->link[i] = 0; - if (eth->soc->mdio_adjust_link) - eth->soc->mdio_adjust_link(eth, i); - spin_unlock_irqrestore(ð->phy->lock, flags); - } else if (eth->phy->phy[i]) { - phy_disconnect(eth->phy->phy[i]); - } else if (eth->mii_bus) { - struct phy_device *phy = - mdiobus_get_phy(eth->mii_bus, i); - - if (phy) - phy_detach(phy); - } -} - -static void mtk_phy_start(struct mtk_mac *mac) -{ - struct mtk_eth *eth = mac->hw; - unsigned long flags; - int i; - - for (i = 0; i < 8; i++) { - if (eth->phy->phy_fixed[i]) { - spin_lock_irqsave(ð->phy->lock, flags); - eth->link[i] = 1; - if (eth->soc->mdio_adjust_link) - eth->soc->mdio_adjust_link(eth, i); - spin_unlock_irqrestore(ð->phy->lock, flags); - } else if (eth->phy->phy[i]) { - phy_start(eth->phy->phy[i]); - } - } -} - -static void mtk_phy_stop(struct mtk_mac *mac) -{ - struct mtk_eth *eth = mac->hw; - unsigned long flags; - int i; - - for (i = 0; i < 8; i++) - if (eth->phy->phy_fixed[i]) { - spin_lock_irqsave(ð->phy->lock, flags); - eth->link[i] = 0; - if (eth->soc->mdio_adjust_link) - eth->soc->mdio_adjust_link(eth, i); - spin_unlock_irqrestore(ð->phy->lock, flags); - } else if (eth->phy->phy[i]) { - phy_stop(eth->phy->phy[i]); - } -} - -static struct mtk_phy phy_ralink = { - .connect = mtk_phy_connect, - .disconnect = mtk_phy_disconnect, - .start = mtk_phy_start, - .stop = mtk_phy_stop, -}; - -int mtk_mdio_init(struct mtk_eth *eth) -{ - struct device_node *mii_np; - int err; - - if (!eth->soc->mdio_read || !eth->soc->mdio_write) - return 0; - - spin_lock_init(&phy_ralink.lock); - eth->phy = &phy_ralink; - - mii_np = of_get_child_by_name(eth->dev->of_node, "mdio-bus"); - if (!mii_np) { - dev_err(eth->dev, "no %s child node found", "mdio-bus"); - return -ENODEV; - } - - if (!of_device_is_available(mii_np)) { - err = 0; - goto err_put_node; - } - - eth->mii_bus = mdiobus_alloc(); - if (!eth->mii_bus) { - err = -ENOMEM; - goto err_put_node; - } - - eth->mii_bus->name = "mdio"; - eth->mii_bus->read = eth->soc->mdio_read; - eth->mii_bus->write = eth->soc->mdio_write; - eth->mii_bus->reset = mtk_mdio_reset; - eth->mii_bus->priv = eth; - eth->mii_bus->parent = eth->dev; - - snprintf(eth->mii_bus->id, MII_BUS_ID_SIZE, "%pOFn", mii_np); - err = of_mdiobus_register(eth->mii_bus, mii_np); - if (err) - goto err_free_bus; - - return 0; - -err_free_bus: - kfree(eth->mii_bus); -err_put_node: - of_node_put(mii_np); - eth->mii_bus = NULL; - return err; -} - -void mtk_mdio_cleanup(struct mtk_eth *eth) -{ - if (!eth->mii_bus) - return; - - mdiobus_unregister(eth->mii_bus); - of_node_put(eth->mii_bus->dev.of_node); - kfree(eth->mii_bus); -} diff --git a/drivers/staging/mt7621-eth/mdio.h b/drivers/staging/mt7621-eth/mdio.h deleted file mode 100644 index b14e23842a01..000000000000 --- a/drivers/staging/mt7621-eth/mdio.h +++ /dev/null @@ -1,27 +0,0 @@ -/* This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org> - * Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org> - * Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com> - */ - -#ifndef _RALINK_MDIO_H__ -#define _RALINK_MDIO_H__ - -#ifdef CONFIG_NET_MEDIATEK_MDIO -int mtk_mdio_init(struct mtk_eth *eth); -void mtk_mdio_cleanup(struct mtk_eth *eth); -int mtk_connect_phy_node(struct mtk_eth *eth, struct mtk_mac *mac, - struct device_node *phy_node); -#else -static inline int mtk_mdio_init(struct mtk_eth *eth) { return 0; } -static inline void mtk_mdio_cleanup(struct mtk_eth *eth) {} -#endif -#endif diff --git a/drivers/staging/mt7621-eth/mdio_mt7620.c b/drivers/staging/mt7621-eth/mdio_mt7620.c deleted file mode 100644 index ced605c2914e..000000000000 --- a/drivers/staging/mt7621-eth/mdio_mt7620.c +++ /dev/null @@ -1,173 +0,0 @@ -/* This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org> - * Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org> - * Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com> - */ - -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/types.h> - -#include "mtk_eth_soc.h" -#include "gsw_mt7620.h" -#include "mdio.h" - -static int mt7620_mii_busy_wait(struct mt7620_gsw *gsw) -{ - unsigned long t_start = jiffies; - - while (1) { - if (!(mtk_switch_r32(gsw, - gsw->piac_offset + MT7620_GSW_REG_PIAC) & - GSW_MDIO_ACCESS)) - return 0; - if (time_after(jiffies, t_start + GSW_REG_PHY_TIMEOUT)) - break; - } - - dev_err(gsw->dev, "mdio: MDIO timeout\n"); - return -1; -} - -u32 _mt7620_mii_write(struct mt7620_gsw *gsw, u32 phy_addr, - u32 phy_register, u32 write_data) -{ - if (mt7620_mii_busy_wait(gsw)) - return -1; - - write_data &= 0xffff; - - mtk_switch_w32(gsw, GSW_MDIO_ACCESS | GSW_MDIO_START | GSW_MDIO_WRITE | - (phy_register << GSW_MDIO_REG_SHIFT) | - (phy_addr << GSW_MDIO_ADDR_SHIFT) | write_data, - MT7620_GSW_REG_PIAC); - - if (mt7620_mii_busy_wait(gsw)) - return -1; - - return 0; -} -EXPORT_SYMBOL_GPL(_mt7620_mii_write); - -u32 _mt7620_mii_read(struct mt7620_gsw *gsw, int phy_addr, int phy_reg) -{ - u32 d; - - if (mt7620_mii_busy_wait(gsw)) - return 0xffff; - - mtk_switch_w32(gsw, GSW_MDIO_ACCESS | GSW_MDIO_START | GSW_MDIO_READ | - (phy_reg << GSW_MDIO_REG_SHIFT) | - (phy_addr << GSW_MDIO_ADDR_SHIFT), - MT7620_GSW_REG_PIAC); - - if (mt7620_mii_busy_wait(gsw)) - return 0xffff; - - d = mtk_switch_r32(gsw, MT7620_GSW_REG_PIAC) & 0xffff; - - return d; -} -EXPORT_SYMBOL_GPL(_mt7620_mii_read); - -int mt7620_mdio_write(struct mii_bus *bus, int phy_addr, int phy_reg, u16 val) -{ - struct mtk_eth *eth = bus->priv; - struct mt7620_gsw *gsw = (struct mt7620_gsw *)eth->sw_priv; - - return _mt7620_mii_write(gsw, phy_addr, phy_reg, val); -} - -int mt7620_mdio_read(struct mii_bus *bus, int phy_addr, int phy_reg) -{ - struct mtk_eth *eth = bus->priv; - struct mt7620_gsw *gsw = (struct mt7620_gsw *)eth->sw_priv; - - return _mt7620_mii_read(gsw, phy_addr, phy_reg); -} - -void mt7530_mdio_w32(struct mt7620_gsw *gsw, u32 reg, u32 val) -{ - _mt7620_mii_write(gsw, 0x1f, 0x1f, (reg >> 6) & 0x3ff); - _mt7620_mii_write(gsw, 0x1f, (reg >> 2) & 0xf, val & 0xffff); - _mt7620_mii_write(gsw, 0x1f, 0x10, val >> 16); -} -EXPORT_SYMBOL_GPL(mt7530_mdio_w32); - -u32 mt7530_mdio_r32(struct mt7620_gsw *gsw, u32 reg) -{ - u16 high, low; - - _mt7620_mii_write(gsw, 0x1f, 0x1f, (reg >> 6) & 0x3ff); - low = _mt7620_mii_read(gsw, 0x1f, (reg >> 2) & 0xf); - high = _mt7620_mii_read(gsw, 0x1f, 0x10); - - return (high << 16) | (low & 0xffff); -} -EXPORT_SYMBOL_GPL(mt7530_mdio_r32); - -void mt7530_mdio_m32(struct mt7620_gsw *gsw, u32 mask, u32 set, u32 reg) -{ - u32 val = mt7530_mdio_r32(gsw, reg); - - val &= ~mask; - val |= set; - mt7530_mdio_w32(gsw, reg, val); -} -EXPORT_SYMBOL_GPL(mt7530_mdio_m32); - -static unsigned char *mtk_speed_str(int speed) -{ - switch (speed) { - case 2: - case SPEED_1000: - return "1000"; - case 1: - case SPEED_100: - return "100"; - case 0: - case SPEED_10: - return "10"; - } - - return "? "; -} - -int mt7620_has_carrier(struct mtk_eth *eth) -{ - struct mt7620_gsw *gsw = (struct mt7620_gsw *)eth->sw_priv; - int i; - - for (i = 0; i < GSW_PORT6; i++) - if (mt7530_mdio_r32(gsw, GSW_REG_PORT_STATUS(i)) & 0x1) - return 1; - return 0; -} - -void mt7620_print_link_state(struct mtk_eth *eth, int port, int link, - int speed, int duplex) -{ - struct mt7620_gsw *gsw = eth->sw_priv; - - if (link) - dev_info(gsw->dev, "port %d link up (%sMbps/%s duplex)\n", - port, mtk_speed_str(speed), - (duplex) ? "Full" : "Half"); - else - dev_info(gsw->dev, "port %d link down\n", port); -} - -void mt7620_mdio_link_adjust(struct mtk_eth *eth, int port) -{ - mt7620_print_link_state(eth, port, eth->link[port], - eth->phy->speed[port], - (eth->phy->duplex[port] == DUPLEX_FULL)); -} diff --git a/drivers/staging/mt7621-eth/mtk_eth_soc.c b/drivers/staging/mt7621-eth/mtk_eth_soc.c deleted file mode 100644 index 6027b19f7bc2..000000000000 --- a/drivers/staging/mt7621-eth/mtk_eth_soc.c +++ /dev/null @@ -1,2176 +0,0 @@ -/* This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org> - * Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org> - * Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com> - */ - -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/dma-mapping.h> -#include <linux/init.h> -#include <linux/skbuff.h> -#include <linux/etherdevice.h> -#include <linux/ethtool.h> -#include <linux/platform_device.h> -#include <linux/of_device.h> -#include <linux/mfd/syscon.h> -#include <linux/clk.h> -#include <linux/of_net.h> -#include <linux/of_mdio.h> -#include <linux/if_vlan.h> -#include <linux/reset.h> -#include <linux/tcp.h> -#include <linux/io.h> -#include <linux/bug.h> -#include <linux/regmap.h> - -#include "mtk_eth_soc.h" -#include "mdio.h" -#include "ethtool.h" - -#define MAX_RX_LENGTH 1536 -#define MTK_RX_ETH_HLEN (VLAN_ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN) -#define MTK_RX_HLEN (NET_SKB_PAD + MTK_RX_ETH_HLEN + NET_IP_ALIGN) -#define DMA_DUMMY_DESC 0xffffffff -#define MTK_DEFAULT_MSG_ENABLE \ - (NETIF_MSG_DRV | \ - NETIF_MSG_PROBE | \ - NETIF_MSG_LINK | \ - NETIF_MSG_TIMER | \ - NETIF_MSG_IFDOWN | \ - NETIF_MSG_IFUP | \ - NETIF_MSG_RX_ERR | \ - NETIF_MSG_TX_ERR) - -#define TX_DMA_DESP2_DEF (TX_DMA_LS0 | TX_DMA_DONE) -#define NEXT_TX_DESP_IDX(X) (((X) + 1) & (ring->tx_ring_size - 1)) -#define NEXT_RX_DESP_IDX(X) (((X) + 1) & (ring->rx_ring_size - 1)) - -#define SYSC_REG_RSTCTRL 0x34 - -static int mtk_msg_level = -1; -module_param_named(msg_level, mtk_msg_level, int, 0); -MODULE_PARM_DESC(msg_level, "Message level (-1=defaults,0=none,...,16=all)"); - -static const u16 mtk_reg_table_default[MTK_REG_COUNT] = { - [MTK_REG_PDMA_GLO_CFG] = MTK_PDMA_GLO_CFG, - [MTK_REG_PDMA_RST_CFG] = MTK_PDMA_RST_CFG, - [MTK_REG_DLY_INT_CFG] = MTK_DLY_INT_CFG, - [MTK_REG_TX_BASE_PTR0] = MTK_TX_BASE_PTR0, - [MTK_REG_TX_MAX_CNT0] = MTK_TX_MAX_CNT0, - [MTK_REG_TX_CTX_IDX0] = MTK_TX_CTX_IDX0, - [MTK_REG_TX_DTX_IDX0] = MTK_TX_DTX_IDX0, - [MTK_REG_RX_BASE_PTR0] = MTK_RX_BASE_PTR0, - [MTK_REG_RX_MAX_CNT0] = MTK_RX_MAX_CNT0, - [MTK_REG_RX_CALC_IDX0] = MTK_RX_CALC_IDX0, - [MTK_REG_RX_DRX_IDX0] = MTK_RX_DRX_IDX0, - [MTK_REG_MTK_INT_ENABLE] = MTK_INT_ENABLE, - [MTK_REG_MTK_INT_STATUS] = MTK_INT_STATUS, - [MTK_REG_MTK_DMA_VID_BASE] = MTK_DMA_VID0, - [MTK_REG_MTK_COUNTER_BASE] = MTK_GDMA1_TX_GBCNT, - [MTK_REG_MTK_RST_GL] = MTK_RST_GL, -}; - -static const u16 *mtk_reg_table = mtk_reg_table_default; - -void mtk_w32(struct mtk_eth *eth, u32 val, unsigned int reg) -{ - __raw_writel(val, eth->base + reg); -} - -u32 mtk_r32(struct mtk_eth *eth, unsigned int reg) -{ - return __raw_readl(eth->base + reg); -} - -static void mtk_reg_w32(struct mtk_eth *eth, u32 val, enum mtk_reg reg) -{ - mtk_w32(eth, val, mtk_reg_table[reg]); -} - -static u32 mtk_reg_r32(struct mtk_eth *eth, enum mtk_reg reg) -{ - return mtk_r32(eth, mtk_reg_table[reg]); -} - -/* these bits are also exposed via the reset-controller API. however the switch - * and FE need to be brought out of reset in the exakt same moemtn and the - * reset-controller api does not provide this feature yet. Do the reset manually - * until we fixed the reset-controller api to be able to do this - */ -void mtk_reset(struct mtk_eth *eth, u32 reset_bits) -{ - u32 val; - - regmap_read(eth->ethsys, SYSC_REG_RSTCTRL, &val); - val |= reset_bits; - regmap_write(eth->ethsys, SYSC_REG_RSTCTRL, val); - usleep_range(10, 20); - val &= ~reset_bits; - regmap_write(eth->ethsys, SYSC_REG_RSTCTRL, val); - usleep_range(10, 20); -} -EXPORT_SYMBOL(mtk_reset); - -static inline void mtk_irq_ack(struct mtk_eth *eth, u32 mask) -{ - if (eth->soc->dma_type & MTK_PDMA) - mtk_reg_w32(eth, mask, MTK_REG_MTK_INT_STATUS); - if (eth->soc->dma_type & MTK_QDMA) - mtk_w32(eth, mask, MTK_QMTK_INT_STATUS); -} - -static inline u32 mtk_irq_pending(struct mtk_eth *eth) -{ - u32 status = 0; - - if (eth->soc->dma_type & MTK_PDMA) - status |= mtk_reg_r32(eth, MTK_REG_MTK_INT_STATUS); - if (eth->soc->dma_type & MTK_QDMA) - status |= mtk_r32(eth, MTK_QMTK_INT_STATUS); - - return status; -} - -static void mtk_irq_ack_status(struct mtk_eth *eth, u32 mask) -{ - u32 status_reg = MTK_REG_MTK_INT_STATUS; - - if (mtk_reg_table[MTK_REG_MTK_INT_STATUS2]) - status_reg = MTK_REG_MTK_INT_STATUS2; - - mtk_reg_w32(eth, mask, status_reg); -} - -static u32 mtk_irq_pending_status(struct mtk_eth *eth) -{ - u32 status_reg = MTK_REG_MTK_INT_STATUS; - - if (mtk_reg_table[MTK_REG_MTK_INT_STATUS2]) - status_reg = MTK_REG_MTK_INT_STATUS2; - - return mtk_reg_r32(eth, status_reg); -} - -static inline void mtk_irq_disable(struct mtk_eth *eth, u32 mask) -{ - u32 val; - - if (eth->soc->dma_type & MTK_PDMA) { - val = mtk_reg_r32(eth, MTK_REG_MTK_INT_ENABLE); - mtk_reg_w32(eth, val & ~mask, MTK_REG_MTK_INT_ENABLE); - /* flush write */ - mtk_reg_r32(eth, MTK_REG_MTK_INT_ENABLE); - } - if (eth->soc->dma_type & MTK_QDMA) { - val = mtk_r32(eth, MTK_QMTK_INT_ENABLE); - mtk_w32(eth, val & ~mask, MTK_QMTK_INT_ENABLE); - /* flush write */ - mtk_r32(eth, MTK_QMTK_INT_ENABLE); - } -} - -static inline void mtk_irq_enable(struct mtk_eth *eth, u32 mask) -{ - u32 val; - - if (eth->soc->dma_type & MTK_PDMA) { - val = mtk_reg_r32(eth, MTK_REG_MTK_INT_ENABLE); - mtk_reg_w32(eth, val | mask, MTK_REG_MTK_INT_ENABLE); - /* flush write */ - mtk_reg_r32(eth, MTK_REG_MTK_INT_ENABLE); - } - if (eth->soc->dma_type & MTK_QDMA) { - val = mtk_r32(eth, MTK_QMTK_INT_ENABLE); - mtk_w32(eth, val | mask, MTK_QMTK_INT_ENABLE); - /* flush write */ - mtk_r32(eth, MTK_QMTK_INT_ENABLE); - } -} - -static inline u32 mtk_irq_enabled(struct mtk_eth *eth) -{ - u32 enabled = 0; - - if (eth->soc->dma_type & MTK_PDMA) - enabled |= mtk_reg_r32(eth, MTK_REG_MTK_INT_ENABLE); - if (eth->soc->dma_type & MTK_QDMA) - enabled |= mtk_r32(eth, MTK_QMTK_INT_ENABLE); - - return enabled; -} - -static inline void mtk_hw_set_macaddr(struct mtk_mac *mac, - unsigned char *macaddr) -{ - unsigned long flags; - - spin_lock_irqsave(&mac->hw->page_lock, flags); - mtk_w32(mac->hw, (macaddr[0] << 8) | macaddr[1], MTK_GDMA1_MAC_ADRH); - mtk_w32(mac->hw, (macaddr[2] << 24) | (macaddr[3] << 16) | - (macaddr[4] << 8) | macaddr[5], - MTK_GDMA1_MAC_ADRL); - spin_unlock_irqrestore(&mac->hw->page_lock, flags); -} - -static int mtk_set_mac_address(struct net_device *dev, void *p) -{ - int ret = eth_mac_addr(dev, p); - struct mtk_mac *mac = netdev_priv(dev); - struct mtk_eth *eth = mac->hw; - - if (ret) - return ret; - - if (eth->soc->set_mac) - eth->soc->set_mac(mac, dev->dev_addr); - else - mtk_hw_set_macaddr(mac, p); - - return 0; -} - -static inline int mtk_max_frag_size(int mtu) -{ - /* make sure buf_size will be at least MAX_RX_LENGTH */ - if (mtu + MTK_RX_ETH_HLEN < MAX_RX_LENGTH) - mtu = MAX_RX_LENGTH - MTK_RX_ETH_HLEN; - - return SKB_DATA_ALIGN(MTK_RX_HLEN + mtu) + - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); -} - -static inline int mtk_max_buf_size(int frag_size) -{ - int buf_size = frag_size - NET_SKB_PAD - NET_IP_ALIGN - - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - - WARN_ON(buf_size < MAX_RX_LENGTH); - - return buf_size; -} - -static inline void mtk_get_rxd(struct mtk_rx_dma *rxd, - struct mtk_rx_dma *dma_rxd) -{ - rxd->rxd1 = READ_ONCE(dma_rxd->rxd1); - rxd->rxd2 = READ_ONCE(dma_rxd->rxd2); - rxd->rxd3 = READ_ONCE(dma_rxd->rxd3); - rxd->rxd4 = READ_ONCE(dma_rxd->rxd4); -} - -static inline void mtk_set_txd_pdma(struct mtk_tx_dma *txd, - struct mtk_tx_dma *dma_txd) -{ - WRITE_ONCE(dma_txd->txd1, txd->txd1); - WRITE_ONCE(dma_txd->txd3, txd->txd3); - WRITE_ONCE(dma_txd->txd4, txd->txd4); - /* clean dma done flag last */ - WRITE_ONCE(dma_txd->txd2, txd->txd2); -} - -static void mtk_clean_rx(struct mtk_eth *eth, struct mtk_rx_ring *ring) -{ - int i; - - if (ring->rx_data && ring->rx_dma) { - for (i = 0; i < ring->rx_ring_size; i++) { - if (!ring->rx_data[i]) - continue; - if (!ring->rx_dma[i].rxd1) - continue; - dma_unmap_single(eth->dev, - ring->rx_dma[i].rxd1, - ring->rx_buf_size, - DMA_FROM_DEVICE); - skb_free_frag(ring->rx_data[i]); - } - kfree(ring->rx_data); - ring->rx_data = NULL; - } - - if (ring->rx_dma) { - dma_free_coherent(eth->dev, - ring->rx_ring_size * sizeof(*ring->rx_dma), - ring->rx_dma, - ring->rx_phys); - ring->rx_dma = NULL; - } -} - -static int mtk_dma_rx_alloc(struct mtk_eth *eth, struct mtk_rx_ring *ring) -{ - int i, pad = 0; - - ring->frag_size = mtk_max_frag_size(ETH_DATA_LEN); - ring->rx_buf_size = mtk_max_buf_size(ring->frag_size); - ring->rx_ring_size = eth->soc->dma_ring_size; - ring->rx_data = kcalloc(ring->rx_ring_size, sizeof(*ring->rx_data), - GFP_KERNEL); - if (!ring->rx_data) - goto no_rx_mem; - - for (i = 0; i < ring->rx_ring_size; i++) { - ring->rx_data[i] = netdev_alloc_frag(ring->frag_size); - if (!ring->rx_data[i]) - goto no_rx_mem; - } - - ring->rx_dma = - dma_alloc_coherent(eth->dev, - ring->rx_ring_size * sizeof(*ring->rx_dma), - &ring->rx_phys, GFP_ATOMIC | __GFP_ZERO); - if (!ring->rx_dma) - goto no_rx_mem; - - if (!eth->soc->rx_2b_offset) - pad = NET_IP_ALIGN; - - for (i = 0; i < ring->rx_ring_size; i++) { - dma_addr_t dma_addr = dma_map_single(eth->dev, - ring->rx_data[i] + NET_SKB_PAD + pad, - ring->rx_buf_size, - DMA_FROM_DEVICE); - if (unlikely(dma_mapping_error(eth->dev, dma_addr))) - goto no_rx_mem; - ring->rx_dma[i].rxd1 = (unsigned int)dma_addr; - - if (eth->soc->rx_sg_dma) - ring->rx_dma[i].rxd2 = RX_DMA_PLEN0(ring->rx_buf_size); - else - ring->rx_dma[i].rxd2 = RX_DMA_LSO; - } - ring->rx_calc_idx = ring->rx_ring_size - 1; - /* make sure that all changes to the dma ring are flushed before we - * continue - */ - wmb(); - - return 0; - -no_rx_mem: - return -ENOMEM; -} - -static void mtk_txd_unmap(struct device *dev, struct mtk_tx_buf *tx_buf) -{ - if (tx_buf->flags & MTK_TX_FLAGS_SINGLE0) { - dma_unmap_single(dev, - dma_unmap_addr(tx_buf, dma_addr0), - dma_unmap_len(tx_buf, dma_len0), - DMA_TO_DEVICE); - } else if (tx_buf->flags & MTK_TX_FLAGS_PAGE0) { - dma_unmap_page(dev, - dma_unmap_addr(tx_buf, dma_addr0), - dma_unmap_len(tx_buf, dma_len0), - DMA_TO_DEVICE); - } - if (tx_buf->flags & MTK_TX_FLAGS_PAGE1) - dma_unmap_page(dev, - dma_unmap_addr(tx_buf, dma_addr1), - dma_unmap_len(tx_buf, dma_len1), - DMA_TO_DEVICE); - - tx_buf->flags = 0; - if (tx_buf->skb && (tx_buf->skb != (struct sk_buff *)DMA_DUMMY_DESC)) - dev_kfree_skb_any(tx_buf->skb); - tx_buf->skb = NULL; -} - -static void mtk_pdma_tx_clean(struct mtk_eth *eth) -{ - struct mtk_tx_ring *ring = ð->tx_ring; - int i; - - if (ring->tx_buf) { - for (i = 0; i < ring->tx_ring_size; i++) - mtk_txd_unmap(eth->dev, &ring->tx_buf[i]); - kfree(ring->tx_buf); - ring->tx_buf = NULL; - } - - if (ring->tx_dma) { - dma_free_coherent(eth->dev, - ring->tx_ring_size * sizeof(*ring->tx_dma), - ring->tx_dma, - ring->tx_phys); - ring->tx_dma = NULL; - } -} - -static void mtk_qdma_tx_clean(struct mtk_eth *eth) -{ - struct mtk_tx_ring *ring = ð->tx_ring; - int i; - - if (ring->tx_buf) { - for (i = 0; i < ring->tx_ring_size; i++) - mtk_txd_unmap(eth->dev, &ring->tx_buf[i]); - kfree(ring->tx_buf); - ring->tx_buf = NULL; - } - - if (ring->tx_dma) { - dma_free_coherent(eth->dev, - ring->tx_ring_size * sizeof(*ring->tx_dma), - ring->tx_dma, - ring->tx_phys); - ring->tx_dma = NULL; - } -} - -void mtk_stats_update_mac(struct mtk_mac *mac) -{ - struct mtk_hw_stats *hw_stats = mac->hw_stats; - unsigned int base = mtk_reg_table[MTK_REG_MTK_COUNTER_BASE]; - u64 stats; - - base += hw_stats->reg_offset; - - u64_stats_update_begin(&hw_stats->syncp); - - if (mac->hw->soc->new_stats) { - hw_stats->rx_bytes += mtk_r32(mac->hw, base); - stats = mtk_r32(mac->hw, base + 0x04); - if (stats) - hw_stats->rx_bytes += (stats << 32); - hw_stats->rx_packets += mtk_r32(mac->hw, base + 0x08); - hw_stats->rx_overflow += mtk_r32(mac->hw, base + 0x10); - hw_stats->rx_fcs_errors += mtk_r32(mac->hw, base + 0x14); - hw_stats->rx_short_errors += mtk_r32(mac->hw, base + 0x18); - hw_stats->rx_long_errors += mtk_r32(mac->hw, base + 0x1c); - hw_stats->rx_checksum_errors += mtk_r32(mac->hw, base + 0x20); - hw_stats->rx_flow_control_packets += - mtk_r32(mac->hw, base + 0x24); - hw_stats->tx_skip += mtk_r32(mac->hw, base + 0x28); - hw_stats->tx_collisions += mtk_r32(mac->hw, base + 0x2c); - hw_stats->tx_bytes += mtk_r32(mac->hw, base + 0x30); - stats = mtk_r32(mac->hw, base + 0x34); - if (stats) - hw_stats->tx_bytes += (stats << 32); - hw_stats->tx_packets += mtk_r32(mac->hw, base + 0x38); - } else { - hw_stats->tx_bytes += mtk_r32(mac->hw, base); - hw_stats->tx_packets += mtk_r32(mac->hw, base + 0x04); - hw_stats->tx_skip += mtk_r32(mac->hw, base + 0x08); - hw_stats->tx_collisions += mtk_r32(mac->hw, base + 0x0c); - hw_stats->rx_bytes += mtk_r32(mac->hw, base + 0x20); - hw_stats->rx_packets += mtk_r32(mac->hw, base + 0x24); - hw_stats->rx_overflow += mtk_r32(mac->hw, base + 0x28); - hw_stats->rx_fcs_errors += mtk_r32(mac->hw, base + 0x2c); - hw_stats->rx_short_errors += mtk_r32(mac->hw, base + 0x30); - hw_stats->rx_long_errors += mtk_r32(mac->hw, base + 0x34); - hw_stats->rx_checksum_errors += mtk_r32(mac->hw, base + 0x38); - hw_stats->rx_flow_control_packets += - mtk_r32(mac->hw, base + 0x3c); - } - - u64_stats_update_end(&hw_stats->syncp); -} - -static void mtk_get_stats64(struct net_device *dev, - struct rtnl_link_stats64 *storage) -{ - struct mtk_mac *mac = netdev_priv(dev); - struct mtk_hw_stats *hw_stats = mac->hw_stats; - unsigned int base = mtk_reg_table[MTK_REG_MTK_COUNTER_BASE]; - unsigned int start; - - if (!base) { - netdev_stats_to_stats64(storage, &dev->stats); - return; - } - - if (netif_running(dev) && netif_device_present(dev)) { - if (spin_trylock(&hw_stats->stats_lock)) { - mtk_stats_update_mac(mac); - spin_unlock(&hw_stats->stats_lock); - } - } - - do { - start = u64_stats_fetch_begin_irq(&hw_stats->syncp); - storage->rx_packets = hw_stats->rx_packets; - storage->tx_packets = hw_stats->tx_packets; - storage->rx_bytes = hw_stats->rx_bytes; - storage->tx_bytes = hw_stats->tx_bytes; - storage->collisions = hw_stats->tx_collisions; - storage->rx_length_errors = hw_stats->rx_short_errors + - hw_stats->rx_long_errors; - storage->rx_over_errors = hw_stats->rx_overflow; - storage->rx_crc_errors = hw_stats->rx_fcs_errors; - storage->rx_errors = hw_stats->rx_checksum_errors; - storage->tx_aborted_errors = hw_stats->tx_skip; - } while (u64_stats_fetch_retry_irq(&hw_stats->syncp, start)); - - storage->tx_errors = dev->stats.tx_errors; - storage->rx_dropped = dev->stats.rx_dropped; - storage->tx_dropped = dev->stats.tx_dropped; -} - -static int mtk_vlan_rx_add_vid(struct net_device *dev, - __be16 proto, u16 vid) -{ - struct mtk_mac *mac = netdev_priv(dev); - struct mtk_eth *eth = mac->hw; - u32 idx = (vid & 0xf); - u32 vlan_cfg; - - if (!((mtk_reg_table[MTK_REG_MTK_DMA_VID_BASE]) && - (dev->features & NETIF_F_HW_VLAN_CTAG_TX))) - return 0; - - if (test_bit(idx, ð->vlan_map)) { - netdev_warn(dev, "disable tx vlan offload\n"); - dev->wanted_features &= ~NETIF_F_HW_VLAN_CTAG_TX; - netdev_update_features(dev); - } else { - vlan_cfg = mtk_r32(eth, - mtk_reg_table[MTK_REG_MTK_DMA_VID_BASE] + - ((idx >> 1) << 2)); - if (idx & 0x1) { - vlan_cfg &= 0xffff; - vlan_cfg |= (vid << 16); - } else { - vlan_cfg &= 0xffff0000; - vlan_cfg |= vid; - } - mtk_w32(eth, - vlan_cfg, mtk_reg_table[MTK_REG_MTK_DMA_VID_BASE] + - ((idx >> 1) << 2)); - set_bit(idx, ð->vlan_map); - } - - return 0; -} - -static int mtk_vlan_rx_kill_vid(struct net_device *dev, - __be16 proto, u16 vid) -{ - struct mtk_mac *mac = netdev_priv(dev); - struct mtk_eth *eth = mac->hw; - u32 idx = (vid & 0xf); - - if (!((mtk_reg_table[MTK_REG_MTK_DMA_VID_BASE]) && - (dev->features & NETIF_F_HW_VLAN_CTAG_TX))) - return 0; - - clear_bit(idx, ð->vlan_map); - - return 0; -} - -static inline u32 mtk_pdma_empty_txd(struct mtk_tx_ring *ring) -{ - barrier(); - return (u32)(ring->tx_ring_size - - ((ring->tx_next_idx - ring->tx_free_idx) & - (ring->tx_ring_size - 1))); -} - -static int mtk_skb_padto(struct sk_buff *skb, struct mtk_eth *eth) -{ - unsigned int len; - int ret; - - if (unlikely(skb->len >= VLAN_ETH_ZLEN)) - return 0; - - if (eth->soc->padding_64b && !eth->soc->padding_bug) - return 0; - - if (skb_vlan_tag_present(skb)) - len = ETH_ZLEN; - else if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) - len = VLAN_ETH_ZLEN; - else if (!eth->soc->padding_64b) - len = ETH_ZLEN; - else - return 0; - - if (skb->len >= len) - return 0; - - ret = skb_pad(skb, len - skb->len); - if (ret < 0) - return ret; - skb->len = len; - skb_set_tail_pointer(skb, len); - - return ret; -} - -static int mtk_pdma_tx_map(struct sk_buff *skb, struct net_device *dev, - int tx_num, struct mtk_tx_ring *ring, bool gso) -{ - struct mtk_mac *mac = netdev_priv(dev); - struct mtk_eth *eth = mac->hw; - struct skb_frag_struct *frag; - struct mtk_tx_dma txd, *ptxd; - struct mtk_tx_buf *tx_buf; - int i, j, k, frag_size, frag_map_size, offset; - dma_addr_t mapped_addr; - unsigned int nr_frags; - u32 def_txd4; - - if (mtk_skb_padto(skb, eth)) { - netif_warn(eth, tx_err, dev, "tx padding failed!\n"); - return -1; - } - - tx_buf = &ring->tx_buf[ring->tx_next_idx]; - memset(tx_buf, 0, sizeof(*tx_buf)); - memset(&txd, 0, sizeof(txd)); - nr_frags = skb_shinfo(skb)->nr_frags; - - /* init tx descriptor */ - def_txd4 = eth->soc->txd4; - txd.txd4 = def_txd4; - - if (eth->soc->mac_count > 1) - txd.txd4 |= (mac->id + 1) << TX_DMA_FPORT_SHIFT; - - if (gso) - txd.txd4 |= TX_DMA_TSO; - - /* TX Checksum offload */ - if (skb->ip_summed == CHECKSUM_PARTIAL) - txd.txd4 |= TX_DMA_CHKSUM; - - /* VLAN header offload */ - if (skb_vlan_tag_present(skb)) { - u16 tag = skb_vlan_tag_get(skb); - - txd.txd4 |= TX_DMA_INS_VLAN | - ((tag >> VLAN_PRIO_SHIFT) << 4) | - (tag & 0xF); - } - - mapped_addr = dma_map_single(&dev->dev, skb->data, - skb_headlen(skb), DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(&dev->dev, mapped_addr))) - return -1; - - txd.txd1 = mapped_addr; - txd.txd2 = TX_DMA_PLEN0(skb_headlen(skb)); - - tx_buf->flags |= MTK_TX_FLAGS_SINGLE0; - dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr); - dma_unmap_len_set(tx_buf, dma_len0, skb_headlen(skb)); - - /* TX SG offload */ - j = ring->tx_next_idx; - k = 0; - for (i = 0; i < nr_frags; i++) { - offset = 0; - frag = &skb_shinfo(skb)->frags[i]; - frag_size = skb_frag_size(frag); - - while (frag_size > 0) { - frag_map_size = min(frag_size, TX_DMA_BUF_LEN); - mapped_addr = skb_frag_dma_map(&dev->dev, frag, offset, - frag_map_size, - DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(&dev->dev, mapped_addr))) - goto err_dma; - - if (k & 0x1) { - j = NEXT_TX_DESP_IDX(j); - txd.txd1 = mapped_addr; - txd.txd2 = TX_DMA_PLEN0(frag_map_size); - txd.txd4 = def_txd4; - - tx_buf = &ring->tx_buf[j]; - memset(tx_buf, 0, sizeof(*tx_buf)); - - tx_buf->flags |= MTK_TX_FLAGS_PAGE0; - dma_unmap_addr_set(tx_buf, dma_addr0, - mapped_addr); - dma_unmap_len_set(tx_buf, dma_len0, - frag_map_size); - } else { - txd.txd3 = mapped_addr; - txd.txd2 |= TX_DMA_PLEN1(frag_map_size); - - tx_buf->skb = (struct sk_buff *)DMA_DUMMY_DESC; - tx_buf->flags |= MTK_TX_FLAGS_PAGE1; - dma_unmap_addr_set(tx_buf, dma_addr1, - mapped_addr); - dma_unmap_len_set(tx_buf, dma_len1, - frag_map_size); - - if (!((i == (nr_frags - 1)) && - (frag_map_size == frag_size))) { - mtk_set_txd_pdma(&txd, - &ring->tx_dma[j]); - memset(&txd, 0, sizeof(txd)); - } - } - frag_size -= frag_map_size; - offset += frag_map_size; - k++; - } - } - - /* set last segment */ - if (k & 0x1) - txd.txd2 |= TX_DMA_LS1; - else - txd.txd2 |= TX_DMA_LS0; - mtk_set_txd_pdma(&txd, &ring->tx_dma[j]); - - /* store skb to cleanup */ - tx_buf->skb = skb; - - netdev_sent_queue(dev, skb->len); - skb_tx_timestamp(skb); - - ring->tx_next_idx = NEXT_TX_DESP_IDX(j); - /* make sure that all changes to the dma ring are flushed before we - * continue - */ - wmb(); - atomic_set(&ring->tx_free_count, mtk_pdma_empty_txd(ring)); - - if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) || !skb->xmit_more) - mtk_reg_w32(eth, ring->tx_next_idx, MTK_REG_TX_CTX_IDX0); - - return 0; - -err_dma: - j = ring->tx_next_idx; - for (i = 0; i < tx_num; i++) { - ptxd = &ring->tx_dma[j]; - tx_buf = &ring->tx_buf[j]; - - /* unmap dma */ - mtk_txd_unmap(&dev->dev, tx_buf); - - ptxd->txd2 = TX_DMA_DESP2_DEF; - j = NEXT_TX_DESP_IDX(j); - } - /* make sure that all changes to the dma ring are flushed before we - * continue - */ - wmb(); - return -1; -} - -/* the qdma core needs scratch memory to be setup */ -static int mtk_init_fq_dma(struct mtk_eth *eth) -{ - dma_addr_t dma_addr, phy_ring_head, phy_ring_tail; - int cnt = eth->soc->dma_ring_size; - int i; - - eth->scratch_ring = dma_alloc_coherent(eth->dev, - cnt * sizeof(struct mtk_tx_dma), - &phy_ring_head, - GFP_ATOMIC | __GFP_ZERO); - if (unlikely(!eth->scratch_ring)) - return -ENOMEM; - - eth->scratch_head = kcalloc(cnt, QDMA_PAGE_SIZE, - GFP_KERNEL); - dma_addr = dma_map_single(eth->dev, - eth->scratch_head, cnt * QDMA_PAGE_SIZE, - DMA_FROM_DEVICE); - if (unlikely(dma_mapping_error(eth->dev, dma_addr))) - return -ENOMEM; - - memset(eth->scratch_ring, 0x0, sizeof(struct mtk_tx_dma) * cnt); - phy_ring_tail = phy_ring_head + (sizeof(struct mtk_tx_dma) * (cnt - 1)); - - for (i = 0; i < cnt; i++) { - eth->scratch_ring[i].txd1 = (dma_addr + (i * QDMA_PAGE_SIZE)); - if (i < cnt - 1) - eth->scratch_ring[i].txd2 = (phy_ring_head + - ((i + 1) * sizeof(struct mtk_tx_dma))); - eth->scratch_ring[i].txd3 = TX_QDMA_SDL(QDMA_PAGE_SIZE); - } - - mtk_w32(eth, phy_ring_head, MTK_QDMA_FQ_HEAD); - mtk_w32(eth, phy_ring_tail, MTK_QDMA_FQ_TAIL); - mtk_w32(eth, (cnt << 16) | cnt, MTK_QDMA_FQ_CNT); - mtk_w32(eth, QDMA_PAGE_SIZE << 16, MTK_QDMA_FQ_BLEN); - - return 0; -} - -static void *mtk_qdma_phys_to_virt(struct mtk_tx_ring *ring, u32 desc) -{ - void *ret = ring->tx_dma; - - return ret + (desc - ring->tx_phys); -} - -static struct mtk_tx_dma *mtk_tx_next_qdma(struct mtk_tx_ring *ring, - struct mtk_tx_dma *txd) -{ - return mtk_qdma_phys_to_virt(ring, txd->txd2); -} - -static struct mtk_tx_buf *mtk_desc_to_tx_buf(struct mtk_tx_ring *ring, - struct mtk_tx_dma *txd) -{ - int idx = txd - ring->tx_dma; - - return &ring->tx_buf[idx]; -} - -static int mtk_qdma_tx_map(struct sk_buff *skb, struct net_device *dev, - int tx_num, struct mtk_tx_ring *ring, bool gso) -{ - struct mtk_mac *mac = netdev_priv(dev); - struct mtk_eth *eth = mac->hw; - struct mtk_tx_dma *itxd, *txd; - struct mtk_tx_buf *tx_buf; - dma_addr_t mapped_addr; - unsigned int nr_frags; - int i, n_desc = 1; - u32 txd4 = eth->soc->txd4; - - itxd = ring->tx_next_free; - if (itxd == ring->tx_last_free) - return -ENOMEM; - - if (eth->soc->mac_count > 1) - txd4 |= (mac->id + 1) << TX_DMA_FPORT_SHIFT; - - tx_buf = mtk_desc_to_tx_buf(ring, itxd); - memset(tx_buf, 0, sizeof(*tx_buf)); - - if (gso) - txd4 |= TX_DMA_TSO; - - /* TX Checksum offload */ - if (skb->ip_summed == CHECKSUM_PARTIAL) - txd4 |= TX_DMA_CHKSUM; - - /* VLAN header offload */ - if (skb_vlan_tag_present(skb)) - txd4 |= TX_DMA_INS_VLAN_MT7621 | skb_vlan_tag_get(skb); - - mapped_addr = dma_map_single(&dev->dev, skb->data, - skb_headlen(skb), DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(&dev->dev, mapped_addr))) - return -ENOMEM; - - WRITE_ONCE(itxd->txd1, mapped_addr); - tx_buf->flags |= MTK_TX_FLAGS_SINGLE0; - dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr); - dma_unmap_len_set(tx_buf, dma_len0, skb_headlen(skb)); - - /* TX SG offload */ - txd = itxd; - nr_frags = skb_shinfo(skb)->nr_frags; - for (i = 0; i < nr_frags; i++) { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i]; - unsigned int offset = 0; - int frag_size = skb_frag_size(frag); - - while (frag_size) { - bool last_frag = false; - unsigned int frag_map_size; - - txd = mtk_tx_next_qdma(ring, txd); - if (txd == ring->tx_last_free) - goto err_dma; - - n_desc++; - frag_map_size = min(frag_size, TX_DMA_BUF_LEN); - mapped_addr = skb_frag_dma_map(&dev->dev, frag, offset, - frag_map_size, - DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(&dev->dev, mapped_addr))) - goto err_dma; - - if (i == nr_frags - 1 && - (frag_size - frag_map_size) == 0) - last_frag = true; - - WRITE_ONCE(txd->txd1, mapped_addr); - WRITE_ONCE(txd->txd3, (QDMA_TX_SWC | - TX_DMA_PLEN0(frag_map_size) | - last_frag * TX_DMA_LS0) | - mac->id); - WRITE_ONCE(txd->txd4, 0); - - tx_buf->skb = (struct sk_buff *)DMA_DUMMY_DESC; - tx_buf = mtk_desc_to_tx_buf(ring, txd); - memset(tx_buf, 0, sizeof(*tx_buf)); - - tx_buf->flags |= MTK_TX_FLAGS_PAGE0; - dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr); - dma_unmap_len_set(tx_buf, dma_len0, frag_map_size); - frag_size -= frag_map_size; - offset += frag_map_size; - } - } - - /* store skb to cleanup */ - tx_buf->skb = skb; - - WRITE_ONCE(itxd->txd4, txd4); - WRITE_ONCE(itxd->txd3, (QDMA_TX_SWC | TX_DMA_PLEN0(skb_headlen(skb)) | - (!nr_frags * TX_DMA_LS0))); - - netdev_sent_queue(dev, skb->len); - skb_tx_timestamp(skb); - - ring->tx_next_free = mtk_tx_next_qdma(ring, txd); - atomic_sub(n_desc, &ring->tx_free_count); - - /* make sure that all changes to the dma ring are flushed before we - * continue - */ - wmb(); - - if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) || !skb->xmit_more) - mtk_w32(eth, txd->txd2, MTK_QTX_CTX_PTR); - - return 0; - -err_dma: - do { - tx_buf = mtk_desc_to_tx_buf(ring, txd); - - /* unmap dma */ - mtk_txd_unmap(&dev->dev, tx_buf); - - itxd->txd3 = TX_DMA_DESP2_DEF; - itxd = mtk_tx_next_qdma(ring, itxd); - } while (itxd != txd); - - return -ENOMEM; -} - -static inline int mtk_cal_txd_req(struct sk_buff *skb) -{ - int i, nfrags; - struct skb_frag_struct *frag; - - nfrags = 1; - if (skb_is_gso(skb)) { - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - frag = &skb_shinfo(skb)->frags[i]; - nfrags += DIV_ROUND_UP(frag->size, TX_DMA_BUF_LEN); - } - } else { - nfrags += skb_shinfo(skb)->nr_frags; - } - - return DIV_ROUND_UP(nfrags, 2); -} - -static int mtk_start_xmit(struct sk_buff *skb, struct net_device *dev) -{ - struct mtk_mac *mac = netdev_priv(dev); - struct mtk_eth *eth = mac->hw; - struct mtk_tx_ring *ring = ð->tx_ring; - struct net_device_stats *stats = &dev->stats; - int tx_num; - int len = skb->len; - bool gso = false; - - tx_num = mtk_cal_txd_req(skb); - if (unlikely(atomic_read(&ring->tx_free_count) <= tx_num)) { - netif_stop_queue(dev); - netif_err(eth, tx_queued, dev, - "Tx Ring full when queue awake!\n"); - return NETDEV_TX_BUSY; - } - - /* TSO: fill MSS info in tcp checksum field */ - if (skb_is_gso(skb)) { - if (skb_cow_head(skb, 0)) { - netif_warn(eth, tx_err, dev, - "GSO expand head fail.\n"); - goto drop; - } - - if (skb_shinfo(skb)->gso_type & - (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) { - gso = true; - tcp_hdr(skb)->check = htons(skb_shinfo(skb)->gso_size); - } - } - - if (ring->tx_map(skb, dev, tx_num, ring, gso) < 0) - goto drop; - - stats->tx_packets++; - stats->tx_bytes += len; - - if (unlikely(atomic_read(&ring->tx_free_count) <= ring->tx_thresh)) { - netif_stop_queue(dev); - smp_mb(); - if (unlikely(atomic_read(&ring->tx_free_count) > - ring->tx_thresh)) - netif_wake_queue(dev); - } - - return NETDEV_TX_OK; - -drop: - stats->tx_dropped++; - dev_kfree_skb(skb); - return NETDEV_TX_OK; -} - -static int mtk_poll_rx(struct napi_struct *napi, int budget, - struct mtk_eth *eth, u32 rx_intr) -{ - struct mtk_soc_data *soc = eth->soc; - struct mtk_rx_ring *ring = ð->rx_ring[0]; - int idx = ring->rx_calc_idx; - u32 checksum_bit; - struct sk_buff *skb; - u8 *data, *new_data; - struct mtk_rx_dma *rxd, trxd; - int done = 0, pad; - - if (eth->soc->hw_features & NETIF_F_RXCSUM) - checksum_bit = soc->checksum_bit; - else - checksum_bit = 0; - - if (eth->soc->rx_2b_offset) - pad = 0; - else - pad = NET_IP_ALIGN; - - while (done < budget) { - struct net_device *netdev; - unsigned int pktlen; - dma_addr_t dma_addr; - int mac = 0; - - idx = NEXT_RX_DESP_IDX(idx); - rxd = &ring->rx_dma[idx]; - data = ring->rx_data[idx]; - - mtk_get_rxd(&trxd, rxd); - if (!(trxd.rxd2 & RX_DMA_DONE)) - break; - - /* find out which mac the packet come from. values start at 1 */ - if (eth->soc->mac_count > 1) { - mac = (trxd.rxd4 >> RX_DMA_FPORT_SHIFT) & - RX_DMA_FPORT_MASK; - mac--; - if (mac < 0 || mac >= eth->soc->mac_count) - goto release_desc; - } - - netdev = eth->netdev[mac]; - - /* alloc new buffer */ - new_data = napi_alloc_frag(ring->frag_size); - if (unlikely(!new_data || !netdev)) { - netdev->stats.rx_dropped++; - goto release_desc; - } - dma_addr = dma_map_single(&netdev->dev, - new_data + NET_SKB_PAD + pad, - ring->rx_buf_size, - DMA_FROM_DEVICE); - if (unlikely(dma_mapping_error(&netdev->dev, dma_addr))) { - skb_free_frag(new_data); - goto release_desc; - } - - /* receive data */ - skb = build_skb(data, ring->frag_size); - if (unlikely(!skb)) { - put_page(virt_to_head_page(new_data)); - goto release_desc; - } - skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); - - dma_unmap_single(&netdev->dev, trxd.rxd1, - ring->rx_buf_size, DMA_FROM_DEVICE); - pktlen = RX_DMA_GET_PLEN0(trxd.rxd2); - skb->dev = netdev; - skb_put(skb, pktlen); - if (trxd.rxd4 & checksum_bit) - skb->ip_summed = CHECKSUM_UNNECESSARY; - else - skb_checksum_none_assert(skb); - skb->protocol = eth_type_trans(skb, netdev); - - netdev->stats.rx_packets++; - netdev->stats.rx_bytes += pktlen; - - if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX && - RX_DMA_VID(trxd.rxd3)) - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), - RX_DMA_VID(trxd.rxd3)); - napi_gro_receive(napi, skb); - - ring->rx_data[idx] = new_data; - rxd->rxd1 = (unsigned int)dma_addr; - -release_desc: - if (eth->soc->rx_sg_dma) - rxd->rxd2 = RX_DMA_PLEN0(ring->rx_buf_size); - else - rxd->rxd2 = RX_DMA_LSO; - - ring->rx_calc_idx = idx; - /* make sure that all changes to the dma ring are flushed before - * we continue - */ - wmb(); - if (eth->soc->dma_type == MTK_QDMA) - mtk_w32(eth, ring->rx_calc_idx, MTK_QRX_CRX_IDX0); - else - mtk_reg_w32(eth, ring->rx_calc_idx, - MTK_REG_RX_CALC_IDX0); - done++; - } - - if (done < budget) - mtk_irq_ack(eth, rx_intr); - - return done; -} - -static int mtk_pdma_tx_poll(struct mtk_eth *eth, int budget, bool *tx_again) -{ - struct sk_buff *skb; - struct mtk_tx_buf *tx_buf; - int done = 0; - u32 idx, hwidx; - struct mtk_tx_ring *ring = ð->tx_ring; - unsigned int bytes = 0; - - idx = ring->tx_free_idx; - hwidx = mtk_reg_r32(eth, MTK_REG_TX_DTX_IDX0); - - while ((idx != hwidx) && budget) { - tx_buf = &ring->tx_buf[idx]; - skb = tx_buf->skb; - - if (!skb) - break; - - if (skb != (struct sk_buff *)DMA_DUMMY_DESC) { - bytes += skb->len; - done++; - budget--; - } - mtk_txd_unmap(eth->dev, tx_buf); - idx = NEXT_TX_DESP_IDX(idx); - } - ring->tx_free_idx = idx; - atomic_set(&ring->tx_free_count, mtk_pdma_empty_txd(ring)); - - /* read hw index again make sure no new tx packet */ - if (idx != hwidx || idx != mtk_reg_r32(eth, MTK_REG_TX_DTX_IDX0)) - *tx_again = 1; - - if (done) - netdev_completed_queue(*eth->netdev, done, bytes); - - return done; -} - -static int mtk_qdma_tx_poll(struct mtk_eth *eth, int budget, bool *tx_again) -{ - struct mtk_tx_ring *ring = ð->tx_ring; - struct mtk_tx_dma *desc; - struct sk_buff *skb; - struct mtk_tx_buf *tx_buf; - int total = 0, done[MTK_MAX_DEVS]; - unsigned int bytes[MTK_MAX_DEVS]; - u32 cpu, dma; - int i; - - memset(done, 0, sizeof(done)); - memset(bytes, 0, sizeof(bytes)); - - cpu = mtk_r32(eth, MTK_QTX_CRX_PTR); - dma = mtk_r32(eth, MTK_QTX_DRX_PTR); - - desc = mtk_qdma_phys_to_virt(ring, cpu); - - while ((cpu != dma) && budget) { - u32 next_cpu = desc->txd2; - int mac; - - desc = mtk_tx_next_qdma(ring, desc); - if ((desc->txd3 & QDMA_TX_OWNER_CPU) == 0) - break; - - mac = (desc->txd4 >> TX_DMA_FPORT_SHIFT) & - TX_DMA_FPORT_MASK; - mac--; - - tx_buf = mtk_desc_to_tx_buf(ring, desc); - skb = tx_buf->skb; - if (!skb) - break; - - if (skb != (struct sk_buff *)DMA_DUMMY_DESC) { - bytes[mac] += skb->len; - done[mac]++; - budget--; - } - mtk_txd_unmap(eth->dev, tx_buf); - - ring->tx_last_free->txd2 = next_cpu; - ring->tx_last_free = desc; - atomic_inc(&ring->tx_free_count); - - cpu = next_cpu; - } - - mtk_w32(eth, cpu, MTK_QTX_CRX_PTR); - - /* read hw index again make sure no new tx packet */ - if (cpu != dma || cpu != mtk_r32(eth, MTK_QTX_DRX_PTR)) - *tx_again = true; - - for (i = 0; i < eth->soc->mac_count; i++) { - if (!done[i]) - continue; - netdev_completed_queue(eth->netdev[i], done[i], bytes[i]); - total += done[i]; - } - - return total; -} - -static int mtk_poll_tx(struct mtk_eth *eth, int budget, u32 tx_intr, - bool *tx_again) -{ - struct mtk_tx_ring *ring = ð->tx_ring; - struct net_device *netdev = eth->netdev[0]; - int done; - - done = eth->tx_ring.tx_poll(eth, budget, tx_again); - if (!*tx_again) - mtk_irq_ack(eth, tx_intr); - - if (!done) - return 0; - - smp_mb(); - if (unlikely(!netif_queue_stopped(netdev))) - return done; - - if (atomic_read(&ring->tx_free_count) > ring->tx_thresh) - netif_wake_queue(netdev); - - return done; -} - -static void mtk_stats_update(struct mtk_eth *eth) -{ - int i; - - for (i = 0; i < eth->soc->mac_count; i++) { - if (!eth->mac[i] || !eth->mac[i]->hw_stats) - continue; - if (spin_trylock(ð->mac[i]->hw_stats->stats_lock)) { - mtk_stats_update_mac(eth->mac[i]); - spin_unlock(ð->mac[i]->hw_stats->stats_lock); - } - } -} - -static int mtk_poll(struct napi_struct *napi, int budget) -{ - struct mtk_eth *eth = container_of(napi, struct mtk_eth, rx_napi); - u32 status, mtk_status, mask, tx_intr, rx_intr, status_intr; - int tx_done, rx_done; - bool tx_again = false; - - status = mtk_irq_pending(eth); - mtk_status = mtk_irq_pending_status(eth); - tx_intr = eth->soc->tx_int; - rx_intr = eth->soc->rx_int; - status_intr = eth->soc->status_int; - tx_done = 0; - rx_done = 0; - tx_again = 0; - - if (status & tx_intr) - tx_done = mtk_poll_tx(eth, budget, tx_intr, &tx_again); - - if (status & rx_intr) - rx_done = mtk_poll_rx(napi, budget, eth, rx_intr); - - if (unlikely(mtk_status & status_intr)) { - mtk_stats_update(eth); - mtk_irq_ack_status(eth, status_intr); - } - - if (unlikely(netif_msg_intr(eth))) { - mask = mtk_irq_enabled(eth); - netdev_info(eth->netdev[0], - "done tx %d, rx %d, intr 0x%08x/0x%x\n", - tx_done, rx_done, status, mask); - } - - if (tx_again || rx_done == budget) - return budget; - - status = mtk_irq_pending(eth); - if (status & (tx_intr | rx_intr)) - return budget; - - napi_complete(napi); - mtk_irq_enable(eth, tx_intr | rx_intr); - - return rx_done; -} - -static int mtk_pdma_tx_alloc(struct mtk_eth *eth) -{ - int i; - struct mtk_tx_ring *ring = ð->tx_ring; - - ring->tx_ring_size = eth->soc->dma_ring_size; - ring->tx_free_idx = 0; - ring->tx_next_idx = 0; - ring->tx_thresh = max((unsigned long)ring->tx_ring_size >> 2, - MAX_SKB_FRAGS); - - ring->tx_buf = kcalloc(ring->tx_ring_size, sizeof(*ring->tx_buf), - GFP_KERNEL); - if (!ring->tx_buf) - goto no_tx_mem; - - ring->tx_dma = - dma_alloc_coherent(eth->dev, - ring->tx_ring_size * sizeof(*ring->tx_dma), - &ring->tx_phys, GFP_ATOMIC | __GFP_ZERO); - if (!ring->tx_dma) - goto no_tx_mem; - - for (i = 0; i < ring->tx_ring_size; i++) { - ring->tx_dma[i].txd2 = TX_DMA_DESP2_DEF; - ring->tx_dma[i].txd4 = eth->soc->txd4; - } - - atomic_set(&ring->tx_free_count, mtk_pdma_empty_txd(ring)); - ring->tx_map = mtk_pdma_tx_map; - ring->tx_poll = mtk_pdma_tx_poll; - ring->tx_clean = mtk_pdma_tx_clean; - - /* make sure that all changes to the dma ring are flushed before we - * continue - */ - wmb(); - - mtk_reg_w32(eth, ring->tx_phys, MTK_REG_TX_BASE_PTR0); - mtk_reg_w32(eth, ring->tx_ring_size, MTK_REG_TX_MAX_CNT0); - mtk_reg_w32(eth, 0, MTK_REG_TX_CTX_IDX0); - mtk_reg_w32(eth, MTK_PST_DTX_IDX0, MTK_REG_PDMA_RST_CFG); - - return 0; - -no_tx_mem: - return -ENOMEM; -} - -static int mtk_qdma_tx_alloc_tx(struct mtk_eth *eth) -{ - struct mtk_tx_ring *ring = ð->tx_ring; - int i, sz = sizeof(*ring->tx_dma); - - ring->tx_ring_size = eth->soc->dma_ring_size; - ring->tx_buf = kcalloc(ring->tx_ring_size, sizeof(*ring->tx_buf), - GFP_KERNEL); - if (!ring->tx_buf) - goto no_tx_mem; - - ring->tx_dma = dma_alloc_coherent(eth->dev, ring->tx_ring_size * sz, - &ring->tx_phys, - GFP_ATOMIC | __GFP_ZERO); - if (!ring->tx_dma) - goto no_tx_mem; - - for (i = 0; i < ring->tx_ring_size; i++) { - int next = (i + 1) % ring->tx_ring_size; - u32 next_ptr = ring->tx_phys + next * sz; - - ring->tx_dma[i].txd2 = next_ptr; - ring->tx_dma[i].txd3 = TX_DMA_DESP2_DEF; - } - - atomic_set(&ring->tx_free_count, ring->tx_ring_size - 2); - ring->tx_next_free = &ring->tx_dma[0]; - ring->tx_last_free = &ring->tx_dma[ring->tx_ring_size - 2]; - ring->tx_thresh = max((unsigned long)ring->tx_ring_size >> 2, - MAX_SKB_FRAGS); - - ring->tx_map = mtk_qdma_tx_map; - ring->tx_poll = mtk_qdma_tx_poll; - ring->tx_clean = mtk_qdma_tx_clean; - - /* make sure that all changes to the dma ring are flushed before we - * continue - */ - wmb(); - - mtk_w32(eth, ring->tx_phys, MTK_QTX_CTX_PTR); - mtk_w32(eth, ring->tx_phys, MTK_QTX_DTX_PTR); - mtk_w32(eth, - ring->tx_phys + ((ring->tx_ring_size - 1) * sz), - MTK_QTX_CRX_PTR); - mtk_w32(eth, - ring->tx_phys + ((ring->tx_ring_size - 1) * sz), - MTK_QTX_DRX_PTR); - - return 0; - -no_tx_mem: - return -ENOMEM; -} - -static int mtk_qdma_init(struct mtk_eth *eth, int ring) -{ - int err; - - err = mtk_init_fq_dma(eth); - if (err) - return err; - - err = mtk_qdma_tx_alloc_tx(eth); - if (err) - return err; - - err = mtk_dma_rx_alloc(eth, ð->rx_ring[ring]); - if (err) - return err; - - mtk_w32(eth, eth->rx_ring[ring].rx_phys, MTK_QRX_BASE_PTR0); - mtk_w32(eth, eth->rx_ring[ring].rx_ring_size, MTK_QRX_MAX_CNT0); - mtk_w32(eth, eth->rx_ring[ring].rx_calc_idx, MTK_QRX_CRX_IDX0); - mtk_w32(eth, MTK_PST_DRX_IDX0, MTK_QDMA_RST_IDX); - mtk_w32(eth, (QDMA_RES_THRES << 8) | QDMA_RES_THRES, MTK_QTX_CFG(0)); - - /* Enable random early drop and set drop threshold automatically */ - mtk_w32(eth, 0x174444, MTK_QDMA_FC_THRES); - mtk_w32(eth, 0x0, MTK_QDMA_HRED2); - - return 0; -} - -static int mtk_pdma_qdma_init(struct mtk_eth *eth) -{ - int err = mtk_qdma_init(eth, 1); - - if (err) - return err; - - err = mtk_dma_rx_alloc(eth, ð->rx_ring[0]); - if (err) - return err; - - mtk_reg_w32(eth, eth->rx_ring[0].rx_phys, MTK_REG_RX_BASE_PTR0); - mtk_reg_w32(eth, eth->rx_ring[0].rx_ring_size, MTK_REG_RX_MAX_CNT0); - mtk_reg_w32(eth, eth->rx_ring[0].rx_calc_idx, MTK_REG_RX_CALC_IDX0); - mtk_reg_w32(eth, MTK_PST_DRX_IDX0, MTK_REG_PDMA_RST_CFG); - - return 0; -} - -static int mtk_pdma_init(struct mtk_eth *eth) -{ - struct mtk_rx_ring *ring = ð->rx_ring[0]; - int err; - - err = mtk_pdma_tx_alloc(eth); - if (err) - return err; - - err = mtk_dma_rx_alloc(eth, ring); - if (err) - return err; - - mtk_reg_w32(eth, ring->rx_phys, MTK_REG_RX_BASE_PTR0); - mtk_reg_w32(eth, ring->rx_ring_size, MTK_REG_RX_MAX_CNT0); - mtk_reg_w32(eth, ring->rx_calc_idx, MTK_REG_RX_CALC_IDX0); - mtk_reg_w32(eth, MTK_PST_DRX_IDX0, MTK_REG_PDMA_RST_CFG); - - return 0; -} - -static void mtk_dma_free(struct mtk_eth *eth) -{ - int i; - - for (i = 0; i < eth->soc->mac_count; i++) - if (eth->netdev[i]) - netdev_reset_queue(eth->netdev[i]); - eth->tx_ring.tx_clean(eth); - mtk_clean_rx(eth, ð->rx_ring[0]); - mtk_clean_rx(eth, ð->rx_ring[1]); - kfree(eth->scratch_head); -} - -static void mtk_tx_timeout(struct net_device *dev) -{ - struct mtk_mac *mac = netdev_priv(dev); - struct mtk_eth *eth = mac->hw; - struct mtk_tx_ring *ring = ð->tx_ring; - - eth->netdev[mac->id]->stats.tx_errors++; - netif_err(eth, tx_err, dev, - "transmit timed out\n"); - if (eth->soc->dma_type & MTK_PDMA) { - netif_info(eth, drv, dev, "pdma_cfg:%08x\n", - mtk_reg_r32(eth, MTK_REG_PDMA_GLO_CFG)); - netif_info(eth, drv, dev, - "tx_ring=%d, base=%08x, max=%u, ctx=%u, dtx=%u, fdx=%hu, next=%hu\n", - 0, mtk_reg_r32(eth, MTK_REG_TX_BASE_PTR0), - mtk_reg_r32(eth, MTK_REG_TX_MAX_CNT0), - mtk_reg_r32(eth, MTK_REG_TX_CTX_IDX0), - mtk_reg_r32(eth, MTK_REG_TX_DTX_IDX0), - ring->tx_free_idx, - ring->tx_next_idx); - } - if (eth->soc->dma_type & MTK_QDMA) { - netif_info(eth, drv, dev, "qdma_cfg:%08x\n", - mtk_r32(eth, MTK_QDMA_GLO_CFG)); - netif_info(eth, drv, dev, - "tx_ring=%d, ctx=%08x, dtx=%08x, crx=%08x, drx=%08x, free=%hu\n", - 0, mtk_r32(eth, MTK_QTX_CTX_PTR), - mtk_r32(eth, MTK_QTX_DTX_PTR), - mtk_r32(eth, MTK_QTX_CRX_PTR), - mtk_r32(eth, MTK_QTX_DRX_PTR), - atomic_read(&ring->tx_free_count)); - } - netif_info(eth, drv, dev, - "rx_ring=%d, base=%08x, max=%u, calc=%u, drx=%u\n", - 0, mtk_reg_r32(eth, MTK_REG_RX_BASE_PTR0), - mtk_reg_r32(eth, MTK_REG_RX_MAX_CNT0), - mtk_reg_r32(eth, MTK_REG_RX_CALC_IDX0), - mtk_reg_r32(eth, MTK_REG_RX_DRX_IDX0)); - - schedule_work(&mac->pending_work); -} - -static irqreturn_t mtk_handle_irq(int irq, void *_eth) -{ - struct mtk_eth *eth = _eth; - u32 status, int_mask; - - status = mtk_irq_pending(eth); - if (unlikely(!status)) - return IRQ_NONE; - - int_mask = (eth->soc->rx_int | eth->soc->tx_int); - if (likely(status & int_mask)) { - if (likely(napi_schedule_prep(ð->rx_napi))) - __napi_schedule(ð->rx_napi); - } else { - mtk_irq_ack(eth, status); - } - mtk_irq_disable(eth, int_mask); - - return IRQ_HANDLED; -} - -#ifdef CONFIG_NET_POLL_CONTROLLER -static void mtk_poll_controller(struct net_device *dev) -{ - struct mtk_mac *mac = netdev_priv(dev); - struct mtk_eth *eth = mac->hw; - u32 int_mask = eth->soc->tx_int | eth->soc->rx_int; - - mtk_irq_disable(eth, int_mask); - mtk_handle_irq(dev->irq, dev); - mtk_irq_enable(eth, int_mask); -} -#endif - -int mtk_set_clock_cycle(struct mtk_eth *eth) -{ - unsigned long sysclk = eth->sysclk; - - sysclk /= MTK_US_CYC_CNT_DIVISOR; - sysclk <<= MTK_US_CYC_CNT_SHIFT; - - mtk_w32(eth, (mtk_r32(eth, MTK_GLO_CFG) & - ~(MTK_US_CYC_CNT_MASK << MTK_US_CYC_CNT_SHIFT)) | - sysclk, - MTK_GLO_CFG); - return 0; -} - -void mtk_fwd_config(struct mtk_eth *eth) -{ - u32 fwd_cfg; - - fwd_cfg = mtk_r32(eth, MTK_GDMA1_FWD_CFG); - - /* disable jumbo frame */ - if (eth->soc->jumbo_frame) - fwd_cfg &= ~MTK_GDM1_JMB_EN; - - /* set unicast/multicast/broadcast frame to cpu */ - fwd_cfg &= ~0xffff; - - mtk_w32(eth, fwd_cfg, MTK_GDMA1_FWD_CFG); -} - -void mtk_csum_config(struct mtk_eth *eth) -{ - if (eth->soc->hw_features & NETIF_F_RXCSUM) - mtk_w32(eth, mtk_r32(eth, MTK_GDMA1_FWD_CFG) | - (MTK_GDM1_ICS_EN | MTK_GDM1_TCS_EN | MTK_GDM1_UCS_EN), - MTK_GDMA1_FWD_CFG); - else - mtk_w32(eth, mtk_r32(eth, MTK_GDMA1_FWD_CFG) & - ~(MTK_GDM1_ICS_EN | MTK_GDM1_TCS_EN | MTK_GDM1_UCS_EN), - MTK_GDMA1_FWD_CFG); - if (eth->soc->hw_features & NETIF_F_IP_CSUM) - mtk_w32(eth, mtk_r32(eth, MTK_CDMA_CSG_CFG) | - (MTK_ICS_GEN_EN | MTK_TCS_GEN_EN | MTK_UCS_GEN_EN), - MTK_CDMA_CSG_CFG); - else - mtk_w32(eth, mtk_r32(eth, MTK_CDMA_CSG_CFG) & - ~(MTK_ICS_GEN_EN | MTK_TCS_GEN_EN | MTK_UCS_GEN_EN), - MTK_CDMA_CSG_CFG); -} - -static int mtk_start_dma(struct mtk_eth *eth) -{ - unsigned long flags; - u32 val; - int err; - - if (eth->soc->dma_type == MTK_PDMA) - err = mtk_pdma_init(eth); - else if (eth->soc->dma_type == MTK_QDMA) - err = mtk_qdma_init(eth, 0); - else - err = mtk_pdma_qdma_init(eth); - if (err) { - mtk_dma_free(eth); - return err; - } - - spin_lock_irqsave(ð->page_lock, flags); - - val = MTK_TX_WB_DDONE | MTK_RX_DMA_EN | MTK_TX_DMA_EN; - if (eth->soc->rx_2b_offset) - val |= MTK_RX_2B_OFFSET; - val |= eth->soc->pdma_glo_cfg; - - if (eth->soc->dma_type & MTK_PDMA) - mtk_reg_w32(eth, val, MTK_REG_PDMA_GLO_CFG); - - if (eth->soc->dma_type & MTK_QDMA) - mtk_w32(eth, val, MTK_QDMA_GLO_CFG); - - spin_unlock_irqrestore(ð->page_lock, flags); - - return 0; -} - -static int mtk_open(struct net_device *dev) -{ - struct mtk_mac *mac = netdev_priv(dev); - struct mtk_eth *eth = mac->hw; - - dma_coerce_mask_and_coherent(&dev->dev, DMA_BIT_MASK(32)); - - if (!atomic_read(ð->dma_refcnt)) { - int err = mtk_start_dma(eth); - - if (err) - return err; - - napi_enable(ð->rx_napi); - mtk_irq_enable(eth, eth->soc->tx_int | eth->soc->rx_int); - } - atomic_inc(ð->dma_refcnt); - - if (eth->phy) - eth->phy->start(mac); - - if (eth->soc->has_carrier && eth->soc->has_carrier(eth)) - netif_carrier_on(dev); - - netif_start_queue(dev); - eth->soc->fwd_config(eth); - - return 0; -} - -static void mtk_stop_dma(struct mtk_eth *eth, u32 glo_cfg) -{ - unsigned long flags; - u32 val; - int i; - - /* stop the dma enfine */ - spin_lock_irqsave(ð->page_lock, flags); - val = mtk_r32(eth, glo_cfg); - mtk_w32(eth, val & ~(MTK_TX_WB_DDONE | MTK_RX_DMA_EN | MTK_TX_DMA_EN), - glo_cfg); - spin_unlock_irqrestore(ð->page_lock, flags); - - /* wait for dma stop */ - for (i = 0; i < 10; i++) { - val = mtk_r32(eth, glo_cfg); - if (val & (MTK_TX_DMA_BUSY | MTK_RX_DMA_BUSY)) { - msleep(20); - continue; - } - break; - } -} - -static int mtk_stop(struct net_device *dev) -{ - struct mtk_mac *mac = netdev_priv(dev); - struct mtk_eth *eth = mac->hw; - - netif_tx_disable(dev); - if (eth->phy) - eth->phy->stop(mac); - - if (!atomic_dec_and_test(ð->dma_refcnt)) - return 0; - - mtk_irq_disable(eth, eth->soc->tx_int | eth->soc->rx_int); - napi_disable(ð->rx_napi); - - if (eth->soc->dma_type & MTK_PDMA) - mtk_stop_dma(eth, mtk_reg_table[MTK_REG_PDMA_GLO_CFG]); - - if (eth->soc->dma_type & MTK_QDMA) - mtk_stop_dma(eth, MTK_QDMA_GLO_CFG); - - mtk_dma_free(eth); - - return 0; -} - -static int __init mtk_init_hw(struct mtk_eth *eth) -{ - int i, err; - - eth->soc->reset_fe(eth); - - if (eth->soc->switch_init) - if (eth->soc->switch_init(eth)) { - dev_err(eth->dev, "failed to initialize switch core\n"); - return -ENODEV; - } - - err = devm_request_irq(eth->dev, eth->irq, mtk_handle_irq, 0, - dev_name(eth->dev), eth); - if (err) - return err; - - err = mtk_mdio_init(eth); - if (err) - return err; - - /* disable delay and normal interrupt */ - mtk_reg_w32(eth, 0, MTK_REG_DLY_INT_CFG); - if (eth->soc->dma_type & MTK_QDMA) - mtk_w32(eth, 0, MTK_QDMA_DELAY_INT); - mtk_irq_disable(eth, eth->soc->tx_int | eth->soc->rx_int); - - /* frame engine will push VLAN tag regarding to VIDX field in Tx desc */ - if (mtk_reg_table[MTK_REG_MTK_DMA_VID_BASE]) - for (i = 0; i < 16; i += 2) - mtk_w32(eth, ((i + 1) << 16) + i, - mtk_reg_table[MTK_REG_MTK_DMA_VID_BASE] + - (i * 2)); - - if (eth->soc->fwd_config(eth)) - dev_err(eth->dev, "unable to get clock\n"); - - if (mtk_reg_table[MTK_REG_MTK_RST_GL]) { - mtk_reg_w32(eth, 1, MTK_REG_MTK_RST_GL); - mtk_reg_w32(eth, 0, MTK_REG_MTK_RST_GL); - } - - return 0; -} - -static int __init mtk_init(struct net_device *dev) -{ - struct mtk_mac *mac = netdev_priv(dev); - struct mtk_eth *eth = mac->hw; - struct device_node *port; - const char *mac_addr; - int err; - - mac_addr = of_get_mac_address(mac->of_node); - if (mac_addr) - ether_addr_copy(dev->dev_addr, mac_addr); - - /* If the mac address is invalid, use random mac address */ - if (!is_valid_ether_addr(dev->dev_addr)) { - eth_hw_addr_random(dev); - dev_err(eth->dev, "generated random MAC address %pM\n", - dev->dev_addr); - } - mac->hw->soc->set_mac(mac, dev->dev_addr); - - if (eth->soc->port_init) - for_each_child_of_node(mac->of_node, port) - if (of_device_is_compatible(port, - "mediatek,eth-port") && - of_device_is_available(port)) - eth->soc->port_init(eth, mac, port); - - if (eth->phy) { - err = eth->phy->connect(mac); - if (err) - return err; - } - - return 0; -} - -static void mtk_uninit(struct net_device *dev) -{ - struct mtk_mac *mac = netdev_priv(dev); - struct mtk_eth *eth = mac->hw; - - if (eth->phy) - eth->phy->disconnect(mac); - mtk_mdio_cleanup(eth); - - mtk_irq_disable(eth, ~0); - free_irq(dev->irq, dev); -} - -static int mtk_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) -{ - struct mtk_mac *mac = netdev_priv(dev); - - if (!mac->phy_dev) - return -ENODEV; - - switch (cmd) { - case SIOCGMIIPHY: - case SIOCGMIIREG: - case SIOCSMIIREG: - return phy_mii_ioctl(mac->phy_dev, ifr, cmd); - default: - break; - } - - return -EOPNOTSUPP; -} - -static int mtk_change_mtu(struct net_device *dev, int new_mtu) -{ - struct mtk_mac *mac = netdev_priv(dev); - struct mtk_eth *eth = mac->hw; - int frag_size, old_mtu; - u32 fwd_cfg; - - if (!eth->soc->jumbo_frame) - return eth_change_mtu(dev, new_mtu); - - frag_size = mtk_max_frag_size(new_mtu); - if (new_mtu < 68 || frag_size > PAGE_SIZE) - return -EINVAL; - - old_mtu = dev->mtu; - dev->mtu = new_mtu; - - /* return early if the buffer sizes will not change */ - if (old_mtu <= ETH_DATA_LEN && new_mtu <= ETH_DATA_LEN) - return 0; - if (old_mtu > ETH_DATA_LEN && new_mtu > ETH_DATA_LEN) - return 0; - - if (new_mtu <= ETH_DATA_LEN) - eth->rx_ring[0].frag_size = mtk_max_frag_size(ETH_DATA_LEN); - else - eth->rx_ring[0].frag_size = PAGE_SIZE; - eth->rx_ring[0].rx_buf_size = - mtk_max_buf_size(eth->rx_ring[0].frag_size); - - if (!netif_running(dev)) - return 0; - - mtk_stop(dev); - fwd_cfg = mtk_r32(eth, MTK_GDMA1_FWD_CFG); - if (new_mtu <= ETH_DATA_LEN) { - fwd_cfg &= ~MTK_GDM1_JMB_EN; - } else { - fwd_cfg &= ~(MTK_GDM1_JMB_LEN_MASK << MTK_GDM1_JMB_LEN_SHIFT); - fwd_cfg |= (DIV_ROUND_UP(frag_size, 1024) << - MTK_GDM1_JMB_LEN_SHIFT) | MTK_GDM1_JMB_EN; - } - mtk_w32(eth, fwd_cfg, MTK_GDMA1_FWD_CFG); - - return mtk_open(dev); -} - -static void mtk_pending_work(struct work_struct *work) -{ - struct mtk_mac *mac = container_of(work, struct mtk_mac, pending_work); - struct mtk_eth *eth = mac->hw; - struct net_device *dev = eth->netdev[mac->id]; - int err; - - rtnl_lock(); - mtk_stop(dev); - - err = mtk_open(dev); - if (err) { - netif_alert(eth, ifup, dev, - "Driver up/down cycle failed, closing device.\n"); - dev_close(dev); - } - rtnl_unlock(); -} - -static int mtk_cleanup(struct mtk_eth *eth) -{ - int i; - - for (i = 0; i < eth->soc->mac_count; i++) { - struct mtk_mac *mac = netdev_priv(eth->netdev[i]); - - if (!eth->netdev[i]) - continue; - - unregister_netdev(eth->netdev[i]); - free_netdev(eth->netdev[i]); - cancel_work_sync(&mac->pending_work); - } - - return 0; -} - -static const struct net_device_ops mtk_netdev_ops = { - .ndo_init = mtk_init, - .ndo_uninit = mtk_uninit, - .ndo_open = mtk_open, - .ndo_stop = mtk_stop, - .ndo_start_xmit = mtk_start_xmit, - .ndo_set_mac_address = mtk_set_mac_address, - .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = mtk_do_ioctl, - .ndo_change_mtu = mtk_change_mtu, - .ndo_tx_timeout = mtk_tx_timeout, - .ndo_get_stats64 = mtk_get_stats64, - .ndo_vlan_rx_add_vid = mtk_vlan_rx_add_vid, - .ndo_vlan_rx_kill_vid = mtk_vlan_rx_kill_vid, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = mtk_poll_controller, -#endif -}; - -static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) -{ - struct mtk_mac *mac; - const __be32 *_id = of_get_property(np, "reg", NULL); - int id, err; - - if (!_id) { - dev_err(eth->dev, "missing mac id\n"); - return -EINVAL; - } - id = be32_to_cpup(_id); - if (id >= eth->soc->mac_count || eth->netdev[id]) { - dev_err(eth->dev, "%d is not a valid mac id\n", id); - return -EINVAL; - } - - eth->netdev[id] = alloc_etherdev(sizeof(*mac)); - if (!eth->netdev[id]) { - dev_err(eth->dev, "alloc_etherdev failed\n"); - return -ENOMEM; - } - mac = netdev_priv(eth->netdev[id]); - eth->mac[id] = mac; - mac->id = id; - mac->hw = eth; - mac->of_node = np; - INIT_WORK(&mac->pending_work, mtk_pending_work); - - if (mtk_reg_table[MTK_REG_MTK_COUNTER_BASE]) { - mac->hw_stats = devm_kzalloc(eth->dev, - sizeof(*mac->hw_stats), - GFP_KERNEL); - if (!mac->hw_stats) { - err = -ENOMEM; - goto free_netdev; - } - spin_lock_init(&mac->hw_stats->stats_lock); - mac->hw_stats->reg_offset = id * MTK_STAT_OFFSET; - } - - SET_NETDEV_DEV(eth->netdev[id], eth->dev); - eth->netdev[id]->netdev_ops = &mtk_netdev_ops; - eth->netdev[id]->base_addr = (unsigned long)eth->base; - - if (eth->soc->init_data) - eth->soc->init_data(eth->soc, eth->netdev[id]); - - eth->netdev[id]->vlan_features = eth->soc->hw_features & - ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX); - eth->netdev[id]->features |= eth->soc->hw_features; - - if (mtk_reg_table[MTK_REG_MTK_DMA_VID_BASE]) - eth->netdev[id]->features |= NETIF_F_HW_VLAN_CTAG_FILTER; - - mtk_set_ethtool_ops(eth->netdev[id]); - - err = register_netdev(eth->netdev[id]); - if (err) { - dev_err(eth->dev, "error bringing up device\n"); - err = -ENOMEM; - goto free_netdev; - } - eth->netdev[id]->irq = eth->irq; - netif_info(eth, probe, eth->netdev[id], - "mediatek frame engine at 0x%08lx, irq %d\n", - eth->netdev[id]->base_addr, eth->netdev[id]->irq); - - return 0; - -free_netdev: - free_netdev(eth->netdev[id]); - return err; -} - -static int mtk_probe(struct platform_device *pdev) -{ - struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - const struct of_device_id *match; - struct device_node *mac_np; - struct mtk_soc_data *soc; - struct mtk_eth *eth; - struct clk *sysclk; - int err; - - device_reset(&pdev->dev); - - match = of_match_device(of_mtk_match, &pdev->dev); - soc = (struct mtk_soc_data *)match->data; - - if (soc->reg_table) - mtk_reg_table = soc->reg_table; - - eth = devm_kzalloc(&pdev->dev, sizeof(*eth), GFP_KERNEL); - if (!eth) - return -ENOMEM; - - eth->base = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(eth->base)) - return PTR_ERR(eth->base); - - spin_lock_init(ð->page_lock); - - eth->ethsys = syscon_regmap_lookup_by_phandle(pdev->dev.of_node, - "mediatek,ethsys"); - if (IS_ERR(eth->ethsys)) - return PTR_ERR(eth->ethsys); - - eth->irq = platform_get_irq(pdev, 0); - if (eth->irq < 0) { - dev_err(&pdev->dev, "no IRQ resource found\n"); - return -ENXIO; - } - - sysclk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(sysclk)) { - dev_err(&pdev->dev, - "the clock is not defined in the devicetree\n"); - return -ENXIO; - } - eth->sysclk = clk_get_rate(sysclk); - - eth->switch_np = of_parse_phandle(pdev->dev.of_node, - "mediatek,switch", 0); - if (soc->has_switch && !eth->switch_np) { - dev_err(&pdev->dev, "failed to read switch phandle\n"); - return -ENODEV; - } - - eth->dev = &pdev->dev; - eth->soc = soc; - eth->msg_enable = netif_msg_init(mtk_msg_level, MTK_DEFAULT_MSG_ENABLE); - - err = mtk_init_hw(eth); - if (err) - return err; - - if (eth->soc->mac_count > 1) { - for_each_child_of_node(pdev->dev.of_node, mac_np) { - if (!of_device_is_compatible(mac_np, - "mediatek,eth-mac")) - continue; - - if (!of_device_is_available(mac_np)) - continue; - - err = mtk_add_mac(eth, mac_np); - if (err) - goto err_free_dev; - } - - init_dummy_netdev(ð->dummy_dev); - netif_napi_add(ð->dummy_dev, ð->rx_napi, mtk_poll, - soc->napi_weight); - } else { - err = mtk_add_mac(eth, pdev->dev.of_node); - if (err) - goto err_free_dev; - netif_napi_add(eth->netdev[0], ð->rx_napi, mtk_poll, - soc->napi_weight); - } - - platform_set_drvdata(pdev, eth); - - return 0; - -err_free_dev: - mtk_cleanup(eth); - return err; -} - -static int mtk_remove(struct platform_device *pdev) -{ - struct mtk_eth *eth = platform_get_drvdata(pdev); - - netif_napi_del(ð->rx_napi); - mtk_cleanup(eth); - platform_set_drvdata(pdev, NULL); - - return 0; -} - -static struct platform_driver mtk_driver = { - .probe = mtk_probe, - .remove = mtk_remove, - .driver = { - .name = "mtk_soc_eth", - .of_match_table = of_mtk_match, - }, -}; - -module_platform_driver(mtk_driver); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("John Crispin <blogic@openwrt.org>"); -MODULE_DESCRIPTION("Ethernet driver for MediaTek SoC"); diff --git a/drivers/staging/mt7621-eth/mtk_eth_soc.h b/drivers/staging/mt7621-eth/mtk_eth_soc.h deleted file mode 100644 index e6ed80433f49..000000000000 --- a/drivers/staging/mt7621-eth/mtk_eth_soc.h +++ /dev/null @@ -1,716 +0,0 @@ -/* This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org> - * Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org> - * Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com> - */ - -#ifndef MTK_ETH_H -#define MTK_ETH_H - -#include <linux/mii.h> -#include <linux/interrupt.h> -#include <linux/netdevice.h> -#include <linux/dma-mapping.h> -#include <linux/phy.h> -#include <linux/ethtool.h> -#include <linux/version.h> -#include <linux/atomic.h> - -/* these registers have different offsets depending on the SoC. we use a lookup - * table for these - */ -enum mtk_reg { - MTK_REG_PDMA_GLO_CFG = 0, - MTK_REG_PDMA_RST_CFG, - MTK_REG_DLY_INT_CFG, - MTK_REG_TX_BASE_PTR0, - MTK_REG_TX_MAX_CNT0, - MTK_REG_TX_CTX_IDX0, - MTK_REG_TX_DTX_IDX0, - MTK_REG_RX_BASE_PTR0, - MTK_REG_RX_MAX_CNT0, - MTK_REG_RX_CALC_IDX0, - MTK_REG_RX_DRX_IDX0, - MTK_REG_MTK_INT_ENABLE, - MTK_REG_MTK_INT_STATUS, - MTK_REG_MTK_DMA_VID_BASE, - MTK_REG_MTK_COUNTER_BASE, - MTK_REG_MTK_RST_GL, - MTK_REG_MTK_INT_STATUS2, - MTK_REG_COUNT -}; - -/* delayed interrupt bits */ -#define MTK_DELAY_EN_INT 0x80 -#define MTK_DELAY_MAX_INT 0x04 -#define MTK_DELAY_MAX_TOUT 0x04 -#define MTK_DELAY_TIME 20 -#define MTK_DELAY_CHAN (((MTK_DELAY_EN_INT | MTK_DELAY_MAX_INT) << 8) \ - | MTK_DELAY_MAX_TOUT) -#define MTK_DELAY_INIT ((MTK_DELAY_CHAN << 16) | MTK_DELAY_CHAN) -#define MTK_PSE_FQFC_CFG_INIT 0x80504000 -#define MTK_PSE_FQFC_CFG_256Q 0xff908000 - -/* interrupt bits */ -#define MTK_CNT_PPE_AF BIT(31) -#define MTK_CNT_GDM_AF BIT(29) -#define MTK_PSE_P2_FC BIT(26) -#define MTK_PSE_BUF_DROP BIT(24) -#define MTK_GDM_OTHER_DROP BIT(23) -#define MTK_PSE_P1_FC BIT(22) -#define MTK_PSE_P0_FC BIT(21) -#define MTK_PSE_FQ_EMPTY BIT(20) -#define MTK_GE1_STA_CHG BIT(18) -#define MTK_TX_COHERENT BIT(17) -#define MTK_RX_COHERENT BIT(16) -#define MTK_TX_DONE_INT3 BIT(11) -#define MTK_TX_DONE_INT2 BIT(10) -#define MTK_TX_DONE_INT1 BIT(9) -#define MTK_TX_DONE_INT0 BIT(8) -#define MTK_RX_DONE_INT0 BIT(2) -#define MTK_TX_DLY_INT BIT(1) -#define MTK_RX_DLY_INT BIT(0) - -#define MTK_RX_DONE_INT MTK_RX_DONE_INT0 -#define MTK_TX_DONE_INT (MTK_TX_DONE_INT0 | MTK_TX_DONE_INT1 | \ - MTK_TX_DONE_INT2 | MTK_TX_DONE_INT3) - -#define RT5350_RX_DLY_INT BIT(30) -#define RT5350_TX_DLY_INT BIT(28) -#define RT5350_RX_DONE_INT1 BIT(17) -#define RT5350_RX_DONE_INT0 BIT(16) -#define RT5350_TX_DONE_INT3 BIT(3) -#define RT5350_TX_DONE_INT2 BIT(2) -#define RT5350_TX_DONE_INT1 BIT(1) -#define RT5350_TX_DONE_INT0 BIT(0) - -#define RT5350_RX_DONE_INT (RT5350_RX_DONE_INT0 | RT5350_RX_DONE_INT1) -#define RT5350_TX_DONE_INT (RT5350_TX_DONE_INT0 | RT5350_TX_DONE_INT1 | \ - RT5350_TX_DONE_INT2 | RT5350_TX_DONE_INT3) - -/* registers */ -#define MTK_GDMA_OFFSET 0x0020 -#define MTK_PSE_OFFSET 0x0040 -#define MTK_GDMA2_OFFSET 0x0060 -#define MTK_CDMA_OFFSET 0x0080 -#define MTK_DMA_VID0 0x00a8 -#define MTK_PDMA_OFFSET 0x0100 -#define MTK_PPE_OFFSET 0x0200 -#define MTK_CMTABLE_OFFSET 0x0400 -#define MTK_POLICYTABLE_OFFSET 0x1000 - -#define MT7621_GDMA_OFFSET 0x0500 -#define MT7620_GDMA_OFFSET 0x0600 - -#define RT5350_PDMA_OFFSET 0x0800 -#define RT5350_SDM_OFFSET 0x0c00 - -#define MTK_MDIO_ACCESS 0x00 -#define MTK_MDIO_CFG 0x04 -#define MTK_GLO_CFG 0x08 -#define MTK_RST_GL 0x0C -#define MTK_INT_STATUS 0x10 -#define MTK_INT_ENABLE 0x14 -#define MTK_MDIO_CFG2 0x18 -#define MTK_FOC_TS_T 0x1C - -#define MTK_GDMA1_FWD_CFG (MTK_GDMA_OFFSET + 0x00) -#define MTK_GDMA1_SCH_CFG (MTK_GDMA_OFFSET + 0x04) -#define MTK_GDMA1_SHPR_CFG (MTK_GDMA_OFFSET + 0x08) -#define MTK_GDMA1_MAC_ADRL (MTK_GDMA_OFFSET + 0x0C) -#define MTK_GDMA1_MAC_ADRH (MTK_GDMA_OFFSET + 0x10) - -#define MTK_GDMA2_FWD_CFG (MTK_GDMA2_OFFSET + 0x00) -#define MTK_GDMA2_SCH_CFG (MTK_GDMA2_OFFSET + 0x04) -#define MTK_GDMA2_SHPR_CFG (MTK_GDMA2_OFFSET + 0x08) -#define MTK_GDMA2_MAC_ADRL (MTK_GDMA2_OFFSET + 0x0C) -#define MTK_GDMA2_MAC_ADRH (MTK_GDMA2_OFFSET + 0x10) - -#define MTK_PSE_FQ_CFG (MTK_PSE_OFFSET + 0x00) -#define MTK_CDMA_FC_CFG (MTK_PSE_OFFSET + 0x04) -#define MTK_GDMA1_FC_CFG (MTK_PSE_OFFSET + 0x08) -#define MTK_GDMA2_FC_CFG (MTK_PSE_OFFSET + 0x0C) - -#define MTK_CDMA_CSG_CFG (MTK_CDMA_OFFSET + 0x00) -#define MTK_CDMA_SCH_CFG (MTK_CDMA_OFFSET + 0x04) - -#define MT7621_GDMA_FWD_CFG(x) (MT7621_GDMA_OFFSET + (x * 0x1000)) - -/* FIXME this might be different for different SOCs */ -#define MT7620_GDMA1_FWD_CFG (MT7621_GDMA_OFFSET + 0x00) - -#define RT5350_TX_BASE_PTR0 (RT5350_PDMA_OFFSET + 0x00) -#define RT5350_TX_MAX_CNT0 (RT5350_PDMA_OFFSET + 0x04) -#define RT5350_TX_CTX_IDX0 (RT5350_PDMA_OFFSET + 0x08) -#define RT5350_TX_DTX_IDX0 (RT5350_PDMA_OFFSET + 0x0C) -#define RT5350_TX_BASE_PTR1 (RT5350_PDMA_OFFSET + 0x10) -#define RT5350_TX_MAX_CNT1 (RT5350_PDMA_OFFSET + 0x14) -#define RT5350_TX_CTX_IDX1 (RT5350_PDMA_OFFSET + 0x18) -#define RT5350_TX_DTX_IDX1 (RT5350_PDMA_OFFSET + 0x1C) -#define RT5350_TX_BASE_PTR2 (RT5350_PDMA_OFFSET + 0x20) -#define RT5350_TX_MAX_CNT2 (RT5350_PDMA_OFFSET + 0x24) -#define RT5350_TX_CTX_IDX2 (RT5350_PDMA_OFFSET + 0x28) -#define RT5350_TX_DTX_IDX2 (RT5350_PDMA_OFFSET + 0x2C) -#define RT5350_TX_BASE_PTR3 (RT5350_PDMA_OFFSET + 0x30) -#define RT5350_TX_MAX_CNT3 (RT5350_PDMA_OFFSET + 0x34) -#define RT5350_TX_CTX_IDX3 (RT5350_PDMA_OFFSET + 0x38) -#define RT5350_TX_DTX_IDX3 (RT5350_PDMA_OFFSET + 0x3C) -#define RT5350_RX_BASE_PTR0 (RT5350_PDMA_OFFSET + 0x100) -#define RT5350_RX_MAX_CNT0 (RT5350_PDMA_OFFSET + 0x104) -#define RT5350_RX_CALC_IDX0 (RT5350_PDMA_OFFSET + 0x108) -#define RT5350_RX_DRX_IDX0 (RT5350_PDMA_OFFSET + 0x10C) -#define RT5350_RX_BASE_PTR1 (RT5350_PDMA_OFFSET + 0x110) -#define RT5350_RX_MAX_CNT1 (RT5350_PDMA_OFFSET + 0x114) -#define RT5350_RX_CALC_IDX1 (RT5350_PDMA_OFFSET + 0x118) -#define RT5350_RX_DRX_IDX1 (RT5350_PDMA_OFFSET + 0x11C) -#define RT5350_PDMA_GLO_CFG (RT5350_PDMA_OFFSET + 0x204) -#define RT5350_PDMA_RST_CFG (RT5350_PDMA_OFFSET + 0x208) -#define RT5350_DLY_INT_CFG (RT5350_PDMA_OFFSET + 0x20c) -#define RT5350_MTK_INT_STATUS (RT5350_PDMA_OFFSET + 0x220) -#define RT5350_MTK_INT_ENABLE (RT5350_PDMA_OFFSET + 0x228) -#define RT5350_PDMA_SCH_CFG (RT5350_PDMA_OFFSET + 0x280) - -#define MTK_PDMA_GLO_CFG (MTK_PDMA_OFFSET + 0x00) -#define MTK_PDMA_RST_CFG (MTK_PDMA_OFFSET + 0x04) -#define MTK_PDMA_SCH_CFG (MTK_PDMA_OFFSET + 0x08) -#define MTK_DLY_INT_CFG (MTK_PDMA_OFFSET + 0x0C) -#define MTK_TX_BASE_PTR0 (MTK_PDMA_OFFSET + 0x10) -#define MTK_TX_MAX_CNT0 (MTK_PDMA_OFFSET + 0x14) -#define MTK_TX_CTX_IDX0 (MTK_PDMA_OFFSET + 0x18) -#define MTK_TX_DTX_IDX0 (MTK_PDMA_OFFSET + 0x1C) -#define MTK_TX_BASE_PTR1 (MTK_PDMA_OFFSET + 0x20) -#define MTK_TX_MAX_CNT1 (MTK_PDMA_OFFSET + 0x24) -#define MTK_TX_CTX_IDX1 (MTK_PDMA_OFFSET + 0x28) -#define MTK_TX_DTX_IDX1 (MTK_PDMA_OFFSET + 0x2C) -#define MTK_RX_BASE_PTR0 (MTK_PDMA_OFFSET + 0x30) -#define MTK_RX_MAX_CNT0 (MTK_PDMA_OFFSET + 0x34) -#define MTK_RX_CALC_IDX0 (MTK_PDMA_OFFSET + 0x38) -#define MTK_RX_DRX_IDX0 (MTK_PDMA_OFFSET + 0x3C) -#define MTK_TX_BASE_PTR2 (MTK_PDMA_OFFSET + 0x40) -#define MTK_TX_MAX_CNT2 (MTK_PDMA_OFFSET + 0x44) -#define MTK_TX_CTX_IDX2 (MTK_PDMA_OFFSET + 0x48) -#define MTK_TX_DTX_IDX2 (MTK_PDMA_OFFSET + 0x4C) -#define MTK_TX_BASE_PTR3 (MTK_PDMA_OFFSET + 0x50) -#define MTK_TX_MAX_CNT3 (MTK_PDMA_OFFSET + 0x54) -#define MTK_TX_CTX_IDX3 (MTK_PDMA_OFFSET + 0x58) -#define MTK_TX_DTX_IDX3 (MTK_PDMA_OFFSET + 0x5C) -#define MTK_RX_BASE_PTR1 (MTK_PDMA_OFFSET + 0x60) -#define MTK_RX_MAX_CNT1 (MTK_PDMA_OFFSET + 0x64) -#define MTK_RX_CALC_IDX1 (MTK_PDMA_OFFSET + 0x68) -#define MTK_RX_DRX_IDX1 (MTK_PDMA_OFFSET + 0x6C) - -/* Switch DMA configuration */ -#define RT5350_SDM_CFG (RT5350_SDM_OFFSET + 0x00) -#define RT5350_SDM_RRING (RT5350_SDM_OFFSET + 0x04) -#define RT5350_SDM_TRING (RT5350_SDM_OFFSET + 0x08) -#define RT5350_SDM_MAC_ADRL (RT5350_SDM_OFFSET + 0x0C) -#define RT5350_SDM_MAC_ADRH (RT5350_SDM_OFFSET + 0x10) -#define RT5350_SDM_TPCNT (RT5350_SDM_OFFSET + 0x100) -#define RT5350_SDM_TBCNT (RT5350_SDM_OFFSET + 0x104) -#define RT5350_SDM_RPCNT (RT5350_SDM_OFFSET + 0x108) -#define RT5350_SDM_RBCNT (RT5350_SDM_OFFSET + 0x10C) -#define RT5350_SDM_CS_ERR (RT5350_SDM_OFFSET + 0x110) - -#define RT5350_SDM_ICS_EN BIT(16) -#define RT5350_SDM_TCS_EN BIT(17) -#define RT5350_SDM_UCS_EN BIT(18) - -/* QDMA registers */ -#define MTK_QTX_CFG(x) (0x1800 + (x * 0x10)) -#define MTK_QTX_SCH(x) (0x1804 + (x * 0x10)) -#define MTK_QRX_BASE_PTR0 0x1900 -#define MTK_QRX_MAX_CNT0 0x1904 -#define MTK_QRX_CRX_IDX0 0x1908 -#define MTK_QRX_DRX_IDX0 0x190C -#define MTK_QDMA_GLO_CFG 0x1A04 -#define MTK_QDMA_RST_IDX 0x1A08 -#define MTK_QDMA_DELAY_INT 0x1A0C -#define MTK_QDMA_FC_THRES 0x1A10 -#define MTK_QMTK_INT_STATUS 0x1A18 -#define MTK_QMTK_INT_ENABLE 0x1A1C -#define MTK_QDMA_HRED2 0x1A44 - -#define MTK_QTX_CTX_PTR 0x1B00 -#define MTK_QTX_DTX_PTR 0x1B04 - -#define MTK_QTX_CRX_PTR 0x1B10 -#define MTK_QTX_DRX_PTR 0x1B14 - -#define MTK_QDMA_FQ_HEAD 0x1B20 -#define MTK_QDMA_FQ_TAIL 0x1B24 -#define MTK_QDMA_FQ_CNT 0x1B28 -#define MTK_QDMA_FQ_BLEN 0x1B2C - -#define QDMA_PAGE_SIZE 2048 -#define QDMA_TX_OWNER_CPU BIT(31) -#define QDMA_TX_SWC BIT(14) -#define TX_QDMA_SDL(_x) (((_x) & 0x3fff) << 16) -#define QDMA_RES_THRES 4 - -/* MDIO_CFG register bits */ -#define MTK_MDIO_CFG_AUTO_POLL_EN BIT(29) -#define MTK_MDIO_CFG_GP1_BP_EN BIT(16) -#define MTK_MDIO_CFG_GP1_FRC_EN BIT(15) -#define MTK_MDIO_CFG_GP1_SPEED_10 (0 << 13) -#define MTK_MDIO_CFG_GP1_SPEED_100 (1 << 13) -#define MTK_MDIO_CFG_GP1_SPEED_1000 (2 << 13) -#define MTK_MDIO_CFG_GP1_DUPLEX BIT(12) -#define MTK_MDIO_CFG_GP1_FC_TX BIT(11) -#define MTK_MDIO_CFG_GP1_FC_RX BIT(10) -#define MTK_MDIO_CFG_GP1_LNK_DWN BIT(9) -#define MTK_MDIO_CFG_GP1_AN_FAIL BIT(8) -#define MTK_MDIO_CFG_MDC_CLK_DIV_1 (0 << 6) -#define MTK_MDIO_CFG_MDC_CLK_DIV_2 (1 << 6) -#define MTK_MDIO_CFG_MDC_CLK_DIV_4 (2 << 6) -#define MTK_MDIO_CFG_MDC_CLK_DIV_8 (3 << 6) -#define MTK_MDIO_CFG_TURBO_MII_FREQ BIT(5) -#define MTK_MDIO_CFG_TURBO_MII_MODE BIT(4) -#define MTK_MDIO_CFG_RX_CLK_SKEW_0 (0 << 2) -#define MTK_MDIO_CFG_RX_CLK_SKEW_200 (1 << 2) -#define MTK_MDIO_CFG_RX_CLK_SKEW_400 (2 << 2) -#define MTK_MDIO_CFG_RX_CLK_SKEW_INV (3 << 2) -#define MTK_MDIO_CFG_TX_CLK_SKEW_0 0 -#define MTK_MDIO_CFG_TX_CLK_SKEW_200 1 -#define MTK_MDIO_CFG_TX_CLK_SKEW_400 2 -#define MTK_MDIO_CFG_TX_CLK_SKEW_INV 3 - -/* uni-cast port */ -#define MTK_GDM1_JMB_LEN_MASK 0xf -#define MTK_GDM1_JMB_LEN_SHIFT 28 -#define MTK_GDM1_ICS_EN BIT(22) -#define MTK_GDM1_TCS_EN BIT(21) -#define MTK_GDM1_UCS_EN BIT(20) -#define MTK_GDM1_JMB_EN BIT(19) -#define MTK_GDM1_STRPCRC BIT(16) -#define MTK_GDM1_UFRC_P_CPU (0 << 12) -#define MTK_GDM1_UFRC_P_GDMA1 (1 << 12) -#define MTK_GDM1_UFRC_P_PPE (6 << 12) - -/* checksums */ -#define MTK_ICS_GEN_EN BIT(2) -#define MTK_UCS_GEN_EN BIT(1) -#define MTK_TCS_GEN_EN BIT(0) - -/* dma mode */ -#define MTK_PDMA BIT(0) -#define MTK_QDMA BIT(1) -#define MTK_PDMA_RX_QDMA_TX (MTK_PDMA | MTK_QDMA) - -/* dma ring */ -#define MTK_PST_DRX_IDX0 BIT(16) -#define MTK_PST_DTX_IDX3 BIT(3) -#define MTK_PST_DTX_IDX2 BIT(2) -#define MTK_PST_DTX_IDX1 BIT(1) -#define MTK_PST_DTX_IDX0 BIT(0) - -#define MTK_RX_2B_OFFSET BIT(31) -#define MTK_TX_WB_DDONE BIT(6) -#define MTK_RX_DMA_BUSY BIT(3) -#define MTK_TX_DMA_BUSY BIT(1) -#define MTK_RX_DMA_EN BIT(2) -#define MTK_TX_DMA_EN BIT(0) - -#define MTK_PDMA_SIZE_4DWORDS (0 << 4) -#define MTK_PDMA_SIZE_8DWORDS (1 << 4) -#define MTK_PDMA_SIZE_16DWORDS (2 << 4) - -#define MTK_US_CYC_CNT_MASK 0xff -#define MTK_US_CYC_CNT_SHIFT 0x8 -#define MTK_US_CYC_CNT_DIVISOR 1000000 - -/* PDMA descriptor rxd2 */ -#define RX_DMA_DONE BIT(31) -#define RX_DMA_LSO BIT(30) -#define RX_DMA_PLEN0(_x) (((_x) & 0x3fff) << 16) -#define RX_DMA_GET_PLEN0(_x) (((_x) >> 16) & 0x3fff) -#define RX_DMA_TAG BIT(15) - -/* PDMA descriptor rxd3 */ -#define RX_DMA_TPID(_x) (((_x) >> 16) & 0xffff) -#define RX_DMA_VID(_x) ((_x) & 0xfff) - -/* PDMA descriptor rxd4 */ -#define RX_DMA_L4VALID BIT(30) -#define RX_DMA_FPORT_SHIFT 19 -#define RX_DMA_FPORT_MASK 0x7 - -struct mtk_rx_dma { - unsigned int rxd1; - unsigned int rxd2; - unsigned int rxd3; - unsigned int rxd4; -} __packed __aligned(4); - -/* PDMA tx descriptor bits */ -#define TX_DMA_BUF_LEN 0x3fff -#define TX_DMA_PLEN0_MASK (TX_DMA_BUF_LEN << 16) -#define TX_DMA_PLEN0(_x) (((_x) & TX_DMA_BUF_LEN) << 16) -#define TX_DMA_PLEN1(_x) ((_x) & TX_DMA_BUF_LEN) -#define TX_DMA_GET_PLEN0(_x) (((_x) >> 16) & TX_DMA_BUF_LEN) -#define TX_DMA_GET_PLEN1(_x) ((_x) & TX_DMA_BUF_LEN) -#define TX_DMA_LS1 BIT(14) -#define TX_DMA_LS0 BIT(30) -#define TX_DMA_DONE BIT(31) -#define TX_DMA_FPORT_SHIFT 25 -#define TX_DMA_FPORT_MASK 0x7 -#define TX_DMA_INS_VLAN_MT7621 BIT(16) -#define TX_DMA_INS_VLAN BIT(7) -#define TX_DMA_INS_PPPOE BIT(12) -#define TX_DMA_TAG BIT(15) -#define TX_DMA_TAG_MASK BIT(15) -#define TX_DMA_QN(_x) ((_x) << 16) -#define TX_DMA_PN(_x) ((_x) << 24) -#define TX_DMA_QN_MASK TX_DMA_QN(0x7) -#define TX_DMA_PN_MASK TX_DMA_PN(0x7) -#define TX_DMA_UDF BIT(20) -#define TX_DMA_CHKSUM (0x7 << 29) -#define TX_DMA_TSO BIT(28) -#define TX_DMA_DESP4_DEF (TX_DMA_QN(3) | TX_DMA_PN(1)) - -/* frame engine counters */ -#define MTK_PPE_AC_BCNT0 (MTK_CMTABLE_OFFSET + 0x00) -#define MTK_GDMA1_TX_GBCNT (MTK_CMTABLE_OFFSET + 0x300) -#define MTK_GDMA2_TX_GBCNT (MTK_GDMA1_TX_GBCNT + 0x40) - -/* phy device flags */ -#define MTK_PHY_FLAG_PORT BIT(0) -#define MTK_PHY_FLAG_ATTACH BIT(1) - -struct mtk_tx_dma { - unsigned int txd1; - unsigned int txd2; - unsigned int txd3; - unsigned int txd4; -} __packed __aligned(4); - -struct mtk_eth; -struct mtk_mac; - -/* manage the attached phys */ -struct mtk_phy { - spinlock_t lock; - - struct phy_device *phy[8]; - struct device_node *phy_node[8]; - const __be32 *phy_fixed[8]; - int duplex[8]; - int speed[8]; - int tx_fc[8]; - int rx_fc[8]; - int (*connect)(struct mtk_mac *mac); - void (*disconnect)(struct mtk_mac *mac); - void (*start)(struct mtk_mac *mac); - void (*stop)(struct mtk_mac *mac); -}; - -/* struct mtk_soc_data - the structure that holds the SoC specific data - * @reg_table: Some of the legacy registers changed their location - * over time. Their offsets are stored in this table - * - * @init_data: Some features depend on the silicon revision. This - * callback allows runtime modification of the content of - * this struct - * @reset_fe: This callback is used to trigger the reset of the frame - * engine - * @set_mac: This callback is used to set the unicast mac address - * filter - * @fwd_config: This callback is used to setup the forward config - * register of the MAC - * @switch_init: This callback is used to bring up the switch core - * @port_init: Some SoCs have ports that can be router to a switch port - * or an external PHY. This callback is used to setup these - * ports. - * @has_carrier: This callback allows driver to check if there is a cable - * attached. - * @mdio_init: This callbck is used to setup the MDIO bus if one is - * present - * @mdio_cleanup: This callback is used to cleanup the MDIO state. - * @mdio_write: This callback is used to write data to the MDIO bus. - * @mdio_read: This callback is used to write data to the MDIO bus. - * @mdio_adjust_link: This callback is used to apply the PHY settings. - * @piac_offset: the PIAC register has a different different base offset - * @hw_features: feature set depends on the SoC type - * @dma_ring_size: allow GBit SoCs to set bigger rings than FE SoCs - * @napi_weight: allow GBit SoCs to set bigger napi weight than FE SoCs - * @dma_type: SoCs is PDMA, QDMA or a mix of the 2 - * @pdma_glo_cfg: the default DMA configuration - * @rx_int: the TX interrupt bits used by the SoC - * @tx_int: the TX interrupt bits used by the SoC - * @status_int: the Status interrupt bits used by the SoC - * @checksum_bit: the bits used to turn on HW checksumming - * @txd4: default value of the TXD4 descriptor - * @mac_count: the number of MACs that the SoC has - * @new_stats: there is a old and new way to read hardware stats - * registers - * @jumbo_frame: does the SoC support jumbo frames ? - * @rx_2b_offset: tell the rx dma to offset the data by 2 bytes - * @rx_sg_dma: scatter gather support - * @padding_64b enable 64 bit padding - * @padding_bug: rt2880 has a padding bug - * @has_switch: does the SoC have a built-in switch - * - * Although all of the supported SoCs share the same basic functionality, there - * are several SoC specific functions and features that we need to support. This - * struct holds the SoC specific data so that the common core can figure out - * how to setup and use these differences. - */ -struct mtk_soc_data { - const u16 *reg_table; - - void (*init_data)(struct mtk_soc_data *data, struct net_device *netdev); - void (*reset_fe)(struct mtk_eth *eth); - void (*set_mac)(struct mtk_mac *mac, unsigned char *macaddr); - int (*fwd_config)(struct mtk_eth *eth); - int (*switch_init)(struct mtk_eth *eth); - void (*port_init)(struct mtk_eth *eth, struct mtk_mac *mac, - struct device_node *port); - int (*has_carrier)(struct mtk_eth *eth); - int (*mdio_init)(struct mtk_eth *eth); - void (*mdio_cleanup)(struct mtk_eth *eth); - int (*mdio_write)(struct mii_bus *bus, int phy_addr, int phy_reg, - u16 val); - int (*mdio_read)(struct mii_bus *bus, int phy_addr, int phy_reg); - void (*mdio_adjust_link)(struct mtk_eth *eth, int port); - u32 piac_offset; - netdev_features_t hw_features; - u32 dma_ring_size; - u32 napi_weight; - u32 dma_type; - u32 pdma_glo_cfg; - u32 rx_int; - u32 tx_int; - u32 status_int; - u32 checksum_bit; - u32 txd4; - u32 mac_count; - - u32 new_stats:1; - u32 jumbo_frame:1; - u32 rx_2b_offset:1; - u32 rx_sg_dma:1; - u32 padding_64b:1; - u32 padding_bug:1; - u32 has_switch:1; -}; - -#define MTK_STAT_OFFSET 0x40 - -/* struct mtk_hw_stats - the structure that holds the traffic statistics. - * @stats_lock: make sure that stats operations are atomic - * @reg_offset: the status register offset of the SoC - * @syncp: the refcount - * - * All of the supported SoCs have hardware counters for traffic statstics. - * Whenever the status IRQ triggers we can read the latest stats from these - * counters and store them in this struct. - */ -struct mtk_hw_stats { - spinlock_t stats_lock; - u32 reg_offset; - struct u64_stats_sync syncp; - - u64 tx_bytes; - u64 tx_packets; - u64 tx_skip; - u64 tx_collisions; - u64 rx_bytes; - u64 rx_packets; - u64 rx_overflow; - u64 rx_fcs_errors; - u64 rx_short_errors; - u64 rx_long_errors; - u64 rx_checksum_errors; - u64 rx_flow_control_packets; -}; - -/* PDMA descriptor can point at 1-2 segments. This enum allows us to track how - * memory was allocated so that it can be freed properly - */ -enum mtk_tx_flags { - MTK_TX_FLAGS_SINGLE0 = 0x01, - MTK_TX_FLAGS_PAGE0 = 0x02, - MTK_TX_FLAGS_PAGE1 = 0x04, -}; - -/* struct mtk_tx_buf - This struct holds the pointers to the memory pointed at - * by the TX descriptor s - * @skb: The SKB pointer of the packet being sent - * @dma_addr0: The base addr of the first segment - * @dma_len0: The length of the first segment - * @dma_addr1: The base addr of the second segment - * @dma_len1: The length of the second segment - */ -struct mtk_tx_buf { - struct sk_buff *skb; - u32 flags; - DEFINE_DMA_UNMAP_ADDR(dma_addr0); - DEFINE_DMA_UNMAP_LEN(dma_len0); - DEFINE_DMA_UNMAP_ADDR(dma_addr1); - DEFINE_DMA_UNMAP_LEN(dma_len1); -}; - -/* struct mtk_tx_ring - This struct holds info describing a TX ring - * @tx_dma: The descriptor ring - * @tx_buf: The memory pointed at by the ring - * @tx_phys: The physical addr of tx_buf - * @tx_next_free: Pointer to the next free descriptor - * @tx_last_free: Pointer to the last free descriptor - * @tx_thresh: The threshold of minimum amount of free descriptors - * @tx_map: Callback to map a new packet into the ring - * @tx_poll: Callback for the housekeeping function - * @tx_clean: Callback for the cleanup function - * @tx_ring_size: How many descriptors are in the ring - * @tx_free_idx: The index of th next free descriptor - * @tx_next_idx: QDMA uses a linked list. This element points to the next - * free descriptor in the list - * @tx_free_count: QDMA uses a linked list. Track how many free descriptors - * are present - */ -struct mtk_tx_ring { - struct mtk_tx_dma *tx_dma; - struct mtk_tx_buf *tx_buf; - dma_addr_t tx_phys; - struct mtk_tx_dma *tx_next_free; - struct mtk_tx_dma *tx_last_free; - u16 tx_thresh; - int (*tx_map)(struct sk_buff *skb, struct net_device *dev, int tx_num, - struct mtk_tx_ring *ring, bool gso); - int (*tx_poll)(struct mtk_eth *eth, int budget, bool *tx_again); - void (*tx_clean)(struct mtk_eth *eth); - - /* PDMA only */ - u16 tx_ring_size; - u16 tx_free_idx; - - /* QDMA only */ - u16 tx_next_idx; - atomic_t tx_free_count; -}; - -/* struct mtk_rx_ring - This struct holds info describing a RX ring - * @rx_dma: The descriptor ring - * @rx_data: The memory pointed at by the ring - * @trx_phys: The physical addr of rx_buf - * @rx_ring_size: How many descriptors are in the ring - * @rx_buf_size: The size of each packet buffer - * @rx_calc_idx: The current head of ring - */ -struct mtk_rx_ring { - struct mtk_rx_dma *rx_dma; - u8 **rx_data; - dma_addr_t rx_phys; - u16 rx_ring_size; - u16 frag_size; - u16 rx_buf_size; - u16 rx_calc_idx; -}; - -/* currently no SoC has more than 2 macs */ -#define MTK_MAX_DEVS 2 - -/* struct mtk_eth - This is the main datasructure for holding the state - * of the driver - * @dev: The device pointer - * @base: The mapped register i/o base - * @page_lock: Make sure that register operations are atomic - * @soc: pointer to our SoC specific data - * @dummy_dev: we run 2 netdevs on 1 physical DMA ring and need a - * dummy for NAPI to work - * @netdev: The netdev instances - * @mac: Each netdev is linked to a physical MAC - * @switch_np: The phandle for the switch - * @irq: The IRQ that we are using - * @msg_enable: Ethtool msg level - * @ysclk: The sysclk rate - neeed for calibration - * @ethsys: The register map pointing at the range used to setup - * MII modes - * @dma_refcnt: track how many netdevs are using the DMA engine - * @tx_ring: Pointer to the memore holding info about the TX ring - * @rx_ring: Pointer to the memore holding info about the RX ring - * @rx_napi: The NAPI struct - * @scratch_ring: Newer SoCs need memory for a second HW managed TX ring - * @scratch_head: The scratch memory that scratch_ring points to. - * @phy: Info about the attached PHYs - * @mii_bus: If there is a bus we need to create an instance for it - * @link: Track if the ports have a physical link - * @sw_priv: Pointer to the switches private data - * @vlan_map: RX VID tracking - */ - -struct mtk_eth { - struct device *dev; - void __iomem *base; - spinlock_t page_lock; - struct mtk_soc_data *soc; - struct net_device dummy_dev; - struct net_device *netdev[MTK_MAX_DEVS]; - struct mtk_mac *mac[MTK_MAX_DEVS]; - struct device_node *switch_np; - int irq; - u32 msg_enable; - unsigned long sysclk; - struct regmap *ethsys; - atomic_t dma_refcnt; - struct mtk_tx_ring tx_ring; - struct mtk_rx_ring rx_ring[2]; - struct napi_struct rx_napi; - struct mtk_tx_dma *scratch_ring; - void *scratch_head; - struct mtk_phy *phy; - struct mii_bus *mii_bus; - int link[8]; - void *sw_priv; - unsigned long vlan_map; -}; - -/* struct mtk_mac - the structure that holds the info about the MACs of the - * SoC - * @id: The number of the MAC - * @of_node: Our devicetree node - * @hw: Backpointer to our main datastruture - * @hw_stats: Packet statistics counter - * @phy_dev: The attached PHY if available - * @phy_flags: The PHYs flags - * @pending_work: The workqueue used to reset the dma ring - */ -struct mtk_mac { - int id; - struct device_node *of_node; - struct mtk_eth *hw; - struct mtk_hw_stats *hw_stats; - struct phy_device *phy_dev; - u32 phy_flags; - struct work_struct pending_work; -}; - -/* the struct describing the SoC. these are declared in the soc_xyz.c files */ -extern const struct of_device_id of_mtk_match[]; - -/* read the hardware status register */ -void mtk_stats_update_mac(struct mtk_mac *mac); - -/* default checksum setup handler */ -void mtk_reset(struct mtk_eth *eth, u32 reset_bits); - -/* register i/o wrappers */ -void mtk_w32(struct mtk_eth *eth, u32 val, unsigned int reg); -u32 mtk_r32(struct mtk_eth *eth, unsigned int reg); - -/* default clock calibration handler */ -int mtk_set_clock_cycle(struct mtk_eth *eth); - -/* default checksum setup handler */ -void mtk_csum_config(struct mtk_eth *eth); - -/* default forward config handler */ -void mtk_fwd_config(struct mtk_eth *eth); - -#endif /* MTK_ETH_H */ diff --git a/drivers/staging/mt7621-eth/soc_mt7621.c b/drivers/staging/mt7621-eth/soc_mt7621.c deleted file mode 100644 index 5d63b5d96f6b..000000000000 --- a/drivers/staging/mt7621-eth/soc_mt7621.c +++ /dev/null @@ -1,161 +0,0 @@ -/* This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org> - * Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org> - * Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com> - */ - -#include <linux/module.h> -#include <linux/platform_device.h> -#include <linux/if_vlan.h> -#include <linux/of_net.h> - -#include <asm/mach-ralink/ralink_regs.h> - -#include "mtk_eth_soc.h" -#include "gsw_mt7620.h" -#include "mdio.h" - -#define MT7620_CDMA_CSG_CFG 0x400 -#define MT7621_CDMP_IG_CTRL (MT7620_CDMA_CSG_CFG + 0x00) -#define MT7621_CDMP_EG_CTRL (MT7620_CDMA_CSG_CFG + 0x04) -#define MT7621_RESET_FE BIT(6) -#define MT7621_L4_VALID BIT(24) - -#define MT7621_TX_DMA_UDF BIT(19) - -#define CDMA_ICS_EN BIT(2) -#define CDMA_UCS_EN BIT(1) -#define CDMA_TCS_EN BIT(0) - -#define GDMA_ICS_EN BIT(22) -#define GDMA_TCS_EN BIT(21) -#define GDMA_UCS_EN BIT(20) - -/* frame engine counters */ -#define MT7621_REG_MIB_OFFSET 0x2000 -#define MT7621_PPE_AC_BCNT0 (MT7621_REG_MIB_OFFSET + 0x00) -#define MT7621_GDM1_TX_GBCNT (MT7621_REG_MIB_OFFSET + 0x400) -#define MT7621_GDM2_TX_GBCNT (MT7621_GDM1_TX_GBCNT + 0x40) - -#define GSW_REG_GDMA1_MAC_ADRL 0x508 -#define GSW_REG_GDMA1_MAC_ADRH 0x50C -#define GSW_REG_GDMA2_MAC_ADRL 0x1508 -#define GSW_REG_GDMA2_MAC_ADRH 0x150C - -#define MT7621_MTK_RST_GL 0x04 -#define MT7620_MTK_INT_STATUS2 0x08 - -/* MTK_INT_STATUS reg on mt7620 define CNT_GDM1_AF at BIT(29) - * but after test it should be BIT(13). - */ -#define MT7621_MTK_GDM1_AF BIT(28) -#define MT7621_MTK_GDM2_AF BIT(29) - -static const u16 mt7621_reg_table[MTK_REG_COUNT] = { - [MTK_REG_PDMA_GLO_CFG] = RT5350_PDMA_GLO_CFG, - [MTK_REG_PDMA_RST_CFG] = RT5350_PDMA_RST_CFG, - [MTK_REG_DLY_INT_CFG] = RT5350_DLY_INT_CFG, - [MTK_REG_TX_BASE_PTR0] = RT5350_TX_BASE_PTR0, - [MTK_REG_TX_MAX_CNT0] = RT5350_TX_MAX_CNT0, - [MTK_REG_TX_CTX_IDX0] = RT5350_TX_CTX_IDX0, - [MTK_REG_TX_DTX_IDX0] = RT5350_TX_DTX_IDX0, - [MTK_REG_RX_BASE_PTR0] = RT5350_RX_BASE_PTR0, - [MTK_REG_RX_MAX_CNT0] = RT5350_RX_MAX_CNT0, - [MTK_REG_RX_CALC_IDX0] = RT5350_RX_CALC_IDX0, - [MTK_REG_RX_DRX_IDX0] = RT5350_RX_DRX_IDX0, - [MTK_REG_MTK_INT_ENABLE] = RT5350_MTK_INT_ENABLE, - [MTK_REG_MTK_INT_STATUS] = RT5350_MTK_INT_STATUS, - [MTK_REG_MTK_DMA_VID_BASE] = 0, - [MTK_REG_MTK_COUNTER_BASE] = MT7621_GDM1_TX_GBCNT, - [MTK_REG_MTK_RST_GL] = MT7621_MTK_RST_GL, - [MTK_REG_MTK_INT_STATUS2] = MT7620_MTK_INT_STATUS2, -}; - -static void mt7621_mtk_reset(struct mtk_eth *eth) -{ - mtk_reset(eth, MT7621_RESET_FE); -} - -static int mt7621_fwd_config(struct mtk_eth *eth) -{ - /* Setup GMAC1 only, there is no support for GMAC2 yet */ - mtk_w32(eth, mtk_r32(eth, MT7620_GDMA1_FWD_CFG) & ~0xffff, - MT7620_GDMA1_FWD_CFG); - - /* Enable RX checksum */ - mtk_w32(eth, mtk_r32(eth, MT7620_GDMA1_FWD_CFG) | (GDMA_ICS_EN | - GDMA_TCS_EN | GDMA_UCS_EN), - MT7620_GDMA1_FWD_CFG); - - /* Enable RX VLan Offloading */ - mtk_w32(eth, 0, MT7621_CDMP_EG_CTRL); - - return 0; -} - -static void mt7621_set_mac(struct mtk_mac *mac, unsigned char *hwaddr) -{ - unsigned long flags; - - spin_lock_irqsave(&mac->hw->page_lock, flags); - if (mac->id == 0) { - mtk_w32(mac->hw, (hwaddr[0] << 8) | hwaddr[1], - GSW_REG_GDMA1_MAC_ADRH); - mtk_w32(mac->hw, (hwaddr[2] << 24) | (hwaddr[3] << 16) | - (hwaddr[4] << 8) | hwaddr[5], - GSW_REG_GDMA1_MAC_ADRL); - } - if (mac->id == 1) { - mtk_w32(mac->hw, (hwaddr[0] << 8) | hwaddr[1], - GSW_REG_GDMA2_MAC_ADRH); - mtk_w32(mac->hw, (hwaddr[2] << 24) | (hwaddr[3] << 16) | - (hwaddr[4] << 8) | hwaddr[5], - GSW_REG_GDMA2_MAC_ADRL); - } - spin_unlock_irqrestore(&mac->hw->page_lock, flags); -} - -static struct mtk_soc_data mt7621_data = { - .hw_features = NETIF_F_IP_CSUM | NETIF_F_RXCSUM | - NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | - NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 | - NETIF_F_IPV6_CSUM, - .dma_type = MTK_PDMA, - .dma_ring_size = 256, - .napi_weight = 64, - .new_stats = 1, - .padding_64b = 1, - .rx_2b_offset = 1, - .rx_sg_dma = 1, - .has_switch = 1, - .mac_count = 2, - .reset_fe = mt7621_mtk_reset, - .set_mac = mt7621_set_mac, - .fwd_config = mt7621_fwd_config, - .switch_init = mtk_gsw_init, - .reg_table = mt7621_reg_table, - .pdma_glo_cfg = MTK_PDMA_SIZE_16DWORDS, - .rx_int = RT5350_RX_DONE_INT, - .tx_int = RT5350_TX_DONE_INT, - .status_int = MT7621_MTK_GDM1_AF | MT7621_MTK_GDM2_AF, - .checksum_bit = MT7621_L4_VALID, - .has_carrier = mt7620_has_carrier, - .mdio_read = mt7620_mdio_read, - .mdio_write = mt7620_mdio_write, - .mdio_adjust_link = mt7620_mdio_link_adjust, -}; - -const struct of_device_id of_mtk_match[] = { - { .compatible = "mediatek,mt7621-eth", .data = &mt7621_data }, - {}, -}; - -MODULE_DEVICE_TABLE(of, of_mtk_match); diff --git a/drivers/staging/mt7621-pci/Kconfig b/drivers/staging/mt7621-pci/Kconfig index d33533872a16..c8fa17cfa807 100644 --- a/drivers/staging/mt7621-pci/Kconfig +++ b/drivers/staging/mt7621-pci/Kconfig @@ -1,6 +1,7 @@ config PCI_MT7621 tristate "MediaTek MT7621 PCI Controller" depends on RALINK + depends on PCI select PCI_DRIVERS_GENERIC help This selects a driver for the MediaTek MT7621 PCI Controller. diff --git a/drivers/staging/octeon/ethernet-mdio.c b/drivers/staging/octeon/ethernet-mdio.c index d6248eecf123..2aee64fdaec5 100644 --- a/drivers/staging/octeon/ethernet-mdio.c +++ b/drivers/staging/octeon/ethernet-mdio.c @@ -163,7 +163,7 @@ int cvm_oct_phy_setup_device(struct net_device *dev) goto no_phy; phydev = of_phy_connect(dev, phy_node, cvm_oct_adjust_link, 0, - PHY_INTERFACE_MODE_GMII); + priv->phy_mode); of_node_put(phy_node); if (!phydev) diff --git a/drivers/staging/octeon/ethernet.c b/drivers/staging/octeon/ethernet.c index ce61c5670ef6..986db76705cc 100644 --- a/drivers/staging/octeon/ethernet.c +++ b/drivers/staging/octeon/ethernet.c @@ -653,14 +653,37 @@ static struct device_node *cvm_oct_node_for_port(struct device_node *pip, return np; } -static void cvm_set_rgmii_delay(struct device_node *np, int iface, int port) +static void cvm_set_rgmii_delay(struct octeon_ethernet *priv, int iface, + int port) { + struct device_node *np = priv->of_node; u32 delay_value; + bool rx_delay; + bool tx_delay; - if (!of_property_read_u32(np, "rx-delay", &delay_value)) + /* By default, both RX/TX delay is enabled in + * __cvmx_helper_rgmii_enable(). + */ + rx_delay = true; + tx_delay = true; + + if (!of_property_read_u32(np, "rx-delay", &delay_value)) { cvmx_write_csr(CVMX_ASXX_RX_CLK_SETX(port, iface), delay_value); - if (!of_property_read_u32(np, "tx-delay", &delay_value)) + rx_delay = delay_value > 0; + } + if (!of_property_read_u32(np, "tx-delay", &delay_value)) { cvmx_write_csr(CVMX_ASXX_TX_CLK_SETX(port, iface), delay_value); + tx_delay = delay_value > 0; + } + + if (!rx_delay && !tx_delay) + priv->phy_mode = PHY_INTERFACE_MODE_RGMII_ID; + else if (!rx_delay) + priv->phy_mode = PHY_INTERFACE_MODE_RGMII_RXID; + else if (!tx_delay) + priv->phy_mode = PHY_INTERFACE_MODE_RGMII_TXID; + else + priv->phy_mode = PHY_INTERFACE_MODE_RGMII; } static int cvm_oct_probe(struct platform_device *pdev) @@ -825,6 +848,7 @@ static int cvm_oct_probe(struct platform_device *pdev) priv->port = port; priv->queue = cvmx_pko_get_base_queue(priv->port); priv->fau = fau - cvmx_pko_get_num_queues(port) * 4; + priv->phy_mode = PHY_INTERFACE_MODE_NA; for (qos = 0; qos < 16; qos++) skb_queue_head_init(&priv->tx_free_list[qos]); for (qos = 0; qos < cvmx_pko_get_num_queues(port); @@ -856,6 +880,7 @@ static int cvm_oct_probe(struct platform_device *pdev) break; case CVMX_HELPER_INTERFACE_MODE_SGMII: + priv->phy_mode = PHY_INTERFACE_MODE_SGMII; dev->netdev_ops = &cvm_oct_sgmii_netdev_ops; strcpy(dev->name, "eth%d"); break; @@ -865,11 +890,16 @@ static int cvm_oct_probe(struct platform_device *pdev) strcpy(dev->name, "spi%d"); break; - case CVMX_HELPER_INTERFACE_MODE_RGMII: case CVMX_HELPER_INTERFACE_MODE_GMII: + priv->phy_mode = PHY_INTERFACE_MODE_GMII; + dev->netdev_ops = &cvm_oct_rgmii_netdev_ops; + strcpy(dev->name, "eth%d"); + break; + + case CVMX_HELPER_INTERFACE_MODE_RGMII: dev->netdev_ops = &cvm_oct_rgmii_netdev_ops; strcpy(dev->name, "eth%d"); - cvm_set_rgmii_delay(priv->of_node, interface, + cvm_set_rgmii_delay(priv, interface, port_index); break; } diff --git a/drivers/staging/octeon/octeon-ethernet.h b/drivers/staging/octeon/octeon-ethernet.h index 4a07e7f43d12..be570d33685a 100644 --- a/drivers/staging/octeon/octeon-ethernet.h +++ b/drivers/staging/octeon/octeon-ethernet.h @@ -12,7 +12,7 @@ #define OCTEON_ETHERNET_H #include <linux/of.h> - +#include <linux/phy.h> #include <asm/octeon/cvmx-helper-board.h> /** @@ -33,6 +33,8 @@ struct octeon_ethernet { * cvmx_helper_interface_mode_t */ int imode; + /* PHY mode */ + phy_interface_t phy_mode; /* List of outstanding tx buffers per queue */ struct sk_buff_head tx_free_list[16]; unsigned int last_speed; diff --git a/drivers/staging/olpc_dcon/olpc_dcon_xo_1.c b/drivers/staging/olpc_dcon/olpc_dcon_xo_1.c index 80b8d4153414..a54286498a47 100644 --- a/drivers/staging/olpc_dcon/olpc_dcon_xo_1.c +++ b/drivers/staging/olpc_dcon/olpc_dcon_xo_1.c @@ -45,7 +45,7 @@ static int dcon_init_xo_1(struct dcon_priv *dcon) { unsigned char lob; int ret, i; - struct dcon_gpio *pin = &gpios_asis[0]; + const struct dcon_gpio *pin = &gpios_asis[0]; for (i = 0; i < ARRAY_SIZE(gpios_asis); i++) { gpios[i] = devm_gpiod_get(&dcon->client->dev, pin[i].name, diff --git a/drivers/staging/rtl8188eu/core/rtw_xmit.c b/drivers/staging/rtl8188eu/core/rtw_xmit.c index 1723a47a96b4..952f2ab51347 100644 --- a/drivers/staging/rtl8188eu/core/rtw_xmit.c +++ b/drivers/staging/rtl8188eu/core/rtw_xmit.c @@ -174,7 +174,9 @@ s32 _rtw_init_xmit_priv(struct xmit_priv *pxmitpriv, struct adapter *padapter) pxmitpriv->free_xmit_extbuf_cnt = num_xmit_extbuf; - rtw_alloc_hwxmits(padapter); + res = rtw_alloc_hwxmits(padapter); + if (res == _FAIL) + goto exit; rtw_init_hwxmits(pxmitpriv->hwxmits, pxmitpriv->hwxmit_entry); for (i = 0; i < 4; i++) @@ -1503,7 +1505,7 @@ exit: return res; } -void rtw_alloc_hwxmits(struct adapter *padapter) +s32 rtw_alloc_hwxmits(struct adapter *padapter) { struct hw_xmit *hwxmits; struct xmit_priv *pxmitpriv = &padapter->xmitpriv; @@ -1512,6 +1514,8 @@ void rtw_alloc_hwxmits(struct adapter *padapter) pxmitpriv->hwxmits = kcalloc(pxmitpriv->hwxmit_entry, sizeof(struct hw_xmit), GFP_KERNEL); + if (!pxmitpriv->hwxmits) + return _FAIL; hwxmits = pxmitpriv->hwxmits; @@ -1519,6 +1523,7 @@ void rtw_alloc_hwxmits(struct adapter *padapter) hwxmits[1] .sta_queue = &pxmitpriv->vi_pending; hwxmits[2] .sta_queue = &pxmitpriv->be_pending; hwxmits[3] .sta_queue = &pxmitpriv->bk_pending; + return _SUCCESS; } void rtw_free_hwxmits(struct adapter *padapter) diff --git a/drivers/staging/rtl8188eu/include/rtw_xmit.h b/drivers/staging/rtl8188eu/include/rtw_xmit.h index 788f59c74ea1..ba7e15fbde72 100644 --- a/drivers/staging/rtl8188eu/include/rtw_xmit.h +++ b/drivers/staging/rtl8188eu/include/rtw_xmit.h @@ -336,7 +336,7 @@ s32 rtw_txframes_sta_ac_pending(struct adapter *padapter, void rtw_init_hwxmits(struct hw_xmit *phwxmit, int entry); s32 _rtw_init_xmit_priv(struct xmit_priv *pxmitpriv, struct adapter *padapter); void _rtw_free_xmit_priv(struct xmit_priv *pxmitpriv); -void rtw_alloc_hwxmits(struct adapter *padapter); +s32 rtw_alloc_hwxmits(struct adapter *padapter); void rtw_free_hwxmits(struct adapter *padapter); s32 rtw_xmit(struct adapter *padapter, struct sk_buff **pkt); diff --git a/drivers/staging/rtl8712/rtl8712_cmd.c b/drivers/staging/rtl8712/rtl8712_cmd.c index 1920d02f7c9f..8c36acedf507 100644 --- a/drivers/staging/rtl8712/rtl8712_cmd.c +++ b/drivers/staging/rtl8712/rtl8712_cmd.c @@ -147,17 +147,9 @@ static u8 write_macreg_hdl(struct _adapter *padapter, u8 *pbuf) static u8 read_bbreg_hdl(struct _adapter *padapter, u8 *pbuf) { - u32 val; - void (*pcmd_callback)(struct _adapter *dev, struct cmd_obj *pcmd); struct cmd_obj *pcmd = (struct cmd_obj *)pbuf; - if (pcmd->rsp && pcmd->rspsz > 0) - memcpy(pcmd->rsp, (u8 *)&val, pcmd->rspsz); - pcmd_callback = cmd_callback[pcmd->cmdcode].callback; - if (!pcmd_callback) - r8712_free_cmd_obj(pcmd); - else - pcmd_callback(padapter, pcmd); + r8712_free_cmd_obj(pcmd); return H2C_SUCCESS; } diff --git a/drivers/staging/rtl8712/rtl8712_cmd.h b/drivers/staging/rtl8712/rtl8712_cmd.h index 92fb77666d44..1ef86b8c592f 100644 --- a/drivers/staging/rtl8712/rtl8712_cmd.h +++ b/drivers/staging/rtl8712/rtl8712_cmd.h @@ -140,7 +140,7 @@ enum rtl8712_h2c_cmd { static struct _cmd_callback cmd_callback[] = { {GEN_CMD_CODE(_Read_MACREG), NULL}, /*0*/ {GEN_CMD_CODE(_Write_MACREG), NULL}, - {GEN_CMD_CODE(_Read_BBREG), &r8712_getbbrfreg_cmdrsp_callback}, + {GEN_CMD_CODE(_Read_BBREG), NULL}, {GEN_CMD_CODE(_Write_BBREG), NULL}, {GEN_CMD_CODE(_Read_RFREG), &r8712_getbbrfreg_cmdrsp_callback}, {GEN_CMD_CODE(_Write_RFREG), NULL}, /*5*/ diff --git a/drivers/staging/rtl8723bs/core/rtw_xmit.c b/drivers/staging/rtl8723bs/core/rtw_xmit.c index 094d61bcb469..b87f13a0b563 100644 --- a/drivers/staging/rtl8723bs/core/rtw_xmit.c +++ b/drivers/staging/rtl8723bs/core/rtw_xmit.c @@ -260,7 +260,9 @@ s32 _rtw_init_xmit_priv(struct xmit_priv *pxmitpriv, struct adapter *padapter) } } - rtw_alloc_hwxmits(padapter); + res = rtw_alloc_hwxmits(padapter); + if (res == _FAIL) + goto exit; rtw_init_hwxmits(pxmitpriv->hwxmits, pxmitpriv->hwxmit_entry); for (i = 0; i < 4; i++) { @@ -2144,7 +2146,7 @@ exit: return res; } -void rtw_alloc_hwxmits(struct adapter *padapter) +s32 rtw_alloc_hwxmits(struct adapter *padapter) { struct hw_xmit *hwxmits; struct xmit_priv *pxmitpriv = &padapter->xmitpriv; @@ -2155,10 +2157,8 @@ void rtw_alloc_hwxmits(struct adapter *padapter) pxmitpriv->hwxmits = rtw_zmalloc(sizeof(struct hw_xmit) * pxmitpriv->hwxmit_entry); - if (pxmitpriv->hwxmits == NULL) { - DBG_871X("alloc hwxmits fail!...\n"); - return; - } + if (!pxmitpriv->hwxmits) + return _FAIL; hwxmits = pxmitpriv->hwxmits; @@ -2204,7 +2204,7 @@ void rtw_alloc_hwxmits(struct adapter *padapter) } - + return _SUCCESS; } void rtw_free_hwxmits(struct adapter *padapter) diff --git a/drivers/staging/rtl8723bs/include/rtw_xmit.h b/drivers/staging/rtl8723bs/include/rtw_xmit.h index 1b38b9182b31..37f42b2f22f1 100644 --- a/drivers/staging/rtl8723bs/include/rtw_xmit.h +++ b/drivers/staging/rtl8723bs/include/rtw_xmit.h @@ -487,7 +487,7 @@ s32 _rtw_init_xmit_priv(struct xmit_priv *pxmitpriv, struct adapter *padapter); void _rtw_free_xmit_priv (struct xmit_priv *pxmitpriv); -void rtw_alloc_hwxmits(struct adapter *padapter); +s32 rtw_alloc_hwxmits(struct adapter *padapter); void rtw_free_hwxmits(struct adapter *padapter); diff --git a/drivers/staging/rtlwifi/phydm/rtl_phydm.c b/drivers/staging/rtlwifi/phydm/rtl_phydm.c index 9930ed954abb..4cc77b2016e1 100644 --- a/drivers/staging/rtlwifi/phydm/rtl_phydm.c +++ b/drivers/staging/rtlwifi/phydm/rtl_phydm.c @@ -180,6 +180,8 @@ static int rtl_phydm_init_priv(struct rtl_priv *rtlpriv, rtlpriv->phydm.internal = kzalloc(sizeof(struct phy_dm_struct), GFP_KERNEL); + if (!rtlpriv->phydm.internal) + return 0; _rtl_phydm_init_com_info(rtlpriv, ic, params); diff --git a/drivers/staging/rtlwifi/rtl8822be/fw.c b/drivers/staging/rtlwifi/rtl8822be/fw.c index f061dd1382aa..cf6b7a80b753 100644 --- a/drivers/staging/rtlwifi/rtl8822be/fw.c +++ b/drivers/staging/rtlwifi/rtl8822be/fw.c @@ -743,6 +743,8 @@ void rtl8822be_set_fw_rsvdpagepkt(struct ieee80211_hw *hw, bool b_dl_finished) u1_rsvd_page_loc, 3); skb = dev_alloc_skb(totalpacketlen); + if (!skb) + return; memcpy((u8 *)skb_put(skb, totalpacketlen), &reserved_page_packet, totalpacketlen); diff --git a/drivers/staging/speakup/speakup_soft.c b/drivers/staging/speakup/speakup_soft.c index edff6ce85655..9d85a3a1af4c 100644 --- a/drivers/staging/speakup/speakup_soft.c +++ b/drivers/staging/speakup/speakup_soft.c @@ -210,12 +210,15 @@ static ssize_t softsynthx_read(struct file *fp, char __user *buf, size_t count, return -EINVAL; spin_lock_irqsave(&speakup_info.spinlock, flags); + synth_soft.alive = 1; while (1) { prepare_to_wait(&speakup_event, &wait, TASK_INTERRUPTIBLE); - if (!unicode) - synth_buffer_skip_nonlatin1(); - if (!synth_buffer_empty() || speakup_info.flushing) - break; + if (synth_current() == &synth_soft) { + if (!unicode) + synth_buffer_skip_nonlatin1(); + if (!synth_buffer_empty() || speakup_info.flushing) + break; + } spin_unlock_irqrestore(&speakup_info.spinlock, flags); if (fp->f_flags & O_NONBLOCK) { finish_wait(&speakup_event, &wait); @@ -235,6 +238,8 @@ static ssize_t softsynthx_read(struct file *fp, char __user *buf, size_t count, /* Keep 3 bytes available for a 16bit UTF-8-encoded character */ while (chars_sent <= count - bytes_per_ch) { + if (synth_current() != &synth_soft) + break; if (speakup_info.flushing) { speakup_info.flushing = 0; ch = '\x18'; @@ -331,7 +336,8 @@ static __poll_t softsynth_poll(struct file *fp, struct poll_table_struct *wait) poll_wait(fp, &speakup_event, wait); spin_lock_irqsave(&speakup_info.spinlock, flags); - if (!synth_buffer_empty() || speakup_info.flushing) + if (synth_current() == &synth_soft && + (!synth_buffer_empty() || speakup_info.flushing)) ret = EPOLLIN | EPOLLRDNORM; spin_unlock_irqrestore(&speakup_info.spinlock, flags); return ret; diff --git a/drivers/staging/speakup/spk_priv.h b/drivers/staging/speakup/spk_priv.h index c8e688878fc7..ac6a74883af4 100644 --- a/drivers/staging/speakup/spk_priv.h +++ b/drivers/staging/speakup/spk_priv.h @@ -74,6 +74,7 @@ int synth_request_region(unsigned long start, unsigned long n); int synth_release_region(unsigned long start, unsigned long n); int synth_add(struct spk_synth *in_synth); void synth_remove(struct spk_synth *in_synth); +struct spk_synth *synth_current(void); extern struct speakup_info_t speakup_info; diff --git a/drivers/staging/speakup/synth.c b/drivers/staging/speakup/synth.c index 25f259ee4ffc..3568bfb89912 100644 --- a/drivers/staging/speakup/synth.c +++ b/drivers/staging/speakup/synth.c @@ -481,4 +481,10 @@ void synth_remove(struct spk_synth *in_synth) } EXPORT_SYMBOL_GPL(synth_remove); +struct spk_synth *synth_current(void) +{ + return synth; +} +EXPORT_SYMBOL_GPL(synth_current); + short spk_punc_masks[] = { 0, SOME, MOST, PUNC, PUNC | B_SYM }; diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c index 804daf83be35..064d0db4c51e 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c @@ -3513,6 +3513,7 @@ static int vchiq_probe(struct platform_device *pdev) struct device_node *fw_node; const struct of_device_id *of_id; struct vchiq_drvdata *drvdata; + struct device *vchiq_dev; int err; of_id = of_match_node(vchiq_of_match, pdev->dev.of_node); @@ -3547,9 +3548,12 @@ static int vchiq_probe(struct platform_device *pdev) goto failed_platform_init; } - if (IS_ERR(device_create(vchiq_class, &pdev->dev, vchiq_devid, - NULL, "vchiq"))) + vchiq_dev = device_create(vchiq_class, &pdev->dev, vchiq_devid, NULL, + "vchiq"); + if (IS_ERR(vchiq_dev)) { + err = PTR_ERR(vchiq_dev); goto failed_device_create; + } vchiq_debugfs_init(); diff --git a/drivers/staging/vt6655/device_main.c b/drivers/staging/vt6655/device_main.c index b370985b58a1..c6bb4aaf9bd0 100644 --- a/drivers/staging/vt6655/device_main.c +++ b/drivers/staging/vt6655/device_main.c @@ -1033,8 +1033,6 @@ static void vnt_interrupt_process(struct vnt_private *priv) return; } - MACvIntDisable(priv->PortOffset); - spin_lock_irqsave(&priv->lock, flags); /* Read low level stats */ @@ -1122,8 +1120,6 @@ static void vnt_interrupt_process(struct vnt_private *priv) } spin_unlock_irqrestore(&priv->lock, flags); - - MACvIntEnable(priv->PortOffset, IMR_MASK_VALUE); } static void vnt_interrupt_work(struct work_struct *work) @@ -1133,14 +1129,17 @@ static void vnt_interrupt_work(struct work_struct *work) if (priv->vif) vnt_interrupt_process(priv); + + MACvIntEnable(priv->PortOffset, IMR_MASK_VALUE); } static irqreturn_t vnt_interrupt(int irq, void *arg) { struct vnt_private *priv = arg; - if (priv->vif) - schedule_work(&priv->interrupt_work); + schedule_work(&priv->interrupt_work); + + MACvIntDisable(priv->PortOffset); return IRQ_HANDLED; } diff --git a/drivers/tty/serial/ar933x_uart.c b/drivers/tty/serial/ar933x_uart.c index db5df3d54818..3bdd56a1021b 100644 --- a/drivers/tty/serial/ar933x_uart.c +++ b/drivers/tty/serial/ar933x_uart.c @@ -49,11 +49,6 @@ struct ar933x_uart_port { struct clk *clk; }; -static inline bool ar933x_uart_console_enabled(void) -{ - return IS_ENABLED(CONFIG_SERIAL_AR933X_CONSOLE); -} - static inline unsigned int ar933x_uart_read(struct ar933x_uart_port *up, int offset) { @@ -508,6 +503,7 @@ static const struct uart_ops ar933x_uart_ops = { .verify_port = ar933x_uart_verify_port, }; +#ifdef CONFIG_SERIAL_AR933X_CONSOLE static struct ar933x_uart_port * ar933x_console_ports[CONFIG_SERIAL_AR933X_NR_UARTS]; @@ -604,14 +600,7 @@ static struct console ar933x_uart_console = { .index = -1, .data = &ar933x_uart_driver, }; - -static void ar933x_uart_add_console_port(struct ar933x_uart_port *up) -{ - if (!ar933x_uart_console_enabled()) - return; - - ar933x_console_ports[up->port.line] = up; -} +#endif /* CONFIG_SERIAL_AR933X_CONSOLE */ static struct uart_driver ar933x_uart_driver = { .owner = THIS_MODULE, @@ -700,7 +689,9 @@ static int ar933x_uart_probe(struct platform_device *pdev) baud = ar933x_uart_get_baud(port->uartclk, 0, AR933X_UART_MAX_STEP); up->max_baud = min_t(unsigned int, baud, AR933X_UART_MAX_BAUD); - ar933x_uart_add_console_port(up); +#ifdef CONFIG_SERIAL_AR933X_CONSOLE + ar933x_console_ports[up->port.line] = up; +#endif ret = uart_add_one_port(&ar933x_uart_driver, &up->port); if (ret) @@ -749,8 +740,9 @@ static int __init ar933x_uart_init(void) { int ret; - if (ar933x_uart_console_enabled()) - ar933x_uart_driver.cons = &ar933x_uart_console; +#ifdef CONFIG_SERIAL_AR933X_CONSOLE + ar933x_uart_driver.cons = &ar933x_uart_console; +#endif ret = uart_register_driver(&ar933x_uart_driver); if (ret) diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c index 05147fe24343..0b4f36905321 100644 --- a/drivers/tty/serial/atmel_serial.c +++ b/drivers/tty/serial/atmel_serial.c @@ -166,6 +166,8 @@ struct atmel_uart_port { unsigned int pending_status; spinlock_t lock_suspended; + bool hd_start_rx; /* can start RX during half-duplex operation */ + /* ISO7816 */ unsigned int fidi_min; unsigned int fidi_max; @@ -231,6 +233,13 @@ static inline void atmel_uart_write_char(struct uart_port *port, u8 value) __raw_writeb(value, port->membase + ATMEL_US_THR); } +static inline int atmel_uart_is_half_duplex(struct uart_port *port) +{ + return ((port->rs485.flags & SER_RS485_ENABLED) && + !(port->rs485.flags & SER_RS485_RX_DURING_TX)) || + (port->iso7816.flags & SER_ISO7816_ENABLED); +} + #ifdef CONFIG_SERIAL_ATMEL_PDC static bool atmel_use_pdc_rx(struct uart_port *port) { @@ -608,10 +617,9 @@ static void atmel_stop_tx(struct uart_port *port) /* Disable interrupts */ atmel_uart_writel(port, ATMEL_US_IDR, atmel_port->tx_done_mask); - if (((port->rs485.flags & SER_RS485_ENABLED) && - !(port->rs485.flags & SER_RS485_RX_DURING_TX)) || - port->iso7816.flags & SER_ISO7816_ENABLED) + if (atmel_uart_is_half_duplex(port)) atmel_start_rx(port); + } /* @@ -628,9 +636,7 @@ static void atmel_start_tx(struct uart_port *port) return; if (atmel_use_pdc_tx(port) || atmel_use_dma_tx(port)) - if (((port->rs485.flags & SER_RS485_ENABLED) && - !(port->rs485.flags & SER_RS485_RX_DURING_TX)) || - port->iso7816.flags & SER_ISO7816_ENABLED) + if (atmel_uart_is_half_duplex(port)) atmel_stop_rx(port); if (atmel_use_pdc_tx(port)) @@ -928,11 +934,14 @@ static void atmel_complete_tx_dma(void *arg) */ if (!uart_circ_empty(xmit)) atmel_tasklet_schedule(atmel_port, &atmel_port->tasklet_tx); - else if (((port->rs485.flags & SER_RS485_ENABLED) && - !(port->rs485.flags & SER_RS485_RX_DURING_TX)) || - port->iso7816.flags & SER_ISO7816_ENABLED) { - /* DMA done, stop TX, start RX for RS485 */ - atmel_start_rx(port); + else if (atmel_uart_is_half_duplex(port)) { + /* + * DMA done, re-enable TXEMPTY and signal that we can stop + * TX and start RX for RS485 + */ + atmel_port->hd_start_rx = true; + atmel_uart_writel(port, ATMEL_US_IER, + atmel_port->tx_done_mask); } spin_unlock_irqrestore(&port->lock, flags); @@ -1288,6 +1297,10 @@ static int atmel_prepare_rx_dma(struct uart_port *port) sg_dma_len(&atmel_port->sg_rx)/2, DMA_DEV_TO_MEM, DMA_PREP_INTERRUPT); + if (!desc) { + dev_err(port->dev, "Preparing DMA cyclic failed\n"); + goto chan_err; + } desc->callback = atmel_complete_rx_dma; desc->callback_param = port; atmel_port->desc_rx = desc; @@ -1376,9 +1389,20 @@ atmel_handle_transmit(struct uart_port *port, unsigned int pending) struct atmel_uart_port *atmel_port = to_atmel_uart_port(port); if (pending & atmel_port->tx_done_mask) { - /* Either PDC or interrupt transmission */ atmel_uart_writel(port, ATMEL_US_IDR, atmel_port->tx_done_mask); + + /* Start RX if flag was set and FIFO is empty */ + if (atmel_port->hd_start_rx) { + if (!(atmel_uart_readl(port, ATMEL_US_CSR) + & ATMEL_US_TXEMPTY)) + dev_warn(port->dev, "Should start RX, but TX fifo is not empty\n"); + + atmel_port->hd_start_rx = false; + atmel_start_rx(port); + return; + } + atmel_tasklet_schedule(atmel_port, &atmel_port->tasklet_tx); } } @@ -1508,9 +1532,7 @@ static void atmel_tx_pdc(struct uart_port *port) atmel_uart_writel(port, ATMEL_US_IER, atmel_port->tx_done_mask); } else { - if (((port->rs485.flags & SER_RS485_ENABLED) && - !(port->rs485.flags & SER_RS485_RX_DURING_TX)) || - port->iso7816.flags & SER_ISO7816_ENABLED) { + if (atmel_uart_is_half_duplex(port)) { /* DMA done, stop TX, start RX for RS485 */ atmel_start_rx(port); } diff --git a/drivers/tty/serial/kgdboc.c b/drivers/tty/serial/kgdboc.c index 6fb312e7af71..bfe5e9e034ec 100644 --- a/drivers/tty/serial/kgdboc.c +++ b/drivers/tty/serial/kgdboc.c @@ -148,8 +148,10 @@ static int configure_kgdboc(void) char *cptr = config; struct console *cons; - if (!strlen(config) || isspace(config[0])) + if (!strlen(config) || isspace(config[0])) { + err = 0; goto noconfig; + } kgdboc_io_ops.is_console = 0; kgdb_tty_driver = NULL; diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c index f5bdde405627..450ba6d7996c 100644 --- a/drivers/tty/serial/max310x.c +++ b/drivers/tty/serial/max310x.c @@ -1415,6 +1415,8 @@ static int max310x_spi_probe(struct spi_device *spi) if (spi->dev.of_node) { const struct of_device_id *of_id = of_match_device(max310x_dt_ids, &spi->dev); + if (!of_id) + return -ENODEV; devtype = (struct max310x_devtype *)of_id->data; } else { diff --git a/drivers/tty/serial/mvebu-uart.c b/drivers/tty/serial/mvebu-uart.c index 231f751d1ef4..7e7b1559fa36 100644 --- a/drivers/tty/serial/mvebu-uart.c +++ b/drivers/tty/serial/mvebu-uart.c @@ -810,6 +810,9 @@ static int mvebu_uart_probe(struct platform_device *pdev) return -EINVAL; } + if (!match) + return -ENODEV; + /* Assume that all UART ports have a DT alias or none has */ id = of_alias_get_id(pdev->dev.of_node, "serial"); if (!pdev->dev.of_node || id < 0) diff --git a/drivers/tty/serial/mxs-auart.c b/drivers/tty/serial/mxs-auart.c index 27235a526cce..4c188f4079b3 100644 --- a/drivers/tty/serial/mxs-auart.c +++ b/drivers/tty/serial/mxs-auart.c @@ -1686,6 +1686,10 @@ static int mxs_auart_probe(struct platform_device *pdev) s->port.mapbase = r->start; s->port.membase = ioremap(r->start, resource_size(r)); + if (!s->port.membase) { + ret = -ENOMEM; + goto out_disable_clks; + } s->port.ops = &mxs_auart_ops; s->port.iotype = UPIO_MEM; s->port.fifosize = MXS_AUART_FIFO_SIZE; diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c index 3bcec1c20219..35e5f9c5d5be 100644 --- a/drivers/tty/serial/qcom_geni_serial.c +++ b/drivers/tty/serial/qcom_geni_serial.c @@ -1050,7 +1050,7 @@ static int __init qcom_geni_console_setup(struct console *co, char *options) { struct uart_port *uport; struct qcom_geni_serial_port *port; - int baud; + int baud = 9600; int bits = 8; int parity = 'n'; int flow = 'n'; diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index 635178cf3eed..a31db15cd7c0 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -1507,7 +1507,7 @@ static int __init sc16is7xx_init(void) ret = i2c_add_driver(&sc16is7xx_i2c_uart_driver); if (ret < 0) { pr_err("failed to init sc16is7xx i2c --> %d\n", ret); - return ret; + goto err_i2c; } #endif @@ -1515,10 +1515,20 @@ static int __init sc16is7xx_init(void) ret = spi_register_driver(&sc16is7xx_spi_uart_driver); if (ret < 0) { pr_err("failed to init sc16is7xx spi --> %d\n", ret); - return ret; + goto err_spi; } #endif return ret; + +#ifdef CONFIG_SERIAL_SC16IS7XX_SPI +err_spi: +#endif +#ifdef CONFIG_SERIAL_SC16IS7XX_I2C + i2c_del_driver(&sc16is7xx_i2c_uart_driver); +err_i2c: +#endif + uart_unregister_driver(&sc16is7xx_uart); + return ret; } module_init(sc16is7xx_init); diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 060fcd42b6d5..3cd139752d3f 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -838,19 +838,9 @@ static void sci_transmit_chars(struct uart_port *port) if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS) uart_write_wakeup(port); - if (uart_circ_empty(xmit)) { + if (uart_circ_empty(xmit)) sci_stop_tx(port); - } else { - ctrl = serial_port_in(port, SCSCR); - - if (port->type != PORT_SCI) { - serial_port_in(port, SCxSR); /* Dummy read */ - sci_clear_SCxSR(port, SCxSR_TDxE_CLEAR(port)); - } - ctrl |= SCSCR_TIE; - serial_port_out(port, SCSCR, ctrl); - } } /* On SH3, SCIF may read end-of-break as a space->mark char */ @@ -2522,14 +2512,16 @@ done: * center of the last stop bit in sampling clocks. */ int last_stop = bits * 2 - 1; - int deviation = min_err * srr * last_stop / 2 / baud; + int deviation = DIV_ROUND_CLOSEST(min_err * last_stop * + (int)(srr + 1), + 2 * (int)baud); if (abs(deviation) >= 2) { /* At least two sampling clocks off at the * last stop bit; we can increase the error * margin by shifting the sampling point. */ - int shift = min(-8, max(7, deviation / 2)); + int shift = clamp(deviation / 2, -8, 7); hssrr |= (shift << HSCIF_SRHP_SHIFT) & HSCIF_SRHP_MASK; diff --git a/drivers/tty/tty_port.c b/drivers/tty/tty_port.c index 044c3cbdcfa4..a9e12b3bc31d 100644 --- a/drivers/tty/tty_port.c +++ b/drivers/tty/tty_port.c @@ -325,7 +325,7 @@ static void tty_port_shutdown(struct tty_port *port, struct tty_struct *tty) if (tty && C_HUPCL(tty)) tty_port_lower_dtr_rts(port); - if (port->ops->shutdown) + if (port->ops && port->ops->shutdown) port->ops->shutdown(port); } out: @@ -398,7 +398,7 @@ EXPORT_SYMBOL_GPL(tty_port_tty_wakeup); */ int tty_port_carrier_raised(struct tty_port *port) { - if (port->ops->carrier_raised == NULL) + if (!port->ops || !port->ops->carrier_raised) return 1; return port->ops->carrier_raised(port); } @@ -414,7 +414,7 @@ EXPORT_SYMBOL(tty_port_carrier_raised); */ void tty_port_raise_dtr_rts(struct tty_port *port) { - if (port->ops->dtr_rts) + if (port->ops && port->ops->dtr_rts) port->ops->dtr_rts(port, 1); } EXPORT_SYMBOL(tty_port_raise_dtr_rts); @@ -429,7 +429,7 @@ EXPORT_SYMBOL(tty_port_raise_dtr_rts); */ void tty_port_lower_dtr_rts(struct tty_port *port) { - if (port->ops->dtr_rts) + if (port->ops && port->ops->dtr_rts) port->ops->dtr_rts(port, 0); } EXPORT_SYMBOL(tty_port_lower_dtr_rts); @@ -684,7 +684,7 @@ int tty_port_open(struct tty_port *port, struct tty_struct *tty, if (!tty_port_initialized(port)) { clear_bit(TTY_IO_ERROR, &tty->flags); - if (port->ops->activate) { + if (port->ops && port->ops->activate) { int retval = port->ops->activate(port, tty); if (retval) { mutex_unlock(&port->mutex); diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index d34984aa646d..650c66886c80 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -1520,7 +1520,8 @@ static void csi_J(struct vc_data *vc, int vpar) return; } scr_memsetw(start, vc->vc_video_erase_char, 2 * count); - update_region(vc, (unsigned long) start, count); + if (con_should_update(vc)) + do_update_region(vc, (unsigned long) start, count); vc->vc_need_wrap = 0; } diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 739f8960811a..ec666eb4b7b4 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -558,10 +558,8 @@ static void acm_softint(struct work_struct *work) clear_bit(EVENT_RX_STALL, &acm->flags); } - if (test_bit(EVENT_TTY_WAKEUP, &acm->flags)) { + if (test_and_clear_bit(EVENT_TTY_WAKEUP, &acm->flags)) tty_port_tty_wakeup(&acm->port); - clear_bit(EVENT_TTY_WAKEUP, &acm->flags); - } } /* diff --git a/drivers/usb/common/common.c b/drivers/usb/common/common.c index 48277bbc15e4..73c8e6591746 100644 --- a/drivers/usb/common/common.c +++ b/drivers/usb/common/common.c @@ -145,6 +145,8 @@ enum usb_dr_mode of_usb_get_dr_mode_by_phy(struct device_node *np, int arg0) do { controller = of_find_node_with_property(controller, "phys"); + if (!of_device_is_available(controller)) + continue; index = 0; do { if (arg0 == -1) { diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c index 8987cec9549d..ebcadaad89d1 100644 --- a/drivers/usb/core/driver.c +++ b/drivers/usb/core/driver.c @@ -473,11 +473,6 @@ static int usb_unbind_interface(struct device *dev) pm_runtime_disable(dev); pm_runtime_set_suspended(dev); - /* Undo any residual pm_autopm_get_interface_* calls */ - for (r = atomic_read(&intf->pm_usage_cnt); r > 0; --r) - usb_autopm_put_interface_no_suspend(intf); - atomic_set(&intf->pm_usage_cnt, 0); - if (!error) usb_autosuspend_device(udev); @@ -1633,7 +1628,6 @@ void usb_autopm_put_interface(struct usb_interface *intf) int status; usb_mark_last_busy(udev); - atomic_dec(&intf->pm_usage_cnt); status = pm_runtime_put_sync(&intf->dev); dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n", __func__, atomic_read(&intf->dev.power.usage_count), @@ -1662,7 +1656,6 @@ void usb_autopm_put_interface_async(struct usb_interface *intf) int status; usb_mark_last_busy(udev); - atomic_dec(&intf->pm_usage_cnt); status = pm_runtime_put(&intf->dev); dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n", __func__, atomic_read(&intf->dev.power.usage_count), @@ -1684,7 +1677,6 @@ void usb_autopm_put_interface_no_suspend(struct usb_interface *intf) struct usb_device *udev = interface_to_usbdev(intf); usb_mark_last_busy(udev); - atomic_dec(&intf->pm_usage_cnt); pm_runtime_put_noidle(&intf->dev); } EXPORT_SYMBOL_GPL(usb_autopm_put_interface_no_suspend); @@ -1715,8 +1707,6 @@ int usb_autopm_get_interface(struct usb_interface *intf) status = pm_runtime_get_sync(&intf->dev); if (status < 0) pm_runtime_put_sync(&intf->dev); - else - atomic_inc(&intf->pm_usage_cnt); dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n", __func__, atomic_read(&intf->dev.power.usage_count), status); @@ -1750,8 +1740,6 @@ int usb_autopm_get_interface_async(struct usb_interface *intf) status = pm_runtime_get(&intf->dev); if (status < 0 && status != -EINPROGRESS) pm_runtime_put_noidle(&intf->dev); - else - atomic_inc(&intf->pm_usage_cnt); dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n", __func__, atomic_read(&intf->dev.power.usage_count), status); @@ -1775,7 +1763,6 @@ void usb_autopm_get_interface_no_resume(struct usb_interface *intf) struct usb_device *udev = interface_to_usbdev(intf); usb_mark_last_busy(udev); - atomic_inc(&intf->pm_usage_cnt); pm_runtime_get_noresume(&intf->dev); } EXPORT_SYMBOL_GPL(usb_autopm_get_interface_no_resume); diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 3189181bb628..975d7c1288e3 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -2742,6 +2742,9 @@ int usb_add_hcd(struct usb_hcd *hcd, retval = usb_phy_roothub_set_mode(hcd->phy_roothub, PHY_MODE_USB_HOST_SS); if (retval) + retval = usb_phy_roothub_set_mode(hcd->phy_roothub, + PHY_MODE_USB_HOST); + if (retval) goto err_usb_phy_roothub_power_on; retval = usb_phy_roothub_power_on(hcd->phy_roothub); diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c index 82239f27c4cc..e844bb7b5676 100644 --- a/drivers/usb/core/message.c +++ b/drivers/usb/core/message.c @@ -820,9 +820,11 @@ int usb_string(struct usb_device *dev, int index, char *buf, size_t size) if (dev->state == USB_STATE_SUSPENDED) return -EHOSTUNREACH; - if (size <= 0 || !buf || !index) + if (size <= 0 || !buf) return -EINVAL; buf[0] = 0; + if (index <= 0 || index >= 256) + return -EINVAL; tbuf = kmalloc(256, GFP_NOIO); if (!tbuf) return -ENOMEM; diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index fdc6e4e403e8..8cced3609e24 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -29,6 +29,7 @@ #define PCI_DEVICE_ID_INTEL_BXT_M 0x1aaa #define PCI_DEVICE_ID_INTEL_APL 0x5aaa #define PCI_DEVICE_ID_INTEL_KBP 0xa2b0 +#define PCI_DEVICE_ID_INTEL_CMLH 0x02ee #define PCI_DEVICE_ID_INTEL_GLK 0x31aa #define PCI_DEVICE_ID_INTEL_CNPLP 0x9dee #define PCI_DEVICE_ID_INTEL_CNPH 0xa36e @@ -305,6 +306,9 @@ static const struct pci_device_id dwc3_pci_id_table[] = { { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MRFLD), (kernel_ulong_t) &dwc3_pci_mrfld_properties, }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_CMLH), + (kernel_ulong_t) &dwc3_pci_intel_properties, }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_SPTLP), (kernel_ulong_t) &dwc3_pci_intel_properties, }, diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c index 75b113a5b25c..f3816a5c861e 100644 --- a/drivers/usb/gadget/function/f_hid.c +++ b/drivers/usb/gadget/function/f_hid.c @@ -391,20 +391,20 @@ try_again: req->complete = f_hidg_req_complete; req->context = hidg; + spin_unlock_irqrestore(&hidg->write_spinlock, flags); + status = usb_ep_queue(hidg->in_ep, req, GFP_ATOMIC); if (status < 0) { ERROR(hidg->func.config->cdev, "usb_ep_queue error on int endpoint %zd\n", status); - goto release_write_pending_unlocked; + goto release_write_pending; } else { status = count; } - spin_unlock_irqrestore(&hidg->write_spinlock, flags); return status; release_write_pending: spin_lock_irqsave(&hidg->write_spinlock, flags); -release_write_pending_unlocked: hidg->write_pending = 0; spin_unlock_irqrestore(&hidg->write_spinlock, flags); diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c index baf72f95f0f1..213b52508621 100644 --- a/drivers/usb/gadget/udc/dummy_hcd.c +++ b/drivers/usb/gadget/udc/dummy_hcd.c @@ -979,8 +979,18 @@ static int dummy_udc_start(struct usb_gadget *g, struct dummy_hcd *dum_hcd = gadget_to_dummy_hcd(g); struct dummy *dum = dum_hcd->dum; - if (driver->max_speed == USB_SPEED_UNKNOWN) + switch (g->speed) { + /* All the speeds we support */ + case USB_SPEED_LOW: + case USB_SPEED_FULL: + case USB_SPEED_HIGH: + case USB_SPEED_SUPER: + break; + default: + dev_err(dummy_dev(dum_hcd), "Unsupported driver max speed %d\n", + driver->max_speed); return -EINVAL; + } /* * SLAVE side init ... the layer above hardware, which @@ -1784,9 +1794,10 @@ static void dummy_timer(struct timer_list *t) /* Bus speed is 500000 bytes/ms, so use a little less */ total = 490000; break; - default: + default: /* Can't happen */ dev_err(dummy_dev(dum_hcd), "bogus device speed\n"); - return; + total = 0; + break; } /* FIXME if HZ != 1000 this will probably misbehave ... */ @@ -1828,7 +1839,7 @@ restart: /* Used up this frame's bandwidth? */ if (total <= 0) - break; + continue; /* find the gadget's ep for this request (if configured) */ address = usb_pipeendpoint (urb->pipe); diff --git a/drivers/usb/gadget/udc/net2272.c b/drivers/usb/gadget/udc/net2272.c index b77f3126580e..c2011cd7df8c 100644 --- a/drivers/usb/gadget/udc/net2272.c +++ b/drivers/usb/gadget/udc/net2272.c @@ -945,6 +945,7 @@ net2272_dequeue(struct usb_ep *_ep, struct usb_request *_req) break; } if (&req->req != _req) { + ep->stopped = stopped; spin_unlock_irqrestore(&ep->dev->lock, flags); return -EINVAL; } diff --git a/drivers/usb/gadget/udc/net2280.c b/drivers/usb/gadget/udc/net2280.c index f63f82450bf4..898339e5df10 100644 --- a/drivers/usb/gadget/udc/net2280.c +++ b/drivers/usb/gadget/udc/net2280.c @@ -866,9 +866,6 @@ static void start_queue(struct net2280_ep *ep, u32 dmactl, u32 td_dma) (void) readl(&ep->dev->pci->pcimstctl); writel(BIT(DMA_START), &dma->dmastat); - - if (!ep->is_in) - stop_out_naking(ep); } static void start_dma(struct net2280_ep *ep, struct net2280_request *req) @@ -907,6 +904,7 @@ static void start_dma(struct net2280_ep *ep, struct net2280_request *req) writel(BIT(DMA_START), &dma->dmastat); return; } + stop_out_naking(ep); } tmp = dmactl_default; @@ -1275,9 +1273,9 @@ static int net2280_dequeue(struct usb_ep *_ep, struct usb_request *_req) break; } if (&req->req != _req) { + ep->stopped = stopped; spin_unlock_irqrestore(&ep->dev->lock, flags); - dev_err(&ep->dev->pdev->dev, "%s: Request mismatch\n", - __func__); + ep_dbg(ep->dev, "%s: Request mismatch\n", __func__); return -EINVAL; } diff --git a/drivers/usb/host/u132-hcd.c b/drivers/usb/host/u132-hcd.c index 934584f0a20a..6343fbacd244 100644 --- a/drivers/usb/host/u132-hcd.c +++ b/drivers/usb/host/u132-hcd.c @@ -3204,6 +3204,9 @@ static int __init u132_hcd_init(void) printk(KERN_INFO "driver %s\n", hcd_name); workqueue = create_singlethread_workqueue("u132"); retval = platform_driver_register(&u132_platform_driver); + if (retval) + destroy_workqueue(workqueue); + return retval; } diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c index c78be578abb0..d932cc31711e 100644 --- a/drivers/usb/host/xhci-dbgcap.c +++ b/drivers/usb/host/xhci-dbgcap.c @@ -516,7 +516,6 @@ static int xhci_do_dbc_stop(struct xhci_hcd *xhci) return -1; writel(0, &dbc->regs->control); - xhci_dbc_mem_cleanup(xhci); dbc->state = DS_DISABLED; return 0; @@ -562,8 +561,10 @@ static void xhci_dbc_stop(struct xhci_hcd *xhci) ret = xhci_do_dbc_stop(xhci); spin_unlock_irqrestore(&dbc->lock, flags); - if (!ret) + if (!ret) { + xhci_dbc_mem_cleanup(xhci); pm_runtime_put_sync(xhci_to_hcd(xhci)->self.controller); + } } static void diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index e2eece693655..96a740543183 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -1545,20 +1545,25 @@ int xhci_bus_suspend(struct usb_hcd *hcd) port_index = max_ports; while (port_index--) { u32 t1, t2; - + int retries = 10; +retry: t1 = readl(ports[port_index]->addr); t2 = xhci_port_state_to_neutral(t1); portsc_buf[port_index] = 0; - /* Bail out if a USB3 port has a new device in link training */ - if ((hcd->speed >= HCD_USB3) && + /* + * Give a USB3 port in link training time to finish, but don't + * prevent suspend as port might be stuck + */ + if ((hcd->speed >= HCD_USB3) && retries-- && (t1 & PORT_PLS_MASK) == XDEV_POLLING) { - bus_state->bus_suspended = 0; spin_unlock_irqrestore(&xhci->lock, flags); - xhci_dbg(xhci, "Bus suspend bailout, port in polling\n"); - return -EBUSY; + msleep(XHCI_PORT_POLLING_LFPS_TIME); + spin_lock_irqsave(&xhci->lock, flags); + xhci_dbg(xhci, "port %d polling in bus suspend, waiting\n", + port_index); + goto retry; } - /* suspend ports in U0, or bail out for new connect changes */ if ((t1 & PORT_PE) && (t1 & PORT_PLS_MASK) == XDEV_U0) { if ((t1 & PORT_CSC) && wake_enabled) { diff --git a/drivers/usb/host/xhci-rcar.c b/drivers/usb/host/xhci-rcar.c index a6e463715779..671bce18782c 100644 --- a/drivers/usb/host/xhci-rcar.c +++ b/drivers/usb/host/xhci-rcar.c @@ -246,6 +246,7 @@ int xhci_rcar_init_quirk(struct usb_hcd *hcd) if (!xhci_rcar_wait_for_pll_active(hcd)) return -ETIMEDOUT; + xhci->quirks |= XHCI_TRUST_TX_LENGTH; return xhci_rcar_download_firmware(hcd); } diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 40fa25c4d041..9215a28dad40 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -1647,10 +1647,13 @@ static void handle_port_status(struct xhci_hcd *xhci, } } - if ((portsc & PORT_PLC) && (portsc & PORT_PLS_MASK) == XDEV_U0 && - DEV_SUPERSPEED_ANY(portsc)) { + if ((portsc & PORT_PLC) && + DEV_SUPERSPEED_ANY(portsc) && + ((portsc & PORT_PLS_MASK) == XDEV_U0 || + (portsc & PORT_PLS_MASK) == XDEV_U1 || + (portsc & PORT_PLS_MASK) == XDEV_U2)) { xhci_dbg(xhci, "resume SS port %d finished\n", port_id); - /* We've just brought the device into U0 through either the + /* We've just brought the device into U0/1/2 through either the * Resume state after a device remote wakeup, or through the * U3Exit state after a host-initiated resume. If it's a device * initiated remote wake, don't pass up the link state change, diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 652dc36e3012..9334cdee382a 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -452,6 +452,14 @@ struct xhci_op_regs { */ #define XHCI_DEFAULT_BESL 4 +/* + * USB3 specification define a 360ms tPollingLFPSTiemout for USB3 ports + * to complete link training. usually link trainig completes much faster + * so check status 10 times with 36ms sleep in places we need to wait for + * polling to complete. + */ +#define XHCI_PORT_POLLING_LFPS_TIME 36 + /** * struct xhci_intr_reg - Interrupt Register Set * @irq_pending: IMAN - Interrupt Management Register. Used to enable diff --git a/drivers/usb/misc/usb251xb.c b/drivers/usb/misc/usb251xb.c index 4d72b7d1d383..04684849d683 100644 --- a/drivers/usb/misc/usb251xb.c +++ b/drivers/usb/misc/usb251xb.c @@ -547,7 +547,7 @@ static int usb251xb_get_ofdata(struct usb251xb *hub, */ hub->port_swap = USB251XB_DEF_PORT_SWAP; of_property_for_each_u32(np, "swap-dx-lanes", prop, p, port) { - if ((port >= 0) && (port <= data->port_cnt)) + if (port <= data->port_cnt) hub->port_swap |= BIT(port); } @@ -612,7 +612,7 @@ static int usb251xb_probe(struct usb251xb *hub) dev); int err; - if (np) { + if (np && of_id) { err = usb251xb_get_ofdata(hub, (struct usb251xb_data *)of_id->data); if (err) { diff --git a/drivers/usb/misc/yurex.c b/drivers/usb/misc/yurex.c index 6d9fd5f64903..7b306aa22d25 100644 --- a/drivers/usb/misc/yurex.c +++ b/drivers/usb/misc/yurex.c @@ -314,6 +314,7 @@ static void yurex_disconnect(struct usb_interface *interface) usb_deregister_dev(interface, &yurex_class); /* prevent more I/O from starting */ + usb_poison_urb(dev->urb); mutex_lock(&dev->io_mutex); dev->interface = NULL; mutex_unlock(&dev->io_mutex); diff --git a/drivers/usb/mtu3/Kconfig b/drivers/usb/mtu3/Kconfig index bcc23486c4ed..928c2cd6fc00 100644 --- a/drivers/usb/mtu3/Kconfig +++ b/drivers/usb/mtu3/Kconfig @@ -6,6 +6,7 @@ config USB_MTU3 tristate "MediaTek USB3 Dual Role controller" depends on USB || USB_GADGET depends on ARCH_MEDIATEK || COMPILE_TEST + depends on EXTCON || !EXTCON select USB_XHCI_MTK if USB_SUPPORT && USB_XHCI_HCD help Say Y or M here if your system runs on MediaTek SoCs with diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index fffe23ab0189..979bef9bfb6b 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -80,6 +80,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x804E) }, /* Software Bisque Paramount ME build-in converter */ { USB_DEVICE(0x10C4, 0x8053) }, /* Enfora EDG1228 */ { USB_DEVICE(0x10C4, 0x8054) }, /* Enfora GSM2228 */ + { USB_DEVICE(0x10C4, 0x8056) }, /* Lorenz Messtechnik devices */ { USB_DEVICE(0x10C4, 0x8066) }, /* Argussoft In-System Programmer */ { USB_DEVICE(0x10C4, 0x806F) }, /* IMS USB to RS422 Converter Cable */ { USB_DEVICE(0x10C4, 0x807A) }, /* Crumb128 board */ diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 8f5b17471759..1d8461ae2c34 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -609,6 +609,8 @@ static const struct usb_device_id id_table_combined[] = { .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, { USB_DEVICE(FTDI_VID, FTDI_NT_ORIONLXM_PID), .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, + { USB_DEVICE(FTDI_VID, FTDI_NT_ORIONLX_PLUS_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_NT_ORION_IO_PID) }, { USB_DEVICE(FTDI_VID, FTDI_SYNAPSE_SS200_PID) }, { USB_DEVICE(FTDI_VID, FTDI_CUSTOMWARE_MINIPLEX_PID) }, { USB_DEVICE(FTDI_VID, FTDI_CUSTOMWARE_MINIPLEX2_PID) }, diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index b863bedb55a1..5755f0df0025 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -567,7 +567,9 @@ /* * NovaTech product ids (FTDI_VID) */ -#define FTDI_NT_ORIONLXM_PID 0x7c90 /* OrionLXm Substation Automation Platform */ +#define FTDI_NT_ORIONLXM_PID 0x7c90 /* OrionLXm Substation Automation Platform */ +#define FTDI_NT_ORIONLX_PLUS_PID 0x7c91 /* OrionLX+ Substation Automation Platform */ +#define FTDI_NT_ORION_IO_PID 0x7c92 /* Orion I/O */ /* * Synapse Wireless product ids (FTDI_VID) diff --git a/drivers/usb/serial/mos7720.c b/drivers/usb/serial/mos7720.c index fc52ac75fbf6..18110225d506 100644 --- a/drivers/usb/serial/mos7720.c +++ b/drivers/usb/serial/mos7720.c @@ -366,8 +366,6 @@ static int write_parport_reg_nonblock(struct mos7715_parport *mos_parport, if (!urbtrack) return -ENOMEM; - kref_get(&mos_parport->ref_count); - urbtrack->mos_parport = mos_parport; urbtrack->urb = usb_alloc_urb(0, GFP_ATOMIC); if (!urbtrack->urb) { kfree(urbtrack); @@ -388,6 +386,8 @@ static int write_parport_reg_nonblock(struct mos7715_parport *mos_parport, usb_sndctrlpipe(usbdev, 0), (unsigned char *)urbtrack->setup, NULL, 0, async_complete, urbtrack); + kref_get(&mos_parport->ref_count); + urbtrack->mos_parport = mos_parport; kref_init(&urbtrack->ref_count); INIT_LIST_HEAD(&urbtrack->urblist_entry); diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 11b21d9410f3..83869065b802 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -246,6 +246,7 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_PRODUCT_EC25 0x0125 #define QUECTEL_PRODUCT_BG96 0x0296 #define QUECTEL_PRODUCT_EP06 0x0306 +#define QUECTEL_PRODUCT_EM12 0x0512 #define CMOTECH_VENDOR_ID 0x16d8 #define CMOTECH_PRODUCT_6001 0x6001 @@ -1066,7 +1067,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(3) }, { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6613)}, /* Onda H600/ZTE MF330 */ { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x0023)}, /* ONYX 3G device */ - { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000)}, /* SIMCom SIM5218 */ + { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000), /* SIMCom SIM5218 */ + .driver_info = NCTRL(0) | NCTRL(1) | NCTRL(2) | NCTRL(3) | RSVD(4) }, /* Quectel products using Qualcomm vendor ID */ { USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC15)}, { USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC20), @@ -1087,6 +1089,9 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0xff, 0xff), .driver_info = RSVD(1) | RSVD(2) | RSVD(3) | RSVD(4) | NUMEP2 }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0, 0) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM12, 0xff, 0xff, 0xff), + .driver_info = RSVD(1) | RSVD(2) | RSVD(3) | RSVD(4) | NUMEP2 }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM12, 0xff, 0, 0) }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6003), @@ -1940,10 +1945,12 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(4) }, { USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7e35, 0xff), /* D-Link DWM-222 */ .driver_info = RSVD(4) }, - { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) }, /* D-Link DWM-152/C1 */ - { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/C1 */ - { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x7e11, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/A3 */ - { USB_DEVICE_INTERFACE_CLASS(0x2020, 0x4000, 0xff) }, /* OLICARD300 - MT6225 */ + { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) }, /* D-Link DWM-152/C1 */ + { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/C1 */ + { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x7e11, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/A3 */ + { USB_DEVICE_INTERFACE_CLASS(0x2020, 0x2031, 0xff), /* Olicard 600 */ + .driver_info = RSVD(4) }, + { USB_DEVICE_INTERFACE_CLASS(0x2020, 0x4000, 0xff) }, /* OLICARD300 - MT6225 */ { USB_DEVICE(INOVIA_VENDOR_ID, INOVIA_SEW858) }, { USB_DEVICE(VIATELECOM_VENDOR_ID, VIATELECOM_PRODUCT_CDS7) }, { USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_WMD200, 0xff, 0xff, 0xff) }, diff --git a/drivers/usb/storage/realtek_cr.c b/drivers/usb/storage/realtek_cr.c index 31b024441938..cc794e25a0b6 100644 --- a/drivers/usb/storage/realtek_cr.c +++ b/drivers/usb/storage/realtek_cr.c @@ -763,18 +763,16 @@ static void rts51x_suspend_timer_fn(struct timer_list *t) break; case RTS51X_STAT_IDLE: case RTS51X_STAT_SS: - usb_stor_dbg(us, "RTS51X_STAT_SS, intf->pm_usage_cnt:%d, power.usage:%d\n", - atomic_read(&us->pusb_intf->pm_usage_cnt), + usb_stor_dbg(us, "RTS51X_STAT_SS, power.usage:%d\n", atomic_read(&us->pusb_intf->dev.power.usage_count)); - if (atomic_read(&us->pusb_intf->pm_usage_cnt) > 0) { + if (atomic_read(&us->pusb_intf->dev.power.usage_count) > 0) { usb_stor_dbg(us, "Ready to enter SS state\n"); rts51x_set_stat(chip, RTS51X_STAT_SS); /* ignore mass storage interface's children */ pm_suspend_ignore_children(&us->pusb_intf->dev, true); usb_autopm_put_interface_async(us->pusb_intf); - usb_stor_dbg(us, "RTS51X_STAT_SS 01, intf->pm_usage_cnt:%d, power.usage:%d\n", - atomic_read(&us->pusb_intf->pm_usage_cnt), + usb_stor_dbg(us, "RTS51X_STAT_SS 01, power.usage:%d\n", atomic_read(&us->pusb_intf->dev.power.usage_count)); } break; @@ -807,11 +805,10 @@ static void rts51x_invoke_transport(struct scsi_cmnd *srb, struct us_data *us) int ret; if (working_scsi(srb)) { - usb_stor_dbg(us, "working scsi, intf->pm_usage_cnt:%d, power.usage:%d\n", - atomic_read(&us->pusb_intf->pm_usage_cnt), + usb_stor_dbg(us, "working scsi, power.usage:%d\n", atomic_read(&us->pusb_intf->dev.power.usage_count)); - if (atomic_read(&us->pusb_intf->pm_usage_cnt) <= 0) { + if (atomic_read(&us->pusb_intf->dev.power.usage_count) <= 0) { ret = usb_autopm_get_interface(us->pusb_intf); usb_stor_dbg(us, "working scsi, ret=%d\n", ret); } diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 0f62db091d8d..a2233d72ae7c 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -37,6 +37,7 @@ S(SRC_ATTACHED), \ S(SRC_STARTUP), \ S(SRC_SEND_CAPABILITIES), \ + S(SRC_SEND_CAPABILITIES_TIMEOUT), \ S(SRC_NEGOTIATE_CAPABILITIES), \ S(SRC_TRANSITION_SUPPLY), \ S(SRC_READY), \ @@ -2966,10 +2967,34 @@ static void run_state_machine(struct tcpm_port *port) /* port->hard_reset_count = 0; */ port->caps_count = 0; port->pd_capable = true; - tcpm_set_state_cond(port, hard_reset_state(port), + tcpm_set_state_cond(port, SRC_SEND_CAPABILITIES_TIMEOUT, PD_T_SEND_SOURCE_CAP); } break; + case SRC_SEND_CAPABILITIES_TIMEOUT: + /* + * Error recovery for a PD_DATA_SOURCE_CAP reply timeout. + * + * PD 2.0 sinks are supposed to accept src-capabilities with a + * 3.0 header and simply ignore any src PDOs which the sink does + * not understand such as PPS but some 2.0 sinks instead ignore + * the entire PD_DATA_SOURCE_CAP message, causing contract + * negotiation to fail. + * + * After PD_N_HARD_RESET_COUNT hard-reset attempts, we try + * sending src-capabilities with a lower PD revision to + * make these broken sinks work. + */ + if (port->hard_reset_count < PD_N_HARD_RESET_COUNT) { + tcpm_set_state(port, HARD_RESET_SEND, 0); + } else if (port->negotiated_rev > PD_REV20) { + port->negotiated_rev--; + port->hard_reset_count = 0; + tcpm_set_state(port, SRC_SEND_CAPABILITIES, 0); + } else { + tcpm_set_state(port, hard_reset_state(port), 0); + } + break; case SRC_NEGOTIATE_CAPABILITIES: ret = tcpm_pd_check_request(port); if (ret < 0) { diff --git a/drivers/usb/typec/tcpm/wcove.c b/drivers/usb/typec/tcpm/wcove.c index 423208e19383..6770afd40765 100644 --- a/drivers/usb/typec/tcpm/wcove.c +++ b/drivers/usb/typec/tcpm/wcove.c @@ -615,8 +615,13 @@ static int wcove_typec_probe(struct platform_device *pdev) wcove->dev = &pdev->dev; wcove->regmap = pmic->regmap; - irq = regmap_irq_get_virq(pmic->irq_chip_data_chgr, - platform_get_irq(pdev, 0)); + irq = platform_get_irq(pdev, 0); + if (irq < 0) { + dev_err(&pdev->dev, "Failed to get IRQ: %d\n", irq); + return irq; + } + + irq = regmap_irq_get_virq(pmic->irq_chip_data_chgr, irq); if (irq < 0) return irq; diff --git a/drivers/usb/usbip/stub_rx.c b/drivers/usb/usbip/stub_rx.c index 97b09a42a10c..dbfb2f24d71e 100644 --- a/drivers/usb/usbip/stub_rx.c +++ b/drivers/usb/usbip/stub_rx.c @@ -361,16 +361,10 @@ static int get_pipe(struct stub_device *sdev, struct usbip_header *pdu) } if (usb_endpoint_xfer_isoc(epd)) { - /* validate packet size and number of packets */ - unsigned int maxp, packets, bytes; - - maxp = usb_endpoint_maxp(epd); - maxp *= usb_endpoint_maxp_mult(epd); - bytes = pdu->u.cmd_submit.transfer_buffer_length; - packets = DIV_ROUND_UP(bytes, maxp); - + /* validate number of packets */ if (pdu->u.cmd_submit.number_of_packets < 0 || - pdu->u.cmd_submit.number_of_packets > packets) { + pdu->u.cmd_submit.number_of_packets > + USBIP_MAX_ISO_PACKETS) { dev_err(&sdev->udev->dev, "CMD_SUBMIT: isoc invalid num packets %d\n", pdu->u.cmd_submit.number_of_packets); diff --git a/drivers/usb/usbip/usbip_common.h b/drivers/usb/usbip/usbip_common.h index bf8afe9b5883..8be857a4fa13 100644 --- a/drivers/usb/usbip/usbip_common.h +++ b/drivers/usb/usbip/usbip_common.h @@ -121,6 +121,13 @@ extern struct device_attribute dev_attr_usbip_debug; #define USBIP_DIR_OUT 0x00 #define USBIP_DIR_IN 0x01 +/* + * Arbitrary limit for the maximum number of isochronous packets in an URB, + * compare for example the uhci_submit_isochronous function in + * drivers/usb/host/uhci-q.c + */ +#define USBIP_MAX_ISO_PACKETS 1024 + /** * struct usbip_header_basic - data pertinent to every request * @command: the usbip request type diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index a25659b5a5d1..3fa20e95a6bb 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -1661,11 +1661,11 @@ static void __init vfio_pci_fill_ids(void) rc = pci_add_dynid(&vfio_pci_driver, vendor, device, subvendor, subdevice, class, class_mask, 0); if (rc) - pr_warn("failed to add dynamic id [%04hx:%04hx[%04hx:%04hx]] class %#08x/%08x (%d)\n", + pr_warn("failed to add dynamic id [%04x:%04x[%04x:%04x]] class %#08x/%08x (%d)\n", vendor, device, subvendor, subdevice, class, class_mask, rc); else - pr_info("add [%04hx:%04hx[%04hx:%04hx]] class %#08x/%08x\n", + pr_info("add [%04x:%04x[%04x:%04x]] class %#08x/%08x\n", vendor, device, subvendor, subdevice, class, class_mask); } diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c index 8dbb270998f4..6b64e45a5269 100644 --- a/drivers/vfio/vfio_iommu_spapr_tce.c +++ b/drivers/vfio/vfio_iommu_spapr_tce.c @@ -1398,7 +1398,7 @@ unlock_exit: mutex_unlock(&container->lock); } -const struct vfio_iommu_driver_ops tce_iommu_driver_ops = { +static const struct vfio_iommu_driver_ops tce_iommu_driver_ops = { .name = "iommu-vfio-powerpc", .owner = THIS_MODULE, .open = tce_iommu_open, diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 73652e21efec..d0f731c9920a 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -58,12 +58,18 @@ module_param_named(disable_hugepages, MODULE_PARM_DESC(disable_hugepages, "Disable VFIO IOMMU support for IOMMU hugepages."); +static unsigned int dma_entry_limit __read_mostly = U16_MAX; +module_param_named(dma_entry_limit, dma_entry_limit, uint, 0644); +MODULE_PARM_DESC(dma_entry_limit, + "Maximum number of user DMA mappings per container (65535)."); + struct vfio_iommu { struct list_head domain_list; struct vfio_domain *external_domain; /* domain for external user */ struct mutex lock; struct rb_root dma_list; struct blocking_notifier_head notifier; + unsigned int dma_avail; bool v2; bool nesting; }; @@ -836,6 +842,7 @@ static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma) vfio_unlink_dma(iommu, dma); put_task_struct(dma->task); kfree(dma); + iommu->dma_avail++; } static unsigned long vfio_pgsize_bitmap(struct vfio_iommu *iommu) @@ -1081,12 +1088,18 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu, goto out_unlock; } + if (!iommu->dma_avail) { + ret = -ENOSPC; + goto out_unlock; + } + dma = kzalloc(sizeof(*dma), GFP_KERNEL); if (!dma) { ret = -ENOMEM; goto out_unlock; } + iommu->dma_avail--; dma->iova = iova; dma->vaddr = vaddr; dma->prot = prot; @@ -1583,6 +1596,7 @@ static void *vfio_iommu_type1_open(unsigned long arg) INIT_LIST_HEAD(&iommu->domain_list); iommu->dma_list = RB_ROOT; + iommu->dma_avail = dma_entry_limit; mutex_init(&iommu->lock); BLOCKING_INIT_NOTIFIER_HEAD(&iommu->notifier); diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 5ace833de746..351af88231ad 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -911,8 +911,12 @@ static int vhost_new_umem_range(struct vhost_umem *umem, u64 start, u64 size, u64 end, u64 userspace_addr, int perm) { - struct vhost_umem_node *tmp, *node = kmalloc(sizeof(*node), GFP_ATOMIC); + struct vhost_umem_node *tmp, *node; + if (!size) + return -EFAULT; + + node = kmalloc(sizeof(*node), GFP_ATOMIC); if (!node) return -ENOMEM; diff --git a/drivers/virt/vboxguest/vboxguest_core.c b/drivers/virt/vboxguest/vboxguest_core.c index df7d09409efe..8ca333f21292 100644 --- a/drivers/virt/vboxguest/vboxguest_core.c +++ b/drivers/virt/vboxguest/vboxguest_core.c @@ -27,6 +27,10 @@ #define GUEST_MAPPINGS_TRIES 5 +#define VBG_KERNEL_REQUEST \ + (VMMDEV_REQUESTOR_KERNEL | VMMDEV_REQUESTOR_USR_DRV | \ + VMMDEV_REQUESTOR_CON_DONT_KNOW | VMMDEV_REQUESTOR_TRUST_NOT_GIVEN) + /** * Reserves memory in which the VMM can relocate any guest mappings * that are floating around. @@ -48,7 +52,8 @@ static void vbg_guest_mappings_init(struct vbg_dev *gdev) int i, rc; /* Query the required space. */ - req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_GET_HYPERVISOR_INFO); + req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_GET_HYPERVISOR_INFO, + VBG_KERNEL_REQUEST); if (!req) return; @@ -135,7 +140,8 @@ static void vbg_guest_mappings_exit(struct vbg_dev *gdev) * Tell the host that we're going to free the memory we reserved for * it, the free it up. (Leak the memory if anything goes wrong here.) */ - req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_HYPERVISOR_INFO); + req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_HYPERVISOR_INFO, + VBG_KERNEL_REQUEST); if (!req) return; @@ -172,8 +178,10 @@ static int vbg_report_guest_info(struct vbg_dev *gdev) struct vmmdev_guest_info2 *req2 = NULL; int rc, ret = -ENOMEM; - req1 = vbg_req_alloc(sizeof(*req1), VMMDEVREQ_REPORT_GUEST_INFO); - req2 = vbg_req_alloc(sizeof(*req2), VMMDEVREQ_REPORT_GUEST_INFO2); + req1 = vbg_req_alloc(sizeof(*req1), VMMDEVREQ_REPORT_GUEST_INFO, + VBG_KERNEL_REQUEST); + req2 = vbg_req_alloc(sizeof(*req2), VMMDEVREQ_REPORT_GUEST_INFO2, + VBG_KERNEL_REQUEST); if (!req1 || !req2) goto out_free; @@ -187,8 +195,8 @@ static int vbg_report_guest_info(struct vbg_dev *gdev) req2->additions_minor = VBG_VERSION_MINOR; req2->additions_build = VBG_VERSION_BUILD; req2->additions_revision = VBG_SVN_REV; - /* (no features defined yet) */ - req2->additions_features = 0; + req2->additions_features = + VMMDEV_GUEST_INFO2_ADDITIONS_FEATURES_REQUESTOR_INFO; strlcpy(req2->name, VBG_VERSION_STRING, sizeof(req2->name)); @@ -230,7 +238,8 @@ static int vbg_report_driver_status(struct vbg_dev *gdev, bool active) struct vmmdev_guest_status *req; int rc; - req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_REPORT_GUEST_STATUS); + req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_REPORT_GUEST_STATUS, + VBG_KERNEL_REQUEST); if (!req) return -ENOMEM; @@ -423,7 +432,8 @@ static int vbg_heartbeat_host_config(struct vbg_dev *gdev, bool enabled) struct vmmdev_heartbeat *req; int rc; - req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_HEARTBEAT_CONFIGURE); + req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_HEARTBEAT_CONFIGURE, + VBG_KERNEL_REQUEST); if (!req) return -ENOMEM; @@ -457,7 +467,8 @@ static int vbg_heartbeat_init(struct vbg_dev *gdev) gdev->guest_heartbeat_req = vbg_req_alloc( sizeof(*gdev->guest_heartbeat_req), - VMMDEVREQ_GUEST_HEARTBEAT); + VMMDEVREQ_GUEST_HEARTBEAT, + VBG_KERNEL_REQUEST); if (!gdev->guest_heartbeat_req) return -ENOMEM; @@ -528,7 +539,8 @@ static int vbg_reset_host_event_filter(struct vbg_dev *gdev, struct vmmdev_mask *req; int rc; - req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_CTL_GUEST_FILTER_MASK); + req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_CTL_GUEST_FILTER_MASK, + VBG_KERNEL_REQUEST); if (!req) return -ENOMEM; @@ -567,8 +579,14 @@ static int vbg_set_session_event_filter(struct vbg_dev *gdev, u32 changed, previous; int rc, ret = 0; - /* Allocate a request buffer before taking the spinlock */ - req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_CTL_GUEST_FILTER_MASK); + /* + * Allocate a request buffer before taking the spinlock, when + * the session is being terminated the requestor is the kernel, + * as we're cleaning up. + */ + req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_CTL_GUEST_FILTER_MASK, + session_termination ? VBG_KERNEL_REQUEST : + session->requestor); if (!req) { if (!session_termination) return -ENOMEM; @@ -627,7 +645,8 @@ static int vbg_reset_host_capabilities(struct vbg_dev *gdev) struct vmmdev_mask *req; int rc; - req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_GUEST_CAPABILITIES); + req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_GUEST_CAPABILITIES, + VBG_KERNEL_REQUEST); if (!req) return -ENOMEM; @@ -662,8 +681,14 @@ static int vbg_set_session_capabilities(struct vbg_dev *gdev, u32 changed, previous; int rc, ret = 0; - /* Allocate a request buffer before taking the spinlock */ - req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_GUEST_CAPABILITIES); + /* + * Allocate a request buffer before taking the spinlock, when + * the session is being terminated the requestor is the kernel, + * as we're cleaning up. + */ + req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_GUEST_CAPABILITIES, + session_termination ? VBG_KERNEL_REQUEST : + session->requestor); if (!req) { if (!session_termination) return -ENOMEM; @@ -722,7 +747,8 @@ static int vbg_query_host_version(struct vbg_dev *gdev) struct vmmdev_host_version *req; int rc, ret; - req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_GET_HOST_VERSION); + req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_GET_HOST_VERSION, + VBG_KERNEL_REQUEST); if (!req) return -ENOMEM; @@ -783,19 +809,24 @@ int vbg_core_init(struct vbg_dev *gdev, u32 fixed_events) gdev->mem_balloon.get_req = vbg_req_alloc(sizeof(*gdev->mem_balloon.get_req), - VMMDEVREQ_GET_MEMBALLOON_CHANGE_REQ); + VMMDEVREQ_GET_MEMBALLOON_CHANGE_REQ, + VBG_KERNEL_REQUEST); gdev->mem_balloon.change_req = vbg_req_alloc(sizeof(*gdev->mem_balloon.change_req), - VMMDEVREQ_CHANGE_MEMBALLOON); + VMMDEVREQ_CHANGE_MEMBALLOON, + VBG_KERNEL_REQUEST); gdev->cancel_req = vbg_req_alloc(sizeof(*(gdev->cancel_req)), - VMMDEVREQ_HGCM_CANCEL2); + VMMDEVREQ_HGCM_CANCEL2, + VBG_KERNEL_REQUEST); gdev->ack_events_req = vbg_req_alloc(sizeof(*gdev->ack_events_req), - VMMDEVREQ_ACKNOWLEDGE_EVENTS); + VMMDEVREQ_ACKNOWLEDGE_EVENTS, + VBG_KERNEL_REQUEST); gdev->mouse_status_req = vbg_req_alloc(sizeof(*gdev->mouse_status_req), - VMMDEVREQ_GET_MOUSE_STATUS); + VMMDEVREQ_GET_MOUSE_STATUS, + VBG_KERNEL_REQUEST); if (!gdev->mem_balloon.get_req || !gdev->mem_balloon.change_req || !gdev->cancel_req || !gdev->ack_events_req || @@ -892,9 +923,9 @@ void vbg_core_exit(struct vbg_dev *gdev) * vboxguest_linux.c calls this when userspace opens the char-device. * Return: A pointer to the new session or an ERR_PTR on error. * @gdev: The Guest extension device. - * @user: Set if this is a session for the vboxuser device. + * @requestor: VMMDEV_REQUESTOR_* flags */ -struct vbg_session *vbg_core_open_session(struct vbg_dev *gdev, bool user) +struct vbg_session *vbg_core_open_session(struct vbg_dev *gdev, u32 requestor) { struct vbg_session *session; @@ -903,7 +934,7 @@ struct vbg_session *vbg_core_open_session(struct vbg_dev *gdev, bool user) return ERR_PTR(-ENOMEM); session->gdev = gdev; - session->user_session = user; + session->requestor = requestor; return session; } @@ -924,7 +955,9 @@ void vbg_core_close_session(struct vbg_session *session) if (!session->hgcm_client_ids[i]) continue; - vbg_hgcm_disconnect(gdev, session->hgcm_client_ids[i], &rc); + /* requestor is kernel here, as we're cleaning up. */ + vbg_hgcm_disconnect(gdev, VBG_KERNEL_REQUEST, + session->hgcm_client_ids[i], &rc); } kfree(session); @@ -1152,7 +1185,8 @@ static int vbg_req_allowed(struct vbg_dev *gdev, struct vbg_session *session, return -EPERM; } - if (trusted_apps_only && session->user_session) { + if (trusted_apps_only && + (session->requestor & VMMDEV_REQUESTOR_USER_DEVICE)) { vbg_err("Denying userspace vmm call type %#08x through vboxuser device node\n", req->request_type); return -EPERM; @@ -1209,8 +1243,8 @@ static int vbg_ioctl_hgcm_connect(struct vbg_dev *gdev, if (i >= ARRAY_SIZE(session->hgcm_client_ids)) return -EMFILE; - ret = vbg_hgcm_connect(gdev, &conn->u.in.loc, &client_id, - &conn->hdr.rc); + ret = vbg_hgcm_connect(gdev, session->requestor, &conn->u.in.loc, + &client_id, &conn->hdr.rc); mutex_lock(&gdev->session_mutex); if (ret == 0 && conn->hdr.rc >= 0) { @@ -1251,7 +1285,8 @@ static int vbg_ioctl_hgcm_disconnect(struct vbg_dev *gdev, if (i >= ARRAY_SIZE(session->hgcm_client_ids)) return -EINVAL; - ret = vbg_hgcm_disconnect(gdev, client_id, &disconn->hdr.rc); + ret = vbg_hgcm_disconnect(gdev, session->requestor, client_id, + &disconn->hdr.rc); mutex_lock(&gdev->session_mutex); if (ret == 0 && disconn->hdr.rc >= 0) @@ -1313,12 +1348,12 @@ static int vbg_ioctl_hgcm_call(struct vbg_dev *gdev, } if (IS_ENABLED(CONFIG_COMPAT) && f32bit) - ret = vbg_hgcm_call32(gdev, client_id, + ret = vbg_hgcm_call32(gdev, session->requestor, client_id, call->function, call->timeout_ms, VBG_IOCTL_HGCM_CALL_PARMS32(call), call->parm_count, &call->hdr.rc); else - ret = vbg_hgcm_call(gdev, client_id, + ret = vbg_hgcm_call(gdev, session->requestor, client_id, call->function, call->timeout_ms, VBG_IOCTL_HGCM_CALL_PARMS(call), call->parm_count, &call->hdr.rc); @@ -1408,6 +1443,7 @@ static int vbg_ioctl_check_balloon(struct vbg_dev *gdev, } static int vbg_ioctl_write_core_dump(struct vbg_dev *gdev, + struct vbg_session *session, struct vbg_ioctl_write_coredump *dump) { struct vmmdev_write_core_dump *req; @@ -1415,7 +1451,8 @@ static int vbg_ioctl_write_core_dump(struct vbg_dev *gdev, if (vbg_ioctl_chk(&dump->hdr, sizeof(dump->u.in), 0)) return -EINVAL; - req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_WRITE_COREDUMP); + req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_WRITE_COREDUMP, + session->requestor); if (!req) return -ENOMEM; @@ -1476,7 +1513,7 @@ int vbg_core_ioctl(struct vbg_session *session, unsigned int req, void *data) case VBG_IOCTL_CHECK_BALLOON: return vbg_ioctl_check_balloon(gdev, data); case VBG_IOCTL_WRITE_CORE_DUMP: - return vbg_ioctl_write_core_dump(gdev, data); + return vbg_ioctl_write_core_dump(gdev, session, data); } /* Variable sized requests. */ @@ -1508,7 +1545,8 @@ int vbg_core_set_mouse_status(struct vbg_dev *gdev, u32 features) struct vmmdev_mouse_status *req; int rc; - req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_MOUSE_STATUS); + req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_MOUSE_STATUS, + VBG_KERNEL_REQUEST); if (!req) return -ENOMEM; diff --git a/drivers/virt/vboxguest/vboxguest_core.h b/drivers/virt/vboxguest/vboxguest_core.h index 7ad9ec45bfa9..4188c12b839f 100644 --- a/drivers/virt/vboxguest/vboxguest_core.h +++ b/drivers/virt/vboxguest/vboxguest_core.h @@ -154,15 +154,15 @@ struct vbg_session { * host. Protected by vbg_gdev.session_mutex. */ u32 guest_caps; - /** Does this session belong to a root process or a user one? */ - bool user_session; + /** VMMDEV_REQUESTOR_* flags */ + u32 requestor; /** Set on CANCEL_ALL_WAITEVENTS, protected by vbg_devevent_spinlock. */ bool cancel_waiters; }; int vbg_core_init(struct vbg_dev *gdev, u32 fixed_events); void vbg_core_exit(struct vbg_dev *gdev); -struct vbg_session *vbg_core_open_session(struct vbg_dev *gdev, bool user); +struct vbg_session *vbg_core_open_session(struct vbg_dev *gdev, u32 requestor); void vbg_core_close_session(struct vbg_session *session); int vbg_core_ioctl(struct vbg_session *session, unsigned int req, void *data); int vbg_core_set_mouse_status(struct vbg_dev *gdev, u32 features); @@ -172,12 +172,13 @@ irqreturn_t vbg_core_isr(int irq, void *dev_id); void vbg_linux_mouse_event(struct vbg_dev *gdev); /* Private (non exported) functions form vboxguest_utils.c */ -void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type); +void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type, + u32 requestor); void vbg_req_free(void *req, size_t len); int vbg_req_perform(struct vbg_dev *gdev, void *req); int vbg_hgcm_call32( - struct vbg_dev *gdev, u32 client_id, u32 function, u32 timeout_ms, - struct vmmdev_hgcm_function_parameter32 *parm32, u32 parm_count, - int *vbox_status); + struct vbg_dev *gdev, u32 requestor, u32 client_id, u32 function, + u32 timeout_ms, struct vmmdev_hgcm_function_parameter32 *parm32, + u32 parm_count, int *vbox_status); #endif diff --git a/drivers/virt/vboxguest/vboxguest_linux.c b/drivers/virt/vboxguest/vboxguest_linux.c index 6e2a9619192d..6e8c0f1c1056 100644 --- a/drivers/virt/vboxguest/vboxguest_linux.c +++ b/drivers/virt/vboxguest/vboxguest_linux.c @@ -5,6 +5,7 @@ * Copyright (C) 2006-2016 Oracle Corporation */ +#include <linux/cred.h> #include <linux/input.h> #include <linux/kernel.h> #include <linux/miscdevice.h> @@ -28,6 +29,23 @@ static DEFINE_MUTEX(vbg_gdev_mutex); /** Global vbg_gdev pointer used by vbg_get/put_gdev. */ static struct vbg_dev *vbg_gdev; +static u32 vbg_misc_device_requestor(struct inode *inode) +{ + u32 requestor = VMMDEV_REQUESTOR_USERMODE | + VMMDEV_REQUESTOR_CON_DONT_KNOW | + VMMDEV_REQUESTOR_TRUST_NOT_GIVEN; + + if (from_kuid(current_user_ns(), current->cred->uid) == 0) + requestor |= VMMDEV_REQUESTOR_USR_ROOT; + else + requestor |= VMMDEV_REQUESTOR_USR_USER; + + if (in_egroup_p(inode->i_gid)) + requestor |= VMMDEV_REQUESTOR_GRP_VBOX; + + return requestor; +} + static int vbg_misc_device_open(struct inode *inode, struct file *filp) { struct vbg_session *session; @@ -36,7 +54,7 @@ static int vbg_misc_device_open(struct inode *inode, struct file *filp) /* misc_open sets filp->private_data to our misc device */ gdev = container_of(filp->private_data, struct vbg_dev, misc_device); - session = vbg_core_open_session(gdev, false); + session = vbg_core_open_session(gdev, vbg_misc_device_requestor(inode)); if (IS_ERR(session)) return PTR_ERR(session); @@ -53,7 +71,8 @@ static int vbg_misc_device_user_open(struct inode *inode, struct file *filp) gdev = container_of(filp->private_data, struct vbg_dev, misc_device_user); - session = vbg_core_open_session(gdev, false); + session = vbg_core_open_session(gdev, vbg_misc_device_requestor(inode) | + VMMDEV_REQUESTOR_USER_DEVICE); if (IS_ERR(session)) return PTR_ERR(session); @@ -115,7 +134,8 @@ static long vbg_misc_device_ioctl(struct file *filp, unsigned int req, req == VBG_IOCTL_VMMDEV_REQUEST_BIG; if (is_vmmdev_req) - buf = vbg_req_alloc(size, VBG_IOCTL_HDR_TYPE_DEFAULT); + buf = vbg_req_alloc(size, VBG_IOCTL_HDR_TYPE_DEFAULT, + session->requestor); else buf = kmalloc(size, GFP_KERNEL); if (!buf) diff --git a/drivers/virt/vboxguest/vboxguest_utils.c b/drivers/virt/vboxguest/vboxguest_utils.c index bf4474214b4d..75fd140b02ff 100644 --- a/drivers/virt/vboxguest/vboxguest_utils.c +++ b/drivers/virt/vboxguest/vboxguest_utils.c @@ -62,7 +62,8 @@ VBG_LOG(vbg_err, pr_err); VBG_LOG(vbg_debug, pr_debug); #endif -void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type) +void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type, + u32 requestor) { struct vmmdev_request_header *req; int order = get_order(PAGE_ALIGN(len)); @@ -78,7 +79,7 @@ void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type) req->request_type = req_type; req->rc = VERR_GENERAL_FAILURE; req->reserved1 = 0; - req->reserved2 = 0; + req->requestor = requestor; return req; } @@ -119,7 +120,7 @@ static bool hgcm_req_done(struct vbg_dev *gdev, return done; } -int vbg_hgcm_connect(struct vbg_dev *gdev, +int vbg_hgcm_connect(struct vbg_dev *gdev, u32 requestor, struct vmmdev_hgcm_service_location *loc, u32 *client_id, int *vbox_status) { @@ -127,7 +128,7 @@ int vbg_hgcm_connect(struct vbg_dev *gdev, int rc; hgcm_connect = vbg_req_alloc(sizeof(*hgcm_connect), - VMMDEVREQ_HGCM_CONNECT); + VMMDEVREQ_HGCM_CONNECT, requestor); if (!hgcm_connect) return -ENOMEM; @@ -153,13 +154,15 @@ int vbg_hgcm_connect(struct vbg_dev *gdev, } EXPORT_SYMBOL(vbg_hgcm_connect); -int vbg_hgcm_disconnect(struct vbg_dev *gdev, u32 client_id, int *vbox_status) +int vbg_hgcm_disconnect(struct vbg_dev *gdev, u32 requestor, + u32 client_id, int *vbox_status) { struct vmmdev_hgcm_disconnect *hgcm_disconnect = NULL; int rc; hgcm_disconnect = vbg_req_alloc(sizeof(*hgcm_disconnect), - VMMDEVREQ_HGCM_DISCONNECT); + VMMDEVREQ_HGCM_DISCONNECT, + requestor); if (!hgcm_disconnect) return -ENOMEM; @@ -593,9 +596,10 @@ static int hgcm_call_copy_back_result( return 0; } -int vbg_hgcm_call(struct vbg_dev *gdev, u32 client_id, u32 function, - u32 timeout_ms, struct vmmdev_hgcm_function_parameter *parms, - u32 parm_count, int *vbox_status) +int vbg_hgcm_call(struct vbg_dev *gdev, u32 requestor, u32 client_id, + u32 function, u32 timeout_ms, + struct vmmdev_hgcm_function_parameter *parms, u32 parm_count, + int *vbox_status) { struct vmmdev_hgcm_call *call; void **bounce_bufs = NULL; @@ -615,7 +619,7 @@ int vbg_hgcm_call(struct vbg_dev *gdev, u32 client_id, u32 function, goto free_bounce_bufs; } - call = vbg_req_alloc(size, VMMDEVREQ_HGCM_CALL); + call = vbg_req_alloc(size, VMMDEVREQ_HGCM_CALL, requestor); if (!call) { ret = -ENOMEM; goto free_bounce_bufs; @@ -647,9 +651,9 @@ EXPORT_SYMBOL(vbg_hgcm_call); #ifdef CONFIG_COMPAT int vbg_hgcm_call32( - struct vbg_dev *gdev, u32 client_id, u32 function, u32 timeout_ms, - struct vmmdev_hgcm_function_parameter32 *parm32, u32 parm_count, - int *vbox_status) + struct vbg_dev *gdev, u32 requestor, u32 client_id, u32 function, + u32 timeout_ms, struct vmmdev_hgcm_function_parameter32 *parm32, + u32 parm_count, int *vbox_status) { struct vmmdev_hgcm_function_parameter *parm64 = NULL; u32 i, size; @@ -689,7 +693,7 @@ int vbg_hgcm_call32( goto out_free; } - ret = vbg_hgcm_call(gdev, client_id, function, timeout_ms, + ret = vbg_hgcm_call(gdev, requestor, client_id, function, timeout_ms, parm64, parm_count, vbox_status); if (ret < 0) goto out_free; diff --git a/drivers/virt/vboxguest/vboxguest_version.h b/drivers/virt/vboxguest/vboxguest_version.h index 77f0c8f8a231..84834dad38d5 100644 --- a/drivers/virt/vboxguest/vboxguest_version.h +++ b/drivers/virt/vboxguest/vboxguest_version.h @@ -9,11 +9,10 @@ #ifndef __VBOX_VERSION_H__ #define __VBOX_VERSION_H__ -/* Last synced October 4th 2017 */ -#define VBG_VERSION_MAJOR 5 -#define VBG_VERSION_MINOR 2 +#define VBG_VERSION_MAJOR 6 +#define VBG_VERSION_MINOR 0 #define VBG_VERSION_BUILD 0 -#define VBG_SVN_REV 68940 -#define VBG_VERSION_STRING "5.2.0" +#define VBG_SVN_REV 127566 +#define VBG_VERSION_STRING "6.0.0" #endif diff --git a/drivers/virt/vboxguest/vmmdev.h b/drivers/virt/vboxguest/vmmdev.h index 5e2ae978935d..6337b8d75d96 100644 --- a/drivers/virt/vboxguest/vmmdev.h +++ b/drivers/virt/vboxguest/vmmdev.h @@ -98,8 +98,8 @@ struct vmmdev_request_header { s32 rc; /** Reserved field no.1. MBZ. */ u32 reserved1; - /** Reserved field no.2. MBZ. */ - u32 reserved2; + /** IN: Requestor information (VMMDEV_REQUESTOR_*) */ + u32 requestor; }; VMMDEV_ASSERT_SIZE(vmmdev_request_header, 24); @@ -247,6 +247,8 @@ struct vmmdev_guest_info { }; VMMDEV_ASSERT_SIZE(vmmdev_guest_info, 24 + 8); +#define VMMDEV_GUEST_INFO2_ADDITIONS_FEATURES_REQUESTOR_INFO BIT(0) + /** struct vmmdev_guestinfo2 - Guest information report, version 2. */ struct vmmdev_guest_info2 { /** Header. */ @@ -259,7 +261,7 @@ struct vmmdev_guest_info2 { u32 additions_build; /** SVN revision. */ u32 additions_revision; - /** Feature mask, currently unused. */ + /** Feature mask. */ u32 additions_features; /** * The intentional meaning of this field was: diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c index d0584c040c60..7a0398bb84f7 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -255,9 +255,11 @@ void vp_del_vqs(struct virtio_device *vdev) for (i = 0; i < vp_dev->msix_used_vectors; ++i) free_irq(pci_irq_vector(vp_dev->pci_dev, i), vp_dev); - for (i = 0; i < vp_dev->msix_vectors; i++) - if (vp_dev->msix_affinity_masks[i]) - free_cpumask_var(vp_dev->msix_affinity_masks[i]); + if (vp_dev->msix_affinity_masks) { + for (i = 0; i < vp_dev->msix_vectors; i++) + if (vp_dev->msix_affinity_masks[i]) + free_cpumask_var(vp_dev->msix_affinity_masks[i]); + } if (vp_dev->msix_enabled) { /* Disable the vector used for configuration */ diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 18846afb39da..5df92c308286 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -882,6 +882,8 @@ static struct virtqueue *vring_create_virtqueue_split( GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO); if (queue) break; + if (!may_reduce_num) + return NULL; } if (!num) diff --git a/drivers/w1/masters/ds2490.c b/drivers/w1/masters/ds2490.c index 0f4ecfcdb549..a9fb77585272 100644 --- a/drivers/w1/masters/ds2490.c +++ b/drivers/w1/masters/ds2490.c @@ -1016,15 +1016,15 @@ static int ds_probe(struct usb_interface *intf, /* alternative 3, 1ms interrupt (greatly speeds search), 64 byte bulk */ alt = 3; err = usb_set_interface(dev->udev, - intf->altsetting[alt].desc.bInterfaceNumber, alt); + intf->cur_altsetting->desc.bInterfaceNumber, alt); if (err) { dev_err(&dev->udev->dev, "Failed to set alternative setting %d " "for %d interface: err=%d.\n", alt, - intf->altsetting[alt].desc.bInterfaceNumber, err); + intf->cur_altsetting->desc.bInterfaceNumber, err); goto err_out_clear; } - iface_desc = &intf->altsetting[alt]; + iface_desc = intf->cur_altsetting; if (iface_desc->desc.bNumEndpoints != NUM_EP-1) { pr_info("Num endpoints=%d. It is not DS9490R.\n", iface_desc->desc.bNumEndpoints); diff --git a/drivers/xen/privcmd-buf.c b/drivers/xen/privcmd-buf.c index de01a6d0059d..a1c61e351d3f 100644 --- a/drivers/xen/privcmd-buf.c +++ b/drivers/xen/privcmd-buf.c @@ -140,8 +140,7 @@ static int privcmd_buf_mmap(struct file *file, struct vm_area_struct *vma) if (!(vma->vm_flags & VM_SHARED)) return -EINVAL; - vma_priv = kzalloc(sizeof(*vma_priv) + count * sizeof(void *), - GFP_KERNEL); + vma_priv = kzalloc(struct_size(vma_priv, pages, count), GFP_KERNEL); if (!vma_priv) return -ENOMEM; diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index c3e201025ef0..0782ff3c2273 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -622,9 +622,7 @@ static int xenbus_file_open(struct inode *inode, struct file *filp) if (xen_store_evtchn == 0) return -ENOENT; - nonseekable_open(inode, filp); - - filp->f_mode &= ~FMODE_ATOMIC_POS; /* cdev-style semantics */ + stream_open(inode, filp); u = kzalloc(sizeof(*u), GFP_KERNEL); if (u == NULL) diff --git a/fs/afs/callback.c b/fs/afs/callback.c index 1c7955f5cdaf..128f2dbe256a 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -203,8 +203,7 @@ void afs_put_cb_interest(struct afs_net *net, struct afs_cb_interest *cbi) */ void afs_init_callback_state(struct afs_server *server) { - if (!test_and_clear_bit(AFS_SERVER_FL_NEW, &server->flags)) - server->cb_s_break++; + server->cb_s_break++; } /* diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index 8ee5972893ed..2f8acb4c556d 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -34,7 +34,7 @@ static void SRXAFSCB_TellMeAboutYourself(struct work_struct *); static int afs_deliver_yfs_cb_callback(struct afs_call *); #define CM_NAME(name) \ - const char afs_SRXCB##name##_name[] __tracepoint_string = \ + char afs_SRXCB##name##_name[] __tracepoint_string = \ "CB." #name /* diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index ca08c83168f5..0b37867b5c20 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -1515,8 +1515,8 @@ static int afs_fs_setattr_size64(struct afs_fs_cursor *fc, struct iattr *attr) xdr_encode_AFS_StoreStatus(&bp, attr); - *bp++ = 0; /* position of start of write */ - *bp++ = 0; + *bp++ = htonl(attr->ia_size >> 32); /* position of start of write */ + *bp++ = htonl((u32) attr->ia_size); *bp++ = 0; /* size of write */ *bp++ = 0; *bp++ = htonl(attr->ia_size >> 32); /* new file length */ @@ -1564,7 +1564,7 @@ static int afs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr) xdr_encode_AFS_StoreStatus(&bp, attr); - *bp++ = 0; /* position of start of write */ + *bp++ = htonl(attr->ia_size); /* position of start of write */ *bp++ = 0; /* size of write */ *bp++ = htonl(attr->ia_size); /* new file length */ diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 1a4ce07fb406..9cedc3fc1b77 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -216,9 +216,7 @@ struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root) set_nlink(inode, 2); inode->i_uid = GLOBAL_ROOT_UID; inode->i_gid = GLOBAL_ROOT_GID; - inode->i_ctime.tv_sec = get_seconds(); - inode->i_ctime.tv_nsec = 0; - inode->i_atime = inode->i_mtime = inode->i_ctime; + inode->i_ctime = inode->i_atime = inode->i_mtime = current_time(inode); inode->i_blocks = 0; inode_set_iversion_raw(inode, 0); inode->i_generation = 0; diff --git a/fs/afs/internal.h b/fs/afs/internal.h index bb1f244b2b3a..3904ab0b9563 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -474,7 +474,6 @@ struct afs_server { time64_t put_time; /* Time at which last put */ time64_t update_at; /* Time at which to next update the record */ unsigned long flags; -#define AFS_SERVER_FL_NEW 0 /* New server, don't inc cb_s_break */ #define AFS_SERVER_FL_NOT_READY 1 /* The record is not ready for use */ #define AFS_SERVER_FL_NOT_FOUND 2 /* VL server says no such server */ #define AFS_SERVER_FL_VL_FAIL 3 /* Failed to access VL server */ @@ -827,7 +826,7 @@ static inline struct afs_cb_interest *afs_get_cb_interest(struct afs_cb_interest static inline unsigned int afs_calc_vnode_cb_break(struct afs_vnode *vnode) { - return vnode->cb_break + vnode->cb_s_break + vnode->cb_v_break; + return vnode->cb_break + vnode->cb_v_break; } static inline bool afs_cb_is_broken(unsigned int cb_break, @@ -835,7 +834,6 @@ static inline bool afs_cb_is_broken(unsigned int cb_break, const struct afs_cb_interest *cbi) { return !cbi || cb_break != (vnode->cb_break + - cbi->server->cb_s_break + vnode->volume->cb_v_break); } diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 2c588f9bbbda..15c7e82d80cb 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -572,13 +572,17 @@ static void afs_deliver_to_call(struct afs_call *call) case -ENODATA: case -EBADMSG: case -EMSGSIZE: - default: abort_code = RXGEN_CC_UNMARSHAL; if (state != AFS_CALL_CL_AWAIT_REPLY) abort_code = RXGEN_SS_UNMARSHAL; rxrpc_kernel_abort_call(call->net->socket, call->rxcall, abort_code, ret, "KUM"); goto local_abort; + default: + abort_code = RX_USER_ABORT; + rxrpc_kernel_abort_call(call->net->socket, call->rxcall, + abort_code, ret, "KER"); + goto local_abort; } } @@ -610,6 +614,7 @@ static long afs_wait_for_call_to_complete(struct afs_call *call, bool stalled = false; u64 rtt; u32 life, last_life; + bool rxrpc_complete = false; DECLARE_WAITQUEUE(myself, current); @@ -621,7 +626,7 @@ static long afs_wait_for_call_to_complete(struct afs_call *call, rtt2 = 2; timeout = rtt2; - last_life = rxrpc_kernel_check_life(call->net->socket, call->rxcall); + rxrpc_kernel_check_life(call->net->socket, call->rxcall, &last_life); add_wait_queue(&call->waitq, &myself); for (;;) { @@ -639,7 +644,12 @@ static long afs_wait_for_call_to_complete(struct afs_call *call, if (afs_check_call_state(call, AFS_CALL_COMPLETE)) break; - life = rxrpc_kernel_check_life(call->net->socket, call->rxcall); + if (!rxrpc_kernel_check_life(call->net->socket, call->rxcall, &life)) { + /* rxrpc terminated the call. */ + rxrpc_complete = true; + break; + } + if (timeout == 0 && life == last_life && signal_pending(current)) { if (stalled) @@ -663,12 +673,16 @@ static long afs_wait_for_call_to_complete(struct afs_call *call, remove_wait_queue(&call->waitq, &myself); __set_current_state(TASK_RUNNING); - /* Kill off the call if it's still live. */ if (!afs_check_call_state(call, AFS_CALL_COMPLETE)) { - _debug("call interrupted"); - if (rxrpc_kernel_abort_call(call->net->socket, call->rxcall, - RX_USER_ABORT, -EINTR, "KWI")) - afs_set_call_complete(call, -EINTR, 0); + if (rxrpc_complete) { + afs_set_call_complete(call, call->error, call->abort_code); + } else { + /* Kill off the call if it's still live. */ + _debug("call interrupted"); + if (rxrpc_kernel_abort_call(call->net->socket, call->rxcall, + RX_USER_ABORT, -EINTR, "KWI")) + afs_set_call_complete(call, -EINTR, 0); + } } spin_lock_bh(&call->state_lock); diff --git a/fs/afs/server.c b/fs/afs/server.c index 642afa2e9783..65b33b6da48b 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -226,7 +226,6 @@ static struct afs_server *afs_alloc_server(struct afs_net *net, RCU_INIT_POINTER(server->addresses, alist); server->addr_version = alist->version; server->uuid = *uuid; - server->flags = (1UL << AFS_SERVER_FL_NEW); server->update_at = ktime_get_real_seconds() + afs_server_update_delay; rwlock_init(&server->fs_lock); INIT_HLIST_HEAD(&server->cb_volumes); diff --git a/fs/afs/write.c b/fs/afs/write.c index 72efcfcf9f95..0122d7445fba 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -264,6 +264,7 @@ static void afs_kill_pages(struct address_space *mapping, first = page->index + 1; lock_page(page); generic_error_remove_page(mapping, page); + unlock_page(page); } __pagevec_release(&pv); diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c index 5aa57929e8c2..6e97a42d24d1 100644 --- a/fs/afs/yfsclient.c +++ b/fs/afs/yfsclient.c @@ -1514,7 +1514,7 @@ static int yfs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr) bp = xdr_encode_u32(bp, 0); /* RPC flags */ bp = xdr_encode_YFSFid(bp, &vnode->fid); bp = xdr_encode_YFS_StoreStatus(bp, attr); - bp = xdr_encode_u64(bp, 0); /* position of start of write */ + bp = xdr_encode_u64(bp, attr->ia_size); /* position of start of write */ bp = xdr_encode_u64(bp, 0); /* size of write */ bp = xdr_encode_u64(bp, attr->ia_size); /* new file length */ yfs_check_req(call, bp); @@ -181,7 +181,7 @@ struct poll_iocb { struct file *file; struct wait_queue_head *head; __poll_t events; - bool woken; + bool done; bool cancelled; struct wait_queue_entry wait; struct work_struct work; @@ -204,8 +204,7 @@ struct aio_kiocb { struct kioctx *ki_ctx; kiocb_cancel_fn *ki_cancel; - struct iocb __user *ki_user_iocb; /* user's aiocb */ - __u64 ki_user_data; /* user's data for completion */ + struct io_event ki_res; struct list_head ki_list; /* the aio core uses this * for cancellation */ @@ -1022,6 +1021,9 @@ static bool get_reqs_available(struct kioctx *ctx) /* aio_get_req * Allocate a slot for an aio request. * Returns NULL if no requests are free. + * + * The refcount is initialized to 2 - one for the async op completion, + * one for the synchronous code that does this. */ static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx) { @@ -1031,10 +1033,15 @@ static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx) if (unlikely(!req)) return NULL; + if (unlikely(!get_reqs_available(ctx))) { + kmem_cache_free(kiocb_cachep, req); + return NULL; + } + percpu_ref_get(&ctx->reqs); req->ki_ctx = ctx; INIT_LIST_HEAD(&req->ki_list); - refcount_set(&req->ki_refcnt, 0); + refcount_set(&req->ki_refcnt, 2); req->ki_eventfd = NULL; return req; } @@ -1067,30 +1074,20 @@ out: return ret; } -static inline void iocb_put(struct aio_kiocb *iocb) -{ - if (refcount_read(&iocb->ki_refcnt) == 0 || - refcount_dec_and_test(&iocb->ki_refcnt)) { - if (iocb->ki_filp) - fput(iocb->ki_filp); - percpu_ref_put(&iocb->ki_ctx->reqs); - kmem_cache_free(kiocb_cachep, iocb); - } -} - -static void aio_fill_event(struct io_event *ev, struct aio_kiocb *iocb, - long res, long res2) +static inline void iocb_destroy(struct aio_kiocb *iocb) { - ev->obj = (u64)(unsigned long)iocb->ki_user_iocb; - ev->data = iocb->ki_user_data; - ev->res = res; - ev->res2 = res2; + if (iocb->ki_eventfd) + eventfd_ctx_put(iocb->ki_eventfd); + if (iocb->ki_filp) + fput(iocb->ki_filp); + percpu_ref_put(&iocb->ki_ctx->reqs); + kmem_cache_free(kiocb_cachep, iocb); } /* aio_complete * Called when the io request on the given iocb is complete. */ -static void aio_complete(struct aio_kiocb *iocb, long res, long res2) +static void aio_complete(struct aio_kiocb *iocb) { struct kioctx *ctx = iocb->ki_ctx; struct aio_ring *ring; @@ -1114,14 +1111,14 @@ static void aio_complete(struct aio_kiocb *iocb, long res, long res2) ev_page = kmap_atomic(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]); event = ev_page + pos % AIO_EVENTS_PER_PAGE; - aio_fill_event(event, iocb, res, res2); + *event = iocb->ki_res; kunmap_atomic(ev_page); flush_dcache_page(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]); - pr_debug("%p[%u]: %p: %p %Lx %lx %lx\n", - ctx, tail, iocb, iocb->ki_user_iocb, iocb->ki_user_data, - res, res2); + pr_debug("%p[%u]: %p: %p %Lx %Lx %Lx\n", ctx, tail, iocb, + (void __user *)(unsigned long)iocb->ki_res.obj, + iocb->ki_res.data, iocb->ki_res.res, iocb->ki_res.res2); /* after flagging the request as done, we * must never even look at it again @@ -1148,10 +1145,8 @@ static void aio_complete(struct aio_kiocb *iocb, long res, long res2) * eventfd. The eventfd_signal() function is safe to be called * from IRQ context. */ - if (iocb->ki_eventfd) { + if (iocb->ki_eventfd) eventfd_signal(iocb->ki_eventfd, 1); - eventfd_ctx_put(iocb->ki_eventfd); - } /* * We have to order our ring_info tail store above and test @@ -1163,7 +1158,14 @@ static void aio_complete(struct aio_kiocb *iocb, long res, long res2) if (waitqueue_active(&ctx->wait)) wake_up(&ctx->wait); - iocb_put(iocb); +} + +static inline void iocb_put(struct aio_kiocb *iocb) +{ + if (refcount_dec_and_test(&iocb->ki_refcnt)) { + aio_complete(iocb); + iocb_destroy(iocb); + } } /* aio_read_events_ring @@ -1437,7 +1439,9 @@ static void aio_complete_rw(struct kiocb *kiocb, long res, long res2) file_end_write(kiocb->ki_filp); } - aio_complete(iocb, res, res2); + iocb->ki_res.res = res; + iocb->ki_res.res2 = res2; + iocb_put(iocb); } static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) @@ -1514,13 +1518,13 @@ static inline void aio_rw_done(struct kiocb *req, ssize_t ret) } } -static ssize_t aio_read(struct kiocb *req, const struct iocb *iocb, +static int aio_read(struct kiocb *req, const struct iocb *iocb, bool vectored, bool compat) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct iov_iter iter; struct file *file; - ssize_t ret; + int ret; ret = aio_prep_rw(req, iocb); if (ret) @@ -1542,13 +1546,13 @@ static ssize_t aio_read(struct kiocb *req, const struct iocb *iocb, return ret; } -static ssize_t aio_write(struct kiocb *req, const struct iocb *iocb, +static int aio_write(struct kiocb *req, const struct iocb *iocb, bool vectored, bool compat) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct iov_iter iter; struct file *file; - ssize_t ret; + int ret; ret = aio_prep_rw(req, iocb); if (ret) @@ -1585,11 +1589,10 @@ static ssize_t aio_write(struct kiocb *req, const struct iocb *iocb, static void aio_fsync_work(struct work_struct *work) { - struct fsync_iocb *req = container_of(work, struct fsync_iocb, work); - int ret; + struct aio_kiocb *iocb = container_of(work, struct aio_kiocb, fsync.work); - ret = vfs_fsync(req->file, req->datasync); - aio_complete(container_of(req, struct aio_kiocb, fsync), ret, 0); + iocb->ki_res.res = vfs_fsync(iocb->fsync.file, iocb->fsync.datasync); + iocb_put(iocb); } static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb, @@ -1608,11 +1611,6 @@ static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb, return 0; } -static inline void aio_poll_complete(struct aio_kiocb *iocb, __poll_t mask) -{ - aio_complete(iocb, mangle_poll(mask), 0); -} - static void aio_poll_complete_work(struct work_struct *work) { struct poll_iocb *req = container_of(work, struct poll_iocb, work); @@ -1638,9 +1636,11 @@ static void aio_poll_complete_work(struct work_struct *work) return; } list_del_init(&iocb->ki_list); + iocb->ki_res.res = mangle_poll(mask); + req->done = true; spin_unlock_irq(&ctx->ctx_lock); - aio_poll_complete(iocb, mask); + iocb_put(iocb); } /* assumes we are called with irqs disabled */ @@ -1668,31 +1668,27 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, __poll_t mask = key_to_poll(key); unsigned long flags; - req->woken = true; - /* for instances that support it check for an event match first: */ - if (mask) { - if (!(mask & req->events)) - return 0; + if (mask && !(mask & req->events)) + return 0; + + list_del_init(&req->wait.entry); + if (mask && spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) { /* * Try to complete the iocb inline if we can. Use * irqsave/irqrestore because not all filesystems (e.g. fuse) * call this function with IRQs disabled and because IRQs * have to be disabled before ctx_lock is obtained. */ - if (spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) { - list_del(&iocb->ki_list); - spin_unlock_irqrestore(&iocb->ki_ctx->ctx_lock, flags); - - list_del_init(&req->wait.entry); - aio_poll_complete(iocb, mask); - return 1; - } + list_del(&iocb->ki_list); + iocb->ki_res.res = mangle_poll(mask); + req->done = true; + spin_unlock_irqrestore(&iocb->ki_ctx->ctx_lock, flags); + iocb_put(iocb); + } else { + schedule_work(&req->work); } - - list_del_init(&req->wait.entry); - schedule_work(&req->work); return 1; } @@ -1719,11 +1715,12 @@ aio_poll_queue_proc(struct file *file, struct wait_queue_head *head, add_wait_queue(head, &pt->iocb->poll.wait); } -static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) +static int aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) { struct kioctx *ctx = aiocb->ki_ctx; struct poll_iocb *req = &aiocb->poll; struct aio_poll_table apt; + bool cancel = false; __poll_t mask; /* reject any unknown events outside the normal event mask. */ @@ -1737,7 +1734,7 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP; req->head = NULL; - req->woken = false; + req->done = false; req->cancelled = false; apt.pt._qproc = aio_poll_queue_proc; @@ -1749,156 +1746,135 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) INIT_LIST_HEAD(&req->wait.entry); init_waitqueue_func_entry(&req->wait, aio_poll_wake); - /* one for removal from waitqueue, one for this function */ - refcount_set(&aiocb->ki_refcnt, 2); - mask = vfs_poll(req->file, &apt.pt) & req->events; - if (unlikely(!req->head)) { - /* we did not manage to set up a waitqueue, done */ - goto out; - } - spin_lock_irq(&ctx->ctx_lock); - spin_lock(&req->head->lock); - if (req->woken) { - /* wake_up context handles the rest */ - mask = 0; + if (likely(req->head)) { + spin_lock(&req->head->lock); + if (unlikely(list_empty(&req->wait.entry))) { + if (apt.error) + cancel = true; + apt.error = 0; + mask = 0; + } + if (mask || apt.error) { + list_del_init(&req->wait.entry); + } else if (cancel) { + WRITE_ONCE(req->cancelled, true); + } else if (!req->done) { /* actually waiting for an event */ + list_add_tail(&aiocb->ki_list, &ctx->active_reqs); + aiocb->ki_cancel = aio_poll_cancel; + } + spin_unlock(&req->head->lock); + } + if (mask) { /* no async, we'd stolen it */ + aiocb->ki_res.res = mangle_poll(mask); apt.error = 0; - } else if (mask || apt.error) { - /* if we get an error or a mask we are done */ - WARN_ON_ONCE(list_empty(&req->wait.entry)); - list_del_init(&req->wait.entry); - } else { - /* actually waiting for an event */ - list_add_tail(&aiocb->ki_list, &ctx->active_reqs); - aiocb->ki_cancel = aio_poll_cancel; } - spin_unlock(&req->head->lock); spin_unlock_irq(&ctx->ctx_lock); - -out: - if (unlikely(apt.error)) - return apt.error; - if (mask) - aio_poll_complete(aiocb, mask); - iocb_put(aiocb); - return 0; + iocb_put(aiocb); + return apt.error; } static int __io_submit_one(struct kioctx *ctx, const struct iocb *iocb, - struct iocb __user *user_iocb, bool compat) + struct iocb __user *user_iocb, struct aio_kiocb *req, + bool compat) { - struct aio_kiocb *req; - ssize_t ret; - - /* enforce forwards compatibility on users */ - if (unlikely(iocb->aio_reserved2)) { - pr_debug("EINVAL: reserve field set\n"); - return -EINVAL; - } - - /* prevent overflows */ - if (unlikely( - (iocb->aio_buf != (unsigned long)iocb->aio_buf) || - (iocb->aio_nbytes != (size_t)iocb->aio_nbytes) || - ((ssize_t)iocb->aio_nbytes < 0) - )) { - pr_debug("EINVAL: overflow check\n"); - return -EINVAL; - } - - if (!get_reqs_available(ctx)) - return -EAGAIN; - - ret = -EAGAIN; - req = aio_get_req(ctx); - if (unlikely(!req)) - goto out_put_reqs_available; - req->ki_filp = fget(iocb->aio_fildes); - ret = -EBADF; if (unlikely(!req->ki_filp)) - goto out_put_req; + return -EBADF; if (iocb->aio_flags & IOCB_FLAG_RESFD) { + struct eventfd_ctx *eventfd; /* * If the IOCB_FLAG_RESFD flag of aio_flags is set, get an * instance of the file* now. The file descriptor must be * an eventfd() fd, and will be signaled for each completed * event using the eventfd_signal() function. */ - req->ki_eventfd = eventfd_ctx_fdget((int) iocb->aio_resfd); - if (IS_ERR(req->ki_eventfd)) { - ret = PTR_ERR(req->ki_eventfd); - req->ki_eventfd = NULL; - goto out_put_req; - } + eventfd = eventfd_ctx_fdget(iocb->aio_resfd); + if (IS_ERR(eventfd)) + return PTR_ERR(eventfd); + + req->ki_eventfd = eventfd; } - ret = put_user(KIOCB_KEY, &user_iocb->aio_key); - if (unlikely(ret)) { + if (unlikely(put_user(KIOCB_KEY, &user_iocb->aio_key))) { pr_debug("EFAULT: aio_key\n"); - goto out_put_req; + return -EFAULT; } - req->ki_user_iocb = user_iocb; - req->ki_user_data = iocb->aio_data; + req->ki_res.obj = (u64)(unsigned long)user_iocb; + req->ki_res.data = iocb->aio_data; + req->ki_res.res = 0; + req->ki_res.res2 = 0; switch (iocb->aio_lio_opcode) { case IOCB_CMD_PREAD: - ret = aio_read(&req->rw, iocb, false, compat); - break; + return aio_read(&req->rw, iocb, false, compat); case IOCB_CMD_PWRITE: - ret = aio_write(&req->rw, iocb, false, compat); - break; + return aio_write(&req->rw, iocb, false, compat); case IOCB_CMD_PREADV: - ret = aio_read(&req->rw, iocb, true, compat); - break; + return aio_read(&req->rw, iocb, true, compat); case IOCB_CMD_PWRITEV: - ret = aio_write(&req->rw, iocb, true, compat); - break; + return aio_write(&req->rw, iocb, true, compat); case IOCB_CMD_FSYNC: - ret = aio_fsync(&req->fsync, iocb, false); - break; + return aio_fsync(&req->fsync, iocb, false); case IOCB_CMD_FDSYNC: - ret = aio_fsync(&req->fsync, iocb, true); - break; + return aio_fsync(&req->fsync, iocb, true); case IOCB_CMD_POLL: - ret = aio_poll(req, iocb); - break; + return aio_poll(req, iocb); default: pr_debug("invalid aio operation %d\n", iocb->aio_lio_opcode); - ret = -EINVAL; - break; + return -EINVAL; } - - /* - * If ret is 0, we'd either done aio_complete() ourselves or have - * arranged for that to be done asynchronously. Anything non-zero - * means that we need to destroy req ourselves. - */ - if (ret) - goto out_put_req; - return 0; -out_put_req: - if (req->ki_eventfd) - eventfd_ctx_put(req->ki_eventfd); - iocb_put(req); -out_put_reqs_available: - put_reqs_available(ctx, 1); - return ret; } static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, bool compat) { + struct aio_kiocb *req; struct iocb iocb; + int err; if (unlikely(copy_from_user(&iocb, user_iocb, sizeof(iocb)))) return -EFAULT; - return __io_submit_one(ctx, &iocb, user_iocb, compat); + /* enforce forwards compatibility on users */ + if (unlikely(iocb.aio_reserved2)) { + pr_debug("EINVAL: reserve field set\n"); + return -EINVAL; + } + + /* prevent overflows */ + if (unlikely( + (iocb.aio_buf != (unsigned long)iocb.aio_buf) || + (iocb.aio_nbytes != (size_t)iocb.aio_nbytes) || + ((ssize_t)iocb.aio_nbytes < 0) + )) { + pr_debug("EINVAL: overflow check\n"); + return -EINVAL; + } + + req = aio_get_req(ctx); + if (unlikely(!req)) + return -EAGAIN; + + err = __io_submit_one(ctx, &iocb, user_iocb, req, compat); + + /* Done with the synchronous reference */ + iocb_put(req); + + /* + * If err is 0, we'd either done aio_complete() ourselves or have + * arranged for that to be done asynchronously. Anything non-zero + * means that we need to destroy req ourselves. + */ + if (unlikely(err)) { + iocb_destroy(req); + put_reqs_available(ctx, 1); + } + return err; } /* sys_io_submit: @@ -1997,24 +1973,6 @@ COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id, } #endif -/* lookup_kiocb - * Finds a given iocb for cancellation. - */ -static struct aio_kiocb * -lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb) -{ - struct aio_kiocb *kiocb; - - assert_spin_locked(&ctx->ctx_lock); - - /* TODO: use a hash or array, this sucks. */ - list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) { - if (kiocb->ki_user_iocb == iocb) - return kiocb; - } - return NULL; -} - /* sys_io_cancel: * Attempts to cancel an iocb previously passed to io_submit. If * the operation is successfully cancelled, the resulting event is @@ -2032,6 +1990,7 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, struct aio_kiocb *kiocb; int ret = -EINVAL; u32 key; + u64 obj = (u64)(unsigned long)iocb; if (unlikely(get_user(key, &iocb->aio_key))) return -EFAULT; @@ -2043,10 +2002,13 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, return -EINVAL; spin_lock_irq(&ctx->ctx_lock); - kiocb = lookup_kiocb(ctx, iocb); - if (kiocb) { - ret = kiocb->ki_cancel(&kiocb->rw); - list_del_init(&kiocb->ki_list); + /* TODO: use a hash or array, this sucks. */ + list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) { + if (kiocb->ki_res.obj == obj) { + ret = kiocb->ki_cancel(&kiocb->rw); + list_del_init(&kiocb->ki_list); + break; + } } spin_unlock_irq(&ctx->ctx_lock); diff --git a/fs/block_dev.c b/fs/block_dev.c index 78d3257435c0..bb28e2ead679 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -264,7 +264,8 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, bio_for_each_segment_all(bvec, &bio, i, iter_all) { if (should_dirty && !PageCompound(bvec->bv_page)) set_page_dirty_lock(bvec->bv_page); - put_page(bvec->bv_page); + if (!bio_flagged(&bio, BIO_NO_PAGE_REF)) + put_page(bvec->bv_page); } if (unlikely(bio.bi_status)) @@ -307,10 +308,10 @@ static void blkdev_bio_end_io(struct bio *bio) struct blkdev_dio *dio = bio->bi_private; bool should_dirty = dio->should_dirty; - if (dio->multi_bio && !atomic_dec_and_test(&dio->ref)) { - if (bio->bi_status && !dio->bio.bi_status) - dio->bio.bi_status = bio->bi_status; - } else { + if (bio->bi_status && !dio->bio.bi_status) + dio->bio.bi_status = bio->bi_status; + + if (!dio->multi_bio || atomic_dec_and_test(&dio->ref)) { if (!dio->is_sync) { struct kiocb *iocb = dio->iocb; ssize_t ret; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 1d49694e6ae3..c5880329ae37 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -6174,7 +6174,7 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info, * * This is overestimating in most cases. */ - qgroup_rsv_size = outstanding_extents * fs_info->nodesize; + qgroup_rsv_size = (u64)outstanding_extents * fs_info->nodesize; spin_lock(&block_rsv->lock); block_rsv->size = reserve_size; diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 920bf3b4b0ef..cccc75d15970 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -7,6 +7,7 @@ #include <linux/slab.h> #include <linux/pagemap.h> #include <linux/highmem.h> +#include <linux/sched/mm.h> #include "ctree.h" #include "disk-io.h" #include "transaction.h" @@ -427,9 +428,13 @@ blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio, unsigned long this_sum_bytes = 0; int i; u64 offset; + unsigned nofs_flag; + + nofs_flag = memalloc_nofs_save(); + sums = kvzalloc(btrfs_ordered_sum_size(fs_info, bio->bi_iter.bi_size), + GFP_KERNEL); + memalloc_nofs_restore(nofs_flag); - sums = kzalloc(btrfs_ordered_sum_size(fs_info, bio->bi_iter.bi_size), - GFP_NOFS); if (!sums) return BLK_STS_RESOURCE; @@ -472,8 +477,10 @@ blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio, bytes_left = bio->bi_iter.bi_size - total_bytes; - sums = kzalloc(btrfs_ordered_sum_size(fs_info, bytes_left), - GFP_NOFS); + nofs_flag = memalloc_nofs_save(); + sums = kvzalloc(btrfs_ordered_sum_size(fs_info, + bytes_left), GFP_KERNEL); + memalloc_nofs_restore(nofs_flag); BUG_ON(!sums); /* -ENOMEM */ sums->len = bytes_left; ordered = btrfs_lookup_ordered_extent(inode, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 82fdda8ff5ab..2973608824ec 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -6783,7 +6783,7 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode, u64 extent_start = 0; u64 extent_end = 0; u64 objectid = btrfs_ino(inode); - u8 extent_type; + int extent_type = -1; struct btrfs_path *path = NULL; struct btrfs_root *root = inode->root; struct btrfs_file_extent_item *item; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index ec2d8919e7fb..cd4e693406a0 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -501,6 +501,16 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg) if (!capable(CAP_SYS_ADMIN)) return -EPERM; + /* + * If the fs is mounted with nologreplay, which requires it to be + * mounted in RO mode as well, we can not allow discard on free space + * inside block groups, because log trees refer to extents that are not + * pinned in a block group's free space cache (pinning the extents is + * precisely the first phase of replaying a log tree). + */ + if (btrfs_test_opt(fs_info, NOLOGREPLAY)) + return -EROFS; + rcu_read_lock(); list_for_each_entry_rcu(device, &fs_info->fs_devices->devices, dev_list) { diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 6fde2b2741ef..45e3cfd1198b 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -6,6 +6,7 @@ #include <linux/slab.h> #include <linux/blkdev.h> #include <linux/writeback.h> +#include <linux/sched/mm.h> #include "ctree.h" #include "transaction.h" #include "btrfs_inode.h" @@ -442,7 +443,7 @@ void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry) cur = entry->list.next; sum = list_entry(cur, struct btrfs_ordered_sum, list); list_del(&sum->list); - kfree(sum); + kvfree(sum); } kmem_cache_free(btrfs_ordered_extent_cache, entry); } diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c index dc6140013ae8..61d22a56c0ba 100644 --- a/fs/btrfs/props.c +++ b/fs/btrfs/props.c @@ -366,11 +366,11 @@ int btrfs_subvol_inherit_props(struct btrfs_trans_handle *trans, static int prop_compression_validate(const char *value, size_t len) { - if (!strncmp("lzo", value, len)) + if (!strncmp("lzo", value, 3)) return 0; - else if (!strncmp("zlib", value, len)) + else if (!strncmp("zlib", value, 4)) return 0; - else if (!strncmp("zstd", value, len)) + else if (!strncmp("zstd", value, 4)) return 0; return -EINVAL; @@ -396,7 +396,7 @@ static int prop_compression_apply(struct inode *inode, btrfs_set_fs_incompat(fs_info, COMPRESS_LZO); } else if (!strncmp("zlib", value, 4)) { type = BTRFS_COMPRESS_ZLIB; - } else if (!strncmp("zstd", value, len)) { + } else if (!strncmp("zstd", value, 4)) { type = BTRFS_COMPRESS_ZSTD; btrfs_set_fs_incompat(fs_info, COMPRESS_ZSTD); } else { diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index eb680b715dd6..e659d9d61107 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1922,8 +1922,8 @@ static int qgroup_trace_new_subtree_blocks(struct btrfs_trans_handle* trans, int i; /* Level sanity check */ - if (cur_level < 0 || cur_level >= BTRFS_MAX_LEVEL || - root_level < 0 || root_level >= BTRFS_MAX_LEVEL || + if (cur_level < 0 || cur_level >= BTRFS_MAX_LEVEL - 1 || + root_level < 0 || root_level >= BTRFS_MAX_LEVEL - 1 || root_level < cur_level) { btrfs_err_rl(fs_info, "%s: bad levels, cur_level=%d root_level=%d", diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 1869ba8e5981..67a6f7d47402 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -2430,8 +2430,9 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio, bitmap_clear(rbio->dbitmap, pagenr, 1); kunmap(p); - for (stripe = 0; stripe < rbio->real_stripes; stripe++) + for (stripe = 0; stripe < nr_data; stripe++) kunmap(page_in_rbio(rbio, stripe, pagenr, 0)); + kunmap(p_page); } __free_page(p_page); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index acdad6d658f5..e4e665f422fc 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1886,8 +1886,10 @@ static void btrfs_cleanup_pending_block_groups(struct btrfs_trans_handle *trans) } } -static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info) +static inline int btrfs_start_delalloc_flush(struct btrfs_trans_handle *trans) { + struct btrfs_fs_info *fs_info = trans->fs_info; + /* * We use writeback_inodes_sb here because if we used * btrfs_start_delalloc_roots we would deadlock with fs freeze. @@ -1897,15 +1899,50 @@ static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info) * from already being in a transaction and our join_transaction doesn't * have to re-take the fs freeze lock. */ - if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) + if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) { writeback_inodes_sb(fs_info->sb, WB_REASON_SYNC); + } else { + struct btrfs_pending_snapshot *pending; + struct list_head *head = &trans->transaction->pending_snapshots; + + /* + * Flush dellaloc for any root that is going to be snapshotted. + * This is done to avoid a corrupted version of files, in the + * snapshots, that had both buffered and direct IO writes (even + * if they were done sequentially) due to an unordered update of + * the inode's size on disk. + */ + list_for_each_entry(pending, head, list) { + int ret; + + ret = btrfs_start_delalloc_snapshot(pending->root); + if (ret) + return ret; + } + } return 0; } -static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info) +static inline void btrfs_wait_delalloc_flush(struct btrfs_trans_handle *trans) { - if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) + struct btrfs_fs_info *fs_info = trans->fs_info; + + if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) { btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); + } else { + struct btrfs_pending_snapshot *pending; + struct list_head *head = &trans->transaction->pending_snapshots; + + /* + * Wait for any dellaloc that we started previously for the roots + * that are going to be snapshotted. This is to avoid a corrupted + * version of files in the snapshots that had both buffered and + * direct IO writes (even if they were done sequentially). + */ + list_for_each_entry(pending, head, list) + btrfs_wait_ordered_extents(pending->root, + U64_MAX, 0, U64_MAX); + } } int btrfs_commit_transaction(struct btrfs_trans_handle *trans) @@ -2023,7 +2060,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) extwriter_counter_dec(cur_trans, trans->type); - ret = btrfs_start_delalloc_flush(fs_info); + ret = btrfs_start_delalloc_flush(trans); if (ret) goto cleanup_transaction; @@ -2039,7 +2076,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) if (ret) goto cleanup_transaction; - btrfs_wait_delalloc_flush(fs_info); + btrfs_wait_delalloc_flush(trans); btrfs_scrub_pause(fs_info); /* diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index f06454a55e00..561884f60d35 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3578,9 +3578,16 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans, } btrfs_release_path(path); - /* find the first key from this transaction again */ + /* + * Find the first key from this transaction again. See the note for + * log_new_dir_dentries, if we're logging a directory recursively we + * won't be holding its i_mutex, which means we can modify the directory + * while we're logging it. If we remove an entry between our first + * search and this search we'll not find the key again and can just + * bail. + */ ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0); - if (WARN_ON(ret != 0)) + if (ret != 0) goto done; /* @@ -4544,6 +4551,19 @@ static int logged_inode_size(struct btrfs_root *log, struct btrfs_inode *inode, item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_inode_item); *size_ret = btrfs_inode_size(path->nodes[0], item); + /* + * If the in-memory inode's i_size is smaller then the inode + * size stored in the btree, return the inode's i_size, so + * that we get a correct inode size after replaying the log + * when before a power failure we had a shrinking truncate + * followed by addition of a new name (rename / new hard link). + * Otherwise return the inode size from the btree, to avoid + * data loss when replaying a log due to previously doing a + * write that expands the inode's size and logging a new name + * immediately after. + */ + if (*size_ret > inode->vfs_inode.i_size) + *size_ret = inode->vfs_inode.i_size; } btrfs_release_path(path); @@ -4705,15 +4725,8 @@ static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans, struct btrfs_file_extent_item); if (btrfs_file_extent_type(leaf, extent) == - BTRFS_FILE_EXTENT_INLINE) { - len = btrfs_file_extent_ram_bytes(leaf, extent); - ASSERT(len == i_size || - (len == fs_info->sectorsize && - btrfs_file_extent_compression(leaf, extent) != - BTRFS_COMPRESS_NONE) || - (len < i_size && i_size < fs_info->sectorsize)); + BTRFS_FILE_EXTENT_INLINE) return 0; - } len = btrfs_file_extent_num_bytes(leaf, extent); /* Last extent goes beyond i_size, no need to log a hole. */ diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 9024eee889b9..db934ceae9c1 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -6407,7 +6407,7 @@ static void btrfs_end_bio(struct bio *bio) if (bio_op(bio) == REQ_OP_WRITE) btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS); - else + else if (!(bio->bi_opf & REQ_RAHEAD)) btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_READ_ERRS); if (bio->bi_opf & REQ_PREFLUSH) diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index a8f429882249..0637149fb9f9 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1766,6 +1766,7 @@ static ssize_t ceph_read_dir(struct file *file, char __user *buf, size_t size, unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn) { struct ceph_inode_info *dci = ceph_inode(dir); + unsigned hash; switch (dci->i_dir_layout.dl_dir_hash) { case 0: /* for backward compat */ @@ -1773,8 +1774,11 @@ unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn) return dn->d_name.hash; default: - return ceph_str_hash(dci->i_dir_layout.dl_dir_hash, + spin_lock(&dn->d_lock); + hash = ceph_str_hash(dci->i_dir_layout.dl_dir_hash, dn->d_name.name, dn->d_name.len); + spin_unlock(&dn->d_lock); + return hash; } } diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index e3346628efe2..c2feb310ac1e 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -524,6 +524,7 @@ static void ceph_i_callback(struct rcu_head *head) struct inode *inode = container_of(head, struct inode, i_rcu); struct ceph_inode_info *ci = ceph_inode(inode); + kfree(ci->i_symlink); kmem_cache_free(ceph_inode_cachep, ci); } @@ -566,7 +567,6 @@ void ceph_destroy_inode(struct inode *inode) } } - kfree(ci->i_symlink); while ((n = rb_first(&ci->i_fragtree)) != NULL) { frag = rb_entry(n, struct ceph_inode_frag, node); rb_erase(n, &ci->i_fragtree); @@ -1163,6 +1163,19 @@ static int splice_dentry(struct dentry **pdn, struct inode *in) return 0; } +static int d_name_cmp(struct dentry *dentry, const char *name, size_t len) +{ + int ret; + + /* take d_lock to ensure dentry->d_name stability */ + spin_lock(&dentry->d_lock); + ret = dentry->d_name.len - len; + if (!ret) + ret = memcmp(dentry->d_name.name, name, len); + spin_unlock(&dentry->d_lock); + return ret; +} + /* * Incorporate results into the local cache. This is either just * one inode, or a directory, dentry, and possibly linked-to inode (e.g., @@ -1412,7 +1425,8 @@ retry_lookup: err = splice_dentry(&req->r_dentry, in); if (err < 0) goto done; - } else if (rinfo->head->is_dentry) { + } else if (rinfo->head->is_dentry && + !d_name_cmp(req->r_dentry, rinfo->dname, rinfo->dname_len)) { struct ceph_vino *ptvino = NULL; if ((le32_to_cpu(rinfo->diri.in->cap.caps) & CEPH_CAP_FILE_SHARED) || diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 21c33ed048ed..9049c2a3e972 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1414,6 +1414,15 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap, list_add(&ci->i_prealloc_cap_flush->i_list, &to_remove); ci->i_prealloc_cap_flush = NULL; } + + if (drop && + ci->i_wrbuffer_ref_head == 0 && + ci->i_wr_ref == 0 && + ci->i_dirty_caps == 0 && + ci->i_flushing_caps == 0) { + ceph_put_snap_context(ci->i_head_snapc); + ci->i_head_snapc = NULL; + } } spin_unlock(&ci->i_ceph_lock); while (!list_empty(&to_remove)) { @@ -2161,10 +2170,39 @@ retry: return path; } +/* Duplicate the dentry->d_name.name safely */ +static int clone_dentry_name(struct dentry *dentry, const char **ppath, + int *ppathlen) +{ + u32 len; + char *name; + +retry: + len = READ_ONCE(dentry->d_name.len); + name = kmalloc(len + 1, GFP_NOFS); + if (!name) + return -ENOMEM; + + spin_lock(&dentry->d_lock); + if (dentry->d_name.len != len) { + spin_unlock(&dentry->d_lock); + kfree(name); + goto retry; + } + memcpy(name, dentry->d_name.name, len); + spin_unlock(&dentry->d_lock); + + name[len] = '\0'; + *ppath = name; + *ppathlen = len; + return 0; +} + static int build_dentry_path(struct dentry *dentry, struct inode *dir, const char **ppath, int *ppathlen, u64 *pino, - int *pfreepath) + bool *pfreepath, bool parent_locked) { + int ret; char *path; rcu_read_lock(); @@ -2173,8 +2211,15 @@ static int build_dentry_path(struct dentry *dentry, struct inode *dir, if (dir && ceph_snap(dir) == CEPH_NOSNAP) { *pino = ceph_ino(dir); rcu_read_unlock(); - *ppath = dentry->d_name.name; - *ppathlen = dentry->d_name.len; + if (parent_locked) { + *ppath = dentry->d_name.name; + *ppathlen = dentry->d_name.len; + } else { + ret = clone_dentry_name(dentry, ppath, ppathlen); + if (ret) + return ret; + *pfreepath = true; + } return 0; } rcu_read_unlock(); @@ -2182,13 +2227,13 @@ static int build_dentry_path(struct dentry *dentry, struct inode *dir, if (IS_ERR(path)) return PTR_ERR(path); *ppath = path; - *pfreepath = 1; + *pfreepath = true; return 0; } static int build_inode_path(struct inode *inode, const char **ppath, int *ppathlen, u64 *pino, - int *pfreepath) + bool *pfreepath) { struct dentry *dentry; char *path; @@ -2204,7 +2249,7 @@ static int build_inode_path(struct inode *inode, if (IS_ERR(path)) return PTR_ERR(path); *ppath = path; - *pfreepath = 1; + *pfreepath = true; return 0; } @@ -2215,7 +2260,7 @@ static int build_inode_path(struct inode *inode, static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry, struct inode *rdiri, const char *rpath, u64 rino, const char **ppath, int *pathlen, - u64 *ino, int *freepath) + u64 *ino, bool *freepath, bool parent_locked) { int r = 0; @@ -2225,7 +2270,7 @@ static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry, ceph_snap(rinode)); } else if (rdentry) { r = build_dentry_path(rdentry, rdiri, ppath, pathlen, ino, - freepath); + freepath, parent_locked); dout(" dentry %p %llx/%.*s\n", rdentry, *ino, *pathlen, *ppath); } else if (rpath || rino) { @@ -2251,7 +2296,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, const char *path2 = NULL; u64 ino1 = 0, ino2 = 0; int pathlen1 = 0, pathlen2 = 0; - int freepath1 = 0, freepath2 = 0; + bool freepath1 = false, freepath2 = false; int len; u16 releases; void *p, *end; @@ -2259,16 +2304,19 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, ret = set_request_path_attr(req->r_inode, req->r_dentry, req->r_parent, req->r_path1, req->r_ino1.ino, - &path1, &pathlen1, &ino1, &freepath1); + &path1, &pathlen1, &ino1, &freepath1, + test_bit(CEPH_MDS_R_PARENT_LOCKED, + &req->r_req_flags)); if (ret < 0) { msg = ERR_PTR(ret); goto out; } + /* If r_old_dentry is set, then assume that its parent is locked */ ret = set_request_path_attr(NULL, req->r_old_dentry, req->r_old_dentry_dir, req->r_path2, req->r_ino2.ino, - &path2, &pathlen2, &ino2, &freepath2); + &path2, &pathlen2, &ino2, &freepath2, true); if (ret < 0) { msg = ERR_PTR(ret); goto out_free1; diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 89aa37fa0f84..b26e12cd8ec3 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -572,7 +572,12 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci) old_snapc = NULL; update_snapc: - if (ci->i_head_snapc) { + if (ci->i_wrbuffer_ref_head == 0 && + ci->i_wr_ref == 0 && + ci->i_dirty_caps == 0 && + ci->i_flushing_caps == 0) { + ci->i_head_snapc = NULL; + } else { ci->i_head_snapc = ceph_get_snap_context(new_snapc); dout(" new snapc is %p\n", new_snapc); } diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index f9b71c12cc9f..a05bf1d6e1d0 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -559,6 +559,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root) tcon->ses->server->echo_interval / HZ); if (tcon->snapshot_time) seq_printf(s, ",snapshot=%llu", tcon->snapshot_time); + if (tcon->handle_timeout) + seq_printf(s, ",handletimeout=%u", tcon->handle_timeout); /* convert actimeo and display it in seconds */ seq_printf(s, ",actimeo=%lu", cifs_sb->actimeo / HZ); diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 38feae812b47..585ad3207cb1 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -60,6 +60,12 @@ #define CIFS_MAX_ACTIMEO (1 << 30) /* + * Max persistent and resilient handle timeout (milliseconds). + * Windows durable max was 960000 (16 minutes) + */ +#define SMB3_MAX_HANDLE_TIMEOUT 960000 + +/* * MAX_REQ is the maximum number of requests that WE will send * on one socket concurrently. */ @@ -586,6 +592,7 @@ struct smb_vol { struct nls_table *local_nls; unsigned int echo_interval; /* echo interval in secs */ __u64 snapshot_time; /* needed for timewarp tokens */ + __u32 handle_timeout; /* persistent and durable handle timeout in ms */ unsigned int max_credits; /* smb3 max_credits 10 < credits < 60000 */ }; @@ -1058,6 +1065,7 @@ struct cifs_tcon { __u32 vol_serial_number; __le64 vol_create_time; __u64 snapshot_time; /* for timewarp tokens - timestamp of snapshot */ + __u32 handle_timeout; /* persistent and durable handle timeout in ms */ __u32 ss_flags; /* sector size flags */ __u32 perf_sector_size; /* best sector size for perf */ __u32 max_chunks; @@ -1325,6 +1333,7 @@ cifsFileInfo_get_locked(struct cifsFileInfo *cifs_file) } struct cifsFileInfo *cifsFileInfo_get(struct cifsFileInfo *cifs_file); +void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_hdlr); void cifsFileInfo_put(struct cifsFileInfo *cifs_file); #define CIFS_CACHE_READ_FLG 1 @@ -1847,6 +1856,7 @@ GLOBAL_EXTERN spinlock_t gidsidlock; #endif /* CONFIG_CIFS_ACL */ void cifs_oplock_break(struct work_struct *work); +void cifs_queue_oplock_break(struct cifsFileInfo *cfile); extern const struct slow_work_ops cifs_oplock_break_ops; extern struct workqueue_struct *cifsiod_wq; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index a8e9738db691..4c0e44489f21 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -103,7 +103,7 @@ enum { Opt_cruid, Opt_gid, Opt_file_mode, Opt_dirmode, Opt_port, Opt_blocksize, Opt_rsize, Opt_wsize, Opt_actimeo, - Opt_echo_interval, Opt_max_credits, + Opt_echo_interval, Opt_max_credits, Opt_handletimeout, Opt_snapshot, /* Mount options which take string value */ @@ -208,6 +208,7 @@ static const match_table_t cifs_mount_option_tokens = { { Opt_rsize, "rsize=%s" }, { Opt_wsize, "wsize=%s" }, { Opt_actimeo, "actimeo=%s" }, + { Opt_handletimeout, "handletimeout=%s" }, { Opt_echo_interval, "echo_interval=%s" }, { Opt_max_credits, "max_credits=%s" }, { Opt_snapshot, "snapshot=%s" }, @@ -1619,6 +1620,9 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, vol->actimeo = CIFS_DEF_ACTIMEO; + /* Most clients set timeout to 0, allows server to use its default */ + vol->handle_timeout = 0; /* See MS-SMB2 spec section 2.2.14.2.12 */ + /* offer SMB2.1 and later (SMB3 etc). Secure and widely accepted */ vol->ops = &smb30_operations; vol->vals = &smbdefault_values; @@ -2017,6 +2021,18 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, goto cifs_parse_mount_err; } break; + case Opt_handletimeout: + if (get_option_ul(args, &option)) { + cifs_dbg(VFS, "%s: Invalid handletimeout value\n", + __func__); + goto cifs_parse_mount_err; + } + vol->handle_timeout = option; + if (vol->handle_timeout > SMB3_MAX_HANDLE_TIMEOUT) { + cifs_dbg(VFS, "Invalid handle cache timeout, longer than 16 minutes\n"); + goto cifs_parse_mount_err; + } + break; case Opt_echo_interval: if (get_option_ul(args, &option)) { cifs_dbg(VFS, "%s: Invalid echo interval value\n", @@ -3183,6 +3199,8 @@ static int match_tcon(struct cifs_tcon *tcon, struct smb_vol *volume_info) return 0; if (tcon->snapshot_time != volume_info->snapshot_time) return 0; + if (tcon->handle_timeout != volume_info->handle_timeout) + return 0; return 1; } @@ -3297,6 +3315,16 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info) tcon->snapshot_time = volume_info->snapshot_time; } + if (volume_info->handle_timeout) { + if (ses->server->vals->protocol_id == 0) { + cifs_dbg(VFS, + "Use SMB2.1 or later for handle timeout option\n"); + rc = -EOPNOTSUPP; + goto out_fail; + } else + tcon->handle_timeout = volume_info->handle_timeout; + } + tcon->ses = ses; if (volume_info->password) { tcon->password = kstrdup(volume_info->password, GFP_KERNEL); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 89006e044973..7037a137fa53 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -360,13 +360,31 @@ cifsFileInfo_get(struct cifsFileInfo *cifs_file) return cifs_file; } -/* - * Release a reference on the file private data. This may involve closing - * the filehandle out on the server. Must be called without holding - * tcon->open_file_lock and cifs_file->file_info_lock. +/** + * cifsFileInfo_put - release a reference of file priv data + * + * Always potentially wait for oplock handler. See _cifsFileInfo_put(). */ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) { + _cifsFileInfo_put(cifs_file, true); +} + +/** + * _cifsFileInfo_put - release a reference of file priv data + * + * This may involve closing the filehandle @cifs_file out on the + * server. Must be called without holding tcon->open_file_lock and + * cifs_file->file_info_lock. + * + * If @wait_for_oplock_handler is true and we are releasing the last + * reference, wait for any running oplock break handler of the file + * and cancel any pending one. If calling this function from the + * oplock break handler, you need to pass false. + * + */ +void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler) +{ struct inode *inode = d_inode(cifs_file->dentry); struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink); struct TCP_Server_Info *server = tcon->ses->server; @@ -414,7 +432,8 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) spin_unlock(&tcon->open_file_lock); - oplock_break_cancelled = cancel_work_sync(&cifs_file->oplock_break); + oplock_break_cancelled = wait_oplock_handler ? + cancel_work_sync(&cifs_file->oplock_break) : false; if (!tcon->need_reconnect && !cifs_file->invalidHandle) { struct TCP_Server_Info *server = tcon->ses->server; @@ -2858,7 +2877,6 @@ static void collect_uncached_write_data(struct cifs_aio_ctx *ctx) struct cifs_tcon *tcon; struct cifs_sb_info *cifs_sb; struct dentry *dentry = ctx->cfile->dentry; - unsigned int i; int rc; tcon = tlink_tcon(ctx->cfile->tlink); @@ -2922,10 +2940,6 @@ restart_loop: kref_put(&wdata->refcount, cifs_uncached_writedata_release); } - if (!ctx->direct_io) - for (i = 0; i < ctx->npages; i++) - put_page(ctx->bv[i].bv_page); - cifs_stats_bytes_written(tcon, ctx->total_len); set_bit(CIFS_INO_INVALID_MAPPING, &CIFS_I(dentry->d_inode)->flags); @@ -3563,7 +3577,6 @@ collect_uncached_read_data(struct cifs_aio_ctx *ctx) struct iov_iter *to = &ctx->iter; struct cifs_sb_info *cifs_sb; struct cifs_tcon *tcon; - unsigned int i; int rc; tcon = tlink_tcon(ctx->cfile->tlink); @@ -3647,15 +3660,8 @@ again: kref_put(&rdata->refcount, cifs_uncached_readdata_release); } - if (!ctx->direct_io) { - for (i = 0; i < ctx->npages; i++) { - if (ctx->should_dirty) - set_page_dirty(ctx->bv[i].bv_page); - put_page(ctx->bv[i].bv_page); - } - + if (!ctx->direct_io) ctx->total_len = ctx->len - iov_iter_count(to); - } /* mask nodata case */ if (rc == -ENODATA) @@ -4603,6 +4609,7 @@ void cifs_oplock_break(struct work_struct *work) cinode); cifs_dbg(FYI, "Oplock release rc = %d\n", rc); } + _cifsFileInfo_put(cfile, false /* do not wait for ourself */); cifs_done_oplock_break(cinode); } diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 53fdb5df0d2e..538fd7d807e4 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1735,6 +1735,10 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry, if (rc == 0 || rc != -EBUSY) goto do_rename_exit; + /* Don't fall back to using SMB on SMB 2+ mount */ + if (server->vals->protocol_id != 0) + goto do_rename_exit; + /* open-file renames don't work across directories */ if (to_dentry->d_parent != from_dentry->d_parent) goto do_rename_exit; diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index bee203055b30..0dc6f08020ac 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -501,8 +501,7 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &pCifsInode->flags); - queue_work(cifsoplockd_wq, - &netfile->oplock_break); + cifs_queue_oplock_break(netfile); netfile->oplock_break_cancelled = false; spin_unlock(&tcon->open_file_lock); @@ -607,6 +606,28 @@ void cifs_put_writer(struct cifsInodeInfo *cinode) spin_unlock(&cinode->writers_lock); } +/** + * cifs_queue_oplock_break - queue the oplock break handler for cfile + * + * This function is called from the demultiplex thread when it + * receives an oplock break for @cfile. + * + * Assumes the tcon->open_file_lock is held. + * Assumes cfile->file_info_lock is NOT held. + */ +void cifs_queue_oplock_break(struct cifsFileInfo *cfile) +{ + /* + * Bump the handle refcount now while we hold the + * open_file_lock to enforce the validity of it for the oplock + * break handler. The matching put is done at the end of the + * handler. + */ + cifsFileInfo_get(cfile); + + queue_work(cifsoplockd_wq, &cfile->oplock_break); +} + void cifs_done_oplock_break(struct cifsInodeInfo *cinode) { clear_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cinode->flags); @@ -768,6 +789,11 @@ cifs_aio_ctx_alloc(void) { struct cifs_aio_ctx *ctx; + /* + * Must use kzalloc to initialize ctx->bv to NULL and ctx->direct_io + * to false so that we know when we have to unreference pages within + * cifs_aio_ctx_release() + */ ctx = kzalloc(sizeof(struct cifs_aio_ctx), GFP_KERNEL); if (!ctx) return NULL; @@ -786,7 +812,23 @@ cifs_aio_ctx_release(struct kref *refcount) struct cifs_aio_ctx, refcount); cifsFileInfo_put(ctx->cfile); - kvfree(ctx->bv); + + /* + * ctx->bv is only set if setup_aio_ctx_iter() was call successfuly + * which means that iov_iter_get_pages() was a success and thus that + * we have taken reference on pages. + */ + if (ctx->bv) { + unsigned i; + + for (i = 0; i < ctx->npages; i++) { + if (ctx->should_dirty) + set_page_dirty(ctx->bv[i].bv_page); + put_page(ctx->bv[i].bv_page); + } + kvfree(ctx->bv); + } + kfree(ctx); } diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index b204e84b87fb..54bffb2a1786 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -68,13 +68,15 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, if (oparms->tcon->use_resilient) { - nr_ioctl_req.Timeout = 0; /* use server default (120 seconds) */ + /* default timeout is 0, servers pick default (120 seconds) */ + nr_ioctl_req.Timeout = + cpu_to_le32(oparms->tcon->handle_timeout); nr_ioctl_req.Reserved = 0; rc = SMB2_ioctl(xid, oparms->tcon, fid->persistent_fid, fid->volatile_fid, FSCTL_LMR_REQUEST_RESILIENCY, true /* is_fsctl */, (char *)&nr_ioctl_req, sizeof(nr_ioctl_req), - NULL, NULL /* no return info */); + CIFSMaxBufSize, NULL, NULL /* no return info */); if (rc == -EOPNOTSUPP) { cifs_dbg(VFS, "resiliency not supported by server, disabling\n"); diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 0e3570e40ff8..e311f58dc1c8 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -555,7 +555,7 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp, clear_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cinode->flags); - queue_work(cifsoplockd_wq, &cfile->oplock_break); + cifs_queue_oplock_break(cfile); kfree(lw); return true; } @@ -712,8 +712,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cinode->flags); spin_unlock(&cfile->file_info_lock); - queue_work(cifsoplockd_wq, - &cfile->oplock_break); + + cifs_queue_oplock_break(cfile); spin_unlock(&tcon->open_file_lock); spin_unlock(&cifs_tcp_ses_lock); diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 1022a3771e14..c36ff0d1fe2a 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -581,7 +581,7 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon) rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID, FSCTL_QUERY_NETWORK_INTERFACE_INFO, true /* is_fsctl */, NULL /* no data input */, 0 /* no data input */, - (char **)&out_buf, &ret_data_len); + CIFSMaxBufSize, (char **)&out_buf, &ret_data_len); if (rc == -EOPNOTSUPP) { cifs_dbg(FYI, "server does not support query network interfaces\n"); @@ -717,32 +717,28 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid) oparms.fid->mid = le64_to_cpu(o_rsp->sync_hdr.MessageId); #endif /* CIFS_DEBUG2 */ - if (o_rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE) - oplock = smb2_parse_lease_state(server, o_rsp, - &oparms.fid->epoch, - oparms.fid->lease_key); - else - goto oshr_exit; - - memcpy(tcon->crfid.fid, pfid, sizeof(struct cifs_fid)); tcon->crfid.tcon = tcon; tcon->crfid.is_valid = true; kref_init(&tcon->crfid.refcount); - kref_get(&tcon->crfid.refcount); + if (o_rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE) { + kref_get(&tcon->crfid.refcount); + oplock = smb2_parse_lease_state(server, o_rsp, + &oparms.fid->epoch, + oparms.fid->lease_key); + } else + goto oshr_exit; qi_rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base; if (le32_to_cpu(qi_rsp->OutputBufferLength) < sizeof(struct smb2_file_all_info)) goto oshr_exit; - rc = smb2_validate_and_copy_iov( + if (!smb2_validate_and_copy_iov( le16_to_cpu(qi_rsp->OutputBufferOffset), sizeof(struct smb2_file_all_info), &rsp_iov[1], sizeof(struct smb2_file_all_info), - (char *)&tcon->crfid.file_all_info); - if (rc) - goto oshr_exit; - tcon->crfid.file_all_info_is_valid = 1; + (char *)&tcon->crfid.file_all_info)) + tcon->crfid.file_all_info_is_valid = 1; oshr_exit: mutex_unlock(&tcon->crfid.fid_mutex); @@ -1299,7 +1295,7 @@ SMB2_request_res_key(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_ioctl(xid, tcon, persistent_fid, volatile_fid, FSCTL_SRV_REQUEST_RESUME_KEY, true /* is_fsctl */, - NULL, 0 /* no input */, + NULL, 0 /* no input */, CIFSMaxBufSize, (char **)&res_key, &ret_data_len); if (rc) { @@ -1404,7 +1400,7 @@ smb2_ioctl_query_info(const unsigned int xid, rc = SMB2_ioctl_init(tcon, &rqst[1], COMPOUND_FID, COMPOUND_FID, qi.info_type, true, NULL, - 0); + 0, CIFSMaxBufSize); } } else if (qi.flags == PASSTHRU_QUERY_INFO) { memset(&qi_iov, 0, sizeof(qi_iov)); @@ -1532,8 +1528,8 @@ smb2_copychunk_range(const unsigned int xid, rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid, trgtfile->fid.volatile_fid, FSCTL_SRV_COPYCHUNK_WRITE, true /* is_fsctl */, (char *)pcchunk, - sizeof(struct copychunk_ioctl), (char **)&retbuf, - &ret_data_len); + sizeof(struct copychunk_ioctl), CIFSMaxBufSize, + (char **)&retbuf, &ret_data_len); if (rc == 0) { if (ret_data_len != sizeof(struct copychunk_ioctl_rsp)) { @@ -1693,7 +1689,7 @@ static bool smb2_set_sparse(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, FSCTL_SET_SPARSE, true /* is_fctl */, - &setsparse, 1, NULL, NULL); + &setsparse, 1, CIFSMaxBufSize, NULL, NULL); if (rc) { tcon->broken_sparse_sup = true; cifs_dbg(FYI, "set sparse rc = %d\n", rc); @@ -1766,7 +1762,7 @@ smb2_duplicate_extents(const unsigned int xid, true /* is_fsctl */, (char *)&dup_ext_buf, sizeof(struct duplicate_extents_to_file), - NULL, + CIFSMaxBufSize, NULL, &ret_data_len); if (ret_data_len > 0) @@ -1801,7 +1797,7 @@ smb3_set_integrity(const unsigned int xid, struct cifs_tcon *tcon, true /* is_fsctl */, (char *)&integr_info, sizeof(struct fsctl_set_integrity_information_req), - NULL, + CIFSMaxBufSize, NULL, &ret_data_len); } @@ -1809,6 +1805,8 @@ smb3_set_integrity(const unsigned int xid, struct cifs_tcon *tcon, /* GMT Token is @GMT-YYYY.MM.DD-HH.MM.SS Unicode which is 48 bytes + null */ #define GMT_TOKEN_SIZE 50 +#define MIN_SNAPSHOT_ARRAY_SIZE 16 /* See MS-SMB2 section 3.3.5.15.1 */ + /* * Input buffer contains (empty) struct smb_snapshot array with size filled in * For output see struct SRV_SNAPSHOT_ARRAY in MS-SMB2 section 2.2.32.2 @@ -1820,13 +1818,29 @@ smb3_enum_snapshots(const unsigned int xid, struct cifs_tcon *tcon, char *retbuf = NULL; unsigned int ret_data_len = 0; int rc; + u32 max_response_size; struct smb_snapshot_array snapshot_in; + if (get_user(ret_data_len, (unsigned int __user *)ioc_buf)) + return -EFAULT; + + /* + * Note that for snapshot queries that servers like Azure expect that + * the first query be minimal size (and just used to get the number/size + * of previous versions) so response size must be specified as EXACTLY + * sizeof(struct snapshot_array) which is 16 when rounded up to multiple + * of eight bytes. + */ + if (ret_data_len == 0) + max_response_size = MIN_SNAPSHOT_ARRAY_SIZE; + else + max_response_size = CIFSMaxBufSize; + rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, FSCTL_SRV_ENUMERATE_SNAPSHOTS, true /* is_fsctl */, - NULL, 0 /* no input data */, + NULL, 0 /* no input data */, max_response_size, (char **)&retbuf, &ret_data_len); cifs_dbg(FYI, "enum snaphots ioctl returned %d and ret buflen is %d\n", @@ -2304,7 +2318,7 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID, FSCTL_DFS_GET_REFERRALS, true /* is_fsctl */, - (char *)dfs_req, dfs_req_size, + (char *)dfs_req, dfs_req_size, CIFSMaxBufSize, (char **)&dfs_rsp, &dfs_rsp_size); } while (rc == -EAGAIN); @@ -2375,6 +2389,8 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, &err_iov, &resp_buftype); + if (!rc) + SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); if (!rc || !err_iov.iov_base) { rc = -ENOENT; goto free_path; @@ -2658,7 +2674,8 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, rc = SMB2_ioctl_init(tcon, &rqst[num++], cfile->fid.persistent_fid, cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA, true /* is_fctl */, (char *)&fsctl_buf, - sizeof(struct file_zero_data_information)); + sizeof(struct file_zero_data_information), + CIFSMaxBufSize); if (rc) goto zero_range_exit; @@ -2735,7 +2752,8 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA, true /* is_fctl */, (char *)&fsctl_buf, - sizeof(struct file_zero_data_information), NULL, NULL); + sizeof(struct file_zero_data_information), + CIFSMaxBufSize, NULL, NULL); free_xid(xid); return rc; } diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 21ac19ff19cb..a37774a55f3a 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -832,8 +832,11 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) } else if (rsp->DialectRevision == cpu_to_le16(SMB21_PROT_ID)) { /* ops set to 3.0 by default for default so update */ ses->server->ops = &smb21_operations; - } else if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID)) + ses->server->vals = &smb21_values; + } else if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID)) { ses->server->ops = &smb311_operations; + ses->server->vals = &smb311_values; + } } else if (le16_to_cpu(rsp->DialectRevision) != ses->server->vals->protocol_id) { /* if requested single dialect ensure returned dialect matched */ @@ -1002,7 +1005,8 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon) rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID, FSCTL_VALIDATE_NEGOTIATE_INFO, true /* is_fsctl */, - (char *)pneg_inbuf, inbuflen, (char **)&pneg_rsp, &rsplen); + (char *)pneg_inbuf, inbuflen, CIFSMaxBufSize, + (char **)&pneg_rsp, &rsplen); if (rc == -EOPNOTSUPP) { /* * Old Windows versions or Netapp SMB server can return @@ -1858,8 +1862,9 @@ add_lease_context(struct TCP_Server_Info *server, struct kvec *iov, } static struct create_durable_v2 * -create_durable_v2_buf(struct cifs_fid *pfid) +create_durable_v2_buf(struct cifs_open_parms *oparms) { + struct cifs_fid *pfid = oparms->fid; struct create_durable_v2 *buf; buf = kzalloc(sizeof(struct create_durable_v2), GFP_KERNEL); @@ -1873,7 +1878,14 @@ create_durable_v2_buf(struct cifs_fid *pfid) (struct create_durable_v2, Name)); buf->ccontext.NameLength = cpu_to_le16(4); - buf->dcontext.Timeout = 0; /* Should this be configurable by workload */ + /* + * NB: Handle timeout defaults to 0, which allows server to choose + * (most servers default to 120 seconds) and most clients default to 0. + * This can be overridden at mount ("handletimeout=") if the user wants + * a different persistent (or resilient) handle timeout for all opens + * opens on a particular SMB3 mount. + */ + buf->dcontext.Timeout = cpu_to_le32(oparms->tcon->handle_timeout); buf->dcontext.Flags = cpu_to_le32(SMB2_DHANDLE_FLAG_PERSISTENT); generate_random_uuid(buf->dcontext.CreateGuid); memcpy(pfid->create_guid, buf->dcontext.CreateGuid, 16); @@ -1926,7 +1938,7 @@ add_durable_v2_context(struct kvec *iov, unsigned int *num_iovec, struct smb2_create_req *req = iov[0].iov_base; unsigned int num = *num_iovec; - iov[num].iov_base = create_durable_v2_buf(oparms->fid); + iov[num].iov_base = create_durable_v2_buf(oparms); if (iov[num].iov_base == NULL) return -ENOMEM; iov[num].iov_len = sizeof(struct create_durable_v2); @@ -2478,7 +2490,8 @@ creat_exit: int SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, u64 persistent_fid, u64 volatile_fid, u32 opcode, - bool is_fsctl, char *in_data, u32 indatalen) + bool is_fsctl, char *in_data, u32 indatalen, + __u32 max_response_size) { struct smb2_ioctl_req *req; struct kvec *iov = rqst->rq_iov; @@ -2520,16 +2533,21 @@ SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, req->OutputCount = 0; /* MBZ */ /* - * Could increase MaxOutputResponse, but that would require more - * than one credit. Windows typically sets this smaller, but for some + * In most cases max_response_size is set to 16K (CIFSMaxBufSize) + * We Could increase default MaxOutputResponse, but that could require + * more credits. Windows typically sets this smaller, but for some * ioctls it may be useful to allow server to send more. No point * limiting what the server can send as long as fits in one credit - * Unfortunately - we can not handle more than CIFS_MAX_MSG_SIZE - * (by default, note that it can be overridden to make max larger) - * in responses (except for read responses which can be bigger. - * We may want to bump this limit up + * We can not handle more than CIFS_MAX_BUF_SIZE yet but may want + * to increase this limit up in the future. + * Note that for snapshot queries that servers like Azure expect that + * the first query be minimal size (and just used to get the number/size + * of previous versions) so response size must be specified as EXACTLY + * sizeof(struct snapshot_array) which is 16 when rounded up to multiple + * of eight bytes. Currently that is the only case where we set max + * response size smaller. */ - req->MaxOutputResponse = cpu_to_le32(CIFSMaxBufSize); + req->MaxOutputResponse = cpu_to_le32(max_response_size); if (is_fsctl) req->Flags = cpu_to_le32(SMB2_0_IOCTL_IS_FSCTL); @@ -2550,13 +2568,14 @@ SMB2_ioctl_free(struct smb_rqst *rqst) cifs_small_buf_release(rqst->rq_iov[0].iov_base); /* request */ } + /* * SMB2 IOCTL is used for both IOCTLs and FSCTLs */ int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, u32 opcode, bool is_fsctl, - char *in_data, u32 indatalen, + char *in_data, u32 indatalen, u32 max_out_data_len, char **out_data, u32 *plen /* returned data len */) { struct smb_rqst rqst; @@ -2593,8 +2612,8 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, rqst.rq_iov = iov; rqst.rq_nvec = SMB2_IOCTL_IOV_SIZE; - rc = SMB2_ioctl_init(tcon, &rqst, persistent_fid, volatile_fid, - opcode, is_fsctl, in_data, indatalen); + rc = SMB2_ioctl_init(tcon, &rqst, persistent_fid, volatile_fid, opcode, + is_fsctl, in_data, indatalen, max_out_data_len); if (rc) goto ioctl_exit; @@ -2672,7 +2691,8 @@ SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_ioctl(xid, tcon, persistent_fid, volatile_fid, FSCTL_SET_COMPRESSION, true /* is_fsctl */, (char *)&fsctl_input /* data input */, - 2 /* in data len */, &ret_data /* out data */, NULL); + 2 /* in data len */, CIFSMaxBufSize /* max out data */, + &ret_data /* out data */, NULL); cifs_dbg(FYI, "set compression rc %d\n", rc); @@ -3431,8 +3451,6 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms, rqst.rq_nvec = 1; rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); - cifs_small_buf_release(req); - rsp = (struct smb2_read_rsp *)rsp_iov.iov_base; if (rc) { @@ -3448,12 +3466,15 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms, io_parms->tcon->tid, ses->Suid, io_parms->offset, 0); free_rsp_buf(resp_buftype, rsp_iov.iov_base); + cifs_small_buf_release(req); return rc == -ENODATA ? 0 : rc; } else trace_smb3_read_done(xid, req->PersistentFileId, io_parms->tcon->tid, ses->Suid, io_parms->offset, io_parms->length); + cifs_small_buf_release(req); + *nbytes = le32_to_cpu(rsp->DataLength); if ((*nbytes > CIFS_MAX_MSGSIZE) || (*nbytes > io_parms->length)) { @@ -3752,7 +3773,6 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms, rc = cifs_send_recv(xid, io_parms->tcon->ses, &rqst, &resp_buftype, flags, &rsp_iov); - cifs_small_buf_release(req); rsp = (struct smb2_write_rsp *)rsp_iov.iov_base; if (rc) { @@ -3770,6 +3790,7 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms, io_parms->offset, *nbytes); } + cifs_small_buf_release(req); free_rsp_buf(resp_buftype, rsp); return rc; } diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 3c32d0cfea69..52df125e9189 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -142,11 +142,12 @@ extern int SMB2_open_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, extern void SMB2_open_free(struct smb_rqst *rqst); extern int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, u32 opcode, - bool is_fsctl, char *in_data, u32 indatalen, + bool is_fsctl, char *in_data, u32 indatalen, u32 maxoutlen, char **out_data, u32 *plen /* returned data len */); extern int SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, u64 persistent_fid, u64 volatile_fid, u32 opcode, - bool is_fsctl, char *in_data, u32 indatalen); + bool is_fsctl, char *in_data, u32 indatalen, + __u32 max_response_size); extern void SMB2_ioctl_free(struct smb_rqst *rqst); extern int SMB2_close(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_file_id, u64 volatile_file_id); @@ -33,6 +33,7 @@ #include <linux/sizes.h> #include <linux/mmu_notifier.h> #include <linux/iomap.h> +#include <asm/pgalloc.h> #include "internal.h" #define CREATE_TRACE_POINTS @@ -1407,7 +1408,9 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, { struct address_space *mapping = vmf->vma->vm_file->f_mapping; unsigned long pmd_addr = vmf->address & PMD_MASK; + struct vm_area_struct *vma = vmf->vma; struct inode *inode = mapping->host; + pgtable_t pgtable = NULL; struct page *zero_page; spinlock_t *ptl; pmd_t pmd_entry; @@ -1422,12 +1425,22 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, *entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn, DAX_PMD | DAX_ZERO_PAGE, false); + if (arch_needs_pgtable_deposit()) { + pgtable = pte_alloc_one(vma->vm_mm); + if (!pgtable) + return VM_FAULT_OOM; + } + ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd); if (!pmd_none(*(vmf->pmd))) { spin_unlock(ptl); goto fallback; } + if (pgtable) { + pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); + mm_inc_nr_ptes(vma->vm_mm); + } pmd_entry = mk_pmd(zero_page, vmf->vma->vm_page_prot); pmd_entry = pmd_mkhuge(pmd_entry); set_pmd_at(vmf->vma->vm_mm, pmd_addr, vmf->pmd, pmd_entry); @@ -1436,6 +1449,8 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, return VM_FAULT_NOPAGE; fallback: + if (pgtable) + pte_free(vma->vm_mm, pgtable); trace_dax_pmd_load_hole_fallback(inode, vmf, zero_page, *entry); return VM_FAULT_FALLBACK; } diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 95b5e78c22b1..f25daa207421 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -163,19 +163,24 @@ static int debugfs_show_options(struct seq_file *m, struct dentry *root) return 0; } -static void debugfs_evict_inode(struct inode *inode) +static void debugfs_i_callback(struct rcu_head *head) { - truncate_inode_pages_final(&inode->i_data); - clear_inode(inode); + struct inode *inode = container_of(head, struct inode, i_rcu); if (S_ISLNK(inode->i_mode)) kfree(inode->i_link); + free_inode_nonrcu(inode); +} + +static void debugfs_destroy_inode(struct inode *inode) +{ + call_rcu(&inode->i_rcu, debugfs_i_callback); } static const struct super_operations debugfs_super_operations = { .statfs = simple_statfs, .remount_fs = debugfs_remount, .show_options = debugfs_show_options, - .evict_inode = debugfs_evict_inode, + .destroy_inode = debugfs_destroy_inode, }; static void debugfs_release_dentry(struct dentry *dentry) diff --git a/fs/fs_parser.c b/fs/fs_parser.c index 842e8f749db6..570d71043acf 100644 --- a/fs/fs_parser.c +++ b/fs/fs_parser.c @@ -410,7 +410,7 @@ bool fs_validate_description(const struct fs_parameter_description *desc) for (param = desc->specs; param->name; param++) { if (param->opt == e->opt && param->type != fs_param_is_enum) { - pr_err("VALIDATE %s: e[%lu] enum val for %s\n", + pr_err("VALIDATE %s: e[%tu] enum val for %s\n", name, e - desc->enums, param->name); good = false; } diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 8a63e52785e9..9971a35cf1ef 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -2056,10 +2056,8 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, rem += pipe->bufs[(pipe->curbuf + idx) & (pipe->buffers - 1)].len; ret = -EINVAL; - if (rem < len) { - pipe_unlock(pipe); - goto out; - } + if (rem < len) + goto out_free; rem = len; while (rem) { @@ -2077,7 +2075,9 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1); pipe->nrbufs--; } else { - pipe_buf_get(pipe, ibuf); + if (!pipe_buf_get(pipe, ibuf)) + goto out_free; + *obuf = *ibuf; obuf->flags &= ~PIPE_BUF_FLAG_GIFT; obuf->len = rem; @@ -2100,11 +2100,11 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, ret = fuse_dev_do_write(fud, &cs, len); pipe_lock(pipe); +out_free: for (idx = 0; idx < nbuf; idx++) pipe_buf_release(pipe, &bufs[idx]); pipe_unlock(pipe); -out: kvfree(bufs); return ret; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index ec32fece5e1e..9285dd4f4b1c 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -755,11 +755,17 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, umode_t mode, dev_t dev) { struct inode *inode; - struct resv_map *resv_map; + struct resv_map *resv_map = NULL; - resv_map = resv_map_alloc(); - if (!resv_map) - return NULL; + /* + * Reserve maps are only needed for inodes that can have associated + * page allocations. + */ + if (S_ISREG(mode) || S_ISLNK(mode)) { + resv_map = resv_map_alloc(); + if (!resv_map) + return NULL; + } inode = new_inode(sb); if (inode) { @@ -794,8 +800,10 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, break; } lockdep_annotate_inode_mutex_key(inode); - } else - kref_put(&resv_map->refs, resv_map_release); + } else { + if (resv_map) + kref_put(&resv_map->refs, resv_map_release); + } return inode; } diff --git a/fs/inode.c b/fs/inode.c index e9d97add2b36..9a453f3637f8 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1817,8 +1817,13 @@ int file_remove_privs(struct file *file) int kill; int error = 0; - /* Fast path for nothing security related */ - if (IS_NOSEC(inode)) + /* + * Fast path for nothing security related. + * As well for non-regular files, e.g. blkdev inodes. + * For example, blkdev_write_iter() might get here + * trying to remove privs which it is not allowed to. + */ + if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode)) return 0; kill = dentry_needs_remove_privs(dentry); diff --git a/fs/io_uring.c b/fs/io_uring.c index 6aaa30580a2b..84efb8956734 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -4,15 +4,28 @@ * supporting fast/efficient IO. * * A note on the read/write ordering memory barriers that are matched between - * the application and kernel side. When the application reads the CQ ring - * tail, it must use an appropriate smp_rmb() to order with the smp_wmb() - * the kernel uses after writing the tail. Failure to do so could cause a - * delay in when the application notices that completion events available. - * This isn't a fatal condition. Likewise, the application must use an - * appropriate smp_wmb() both before writing the SQ tail, and after writing - * the SQ tail. The first one orders the sqe writes with the tail write, and - * the latter is paired with the smp_rmb() the kernel will issue before - * reading the SQ tail on submission. + * the application and kernel side. + * + * After the application reads the CQ ring tail, it must use an + * appropriate smp_rmb() to pair with the smp_wmb() the kernel uses + * before writing the tail (using smp_load_acquire to read the tail will + * do). It also needs a smp_mb() before updating CQ head (ordering the + * entry load(s) with the head store), pairing with an implicit barrier + * through a control-dependency in io_get_cqring (smp_store_release to + * store head will do). Failure to do so could lead to reading invalid + * CQ entries. + * + * Likewise, the application must use an appropriate smp_wmb() before + * writing the SQ tail (ordering SQ entry stores with the tail store), + * which pairs with smp_load_acquire in io_get_sqring (smp_store_release + * to store the tail will do). And it needs a barrier ordering the SQ + * head load before writing new SQ entries (smp_load_acquire to read + * head will do). + * + * When using the SQ poll thread (IORING_SETUP_SQPOLL), the application + * needs to check the SQ flags for IORING_SQ_NEED_WAKEUP *after* + * updating the SQ tail; a full memory barrier smp_mb() is needed + * between. * * Also see the examples in the liburing library: * @@ -70,20 +83,108 @@ struct io_uring { u32 tail ____cacheline_aligned_in_smp; }; +/* + * This data is shared with the application through the mmap at offset + * IORING_OFF_SQ_RING. + * + * The offsets to the member fields are published through struct + * io_sqring_offsets when calling io_uring_setup. + */ struct io_sq_ring { + /* + * Head and tail offsets into the ring; the offsets need to be + * masked to get valid indices. + * + * The kernel controls head and the application controls tail. + */ struct io_uring r; + /* + * Bitmask to apply to head and tail offsets (constant, equals + * ring_entries - 1) + */ u32 ring_mask; + /* Ring size (constant, power of 2) */ u32 ring_entries; + /* + * Number of invalid entries dropped by the kernel due to + * invalid index stored in array + * + * Written by the kernel, shouldn't be modified by the + * application (i.e. get number of "new events" by comparing to + * cached value). + * + * After a new SQ head value was read by the application this + * counter includes all submissions that were dropped reaching + * the new SQ head (and possibly more). + */ u32 dropped; + /* + * Runtime flags + * + * Written by the kernel, shouldn't be modified by the + * application. + * + * The application needs a full memory barrier before checking + * for IORING_SQ_NEED_WAKEUP after updating the sq tail. + */ u32 flags; + /* + * Ring buffer of indices into array of io_uring_sqe, which is + * mmapped by the application using the IORING_OFF_SQES offset. + * + * This indirection could e.g. be used to assign fixed + * io_uring_sqe entries to operations and only submit them to + * the queue when needed. + * + * The kernel modifies neither the indices array nor the entries + * array. + */ u32 array[]; }; +/* + * This data is shared with the application through the mmap at offset + * IORING_OFF_CQ_RING. + * + * The offsets to the member fields are published through struct + * io_cqring_offsets when calling io_uring_setup. + */ struct io_cq_ring { + /* + * Head and tail offsets into the ring; the offsets need to be + * masked to get valid indices. + * + * The application controls head and the kernel tail. + */ struct io_uring r; + /* + * Bitmask to apply to head and tail offsets (constant, equals + * ring_entries - 1) + */ u32 ring_mask; + /* Ring size (constant, power of 2) */ u32 ring_entries; + /* + * Number of completion events lost because the queue was full; + * this should be avoided by the application by making sure + * there are not more requests pending thatn there is space in + * the completion queue. + * + * Written by the kernel, shouldn't be modified by the + * application (i.e. get number of "new events" by comparing to + * cached value). + * + * As completion events come in out of order this counter is not + * ordered with any other data. + */ u32 overflow; + /* + * Ring buffer of completion events. + * + * The kernel writes completion events fresh every time they are + * produced, so the application is allowed to modify pending + * entries. + */ struct io_uring_cqe cqes[]; }; @@ -221,7 +322,7 @@ struct io_kiocb { struct list_head list; unsigned int flags; refcount_t refs; -#define REQ_F_FORCE_NONBLOCK 1 /* inline submission attempt */ +#define REQ_F_NOWAIT 1 /* must not punt to workers */ #define REQ_F_IOPOLL_COMPLETED 2 /* polled IO has completed */ #define REQ_F_FIXED_FILE 4 /* ctx owns file */ #define REQ_F_SEQ_PREV 8 /* sequential with previous */ @@ -317,12 +418,6 @@ static void io_commit_cqring(struct io_ring_ctx *ctx) /* order cqe stores with ring update */ smp_store_release(&ring->r.tail, ctx->cached_cq_tail); - /* - * Write sider barrier of tail update, app has read side. See - * comment at the top of this file. - */ - smp_wmb(); - if (wq_has_sleeper(&ctx->cq_wait)) { wake_up_interruptible(&ctx->cq_wait); kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN); @@ -336,9 +431,12 @@ static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx) unsigned tail; tail = ctx->cached_cq_tail; - /* See comment at the top of the file */ - smp_rmb(); - if (tail + 1 == READ_ONCE(ring->r.head)) + /* + * writes to the cq entry need to come after reading head; the + * control dependency is enough as we're using WRITE_ONCE to + * fill the cq entry + */ + if (tail - READ_ONCE(ring->r.head) == ring->ring_entries) return NULL; ctx->cached_cq_tail++; @@ -682,11 +780,9 @@ static void io_iopoll_req_issued(struct io_kiocb *req) list_add_tail(&req->list, &ctx->poll_list); } -static void io_file_put(struct io_submit_state *state, struct file *file) +static void io_file_put(struct io_submit_state *state) { - if (!state) { - fput(file); - } else if (state->file) { + if (state->file) { int diff = state->has_refs - state->used_refs; if (diff) @@ -711,7 +807,7 @@ static struct file *io_file_get(struct io_submit_state *state, int fd) state->ios_left--; return state->file; } - io_file_put(state, NULL); + io_file_put(state); } state->file = fget_many(fd, state->ios_left); if (!state->file) @@ -742,7 +838,7 @@ static bool io_file_supports_async(struct file *file) } static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s, - bool force_nonblock, struct io_submit_state *state) + bool force_nonblock) { const struct io_uring_sqe *sqe = s->sqe; struct io_ring_ctx *ctx = req->ctx; @@ -776,10 +872,14 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s, ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags)); if (unlikely(ret)) return ret; - if (force_nonblock) { + + /* don't allow async punt if RWF_NOWAIT was requested */ + if (kiocb->ki_flags & IOCB_NOWAIT) + req->flags |= REQ_F_NOWAIT; + + if (force_nonblock) kiocb->ki_flags |= IOCB_NOWAIT; - req->flags |= REQ_F_FORCE_NONBLOCK; - } + if (ctx->flags & IORING_SETUP_IOPOLL) { if (!(kiocb->ki_flags & IOCB_DIRECT) || !kiocb->ki_filp->f_op->iopoll) @@ -940,7 +1040,7 @@ static void io_async_list_note(int rw, struct io_kiocb *req, size_t len) } static int io_read(struct io_kiocb *req, const struct sqe_submit *s, - bool force_nonblock, struct io_submit_state *state) + bool force_nonblock) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct kiocb *kiocb = &req->rw; @@ -949,7 +1049,7 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s, size_t iov_count; int ret; - ret = io_prep_rw(req, s, force_nonblock, state); + ret = io_prep_rw(req, s, force_nonblock); if (ret) return ret; file = kiocb->ki_filp; @@ -987,7 +1087,7 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s, } static int io_write(struct io_kiocb *req, const struct sqe_submit *s, - bool force_nonblock, struct io_submit_state *state) + bool force_nonblock) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct kiocb *kiocb = &req->rw; @@ -996,7 +1096,7 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s, size_t iov_count; int ret; - ret = io_prep_rw(req, s, force_nonblock, state); + ret = io_prep_rw(req, s, force_nonblock); if (ret) return ret; @@ -1022,6 +1122,8 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s, ret = rw_verify_area(WRITE, file, &kiocb->ki_pos, iov_count); if (!ret) { + ssize_t ret2; + /* * Open-code file_start_write here to grab freeze protection, * which will be released by another thread in @@ -1036,7 +1138,19 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s, SB_FREEZE_WRITE); } kiocb->ki_flags |= IOCB_WRITE; - io_rw_done(kiocb, call_write_iter(file, kiocb, &iter)); + + ret2 = call_write_iter(file, kiocb, &iter); + if (!force_nonblock || ret2 != -EAGAIN) { + io_rw_done(kiocb, ret2); + } else { + /* + * If ->needs_lock is true, we're already in async + * context. + */ + if (!s->needs_lock) + io_async_list_note(WRITE, req, iov_count); + ret = -EAGAIN; + } } out_free: kfree(iovec); @@ -1324,8 +1438,7 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe) } static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, - const struct sqe_submit *s, bool force_nonblock, - struct io_submit_state *state) + const struct sqe_submit *s, bool force_nonblock) { int ret, opcode; @@ -1341,18 +1454,18 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, case IORING_OP_READV: if (unlikely(s->sqe->buf_index)) return -EINVAL; - ret = io_read(req, s, force_nonblock, state); + ret = io_read(req, s, force_nonblock); break; case IORING_OP_WRITEV: if (unlikely(s->sqe->buf_index)) return -EINVAL; - ret = io_write(req, s, force_nonblock, state); + ret = io_write(req, s, force_nonblock); break; case IORING_OP_READ_FIXED: - ret = io_read(req, s, force_nonblock, state); + ret = io_read(req, s, force_nonblock); break; case IORING_OP_WRITE_FIXED: - ret = io_write(req, s, force_nonblock, state); + ret = io_write(req, s, force_nonblock); break; case IORING_OP_FSYNC: ret = io_fsync(req, s->sqe, force_nonblock); @@ -1425,8 +1538,7 @@ restart: struct sqe_submit *s = &req->submit; const struct io_uring_sqe *sqe = s->sqe; - /* Ensure we clear previously set forced non-block flag */ - req->flags &= ~REQ_F_FORCE_NONBLOCK; + /* Ensure we clear previously set non-block flag */ req->rw.ki_flags &= ~IOCB_NOWAIT; ret = 0; @@ -1445,7 +1557,7 @@ restart: s->has_user = cur_mm != NULL; s->needs_lock = true; do { - ret = __io_submit_sqe(ctx, req, s, false, NULL); + ret = __io_submit_sqe(ctx, req, s, false); /* * We can get EAGAIN for polled IO even though * we're forcing a sync submission from here, @@ -1456,10 +1568,11 @@ restart: break; cond_resched(); } while (1); - - /* drop submission reference */ - io_put_req(req); } + + /* drop submission reference */ + io_put_req(req); + if (ret) { io_cqring_add_event(ctx, sqe->user_data, ret, 0); io_put_req(req); @@ -1611,8 +1724,8 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s, if (unlikely(ret)) goto out; - ret = __io_submit_sqe(ctx, req, s, true, state); - if (ret == -EAGAIN) { + ret = __io_submit_sqe(ctx, req, s, true); + if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) { struct io_uring_sqe *sqe_copy; sqe_copy = kmalloc(sizeof(*sqe_copy), GFP_KERNEL); @@ -1657,7 +1770,7 @@ out: static void io_submit_state_end(struct io_submit_state *state) { blk_finish_plug(&state->plug); - io_file_put(state, NULL); + io_file_put(state); if (state->free_reqs) kmem_cache_free_bulk(req_cachep, state->free_reqs, &state->reqs[state->cur_req]); @@ -1686,24 +1799,10 @@ static void io_commit_sqring(struct io_ring_ctx *ctx) * write new data to them. */ smp_store_release(&ring->r.head, ctx->cached_sq_head); - - /* - * write side barrier of head update, app has read side. See - * comment at the top of this file - */ - smp_wmb(); } } /* - * Undo last io_get_sqring() - */ -static void io_drop_sqring(struct io_ring_ctx *ctx) -{ - ctx->cached_sq_head--; -} - -/* * Fetch an sqe, if one is available. Note that s->sqe will point to memory * that is mapped by userspace. This means that care needs to be taken to * ensure that reads are stable, as we cannot rely on userspace always @@ -1725,9 +1824,8 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s) * though the application is the one updating it. */ head = ctx->cached_sq_head; - /* See comment at the top of this file */ - smp_rmb(); - if (head == READ_ONCE(ring->r.tail)) + /* make sure SQ entry isn't read before tail */ + if (head == smp_load_acquire(&ring->r.tail)) return false; head = READ_ONCE(ring->array[head & ctx->sq_mask]); @@ -1741,8 +1839,6 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s) /* drop invalid entries */ ctx->cached_sq_head++; ring->dropped++; - /* See comment at the top of this file */ - smp_wmb(); return false; } @@ -1852,7 +1948,8 @@ static int io_sq_thread(void *data) /* Tell userspace we may need a wakeup call */ ctx->sq_ring->flags |= IORING_SQ_NEED_WAKEUP; - smp_wmb(); + /* make sure to read SQ tail after writing flags */ + smp_mb(); if (!io_get_sqring(ctx, &sqes[0])) { if (kthread_should_stop()) { @@ -1865,13 +1962,11 @@ static int io_sq_thread(void *data) finish_wait(&ctx->sqo_wait, &wait); ctx->sq_ring->flags &= ~IORING_SQ_NEED_WAKEUP; - smp_wmb(); continue; } finish_wait(&ctx->sqo_wait, &wait); ctx->sq_ring->flags &= ~IORING_SQ_NEED_WAKEUP; - smp_wmb(); } i = 0; @@ -1906,13 +2001,17 @@ static int io_sq_thread(void *data) unuse_mm(cur_mm); mmput(cur_mm); } + + if (kthread_should_park()) + kthread_parkme(); + return 0; } static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit) { struct io_submit_state state, *statep = NULL; - int i, ret = 0, submit = 0; + int i, submit = 0; if (to_submit > IO_PLUG_THRESHOLD) { io_submit_state_start(&state, ctx, to_submit); @@ -1921,6 +2020,7 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit) for (i = 0; i < to_submit; i++) { struct sqe_submit s; + int ret; if (!io_get_sqring(ctx, &s)) break; @@ -1928,21 +2028,18 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit) s.has_user = true; s.needs_lock = false; s.needs_fixed_file = false; + submit++; ret = io_submit_sqe(ctx, &s, statep); - if (ret) { - io_drop_sqring(ctx); - break; - } - - submit++; + if (ret) + io_cqring_add_event(ctx, s.sqe->user_data, ret, 0); } io_commit_sqring(ctx); if (statep) io_submit_state_end(statep); - return submit ? submit : ret; + return submit; } static unsigned io_cqring_events(struct io_cq_ring *ring) @@ -1968,7 +2065,15 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, return 0; if (sig) { - ret = set_user_sigmask(sig, &ksigmask, &sigsaved, sigsz); +#ifdef CONFIG_COMPAT + if (in_compat_syscall()) + ret = set_compat_user_sigmask((const compat_sigset_t __user *)sig, + &ksigmask, &sigsaved, sigsz); + else +#endif + ret = set_user_sigmask(sig, &ksigmask, + &sigsaved, sigsz); + if (ret) return ret; } @@ -2032,6 +2137,7 @@ static void io_sq_thread_stop(struct io_ring_ctx *ctx) if (ctx->sqo_thread) { ctx->sqo_stop = 1; mb(); + kthread_park(ctx->sqo_thread); kthread_stop(ctx->sqo_thread); ctx->sqo_thread = NULL; } @@ -2193,6 +2299,7 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, fput(ctx->user_files[i]); kfree(ctx->user_files); + ctx->user_files = NULL; ctx->nr_user_files = 0; return ret; } @@ -2213,19 +2320,23 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx, mmgrab(current->mm); ctx->sqo_mm = current->mm; - ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle); - if (!ctx->sq_thread_idle) - ctx->sq_thread_idle = HZ; + if (ctx->flags & IORING_SETUP_SQPOLL) { + ret = -EPERM; + if (!capable(CAP_SYS_ADMIN)) + goto err; - ret = -EINVAL; - if (!cpu_possible(p->sq_thread_cpu)) - goto err; + ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle); + if (!ctx->sq_thread_idle) + ctx->sq_thread_idle = HZ; - if (ctx->flags & IORING_SETUP_SQPOLL) { if (p->flags & IORING_SETUP_SQ_AFF) { - int cpu; + int cpu = array_index_nospec(p->sq_thread_cpu, + nr_cpu_ids); + + ret = -EINVAL; + if (!cpu_possible(cpu)) + goto err; - cpu = array_index_nospec(p->sq_thread_cpu, NR_CPUS); ctx->sqo_thread = kthread_create_on_cpu(io_sq_thread, ctx, cpu, "io_uring-sq"); @@ -2286,8 +2397,12 @@ static int io_account_mem(struct user_struct *user, unsigned long nr_pages) static void io_mem_free(void *ptr) { - struct page *page = virt_to_head_page(ptr); + struct page *page; + + if (!ptr) + return; + page = virt_to_head_page(ptr); if (put_page_testzero(page)) free_compound_page(page); } @@ -2328,7 +2443,7 @@ static int io_sqe_buffer_unregister(struct io_ring_ctx *ctx) if (ctx->account_mem) io_unaccount_mem(ctx->user, imu->nr_bvecs); - kfree(imu->bvec); + kvfree(imu->bvec); imu->nr_bvecs = 0; } @@ -2420,9 +2535,9 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg, if (!pages || nr_pages > got_pages) { kfree(vmas); kfree(pages); - pages = kmalloc_array(nr_pages, sizeof(struct page *), + pages = kvmalloc_array(nr_pages, sizeof(struct page *), GFP_KERNEL); - vmas = kmalloc_array(nr_pages, + vmas = kvmalloc_array(nr_pages, sizeof(struct vm_area_struct *), GFP_KERNEL); if (!pages || !vmas) { @@ -2434,7 +2549,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg, got_pages = nr_pages; } - imu->bvec = kmalloc_array(nr_pages, sizeof(struct bio_vec), + imu->bvec = kvmalloc_array(nr_pages, sizeof(struct bio_vec), GFP_KERNEL); ret = -ENOMEM; if (!imu->bvec) { @@ -2473,6 +2588,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg, } if (ctx->account_mem) io_unaccount_mem(ctx->user, nr_pages); + kvfree(imu->bvec); goto err; } @@ -2495,12 +2611,12 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg, ctx->nr_user_bufs++; } - kfree(pages); - kfree(vmas); + kvfree(pages); + kvfree(vmas); return 0; err: - kfree(pages); - kfree(vmas); + kvfree(pages); + kvfree(vmas); io_sqe_buffer_unregister(ctx); return ret; } @@ -2538,9 +2654,13 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait) __poll_t mask = 0; poll_wait(file, &ctx->cq_wait, wait); - /* See comment at the top of this file */ + /* + * synchronizes with barrier from wq_has_sleeper call in + * io_commit_cqring + */ smp_rmb(); - if (READ_ONCE(ctx->sq_ring->r.tail) + 1 != ctx->cached_sq_head) + if (READ_ONCE(ctx->sq_ring->r.tail) - ctx->cached_sq_head != + ctx->sq_ring->ring_entries) mask |= EPOLLOUT | EPOLLWRNORM; if (READ_ONCE(ctx->cq_ring->r.head) != ctx->cached_cq_tail) mask |= EPOLLIN | EPOLLRDNORM; @@ -2651,24 +2771,12 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, mutex_lock(&ctx->uring_lock); submitted = io_ring_submit(ctx, to_submit); mutex_unlock(&ctx->uring_lock); - - if (submitted < 0) - goto out_ctx; } if (flags & IORING_ENTER_GETEVENTS) { unsigned nr_events = 0; min_complete = min(min_complete, ctx->cq_entries); - /* - * The application could have included the 'to_submit' count - * in how many events it wanted to wait for. If we failed to - * submit the desired count, we may need to adjust the number - * of events to poll/wait for. - */ - if (submitted < to_submit) - min_complete = min_t(unsigned, submitted, min_complete); - if (ctx->flags & IORING_SETUP_IOPOLL) { mutex_lock(&ctx->uring_lock); ret = io_iopoll_check(ctx, &nr_events, min_complete); @@ -2714,17 +2822,12 @@ static int io_allocate_scq_urings(struct io_ring_ctx *ctx, return -EOVERFLOW; ctx->sq_sqes = io_mem_alloc(size); - if (!ctx->sq_sqes) { - io_mem_free(ctx->sq_ring); + if (!ctx->sq_sqes) return -ENOMEM; - } cq_ring = io_mem_alloc(struct_size(cq_ring, cqes, p->cq_entries)); - if (!cq_ring) { - io_mem_free(ctx->sq_ring); - io_mem_free(ctx->sq_sqes); + if (!cq_ring) return -ENOMEM; - } ctx->cq_ring = cq_ring; cq_ring->ring_mask = p->cq_entries - 1; @@ -2895,11 +2998,31 @@ SYSCALL_DEFINE2(io_uring_setup, u32, entries, static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, void __user *arg, unsigned nr_args) + __releases(ctx->uring_lock) + __acquires(ctx->uring_lock) { int ret; + /* + * We're inside the ring mutex, if the ref is already dying, then + * someone else killed the ctx or is already going through + * io_uring_register(). + */ + if (percpu_ref_is_dying(&ctx->refs)) + return -ENXIO; + percpu_ref_kill(&ctx->refs); + + /* + * Drop uring mutex before waiting for references to exit. If another + * thread is currently inside io_uring_enter() it might need to grab + * the uring_lock to make progress. If we hold it here across the drain + * wait, then we can deadlock. It's safe to drop the mutex here, since + * no new references will come in after we've killed the percpu ref. + */ + mutex_unlock(&ctx->uring_lock); wait_for_completion(&ctx->ctx_done); + mutex_lock(&ctx->uring_lock); switch (opcode) { case IORING_REGISTER_BUFFERS: diff --git a/fs/jffs2/readinode.c b/fs/jffs2/readinode.c index 389ea53ea487..bccfc40b3a74 100644 --- a/fs/jffs2/readinode.c +++ b/fs/jffs2/readinode.c @@ -1414,11 +1414,6 @@ void jffs2_do_clear_inode(struct jffs2_sb_info *c, struct jffs2_inode_info *f) jffs2_kill_fragtree(&f->fragtree, deleted?c:NULL); - if (f->target) { - kfree(f->target); - f->target = NULL; - } - fds = f->dents; while(fds) { fd = fds; diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index bb6ae387469f..05d892c79339 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -47,7 +47,10 @@ static struct inode *jffs2_alloc_inode(struct super_block *sb) static void jffs2_i_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); - kmem_cache_free(jffs2_inode_cachep, JFFS2_INODE_INFO(inode)); + struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); + + kfree(f->target); + kmem_cache_free(jffs2_inode_cachep, f); } static void jffs2_destroy_inode(struct inode *inode) diff --git a/fs/lockd/host.c b/fs/lockd/host.c index 93fb7cf0b92b..f0b5c987d6ae 100644 --- a/fs/lockd/host.c +++ b/fs/lockd/host.c @@ -290,12 +290,11 @@ void nlmclnt_release_host(struct nlm_host *host) WARN_ON_ONCE(host->h_server); - if (refcount_dec_and_test(&host->h_count)) { + if (refcount_dec_and_mutex_lock(&host->h_count, &nlm_host_mutex)) { WARN_ON_ONCE(!list_empty(&host->h_lockowners)); WARN_ON_ONCE(!list_empty(&host->h_granted)); WARN_ON_ONCE(!list_empty(&host->h_reclaim)); - mutex_lock(&nlm_host_mutex); nlm_destroy_host_locked(host); mutex_unlock(&nlm_host_mutex); } diff --git a/fs/locks.c b/fs/locks.c index eaa1cfaf73b0..71d0c6c2aac5 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1160,6 +1160,11 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, */ error = -EDEADLK; spin_lock(&blocked_lock_lock); + /* + * Ensure that we don't find any locks blocked on this + * request during deadlock detection. + */ + __locks_wake_up_blocks(request); if (likely(!posix_locks_deadlock(request, fl))) { error = FILE_LOCK_DEFERRED; __locks_insert_block(fl, request, diff --git a/fs/nfs/client.c b/fs/nfs/client.c index fb1cf1a4bda2..90d71fda65ce 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -453,7 +453,7 @@ void nfs_init_timeout_values(struct rpc_timeout *to, int proto, case XPRT_TRANSPORT_RDMA: if (retrans == NFS_UNSPEC_RETRANS) to->to_retries = NFS_DEF_TCP_RETRANS; - if (timeo == NFS_UNSPEC_TIMEO || to->to_retries == 0) + if (timeo == NFS_UNSPEC_TIMEO || to->to_initval == 0) to->to_initval = NFS_DEF_TCP_TIMEO * HZ / 10; if (to->to_initval > NFS_MAX_TCP_TIMEOUT) to->to_initval = NFS_MAX_TCP_TIMEOUT; diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index f9264e1922a2..6673d4ff5a2a 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1289,6 +1289,7 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, static int ff_layout_read_done_cb(struct rpc_task *task, struct nfs_pgio_header *hdr) { + int new_idx = hdr->pgio_mirror_idx; int err; trace_nfs4_pnfs_read(hdr, task->tk_status); @@ -1307,7 +1308,7 @@ static int ff_layout_read_done_cb(struct rpc_task *task, case -NFS4ERR_RESET_TO_PNFS: if (ff_layout_choose_best_ds_for_read(hdr->lseg, hdr->pgio_mirror_idx + 1, - &hdr->pgio_mirror_idx)) + &new_idx)) goto out_layouterror; set_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags); return task->tk_status; @@ -1320,7 +1321,9 @@ static int ff_layout_read_done_cb(struct rpc_task *task, return 0; out_layouterror: + ff_layout_read_record_layoutstats_done(task, hdr); ff_layout_send_layouterror(hdr->lseg); + hdr->pgio_mirror_idx = new_idx; out_eagain: rpc_restart_call_prepare(task); return -EAGAIN; diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index ff6f85fb676b..5196bfa7894d 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -329,9 +329,6 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src, }; ssize_t err, err2; - if (!nfs_server_capable(file_inode(dst), NFS_CAP_COPY)) - return -EOPNOTSUPP; - src_lock = nfs_get_lock_context(nfs_file_open_context(src)); if (IS_ERR(src_lock)) return PTR_ERR(src_lock); diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 45b2322e092d..00d17198ee12 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -133,8 +133,10 @@ static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t count, unsigned int flags) { + if (!nfs_server_capable(file_inode(file_out), NFS_CAP_COPY)) + return -EOPNOTSUPP; if (file_inode(file_in) == file_inode(file_out)) - return -EINVAL; + return -EOPNOTSUPP; return nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count); } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 4dbb0ee23432..741ff8c9c6ed 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2933,7 +2933,8 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, } out: - nfs4_sequence_free_slot(&opendata->o_res.seq_res); + if (!opendata->cancelled) + nfs4_sequence_free_slot(&opendata->o_res.seq_res); return ret; } @@ -6301,7 +6302,6 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl, p->arg.seqid = seqid; p->res.seqid = seqid; p->lsp = lsp; - refcount_inc(&lsp->ls_count); /* Ensure we don't close file until we're done freeing locks! */ p->ctx = get_nfs_open_context(ctx); p->l_ctx = nfs_get_lock_context(ctx); @@ -6526,7 +6526,6 @@ static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl, p->res.lock_seqid = p->arg.lock_seqid; p->lsp = lsp; p->server = server; - refcount_inc(&lsp->ls_count); p->ctx = get_nfs_open_context(ctx); locks_init_lock(&p->fl); locks_copy_lock(&p->fl, fl); diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index cfcabc33e24d..602446158bfb 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -2589,7 +2589,7 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr, ARRAY_SIZE(nfs4_acl_bitmap), &hdr); rpc_prepare_reply_pages(req, args->acl_pages, 0, - args->acl_len, replen); + args->acl_len, replen + 1); encode_nops(&hdr); } @@ -2811,7 +2811,7 @@ static void nfs4_xdr_enc_fs_locations(struct rpc_rqst *req, } rpc_prepare_reply_pages(req, (struct page **)&args->page, 0, - PAGE_SIZE, replen); + PAGE_SIZE, replen + 1); encode_nops(&hdr); } diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 23790c7b2289..c27ac96a95bd 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2041,7 +2041,8 @@ static int nfs23_validate_mount_data(void *options, memcpy(sap, &data->addr, sizeof(data->addr)); args->nfs_server.addrlen = sizeof(data->addr); args->nfs_server.port = ntohs(data->addr.sin_port); - if (!nfs_verify_server_address(sap)) + if (sap->sa_family != AF_INET || + !nfs_verify_server_address(sap)) goto out_no_address; if (!(data->flags & NFS_MOUNT_TCP)) diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 8f933e84cec1..9bc32af4e2da 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -442,7 +442,9 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp) struct nfsd3_readdirargs *argp = rqstp->rq_argp; struct nfsd3_readdirres *resp = rqstp->rq_resp; __be32 nfserr; - int count; + int count = 0; + struct page **p; + caddr_t page_addr = NULL; dprintk("nfsd: READDIR(3) %s %d bytes at %d\n", SVCFH_fmt(&argp->fh), @@ -462,7 +464,18 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp) nfserr = nfsd_readdir(rqstp, &resp->fh, (loff_t*) &argp->cookie, &resp->common, nfs3svc_encode_entry); memcpy(resp->verf, argp->verf, 8); - resp->count = resp->buffer - argp->buffer; + count = 0; + for (p = rqstp->rq_respages + 1; p < rqstp->rq_next_page; p++) { + page_addr = page_address(*p); + + if (((caddr_t)resp->buffer >= page_addr) && + ((caddr_t)resp->buffer < page_addr + PAGE_SIZE)) { + count += (caddr_t)resp->buffer - page_addr; + break; + } + count += PAGE_SIZE; + } + resp->count = count >> 2; if (resp->offset) { loff_t offset = argp->cookie; diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 93fea246f676..8d789124ed3c 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -573,6 +573,7 @@ int nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p) { struct nfsd3_readdirargs *args = rqstp->rq_argp; + int len; u32 max_blocksize = svc_max_payload(rqstp); p = decode_fh(p, &args->fh); @@ -582,8 +583,14 @@ nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p) args->verf = p; p += 2; args->dircount = ~0; args->count = ntohl(*p++); - args->count = min_t(u32, args->count, max_blocksize); - args->buffer = page_address(*(rqstp->rq_next_page++)); + len = args->count = min_t(u32, args->count, max_blocksize); + + while (len > 0) { + struct page *p = *(rqstp->rq_next_page++); + if (!args->buffer) + args->buffer = page_address(p); + len -= PAGE_SIZE; + } return xdr_argsize_check(rqstp, p); } diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index d219159b98af..7caa3801ce72 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -1010,8 +1010,9 @@ static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata) cb->cb_seq_status = 1; cb->cb_status = 0; if (minorversion) { - if (!nfsd41_cb_get_slot(clp, task)) + if (!cb->cb_holds_slot && !nfsd41_cb_get_slot(clp, task)) return; + cb->cb_holds_slot = true; } rpc_call_start(task); } @@ -1038,6 +1039,9 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback return true; } + if (!cb->cb_holds_slot) + goto need_restart; + switch (cb->cb_seq_status) { case 0: /* @@ -1076,6 +1080,7 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback cb->cb_seq_status); } + cb->cb_holds_slot = false; clear_bit(0, &clp->cl_cb_slot_busy); rpc_wake_up_next(&clp->cl_cb_waitq); dprintk("%s: freed slot, new seqid=%d\n", __func__, @@ -1283,6 +1288,7 @@ void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp, cb->cb_seq_status = 1; cb->cb_status = 0; cb->cb_need_restart = false; + cb->cb_holds_slot = false; } void nfsd4_run_cb(struct nfsd4_callback *cb) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 6a45fb00c5fc..f056b1d3fecd 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -265,6 +265,7 @@ find_or_allocate_block(struct nfs4_lockowner *lo, struct knfsd_fh *fh, static void free_blocked_lock(struct nfsd4_blocked_lock *nbl) { + locks_delete_block(&nbl->nbl_lock); locks_release_private(&nbl->nbl_lock); kfree(nbl); } @@ -293,11 +294,18 @@ remove_blocked_locks(struct nfs4_lockowner *lo) nbl = list_first_entry(&reaplist, struct nfsd4_blocked_lock, nbl_lru); list_del_init(&nbl->nbl_lru); - locks_delete_block(&nbl->nbl_lock); free_blocked_lock(nbl); } } +static void +nfsd4_cb_notify_lock_prepare(struct nfsd4_callback *cb) +{ + struct nfsd4_blocked_lock *nbl = container_of(cb, + struct nfsd4_blocked_lock, nbl_cb); + locks_delete_block(&nbl->nbl_lock); +} + static int nfsd4_cb_notify_lock_done(struct nfsd4_callback *cb, struct rpc_task *task) { @@ -325,6 +333,7 @@ nfsd4_cb_notify_lock_release(struct nfsd4_callback *cb) } static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops = { + .prepare = nfsd4_cb_notify_lock_prepare, .done = nfsd4_cb_notify_lock_done, .release = nfsd4_cb_notify_lock_release, }; @@ -4863,7 +4872,6 @@ nfs4_laundromat(struct nfsd_net *nn) nbl = list_first_entry(&reaplist, struct nfsd4_blocked_lock, nbl_lru); list_del_init(&nbl->nbl_lru); - locks_delete_block(&nbl->nbl_lock); free_blocked_lock(nbl); } out: diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 396c76755b03..9d6cb246c6c5 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -70,6 +70,7 @@ struct nfsd4_callback { int cb_seq_status; int cb_status; bool cb_need_restart; + bool cb_holds_slot; }; struct nfsd4_callback_ops { diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 6b9c27548997..63c6bb1f8c4d 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -346,10 +346,16 @@ static __kernel_fsid_t fanotify_get_fsid(struct fsnotify_iter_info *iter_info) __kernel_fsid_t fsid = {}; fsnotify_foreach_obj_type(type) { + struct fsnotify_mark_connector *conn; + if (!fsnotify_iter_should_report_type(iter_info, type)) continue; - fsid = iter_info->marks[type]->connector->fsid; + conn = READ_ONCE(iter_info->marks[type]->connector); + /* Mark is just getting destroyed or created? */ + if (!conn) + continue; + fsid = conn->fsid; if (WARN_ON_ONCE(!fsid.val[0] && !fsid.val[1])) continue; return fsid; @@ -408,8 +414,12 @@ static int fanotify_handle_event(struct fsnotify_group *group, return 0; } - if (FAN_GROUP_FLAG(group, FAN_REPORT_FID)) + if (FAN_GROUP_FLAG(group, FAN_REPORT_FID)) { fsid = fanotify_get_fsid(iter_info); + /* Racing with mark destruction or creation? */ + if (!fsid.val[0] && !fsid.val[1]) + return 0; + } event = fanotify_alloc_event(group, inode, mask, data, data_type, &fsid); diff --git a/fs/notify/mark.c b/fs/notify/mark.c index d593d4269561..22acb0a79b53 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -239,13 +239,13 @@ static void fsnotify_drop_object(unsigned int type, void *objp) void fsnotify_put_mark(struct fsnotify_mark *mark) { - struct fsnotify_mark_connector *conn; + struct fsnotify_mark_connector *conn = READ_ONCE(mark->connector); void *objp = NULL; unsigned int type = FSNOTIFY_OBJ_TYPE_DETACHED; bool free_conn = false; /* Catch marks that were actually never attached to object */ - if (!mark->connector) { + if (!conn) { if (refcount_dec_and_test(&mark->refcnt)) fsnotify_final_mark_destroy(mark); return; @@ -255,10 +255,9 @@ void fsnotify_put_mark(struct fsnotify_mark *mark) * We have to be careful so that traversals of obj_list under lock can * safely grab mark reference. */ - if (!refcount_dec_and_lock(&mark->refcnt, &mark->connector->lock)) + if (!refcount_dec_and_lock(&mark->refcnt, &conn->lock)) return; - conn = mark->connector; hlist_del_init_rcu(&mark->obj_list); if (hlist_empty(&conn->list)) { objp = fsnotify_detach_connector_from_object(conn, &type); @@ -266,7 +265,7 @@ void fsnotify_put_mark(struct fsnotify_mark *mark) } else { __fsnotify_recalc_mask(conn); } - mark->connector = NULL; + WRITE_ONCE(mark->connector, NULL); spin_unlock(&conn->lock); fsnotify_drop_object(type, objp); @@ -620,7 +619,7 @@ restart: /* mark should be the last entry. last is the current last entry */ hlist_add_behind_rcu(&mark->obj_list, &last->obj_list); added: - mark->connector = conn; + WRITE_ONCE(mark->connector, conn); out_err: spin_unlock(&conn->lock); spin_unlock(&mark->lock); @@ -808,6 +807,7 @@ void fsnotify_init_mark(struct fsnotify_mark *mark, refcount_set(&mark->refcnt, 1); fsnotify_get_group(group); mark->group = group; + WRITE_ONCE(mark->connector, NULL); } /* diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index a35259eebc56..1dc9a08e8bdc 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -4719,22 +4719,23 @@ out: /* Lock an inode and grab a bh pointing to the inode. */ int ocfs2_reflink_inodes_lock(struct inode *s_inode, - struct buffer_head **bh1, + struct buffer_head **bh_s, struct inode *t_inode, - struct buffer_head **bh2) + struct buffer_head **bh_t) { - struct inode *inode1; - struct inode *inode2; + struct inode *inode1 = s_inode; + struct inode *inode2 = t_inode; struct ocfs2_inode_info *oi1; struct ocfs2_inode_info *oi2; + struct buffer_head *bh1 = NULL; + struct buffer_head *bh2 = NULL; bool same_inode = (s_inode == t_inode); + bool need_swap = (inode1->i_ino > inode2->i_ino); int status; /* First grab the VFS and rw locks. */ lock_two_nondirectories(s_inode, t_inode); - inode1 = s_inode; - inode2 = t_inode; - if (inode1->i_ino > inode2->i_ino) + if (need_swap) swap(inode1, inode2); status = ocfs2_rw_lock(inode1, 1); @@ -4757,17 +4758,13 @@ int ocfs2_reflink_inodes_lock(struct inode *s_inode, trace_ocfs2_double_lock((unsigned long long)oi1->ip_blkno, (unsigned long long)oi2->ip_blkno); - if (*bh1) - *bh1 = NULL; - if (*bh2) - *bh2 = NULL; - /* We always want to lock the one with the lower lockid first. */ if (oi1->ip_blkno > oi2->ip_blkno) mlog_errno(-ENOLCK); /* lock id1 */ - status = ocfs2_inode_lock_nested(inode1, bh1, 1, OI_LS_REFLINK_TARGET); + status = ocfs2_inode_lock_nested(inode1, &bh1, 1, + OI_LS_REFLINK_TARGET); if (status < 0) { if (status != -ENOENT) mlog_errno(status); @@ -4776,15 +4773,25 @@ int ocfs2_reflink_inodes_lock(struct inode *s_inode, /* lock id2 */ if (!same_inode) { - status = ocfs2_inode_lock_nested(inode2, bh2, 1, + status = ocfs2_inode_lock_nested(inode2, &bh2, 1, OI_LS_REFLINK_TARGET); if (status < 0) { if (status != -ENOENT) mlog_errno(status); goto out_cl1; } - } else - *bh2 = *bh1; + } else { + bh2 = bh1; + } + + /* + * If we swapped inode order above, we have to swap the buffer heads + * before passing them back to the caller. + */ + if (need_swap) + swap(bh1, bh2); + *bh_s = bh1; + *bh_t = bh2; trace_ocfs2_double_lock_end( (unsigned long long)oi1->ip_blkno, @@ -4794,8 +4801,7 @@ int ocfs2_reflink_inodes_lock(struct inode *s_inode, out_cl1: ocfs2_inode_unlock(inode1, 1); - brelse(*bh1); - *bh1 = NULL; + brelse(bh1); out_rw2: ocfs2_rw_unlock(inode2, 1); out_i2: diff --git a/fs/open.c b/fs/open.c index 0285ce7dbd51..a00350018a47 100644 --- a/fs/open.c +++ b/fs/open.c @@ -733,6 +733,12 @@ static int do_dentry_open(struct file *f, return 0; } + /* Any file opened for execve()/uselib() has to be a regular file. */ + if (unlikely(f->f_flags & FMODE_EXEC && !S_ISREG(inode->i_mode))) { + error = -EACCES; + goto cleanup_file; + } + if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) { error = get_write_access(inode); if (unlikely(error)) @@ -1209,3 +1215,21 @@ int nonseekable_open(struct inode *inode, struct file *filp) } EXPORT_SYMBOL(nonseekable_open); + +/* + * stream_open is used by subsystems that want stream-like file descriptors. + * Such file descriptors are not seekable and don't have notion of position + * (file.f_pos is always 0). Contrary to file descriptors of other regular + * files, .read() and .write() can run simultaneously. + * + * stream_open never fails and is marked to return int so that it could be + * directly used as file_operations.open . + */ +int stream_open(struct inode *inode, struct file *filp) +{ + filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE | FMODE_ATOMIC_POS); + filp->f_mode |= FMODE_STREAM; + return 0; +} + +EXPORT_SYMBOL(stream_open); diff --git a/fs/pipe.c b/fs/pipe.c index 070aad543382..41065901106b 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -188,9 +188,9 @@ EXPORT_SYMBOL(generic_pipe_buf_steal); * in the tee() system call, when we duplicate the buffers in one * pipe into another. */ -void generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) +bool generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { - get_page(buf->page); + return try_get_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_get); diff --git a/fs/proc/base.c b/fs/proc/base.c index ddef482f1334..6a803a0b75df 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -616,24 +616,25 @@ static int proc_pid_limits(struct seq_file *m, struct pid_namespace *ns, static int proc_pid_syscall(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { - long nr; - unsigned long args[6], sp, pc; + struct syscall_info info; + u64 *args = &info.data.args[0]; int res; res = lock_trace(task); if (res) return res; - if (task_current_syscall(task, &nr, args, 6, &sp, &pc)) + if (task_current_syscall(task, &info)) seq_puts(m, "running\n"); - else if (nr < 0) - seq_printf(m, "%ld 0x%lx 0x%lx\n", nr, sp, pc); + else if (info.data.nr < 0) + seq_printf(m, "%d 0x%llx 0x%llx\n", + info.data.nr, info.sp, info.data.instruction_pointer); else seq_printf(m, - "%ld 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx\n", - nr, + "%d 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx\n", + info.data.nr, args[0], args[1], args[2], args[3], args[4], args[5], - sp, pc); + info.sp, info.data.instruction_pointer); unlock_trace(task); return 0; diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index d29d869abec1..f5834488b67d 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -615,7 +615,7 @@ static void __init proc_kcore_text_init(void) /* * MODULES_VADDR has no intersection with VMALLOC_ADDR. */ -struct kcore_list kcore_modules; +static struct kcore_list kcore_modules; static void __init add_modules_range(void) { if (MODULES_VADDR != VMALLOC_START && MODULES_END != VMALLOC_END) { diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 4d598a399bbf..7325baa8f9d4 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1626,8 +1626,11 @@ static void drop_sysctl_table(struct ctl_table_header *header) if (--header->nreg) return; - put_links(header); - start_unregistering(header); + if (parent) { + put_links(header); + start_unregistering(header); + } + if (!--header->count) kfree_rcu(header, rcu); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 92a91e7816d8..95ca1fe7283c 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1143,6 +1143,24 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, count = -EINTR; goto out_mm; } + /* + * Avoid to modify vma->vm_flags + * without locked ops while the + * coredump reads the vm_flags. + */ + if (!mmget_still_valid(mm)) { + /* + * Silently return "count" + * like if get_task_mm() + * failed. FIXME: should this + * function have returned + * -ESRCH if get_task_mm() + * failed like if + * get_proc_task() fails? + */ + up_write(&mm->mmap_sem); + goto out_mm; + } for (vma = mm->mmap; vma; vma = vma->vm_next) { vma->vm_flags &= ~VM_SOFTDIRTY; vma_set_page_prot(vma); diff --git a/fs/read_write.c b/fs/read_write.c index 177ccc3d405a..61b43ad7608e 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -560,12 +560,13 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_ static inline loff_t file_pos_read(struct file *file) { - return file->f_pos; + return file->f_mode & FMODE_STREAM ? 0 : file->f_pos; } static inline void file_pos_write(struct file *file, loff_t pos) { - file->f_pos = pos; + if ((file->f_mode & FMODE_STREAM) == 0) + file->f_pos = pos; } ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count) diff --git a/fs/splice.c b/fs/splice.c index 3ee7e82df48f..25212dcca2df 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -330,8 +330,8 @@ const struct pipe_buf_operations default_pipe_buf_ops = { .get = generic_pipe_buf_get, }; -static int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe, - struct pipe_buffer *buf) +int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) { return 1; } @@ -1593,7 +1593,11 @@ retry: * Get a reference to this pipe buffer, * so we can copy the contents over. */ - pipe_buf_get(ipipe, ibuf); + if (!pipe_buf_get(ipipe, ibuf)) { + if (ret == 0) + ret = -EFAULT; + break; + } *obuf = *ibuf; /* @@ -1667,7 +1671,11 @@ static int link_pipe(struct pipe_inode_info *ipipe, * Get a reference to this pipe buffer, * so we can copy the contents over. */ - pipe_buf_get(ipipe, ibuf); + if (!pipe_buf_get(ipipe, ibuf)) { + if (ret == 0) + ret = -EFAULT; + break; + } obuf = opipe->bufs + nbuf; *obuf = *ibuf; diff --git a/fs/super.c b/fs/super.c index 583a0124bc39..2739f57515f8 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1467,11 +1467,6 @@ int vfs_get_tree(struct fs_context *fc) struct super_block *sb; int error; - if (fc->fs_type->fs_flags & FS_REQUIRES_DEV && !fc->source) { - errorf(fc, "Filesystem requires source device"); - return -ENOENT; - } - if (fc->root) return -EBUSY; diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 8dc2818fdd84..12628184772c 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -276,14 +276,12 @@ static void ubifs_i_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); struct ubifs_inode *ui = ubifs_inode(inode); + kfree(ui->data); kmem_cache_free(ubifs_inode_slab, ui); } static void ubifs_destroy_inode(struct inode *inode) { - struct ubifs_inode *ui = ubifs_inode(inode); - - kfree(ui->data); call_rcu(&inode->i_rcu, ubifs_i_callback); } diff --git a/fs/ufs/util.h b/fs/ufs/util.h index 1fd3011ea623..7fd4802222b8 100644 --- a/fs/ufs/util.h +++ b/fs/ufs/util.h @@ -229,7 +229,7 @@ ufs_get_inode_gid(struct super_block *sb, struct ufs_inode *inode) case UFS_UID_44BSD: return fs32_to_cpu(sb, inode->ui_u3.ui_44.ui_gid); case UFS_UID_EFT: - if (inode->ui_u1.oldids.ui_suid == 0xFFFF) + if (inode->ui_u1.oldids.ui_sgid == 0xFFFF) return fs32_to_cpu(sb, inode->ui_u3.ui_sun.ui_gid); /* Fall through */ default: diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 89800fc7dc9d..f5de1e726356 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -629,6 +629,8 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, /* the various vma->vm_userfaultfd_ctx still points to it */ down_write(&mm->mmap_sem); + /* no task can run (and in turn coredump) yet */ + VM_WARN_ON(!mmget_still_valid(mm)); for (vma = mm->mmap; vma; vma = vma->vm_next) if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) { vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; @@ -883,6 +885,8 @@ static int userfaultfd_release(struct inode *inode, struct file *file) * taking the mmap_sem for writing. */ down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto skip_mm; prev = NULL; for (vma = mm->mmap; vma; vma = vma->vm_next) { cond_resched(); @@ -905,6 +909,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file) vma->vm_flags = new_flags; vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; } +skip_mm: up_write(&mm->mmap_sem); mmput(mm); wakeup: @@ -1333,6 +1338,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, goto out; down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto out_unlock; vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; @@ -1520,6 +1527,8 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, goto out; down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto out_unlock; vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 48502cb9990f..4637ae1ae91c 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -1191,7 +1191,10 @@ xfs_iread_extents( * Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out. */ level = be16_to_cpu(block->bb_level); - ASSERT(level > 0); + if (unlikely(level == 0)) { + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp); + return -EFSCORRUPTED; + } pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes); bno = be64_to_cpu(*pp); @@ -4249,9 +4252,13 @@ xfs_bmapi_write( struct xfs_bmbt_irec *mval, /* output: map values */ int *nmap) /* i/o: mval size/count */ { + struct xfs_bmalloca bma = { + .tp = tp, + .ip = ip, + .total = total, + }; struct xfs_mount *mp = ip->i_mount; struct xfs_ifork *ifp; - struct xfs_bmalloca bma = { NULL }; /* args for xfs_bmap_alloc */ xfs_fileoff_t end; /* end of mapped file region */ bool eof = false; /* after the end of extents */ int error; /* error return */ @@ -4319,10 +4326,6 @@ xfs_bmapi_write( eof = true; if (!xfs_iext_peek_prev_extent(ifp, &bma.icur, &bma.prev)) bma.prev.br_startoff = NULLFILEOFF; - bma.tp = tp; - bma.ip = ip; - bma.total = total; - bma.datatype = 0; bma.minleft = xfs_bmapi_minleft(tp, ip, whichfork); n = 0; diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c index 6f94d1f7322d..117910db51b8 100644 --- a/fs/xfs/scrub/btree.c +++ b/fs/xfs/scrub/btree.c @@ -415,8 +415,17 @@ xchk_btree_check_owner( struct xfs_btree_cur *cur = bs->cur; struct check_owner *co; - if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) && bp == NULL) + /* + * In theory, xfs_btree_get_block should only give us a null buffer + * pointer for the root of a root-in-inode btree type, but we need + * to check defensively here in case the cursor state is also screwed + * up. + */ + if (bp == NULL) { + if (!(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)) + xchk_btree_set_corrupt(bs->sc, bs->cur, level); return 0; + } /* * We want to cross-reference each btree block with the bnobt diff --git a/fs/xfs/scrub/dabtree.c b/fs/xfs/scrub/dabtree.c index f1260b4bfdee..90527b094878 100644 --- a/fs/xfs/scrub/dabtree.c +++ b/fs/xfs/scrub/dabtree.c @@ -574,6 +574,11 @@ xchk_da_btree( /* Drill another level deeper. */ blkno = be32_to_cpu(key->before); level++; + if (level >= XFS_DA_NODE_MAXDEPTH) { + /* Too deep! */ + xchk_da_set_corrupt(&ds, level - 1); + break; + } ds.tree_level--; error = xchk_da_btree_block(&ds, level, blkno); if (error) diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c index 93f07edafd81..9ee2a7d02e70 100644 --- a/fs/xfs/xfs_discard.c +++ b/fs/xfs/xfs_discard.c @@ -161,6 +161,14 @@ xfs_ioc_trim( return -EPERM; if (!blk_queue_discard(q)) return -EOPNOTSUPP; + + /* + * We haven't recovered the log, so we cannot use our bnobt-guided + * storage zapping commands. + */ + if (mp->m_flags & XFS_MOUNT_NORECOVERY) + return -EROFS; + if (copy_from_user(&range, urange, sizeof(range))) return -EFAULT; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 1f2e2845eb76..a7ceae90110e 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -529,18 +529,17 @@ xfs_file_dio_aio_write( count = iov_iter_count(from); /* - * If we are doing unaligned IO, wait for all other IO to drain, - * otherwise demote the lock if we had to take the exclusive lock - * for other reasons in xfs_file_aio_write_checks. + * If we are doing unaligned IO, we can't allow any other overlapping IO + * in-flight at the same time or we risk data corruption. Wait for all + * other IO to drain before we submit. If the IO is aligned, demote the + * iolock if we had to take the exclusive lock in + * xfs_file_aio_write_checks() for other reasons. */ if (unaligned_io) { - /* If we are going to wait for other DIO to finish, bail */ - if (iocb->ki_flags & IOCB_NOWAIT) { - if (atomic_read(&inode->i_dio_count)) - return -EAGAIN; - } else { - inode_dio_wait(inode); - } + /* unaligned dio always waits, bail */ + if (iocb->ki_flags & IOCB_NOWAIT) + return -EAGAIN; + inode_dio_wait(inode); } else if (iolock == XFS_IOLOCK_EXCL) { xfs_ilock_demote(ip, XFS_IOLOCK_EXCL); iolock = XFS_IOLOCK_SHARED; @@ -548,6 +547,14 @@ xfs_file_dio_aio_write( trace_xfs_file_direct_write(ip, count, iocb->ki_pos); ret = iomap_dio_rw(iocb, from, &xfs_iomap_ops, xfs_dio_write_end_io); + + /* + * If unaligned, this is the only IO in-flight. If it has not yet + * completed, wait on it before we release the iolock to prevent + * subsequent overlapping IO. + */ + if (ret == -EIOCBQUEUED && unaligned_io) + inode_dio_wait(inode); out: xfs_iunlock(ip, iolock); diff --git a/include/acpi/acoutput.h b/include/acpi/acoutput.h index 30b1ae53689f..c50542dc71e0 100644 --- a/include/acpi/acoutput.h +++ b/include/acpi/acoutput.h @@ -150,7 +150,10 @@ /* Defaults for debug_level, debug and normal */ +#ifndef ACPI_DEBUG_DEFAULT #define ACPI_DEBUG_DEFAULT (ACPI_LV_INIT | ACPI_LV_DEBUG_OBJECT | ACPI_LV_EVALUATION | ACPI_LV_REPAIR) +#endif + #define ACPI_NORMAL_DEFAULT (ACPI_LV_INIT | ACPI_LV_DEBUG_OBJECT | ACPI_LV_REPAIR) #define ACPI_DEBUG_ALL (ACPI_LV_AML_DISASSEMBLE | ACPI_LV_ALL_EXCEPTIONS | ACPI_LV_ALL) diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h index 9ff328fd946a..624b90b34085 100644 --- a/include/acpi/platform/aclinux.h +++ b/include/acpi/platform/aclinux.h @@ -82,6 +82,11 @@ #define ACPI_NO_ERROR_MESSAGES #undef ACPI_DEBUG_OUTPUT +/* Use a specific bugging default separate from ACPICA */ + +#undef ACPI_DEBUG_DEFAULT +#define ACPI_DEBUG_DEFAULT (ACPI_LV_INFO | ACPI_LV_REPAIR) + /* External interface for __KERNEL__, stub is needed */ #define ACPI_EXTERNAL_RETURN_STATUS(prototype) \ diff --git a/include/asm-generic/syscall.h b/include/asm-generic/syscall.h index 0c938a4354f6..b88239e9efe4 100644 --- a/include/asm-generic/syscall.h +++ b/include/asm-generic/syscall.h @@ -105,41 +105,30 @@ void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs, * syscall_get_arguments - extract system call parameter values * @task: task of interest, must be blocked * @regs: task_pt_regs() of @task - * @i: argument index [0,5] - * @n: number of arguments; n+i must be [1,6]. * @args: array filled with argument values * - * Fetches @n arguments to the system call starting with the @i'th argument - * (from 0 through 5). Argument @i is stored in @args[0], and so on. - * An arch inline version is probably optimal when @i and @n are constants. + * Fetches 6 arguments to the system call. First argument is stored in +* @args[0], and so on. * * It's only valid to call this when @task is stopped for tracing on * entry to a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT. - * It's invalid to call this with @i + @n > 6; we only support system calls - * taking up to 6 arguments. */ void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args); + unsigned long *args); /** * syscall_set_arguments - change system call parameter value * @task: task of interest, must be in system call entry tracing * @regs: task_pt_regs() of @task - * @i: argument index [0,5] - * @n: number of arguments; n+i must be [1,6]. * @args: array of argument values to store * - * Changes @n arguments to the system call starting with the @i'th argument. - * Argument @i gets value @args[0], and so on. - * An arch inline version is probably optimal when @i and @n are constants. + * Changes 6 arguments to the system call. + * The first argument gets value @args[0], and so on. * * It's only valid to call this when @task is stopped for tracing on * entry to a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT. - * It's invalid to call this with @i + @n > 6; we only support system calls - * taking up to 6 arguments. */ void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, const unsigned long *args); /** diff --git a/include/drm/drm_modeset_helper_vtables.h b/include/drm/drm_modeset_helper_vtables.h index cfb7be40bed7..ce4de6b1e444 100644 --- a/include/drm/drm_modeset_helper_vtables.h +++ b/include/drm/drm_modeset_helper_vtables.h @@ -418,6 +418,8 @@ struct drm_crtc_helper_funcs { * Drivers can use the @old_crtc_state input parameter if the operations * needed to enable the CRTC don't depend solely on the new state but * also on the transition between the old state and the new state. + * + * This function is optional. */ void (*atomic_enable)(struct drm_crtc *crtc, struct drm_crtc_state *old_crtc_state); @@ -441,6 +443,8 @@ struct drm_crtc_helper_funcs { * parameter @old_crtc_state which could be used to access the old * state. Atomic drivers should consider to use this one instead * of @disable. + * + * This function is optional. */ void (*atomic_disable)(struct drm_crtc *crtc, struct drm_crtc_state *old_crtc_state); diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index cbf3180cb612..668ad971cd7b 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -420,7 +420,6 @@ extern struct ttm_bo_global { /** * Protected by ttm_global_mutex. */ - unsigned int use_count; struct list_head device_list; /** diff --git a/include/dt-bindings/clock/sifive-fu540-prci.h b/include/dt-bindings/clock/sifive-fu540-prci.h new file mode 100644 index 000000000000..6a0b70a37d78 --- /dev/null +++ b/include/dt-bindings/clock/sifive-fu540-prci.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2018-2019 SiFive, Inc. + * Wesley Terpstra + * Paul Walmsley + */ + +#ifndef __DT_BINDINGS_CLOCK_SIFIVE_FU540_PRCI_H +#define __DT_BINDINGS_CLOCK_SIFIVE_FU540_PRCI_H + +/* Clock indexes for use by Device Tree data and the PRCI driver */ + +#define PRCI_CLK_COREPLL 0 +#define PRCI_CLK_DDRPLL 1 +#define PRCI_CLK_GEMGXLPLL 2 +#define PRCI_CLK_TLCLK 3 + +#endif diff --git a/include/dt-bindings/reset/amlogic,meson-g12a-reset.h b/include/dt-bindings/reset/amlogic,meson-g12a-reset.h index 8063e8314eef..6d487c5eba2c 100644 --- a/include/dt-bindings/reset/amlogic,meson-g12a-reset.h +++ b/include/dt-bindings/reset/amlogic,meson-g12a-reset.h @@ -51,7 +51,10 @@ #define RESET_SD_EMMC_A 44 #define RESET_SD_EMMC_B 45 #define RESET_SD_EMMC_C 46 -/* 47-60 */ +/* 47 */ +#define RESET_USB_PHY20 48 +#define RESET_USB_PHY21 49 +/* 50-60 */ #define RESET_AUDIO_CODEC 61 /* 62-63 */ /* RESET2 */ diff --git a/include/keys/trusted.h b/include/keys/trusted.h index adbcb6817826..0071298b9b28 100644 --- a/include/keys/trusted.h +++ b/include/keys/trusted.h @@ -38,7 +38,7 @@ enum { int TSS_authhmac(unsigned char *digest, const unsigned char *key, unsigned int keylen, unsigned char *h1, - unsigned char *h2, unsigned char h3, ...); + unsigned char *h2, unsigned int h3, ...); int TSS_checkhmac1(unsigned char *buffer, const uint32_t command, const unsigned char *ononce, diff --git a/include/linux/atalk.h b/include/linux/atalk.h index d5cfc0b15b76..f6034ba774be 100644 --- a/include/linux/atalk.h +++ b/include/linux/atalk.h @@ -108,7 +108,7 @@ static __inline__ struct elapaarp *aarp_hdr(struct sk_buff *skb) #define AARP_RESOLVE_TIME (10 * HZ) extern struct datalink_proto *ddp_dl, *aarp_dl; -extern void aarp_proto_init(void); +extern int aarp_proto_init(void); /* Inter module exports */ diff --git a/include/linux/bio.h b/include/linux/bio.h index bb6090aa165d..e584673c1881 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -120,19 +120,23 @@ static inline bool bio_full(struct bio *bio) return bio->bi_vcnt >= bio->bi_max_vecs; } -#define mp_bvec_for_each_segment(bv, bvl, i, iter_all) \ - for (bv = bvec_init_iter_all(&iter_all); \ - (iter_all.done < (bvl)->bv_len) && \ - (mp_bvec_next_segment((bvl), &iter_all), 1); \ - iter_all.done += bv->bv_len, i += 1) +static inline bool bio_next_segment(const struct bio *bio, + struct bvec_iter_all *iter) +{ + if (iter->idx >= bio->bi_vcnt) + return false; + + bvec_advance(&bio->bi_io_vec[iter->idx], iter); + return true; +} /* * drivers should _never_ use the all version - the bio may have been split * before it got to the driver and the driver won't own all of it */ -#define bio_for_each_segment_all(bvl, bio, i, iter_all) \ - for (i = 0, iter_all.idx = 0; iter_all.idx < (bio)->bi_vcnt; iter_all.idx++) \ - mp_bvec_for_each_segment(bvl, &((bio)->bi_io_vec[iter_all.idx]), i, iter_all) +#define bio_for_each_segment_all(bvl, bio, i, iter) \ + for (i = 0, bvl = bvec_init_iter_all(&iter); \ + bio_next_segment((bio), &iter); i++) static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter, unsigned bytes) diff --git a/include/linux/bitrev.h b/include/linux/bitrev.h index 50fb0dee23e8..d35b8ec1c485 100644 --- a/include/linux/bitrev.h +++ b/include/linux/bitrev.h @@ -34,41 +34,41 @@ static inline u32 __bitrev32(u32 x) #define __constant_bitrev32(x) \ ({ \ - u32 __x = x; \ - __x = (__x >> 16) | (__x << 16); \ - __x = ((__x & (u32)0xFF00FF00UL) >> 8) | ((__x & (u32)0x00FF00FFUL) << 8); \ - __x = ((__x & (u32)0xF0F0F0F0UL) >> 4) | ((__x & (u32)0x0F0F0F0FUL) << 4); \ - __x = ((__x & (u32)0xCCCCCCCCUL) >> 2) | ((__x & (u32)0x33333333UL) << 2); \ - __x = ((__x & (u32)0xAAAAAAAAUL) >> 1) | ((__x & (u32)0x55555555UL) << 1); \ - __x; \ + u32 ___x = x; \ + ___x = (___x >> 16) | (___x << 16); \ + ___x = ((___x & (u32)0xFF00FF00UL) >> 8) | ((___x & (u32)0x00FF00FFUL) << 8); \ + ___x = ((___x & (u32)0xF0F0F0F0UL) >> 4) | ((___x & (u32)0x0F0F0F0FUL) << 4); \ + ___x = ((___x & (u32)0xCCCCCCCCUL) >> 2) | ((___x & (u32)0x33333333UL) << 2); \ + ___x = ((___x & (u32)0xAAAAAAAAUL) >> 1) | ((___x & (u32)0x55555555UL) << 1); \ + ___x; \ }) #define __constant_bitrev16(x) \ ({ \ - u16 __x = x; \ - __x = (__x >> 8) | (__x << 8); \ - __x = ((__x & (u16)0xF0F0U) >> 4) | ((__x & (u16)0x0F0FU) << 4); \ - __x = ((__x & (u16)0xCCCCU) >> 2) | ((__x & (u16)0x3333U) << 2); \ - __x = ((__x & (u16)0xAAAAU) >> 1) | ((__x & (u16)0x5555U) << 1); \ - __x; \ + u16 ___x = x; \ + ___x = (___x >> 8) | (___x << 8); \ + ___x = ((___x & (u16)0xF0F0U) >> 4) | ((___x & (u16)0x0F0FU) << 4); \ + ___x = ((___x & (u16)0xCCCCU) >> 2) | ((___x & (u16)0x3333U) << 2); \ + ___x = ((___x & (u16)0xAAAAU) >> 1) | ((___x & (u16)0x5555U) << 1); \ + ___x; \ }) #define __constant_bitrev8x4(x) \ ({ \ - u32 __x = x; \ - __x = ((__x & (u32)0xF0F0F0F0UL) >> 4) | ((__x & (u32)0x0F0F0F0FUL) << 4); \ - __x = ((__x & (u32)0xCCCCCCCCUL) >> 2) | ((__x & (u32)0x33333333UL) << 2); \ - __x = ((__x & (u32)0xAAAAAAAAUL) >> 1) | ((__x & (u32)0x55555555UL) << 1); \ - __x; \ + u32 ___x = x; \ + ___x = ((___x & (u32)0xF0F0F0F0UL) >> 4) | ((___x & (u32)0x0F0F0F0FUL) << 4); \ + ___x = ((___x & (u32)0xCCCCCCCCUL) >> 2) | ((___x & (u32)0x33333333UL) << 2); \ + ___x = ((___x & (u32)0xAAAAAAAAUL) >> 1) | ((___x & (u32)0x55555555UL) << 1); \ + ___x; \ }) #define __constant_bitrev8(x) \ ({ \ - u8 __x = x; \ - __x = (__x >> 4) | (__x << 4); \ - __x = ((__x & (u8)0xCCU) >> 2) | ((__x & (u8)0x33U) << 2); \ - __x = ((__x & (u8)0xAAU) >> 1) | ((__x & (u8)0x55U) << 1); \ - __x; \ + u8 ___x = x; \ + ___x = (___x >> 4) | (___x << 4); \ + ___x = ((___x & (u8)0xCCU) >> 2) | ((___x & (u8)0x33U) << 2); \ + ___x = ((___x & (u8)0xAAU) >> 1) | ((___x & (u8)0x55U) << 1); \ + ___x; \ }) #define bitrev32(x) \ diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index cb2aa7ecafff..db29928de467 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -302,6 +302,7 @@ void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list); void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs); bool blk_mq_complete_request(struct request *rq); +void blk_mq_complete_request_sync(struct request *rq); bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list, struct bio *bio); bool blk_mq_queue_stopped(struct request_queue *q); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5c58a3b2bf00..317ab30d2904 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -548,7 +548,6 @@ struct request_queue { struct rcu_head rcu_head; wait_queue_head_t mq_freeze_wq; struct percpu_ref q_usage_counter; - struct list_head all_q_node; struct blk_mq_tag_set *tag_set; struct list_head tag_set_list; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a2132e09dc1c..944ccc310201 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -193,7 +193,6 @@ enum bpf_arg_type { ARG_PTR_TO_CTX, /* pointer to context */ ARG_ANYTHING, /* any (initialized) argument is ok */ - ARG_PTR_TO_SOCKET, /* pointer to bpf_sock */ ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */ ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */ }; @@ -511,7 +510,7 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, } \ _out: \ rcu_read_unlock(); \ - preempt_enable_no_resched(); \ + preempt_enable(); \ _ret; \ }) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 69f7a3449eda..7d8228d1c898 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -66,6 +66,46 @@ struct bpf_reg_state { * same reference to the socket, to determine proper reference freeing. */ u32 id; + /* PTR_TO_SOCKET and PTR_TO_TCP_SOCK could be a ptr returned + * from a pointer-cast helper, bpf_sk_fullsock() and + * bpf_tcp_sock(). + * + * Consider the following where "sk" is a reference counted + * pointer returned from "sk = bpf_sk_lookup_tcp();": + * + * 1: sk = bpf_sk_lookup_tcp(); + * 2: if (!sk) { return 0; } + * 3: fullsock = bpf_sk_fullsock(sk); + * 4: if (!fullsock) { bpf_sk_release(sk); return 0; } + * 5: tp = bpf_tcp_sock(fullsock); + * 6: if (!tp) { bpf_sk_release(sk); return 0; } + * 7: bpf_sk_release(sk); + * 8: snd_cwnd = tp->snd_cwnd; // verifier will complain + * + * After bpf_sk_release(sk) at line 7, both "fullsock" ptr and + * "tp" ptr should be invalidated also. In order to do that, + * the reg holding "fullsock" and "sk" need to remember + * the original refcounted ptr id (i.e. sk_reg->id) in ref_obj_id + * such that the verifier can reset all regs which have + * ref_obj_id matching the sk_reg->id. + * + * sk_reg->ref_obj_id is set to sk_reg->id at line 1. + * sk_reg->id will stay as NULL-marking purpose only. + * After NULL-marking is done, sk_reg->id can be reset to 0. + * + * After "fullsock = bpf_sk_fullsock(sk);" at line 3, + * fullsock_reg->ref_obj_id is set to sk_reg->ref_obj_id. + * + * After "tp = bpf_tcp_sock(fullsock);" at line 5, + * tp_reg->ref_obj_id is set to fullsock_reg->ref_obj_id + * which is the same as sk_reg->ref_obj_id. + * + * From the verifier perspective, if sk, fullsock and tp + * are not NULL, they are the same ptr with different + * reg->type. In particular, bpf_sk_release(tp) is also + * allowed and has the same effect as bpf_sk_release(sk). + */ + u32 ref_obj_id; /* For scalar types (SCALAR_VALUE), this represents our knowledge of * the actual value. * For pointer types, this represents the variable part of the offset diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 9cd00a37b8d3..6db2d9a6e503 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -148,6 +148,22 @@ #define BCM_LED_SRC_OFF 0xe /* Tied high */ #define BCM_LED_SRC_ON 0xf /* Tied low */ +/* + * Broadcom Multicolor LED configurations (expansion register 4) + */ +#define BCM_EXP_MULTICOLOR (MII_BCM54XX_EXP_SEL_ER + 0x04) +#define BCM_LED_MULTICOLOR_IN_PHASE BIT(8) +#define BCM_LED_MULTICOLOR_LINK_ACT 0x0 +#define BCM_LED_MULTICOLOR_SPEED 0x1 +#define BCM_LED_MULTICOLOR_ACT_FLASH 0x2 +#define BCM_LED_MULTICOLOR_FDX 0x3 +#define BCM_LED_MULTICOLOR_OFF 0x4 +#define BCM_LED_MULTICOLOR_ON 0x5 +#define BCM_LED_MULTICOLOR_ALT 0x6 +#define BCM_LED_MULTICOLOR_FLASH 0x7 +#define BCM_LED_MULTICOLOR_LINK 0x8 +#define BCM_LED_MULTICOLOR_ACT 0x9 +#define BCM_LED_MULTICOLOR_PROGRAM 0xa /* * BCM5482: Shadow registers diff --git a/include/linux/bvec.h b/include/linux/bvec.h index f6275c4da13a..ff13cbc1887d 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -145,26 +145,33 @@ static inline bool bvec_iter_advance(const struct bio_vec *bv, static inline struct bio_vec *bvec_init_iter_all(struct bvec_iter_all *iter_all) { - iter_all->bv.bv_page = NULL; iter_all->done = 0; + iter_all->idx = 0; return &iter_all->bv; } -static inline void mp_bvec_next_segment(const struct bio_vec *bvec, - struct bvec_iter_all *iter_all) +static inline void bvec_advance(const struct bio_vec *bvec, + struct bvec_iter_all *iter_all) { struct bio_vec *bv = &iter_all->bv; - if (bv->bv_page) { + if (iter_all->done) { bv->bv_page = nth_page(bv->bv_page, 1); bv->bv_offset = 0; } else { - bv->bv_page = bvec->bv_page; - bv->bv_offset = bvec->bv_offset; + bv->bv_page = bvec_nth_page(bvec->bv_page, bvec->bv_offset / + PAGE_SIZE); + bv->bv_offset = bvec->bv_offset & ~PAGE_MASK; } bv->bv_len = min_t(unsigned int, PAGE_SIZE - bv->bv_offset, bvec->bv_len - iter_all->done); + iter_all->done += bv->bv_len; + + if (iter_all->done == bvec->bv_len) { + iter_all->idx++; + iter_all->done = 0; + } } /* diff --git a/include/linux/clk.h b/include/linux/clk.h index d8bc1a856b39..f689fc58d7be 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -811,6 +811,22 @@ static inline bool clk_has_parent(struct clk *clk, struct clk *parent) return true; } +static inline int clk_set_rate_range(struct clk *clk, unsigned long min, + unsigned long max) +{ + return 0; +} + +static inline int clk_set_min_rate(struct clk *clk, unsigned long rate) +{ + return 0; +} + +static inline int clk_set_max_rate(struct clk *clk, unsigned long rate) +{ + return 0; +} + static inline int clk_set_parent(struct clk *clk, struct clk *parent) { return 0; diff --git a/include/linux/device.h b/include/linux/device.h index b425a7ee04ce..4e6987e11f68 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -49,8 +49,6 @@ struct bus_attribute { ssize_t (*store)(struct bus_type *bus, const char *buf, size_t count); }; -#define BUS_ATTR(_name, _mode, _show, _store) \ - struct bus_attribute bus_attr_##_name = __ATTR(_name, _mode, _show, _store) #define BUS_ATTR_RW(_name) \ struct bus_attribute bus_attr_##_name = __ATTR_RW(_name) #define BUS_ATTR_RO(_name) \ diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 2e9e2763bf47..6e8bc53740f0 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -31,6 +31,7 @@ struct elevator_mq_ops { void (*exit_sched)(struct elevator_queue *); int (*init_hctx)(struct blk_mq_hw_ctx *, unsigned int); void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int); + void (*depth_updated)(struct blk_mq_hw_ctx *); bool (*allow_merge)(struct request_queue *, struct request *, struct bio *); bool (*bio_merge)(struct blk_mq_hw_ctx *, struct bio *); diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index e2f3b21cd72a..aa8bfd6f738c 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -449,6 +449,18 @@ static inline void eth_addr_dec(u8 *addr) } /** + * eth_addr_inc() - Increment the given MAC address. + * @addr: Pointer to a six-byte array containing Ethernet address to increment. + */ +static inline void eth_addr_inc(u8 *addr) +{ + u64 u = ether_addr_to_u64(addr); + + u++; + u64_to_ether_addr(u, addr); +} + +/** * is_etherdev_addr - Tell if given Ethernet address belongs to the device. * @dev: Pointer to a device structure * @addr: Pointer to a six-byte array containing the Ethernet address diff --git a/include/linux/fs.h b/include/linux/fs.h index 8b42df09b04c..dd28e7679089 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -158,6 +158,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define FMODE_OPENED ((__force fmode_t)0x80000) #define FMODE_CREATED ((__force fmode_t)0x100000) +/* File is stream-like */ +#define FMODE_STREAM ((__force fmode_t)0x200000) + /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000) @@ -3074,6 +3077,7 @@ extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t); extern loff_t no_seek_end_llseek(struct file *, loff_t, int); extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); +extern int stream_open(struct inode * inode, struct file * filp); #ifdef CONFIG_BLOCK typedef void (dio_submit_t)(struct bio *bio, struct inode *inode, diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index ea35263eb76b..11943b60f208 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -203,7 +203,6 @@ static inline void hugetlb_show_meminfo(void) #define pud_huge(x) 0 #define is_hugepage_only_range(mm, addr, len) 0 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; }) -#define hugetlb_fault(mm, vma, addr, flags) ({ BUG(); 0; }) #define hugetlb_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \ src_addr, pagep) ({ BUG(); 0; }) #define huge_pte_offset(mm, address, sz) 0 @@ -234,6 +233,13 @@ static inline void __unmap_hugepage_range(struct mmu_gather *tlb, { BUG(); } +static inline vm_fault_t hugetlb_fault(struct mm_struct *mm, + struct vm_area_struct *vma, unsigned long address, + unsigned int flags) +{ + BUG(); + return 0; +} #endif /* !CONFIG_HUGETLB_PAGE */ /* diff --git a/include/linux/kcore.h b/include/linux/kcore.h index c843f4a9c512..da676cdbd727 100644 --- a/include/linux/kcore.h +++ b/include/linux/kcore.h @@ -38,12 +38,6 @@ struct vmcoredd_node { #ifdef CONFIG_PROC_KCORE void __init kclist_add(struct kcore_list *, void *, size_t, int type); -static inline -void kclist_add_remap(struct kcore_list *m, void *addr, void *vaddr, size_t sz) -{ - m->vaddr = (unsigned long)vaddr; - kclist_add(m, addr, sz, KCORE_REMAP); -} extern int __init register_mem_pfn_is_ram(int (*fn)(unsigned long pfn)); #else @@ -51,11 +45,6 @@ static inline void kclist_add(struct kcore_list *new, void *addr, size_t size, int type) { } - -static inline -void kclist_add_remap(struct kcore_list *m, void *addr, void *vaddr, size_t sz) -{ -} #endif #endif /* _LINUX_KCORE_H */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 34a5036debd3..2d14e21c16c0 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -47,8 +47,8 @@ #define u64_to_user_ptr(x) ( \ { \ - typecheck(u64, x); \ - (void __user *)(uintptr_t)x; \ + typecheck(u64, (x)); \ + (void __user *)(uintptr_t)(x); \ } \ ) diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 201f0f2683f2..9a897256e481 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -173,6 +173,7 @@ struct kretprobe_instance { struct kretprobe *rp; kprobe_opcode_t *ret_addr; struct task_struct *task; + void *fp; char data[0]; }; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9d55c63db09b..640a03642766 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -28,6 +28,7 @@ #include <linux/irqbypass.h> #include <linux/swait.h> #include <linux/refcount.h> +#include <linux/nospec.h> #include <asm/signal.h> #include <linux/kvm.h> @@ -513,10 +514,10 @@ static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx) static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) { - /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu, in case - * the caller has read kvm->online_vcpus before (as is the case - * for kvm_for_each_vcpu, for example). - */ + int num_vcpus = atomic_read(&kvm->online_vcpus); + i = array_index_nospec(i, num_vcpus); + + /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu. */ smp_rmb(); return kvm->vcpus[i]; } @@ -600,6 +601,7 @@ void kvm_put_kvm(struct kvm *kvm); static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id) { + as_id = array_index_nospec(as_id, KVM_ADDRESS_SPACE_NUM); return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu, lockdep_is_held(&kvm->slots_lock) || !refcount_read(&kvm->users_count)); diff --git a/include/linux/list.h b/include/linux/list.h index 79626b5ab36c..58aa3adf94e6 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -207,7 +207,7 @@ static inline void list_bulk_move_tail(struct list_head *head, } /** - * list_is_first -- tests whether @ list is the first entry in list @head + * list_is_first -- tests whether @list is the first entry in list @head * @list: the entry to test * @head: the head of the list */ diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 1f3d880b7ca1..dbb6118370c1 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -566,7 +566,10 @@ struct mem_cgroup *lock_page_memcg(struct page *page); void __unlock_page_memcg(struct mem_cgroup *memcg); void unlock_page_memcg(struct page *page); -/* idx can be of type enum memcg_stat_item or node_stat_item */ +/* + * idx can be of type enum memcg_stat_item or node_stat_item. + * Keep in sync with memcg_exact_page_state(). + */ static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { diff --git a/include/linux/mii.h b/include/linux/mii.h index 6fee8b1a4400..5cd824c1c0ca 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -469,7 +469,7 @@ static inline u32 linkmode_adv_to_lcl_adv_t(unsigned long *advertising) if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertising)) lcl_adv |= ADVERTISE_PAUSE_CAP; - if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, + if (linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising)) lcl_adv |= ADVERTISE_PAUSE_ASYM; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 022541dc5dbf..0d0729648844 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -594,6 +594,8 @@ enum mlx5_pagefault_type_flags { }; struct mlx5_td { + /* protects tirs list changes while tirs refresh */ + struct mutex list_lock; struct list_head tirs_list; u32 tdn; }; diff --git a/include/linux/mm.h b/include/linux/mm.h index 76769749b5a5..6b10c21630f5 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -966,6 +966,10 @@ static inline bool is_pci_p2pdma_page(const struct page *page) } #endif /* CONFIG_DEV_PAGEMAP_OPS */ +/* 127: arbitrary random number, small enough to assemble well */ +#define page_ref_zero_or_close_to_overflow(page) \ + ((unsigned int) page_ref_count(page) + 127u <= 127u) + static inline void get_page(struct page *page) { page = compound_head(page); @@ -973,8 +977,17 @@ static inline void get_page(struct page *page) * Getting a normal page or the head of a compound page * requires to already have an elevated page->_refcount. */ - VM_BUG_ON_PAGE(page_ref_count(page) <= 0, page); + VM_BUG_ON_PAGE(page_ref_zero_or_close_to_overflow(page), page); + page_ref_inc(page); +} + +static inline __must_check bool try_get_page(struct page *page) +{ + page = compound_head(page); + if (WARN_ON_ONCE(page_ref_count(page) <= 0)) + return false; page_ref_inc(page); + return true; } static inline void put_page(struct page *page) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7eade9132f02..4ef4bbe78a1d 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -671,7 +671,7 @@ enum vm_fault_reason { /* Encode hstate index for a hwpoisoned large page */ #define VM_FAULT_SET_HINDEX(x) ((__force vm_fault_t)((x) << 16)) -#define VM_FAULT_GET_HINDEX(x) (((x) >> 16) & 0xf) +#define VM_FAULT_GET_HINDEX(x) (((__force unsigned int)(x) >> 16) & 0xf) #define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | \ VM_FAULT_SIGSEGV | VM_FAULT_HWPOISON | \ diff --git a/include/linux/net.h b/include/linux/net.h index 651fca72286c..c606c72311d0 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -83,6 +83,12 @@ enum sock_type { #endif /* ARCH_HAS_SOCKET_TYPES */ +/** + * enum sock_shutdown_cmd - Shutdown types + * @SHUT_RD: shutdown receptions + * @SHUT_WR: shutdown transmissions + * @SHUT_RDWR: shutdown receptions/transmissions + */ enum sock_shutdown_cmd { SHUT_RD, SHUT_WR, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 26f69cf763f4..324e872c91d1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1500,6 +1500,7 @@ struct net_device_ops { * @IFF_FAILOVER: device is a failover master device * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device * @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device + * @IFF_LIVE_RENAME_OK: rename is allowed while device is up and running */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1532,6 +1533,7 @@ enum netdev_priv_flags { IFF_FAILOVER = 1<<27, IFF_FAILOVER_SLAVE = 1<<28, IFF_L3MDEV_RX_HANDLER = 1<<29, + IFF_LIVE_RENAME_OK = 1<<30, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1563,6 +1565,7 @@ enum netdev_priv_flags { #define IFF_FAILOVER IFF_FAILOVER #define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE #define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER +#define IFF_LIVE_RENAME_OK IFF_LIVE_RENAME_OK /** * struct net_device - The DEVICE structure. diff --git a/include/linux/nvme.h b/include/linux/nvme.h index baa49e6a23cc..c40720cb59ac 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -967,8 +967,13 @@ struct nvme_get_log_page_command { __le16 numdl; __le16 numdu; __u16 rsvd11; - __le32 lpol; - __le32 lpou; + union { + struct { + __le32 lpol; + __le32 lpou; + }; + __le64 lpo; + }; __u32 rsvd14[2]; }; diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 4eb26d278046..280ae96dc4c3 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -41,16 +41,6 @@ int move_freepages_block(struct zone *zone, struct page *page, /* * Changes migrate type in [start_pfn, end_pfn) to be MIGRATE_ISOLATE. - * If specified range includes migrate types other than MOVABLE or CMA, - * this will fail with -EBUSY. - * - * For isolating all pages in the range finally, the caller have to - * free all pages in the range. test_page_isolated() can be used for - * test it. - * - * The following flags are allowed (they can be combined in a bit mask) - * SKIP_HWPOISON - ignore hwpoison pages - * REPORT_FAILURE - report details about the failure to isolate the range */ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, diff --git a/include/linux/parport.h b/include/linux/parport.h index f41f1d041e2c..397607a0c0eb 100644 --- a/include/linux/parport.h +++ b/include/linux/parport.h @@ -460,7 +460,6 @@ extern size_t parport_ieee1284_epp_read_addr (struct parport *, void *, size_t, int); /* IEEE1284.3 functions */ -#define daisy_dev_name "Device ID probe" extern int parport_daisy_init (struct parport *port); extern void parport_daisy_fini (struct parport *port); extern struct pardevice *parport_open (int devnum, const char *name); @@ -469,18 +468,6 @@ extern ssize_t parport_device_id (int devnum, char *buffer, size_t len); extern void parport_daisy_deselect_all (struct parport *port); extern int parport_daisy_select (struct parport *port, int daisy, int mode); -#ifdef CONFIG_PARPORT_1284 -extern int daisy_drv_init(void); -extern void daisy_drv_exit(void); -#else -static inline int daisy_drv_init(void) -{ - return 0; -} - -static inline void daisy_drv_exit(void) {} -#endif - /* Lowlevel drivers _can_ call this support function to handle irqs. */ static inline void parport_generic_irq(struct parport *port) { diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 787d224ff43e..5c626fdc10db 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -101,18 +101,20 @@ struct pipe_buf_operations { /* * Get a reference to the pipe buffer. */ - void (*get)(struct pipe_inode_info *, struct pipe_buffer *); + bool (*get)(struct pipe_inode_info *, struct pipe_buffer *); }; /** * pipe_buf_get - get a reference to a pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to get a reference to + * + * Return: %true if the reference was successfully obtained. */ -static inline void pipe_buf_get(struct pipe_inode_info *pipe, +static inline __must_check bool pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { - buf->ops->get(pipe, buf); + return buf->ops->get(pipe, buf); } /** @@ -171,9 +173,10 @@ struct pipe_inode_info *alloc_pipe_info(void); void free_pipe_info(struct pipe_inode_info *); /* Generic pipe buffer ops functions */ -void generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *); +bool generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *); +int generic_pipe_buf_nosteal(struct pipe_inode_info *, struct pipe_buffer *); void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); void pipe_buf_mark_unmergeable(struct pipe_buffer *buf); diff --git a/include/linux/platform_data/gpio/gpio-amd-fch.h b/include/linux/platform_data/gpio/gpio-amd-fch.h index a867637e172d..9e46678edb2a 100644 --- a/include/linux/platform_data/gpio/gpio-amd-fch.h +++ b/include/linux/platform_data/gpio/gpio-amd-fch.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL+ */ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * AMD FCH gpio driver platform-data diff --git a/include/linux/platform_data/x86/clk-pmc-atom.h b/include/linux/platform_data/x86/clk-pmc-atom.h index 3ab892208343..7a37ac27d0fb 100644 --- a/include/linux/platform_data/x86/clk-pmc-atom.h +++ b/include/linux/platform_data/x86/clk-pmc-atom.h @@ -35,10 +35,13 @@ struct pmc_clk { * * @base: PMC clock register base offset * @clks: pointer to set of registered clocks, typically 0..5 + * @critical: flag to indicate if firmware enabled pmc_plt_clks + * should be marked as critial or not */ struct pmc_clk_data { void __iomem *base; const struct pmc_clk *clks; + bool critical; }; #endif /* __PLATFORM_DATA_X86_CLK_PMC_ATOM_H */ diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index edb9b040c94c..d5084ebd9f03 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -9,6 +9,13 @@ #include <linux/bug.h> /* For BUG_ON. */ #include <linux/pid_namespace.h> /* For task_active_pid_ns. */ #include <uapi/linux/ptrace.h> +#include <linux/seccomp.h> + +/* Add sp to seccomp_data, as seccomp is user API, we don't want to modify it */ +struct syscall_info { + __u64 sp; + struct seccomp_data data; +}; extern int ptrace_access_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags); @@ -407,9 +414,7 @@ static inline void user_single_step_report(struct pt_regs *regs) #define current_user_stack_pointer() user_stack_pointer(current_pt_regs()) #endif -extern int task_current_syscall(struct task_struct *target, long *callno, - unsigned long args[6], unsigned int maxargs, - unsigned long *sp, unsigned long *pc); +extern int task_current_syscall(struct task_struct *target, struct syscall_info *info); extern void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact); #endif diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 0cd9f10423fb..a3fda9f024c3 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -49,6 +49,27 @@ static inline void mmdrop(struct mm_struct *mm) __mmdrop(mm); } +/* + * This has to be called after a get_task_mm()/mmget_not_zero() + * followed by taking the mmap_sem for writing before modifying the + * vmas or anything the coredump pretends not to change from under it. + * + * NOTE: find_extend_vma() called from GUP context is the only place + * that can modify the "mm" (notably the vm_start/end) under mmap_sem + * for reading and outside the context of the process, so it is also + * the only case that holds the mmap_sem for reading that must call + * this function. Generally if the mmap_sem is hold for reading + * there's no need of this check after get_task_mm()/mmget_not_zero(). + * + * This function can be obsoleted and the check can be removed, after + * the coredump code will hold the mmap_sem for writing before + * invoking the ->core_dump methods. + */ +static inline bool mmget_still_valid(struct mm_struct *mm) +{ + return likely(!mm->core_state); +} + /** * mmget() - Pin the address space associated with a &struct mm_struct. * @mm: The address space to pin. diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index ae5655197698..e412c092c1e8 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -418,10 +418,20 @@ static inline void set_restore_sigmask(void) set_thread_flag(TIF_RESTORE_SIGMASK); WARN_ON(!test_thread_flag(TIF_SIGPENDING)); } + +static inline void clear_tsk_restore_sigmask(struct task_struct *tsk) +{ + clear_tsk_thread_flag(tsk, TIF_RESTORE_SIGMASK); +} + static inline void clear_restore_sigmask(void) { clear_thread_flag(TIF_RESTORE_SIGMASK); } +static inline bool test_tsk_restore_sigmask(struct task_struct *tsk) +{ + return test_tsk_thread_flag(tsk, TIF_RESTORE_SIGMASK); +} static inline bool test_restore_sigmask(void) { return test_thread_flag(TIF_RESTORE_SIGMASK); @@ -439,6 +449,10 @@ static inline void set_restore_sigmask(void) current->restore_sigmask = true; WARN_ON(!test_thread_flag(TIF_SIGPENDING)); } +static inline void clear_tsk_restore_sigmask(struct task_struct *tsk) +{ + tsk->restore_sigmask = false; +} static inline void clear_restore_sigmask(void) { current->restore_sigmask = false; @@ -447,6 +461,10 @@ static inline bool test_restore_sigmask(void) { return current->restore_sigmask; } +static inline bool test_tsk_restore_sigmask(struct task_struct *tsk) +{ + return tsk->restore_sigmask; +} static inline bool test_and_clear_restore_sigmask(void) { if (!current->restore_sigmask) diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index f3fb1edb3526..20d815a33145 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -21,6 +21,7 @@ struct shmem_inode_info { struct list_head swaplist; /* chain of maybes on swap */ struct shared_policy policy; /* NUMA memory alloc policy */ struct simple_xattrs xattrs; /* list of xattrs */ + atomic_t stop_eviction; /* hold when working on inode */ struct inode vfs_inode; }; diff --git a/include/linux/slab.h b/include/linux/slab.h index 11b45f7ae405..9449b19c5f10 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -32,6 +32,8 @@ #define SLAB_HWCACHE_ALIGN ((slab_flags_t __force)0x00002000U) /* Use GFP_DMA memory */ #define SLAB_CACHE_DMA ((slab_flags_t __force)0x00004000U) +/* Use GFP_DMA32 memory */ +#define SLAB_CACHE_DMA32 ((slab_flags_t __force)0x00008000U) /* DEBUG: Store the last owner for bug hunting */ #define SLAB_STORE_USER ((slab_flags_t __force)0x00010000U) /* Panic if kmem_cache_create() fails */ diff --git a/include/linux/socket.h b/include/linux/socket.h index 6016daeecee4..b57cd8bf96e2 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -26,7 +26,7 @@ typedef __kernel_sa_family_t sa_family_t; /* * 1003.1g requires sa_family_t and that sa_data is char. */ - + struct sockaddr { sa_family_t sa_family; /* address family, AF_xxx */ char sa_data[14]; /* 14 bytes of protocol address */ @@ -44,7 +44,7 @@ struct linger { * system, not 4.3. Thus msg_accrights(len) are now missing. They * belong in an obscure libc emulation or the bin. */ - + struct msghdr { void *msg_name; /* ptr to socket address structure */ int msg_namelen; /* size of socket address structure */ @@ -54,7 +54,7 @@ struct msghdr { unsigned int msg_flags; /* flags on received message */ struct kiocb *msg_iocb; /* ptr to iocb for async requests */ }; - + struct user_msghdr { void __user *msg_name; /* ptr to socket address structure */ int msg_namelen; /* size of socket address structure */ @@ -122,7 +122,7 @@ struct cmsghdr { * inside range, given by msg->msg_controllen before using * ancillary object DATA. --ANK (980731) */ - + static inline struct cmsghdr * __cmsg_nxthdr(void *__ctl, __kernel_size_t __size, struct cmsghdr *__cmsg) { @@ -264,10 +264,10 @@ struct ucred { /* Maximum queue length specifiable by listen. */ #define SOMAXCONN 128 -/* Flags we can use with send/ and recv. +/* Flags we can use with send/ and recv. Added those for 1003.1g not all are supported yet */ - + #define MSG_OOB 1 #define MSG_PEEK 2 #define MSG_DONTROUTE 4 diff --git a/include/linux/string.h b/include/linux/string.h index 7927b875f80c..6ab0a6fa512e 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -150,6 +150,9 @@ extern void * memscan(void *,int,__kernel_size_t); #ifndef __HAVE_ARCH_MEMCMP extern int memcmp(const void *,const void *,__kernel_size_t); #endif +#ifndef __HAVE_ARCH_BCMP +extern int bcmp(const void *,const void *,__kernel_size_t); +#endif #ifndef __HAVE_ARCH_MEMCHR extern void * memchr(const void *,int,__kernel_size_t); #endif diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index ec861cd0cfe8..52d41d0c1ae1 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -304,12 +304,4 @@ rpc_clnt_swap_deactivate(struct rpc_clnt *clnt) } #endif /* CONFIG_SUNRPC_SWAP */ -static inline bool -rpc_task_need_resched(const struct rpc_task *task) -{ - if (RPC_IS_QUEUED(task) || task->tk_callback) - return true; - return false; -} - #endif /* _LINUX_SUNRPC_SCHED_H_ */ diff --git a/include/linux/uio.h b/include/linux/uio.h index f184af1999a8..2d0131ad4604 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -60,7 +60,7 @@ struct iov_iter { static inline enum iter_type iov_iter_type(const struct iov_iter *i) { - return i->type & ~(READ | WRITE); + return i->type & ~(READ | WRITE | ITER_BVEC_FLAG_NO_REF); } static inline bool iter_is_iovec(const struct iov_iter *i) diff --git a/include/linux/usb.h b/include/linux/usb.h index 5e49e82c4368..ff010d1fd1c7 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -200,7 +200,6 @@ usb_find_last_int_out_endpoint(struct usb_host_interface *alt, * @dev: driver model's view of this device * @usb_dev: if an interface is bound to the USB major, this will point * to the sysfs representation for that device. - * @pm_usage_cnt: PM usage counter for this interface * @reset_ws: Used for scheduling resets from atomic context. * @resetting_device: USB core reset the device, so use alt setting 0 as * current; needs bandwidth alloc after reset. @@ -257,7 +256,6 @@ struct usb_interface { struct device dev; /* interface specific device info */ struct device *usb_dev; - atomic_t pm_usage_cnt; /* usage counter for autosuspend */ struct work_struct reset_ws; /* for resets in atomic context */ }; #define to_usb_interface(d) container_of(d, struct usb_interface, dev) diff --git a/include/linux/vbox_utils.h b/include/linux/vbox_utils.h index a240ed2a0372..ff56c443180c 100644 --- a/include/linux/vbox_utils.h +++ b/include/linux/vbox_utils.h @@ -24,15 +24,17 @@ __printf(1, 2) void vbg_debug(const char *fmt, ...); #define vbg_debug pr_debug #endif -int vbg_hgcm_connect(struct vbg_dev *gdev, +int vbg_hgcm_connect(struct vbg_dev *gdev, u32 requestor, struct vmmdev_hgcm_service_location *loc, u32 *client_id, int *vbox_status); -int vbg_hgcm_disconnect(struct vbg_dev *gdev, u32 client_id, int *vbox_status); +int vbg_hgcm_disconnect(struct vbg_dev *gdev, u32 requestor, + u32 client_id, int *vbox_status); -int vbg_hgcm_call(struct vbg_dev *gdev, u32 client_id, u32 function, - u32 timeout_ms, struct vmmdev_hgcm_function_parameter *parms, - u32 parm_count, int *vbox_status); +int vbg_hgcm_call(struct vbg_dev *gdev, u32 requestor, u32 client_id, + u32 function, u32 timeout_ms, + struct vmmdev_hgcm_function_parameter *parms, u32 parm_count, + int *vbox_status); /** * Convert a VirtualBox status code to a standard Linux kernel return value. diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index fab02133a919..3dc70adfe5f5 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -63,7 +63,7 @@ struct virtqueue; /* * Creates a virtqueue and allocates the descriptor ring. If * may_reduce_num is set, then this may allocate a smaller ring than - * expected. The caller should query virtqueue_get_ring_size to learn + * expected. The caller should query virtqueue_get_vring_size to learn * the actual size of the ring. */ struct virtqueue *vring_create_virtqueue(unsigned int index, diff --git a/include/net/act_api.h b/include/net/act_api.h index c745e9ccfab2..c61a1bf4e3de 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -39,7 +39,7 @@ struct tc_action { struct gnet_stats_basic_cpu __percpu *cpu_bstats_hw; struct gnet_stats_queue __percpu *cpu_qstats; struct tc_cookie __rcu *act_cookie; - struct tcf_chain *goto_chain; + struct tcf_chain __rcu *goto_chain; }; #define tcf_index common.tcfa_index #define tcf_refcnt common.tcfa_refcnt @@ -90,7 +90,7 @@ struct tc_action_ops { int (*lookup)(struct net *net, struct tc_action **a, u32 index); int (*init)(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **act, int ovr, - int bind, bool rtnl_held, + int bind, bool rtnl_held, struct tcf_proto *tp, struct netlink_ext_ack *extack); int (*walk)(struct net *, struct sk_buff *, struct netlink_callback *, int, @@ -181,6 +181,11 @@ int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int); int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int); int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int); +int tcf_action_check_ctrlact(int action, struct tcf_proto *tp, + struct tcf_chain **handle, + struct netlink_ext_ack *newchain); +struct tcf_chain *tcf_action_set_ctrlact(struct tc_action *a, int action, + struct tcf_chain *newchain); #endif /* CONFIG_NET_CLS_ACT */ static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes, diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index 2bfb87eb98ce..78c856cba4f5 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -61,10 +61,12 @@ int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t, rxrpc_user_attach_call_t, unsigned long, gfp_t, unsigned int); void rxrpc_kernel_set_tx_length(struct socket *, struct rxrpc_call *, s64); -u32 rxrpc_kernel_check_life(const struct socket *, const struct rxrpc_call *); +bool rxrpc_kernel_check_life(const struct socket *, const struct rxrpc_call *, + u32 *); void rxrpc_kernel_probe_life(struct socket *, struct rxrpc_call *); u32 rxrpc_kernel_get_epoch(struct socket *, struct rxrpc_call *); bool rxrpc_kernel_get_reply_time(struct socket *, struct rxrpc_call *, ktime_t *); +bool rxrpc_kernel_call_is_complete(struct rxrpc_call *); #endif /* _NET_RXRPC_H */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index bb307a11ee63..13bfeb712d36 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -7183,6 +7183,11 @@ void cfg80211_pmsr_complete(struct wireless_dev *wdev, #define wiphy_info(wiphy, format, args...) \ dev_info(&(wiphy)->dev, format, ##args) +#define wiphy_err_ratelimited(wiphy, format, args...) \ + dev_err_ratelimited(&(wiphy)->dev, format, ##args) +#define wiphy_warn_ratelimited(wiphy, format, args...) \ + dev_warn_ratelimited(&(wiphy)->dev, format, ##args) + #define wiphy_debug(wiphy, format, args...) \ wiphy_printk(KERN_DEBUG, wiphy, format, ##args) diff --git a/include/net/ip.h b/include/net/ip.h index be3cad9c2e4c..583526aad1d0 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -677,7 +677,7 @@ int ip_options_get_from_user(struct net *net, struct ip_options_rcu **optp, unsigned char __user *data, int optlen); void ip_options_undo(struct ip_options *opt); void ip_forward_options(struct sk_buff *skb); -int ip_options_rcv_srr(struct sk_buff *skb); +int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev); /* * Functions provided by ip_sockglue.c diff --git a/include/net/mac80211.h b/include/net/mac80211.h index ac2ed8ec662b..112dc18c658f 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -6231,8 +6231,6 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, * @hw: pointer as obtained from ieee80211_alloc_hw() * @ac: AC number to return packets from. * - * Should only be called between calls to ieee80211_txq_schedule_start() - * and ieee80211_txq_schedule_end(). * Returns the next txq if successful, %NULL if no queue is eligible. If a txq * is returned, it should be returned with ieee80211_return_txq() after the * driver has finished scheduling it. @@ -6240,51 +6238,58 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac); /** - * ieee80211_return_txq - return a TXQ previously acquired by ieee80211_next_txq() - * - * @hw: pointer as obtained from ieee80211_alloc_hw() - * @txq: pointer obtained from station or virtual interface - * - * Should only be called between calls to ieee80211_txq_schedule_start() - * and ieee80211_txq_schedule_end(). - */ -void ieee80211_return_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq); - -/** - * ieee80211_txq_schedule_start - acquire locks for safe scheduling of an AC + * ieee80211_txq_schedule_start - start new scheduling round for TXQs * * @hw: pointer as obtained from ieee80211_alloc_hw() * @ac: AC number to acquire locks for * - * Acquire locks needed to schedule TXQs from the given AC. Should be called - * before ieee80211_next_txq() or ieee80211_return_txq(). + * Should be called before ieee80211_next_txq() or ieee80211_return_txq(). + * The driver must not call multiple TXQ scheduling rounds concurrently. */ -void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac) - __acquires(txq_lock); +void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac); + +/* (deprecated) */ +static inline void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac) +{ +} + +void __ieee80211_schedule_txq(struct ieee80211_hw *hw, + struct ieee80211_txq *txq, bool force); /** - * ieee80211_txq_schedule_end - release locks for safe scheduling of an AC + * ieee80211_schedule_txq - schedule a TXQ for transmission * * @hw: pointer as obtained from ieee80211_alloc_hw() - * @ac: AC number to acquire locks for + * @txq: pointer obtained from station or virtual interface * - * Release locks previously acquired by ieee80211_txq_schedule_end(). + * Schedules a TXQ for transmission if it is not already scheduled, + * even if mac80211 does not have any packets buffered. + * + * The driver may call this function if it has buffered packets for + * this TXQ internally. */ -void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac) - __releases(txq_lock); +static inline void +ieee80211_schedule_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq) +{ + __ieee80211_schedule_txq(hw, txq, true); +} /** - * ieee80211_schedule_txq - schedule a TXQ for transmission + * ieee80211_return_txq - return a TXQ previously acquired by ieee80211_next_txq() * * @hw: pointer as obtained from ieee80211_alloc_hw() * @txq: pointer obtained from station or virtual interface + * @force: schedule txq even if mac80211 does not have any buffered packets. * - * Schedules a TXQ for transmission if it is not already scheduled. Takes a - * lock, which means it must *not* be called between - * ieee80211_txq_schedule_start() and ieee80211_txq_schedule_end() + * The driver may set force=true if it has buffered packets for this TXQ + * internally. */ -void ieee80211_schedule_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq) - __acquires(txq_lock) __releases(txq_lock); +static inline void +ieee80211_return_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq, + bool force) +{ + __ieee80211_schedule_txq(hw, txq, force); +} /** * ieee80211_txq_may_transmit - check whether TXQ is allowed to transmit diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index a68ced28d8f4..12689ddfc24c 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -59,6 +59,7 @@ struct net { */ spinlock_t rules_mod_lock; + u32 hash_mix; atomic64_t cookie_gen; struct list_head list; /* list of network namespaces */ diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 5ee7b30b4917..d2bc733a2ef1 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -316,6 +316,8 @@ struct nf_conn *nf_ct_tmpl_alloc(struct net *net, gfp_t flags); void nf_ct_tmpl_free(struct nf_conn *tmpl); +u32 nf_ct_get_id(const struct nf_conn *ct); + static inline void nf_ct_set(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info info) { diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 778087591983..a49edfdf47e8 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -75,6 +75,12 @@ bool nf_conntrack_invert_icmp_tuple(struct nf_conntrack_tuple *tuple, bool nf_conntrack_invert_icmpv6_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig); +int nf_conntrack_inet_error(struct nf_conn *tmpl, struct sk_buff *skb, + unsigned int dataoff, + const struct nf_hook_state *state, + u8 l4proto, + union nf_inet_addr *outer_daddr); + int nf_conntrack_icmpv4_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, diff --git a/include/net/netns/hash.h b/include/net/netns/hash.h index 16a842456189..d9b665151f3d 100644 --- a/include/net/netns/hash.h +++ b/include/net/netns/hash.h @@ -2,16 +2,10 @@ #ifndef __NET_NS_HASH_H__ #define __NET_NS_HASH_H__ -#include <asm/cache.h> - -struct net; +#include <net/net_namespace.h> static inline u32 net_hash_mix(const struct net *net) { -#ifdef CONFIG_NET_NS - return (u32)(((unsigned long)net) >> ilog2(sizeof(*net))); -#else - return 0; -#endif + return net->hash_mix; } #endif diff --git a/include/net/netrom.h b/include/net/netrom.h index 5a0714ff500f..80f15b1c1a48 100644 --- a/include/net/netrom.h +++ b/include/net/netrom.h @@ -266,7 +266,7 @@ void nr_stop_idletimer(struct sock *); int nr_t1timer_running(struct sock *); /* sysctl_net_netrom.c */ -void nr_register_sysctl(void); +int nr_register_sysctl(void); void nr_unregister_sysctl(void); #endif diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h index 87499b6b35d6..df5c69db68af 100644 --- a/include/net/nfc/nci_core.h +++ b/include/net/nfc/nci_core.h @@ -166,7 +166,7 @@ struct nci_conn_info { * According to specification 102 622 chapter 4.4 Pipes, * the pipe identifier is 7 bits long. */ -#define NCI_HCI_MAX_PIPES 127 +#define NCI_HCI_MAX_PIPES 128 struct nci_hci_gate { u8 gate; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 31284c078d06..a2b38b3deeca 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -378,6 +378,7 @@ struct tcf_chain { bool flushing; const struct tcf_proto_ops *tmplt_ops; void *tmplt_priv; + struct rcu_head rcu; }; struct tcf_block { @@ -922,6 +923,41 @@ static inline void qdisc_qstats_overlimit(struct Qdisc *sch) sch->qstats.overlimits++; } +static inline int qdisc_qstats_copy(struct gnet_dump *d, struct Qdisc *sch) +{ + __u32 qlen = qdisc_qlen_sum(sch); + + return gnet_stats_copy_queue(d, sch->cpu_qstats, &sch->qstats, qlen); +} + +static inline void qdisc_qstats_qlen_backlog(struct Qdisc *sch, __u32 *qlen, + __u32 *backlog) +{ + struct gnet_stats_queue qstats = { 0 }; + __u32 len = qdisc_qlen_sum(sch); + + __gnet_stats_copy_queue(&qstats, sch->cpu_qstats, &sch->qstats, len); + *qlen = qstats.qlen; + *backlog = qstats.backlog; +} + +static inline void qdisc_tree_flush_backlog(struct Qdisc *sch) +{ + __u32 qlen, backlog; + + qdisc_qstats_qlen_backlog(sch, &qlen, &backlog); + qdisc_tree_reduce_backlog(sch, qlen, backlog); +} + +static inline void qdisc_purge_queue(struct Qdisc *sch) +{ + __u32 qlen, backlog; + + qdisc_qstats_qlen_backlog(sch, &qlen, &backlog); + qdisc_reset(sch); + qdisc_tree_reduce_backlog(sch, qlen, backlog); +} + static inline void qdisc_skb_head_init(struct qdisc_skb_head *qh) { qh->head = NULL; @@ -1105,13 +1141,8 @@ static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new, sch_tree_lock(sch); old = *pold; *pold = new; - if (old != NULL) { - unsigned int qlen = old->q.qlen; - unsigned int backlog = old->qstats.backlog; - - qdisc_reset(old); - qdisc_tree_reduce_backlog(old, qlen, backlog); - } + if (old != NULL) + qdisc_tree_flush_backlog(old); sch_tree_unlock(sch); return old; diff --git a/include/net/sctp/checksum.h b/include/net/sctp/checksum.h index 32ee65a30aff..1c6e6c0766ca 100644 --- a/include/net/sctp/checksum.h +++ b/include/net/sctp/checksum.h @@ -61,7 +61,7 @@ static inline __wsum sctp_csum_combine(__wsum csum, __wsum csum2, static inline __le32 sctp_compute_cksum(const struct sk_buff *skb, unsigned int offset) { - struct sctphdr *sh = sctp_hdr(skb); + struct sctphdr *sh = (struct sctphdr *)(skb->data + offset); const struct skb_checksum_ops ops = { .update = sctp_csum_update, .combine = sctp_csum_combine, diff --git a/include/net/sctp/command.h b/include/net/sctp/command.h index 6640f84fe536..6d5beac29bc1 100644 --- a/include/net/sctp/command.h +++ b/include/net/sctp/command.h @@ -105,7 +105,6 @@ enum sctp_verb { SCTP_CMD_T1_RETRAN, /* Mark for retransmission after T1 timeout */ SCTP_CMD_UPDATE_INITTAG, /* Update peer inittag */ SCTP_CMD_SEND_MSG, /* Send the whole use message */ - SCTP_CMD_SEND_NEXT_ASCONF, /* Send the next ASCONF after ACK */ SCTP_CMD_PURGE_ASCONF_QUEUE, /* Purge all asconf queues.*/ SCTP_CMD_SET_ASOC, /* Restore association context */ SCTP_CMD_LAST diff --git a/include/net/sock.h b/include/net/sock.h index 328cb7cb7b0b..341f8bafa0cf 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -710,6 +710,12 @@ static inline void sk_add_node_rcu(struct sock *sk, struct hlist_head *list) hlist_add_head_rcu(&sk->sk_node, list); } +static inline void sk_add_node_tail_rcu(struct sock *sk, struct hlist_head *list) +{ + sock_hold(sk); + hlist_add_tail_rcu(&sk->sk_node, list); +} + static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) { hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list); @@ -2078,12 +2084,6 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq) * @p: poll_table * * See the comments in the wq_has_sleeper function. - * - * Do not derive sock from filp->private_data here. An SMC socket establishes - * an internal TCP socket that is used in the fallback case. All socket - * operations on the SMC socket are then forwarded to the TCP socket. In case of - * poll, the filp->private_data pointer references the SMC socket because the - * TCP socket has no file assigned. */ static inline void sock_poll_wait(struct file *filp, struct socket *sock, poll_table *p) diff --git a/include/net/tc_act/tc_gact.h b/include/net/tc_act/tc_gact.h index ee8d005f56fc..eb8f01c819e6 100644 --- a/include/net/tc_act/tc_gact.h +++ b/include/net/tc_act/tc_gact.h @@ -56,7 +56,7 @@ static inline bool is_tcf_gact_goto_chain(const struct tc_action *a) static inline u32 tcf_gact_goto_chain_index(const struct tc_action *a) { - return a->goto_chain->index; + return READ_ONCE(a->tcfa_action) & TC_ACT_EXT_VAL_MASK; } #endif /* __NET_TC_GACT_H */ diff --git a/include/net/tls.h b/include/net/tls.h index a5a938583295..5934246b2c6f 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -307,6 +307,7 @@ int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tls_device_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); void tls_device_sk_destruct(struct sock *sk); +void tls_device_free_resources_tx(struct sock *sk); void tls_device_init(void); void tls_device_cleanup(void); int tls_tx_records(struct sock *sk, int flags); @@ -330,6 +331,7 @@ int tls_push_sg(struct sock *sk, struct tls_context *ctx, int flags); int tls_push_partial_record(struct sock *sk, struct tls_context *ctx, int flags); +bool tls_free_partial_record(struct sock *sk, struct tls_context *ctx); static inline struct tls_msg *tls_msg(struct sk_buff *skb) { @@ -379,7 +381,7 @@ tls_validate_xmit_skb(struct sock *sk, struct net_device *dev, static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk) { #ifdef CONFIG_SOCK_VALIDATE_XMIT - return sk_fullsock(sk) & + return sk_fullsock(sk) && (smp_load_acquire(&sk->sk_validate_xmit_skb) == &tls_validate_xmit_skb); #else diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 61cf7dbb6782..d074b6d60f8a 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -36,7 +36,6 @@ struct xdp_umem { u32 headroom; u32 chunk_size_nohr; struct user_struct *user; - struct pid *pid; unsigned long address; refcount_t users; struct work_struct work; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 85386becbaea..c9b0b2b5d672 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -295,7 +295,8 @@ struct xfrm_replay { }; struct xfrm_if_cb { - struct xfrm_if *(*decode_session)(struct sk_buff *skb); + struct xfrm_if *(*decode_session)(struct sk_buff *skb, + unsigned short family); }; void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb); @@ -1404,6 +1405,23 @@ static inline int xfrm_state_kern(const struct xfrm_state *x) return atomic_read(&x->tunnel_users); } +static inline bool xfrm_id_proto_valid(u8 proto) +{ + switch (proto) { + case IPPROTO_AH: + case IPPROTO_ESP: + case IPPROTO_COMP: +#if IS_ENABLED(CONFIG_IPV6) + case IPPROTO_ROUTING: + case IPPROTO_DSTOPTS: +#endif + return true; + default: + return false; + } +} + +/* IPSEC_PROTO_ANY only matches 3 IPsec protocols, 0 could match all. */ static inline int xfrm_id_proto_match(u8 proto, u8 userproto) { return (!userproto || proto == userproto || diff --git a/include/sound/soc.h b/include/sound/soc.h index eb7db605955b..482b4ea87c3c 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -802,8 +802,13 @@ struct snd_soc_component_driver { int probe_order; int remove_order; - /* signal if the module handling the component cannot be removed */ - unsigned int ignore_module_refcount:1; + /* + * signal if the module handling the component should not be removed + * if a pcm is open. Setting this would prevent the module + * refcount being incremented in probe() but allow it be incremented + * when a pcm is opened and decremented when it is closed. + */ + unsigned int module_get_upon_open:1; /* bits */ unsigned int idle_bias_on:1; @@ -1083,6 +1088,8 @@ struct snd_soc_card { struct mutex mutex; struct mutex dapm_mutex; + spinlock_t dpcm_lock; + bool instantiated; bool topology_shortname_created; diff --git a/include/trace/events/syscalls.h b/include/trace/events/syscalls.h index 44a3259ed4a5..b6e0cbc2c71f 100644 --- a/include/trace/events/syscalls.h +++ b/include/trace/events/syscalls.h @@ -28,7 +28,7 @@ TRACE_EVENT_FN(sys_enter, TP_fast_assign( __entry->id = id; - syscall_get_arguments(current, regs, 0, 6, __entry->args); + syscall_get_arguments(current, regs, __entry->args); ), TP_printk("NR %ld (%lx, %lx, %lx, %lx, %lx, %lx)", diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index 5f24b50c9e88..059dc2bedaf6 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -7,5 +7,7 @@ no-export-headers += kvm.h endif ifeq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/uapi/asm/kvm_para.h),) +ifeq ($(wildcard $(objtree)/arch/$(SRCARCH)/include/generated/uapi/asm/kvm_para.h),) no-export-headers += kvm_para.h endif +endif diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 3c38ac9a92a7..929c8e537a14 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -502,16 +502,6 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags) - * Description - * Push an element *value* in *map*. *flags* is one of: - * - * **BPF_EXIST** - * If the queue/stack is full, the oldest element is removed to - * make room for this. - * Return - * 0 on success, or a negative error in case of failure. - * * int bpf_probe_read(void *dst, u32 size, const void *src) * Description * For tracing programs, safely attempt to read *size* bytes from @@ -1435,14 +1425,14 @@ union bpf_attr { * u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx) * Description * Equivalent to bpf_get_socket_cookie() helper that accepts - * *skb*, but gets socket from **struct bpf_sock_addr** contex. + * *skb*, but gets socket from **struct bpf_sock_addr** context. * Return * A 8-byte long non-decreasing number. * * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx) * Description * Equivalent to bpf_get_socket_cookie() helper that accepts - * *skb*, but gets socket from **struct bpf_sock_ops** contex. + * *skb*, but gets socket from **struct bpf_sock_ops** context. * Return * A 8-byte long non-decreasing number. * @@ -2098,52 +2088,52 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle) + * int bpf_rc_repeat(void *ctx) * Description * This helper is used in programs implementing IR decoding, to - * report a successfully decoded key press with *scancode*, - * *toggle* value in the given *protocol*. The scancode will be - * translated to a keycode using the rc keymap, and reported as - * an input key down event. After a period a key up event is - * generated. This period can be extended by calling either - * **bpf_rc_keydown**\ () again with the same values, or calling - * **bpf_rc_repeat**\ (). + * report a successfully decoded repeat key message. This delays + * the generation of a key up event for previously generated + * key down event. * - * Some protocols include a toggle bit, in case the button was - * released and pressed again between consecutive scancodes. + * Some IR protocols like NEC have a special IR message for + * repeating last button, for when a button is held down. * * The *ctx* should point to the lirc sample as passed into * the program. * - * The *protocol* is the decoded protocol number (see - * **enum rc_proto** for some predefined values). - * * This helper is only available is the kernel was compiled with * the **CONFIG_BPF_LIRC_MODE2** configuration option set to * "**y**". * Return * 0 * - * int bpf_rc_repeat(void *ctx) + * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle) * Description * This helper is used in programs implementing IR decoding, to - * report a successfully decoded repeat key message. This delays - * the generation of a key up event for previously generated - * key down event. + * report a successfully decoded key press with *scancode*, + * *toggle* value in the given *protocol*. The scancode will be + * translated to a keycode using the rc keymap, and reported as + * an input key down event. After a period a key up event is + * generated. This period can be extended by calling either + * **bpf_rc_keydown**\ () again with the same values, or calling + * **bpf_rc_repeat**\ (). * - * Some IR protocols like NEC have a special IR message for - * repeating last button, for when a button is held down. + * Some protocols include a toggle bit, in case the button was + * released and pressed again between consecutive scancodes. * * The *ctx* should point to the lirc sample as passed into * the program. * + * The *protocol* is the decoded protocol number (see + * **enum rc_proto** for some predefined values). + * * This helper is only available is the kernel was compiled with * the **CONFIG_BPF_LIRC_MODE2** configuration option set to * "**y**". * Return * 0 * - * uint64_t bpf_skb_cgroup_id(struct sk_buff *skb) + * u64 bpf_skb_cgroup_id(struct sk_buff *skb) * Description * Return the cgroup v2 id of the socket associated with the *skb*. * This is roughly similar to the **bpf_get_cgroup_classid**\ () @@ -2159,30 +2149,12 @@ union bpf_attr { * Return * The id is returned or 0 in case the id could not be retrieved. * - * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level) - * Description - * Return id of cgroup v2 that is ancestor of cgroup associated - * with the *skb* at the *ancestor_level*. The root cgroup is at - * *ancestor_level* zero and each step down the hierarchy - * increments the level. If *ancestor_level* == level of cgroup - * associated with *skb*, then return value will be same as that - * of **bpf_skb_cgroup_id**\ (). - * - * The helper is useful to implement policies based on cgroups - * that are upper in hierarchy than immediate cgroup associated - * with *skb*. - * - * The format of returned id and helper limitations are same as in - * **bpf_skb_cgroup_id**\ (). - * Return - * The id is returned or 0 in case the id could not be retrieved. - * * u64 bpf_get_current_cgroup_id(void) * Return * A 64-bit integer containing the current cgroup id based * on the cgroup within which the current task is running. * - * void* get_local_storage(void *map, u64 flags) + * void *bpf_get_local_storage(void *map, u64 flags) * Description * Get the pointer to the local storage area. * The type and the size of the local storage is defined @@ -2209,6 +2181,24 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * + * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level) + * Description + * Return id of cgroup v2 that is ancestor of cgroup associated + * with the *skb* at the *ancestor_level*. The root cgroup is at + * *ancestor_level* zero and each step down the hierarchy + * increments the level. If *ancestor_level* == level of cgroup + * associated with *skb*, then return value will be same as that + * of **bpf_skb_cgroup_id**\ (). + * + * The helper is useful to implement policies based on cgroups + * that are upper in hierarchy than immediate cgroup associated + * with *skb*. + * + * The format of returned id and helper limitations are same as in + * **bpf_skb_cgroup_id**\ (). + * Return + * The id is returned or 0 in case the id could not be retrieved. + * * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) * Description * Look for TCP socket matching *tuple*, optionally in a child @@ -2289,6 +2279,16 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * + * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags) + * Description + * Push an element *value* in *map*. *flags* is one of: + * + * **BPF_EXIST** + * If the queue/stack is full, the oldest element is + * removed to make room for this. + * Return + * 0 on success, or a negative error in case of failure. + * * int bpf_map_pop_elem(struct bpf_map *map, void *value) * Description * Pop an element from *map*. @@ -2343,29 +2343,94 @@ union bpf_attr { * Return * 0 * + * int bpf_spin_lock(struct bpf_spin_lock *lock) + * Description + * Acquire a spinlock represented by the pointer *lock*, which is + * stored as part of a value of a map. Taking the lock allows to + * safely update the rest of the fields in that value. The + * spinlock can (and must) later be released with a call to + * **bpf_spin_unlock**\ (\ *lock*\ ). + * + * Spinlocks in BPF programs come with a number of restrictions + * and constraints: + * + * * **bpf_spin_lock** objects are only allowed inside maps of + * types **BPF_MAP_TYPE_HASH** and **BPF_MAP_TYPE_ARRAY** (this + * list could be extended in the future). + * * BTF description of the map is mandatory. + * * The BPF program can take ONE lock at a time, since taking two + * or more could cause dead locks. + * * Only one **struct bpf_spin_lock** is allowed per map element. + * * When the lock is taken, calls (either BPF to BPF or helpers) + * are not allowed. + * * The **BPF_LD_ABS** and **BPF_LD_IND** instructions are not + * allowed inside a spinlock-ed region. + * * The BPF program MUST call **bpf_spin_unlock**\ () to release + * the lock, on all execution paths, before it returns. + * * The BPF program can access **struct bpf_spin_lock** only via + * the **bpf_spin_lock**\ () and **bpf_spin_unlock**\ () + * helpers. Loading or storing data into the **struct + * bpf_spin_lock** *lock*\ **;** field of a map is not allowed. + * * To use the **bpf_spin_lock**\ () helper, the BTF description + * of the map value must be a struct and have **struct + * bpf_spin_lock** *anyname*\ **;** field at the top level. + * Nested lock inside another struct is not allowed. + * * The **struct bpf_spin_lock** *lock* field in a map value must + * be aligned on a multiple of 4 bytes in that value. + * * Syscall with command **BPF_MAP_LOOKUP_ELEM** does not copy + * the **bpf_spin_lock** field to user space. + * * Syscall with command **BPF_MAP_UPDATE_ELEM**, or update from + * a BPF program, do not update the **bpf_spin_lock** field. + * * **bpf_spin_lock** cannot be on the stack or inside a + * networking packet (it can only be inside of a map values). + * * **bpf_spin_lock** is available to root only. + * * Tracing programs and socket filter programs cannot use + * **bpf_spin_lock**\ () due to insufficient preemption checks + * (but this may change in the future). + * * **bpf_spin_lock** is not allowed in inner maps of map-in-map. + * Return + * 0 + * + * int bpf_spin_unlock(struct bpf_spin_lock *lock) + * Description + * Release the *lock* previously locked by a call to + * **bpf_spin_lock**\ (\ *lock*\ ). + * Return + * 0 + * * struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk) * Description * This helper gets a **struct bpf_sock** pointer such - * that all the fields in bpf_sock can be accessed. + * that all the fields in this **bpf_sock** can be accessed. * Return - * A **struct bpf_sock** pointer on success, or NULL in + * A **struct bpf_sock** pointer on success, or **NULL** in * case of failure. * * struct bpf_tcp_sock *bpf_tcp_sock(struct bpf_sock *sk) * Description * This helper gets a **struct bpf_tcp_sock** pointer from a * **struct bpf_sock** pointer. - * * Return - * A **struct bpf_tcp_sock** pointer on success, or NULL in + * A **struct bpf_tcp_sock** pointer on success, or **NULL** in * case of failure. * * int bpf_skb_ecn_set_ce(struct sk_buf *skb) - * Description - * Sets ECN of IP header to ce (congestion encountered) if - * current value is ect (ECN capable). Works with IPv6 and IPv4. - * Return - * 1 if set, 0 if not set. + * Description + * Set ECN (Explicit Congestion Notification) field of IP header + * to **CE** (Congestion Encountered) if current value is **ECT** + * (ECN Capable Transport). Otherwise, do nothing. Works with IPv6 + * and IPv4. + * Return + * 1 if the **CE** flag is set (either by the current helper call + * or because it was already present), 0 if it is not set. + * + * struct bpf_sock *bpf_get_listener_sock(struct bpf_sock *sk) + * Description + * Return a **struct bpf_sock** pointer in **TCP_LISTEN** state. + * **bpf_sk_release**\ () is unnecessary and not allowed. + * Return + * A **struct bpf_sock** pointer on success, or **NULL** in + * case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2465,7 +2530,8 @@ union bpf_attr { FN(spin_unlock), \ FN(sk_fullsock), \ FN(tcp_sock), \ - FN(skb_ecn_set_ce), + FN(skb_ecn_set_ce), \ + FN(get_listener_sock), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 3652b239dad1..d473e5ed044c 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1591,7 +1591,7 @@ enum ethtool_link_mode_bit_indices { static inline int ethtool_validate_speed(__u32 speed) { - return speed <= INT_MAX || speed == SPEED_UNKNOWN; + return speed <= INT_MAX || speed == (__u32)SPEED_UNKNOWN; } /* Duplex, half or full. */ diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 7f14d4a66c28..64cee116928e 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -439,10 +439,12 @@ #define KEY_TITLE 0x171 #define KEY_SUBTITLE 0x172 #define KEY_ANGLE 0x173 -#define KEY_ZOOM 0x174 +#define KEY_FULL_SCREEN 0x174 /* AC View Toggle */ +#define KEY_ZOOM KEY_FULL_SCREEN #define KEY_MODE 0x175 #define KEY_KEYBOARD 0x176 -#define KEY_SCREEN 0x177 +#define KEY_ASPECT_RATIO 0x177 /* HUTRR37: Aspect */ +#define KEY_SCREEN KEY_ASPECT_RATIO #define KEY_PC 0x178 /* Media Select Computer */ #define KEY_TV 0x179 /* Media Select TV */ #define KEY_TV2 0x17a /* Media Select Cable */ diff --git a/include/uapi/linux/vbox_vmmdev_types.h b/include/uapi/linux/vbox_vmmdev_types.h index 0e68024f36c7..26f39816af14 100644 --- a/include/uapi/linux/vbox_vmmdev_types.h +++ b/include/uapi/linux/vbox_vmmdev_types.h @@ -102,6 +102,66 @@ enum vmmdev_request_type { #define VMMDEVREQ_HGCM_CALL VMMDEVREQ_HGCM_CALL32 #endif +/* vmmdev_request_header.requestor defines */ + +/* Requestor user not given. */ +#define VMMDEV_REQUESTOR_USR_NOT_GIVEN 0x00000000 +/* The kernel driver (vboxguest) is the requestor. */ +#define VMMDEV_REQUESTOR_USR_DRV 0x00000001 +/* Some other kernel driver is the requestor. */ +#define VMMDEV_REQUESTOR_USR_DRV_OTHER 0x00000002 +/* The root or a admin user is the requestor. */ +#define VMMDEV_REQUESTOR_USR_ROOT 0x00000003 +/* Regular joe user is making the request. */ +#define VMMDEV_REQUESTOR_USR_USER 0x00000006 +/* User classification mask. */ +#define VMMDEV_REQUESTOR_USR_MASK 0x00000007 + +/* Kernel mode request. Note this is 0, check for !USERMODE instead. */ +#define VMMDEV_REQUESTOR_KERNEL 0x00000000 +/* User mode request. */ +#define VMMDEV_REQUESTOR_USERMODE 0x00000008 +/* User or kernel mode classification mask. */ +#define VMMDEV_REQUESTOR_MODE_MASK 0x00000008 + +/* Don't know the physical console association of the requestor. */ +#define VMMDEV_REQUESTOR_CON_DONT_KNOW 0x00000000 +/* + * The request originates with a process that is NOT associated with the + * physical console. + */ +#define VMMDEV_REQUESTOR_CON_NO 0x00000010 +/* Requestor process is associated with the physical console. */ +#define VMMDEV_REQUESTOR_CON_YES 0x00000020 +/* Console classification mask. */ +#define VMMDEV_REQUESTOR_CON_MASK 0x00000030 + +/* Requestor is member of special VirtualBox user group. */ +#define VMMDEV_REQUESTOR_GRP_VBOX 0x00000080 + +/* Note: trust level is for windows guests only, linux always uses not-given */ +/* Requestor trust level: Unspecified */ +#define VMMDEV_REQUESTOR_TRUST_NOT_GIVEN 0x00000000 +/* Requestor trust level: Untrusted (SID S-1-16-0) */ +#define VMMDEV_REQUESTOR_TRUST_UNTRUSTED 0x00001000 +/* Requestor trust level: Untrusted (SID S-1-16-4096) */ +#define VMMDEV_REQUESTOR_TRUST_LOW 0x00002000 +/* Requestor trust level: Medium (SID S-1-16-8192) */ +#define VMMDEV_REQUESTOR_TRUST_MEDIUM 0x00003000 +/* Requestor trust level: Medium plus (SID S-1-16-8448) */ +#define VMMDEV_REQUESTOR_TRUST_MEDIUM_PLUS 0x00004000 +/* Requestor trust level: High (SID S-1-16-12288) */ +#define VMMDEV_REQUESTOR_TRUST_HIGH 0x00005000 +/* Requestor trust level: System (SID S-1-16-16384) */ +#define VMMDEV_REQUESTOR_TRUST_SYSTEM 0x00006000 +/* Requestor trust level >= Protected (SID S-1-16-20480, S-1-16-28672) */ +#define VMMDEV_REQUESTOR_TRUST_PROTECTED 0x00007000 +/* Requestor trust level mask */ +#define VMMDEV_REQUESTOR_TRUST_MASK 0x00007000 + +/* Requestor is using the less trusted user device node (/dev/vboxuser) */ +#define VMMDEV_REQUESTOR_USER_DEVICE 0x00008000 + /** HGCM service location types. */ enum vmmdev_hgcm_service_location_type { VMMDEV_HGCM_LOC_INVALID = 0, diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h index 87b3198f4b5d..f4d4010b7e3e 100644 --- a/include/uapi/rdma/mlx5-abi.h +++ b/include/uapi/rdma/mlx5-abi.h @@ -238,6 +238,7 @@ enum mlx5_ib_query_dev_resp_flags { MLX5_IB_QUERY_DEV_RESP_FLAGS_CQE_128B_COMP = 1 << 0, MLX5_IB_QUERY_DEV_RESP_FLAGS_CQE_128B_PAD = 1 << 1, MLX5_IB_QUERY_DEV_RESP_PACKET_BASED_CREDIT_MODE = 1 << 2, + MLX5_IB_QUERY_DEV_RESP_FLAGS_SCAT2CQE_DCT = 1 << 3, }; enum mlx5_ib_tunnel_offloads { diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h index 404d4b9ffe76..df1153cea0b7 100644 --- a/include/uapi/sound/asound.h +++ b/include/uapi/sound/asound.h @@ -32,6 +32,7 @@ #ifndef __KERNEL__ #include <stdlib.h> +#include <time.h> #endif /* diff --git a/init/main.c b/init/main.c index 598e278b46f7..7d4025d665eb 100644 --- a/init/main.c +++ b/init/main.c @@ -582,6 +582,8 @@ asmlinkage __visible void __init start_kernel(void) page_alloc_init(); pr_notice("Kernel command line: %s\n", boot_command_line); + /* parameters may set static keys */ + jump_label_init(); parse_early_param(); after_dashes = parse_args("Booting kernel", static_command_line, __start___param, @@ -591,8 +593,6 @@ asmlinkage __visible void __init start_kernel(void) parse_args("Setting init args", after_dashes, NULL, 0, -1, -1, NULL, set_init_arg); - jump_label_init(); - /* * These use large bootmem allocations and must precede * kmem_cache_init() diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 8974b3755670..3c18260403dd 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -162,10 +162,14 @@ static void cpu_map_kthread_stop(struct work_struct *work) static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf) { + unsigned int hard_start_headroom; unsigned int frame_size; void *pkt_data_start; struct sk_buff *skb; + /* Part of headroom was reserved to xdpf */ + hard_start_headroom = sizeof(struct xdp_frame) + xdpf->headroom; + /* build_skb need to place skb_shared_info after SKB end, and * also want to know the memory "truesize". Thus, need to * know the memory frame size backing xdp_buff. @@ -183,15 +187,15 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, * is not at a fixed memory location, with mixed length * packets, which is bad for cache-line hotness. */ - frame_size = SKB_DATA_ALIGN(xdpf->len + xdpf->headroom) + + frame_size = SKB_DATA_ALIGN(xdpf->len + hard_start_headroom) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - pkt_data_start = xdpf->data - xdpf->headroom; + pkt_data_start = xdpf->data - hard_start_headroom; skb = build_skb(pkt_data_start, frame_size); if (!skb) return NULL; - skb_reserve(skb, xdpf->headroom); + skb_reserve(skb, hard_start_headroom); __skb_put(skb, xdpf->len); if (xdpf->metasize) skb_metadata_set(skb, xdpf->metasize); @@ -205,6 +209,9 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, * - RX ring dev queue index (skb_record_rx_queue) */ + /* Allow SKB to reuse area used by xdp_frame */ + xdp_scrub_frame(xdpf); + return skb; } diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 2ada5e21dfa6..4a8f390a2b82 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -554,19 +554,6 @@ struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type typ } EXPORT_SYMBOL(bpf_prog_get_type_path); -static void bpf_evict_inode(struct inode *inode) -{ - enum bpf_type type; - - truncate_inode_pages_final(&inode->i_data); - clear_inode(inode); - - if (S_ISLNK(inode->i_mode)) - kfree(inode->i_link); - if (!bpf_inode_type(inode, &type)) - bpf_any_put(inode->i_private, type); -} - /* * Display the mount options in /proc/mounts. */ @@ -579,11 +566,28 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) return 0; } +static void bpf_destroy_inode_deferred(struct rcu_head *head) +{ + struct inode *inode = container_of(head, struct inode, i_rcu); + enum bpf_type type; + + if (S_ISLNK(inode->i_mode)) + kfree(inode->i_link); + if (!bpf_inode_type(inode, &type)) + bpf_any_put(inode->i_private, type); + free_inode_nonrcu(inode); +} + +static void bpf_destroy_inode(struct inode *inode) +{ + call_rcu(&inode->i_rcu, bpf_destroy_inode_deferred); +} + static const struct super_operations bpf_super_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, .show_options = bpf_show_options, - .evict_inode = bpf_evict_inode, + .destroy_inode = bpf_destroy_inode, }; enum { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 62f6bced3a3c..afca36f53c49 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -136,21 +136,29 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) void *bpf_map_area_alloc(size_t size, int numa_node) { - /* We definitely need __GFP_NORETRY, so OOM killer doesn't - * trigger under memory pressure as we really just want to - * fail instead. + /* We really just want to fail instead of triggering OOM killer + * under memory pressure, therefore we set __GFP_NORETRY to kmalloc, + * which is used for lower order allocation requests. + * + * It has been observed that higher order allocation requests done by + * vmalloc with __GFP_NORETRY being set might fail due to not trying + * to reclaim memory from the page cache, thus we set + * __GFP_RETRY_MAYFAIL to avoid such situations. */ - const gfp_t flags = __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO; + + const gfp_t flags = __GFP_NOWARN | __GFP_ZERO; void *area; if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { - area = kmalloc_node(size, GFP_USER | flags, numa_node); + area = kmalloc_node(size, GFP_USER | __GFP_NORETRY | flags, + numa_node); if (area != NULL) return area; } - return __vmalloc_node_flags_caller(size, numa_node, GFP_KERNEL | flags, - __builtin_return_address(0)); + return __vmalloc_node_flags_caller(size, numa_node, + GFP_KERNEL | __GFP_RETRY_MAYFAIL | + flags, __builtin_return_address(0)); } void bpf_map_area_free(void *area) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ce166a002d16..09d5d972c9ff 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -212,7 +212,7 @@ struct bpf_call_arg_meta { int access_size; s64 msize_smax_value; u64 msize_umax_value; - int ptr_id; + int ref_obj_id; int func_id; }; @@ -346,35 +346,23 @@ static bool reg_type_may_be_null(enum bpf_reg_type type) type == PTR_TO_TCP_SOCK_OR_NULL; } -static bool type_is_refcounted(enum bpf_reg_type type) -{ - return type == PTR_TO_SOCKET; -} - -static bool type_is_refcounted_or_null(enum bpf_reg_type type) -{ - return type == PTR_TO_SOCKET || type == PTR_TO_SOCKET_OR_NULL; -} - -static bool reg_is_refcounted(const struct bpf_reg_state *reg) -{ - return type_is_refcounted(reg->type); -} - static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) { return reg->type == PTR_TO_MAP_VALUE && map_value_has_spin_lock(reg->map_ptr); } -static bool reg_is_refcounted_or_null(const struct bpf_reg_state *reg) +static bool reg_type_may_be_refcounted_or_null(enum bpf_reg_type type) { - return type_is_refcounted_or_null(reg->type); + return type == PTR_TO_SOCKET || + type == PTR_TO_SOCKET_OR_NULL || + type == PTR_TO_TCP_SOCK || + type == PTR_TO_TCP_SOCK_OR_NULL; } -static bool arg_type_is_refcounted(enum bpf_arg_type type) +static bool arg_type_may_be_refcounted(enum bpf_arg_type type) { - return type == ARG_PTR_TO_SOCKET; + return type == ARG_PTR_TO_SOCK_COMMON; } /* Determine whether the function releases some resources allocated by another @@ -392,6 +380,12 @@ static bool is_acquire_function(enum bpf_func_id func_id) func_id == BPF_FUNC_sk_lookup_udp; } +static bool is_ptr_cast_function(enum bpf_func_id func_id) +{ + return func_id == BPF_FUNC_tcp_sock || + func_id == BPF_FUNC_sk_fullsock; +} + /* string representation of 'enum bpf_reg_type' */ static const char * const reg_type_str[] = { [NOT_INIT] = "?", @@ -466,6 +460,8 @@ static void print_verifier_state(struct bpf_verifier_env *env, verbose(env, ",call_%d", func(env, reg)->callsite); } else { verbose(env, "(id=%d", reg->id); + if (reg_type_may_be_refcounted_or_null(t)) + verbose(env, ",ref_obj_id=%d", reg->ref_obj_id); if (t != SCALAR_VALUE) verbose(env, ",off=%d", reg->off); if (type_is_pkt_pointer(t)) @@ -1901,8 +1897,9 @@ continue_func: } frame++; if (frame >= MAX_CALL_FRAMES) { - WARN_ONCE(1, "verifier bug. Call stack is too deep\n"); - return -EFAULT; + verbose(env, "the call stack of %d frames is too deep !\n", + frame); + return -E2BIG; } goto process_func; } @@ -2414,16 +2411,15 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, /* Any sk pointer can be ARG_PTR_TO_SOCK_COMMON */ if (!type_is_sk_pointer(type)) goto err_type; - } else if (arg_type == ARG_PTR_TO_SOCKET) { - expected_type = PTR_TO_SOCKET; - if (type != expected_type) - goto err_type; - if (meta->ptr_id || !reg->id) { - verbose(env, "verifier internal error: mismatched references meta=%d, reg=%d\n", - meta->ptr_id, reg->id); - return -EFAULT; + if (reg->ref_obj_id) { + if (meta->ref_obj_id) { + verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n", + regno, reg->ref_obj_id, + meta->ref_obj_id); + return -EFAULT; + } + meta->ref_obj_id = reg->ref_obj_id; } - meta->ptr_id = reg->id; } else if (arg_type == ARG_PTR_TO_SPIN_LOCK) { if (meta->func_id == BPF_FUNC_spin_lock) { if (process_spin_lock(env, regno, true)) @@ -2740,32 +2736,38 @@ static bool check_arg_pair_ok(const struct bpf_func_proto *fn) return true; } -static bool check_refcount_ok(const struct bpf_func_proto *fn) +static bool check_refcount_ok(const struct bpf_func_proto *fn, int func_id) { int count = 0; - if (arg_type_is_refcounted(fn->arg1_type)) + if (arg_type_may_be_refcounted(fn->arg1_type)) count++; - if (arg_type_is_refcounted(fn->arg2_type)) + if (arg_type_may_be_refcounted(fn->arg2_type)) count++; - if (arg_type_is_refcounted(fn->arg3_type)) + if (arg_type_may_be_refcounted(fn->arg3_type)) count++; - if (arg_type_is_refcounted(fn->arg4_type)) + if (arg_type_may_be_refcounted(fn->arg4_type)) count++; - if (arg_type_is_refcounted(fn->arg5_type)) + if (arg_type_may_be_refcounted(fn->arg5_type)) count++; + /* A reference acquiring function cannot acquire + * another refcounted ptr. + */ + if (is_acquire_function(func_id) && count) + return false; + /* We only support one arg being unreferenced at the moment, * which is sufficient for the helper functions we have right now. */ return count <= 1; } -static int check_func_proto(const struct bpf_func_proto *fn) +static int check_func_proto(const struct bpf_func_proto *fn, int func_id) { return check_raw_mode_ok(fn) && check_arg_pair_ok(fn) && - check_refcount_ok(fn) ? 0 : -EINVAL; + check_refcount_ok(fn, func_id) ? 0 : -EINVAL; } /* Packet data might have moved, any old PTR_TO_PACKET[_META,_END] @@ -2799,19 +2801,20 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) } static void release_reg_references(struct bpf_verifier_env *env, - struct bpf_func_state *state, int id) + struct bpf_func_state *state, + int ref_obj_id) { struct bpf_reg_state *regs = state->regs, *reg; int i; for (i = 0; i < MAX_BPF_REG; i++) - if (regs[i].id == id) + if (regs[i].ref_obj_id == ref_obj_id) mark_reg_unknown(env, regs, i); bpf_for_each_spilled_reg(i, state, reg) { if (!reg) continue; - if (reg_is_refcounted(reg) && reg->id == id) + if (reg->ref_obj_id == ref_obj_id) __mark_reg_unknown(reg); } } @@ -2820,15 +2823,20 @@ static void release_reg_references(struct bpf_verifier_env *env, * resources. Identify all copies of the same pointer and clear the reference. */ static int release_reference(struct bpf_verifier_env *env, - struct bpf_call_arg_meta *meta) + int ref_obj_id) { struct bpf_verifier_state *vstate = env->cur_state; + int err; int i; + err = release_reference_state(cur_func(env), ref_obj_id); + if (err) + return err; + for (i = 0; i <= vstate->curframe; i++) - release_reg_references(env, vstate->frame[i], meta->ptr_id); + release_reg_references(env, vstate->frame[i], ref_obj_id); - return release_reference_state(cur_func(env), meta->ptr_id); + return 0; } static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, @@ -3047,7 +3055,7 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn memset(&meta, 0, sizeof(meta)); meta.pkt_access = fn->pkt_access; - err = check_func_proto(fn); + err = check_func_proto(fn, func_id); if (err) { verbose(env, "kernel subsystem misconfigured func %s#%d\n", func_id_name(func_id), func_id); @@ -3093,7 +3101,7 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn return err; } } else if (is_release_function(func_id)) { - err = release_reference(env, &meta); + err = release_reference(env, meta.ref_obj_id); if (err) { verbose(env, "func %s#%d reference has not been acquired before\n", func_id_name(func_id), func_id); @@ -3154,8 +3162,10 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn if (id < 0) return id; - /* For release_reference() */ + /* For mark_ptr_or_null_reg() */ regs[BPF_REG_0].id = id; + /* For release_reference() */ + regs[BPF_REG_0].ref_obj_id = id; } else { /* For mark_ptr_or_null_reg() */ regs[BPF_REG_0].id = ++env->id_gen; @@ -3170,6 +3180,10 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn return -EINVAL; } + if (is_ptr_cast_function(func_id)) + /* For release_reference() */ + regs[BPF_REG_0].ref_obj_id = meta.ref_obj_id; + do_refine_retval_range(regs, fn->ret_type, func_id, &meta); err = check_map_func_compatibility(env, meta.map_ptr, func_id); @@ -3368,7 +3382,7 @@ do_sim: *dst_reg = *ptr_reg; } ret = push_stack(env, env->insn_idx + 1, env->insn_idx, true); - if (!ptr_is_dst_reg) + if (!ptr_is_dst_reg && ret) *dst_reg = tmp; return !ret ? -EFAULT : 0; } @@ -4124,15 +4138,35 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) return 0; } +static void __find_good_pkt_pointers(struct bpf_func_state *state, + struct bpf_reg_state *dst_reg, + enum bpf_reg_type type, u16 new_range) +{ + struct bpf_reg_state *reg; + int i; + + for (i = 0; i < MAX_BPF_REG; i++) { + reg = &state->regs[i]; + if (reg->type == type && reg->id == dst_reg->id) + /* keep the maximum range already checked */ + reg->range = max(reg->range, new_range); + } + + bpf_for_each_spilled_reg(i, state, reg) { + if (!reg) + continue; + if (reg->type == type && reg->id == dst_reg->id) + reg->range = max(reg->range, new_range); + } +} + static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, struct bpf_reg_state *dst_reg, enum bpf_reg_type type, bool range_right_open) { - struct bpf_func_state *state = vstate->frame[vstate->curframe]; - struct bpf_reg_state *regs = state->regs, *reg; u16 new_range; - int i, j; + int i; if (dst_reg->off < 0 || (dst_reg->off == 0 && range_right_open)) @@ -4197,20 +4231,9 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, * the range won't allow anything. * dst_reg->off is known < MAX_PACKET_OFF, therefore it fits in a u16. */ - for (i = 0; i < MAX_BPF_REG; i++) - if (regs[i].type == type && regs[i].id == dst_reg->id) - /* keep the maximum range already checked */ - regs[i].range = max(regs[i].range, new_range); - - for (j = 0; j <= vstate->curframe; j++) { - state = vstate->frame[j]; - bpf_for_each_spilled_reg(i, state, reg) { - if (!reg) - continue; - if (reg->type == type && reg->id == dst_reg->id) - reg->range = max(reg->range, new_range); - } - } + for (i = 0; i <= vstate->curframe; i++) + __find_good_pkt_pointers(vstate->frame[i], dst_reg, type, + new_range); } /* compute branch direction of the expression "if (reg opcode val) goto target;" @@ -4665,17 +4688,41 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state, } else if (reg->type == PTR_TO_TCP_SOCK_OR_NULL) { reg->type = PTR_TO_TCP_SOCK; } - if (is_null || !(reg_is_refcounted(reg) || - reg_may_point_to_spin_lock(reg))) { - /* We don't need id from this point onwards anymore, - * thus we should better reset it, so that state - * pruning has chances to take effect. + if (is_null) { + /* We don't need id and ref_obj_id from this point + * onwards anymore, thus we should better reset it, + * so that state pruning has chances to take effect. + */ + reg->id = 0; + reg->ref_obj_id = 0; + } else if (!reg_may_point_to_spin_lock(reg)) { + /* For not-NULL ptr, reg->ref_obj_id will be reset + * in release_reg_references(). + * + * reg->id is still used by spin_lock ptr. Other + * than spin_lock ptr type, reg->id can be reset. */ reg->id = 0; } } } +static void __mark_ptr_or_null_regs(struct bpf_func_state *state, u32 id, + bool is_null) +{ + struct bpf_reg_state *reg; + int i; + + for (i = 0; i < MAX_BPF_REG; i++) + mark_ptr_or_null_reg(state, &state->regs[i], id, is_null); + + bpf_for_each_spilled_reg(i, state, reg) { + if (!reg) + continue; + mark_ptr_or_null_reg(state, reg, id, is_null); + } +} + /* The logic is similar to find_good_pkt_pointers(), both could eventually * be folded together at some point. */ @@ -4683,24 +4730,20 @@ static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno, bool is_null) { struct bpf_func_state *state = vstate->frame[vstate->curframe]; - struct bpf_reg_state *reg, *regs = state->regs; + struct bpf_reg_state *regs = state->regs; + u32 ref_obj_id = regs[regno].ref_obj_id; u32 id = regs[regno].id; - int i, j; - - if (reg_is_refcounted_or_null(®s[regno]) && is_null) - release_reference_state(state, id); + int i; - for (i = 0; i < MAX_BPF_REG; i++) - mark_ptr_or_null_reg(state, ®s[i], id, is_null); + if (ref_obj_id && ref_obj_id == id && is_null) + /* regs[regno] is in the " == NULL" branch. + * No one could have freed the reference state before + * doing the NULL check. + */ + WARN_ON_ONCE(release_reference_state(state, id)); - for (j = 0; j <= vstate->curframe; j++) { - state = vstate->frame[j]; - bpf_for_each_spilled_reg(i, state, reg) { - if (!reg) - continue; - mark_ptr_or_null_reg(state, reg, id, is_null); - } - } + for (i = 0; i <= vstate->curframe; i++) + __mark_ptr_or_null_regs(vstate->frame[i], id, is_null); } static bool try_match_pkt_pointers(const struct bpf_insn *insn, @@ -6052,15 +6095,17 @@ static int propagate_liveness(struct bpf_verifier_env *env, } /* Propagate read liveness of registers... */ BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG); - /* We don't need to worry about FP liveness because it's read-only */ - for (i = 0; i < BPF_REG_FP; i++) { - if (vparent->frame[vparent->curframe]->regs[i].live & REG_LIVE_READ) - continue; - if (vstate->frame[vstate->curframe]->regs[i].live & REG_LIVE_READ) { - err = mark_reg_read(env, &vstate->frame[vstate->curframe]->regs[i], - &vparent->frame[vstate->curframe]->regs[i]); - if (err) - return err; + for (frame = 0; frame <= vstate->curframe; frame++) { + /* We don't need to worry about FP liveness, it's read-only */ + for (i = frame < vstate->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++) { + if (vparent->frame[frame]->regs[i].live & REG_LIVE_READ) + continue; + if (vstate->frame[frame]->regs[i].live & REG_LIVE_READ) { + err = mark_reg_read(env, &vstate->frame[frame]->regs[i], + &vparent->frame[frame]->regs[i]); + if (err) + return err; + } } } diff --git a/kernel/cpu.c b/kernel/cpu.c index 025f419d16f6..6754f3ecfd94 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -564,6 +564,20 @@ static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st) cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); } +static inline bool can_rollback_cpu(struct cpuhp_cpu_state *st) +{ + if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) + return true; + /* + * When CPU hotplug is disabled, then taking the CPU down is not + * possible because takedown_cpu() and the architecture and + * subsystem specific mechanisms are not available. So the CPU + * which would be completely unplugged again needs to stay around + * in the current state. + */ + return st->state <= CPUHP_BRINGUP_CPU; +} + static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { @@ -574,8 +588,10 @@ static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, st->state++; ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); if (ret) { - st->target = prev_state; - undo_cpu_up(cpu, st); + if (can_rollback_cpu(st)) { + st->target = prev_state; + undo_cpu_up(cpu, st); + } break; } } diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 45d51e8e26f6..a218e43cc382 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -706,7 +706,7 @@ static struct dma_debug_entry *dma_entry_alloc(void) #ifdef CONFIG_STACKTRACE entry->stacktrace.max_entries = DMA_DEBUG_STACKTRACE_ENTRIES; entry->stacktrace.entries = entry->st_entries; - entry->stacktrace.skip = 2; + entry->stacktrace.skip = 1; save_stack_trace(&entry->stacktrace); #endif diff --git a/kernel/events/core.c b/kernel/events/core.c index 72d06e302e99..dc7dead2d2cc 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2009,8 +2009,8 @@ event_sched_out(struct perf_event *event, event->pmu->del(event, 0); event->oncpu = -1; - if (event->pending_disable) { - event->pending_disable = 0; + if (READ_ONCE(event->pending_disable) >= 0) { + WRITE_ONCE(event->pending_disable, -1); state = PERF_EVENT_STATE_OFF; } perf_event_set_state(event, state); @@ -2198,7 +2198,8 @@ EXPORT_SYMBOL_GPL(perf_event_disable); void perf_event_disable_inatomic(struct perf_event *event) { - event->pending_disable = 1; + WRITE_ONCE(event->pending_disable, smp_processor_id()); + /* can fail, see perf_pending_event_disable() */ irq_work_queue(&event->pending); } @@ -5810,10 +5811,45 @@ void perf_event_wakeup(struct perf_event *event) } } +static void perf_pending_event_disable(struct perf_event *event) +{ + int cpu = READ_ONCE(event->pending_disable); + + if (cpu < 0) + return; + + if (cpu == smp_processor_id()) { + WRITE_ONCE(event->pending_disable, -1); + perf_event_disable_local(event); + return; + } + + /* + * CPU-A CPU-B + * + * perf_event_disable_inatomic() + * @pending_disable = CPU-A; + * irq_work_queue(); + * + * sched-out + * @pending_disable = -1; + * + * sched-in + * perf_event_disable_inatomic() + * @pending_disable = CPU-B; + * irq_work_queue(); // FAILS + * + * irq_work_run() + * perf_pending_event() + * + * But the event runs on CPU-B and wants disabling there. + */ + irq_work_queue_on(&event->pending, cpu); +} + static void perf_pending_event(struct irq_work *entry) { - struct perf_event *event = container_of(entry, - struct perf_event, pending); + struct perf_event *event = container_of(entry, struct perf_event, pending); int rctx; rctx = perf_swevent_get_recursion_context(); @@ -5822,10 +5858,7 @@ static void perf_pending_event(struct irq_work *entry) * and we won't recurse 'further'. */ - if (event->pending_disable) { - event->pending_disable = 0; - perf_event_disable_local(event); - } + perf_pending_event_disable(event); if (event->pending_wakeup) { event->pending_wakeup = 0; @@ -9044,26 +9077,29 @@ static void perf_event_addr_filters_apply(struct perf_event *event) if (task == TASK_TOMBSTONE) return; - if (!ifh->nr_file_filters) - return; - - mm = get_task_mm(event->ctx->task); - if (!mm) - goto restart; + if (ifh->nr_file_filters) { + mm = get_task_mm(event->ctx->task); + if (!mm) + goto restart; - down_read(&mm->mmap_sem); + down_read(&mm->mmap_sem); + } raw_spin_lock_irqsave(&ifh->lock, flags); list_for_each_entry(filter, &ifh->list, entry) { - event->addr_filter_ranges[count].start = 0; - event->addr_filter_ranges[count].size = 0; + if (filter->path.dentry) { + /* + * Adjust base offset if the filter is associated to a + * binary that needs to be mapped: + */ + event->addr_filter_ranges[count].start = 0; + event->addr_filter_ranges[count].size = 0; - /* - * Adjust base offset if the filter is associated to a binary - * that needs to be mapped: - */ - if (filter->path.dentry) perf_addr_filter_apply(filter, mm, &event->addr_filter_ranges[count]); + } else { + event->addr_filter_ranges[count].start = filter->offset; + event->addr_filter_ranges[count].size = filter->size; + } count++; } @@ -9071,9 +9107,11 @@ static void perf_event_addr_filters_apply(struct perf_event *event) event->addr_filters_gen++; raw_spin_unlock_irqrestore(&ifh->lock, flags); - up_read(&mm->mmap_sem); + if (ifh->nr_file_filters) { + up_read(&mm->mmap_sem); - mmput(mm); + mmput(mm); + } restart: perf_event_stop(event, 1); @@ -10236,6 +10274,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, init_waitqueue_head(&event->waitq); + event->pending_disable = -1; init_irq_work(&event->pending, perf_pending_event); mutex_init(&event->mmap_mutex); diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index a4047321d7d8..5eedb49a65ea 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -392,7 +392,7 @@ void *perf_aux_output_begin(struct perf_output_handle *handle, * store that will be enabled on successful return */ if (!handle->size) { /* A, matches D */ - event->pending_disable = 1; + event->pending_disable = smp_processor_id(); perf_output_wakeup(handle); local_set(&rb->aux_nest, 0); goto err_put; @@ -455,24 +455,21 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) rb->aux_head += size; } - if (size || handle->aux_flags) { - /* - * Only send RECORD_AUX if we have something useful to communicate - * - * Note: the OVERWRITE records by themselves are not considered - * useful, as they don't communicate any *new* information, - * aside from the short-lived offset, that becomes history at - * the next event sched-in and therefore isn't useful. - * The userspace that needs to copy out AUX data in overwrite - * mode should know to use user_page::aux_head for the actual - * offset. So, from now on we don't output AUX records that - * have *only* OVERWRITE flag set. - */ - - if (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE) - perf_event_aux_event(handle->event, aux_head, size, - handle->aux_flags); - } + /* + * Only send RECORD_AUX if we have something useful to communicate + * + * Note: the OVERWRITE records by themselves are not considered + * useful, as they don't communicate any *new* information, + * aside from the short-lived offset, that becomes history at + * the next event sched-in and therefore isn't useful. + * The userspace that needs to copy out AUX data in overwrite + * mode should know to use user_page::aux_head for the actual + * offset. So, from now on we don't output AUX records that + * have *only* OVERWRITE flag set. + */ + if (size || (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE)) + perf_event_aux_event(handle->event, aux_head, size, + handle->aux_flags); rb->user_page->aux_head = rb->aux_head; if (rb_need_aux_wakeup(rb)) @@ -480,7 +477,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) if (wakeup) { if (handle->aux_flags & PERF_AUX_FLAG_TRUNCATED) - handle->event->pending_disable = 1; + handle->event->pending_disable = smp_processor_id(); perf_output_wakeup(handle); } diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 3faef4a77f71..51128bea3846 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -1449,6 +1449,10 @@ int irq_chip_set_vcpu_affinity_parent(struct irq_data *data, void *vcpu_info) int irq_chip_set_wake_parent(struct irq_data *data, unsigned int on) { data = data->parent_data; + + if (data->chip->flags & IRQCHIP_SKIP_SET_WAKE) + return 0; + if (data->chip->irq_set_wake) return data->chip->irq_set_wake(data, on); diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 13539e12cd80..9f8a709337cf 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -558,6 +558,7 @@ int __init early_irq_init(void) alloc_masks(&desc[i], node); raw_spin_lock_init(&desc[i].lock); lockdep_set_class(&desc[i].lock, &irq_desc_lock_class); + mutex_init(&desc[i].request_mutex); desc_set_defaults(i, &desc[i], node, NULL, NULL); } return arch_early_irq_init(); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index c83e54727131..b1ea30a5540e 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -709,7 +709,6 @@ static void unoptimize_kprobe(struct kprobe *p, bool force) static int reuse_unused_kprobe(struct kprobe *ap) { struct optimized_kprobe *op; - int ret; /* * Unused kprobe MUST be on the way of delayed unoptimizing (means @@ -720,9 +719,8 @@ static int reuse_unused_kprobe(struct kprobe *ap) /* Enable the probe again */ ap->flags &= ~KPROBE_FLAG_DISABLED; /* Optimize it again (remove from op->list) */ - ret = kprobe_optready(ap); - if (ret) - return ret; + if (!kprobe_optready(ap)) + return -EINVAL; optimize_kprobe(ap); return 0; diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 34cdcbedda49..e221be724fe8 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -4689,8 +4689,8 @@ static void free_zapped_rcu(struct rcu_head *ch) return; raw_local_irq_save(flags); - if (!graph_lock()) - goto out_irq; + arch_spin_lock(&lockdep_lock); + current->lockdep_recursion = 1; /* closed head */ pf = delayed_free.pf + (delayed_free.index ^ 1); @@ -4702,8 +4702,8 @@ static void free_zapped_rcu(struct rcu_head *ch) */ call_rcu_zapped(delayed_free.pf + delayed_free.index); - graph_unlock(); -out_irq: + current->lockdep_recursion = 0; + arch_spin_unlock(&lockdep_lock); raw_local_irq_restore(flags); } @@ -4744,21 +4744,17 @@ static void lockdep_free_key_range_reg(void *start, unsigned long size) { struct pending_free *pf; unsigned long flags; - int locked; init_data_structures_once(); raw_local_irq_save(flags); - locked = graph_lock(); - if (!locked) - goto out_irq; - + arch_spin_lock(&lockdep_lock); + current->lockdep_recursion = 1; pf = get_pending_free(); __lockdep_free_key_range(pf, start, size); call_rcu_zapped(pf); - - graph_unlock(); -out_irq: + current->lockdep_recursion = 0; + arch_spin_unlock(&lockdep_lock); raw_local_irq_restore(flags); /* diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 771e93f9c43f..6f357f4fc859 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -29,6 +29,7 @@ #include <linux/hw_breakpoint.h> #include <linux/cn_proc.h> #include <linux/compat.h> +#include <linux/sched/signal.h> /* * Access another process' address space via ptrace. @@ -924,18 +925,26 @@ int ptrace_request(struct task_struct *child, long request, ret = ptrace_setsiginfo(child, &siginfo); break; - case PTRACE_GETSIGMASK: + case PTRACE_GETSIGMASK: { + sigset_t *mask; + if (addr != sizeof(sigset_t)) { ret = -EINVAL; break; } - if (copy_to_user(datavp, &child->blocked, sizeof(sigset_t))) + if (test_tsk_restore_sigmask(child)) + mask = &child->saved_sigmask; + else + mask = &child->blocked; + + if (copy_to_user(datavp, mask, sizeof(sigset_t))) ret = -EFAULT; else ret = 0; break; + } case PTRACE_SETSIGMASK: { sigset_t new_set; @@ -961,6 +970,8 @@ int ptrace_request(struct task_struct *child, long request, child->blocked = new_set; spin_unlock_irq(&child->sighand->siglock); + clear_tsk_restore_sigmask(child); + ret = 0; break; } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 6a73e41a2016..43901fa3f269 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -252,7 +252,6 @@ static void task_non_contending(struct task_struct *p) if (dl_entity_is_special(dl_se)) return; - WARN_ON(hrtimer_active(&dl_se->inactive_timer)); WARN_ON(dl_se->dl_non_contending); zerolag_time = dl_se->deadline - @@ -269,7 +268,7 @@ static void task_non_contending(struct task_struct *p) * If the "0-lag time" already passed, decrease the active * utilization now, instead of starting a timer */ - if (zerolag_time < 0) { + if ((zerolag_time < 0) || hrtimer_active(&dl_se->inactive_timer)) { if (dl_task(p)) sub_running_bw(dl_se, dl_rq); if (!dl_task(p) || p->state == TASK_DEAD) { diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index fdab7eb6f351..35f3ea375084 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2007,6 +2007,10 @@ static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period) if (p->last_task_numa_placement) { delta = runtime - p->last_sum_exec_runtime; *period = now - p->last_task_numa_placement; + + /* Avoid time going backwards, prevent potential divide error: */ + if (unlikely((s64)*period < 0)) + *period = 0; } else { delta = p->se.avg.load_sum; *period = LOAD_AVG_MAX; @@ -4885,6 +4889,8 @@ static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer) return HRTIMER_NORESTART; } +extern const u64 max_cfs_quota_period; + static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) { struct cfs_bandwidth *cfs_b = @@ -4892,6 +4898,7 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) unsigned long flags; int overrun; int idle = 0; + int count = 0; raw_spin_lock_irqsave(&cfs_b->lock, flags); for (;;) { @@ -4899,6 +4906,28 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) if (!overrun) break; + if (++count > 3) { + u64 new, old = ktime_to_ns(cfs_b->period); + + new = (old * 147) / 128; /* ~115% */ + new = min(new, max_cfs_quota_period); + + cfs_b->period = ns_to_ktime(new); + + /* since max is 1s, this is limited to 1e9^2, which fits in u64 */ + cfs_b->quota *= new; + cfs_b->quota = div64_u64(cfs_b->quota, old); + + pr_warn_ratelimited( + "cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us %lld, cfs_quota_us = %lld)\n", + smp_processor_id(), + div_u64(new, NSEC_PER_USEC), + div_u64(cfs_b->quota, NSEC_PER_USEC)); + + /* reset count so we don't come right back in here */ + count = 0; + } + idle = do_sched_cfs_period_timer(cfs_b, overrun, flags); } if (idle) @@ -7784,10 +7813,10 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq) if (cfs_rq->last_h_load_update == now) return; - cfs_rq->h_load_next = NULL; + WRITE_ONCE(cfs_rq->h_load_next, NULL); for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); - cfs_rq->h_load_next = se; + WRITE_ONCE(cfs_rq->h_load_next, se); if (cfs_rq->last_h_load_update == now) break; } @@ -7797,7 +7826,7 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq) cfs_rq->last_h_load_update = now; } - while ((se = cfs_rq->h_load_next) != NULL) { + while ((se = READ_ONCE(cfs_rq->h_load_next)) != NULL) { load = cfs_rq->h_load; load = div64_ul(load * se->avg.load_avg, cfs_rq_load_avg(cfs_rq) + 1); diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 54a0347ca812..3582eeb59893 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -149,7 +149,7 @@ static void populate_seccomp_data(struct seccomp_data *sd) sd->nr = syscall_get_nr(task, regs); sd->arch = syscall_get_arch(); - syscall_get_arguments(task, regs, 0, 6, args); + syscall_get_arguments(task, regs, args); sd->args[0] = args[0]; sd->args[1] = args[1]; sd->args[2] = args[2]; @@ -502,7 +502,10 @@ out: * * Caller must be holding current->sighand->siglock lock. * - * Returns 0 on success, -ve on error. + * Returns 0 on success, -ve on error, or + * - in TSYNC mode: the pid of a thread which was either not in the correct + * seccomp mode or did not have an ancestral seccomp filter + * - in NEW_LISTENER mode: the fd of the new listener */ static long seccomp_attach_filter(unsigned int flags, struct seccomp_filter *filter) @@ -1258,6 +1261,16 @@ static long seccomp_set_mode_filter(unsigned int flags, if (flags & ~SECCOMP_FILTER_FLAG_MASK) return -EINVAL; + /* + * In the successful case, NEW_LISTENER returns the new listener fd. + * But in the failure case, TSYNC returns the thread that died. If you + * combine these two flags, there's no way to tell whether something + * succeeded or failed. So, let's disallow this combination. + */ + if ((flags & SECCOMP_FILTER_FLAG_TSYNC) && + (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER)) + return -EINVAL; + /* Prepare the new filter before holding any locks. */ prepared = seccomp_prepare_user_filter(filter); if (IS_ERR(prepared)) @@ -1304,7 +1317,7 @@ out: mutex_unlock(¤t->signal->cred_guard_mutex); out_put_fd: if (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) { - if (ret < 0) { + if (ret) { listener_f->private_data = NULL; fput(listener_f); put_unused_fd(listener); diff --git a/kernel/signal.c b/kernel/signal.c index b7953934aa99..227ba170298e 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3581,7 +3581,7 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, if (flags) return -EINVAL; - f = fdget_raw(pidfd); + f = fdget(pidfd); if (!f.file) return -EBADF; @@ -3605,16 +3605,11 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, if (unlikely(sig != kinfo.si_signo)) goto err; + /* Only allow sending arbitrary signals to yourself. */ + ret = -EPERM; if ((task_pid(current) != pid) && - (kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL)) { - /* Only allow sending arbitrary signals to yourself. */ - ret = -EPERM; - if (kinfo.si_code != SI_USER) - goto err; - - /* Turn this into a regular kill signal. */ - prepare_kill_siginfo(sig, &kinfo); - } + (kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL)) + goto err; } else { prepare_kill_siginfo(sig, &kinfo); } diff --git a/kernel/sysctl.c b/kernel/sysctl.c index e5da394d1ca3..c9ec050bcf46 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -128,6 +128,7 @@ static int zero; static int __maybe_unused one = 1; static int __maybe_unused two = 2; static int __maybe_unused four = 4; +static unsigned long zero_ul; static unsigned long one_ul = 1; static unsigned long long_max = LONG_MAX; static int one_hundred = 100; @@ -1750,7 +1751,7 @@ static struct ctl_table fs_table[] = { .maxlen = sizeof(files_stat.max_files), .mode = 0644, .proc_handler = proc_doulongvec_minmax, - .extra1 = &zero, + .extra1 = &zero_ul, .extra2 = &long_max, }, { diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 2c97e8c2d29f..0519a8805aab 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -594,7 +594,7 @@ static ktime_t alarm_timer_remaining(struct k_itimer *timr, ktime_t now) { struct alarm *alarm = &timr->it.alarm.alarmtimer; - return ktime_sub(now, alarm->node.expires); + return ktime_sub(alarm->node.expires, now); } /** diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index 094b82ca95e5..930113b9799a 100644 --- a/kernel/time/sched_clock.c +++ b/kernel/time/sched_clock.c @@ -272,7 +272,7 @@ static u64 notrace suspended_sched_clock_read(void) return cd.read_data[seq & 1].epoch_cyc; } -static int sched_clock_suspend(void) +int sched_clock_suspend(void) { struct clock_read_data *rd = &cd.read_data[0]; @@ -283,7 +283,7 @@ static int sched_clock_suspend(void) return 0; } -static void sched_clock_resume(void) +void sched_clock_resume(void) { struct clock_read_data *rd = &cd.read_data[0]; diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 529143b4c8d2..df401463a191 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -487,6 +487,7 @@ void tick_freeze(void) trace_suspend_resume(TPS("timekeeping_freeze"), smp_processor_id(), true); system_state = SYSTEM_SUSPEND; + sched_clock_suspend(); timekeeping_suspend(); } else { tick_suspend_local(); @@ -510,6 +511,7 @@ void tick_unfreeze(void) if (tick_freeze_depth == num_online_cpus()) { timekeeping_resume(); + sched_clock_resume(); system_state = SYSTEM_RUNNING; trace_suspend_resume(TPS("timekeeping_freeze"), smp_processor_id(), false); diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h index 7a9b4eb7a1d5..141ab3ab0354 100644 --- a/kernel/time/timekeeping.h +++ b/kernel/time/timekeeping.h @@ -14,6 +14,13 @@ extern u64 timekeeping_max_deferment(void); extern void timekeeping_warp_clock(void); extern int timekeeping_suspend(void); extern void timekeeping_resume(void); +#ifdef CONFIG_GENERIC_SCHED_CLOCK +extern int sched_clock_suspend(void); +extern void sched_clock_resume(void); +#else +static inline int sched_clock_suspend(void) { return 0; } +static inline void sched_clock_resume(void) { } +#endif extern void do_timer(unsigned long ticks); extern void update_wall_time(void); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index fa79323331b2..b920358dd8f7 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -33,6 +33,7 @@ #include <linux/list.h> #include <linux/hash.h> #include <linux/rcupdate.h> +#include <linux/kprobes.h> #include <trace/events/sched.h> @@ -1992,7 +1993,7 @@ static void print_bug_type(void) * modifying the code. @failed should be one of either: * EFAULT - if the problem happens on reading the @ip address * EINVAL - if what is read at @ip is not what was expected - * EPERM - if the problem happens on writting to the @ip address + * EPERM - if the problem happens on writing to the @ip address */ void ftrace_bug(int failed, struct dyn_ftrace *rec) { @@ -2391,7 +2392,7 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable) return ftrace_modify_call(rec, ftrace_old_addr, ftrace_addr); } - return -1; /* unknow ftrace bug */ + return -1; /* unknown ftrace bug */ } void __weak ftrace_replace_code(int mod_flags) @@ -3004,7 +3005,7 @@ ftrace_allocate_pages(unsigned long num_to_init) int cnt; if (!num_to_init) - return 0; + return NULL; start_pg = pg = kzalloc(sizeof(*pg), GFP_KERNEL); if (!pg) @@ -4755,7 +4756,7 @@ static int ftrace_set_addr(struct ftrace_ops *ops, unsigned long ip, int remove, int reset, int enable) { - return ftrace_set_hash(ops, 0, 0, ip, remove, reset, enable); + return ftrace_set_hash(ops, NULL, 0, ip, remove, reset, enable); } /** @@ -5463,7 +5464,7 @@ void ftrace_create_filter_files(struct ftrace_ops *ops, /* * The name "destroy_filter_files" is really a misnomer. Although - * in the future, it may actualy delete the files, but this is + * in the future, it may actually delete the files, but this is * really intended to make sure the ops passed in are disabled * and that when this function returns, the caller is free to * free the ops. @@ -5786,7 +5787,7 @@ void ftrace_module_enable(struct module *mod) /* * If the tracing is enabled, go ahead and enable the record. * - * The reason not to enable the record immediatelly is the + * The reason not to enable the record immediately is the * inherent check of ftrace_make_nop/ftrace_make_call for * correct previous instructions. Making first the NOP * conversion puts the module to the correct state, thus @@ -6246,7 +6247,7 @@ void ftrace_reset_array_ops(struct trace_array *tr) tr->ops->func = ftrace_stub; } -static inline void +static nokprobe_inline void __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ignored, struct pt_regs *regs) { @@ -6306,11 +6307,13 @@ static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, { __ftrace_ops_list_func(ip, parent_ip, NULL, regs); } +NOKPROBE_SYMBOL(ftrace_ops_list_func); #else static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip) { __ftrace_ops_list_func(ip, parent_ip, NULL, NULL); } +NOKPROBE_SYMBOL(ftrace_ops_no_ops); #endif /* @@ -6337,6 +6340,7 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip, preempt_enable_notrace(); trace_clear_recursion(bit); } +NOKPROBE_SYMBOL(ftrace_ops_assist_func); /** * ftrace_ops_get_func - get the function a trampoline should call diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 41b6f96e5366..4ee8d8aa3d0f 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -762,7 +762,7 @@ u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu) preempt_disable_notrace(); time = rb_time_stamp(buffer); - preempt_enable_no_resched_notrace(); + preempt_enable_notrace(); return time; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 21153e64bf1c..ca1ee656d6d8 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -496,8 +496,10 @@ int trace_pid_write(struct trace_pid_list *filtered_pids, * not modified. */ pid_list = kmalloc(sizeof(*pid_list), GFP_KERNEL); - if (!pid_list) + if (!pid_list) { + trace_parser_put(&parser); return -ENOMEM; + } pid_list->pid_max = READ_ONCE(pid_max); @@ -507,6 +509,7 @@ int trace_pid_write(struct trace_pid_list *filtered_pids, pid_list->pids = vzalloc((pid_list->pid_max + 7) >> 3); if (!pid_list->pids) { + trace_parser_put(&parser); kfree(pid_list); return -ENOMEM; } @@ -7025,35 +7028,43 @@ struct buffer_ref { struct ring_buffer *buffer; void *page; int cpu; - int ref; + refcount_t refcount; }; +static void buffer_ref_release(struct buffer_ref *ref) +{ + if (!refcount_dec_and_test(&ref->refcount)) + return; + ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page); + kfree(ref); +} + static void buffer_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct buffer_ref *ref = (struct buffer_ref *)buf->private; - if (--ref->ref) - return; - - ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page); - kfree(ref); + buffer_ref_release(ref); buf->private = 0; } -static void buffer_pipe_buf_get(struct pipe_inode_info *pipe, +static bool buffer_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct buffer_ref *ref = (struct buffer_ref *)buf->private; - ref->ref++; + if (refcount_read(&ref->refcount) > INT_MAX/2) + return false; + + refcount_inc(&ref->refcount); + return true; } /* Pipe buffer operations for a buffer. */ static const struct pipe_buf_operations buffer_pipe_buf_ops = { .confirm = generic_pipe_buf_confirm, .release = buffer_pipe_buf_release, - .steal = generic_pipe_buf_steal, + .steal = generic_pipe_buf_nosteal, .get = buffer_pipe_buf_get, }; @@ -7066,11 +7077,7 @@ static void buffer_spd_release(struct splice_pipe_desc *spd, unsigned int i) struct buffer_ref *ref = (struct buffer_ref *)spd->partial[i].private; - if (--ref->ref) - return; - - ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page); - kfree(ref); + buffer_ref_release(ref); spd->partial[i].private = 0; } @@ -7125,7 +7132,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, break; } - ref->ref = 1; + refcount_set(&ref->refcount, 1); ref->buffer = iter->trace_buffer->buffer; ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file); if (IS_ERR(ref->page)) { diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c index dd1f43588d70..fa100ed3b4de 100644 --- a/kernel/trace/trace_dynevent.c +++ b/kernel/trace/trace_dynevent.c @@ -74,7 +74,7 @@ int dyn_event_release(int argc, char **argv, struct dyn_event_operations *type) static int create_dyn_event(int argc, char **argv) { struct dyn_event_operations *ops; - int ret; + int ret = -ENODEV; if (argv[0][0] == '-' || argv[0][0] == '!') return dyn_event_release(argc, argv, NULL); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index ca46339f3009..795aa2038377 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -3713,7 +3713,6 @@ static void track_data_destroy(struct hist_trigger_data *hist_data, struct trace_event_file *file = hist_data->event_file; destroy_hist_field(data->track_data.track_var, 0); - destroy_hist_field(data->track_data.var_ref, 0); if (data->action == ACTION_SNAPSHOT) { struct track_data *track_data; diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index f93a56d2db27..fa8fbff736d6 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -314,6 +314,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) struct ring_buffer_event *event; struct ring_buffer *buffer; unsigned long irq_flags; + unsigned long args[6]; int pc; int syscall_nr; int size; @@ -347,7 +348,8 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) entry = ring_buffer_event_data(event); entry->nr = syscall_nr; - syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args); + syscall_get_arguments(current, regs, args); + memcpy(entry->args, args, sizeof(unsigned long) * sys_data->nb_args); event_trigger_unlock_commit(trace_file, buffer, event, entry, irq_flags, pc); @@ -583,6 +585,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) struct syscall_metadata *sys_data; struct syscall_trace_enter *rec; struct hlist_head *head; + unsigned long args[6]; bool valid_prog_array; int syscall_nr; int rctx; @@ -613,8 +616,8 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) return; rec->nr = syscall_nr; - syscall_get_arguments(current, regs, 0, sys_data->nb_args, - (unsigned long *)&rec->args); + syscall_get_arguments(current, regs, args); + memcpy(&rec->args, args, sizeof(unsigned long) * sys_data->nb_args); if ((valid_prog_array && !perf_call_bpf_enter(sys_data->enter_event, regs, sys_data, rec)) || diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 403c9bd90413..6a5787233113 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -554,13 +554,15 @@ static void softlockup_start_all(void) int lockup_detector_online_cpu(unsigned int cpu) { - watchdog_enable(cpu); + if (cpumask_test_cpu(cpu, &watchdog_allowed_mask)) + watchdog_enable(cpu); return 0; } int lockup_detector_offline_cpu(unsigned int cpu) { - watchdog_disable(cpu); + if (cpumask_test_cpu(cpu, &watchdog_allowed_mask)) + watchdog_disable(cpu); return 0; } diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 71381168dede..247bf0b1582c 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -135,7 +135,8 @@ static void watchdog_overflow_callback(struct perf_event *event, if (__this_cpu_read(hard_watchdog_warn) == true) return; - pr_emerg("Watchdog detected hard LOCKUP on cpu %d", this_cpu); + pr_emerg("Watchdog detected hard LOCKUP on cpu %d\n", + this_cpu); print_modules(); print_irqtrace_events(current); if (regs) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 0d9e81779e37..d5a4a4036d2f 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -753,9 +753,9 @@ endmenu # "Memory Debugging" config ARCH_HAS_KCOV bool help - KCOV does not have any arch-specific code, but currently it is enabled - only for x86_64. KCOV requires testing on other archs, and most likely - disabling of instrumentation for some early boot code. + An architecture should select this when it can successfully + build and run with CONFIG_KCOV. This typically requires + disabling instrumentation for some early boot code. config CC_HAS_SANCOV_TRACE_PC def_bool $(cc-option,-fsanitize-coverage=trace-pc) @@ -1929,6 +1929,7 @@ config TEST_KMOD depends on m depends on BLOCK && (64BIT || LBDAF) # for XFS, BTRFS depends on NETDEVICES && NET_CORE && INET # for TUN + depends on BLOCK select TEST_LKM select XFS_FS select TUN diff --git a/lib/iov_iter.c b/lib/iov_iter.c index ea36dc355da1..b396d328a764 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1528,6 +1528,7 @@ EXPORT_SYMBOL(csum_and_copy_to_iter); size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp, struct iov_iter *i) { +#ifdef CONFIG_CRYPTO struct ahash_request *hash = hashp; struct scatterlist sg; size_t copied; @@ -1537,6 +1538,9 @@ size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp, ahash_request_set_crypt(hash, &sg, NULL, copied); crypto_ahash_update(hash); return copied; +#else + return 0; +#endif } EXPORT_SYMBOL(hash_and_copy_to_iter); diff --git a/lib/lzo/lzo1x_compress.c b/lib/lzo/lzo1x_compress.c index 4525fb094844..a8ede77afe0d 100644 --- a/lib/lzo/lzo1x_compress.c +++ b/lib/lzo/lzo1x_compress.c @@ -291,13 +291,14 @@ int lzogeneric1x_1_compress(const unsigned char *in, size_t in_len, { const unsigned char *ip = in; unsigned char *op = out; + unsigned char *data_start; size_t l = in_len; size_t t = 0; signed char state_offset = -2; unsigned int m4_max_offset; - // LZO v0 will never write 17 as first byte, - // so this is used to version the bitstream + // LZO v0 will never write 17 as first byte (except for zero-length + // input), so this is used to version the bitstream if (bitstream_version > 0) { *op++ = 17; *op++ = bitstream_version; @@ -306,6 +307,8 @@ int lzogeneric1x_1_compress(const unsigned char *in, size_t in_len, m4_max_offset = M4_MAX_OFFSET_V0; } + data_start = op; + while (l > 20) { size_t ll = l <= (m4_max_offset + 1) ? l : (m4_max_offset + 1); uintptr_t ll_end = (uintptr_t) ip + ll; @@ -324,7 +327,7 @@ int lzogeneric1x_1_compress(const unsigned char *in, size_t in_len, if (t > 0) { const unsigned char *ii = in + in_len - t; - if (op == out && t <= 238) { + if (op == data_start && t <= 238) { *op++ = (17 + t); } else if (t <= 3) { op[state_offset] |= t; diff --git a/lib/lzo/lzo1x_decompress_safe.c b/lib/lzo/lzo1x_decompress_safe.c index 6d2600ea3b55..9e07e9ef1aad 100644 --- a/lib/lzo/lzo1x_decompress_safe.c +++ b/lib/lzo/lzo1x_decompress_safe.c @@ -54,11 +54,9 @@ int lzo1x_decompress_safe(const unsigned char *in, size_t in_len, if (unlikely(in_len < 3)) goto input_overrun; - if (likely(*ip == 17)) { + if (likely(in_len >= 5) && likely(*ip == 17)) { bitstream_version = ip[1]; ip += 2; - if (unlikely(in_len < 5)) - goto input_overrun; } else { bitstream_version = 0; } diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 0a105d4af166..97f59abc3e92 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -416,8 +416,12 @@ static void rht_deferred_worker(struct work_struct *work) else if (tbl->nest) err = rhashtable_rehash_alloc(ht, tbl, tbl->size); - if (!err) - err = rhashtable_rehash_table(ht); + if (!err || err == -EEXIST) { + int nerr; + + nerr = rhashtable_rehash_table(ht); + err = err ?: nerr; + } mutex_unlock(&ht->mutex); diff --git a/lib/sbitmap.c b/lib/sbitmap.c index 5b382c1244ed..155fe38756ec 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -591,6 +591,17 @@ EXPORT_SYMBOL_GPL(sbitmap_queue_wake_up); void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr, unsigned int cpu) { + /* + * Once the clear bit is set, the bit may be allocated out. + * + * Orders READ/WRITE on the asssociated instance(such as request + * of blk_mq) by this bit for avoiding race with re-allocation, + * and its pair is the memory barrier implied in __sbitmap_get_word. + * + * One invariant is that the clear bit has to be zero when the bit + * is in use. + */ + smp_mb__before_atomic(); sbitmap_deferred_clear_bit(&sbq->sb, nr); /* diff --git a/lib/string.c b/lib/string.c index 38e4ca08e757..3ab861c1a857 100644 --- a/lib/string.c +++ b/lib/string.c @@ -866,6 +866,26 @@ __visible int memcmp(const void *cs, const void *ct, size_t count) EXPORT_SYMBOL(memcmp); #endif +#ifndef __HAVE_ARCH_BCMP +/** + * bcmp - returns 0 if and only if the buffers have identical contents. + * @a: pointer to first buffer. + * @b: pointer to second buffer. + * @len: size of buffers. + * + * The sign or magnitude of a non-zero return value has no particular + * meaning, and architectures may implement their own more efficient bcmp(). So + * while this particular implementation is a simple (tail) call to memcmp, do + * not rely on anything but whether the return value is zero or non-zero. + */ +#undef bcmp +int bcmp(const void *a, const void *b, size_t len) +{ + return memcmp(a, b, len); +} +EXPORT_SYMBOL(bcmp); +#endif + #ifndef __HAVE_ARCH_MEMSCAN /** * memscan - Find a character in an area of memory. diff --git a/lib/syscall.c b/lib/syscall.c index 1a7077f20eae..fb328e7ccb08 100644 --- a/lib/syscall.c +++ b/lib/syscall.c @@ -5,16 +5,14 @@ #include <linux/export.h> #include <asm/syscall.h> -static int collect_syscall(struct task_struct *target, long *callno, - unsigned long args[6], unsigned int maxargs, - unsigned long *sp, unsigned long *pc) +static int collect_syscall(struct task_struct *target, struct syscall_info *info) { struct pt_regs *regs; if (!try_get_task_stack(target)) { /* Task has no stack, so the task isn't in a syscall. */ - *sp = *pc = 0; - *callno = -1; + memset(info, 0, sizeof(*info)); + info->data.nr = -1; return 0; } @@ -24,12 +22,13 @@ static int collect_syscall(struct task_struct *target, long *callno, return -EAGAIN; } - *sp = user_stack_pointer(regs); - *pc = instruction_pointer(regs); + info->sp = user_stack_pointer(regs); + info->data.instruction_pointer = instruction_pointer(regs); - *callno = syscall_get_nr(target, regs); - if (*callno != -1L && maxargs > 0) - syscall_get_arguments(target, regs, 0, maxargs, args); + info->data.nr = syscall_get_nr(target, regs); + if (info->data.nr != -1L) + syscall_get_arguments(target, regs, + (unsigned long *)&info->data.args[0]); put_task_stack(target); return 0; @@ -38,41 +37,35 @@ static int collect_syscall(struct task_struct *target, long *callno, /** * task_current_syscall - Discover what a blocked task is doing. * @target: thread to examine - * @callno: filled with system call number or -1 - * @args: filled with @maxargs system call arguments - * @maxargs: number of elements in @args to fill - * @sp: filled with user stack pointer - * @pc: filled with user PC + * @info: structure with the following fields: + * .sp - filled with user stack pointer + * .data.nr - filled with system call number or -1 + * .data.args - filled with @maxargs system call arguments + * .data.instruction_pointer - filled with user PC * - * If @target is blocked in a system call, returns zero with *@callno - * set to the the call's number and @args filled in with its arguments. - * Registers not used for system call arguments may not be available and - * it is not kosher to use &struct user_regset calls while the system + * If @target is blocked in a system call, returns zero with @info.data.nr + * set to the the call's number and @info.data.args filled in with its + * arguments. Registers not used for system call arguments may not be available + * and it is not kosher to use &struct user_regset calls while the system * call is still in progress. Note we may get this result if @target * has finished its system call but not yet returned to user mode, such * as when it's stopped for signal handling or syscall exit tracing. * * If @target is blocked in the kernel during a fault or exception, - * returns zero with *@callno set to -1 and does not fill in @args. - * If so, it's now safe to examine @target using &struct user_regset - * get() calls as long as we're sure @target won't return to user mode. + * returns zero with *@info.data.nr set to -1 and does not fill in + * @info.data.args. If so, it's now safe to examine @target using + * &struct user_regset get() calls as long as we're sure @target won't return + * to user mode. * * Returns -%EAGAIN if @target does not remain blocked. - * - * Returns -%EINVAL if @maxargs is too large (maximum is six). */ -int task_current_syscall(struct task_struct *target, long *callno, - unsigned long args[6], unsigned int maxargs, - unsigned long *sp, unsigned long *pc) +int task_current_syscall(struct task_struct *target, struct syscall_info *info) { long state; unsigned long ncsw; - if (unlikely(maxargs > 6)) - return -EINVAL; - if (target == current) - return collect_syscall(target, callno, args, maxargs, sp, pc); + return collect_syscall(target, info); state = target->state; if (unlikely(!state)) @@ -80,7 +73,7 @@ int task_current_syscall(struct task_struct *target, long *callno, ncsw = wait_task_inactive(target, state); if (unlikely(!ncsw) || - unlikely(collect_syscall(target, callno, args, maxargs, sp, pc)) || + unlikely(collect_syscall(target, info)) || unlikely(wait_task_inactive(target, state) != ncsw)) return -EAGAIN; diff --git a/lib/test_vmalloc.c b/lib/test_vmalloc.c index 83cdcaa82bf6..f832b095afba 100644 --- a/lib/test_vmalloc.c +++ b/lib/test_vmalloc.c @@ -383,14 +383,14 @@ static void shuffle_array(int *arr, int n) static int test_func(void *private) { struct test_driver *t = private; - cpumask_t newmask = CPU_MASK_NONE; int random_array[ARRAY_SIZE(test_case_array)]; int index, i, j, ret; ktime_t kt; u64 delta; - cpumask_set_cpu(t->cpu, &newmask); - set_cpus_allowed_ptr(current, &newmask); + ret = set_cpus_allowed_ptr(current, cpumask_of(t->cpu)); + if (ret < 0) + pr_err("Failed to set affinity to %d CPU\n", t->cpu); for (i = 0; i < ARRAY_SIZE(test_case_array); i++) random_array[i] = i; diff --git a/mm/compaction.c b/mm/compaction.c index f171a83707ce..3319e0872d01 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -242,6 +242,7 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source, bool check_target) { struct page *page = pfn_to_online_page(pfn); + struct page *block_page; struct page *end_page; unsigned long block_pfn; @@ -267,20 +268,26 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source, get_pageblock_migratetype(page) != MIGRATE_MOVABLE) return false; + /* Ensure the start of the pageblock or zone is online and valid */ + block_pfn = pageblock_start_pfn(pfn); + block_page = pfn_to_online_page(max(block_pfn, zone->zone_start_pfn)); + if (block_page) { + page = block_page; + pfn = block_pfn; + } + + /* Ensure the end of the pageblock or zone is online and valid */ + block_pfn += pageblock_nr_pages; + block_pfn = min(block_pfn, zone_end_pfn(zone) - 1); + end_page = pfn_to_online_page(block_pfn); + if (!end_page) + return false; + /* * Only clear the hint if a sample indicates there is either a * free page or an LRU page in the block. One or other condition * is necessary for the block to be a migration source/target. */ - block_pfn = pageblock_start_pfn(pfn); - pfn = max(block_pfn, zone->zone_start_pfn); - page = pfn_to_page(pfn); - if (zone != page_zone(page)) - return false; - pfn = block_pfn + pageblock_nr_pages; - pfn = min(pfn, zone_end_pfn(zone)); - end_page = pfn_to_page(pfn); - do { if (pfn_valid_within(pfn)) { if (check_source && PageLRU(page)) { @@ -309,7 +316,7 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source, static void __reset_isolation_suitable(struct zone *zone) { unsigned long migrate_pfn = zone->zone_start_pfn; - unsigned long free_pfn = zone_end_pfn(zone); + unsigned long free_pfn = zone_end_pfn(zone) - 1; unsigned long reset_migrate = free_pfn; unsigned long reset_free = migrate_pfn; bool source_set = false; @@ -1363,7 +1370,7 @@ fast_isolate_freepages(struct compact_control *cc) count_compact_events(COMPACTISOLATED, nr_isolated); } else { /* If isolation fails, abort the search */ - order = -1; + order = cc->search_order + 1; page = NULL; } } diff --git a/mm/debug.c b/mm/debug.c index c0b31b6c3877..eee9c221280c 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -79,7 +79,7 @@ void __dump_page(struct page *page, const char *reason) pr_warn("ksm "); else if (mapping) { pr_warn("%ps ", mapping->a_ops); - if (mapping->host->i_dentry.first) { + if (mapping->host && mapping->host->i_dentry.first) { struct dentry *dentry; dentry = container_of(mapping->host->i_dentry.first, struct dentry, d_u.d_alias); pr_warn("name:\"%pd\" ", dentry); @@ -168,7 +168,7 @@ void dump_mm(const struct mm_struct *mm) mm_pgtables_bytes(mm), mm->map_count, mm->hiwater_rss, mm->hiwater_vm, mm->total_vm, mm->locked_vm, - atomic64_read(&mm->pinned_vm), + (u64)atomic64_read(&mm->pinned_vm), mm->data_vm, mm->exec_vm, mm->stack_vm, mm->start_code, mm->end_code, mm->start_data, mm->end_data, mm->start_brk, mm->brk, mm->start_stack, @@ -160,8 +160,12 @@ retry: goto retry; } - if (flags & FOLL_GET) - get_page(page); + if (flags & FOLL_GET) { + if (unlikely(!try_get_page(page))) { + page = ERR_PTR(-ENOMEM); + goto out; + } + } if (flags & FOLL_TOUCH) { if ((flags & FOLL_WRITE) && !pte_dirty(pte) && !PageDirty(page)) @@ -298,7 +302,10 @@ retry_locked: if (pmd_trans_unstable(pmd)) ret = -EBUSY; } else { - get_page(page); + if (unlikely(!try_get_page(page))) { + spin_unlock(ptl); + return ERR_PTR(-ENOMEM); + } spin_unlock(ptl); lock_page(page); ret = split_huge_page(page); @@ -500,7 +507,10 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address, if (is_device_public_page(*page)) goto unmap; } - get_page(*page); + if (unlikely(!try_get_page(*page))) { + ret = -ENOMEM; + goto unmap; + } out: ret = 0; unmap: @@ -1545,6 +1555,20 @@ static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages) } } +/* + * Return the compund head page with ref appropriately incremented, + * or NULL if that failed. + */ +static inline struct page *try_get_compound_head(struct page *page, int refs) +{ + struct page *head = compound_head(page); + if (WARN_ON_ONCE(page_ref_count(head) < 0)) + return NULL; + if (unlikely(!page_cache_add_speculative(head, refs))) + return NULL; + return head; +} + #ifdef CONFIG_ARCH_HAS_PTE_SPECIAL static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) @@ -1579,9 +1603,9 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = pte_page(pte); - head = compound_head(page); - if (!page_cache_get_speculative(head)) + head = try_get_compound_head(page, 1); + if (!head) goto pte_unmap; if (unlikely(pte_val(pte) != pte_val(*ptep))) { @@ -1720,8 +1744,8 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, refs++; } while (addr += PAGE_SIZE, addr != end); - head = compound_head(pmd_page(orig)); - if (!page_cache_add_speculative(head, refs)) { + head = try_get_compound_head(pmd_page(orig), refs); + if (!head) { *nr -= refs; return 0; } @@ -1758,8 +1782,8 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, refs++; } while (addr += PAGE_SIZE, addr != end); - head = compound_head(pud_page(orig)); - if (!page_cache_add_speculative(head, refs)) { + head = try_get_compound_head(pud_page(orig), refs); + if (!head) { *nr -= refs; return 0; } @@ -1795,8 +1819,8 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, refs++; } while (addr += PAGE_SIZE, addr != end); - head = compound_head(pgd_page(orig)); - if (!page_cache_add_speculative(head, refs)) { + head = try_get_compound_head(pgd_page(orig), refs); + if (!head) { *nr -= refs; return 0; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 404acdcd0455..165ea46bf149 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -755,6 +755,21 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, spinlock_t *ptl; ptl = pmd_lock(mm, pmd); + if (!pmd_none(*pmd)) { + if (write) { + if (pmd_pfn(*pmd) != pfn_t_to_pfn(pfn)) { + WARN_ON_ONCE(!is_huge_zero_pmd(*pmd)); + goto out_unlock; + } + entry = pmd_mkyoung(*pmd); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); + if (pmdp_set_access_flags(vma, addr, pmd, entry, 1)) + update_mmu_cache_pmd(vma, addr, pmd); + } + + goto out_unlock; + } + entry = pmd_mkhuge(pfn_t_pmd(pfn, prot)); if (pfn_t_devmap(pfn)) entry = pmd_mkdevmap(entry); @@ -766,11 +781,16 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, if (pgtable) { pgtable_trans_huge_deposit(mm, pmd, pgtable); mm_inc_nr_ptes(mm); + pgtable = NULL; } set_pmd_at(mm, addr, pmd, entry); update_mmu_cache_pmd(vma, addr, pmd); + +out_unlock: spin_unlock(ptl); + if (pgtable) + pte_free(mm, pgtable); } vm_fault_t vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, @@ -821,6 +841,20 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr, spinlock_t *ptl; ptl = pud_lock(mm, pud); + if (!pud_none(*pud)) { + if (write) { + if (pud_pfn(*pud) != pfn_t_to_pfn(pfn)) { + WARN_ON_ONCE(!is_huge_zero_pud(*pud)); + goto out_unlock; + } + entry = pud_mkyoung(*pud); + entry = maybe_pud_mkwrite(pud_mkdirty(entry), vma); + if (pudp_set_access_flags(vma, addr, pud, entry, 1)) + update_mmu_cache_pud(vma, addr, pud); + } + goto out_unlock; + } + entry = pud_mkhuge(pfn_t_pud(pfn, prot)); if (pfn_t_devmap(pfn)) entry = pud_mkdevmap(entry); @@ -830,6 +864,8 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr, } set_pud_at(mm, addr, pud, entry); update_mmu_cache_pud(vma, addr, pud); + +out_unlock: spin_unlock(ptl); } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 97b1e0290c66..6cdc7b2d9100 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4299,6 +4299,19 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT; page = pte_page(huge_ptep_get(pte)); + + /* + * Instead of doing 'try_get_page()' below in the same_page + * loop, just check the count once here. + */ + if (unlikely(page_count(page) <= 0)) { + if (pages) { + spin_unlock(ptl); + remainder = 0; + err = -ENOMEM; + break; + } + } same_page: if (pages) { pages[i] = mem_map_offset(page, pfn_offset); diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 3e0c11f7d7a1..3ce956efa0cb 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -163,7 +163,10 @@ static inline u8 random_tag(void) #endif #ifndef arch_kasan_set_tag -#define arch_kasan_set_tag(addr, tag) ((void *)(addr)) +static inline const void *arch_kasan_set_tag(const void *addr, u8 tag) +{ + return addr; +} #endif #ifndef arch_kasan_reset_tag #define arch_kasan_reset_tag(addr) ((void *)(addr)) diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 707fa5579f66..2e435b8142e5 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1401,6 +1401,7 @@ static void scan_block(void *_start, void *_end, /* * Scan a large memory block in MAX_SCAN_SIZE chunks to reduce the latency. */ +#ifdef CONFIG_SMP static void scan_large_block(void *start, void *end) { void *next; @@ -1412,6 +1413,7 @@ static void scan_large_block(void *start, void *end) cond_resched(); } } +#endif /* * Scan a memory block corresponding to a kmemleak_object. A condition is @@ -1529,11 +1531,6 @@ static void kmemleak_scan(void) } rcu_read_unlock(); - /* data/bss scanning */ - scan_large_block(_sdata, _edata); - scan_large_block(__bss_start, __bss_stop); - scan_large_block(__start_ro_after_init, __end_ro_after_init); - #ifdef CONFIG_SMP /* per-cpu sections scanning */ for_each_possible_cpu(i) @@ -2071,6 +2068,17 @@ void __init kmemleak_init(void) } local_irq_restore(flags); + /* register the data/bss sections */ + create_object((unsigned long)_sdata, _edata - _sdata, + KMEMLEAK_GREY, GFP_ATOMIC); + create_object((unsigned long)__bss_start, __bss_stop - __bss_start, + KMEMLEAK_GREY, GFP_ATOMIC); + /* only register .data..ro_after_init if not within .data */ + if (__start_ro_after_init < _sdata || __end_ro_after_init > _edata) + create_object((unsigned long)__start_ro_after_init, + __end_ro_after_init - __start_ro_after_init, + KMEMLEAK_GREY, GFP_ATOMIC); + /* * This is the point where tracking allocations is safe. Automatic * scanning is started during the late initcall. Add the early logged diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 532e0e2a4817..81a0d3914ec9 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3882,6 +3882,22 @@ struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb) return &memcg->cgwb_domain; } +/* + * idx can be of type enum memcg_stat_item or node_stat_item. + * Keep in sync with memcg_exact_page(). + */ +static unsigned long memcg_exact_page_state(struct mem_cgroup *memcg, int idx) +{ + long x = atomic_long_read(&memcg->stat[idx]); + int cpu; + + for_each_online_cpu(cpu) + x += per_cpu_ptr(memcg->stat_cpu, cpu)->count[idx]; + if (x < 0) + x = 0; + return x; +} + /** * mem_cgroup_wb_stats - retrieve writeback related stats from its memcg * @wb: bdi_writeback in question @@ -3907,10 +3923,10 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css); struct mem_cgroup *parent; - *pdirty = memcg_page_state(memcg, NR_FILE_DIRTY); + *pdirty = memcg_exact_page_state(memcg, NR_FILE_DIRTY); /* this should eventually include NR_UNSTABLE_NFS */ - *pwriteback = memcg_page_state(memcg, NR_WRITEBACK); + *pwriteback = memcg_exact_page_state(memcg, NR_WRITEBACK); *pfilepages = mem_cgroup_nr_lru_pages(memcg, (1 << LRU_INACTIVE_FILE) | (1 << LRU_ACTIVE_FILE)); *pheadroom = PAGE_COUNTER_MAX; diff --git a/mm/memory.c b/mm/memory.c index 47fe250307c7..ab650c21bccd 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1549,10 +1549,12 @@ static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr, WARN_ON_ONCE(!is_zero_pfn(pte_pfn(*pte))); goto out_unlock; } - entry = *pte; - goto out_mkwrite; - } else - goto out_unlock; + entry = pte_mkyoung(*pte); + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + if (ptep_set_access_flags(vma, addr, pte, entry, 1)) + update_mmu_cache(vma, addr, pte); + } + goto out_unlock; } /* Ok, finally just insert the thing.. */ @@ -1561,7 +1563,6 @@ static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr, else entry = pte_mkspecial(pfn_t_pte(pfn, prot)); -out_mkwrite: if (mkwrite) { entry = pte_mkyoung(entry); entry = maybe_mkwrite(pte_mkdirty(entry), vma); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index f767582af4f8..b236069ff0d8 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -874,6 +874,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ */ mem = find_memory_block(__pfn_to_section(pfn)); nid = mem->nid; + put_device(&mem->dev); /* associate pfn range with the zone */ zone = move_pfn_range(online_type, nid, pfn, nr_pages); @@ -1576,7 +1577,7 @@ static int __ref __offline_pages(unsigned long start_pfn, { unsigned long pfn, nr_pages; long offlined_pages; - int ret, node; + int ret, node, nr_isolate_pageblock; unsigned long flags; unsigned long valid_start, valid_end; struct zone *zone; @@ -1602,10 +1603,11 @@ static int __ref __offline_pages(unsigned long start_pfn, ret = start_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE, SKIP_HWPOISON | REPORT_FAILURE); - if (ret) { + if (ret < 0) { reason = "failure to isolate range"; goto failed_removal; } + nr_isolate_pageblock = ret; arg.start_pfn = start_pfn; arg.nr_pages = nr_pages; @@ -1657,8 +1659,16 @@ static int __ref __offline_pages(unsigned long start_pfn, /* Ok, all of our target is isolated. We cannot do rollback at this point. */ offline_isolated_pages(start_pfn, end_pfn); - /* reset pagetype flags and makes migrate type to be MOVABLE */ - undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE); + + /* + * Onlining will reset pagetype flags and makes migrate type + * MOVABLE, so just need to decrease the number of isolated + * pageblocks zone counter here. + */ + spin_lock_irqsave(&zone->lock, flags); + zone->nr_isolate_pageblock -= nr_isolate_pageblock; + spin_unlock_irqrestore(&zone->lock, flags); + /* removal success */ adjust_managed_page_count(pfn_to_page(start_pfn), -offlined_pages); zone->present_pages -= offlined_pages; @@ -1690,12 +1700,12 @@ static int __ref __offline_pages(unsigned long start_pfn, failed_removal_isolated: undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE); + memory_notify(MEM_CANCEL_OFFLINE, &arg); failed_removal: pr_debug("memory offlining [mem %#010llx-%#010llx] failed due to %s\n", (unsigned long long) start_pfn << PAGE_SHIFT, ((unsigned long long) end_pfn << PAGE_SHIFT) - 1, reason); - memory_notify(MEM_CANCEL_OFFLINE, &arg); /* pushback to free area */ mem_hotplug_done(); return ret; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index af171ccb56a2..2219e747df49 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -428,6 +428,13 @@ static inline bool queue_pages_required(struct page *page, return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT); } +/* + * queue_pages_pmd() has three possible return values: + * 1 - pages are placed on the right node or queued successfully. + * 0 - THP was split. + * -EIO - is migration entry or MPOL_MF_STRICT was specified and an existing + * page was already on a node that does not follow the policy. + */ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, unsigned long end, struct mm_walk *walk) { @@ -437,7 +444,7 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, unsigned long flags; if (unlikely(is_pmd_migration_entry(*pmd))) { - ret = 1; + ret = -EIO; goto unlock; } page = pmd_page(*pmd); @@ -454,8 +461,15 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, ret = 1; flags = qp->flags; /* go to thp migration */ - if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) + if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { + if (!vma_migratable(walk->vma)) { + ret = -EIO; + goto unlock; + } + migrate_page_add(page, qp->pagelist, flags); + } else + ret = -EIO; unlock: spin_unlock(ptl); out: @@ -480,8 +494,10 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { ret = queue_pages_pmd(pmd, ptl, addr, end, walk); - if (ret) + if (ret > 0) return 0; + else if (ret < 0) + return ret; } if (pmd_trans_unstable(pmd)) @@ -502,11 +518,16 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, continue; if (!queue_pages_required(page, qp)) continue; - migrate_page_add(page, qp->pagelist, flags); + if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { + if (!vma_migratable(vma)) + break; + migrate_page_add(page, qp->pagelist, flags); + } else + break; } pte_unmap_unlock(pte - 1, ptl); cond_resched(); - return 0; + return addr != end ? -EIO : 0; } static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask, @@ -576,7 +597,12 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, unsigned long endvma = vma->vm_end; unsigned long flags = qp->flags; - if (!vma_migratable(vma)) + /* + * Need check MPOL_MF_STRICT to return -EIO if possible + * regardless of vma_migratable + */ + if (!vma_migratable(vma) && + !(flags & MPOL_MF_STRICT)) return 1; if (endvma > end) @@ -603,7 +629,7 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, } /* queue pages from current vma */ - if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) + if (flags & MPOL_MF_VALID) return 0; return 1; } diff --git a/mm/migrate.c b/mm/migrate.c index ac6f4939bb59..663a5449367a 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -248,10 +248,8 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma, pte = swp_entry_to_pte(entry); } else if (is_device_public_page(new)) { pte = pte_mkdevmap(pte); - flush_dcache_page(new); } - } else - flush_dcache_page(new); + } #ifdef CONFIG_HUGETLB_PAGE if (PageHuge(new)) { @@ -995,6 +993,13 @@ static int move_to_new_page(struct page *newpage, struct page *page, */ if (!PageMappingFlags(page)) page->mapping = NULL; + + if (unlikely(is_zone_device_page(newpage))) { + if (is_device_public_page(newpage)) + flush_dcache_page(newpage); + } else + flush_dcache_page(newpage); + } out: return rc; diff --git a/mm/mmap.c b/mm/mmap.c index 41eb48d9b527..bd7b9f293b39 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -45,6 +45,7 @@ #include <linux/moduleparam.h> #include <linux/pkeys.h> #include <linux/oom.h> +#include <linux/sched/mm.h> #include <linux/uaccess.h> #include <asm/cacheflush.h> @@ -2525,7 +2526,8 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr) vma = find_vma_prev(mm, addr, &prev); if (vma && (vma->vm_start <= addr)) return vma; - if (!prev || expand_stack(prev, addr)) + /* don't alter vm_end if the coredump is running */ + if (!prev || !mmget_still_valid(mm) || expand_stack(prev, addr)) return NULL; if (prev->vm_flags & VM_LOCKED) populate_vma_page_range(prev, addr, prev->vm_end, NULL); @@ -2551,6 +2553,9 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr) return vma; if (!(vma->vm_flags & VM_GROWSDOWN)) return NULL; + /* don't alter vm_start if the coredump is running */ + if (!mmget_still_valid(mm)) + return NULL; start = vma->vm_start; if (expand_stack(vma, addr)) return NULL; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 03fcf73d47da..c02cff1ed56e 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -266,7 +266,20 @@ compound_page_dtor * const compound_page_dtors[] = { int min_free_kbytes = 1024; int user_min_free_kbytes = -1; +#ifdef CONFIG_DISCONTIGMEM +/* + * DiscontigMem defines memory ranges as separate pg_data_t even if the ranges + * are not on separate NUMA nodes. Functionally this works but with + * watermark_boost_factor, it can reclaim prematurely as the ranges can be + * quite small. By default, do not boost watermarks on discontigmem as in + * many cases very high-order allocations like THP are likely to be + * unsupported and the premature reclaim offsets the advantage of long-term + * fragmentation avoidance. + */ +int watermark_boost_factor __read_mostly; +#else int watermark_boost_factor __read_mostly = 15000; +#endif int watermark_scale_factor = 10; static unsigned long nr_kernel_pages __initdata; @@ -3419,8 +3432,11 @@ alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask) alloc_flags |= ALLOC_KSWAPD; #ifdef CONFIG_ZONE_DMA32 + if (!zone) + return alloc_flags; + if (zone_idx(zone) != ZONE_NORMAL) - goto out; + return alloc_flags; /* * If ZONE_DMA32 exists, assume it is the one after ZONE_NORMAL and @@ -3429,9 +3445,9 @@ alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask) */ BUILD_BUG_ON(ZONE_NORMAL - ZONE_DMA32 != 1); if (nr_online_nodes > 1 && !populated_zone(--zone)) - goto out; + return alloc_flags; -out: + alloc_flags |= ALLOC_NOFRAGMENT; #endif /* CONFIG_ZONE_DMA32 */ return alloc_flags; } @@ -3773,11 +3789,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, memalloc_noreclaim_restore(noreclaim_flag); psi_memstall_leave(&pflags); - if (*compact_result <= COMPACT_INACTIVE) { - WARN_ON_ONCE(page); - return NULL; - } - /* * At least in one zone compaction wasn't deferred or skipped, so let's * count a compaction stall @@ -8005,7 +8016,10 @@ void *__init alloc_large_system_hash(const char *tablename, bool has_unmovable_pages(struct zone *zone, struct page *page, int count, int migratetype, int flags) { - unsigned long pfn, iter, found; + unsigned long found; + unsigned long iter = 0; + unsigned long pfn = page_to_pfn(page); + const char *reason = "unmovable page"; /* * TODO we could make this much more efficient by not checking every @@ -8015,17 +8029,20 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, * can still lead to having bootmem allocations in zone_movable. */ - /* - * CMA allocations (alloc_contig_range) really need to mark isolate - * CMA pageblocks even when they are not movable in fact so consider - * them movable here. - */ - if (is_migrate_cma(migratetype) && - is_migrate_cma(get_pageblock_migratetype(page))) - return false; + if (is_migrate_cma_page(page)) { + /* + * CMA allocations (alloc_contig_range) really need to mark + * isolate CMA pageblocks even when they are not movable in fact + * so consider them movable here. + */ + if (is_migrate_cma(migratetype)) + return false; - pfn = page_to_pfn(page); - for (found = 0, iter = 0; iter < pageblock_nr_pages; iter++) { + reason = "CMA page"; + goto unmovable; + } + + for (found = 0; iter < pageblock_nr_pages; iter++) { unsigned long check = pfn + iter; if (!pfn_valid_within(check)) @@ -8105,7 +8122,7 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, unmovable: WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE); if (flags & REPORT_FAILURE) - dump_page(pfn_to_page(pfn+iter), "unmovable page"); + dump_page(pfn_to_page(pfn + iter), reason); return true; } @@ -8233,7 +8250,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, ret = start_isolate_page_range(pfn_max_align_down(start), pfn_max_align_up(end), migratetype, 0); - if (ret) + if (ret < 0) return ret; /* diff --git a/mm/page_isolation.c b/mm/page_isolation.c index ce323e56b34d..019280712e1b 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -59,7 +59,8 @@ static int set_migratetype_isolate(struct page *page, int migratetype, int isol_ * FIXME: Now, memory hotplug doesn't call shrink_slab() by itself. * We just check MOVABLE pages. */ - if (!has_unmovable_pages(zone, page, arg.pages_found, migratetype, flags)) + if (!has_unmovable_pages(zone, page, arg.pages_found, migratetype, + isol_flags)) ret = 0; /* @@ -160,27 +161,36 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages) return NULL; } -/* - * start_isolate_page_range() -- make page-allocation-type of range of pages - * to be MIGRATE_ISOLATE. - * @start_pfn: The lower PFN of the range to be isolated. - * @end_pfn: The upper PFN of the range to be isolated. - * @migratetype: migrate type to set in error recovery. +/** + * start_isolate_page_range() - make page-allocation-type of range of pages to + * be MIGRATE_ISOLATE. + * @start_pfn: The lower PFN of the range to be isolated. + * @end_pfn: The upper PFN of the range to be isolated. + * start_pfn/end_pfn must be aligned to pageblock_order. + * @migratetype: Migrate type to set in error recovery. + * @flags: The following flags are allowed (they can be combined in + * a bit mask) + * SKIP_HWPOISON - ignore hwpoison pages + * REPORT_FAILURE - report details about the failure to + * isolate the range * * Making page-allocation-type to be MIGRATE_ISOLATE means free pages in * the range will never be allocated. Any free pages and pages freed in the - * future will not be allocated again. - * - * start_pfn/end_pfn must be aligned to pageblock_order. - * Return 0 on success and -EBUSY if any part of range cannot be isolated. + * future will not be allocated again. If specified range includes migrate types + * other than MOVABLE or CMA, this will fail with -EBUSY. For isolating all + * pages in the range finally, the caller have to free all pages in the range. + * test_page_isolated() can be used for test it. * * There is no high level synchronization mechanism that prevents two threads - * from trying to isolate overlapping ranges. If this happens, one thread + * from trying to isolate overlapping ranges. If this happens, one thread * will notice pageblocks in the overlapping range already set to isolate. * This happens in set_migratetype_isolate, and set_migratetype_isolate - * returns an error. We then clean up by restoring the migration type on - * pageblocks we may have modified and return -EBUSY to caller. This + * returns an error. We then clean up by restoring the migration type on + * pageblocks we may have modified and return -EBUSY to caller. This * prevents two threads from simultaneously working on overlapping ranges. + * + * Return: the number of isolated pageblocks on success and -EBUSY if any part + * of range cannot be isolated. */ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, unsigned migratetype, int flags) @@ -188,6 +198,7 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, unsigned long pfn; unsigned long undo_pfn; struct page *page; + int nr_isolate_pageblock = 0; BUG_ON(!IS_ALIGNED(start_pfn, pageblock_nr_pages)); BUG_ON(!IS_ALIGNED(end_pfn, pageblock_nr_pages)); @@ -196,13 +207,15 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, pfn < end_pfn; pfn += pageblock_nr_pages) { page = __first_valid_page(pfn, pageblock_nr_pages); - if (page && - set_migratetype_isolate(page, migratetype, flags)) { - undo_pfn = pfn; - goto undo; + if (page) { + if (set_migratetype_isolate(page, migratetype, flags)) { + undo_pfn = pfn; + goto undo; + } + nr_isolate_pageblock++; } } - return 0; + return nr_isolate_pageblock; undo: for (pfn = start_pfn; pfn < undo_pfn; diff --git a/mm/percpu.c b/mm/percpu.c index 2e6fc8d552c9..68dd2e7e73b5 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -2567,8 +2567,8 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, ai->groups[group].base_offset = areas[group] - base; } - pr_info("Embedded %zu pages/cpu @%p s%zu r%zu d%zu u%zu\n", - PFN_DOWN(size_sum), base, ai->static_size, ai->reserved_size, + pr_info("Embedded %zu pages/cpu s%zu r%zu d%zu u%zu\n", + PFN_DOWN(size_sum), ai->static_size, ai->reserved_size, ai->dyn_size, ai->unit_size); rc = pcpu_setup_first_chunk(ai, base); @@ -2692,8 +2692,8 @@ int __init pcpu_page_first_chunk(size_t reserved_size, } /* we're ready, commit */ - pr_info("%d %s pages/cpu @%p s%zu r%zu d%zu\n", - unit_pages, psize_str, vm.addr, ai->static_size, + pr_info("%d %s pages/cpu s%zu r%zu d%zu\n", + unit_pages, psize_str, ai->static_size, ai->reserved_size, ai->dyn_size); rc = pcpu_setup_first_chunk(ai, vm.addr); diff --git a/mm/shmem.c b/mm/shmem.c index b3db3779a30a..2275a0ff7c30 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1081,9 +1081,14 @@ static void shmem_evict_inode(struct inode *inode) } spin_unlock(&sbinfo->shrinklist_lock); } - if (!list_empty(&info->swaplist)) { + while (!list_empty(&info->swaplist)) { + /* Wait while shmem_unuse() is scanning this inode... */ + wait_var_event(&info->stop_eviction, + !atomic_read(&info->stop_eviction)); mutex_lock(&shmem_swaplist_mutex); - list_del_init(&info->swaplist); + /* ...but beware of the race if we peeked too early */ + if (!atomic_read(&info->stop_eviction)) + list_del_init(&info->swaplist); mutex_unlock(&shmem_swaplist_mutex); } } @@ -1099,10 +1104,11 @@ extern struct swap_info_struct *swap_info[]; static int shmem_find_swap_entries(struct address_space *mapping, pgoff_t start, unsigned int nr_entries, struct page **entries, pgoff_t *indices, - bool frontswap) + unsigned int type, bool frontswap) { XA_STATE(xas, &mapping->i_pages, start); struct page *page; + swp_entry_t entry; unsigned int ret = 0; if (!nr_entries) @@ -1116,13 +1122,12 @@ static int shmem_find_swap_entries(struct address_space *mapping, if (!xa_is_value(page)) continue; - if (frontswap) { - swp_entry_t entry = radix_to_swp_entry(page); - - if (!frontswap_test(swap_info[swp_type(entry)], - swp_offset(entry))) - continue; - } + entry = radix_to_swp_entry(page); + if (swp_type(entry) != type) + continue; + if (frontswap && + !frontswap_test(swap_info[type], swp_offset(entry))) + continue; indices[ret] = xas.xa_index; entries[ret] = page; @@ -1194,7 +1199,7 @@ static int shmem_unuse_inode(struct inode *inode, unsigned int type, pvec.nr = shmem_find_swap_entries(mapping, start, nr_entries, pvec.pages, indices, - frontswap); + type, frontswap); if (pvec.nr == 0) { ret = 0; break; @@ -1227,36 +1232,27 @@ int shmem_unuse(unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { struct shmem_inode_info *info, *next; - struct inode *inode; - struct inode *prev_inode = NULL; int error = 0; if (list_empty(&shmem_swaplist)) return 0; mutex_lock(&shmem_swaplist_mutex); - - /* - * The extra refcount on the inode is necessary to safely dereference - * p->next after re-acquiring the lock. New shmem inodes with swap - * get added to the end of the list and we will scan them all. - */ list_for_each_entry_safe(info, next, &shmem_swaplist, swaplist) { if (!info->swapped) { list_del_init(&info->swaplist); continue; } - - inode = igrab(&info->vfs_inode); - if (!inode) - continue; - + /* + * Drop the swaplist mutex while searching the inode for swap; + * but before doing so, make sure shmem_evict_inode() will not + * remove placeholder inode from swaplist, nor let it be freed + * (igrab() would protect from unlink, but not from unmount). + */ + atomic_inc(&info->stop_eviction); mutex_unlock(&shmem_swaplist_mutex); - if (prev_inode) - iput(prev_inode); - prev_inode = inode; - error = shmem_unuse_inode(inode, type, frontswap, + error = shmem_unuse_inode(&info->vfs_inode, type, frontswap, fs_pages_to_unuse); cond_resched(); @@ -1264,14 +1260,13 @@ int shmem_unuse(unsigned int type, bool frontswap, next = list_next_entry(info, swaplist); if (!info->swapped) list_del_init(&info->swaplist); + if (atomic_dec_and_test(&info->stop_eviction)) + wake_up_var(&info->stop_eviction); if (error) break; } mutex_unlock(&shmem_swaplist_mutex); - if (prev_inode) - iput(prev_inode); - return error; } @@ -2238,6 +2233,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode info = SHMEM_I(inode); memset(info, 0, (char *)inode - (char *)info); spin_lock_init(&info->lock); + atomic_set(&info->stop_eviction, 0); info->seals = F_SEAL_SEAL; info->flags = flags & VM_NORESERVE; INIT_LIST_HEAD(&info->shrinklist); diff --git a/mm/slab.c b/mm/slab.c index 28652e4218e0..9142ee992493 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -2115,6 +2115,8 @@ done: cachep->allocflags = __GFP_COMP; if (flags & SLAB_CACHE_DMA) cachep->allocflags |= GFP_DMA; + if (flags & SLAB_CACHE_DMA32) + cachep->allocflags |= GFP_DMA32; if (flags & SLAB_RECLAIM_ACCOUNT) cachep->allocflags |= __GFP_RECLAIMABLE; cachep->size = size; @@ -2372,7 +2374,6 @@ static void *alloc_slabmgmt(struct kmem_cache *cachep, /* Slab management obj is off-slab. */ freelist = kmem_cache_alloc_node(cachep->freelist_cache, local_flags, nodeid); - freelist = kasan_reset_tag(freelist); if (!freelist) return NULL; } else { @@ -4306,7 +4307,8 @@ static void show_symbol(struct seq_file *m, unsigned long address) static int leaks_show(struct seq_file *m, void *p) { - struct kmem_cache *cachep = list_entry(p, struct kmem_cache, list); + struct kmem_cache *cachep = list_entry(p, struct kmem_cache, + root_caches_node); struct page *page; struct kmem_cache_node *n; const char *name; diff --git a/mm/slab.h b/mm/slab.h index e5e6658eeacc..43ac818b8592 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -127,7 +127,8 @@ static inline slab_flags_t kmem_cache_flags(unsigned int object_size, /* Legal flag mask for kmem_cache_create(), for various configurations */ -#define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | SLAB_PANIC | \ +#define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | \ + SLAB_CACHE_DMA32 | SLAB_PANIC | \ SLAB_TYPESAFE_BY_RCU | SLAB_DEBUG_OBJECTS ) #if defined(CONFIG_DEBUG_SLAB) diff --git a/mm/slab_common.c b/mm/slab_common.c index 03eeb8b7b4b1..58251ba63e4a 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -53,7 +53,7 @@ static DECLARE_WORK(slab_caches_to_rcu_destroy_work, SLAB_FAILSLAB | SLAB_KASAN) #define SLAB_MERGE_SAME (SLAB_RECLAIM_ACCOUNT | SLAB_CACHE_DMA | \ - SLAB_ACCOUNT) + SLAB_CACHE_DMA32 | SLAB_ACCOUNT) /* * Merge control. If this is set then no merging of slab caches will occur. diff --git a/mm/slub.c b/mm/slub.c index 1b08fbcb7e61..d30ede89f4a6 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3589,6 +3589,9 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) if (s->flags & SLAB_CACHE_DMA) s->allocflags |= GFP_DMA; + if (s->flags & SLAB_CACHE_DMA32) + s->allocflags |= GFP_DMA32; + if (s->flags & SLAB_RECLAIM_ACCOUNT) s->allocflags |= __GFP_RECLAIMABLE; @@ -5679,6 +5682,8 @@ static char *create_unique_id(struct kmem_cache *s) */ if (s->flags & SLAB_CACHE_DMA) *p++ = 'd'; + if (s->flags & SLAB_CACHE_DMA32) + *p++ = 'D'; if (s->flags & SLAB_RECLAIM_ACCOUNT) *p++ = 'a'; if (s->flags & SLAB_CONSISTENCY_CHECKS) diff --git a/mm/sparse.c b/mm/sparse.c index 69904aa6165b..56e057c432f9 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -567,7 +567,7 @@ void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn) } #ifdef CONFIG_MEMORY_HOTREMOVE -/* Mark all memory sections within the pfn range as online */ +/* Mark all memory sections within the pfn range as offline */ void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn) { unsigned long pfn; diff --git a/mm/swapfile.c b/mm/swapfile.c index 2b8d9c3fbb47..cf63b5f01adf 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2023,7 +2023,6 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si, * If the boolean frontswap is true, only unuse pages_to_unuse pages; * pages_to_unuse==0 means all pages; ignored if frontswap is false */ -#define SWAP_UNUSE_MAX_TRIES 3 int try_to_unuse(unsigned int type, bool frontswap, unsigned long pages_to_unuse) { @@ -2035,7 +2034,6 @@ int try_to_unuse(unsigned int type, bool frontswap, struct page *page; swp_entry_t entry; unsigned int i; - int retries = 0; if (!si->inuse_pages) return 0; @@ -2053,11 +2051,9 @@ retry: spin_lock(&mmlist_lock); p = &init_mm.mmlist; - while ((p = p->next) != &init_mm.mmlist) { - if (signal_pending(current)) { - retval = -EINTR; - break; - } + while (si->inuse_pages && + !signal_pending(current) && + (p = p->next) != &init_mm.mmlist) { mm = list_entry(p, struct mm_struct, mmlist); if (!mmget_not_zero(mm)) @@ -2084,7 +2080,9 @@ retry: mmput(prev_mm); i = 0; - while ((i = find_next_to_unuse(si, i, frontswap)) != 0) { + while (si->inuse_pages && + !signal_pending(current) && + (i = find_next_to_unuse(si, i, frontswap)) != 0) { entry = swp_entry(type, i); page = find_get_page(swap_address_space(entry), i); @@ -2117,14 +2115,18 @@ retry: * If yes, we would need to do retry the unuse logic again. * Under global memory pressure, swap entries can be reinserted back * into process space after the mmlist loop above passes over them. - * Its not worth continuosuly retrying to unuse the swap in this case. - * So we try SWAP_UNUSE_MAX_TRIES times. + * + * Limit the number of retries? No: when mmget_not_zero() above fails, + * that mm is likely to be freeing swap from exit_mmap(), which proceeds + * at its own independent pace; and even shmem_writepage() could have + * been preempted after get_swap_page(), temporarily hiding that swap. + * It's easy and robust (though cpu-intensive) just to keep retrying. */ - if (++retries >= SWAP_UNUSE_MAX_TRIES) - retval = -EBUSY; - else if (si->inuse_pages) - goto retry; - + if (si->inuse_pages) { + if (!signal_pending(current)) + goto retry; + retval = -EINTR; + } out: return (retval == FRONTSWAP_PAGES_UNUSED) ? 0 : retval; } diff --git a/mm/util.c b/mm/util.c index d559bde497a9..43a2984bccaa 100644 --- a/mm/util.c +++ b/mm/util.c @@ -204,7 +204,7 @@ EXPORT_SYMBOL(vmemdup_user); * @s: The string to duplicate * @n: Maximum number of bytes to copy, including the trailing NUL. * - * Return: newly allocated copy of @s or %NULL in case of error + * Return: newly allocated copy of @s or an ERR_PTR() in case of error */ char *strndup_user(const char __user *s, long n) { diff --git a/mm/vmscan.c b/mm/vmscan.c index a5ad0b35ab8e..a815f73ee4d5 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2176,7 +2176,6 @@ static void shrink_active_list(unsigned long nr_to_scan, * 10TB 320 32GB */ static bool inactive_list_is_low(struct lruvec *lruvec, bool file, - struct mem_cgroup *memcg, struct scan_control *sc, bool actual_reclaim) { enum lru_list active_lru = file * LRU_FILE + LRU_ACTIVE; @@ -2197,16 +2196,12 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file, inactive = lruvec_lru_size(lruvec, inactive_lru, sc->reclaim_idx); active = lruvec_lru_size(lruvec, active_lru, sc->reclaim_idx); - if (memcg) - refaults = memcg_page_state(memcg, WORKINGSET_ACTIVATE); - else - refaults = node_page_state(pgdat, WORKINGSET_ACTIVATE); - /* * When refaults are being observed, it means a new workingset * is being established. Disable active list protection to get * rid of the stale workingset quickly. */ + refaults = lruvec_page_state(lruvec, WORKINGSET_ACTIVATE); if (file && actual_reclaim && lruvec->refaults != refaults) { inactive_ratio = 0; } else { @@ -2227,12 +2222,10 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file, } static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, - struct lruvec *lruvec, struct mem_cgroup *memcg, - struct scan_control *sc) + struct lruvec *lruvec, struct scan_control *sc) { if (is_active_lru(lru)) { - if (inactive_list_is_low(lruvec, is_file_lru(lru), - memcg, sc, true)) + if (inactive_list_is_low(lruvec, is_file_lru(lru), sc, true)) shrink_active_list(nr_to_scan, lruvec, sc, lru); return 0; } @@ -2332,7 +2325,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, * anonymous pages on the LRU in eligible zones. * Otherwise, the small LRU gets thrashed. */ - if (!inactive_list_is_low(lruvec, false, memcg, sc, false) && + if (!inactive_list_is_low(lruvec, false, sc, false) && lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, sc->reclaim_idx) >> sc->priority) { scan_balance = SCAN_ANON; @@ -2350,7 +2343,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, * lruvec even if it has plenty of old anonymous pages unless the * system is under heavy pressure. */ - if (!inactive_list_is_low(lruvec, true, memcg, sc, false) && + if (!inactive_list_is_low(lruvec, true, sc, false) && lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, sc->reclaim_idx) >> sc->priority) { scan_balance = SCAN_FILE; goto out; @@ -2503,7 +2496,7 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc nr[lru] -= nr_to_scan; nr_reclaimed += shrink_list(lru, nr_to_scan, - lruvec, memcg, sc); + lruvec, sc); } } @@ -2570,7 +2563,7 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc * Even if we did not try to evict anon pages at all, we want to * rebalance the anon lru active/inactive ratio. */ - if (inactive_list_is_low(lruvec, false, memcg, sc, true)) + if (inactive_list_is_low(lruvec, false, sc, true)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); } @@ -2969,12 +2962,8 @@ static void snapshot_refaults(struct mem_cgroup *root_memcg, pg_data_t *pgdat) unsigned long refaults; struct lruvec *lruvec; - if (memcg) - refaults = memcg_page_state(memcg, WORKINGSET_ACTIVATE); - else - refaults = node_page_state(pgdat, WORKINGSET_ACTIVATE); - lruvec = mem_cgroup_lruvec(pgdat, memcg); + refaults = lruvec_page_state(lruvec, WORKINGSET_ACTIVATE); lruvec->refaults = refaults; } while ((memcg = mem_cgroup_iter(root_memcg, memcg, NULL))); } @@ -3339,7 +3328,7 @@ static void age_active_anon(struct pglist_data *pgdat, do { struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg); - if (inactive_list_is_low(lruvec, false, memcg, sc, true)) + if (inactive_list_is_low(lruvec, false, sc, true)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); diff --git a/mm/vmstat.c b/mm/vmstat.c index 36b56f858f0f..a7d493366a65 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1274,13 +1274,8 @@ const char * const vmstat_text[] = { #endif #endif /* CONFIG_MEMORY_BALLOON */ #ifdef CONFIG_DEBUG_TLBFLUSH -#ifdef CONFIG_SMP "nr_tlb_remote_flush", "nr_tlb_remote_flush_received", -#else - "", /* nr_tlb_remote_flush */ - "", /* nr_tlb_remote_flush_received */ -#endif /* CONFIG_SMP */ "nr_tlb_local_flush_all", "nr_tlb_local_flush_one", #endif /* CONFIG_DEBUG_TLBFLUSH */ diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 15293c2a5dd8..8d77b6ee4477 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -443,27 +443,29 @@ static int vlan_dev_fcoe_disable(struct net_device *dev) return rc; } -static int vlan_dev_fcoe_get_wwn(struct net_device *dev, u64 *wwn, int type) +static int vlan_dev_fcoe_ddp_target(struct net_device *dev, u16 xid, + struct scatterlist *sgl, unsigned int sgc) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; const struct net_device_ops *ops = real_dev->netdev_ops; - int rc = -EINVAL; + int rc = 0; + + if (ops->ndo_fcoe_ddp_target) + rc = ops->ndo_fcoe_ddp_target(real_dev, xid, sgl, sgc); - if (ops->ndo_fcoe_get_wwn) - rc = ops->ndo_fcoe_get_wwn(real_dev, wwn, type); return rc; } +#endif -static int vlan_dev_fcoe_ddp_target(struct net_device *dev, u16 xid, - struct scatterlist *sgl, unsigned int sgc) +#ifdef NETDEV_FCOE_WWNN +static int vlan_dev_fcoe_get_wwn(struct net_device *dev, u64 *wwn, int type) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; const struct net_device_ops *ops = real_dev->netdev_ops; - int rc = 0; - - if (ops->ndo_fcoe_ddp_target) - rc = ops->ndo_fcoe_ddp_target(real_dev, xid, sgl, sgc); + int rc = -EINVAL; + if (ops->ndo_fcoe_get_wwn) + rc = ops->ndo_fcoe_get_wwn(real_dev, wwn, type); return rc; } #endif @@ -794,9 +796,11 @@ static const struct net_device_ops vlan_netdev_ops = { .ndo_fcoe_ddp_done = vlan_dev_fcoe_ddp_done, .ndo_fcoe_enable = vlan_dev_fcoe_enable, .ndo_fcoe_disable = vlan_dev_fcoe_disable, - .ndo_fcoe_get_wwn = vlan_dev_fcoe_get_wwn, .ndo_fcoe_ddp_target = vlan_dev_fcoe_ddp_target, #endif +#ifdef NETDEV_FCOE_WWNN + .ndo_fcoe_get_wwn = vlan_dev_fcoe_get_wwn, +#endif #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = vlan_dev_poll_controller, .ndo_netpoll_setup = vlan_dev_netpoll_setup, diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c index 49a16cee2aae..420a98bf79b5 100644 --- a/net/appletalk/aarp.c +++ b/net/appletalk/aarp.c @@ -879,15 +879,24 @@ static struct notifier_block aarp_notifier = { static unsigned char aarp_snap_id[] = { 0x00, 0x00, 0x00, 0x80, 0xF3 }; -void __init aarp_proto_init(void) +int __init aarp_proto_init(void) { + int rc; + aarp_dl = register_snap_client(aarp_snap_id, aarp_rcv); - if (!aarp_dl) + if (!aarp_dl) { printk(KERN_CRIT "Unable to register AARP with SNAP.\n"); + return -ENOMEM; + } timer_setup(&aarp_timer, aarp_expire_timeout, 0); aarp_timer.expires = jiffies + sysctl_aarp_expiry_time; add_timer(&aarp_timer); - register_netdevice_notifier(&aarp_notifier); + rc = register_netdevice_notifier(&aarp_notifier); + if (rc) { + del_timer_sync(&aarp_timer); + unregister_snap_client(aarp_dl); + } + return rc; } /* Remove the AARP entries associated with a device. */ diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 795fbc6c06aa..dbe8b1993be9 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1904,9 +1904,6 @@ static unsigned char ddp_snap_id[] = { 0x08, 0x00, 0x07, 0x80, 0x9B }; EXPORT_SYMBOL(atrtr_get_dev); EXPORT_SYMBOL(atalk_find_dev_addr); -static const char atalk_err_snap[] __initconst = - KERN_CRIT "Unable to register DDP with SNAP.\n"; - /* Called by proto.c on kernel start up */ static int __init atalk_init(void) { @@ -1921,17 +1918,23 @@ static int __init atalk_init(void) goto out_proto; ddp_dl = register_snap_client(ddp_snap_id, atalk_rcv); - if (!ddp_dl) - printk(atalk_err_snap); + if (!ddp_dl) { + pr_crit("Unable to register DDP with SNAP.\n"); + rc = -ENOMEM; + goto out_sock; + } dev_add_pack(<alk_packet_type); dev_add_pack(&ppptalk_packet_type); rc = register_netdevice_notifier(&ddp_notifier); if (rc) - goto out_sock; + goto out_snap; + + rc = aarp_proto_init(); + if (rc) + goto out_dev; - aarp_proto_init(); rc = atalk_proc_init(); if (rc) goto out_aarp; @@ -1945,11 +1948,13 @@ out_proc: atalk_proc_exit(); out_aarp: aarp_cleanup_module(); +out_dev: unregister_netdevice_notifier(&ddp_notifier); -out_sock: +out_snap: dev_remove_pack(&ppptalk_packet_type); dev_remove_pack(<alk_packet_type); unregister_snap_client(ddp_dl); +out_sock: sock_unregister(PF_APPLETALK); out_proto: proto_unregister(&ddp_proto); diff --git a/net/atm/lec.c b/net/atm/lec.c index d7f5cf5b7594..ad4f829193f0 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -710,7 +710,10 @@ static int lec_vcc_attach(struct atm_vcc *vcc, void __user *arg) static int lec_mcast_attach(struct atm_vcc *vcc, int arg) { - if (arg < 0 || arg >= MAX_LEC_ITF || !dev_lec[arg]) + if (arg < 0 || arg >= MAX_LEC_ITF) + return -EINVAL; + arg = array_index_nospec(arg, MAX_LEC_ITF); + if (!dev_lec[arg]) return -EINVAL; vcc->proto_data = dev_lec[arg]; return lec_mcast_make(netdev_priv(dev_lec[arg]), vcc); @@ -728,6 +731,7 @@ static int lecd_attach(struct atm_vcc *vcc, int arg) i = arg; if (arg >= MAX_LEC_ITF) return -EINVAL; + i = array_index_nospec(arg, MAX_LEC_ITF); if (!dev_lec[i]) { int size; diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index a9b7919c9de5..d5df0114f08a 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -104,8 +104,10 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh) ret = cfg80211_get_station(real_netdev, neigh->addr, &sinfo); - /* free the TID stats immediately */ - cfg80211_sinfo_release_content(&sinfo); + if (!ret) { + /* free the TID stats immediately */ + cfg80211_sinfo_release_content(&sinfo); + } dev_put(real_netdev); if (ret == -ENOENT) { diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index ef39aabdb694..4fb01108e5f5 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -803,6 +803,8 @@ static void batadv_bla_del_claim(struct batadv_priv *bat_priv, const u8 *mac, const unsigned short vid) { struct batadv_bla_claim search_claim, *claim; + struct batadv_bla_claim *claim_removed_entry; + struct hlist_node *claim_removed_node; ether_addr_copy(search_claim.addr, mac); search_claim.vid = vid; @@ -813,10 +815,18 @@ static void batadv_bla_del_claim(struct batadv_priv *bat_priv, batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): %pM, vid %d\n", __func__, mac, batadv_print_vid(vid)); - batadv_hash_remove(bat_priv->bla.claim_hash, batadv_compare_claim, - batadv_choose_claim, claim); - batadv_claim_put(claim); /* reference from the hash is gone */ + claim_removed_node = batadv_hash_remove(bat_priv->bla.claim_hash, + batadv_compare_claim, + batadv_choose_claim, claim); + if (!claim_removed_node) + goto free_claim; + /* reference from the hash is gone */ + claim_removed_entry = hlist_entry(claim_removed_node, + struct batadv_bla_claim, hash_entry); + batadv_claim_put(claim_removed_entry); + +free_claim: /* don't need the reference from hash_find() anymore */ batadv_claim_put(claim); } diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index 0b4b3fb778a6..208655cf6717 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -1116,9 +1116,9 @@ static ssize_t batadv_store_throughput_override(struct kobject *kobj, struct attribute *attr, char *buff, size_t count) { - struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj); struct net_device *net_dev = batadv_kobj_to_netdev(kobj); struct batadv_hard_iface *hard_iface; + struct batadv_priv *bat_priv; u32 tp_override; u32 old_tp_override; bool ret; @@ -1147,7 +1147,10 @@ static ssize_t batadv_store_throughput_override(struct kobject *kobj, atomic_set(&hard_iface->bat_v.throughput_override, tp_override); - batadv_netlink_notify_hardif(bat_priv, hard_iface); + if (hard_iface->soft_iface) { + bat_priv = netdev_priv(hard_iface->soft_iface); + batadv_netlink_notify_hardif(bat_priv, hard_iface); + } out: batadv_hardif_put(hard_iface); diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index f73d79139ae7..26c4e2493ddf 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -616,14 +616,26 @@ static void batadv_tt_global_free(struct batadv_priv *bat_priv, struct batadv_tt_global_entry *tt_global, const char *message) { + struct batadv_tt_global_entry *tt_removed_entry; + struct hlist_node *tt_removed_node; + batadv_dbg(BATADV_DBG_TT, bat_priv, "Deleting global tt entry %pM (vid: %d): %s\n", tt_global->common.addr, batadv_print_vid(tt_global->common.vid), message); - batadv_hash_remove(bat_priv->tt.global_hash, batadv_compare_tt, - batadv_choose_tt, &tt_global->common); - batadv_tt_global_entry_put(tt_global); + tt_removed_node = batadv_hash_remove(bat_priv->tt.global_hash, + batadv_compare_tt, + batadv_choose_tt, + &tt_global->common); + if (!tt_removed_node) + return; + + /* drop reference of remove hash entry */ + tt_removed_entry = hlist_entry(tt_removed_node, + struct batadv_tt_global_entry, + common.hash_entry); + batadv_tt_global_entry_put(tt_removed_entry); } /** @@ -1337,9 +1349,10 @@ u16 batadv_tt_local_remove(struct batadv_priv *bat_priv, const u8 *addr, unsigned short vid, const char *message, bool roaming) { + struct batadv_tt_local_entry *tt_removed_entry; struct batadv_tt_local_entry *tt_local_entry; u16 flags, curr_flags = BATADV_NO_FLAGS; - void *tt_entry_exists; + struct hlist_node *tt_removed_node; tt_local_entry = batadv_tt_local_hash_find(bat_priv, addr, vid); if (!tt_local_entry) @@ -1368,15 +1381,18 @@ u16 batadv_tt_local_remove(struct batadv_priv *bat_priv, const u8 *addr, */ batadv_tt_local_event(bat_priv, tt_local_entry, BATADV_TT_CLIENT_DEL); - tt_entry_exists = batadv_hash_remove(bat_priv->tt.local_hash, + tt_removed_node = batadv_hash_remove(bat_priv->tt.local_hash, batadv_compare_tt, batadv_choose_tt, &tt_local_entry->common); - if (!tt_entry_exists) + if (!tt_removed_node) goto out; - /* extra call to free the local tt entry */ - batadv_tt_local_entry_put(tt_local_entry); + /* drop reference of remove hash entry */ + tt_removed_entry = hlist_entry(tt_removed_node, + struct batadv_tt_local_entry, + common.hash_entry); + batadv_tt_local_entry_put(tt_removed_entry); out: if (tt_local_entry) diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 9a580999ca57..d892b7c3cc42 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -523,12 +523,12 @@ static int sco_sock_bind(struct socket *sock, struct sockaddr *addr, struct sock *sk = sock->sk; int err = 0; - BT_DBG("sk %p %pMR", sk, &sa->sco_bdaddr); - if (!addr || addr_len < sizeof(struct sockaddr_sco) || addr->sa_family != AF_BLUETOOTH) return -EINVAL; + BT_DBG("sk %p %pMR", sk, &sa->sco_bdaddr); + lock_sock(sk); if (sk->sk_state != BT_OPEN) { diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 5ea7e56119c1..ba303ee99b9b 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -197,13 +197,10 @@ static void __br_handle_local_finish(struct sk_buff *skb) /* note: already called with rcu_read_lock */ static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net_bridge_port *p = br_port_get_rcu(skb->dev); - __br_handle_local_finish(skb); - BR_INPUT_SKB_CB(skb)->brdev = p->br->dev; - br_pass_frame_up(skb); - return 0; + /* return 1 to signal the okfn() was called so it's ok to use the skb */ + return 1; } /* @@ -280,10 +277,18 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb) goto forward; } - /* Deliver packet to local host only */ - NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, dev_net(skb->dev), - NULL, skb, skb->dev, NULL, br_handle_local_finish); - return RX_HANDLER_CONSUMED; + /* The else clause should be hit when nf_hook(): + * - returns < 0 (drop/error) + * - returns = 0 (stolen/nf_queue) + * Thus return 1 from the okfn() to signal the skb is ok to pass + */ + if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, + dev_net(skb->dev), NULL, skb, skb->dev, NULL, + br_handle_local_finish) == 1) { + return RX_HANDLER_PASS; + } else { + return RX_HANDLER_CONSUMED; + } } forward: diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index a0e369179f6d..45e7f4173bba 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -601,6 +601,7 @@ static int br_ip4_multicast_add_group(struct net_bridge *br, if (ipv4_is_local_multicast(group)) return 0; + memset(&br_group, 0, sizeof(br_group)); br_group.u.ip4 = group; br_group.proto = htons(ETH_P_IP); br_group.vid = vid; @@ -1497,6 +1498,7 @@ static void br_ip4_multicast_leave_group(struct net_bridge *br, own_query = port ? &port->ip4_own_query : &br->ip4_own_query; + memset(&br_group, 0, sizeof(br_group)); br_group.u.ip4 = group; br_group.proto = htons(ETH_P_IP); br_group.vid = vid; @@ -1520,6 +1522,7 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br, own_query = port ? &port->ip6_own_query : &br->ip6_own_query; + memset(&br_group, 0, sizeof(br_group)); br_group.u.ip6 = *group; br_group.proto = htons(ETH_P_IPV6); br_group.vid = vid; @@ -2028,7 +2031,8 @@ static void br_multicast_start_querier(struct net_bridge *br, __br_multicast_open(br, query); - list_for_each_entry(port, &br->port_list, list) { + rcu_read_lock(); + list_for_each_entry_rcu(port, &br->port_list, list) { if (port->state == BR_STATE_DISABLED || port->state == BR_STATE_BLOCKING) continue; @@ -2040,6 +2044,7 @@ static void br_multicast_start_querier(struct net_bridge *br, br_multicast_enable(&port->ip6_own_query); #endif } + rcu_read_unlock(); } int br_multicast_toggle(struct net_bridge *br, unsigned long val) diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 9d34de68571b..22afa566cbce 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -502,6 +502,7 @@ static unsigned int br_nf_pre_routing(void *priv, nf_bridge->ipv4_daddr = ip_hdr(skb)->daddr; skb->protocol = htons(ETH_P_IP); + skb->transport_header = skb->network_header + ip_hdr(skb)->ihl * 4; NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, state->net, state->sk, skb, skb->dev, NULL, diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c index 564710f88f93..e88d6641647b 100644 --- a/net/bridge/br_netfilter_ipv6.c +++ b/net/bridge/br_netfilter_ipv6.c @@ -235,6 +235,8 @@ unsigned int br_nf_pre_routing_ipv6(void *priv, nf_bridge->ipv6_daddr = ipv6_hdr(skb)->daddr; skb->protocol = htons(ETH_P_IPV6); + skb->transport_header = skb->network_header + sizeof(struct ipv6hdr); + NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, state->net, state->sk, skb, skb->dev, NULL, br_nf_pre_routing_finish_ipv6); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 9c07591b0232..7104cf13da84 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -1441,7 +1441,7 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) nla_put_u8(skb, IFLA_BR_VLAN_STATS_ENABLED, br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) || nla_put_u8(skb, IFLA_BR_VLAN_STATS_PER_PORT, - br_opt_get(br, IFLA_BR_VLAN_STATS_PER_PORT))) + br_opt_get(br, BROPT_VLAN_STATS_PER_PORT))) return -EMSGSIZE; #endif #ifdef CONFIG_BRIDGE_IGMP_SNOOPING diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index eb15891f8b9f..3cad01ac64e4 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -2032,7 +2032,8 @@ static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32, if (match_kern) match_kern->match_size = ret; - if (WARN_ON(type == EBT_COMPAT_TARGET && size_left)) + /* rule should have no remaining data after target */ + if (type == EBT_COMPAT_TARGET && size_left) return -EINVAL; match32 = (struct compat_ebt_entry_mwt *) buf; diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 7e71b0df1fbc..3083988ce729 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -840,6 +840,7 @@ static bool ceph_msg_data_bio_advance(struct ceph_msg_data_cursor *cursor, size_t bytes) { struct ceph_bio_iter *it = &cursor->bio_iter; + struct page *page = bio_iter_page(it->bio, it->iter); BUG_ON(bytes > cursor->resid); BUG_ON(bytes > bio_iter_len(it->bio, it->iter)); @@ -851,7 +852,8 @@ static bool ceph_msg_data_bio_advance(struct ceph_msg_data_cursor *cursor, return false; /* no more data */ } - if (!bytes || (it->iter.bi_size && it->iter.bi_bvec_done)) + if (!bytes || (it->iter.bi_size && it->iter.bi_bvec_done && + page == bio_iter_page(it->bio, it->iter))) return false; /* more bytes to process in this segment */ if (!it->iter.bi_size) { @@ -899,6 +901,7 @@ static bool ceph_msg_data_bvecs_advance(struct ceph_msg_data_cursor *cursor, size_t bytes) { struct bio_vec *bvecs = cursor->data->bvec_pos.bvecs; + struct page *page = bvec_iter_page(bvecs, cursor->bvec_iter); BUG_ON(bytes > cursor->resid); BUG_ON(bytes > bvec_iter_len(bvecs, cursor->bvec_iter)); @@ -910,7 +913,8 @@ static bool ceph_msg_data_bvecs_advance(struct ceph_msg_data_cursor *cursor, return false; /* no more data */ } - if (!bytes || cursor->bvec_iter.bi_bvec_done) + if (!bytes || (cursor->bvec_iter.bi_bvec_done && + page == bvec_iter_page(bvecs, cursor->bvec_iter))) return false; /* more bytes to process in this segment */ BUG_ON(cursor->last_piece); diff --git a/net/core/datagram.c b/net/core/datagram.c index b2651bb6d2a3..e657289db4ac 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -279,7 +279,7 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags, break; sk_busy_loop(sk, flags & MSG_DONTWAIT); - } while (!skb_queue_empty(&sk->sk_receive_queue)); + } while (sk->sk_receive_queue.prev != *last); error = -EAGAIN; diff --git a/net/core/dev.c b/net/core/dev.c index 2b67f2aa59dd..f409406254dd 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1184,7 +1184,21 @@ int dev_change_name(struct net_device *dev, const char *newname) BUG_ON(!dev_net(dev)); net = dev_net(dev); - if (dev->flags & IFF_UP) + + /* Some auto-enslaved devices e.g. failover slaves are + * special, as userspace might rename the device after + * the interface had been brought up and running since + * the point kernel initiated auto-enslavement. Allow + * live name change even when these slave devices are + * up and running. + * + * Typically, users of these auto-enslaving devices + * don't actually care about slave name change, as + * they are supposed to operate on master interface + * directly. + */ + if (dev->flags & IFF_UP && + likely(!(dev->priv_flags & IFF_LIVE_RENAME_OK))) return -EBUSY; write_seqcount_begin(&devnet_rename_seq); @@ -5014,8 +5028,10 @@ static inline void __netif_receive_skb_list_ptype(struct list_head *head, if (pt_prev->list_func != NULL) pt_prev->list_func(head, pt_prev, orig_dev); else - list_for_each_entry_safe(skb, next, head, list) + list_for_each_entry_safe(skb, next, head, list) { + skb_list_del_init(skb); pt_prev->func(skb, skb->dev, pt_prev, orig_dev); + } } static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemalloc) diff --git a/net/core/devlink.c b/net/core/devlink.c index 78e22cea4cc7..da0a29f30885 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -3897,6 +3897,11 @@ static int devlink_nl_cmd_info_get_dumpit(struct sk_buff *msg, continue; } + if (!devlink->ops->info_get) { + idx++; + continue; + } + mutex_lock(&devlink->lock); err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, NETLINK_CB(cb->skb).portid, diff --git a/net/core/ethtool.c b/net/core/ethtool.c index b1eb32419732..36ed619faf36 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1797,11 +1797,16 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr) WARN_ON_ONCE(!ret); gstrings.len = ret; - data = vzalloc(array_size(gstrings.len, ETH_GSTRING_LEN)); - if (gstrings.len && !data) - return -ENOMEM; - __ethtool_get_strings(dev, gstrings.string_set, data); + if (gstrings.len) { + data = vzalloc(array_size(gstrings.len, ETH_GSTRING_LEN)); + if (!data) + return -ENOMEM; + + __ethtool_get_strings(dev, gstrings.string_set, data); + } else { + data = NULL; + } ret = -EFAULT; if (copy_to_user(useraddr, &gstrings, sizeof(gstrings))) @@ -1897,11 +1902,15 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr) return -EFAULT; stats.n_stats = n_stats; - data = vzalloc(array_size(n_stats, sizeof(u64))); - if (n_stats && !data) - return -ENOMEM; - ops->get_ethtool_stats(dev, &stats, data); + if (n_stats) { + data = vzalloc(array_size(n_stats, sizeof(u64))); + if (!data) + return -ENOMEM; + ops->get_ethtool_stats(dev, &stats, data); + } else { + data = NULL; + } ret = -EFAULT; if (copy_to_user(useraddr, &stats, sizeof(stats))) @@ -1941,16 +1950,21 @@ static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr) return -EFAULT; stats.n_stats = n_stats; - data = vzalloc(array_size(n_stats, sizeof(u64))); - if (n_stats && !data) - return -ENOMEM; - if (dev->phydev && !ops->get_ethtool_phy_stats) { - ret = phy_ethtool_get_stats(dev->phydev, &stats, data); - if (ret < 0) - return ret; + if (n_stats) { + data = vzalloc(array_size(n_stats, sizeof(u64))); + if (!data) + return -ENOMEM; + + if (dev->phydev && !ops->get_ethtool_phy_stats) { + ret = phy_ethtool_get_stats(dev->phydev, &stats, data); + if (ret < 0) + goto out; + } else { + ops->get_ethtool_phy_stats(dev, &stats, data); + } } else { - ops->get_ethtool_phy_stats(dev, &stats, data); + data = NULL; } ret = -EFAULT; diff --git a/net/core/failover.c b/net/core/failover.c index 4a92a98ccce9..b5cd3c727285 100644 --- a/net/core/failover.c +++ b/net/core/failover.c @@ -80,14 +80,14 @@ static int failover_slave_register(struct net_device *slave_dev) goto err_upper_link; } - slave_dev->priv_flags |= IFF_FAILOVER_SLAVE; + slave_dev->priv_flags |= (IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK); if (fops && fops->slave_register && !fops->slave_register(slave_dev, failover_dev)) return NOTIFY_OK; netdev_upper_dev_unlink(slave_dev, failover_dev); - slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE; + slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK); err_upper_link: netdev_rx_handler_unregister(slave_dev); done: @@ -121,7 +121,7 @@ int failover_slave_unregister(struct net_device *slave_dev) netdev_rx_handler_unregister(slave_dev); netdev_upper_dev_unlink(slave_dev, failover_dev); - slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE; + slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK); if (fops && fops->slave_unregister && !fops->slave_unregister(slave_dev, failover_dev)) diff --git a/net/core/filter.c b/net/core/filter.c index f274620945ff..27e61ffd9039 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1796,8 +1796,6 @@ static const struct bpf_func_proto bpf_skb_pull_data_proto = { BPF_CALL_1(bpf_sk_fullsock, struct sock *, sk) { - sk = sk_to_full_sk(sk); - return sk_fullsock(sk) ? (unsigned long)sk : (unsigned long)NULL; } @@ -4385,6 +4383,8 @@ BPF_CALL_3(bpf_bind, struct bpf_sock_addr_kern *, ctx, struct sockaddr *, addr, * Only binding to IP is supported. */ err = -EINVAL; + if (addr_len < offsetofend(struct sockaddr, sa_family)) + return err; if (addr->sa_family == AF_INET) { if (addr_len < sizeof(struct sockaddr_in)) return err; @@ -5266,7 +5266,7 @@ static const struct bpf_func_proto bpf_sk_release_proto = { .func = bpf_sk_release, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_SOCKET, + .arg1_type = ARG_PTR_TO_SOCK_COMMON, }; BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx, @@ -5407,8 +5407,6 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, BPF_CALL_1(bpf_tcp_sock, struct sock *, sk) { - sk = sk_to_full_sk(sk); - if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP) return (unsigned long)sk; @@ -5422,6 +5420,23 @@ static const struct bpf_func_proto bpf_tcp_sock_proto = { .arg1_type = ARG_PTR_TO_SOCK_COMMON, }; +BPF_CALL_1(bpf_get_listener_sock, struct sock *, sk) +{ + sk = sk_to_full_sk(sk); + + if (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_RCU_FREE)) + return (unsigned long)sk; + + return (unsigned long)NULL; +} + +static const struct bpf_func_proto bpf_get_listener_sock_proto = { + .func = bpf_get_listener_sock, + .gpl_only = false, + .ret_type = RET_PTR_TO_SOCKET_OR_NULL, + .arg1_type = ARG_PTR_TO_SOCK_COMMON, +}; + BPF_CALL_1(bpf_skb_ecn_set_ce, struct sk_buff *, skb) { unsigned int iphdr_len; @@ -5607,6 +5622,8 @@ cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) #ifdef CONFIG_INET case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; + case BPF_FUNC_get_listener_sock: + return &bpf_get_listener_sock_proto; case BPF_FUNC_skb_ecn_set_ce: return &bpf_skb_ecn_set_ce_proto; #endif @@ -5702,6 +5719,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sk_release_proto; case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; + case BPF_FUNC_get_listener_sock: + return &bpf_get_listener_sock_proto; #endif default: return bpf_base_func_proto(func_id); @@ -6596,14 +6615,8 @@ static bool flow_dissector_is_valid_access(int off, int size, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { - if (type == BPF_WRITE) { - switch (off) { - case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): - break; - default: - return false; - } - } + if (type == BPF_WRITE) + return false; switch (off) { case bpf_ctx_range(struct __sk_buff, data): @@ -6615,11 +6628,7 @@ static bool flow_dissector_is_valid_access(int off, int size, case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): info->reg_type = PTR_TO_FLOW_KEYS; break; - case bpf_ctx_range(struct __sk_buff, tc_classid): - case bpf_ctx_range(struct __sk_buff, data_meta): - case bpf_ctx_range_till(struct __sk_buff, family, local_port): - case bpf_ctx_range(struct __sk_buff, tstamp): - case bpf_ctx_range(struct __sk_buff, wire_len): + default: return false; } diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index bb1a54747d64..94a450b2191a 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -707,6 +707,7 @@ bool __skb_flow_bpf_dissect(struct bpf_prog *prog, /* Pass parameters to the BPF program */ memset(flow_keys, 0, sizeof(*flow_keys)); cb->qdisc_cb.flow_keys = flow_keys; + flow_keys->n_proto = skb->protocol; flow_keys->nhoff = skb_network_offset(skb); flow_keys->thoff = flow_keys->nhoff; @@ -716,7 +717,8 @@ bool __skb_flow_bpf_dissect(struct bpf_prog *prog, /* Restore state */ memcpy(cb, &cb_saved, sizeof(cb_saved)); - flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff, 0, skb->len); + flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff, + skb_network_offset(skb), skb->len); flow_keys->thoff = clamp_t(u16, flow_keys->thoff, flow_keys->nhoff, skb->len); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 4ff661f6f989..8f8b7b6c2945 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -928,6 +928,8 @@ static int rx_queue_add_kobject(struct net_device *dev, int index) if (error) return error; + dev_hold(queue->dev); + if (dev->sysfs_rx_queue_group) { error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group); if (error) { @@ -937,7 +939,6 @@ static int rx_queue_add_kobject(struct net_device *dev, int index) } kobject_uevent(kobj, KOBJ_ADD); - dev_hold(queue->dev); return error; } @@ -1464,6 +1465,8 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index) if (error) return error; + dev_hold(queue->dev); + #ifdef CONFIG_BQL error = sysfs_create_group(kobj, &dql_group); if (error) { @@ -1473,7 +1476,6 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index) #endif kobject_uevent(kobj, KOBJ_ADD); - dev_hold(queue->dev); return 0; } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 17f36317363d..7e6dcc625701 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -304,6 +304,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) refcount_set(&net->count, 1); refcount_set(&net->passive, 1); + get_random_bytes(&net->hash_mix, sizeof(u32)); net->dev_base_seq = 1; net->user_ns = user_ns; idr_init(&net->netns_ids); diff --git a/net/core/ptp_classifier.c b/net/core/ptp_classifier.c index 703cf76aa7c2..7109c168b5e0 100644 --- a/net/core/ptp_classifier.c +++ b/net/core/ptp_classifier.c @@ -185,9 +185,10 @@ void __init ptp_classifier_init(void) { 0x16, 0, 0, 0x00000000 }, { 0x06, 0, 0, 0x00000000 }, }; - struct sock_fprog_kern ptp_prog = { - .len = ARRAY_SIZE(ptp_filter), .filter = ptp_filter, - }; + struct sock_fprog_kern ptp_prog; + + ptp_prog.len = ARRAY_SIZE(ptp_filter); + ptp_prog.filter = ptp_filter; BUG_ON(bpf_prog_create(&ptp_insns, &ptp_prog)); } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index a51cab95ba64..220c56e93659 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -4948,7 +4948,7 @@ static int rtnl_valid_stats_req(const struct nlmsghdr *nlh, bool strict_check, { struct if_stats_msg *ifsm; - if (nlh->nlmsg_len < sizeof(*ifsm)) { + if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifsm))) { NL_SET_ERR_MSG(extack, "Invalid header for stats dump"); return -EINVAL; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 2415d9cb9b89..40796b8bf820 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3801,7 +3801,7 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) unsigned int delta_truesize; struct sk_buff *lp; - if (unlikely(p->len + len >= 65536)) + if (unlikely(p->len + len >= 65536 || NAPI_GRO_CB(skb)->flush)) return -E2BIG; lp = NAPI_GRO_CB(p)->last; @@ -5083,7 +5083,8 @@ EXPORT_SYMBOL_GPL(skb_gso_validate_mac_len); static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb) { - int mac_len; + int mac_len, meta_len; + void *meta; if (skb_cow(skb, skb_headroom(skb)) < 0) { kfree_skb(skb); @@ -5095,6 +5096,13 @@ static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb) memmove(skb_mac_header(skb) + VLAN_HLEN, skb_mac_header(skb), mac_len - VLAN_HLEN - ETH_TLEN); } + + meta_len = skb_metadata_len(skb); + if (meta_len) { + meta = skb_metadata_end(skb) - meta_len; + memmove(meta + VLAN_HLEN, meta, meta_len); + } + skb->mac_header += VLAN_HLEN; return skb; } diff --git a/net/core/sock.c b/net/core/sock.c index 782343bb925b..067878a1e4c5 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -348,7 +348,7 @@ static int sock_get_timeout(long timeo, void *optval, bool old_timeval) tv.tv_usec = ((timeo % HZ) * USEC_PER_SEC) / HZ; } - if (in_compat_syscall() && !COMPAT_USE_64BIT_TIME) { + if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) { struct old_timeval32 tv32 = { tv.tv_sec, tv.tv_usec }; *(struct old_timeval32 *)optval = tv32; return sizeof(tv32); @@ -372,7 +372,7 @@ static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen, bool { struct __kernel_sock_timeval tv; - if (in_compat_syscall() && !COMPAT_USE_64BIT_TIME) { + if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) { struct old_timeval32 tv32; if (optlen < sizeof(tv32)) diff --git a/net/dccp/feat.c b/net/dccp/feat.c index f227f002c73d..db87d9f58019 100644 --- a/net/dccp/feat.c +++ b/net/dccp/feat.c @@ -738,7 +738,12 @@ static int __feat_register_sp(struct list_head *fn, u8 feat, u8 is_local, if (dccp_feat_clone_sp_val(&fval, sp_val, sp_len)) return -ENOMEM; - return dccp_feat_push_change(fn, feat, is_local, mandatory, &fval); + if (dccp_feat_push_change(fn, feat, is_local, mandatory, &fval)) { + kfree(fval.sp.vec); + return -ENOMEM; + } + + return 0; } /** diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index d5740bad5b18..57d84e9b7b6f 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -436,8 +436,8 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk, newnp->ipv6_mc_list = NULL; newnp->ipv6_ac_list = NULL; newnp->ipv6_fl_list = NULL; - newnp->mcast_oif = inet6_iif(skb); - newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; + newnp->mcast_oif = inet_iif(skb); + newnp->mcast_hops = ip_hdr(skb)->ttl; /* * No need to charge this sock to the relevant IPv6 refcnt debug socks count diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index ed4f6dc26365..85c22ada4744 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -98,8 +98,18 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev, return skb; } +static int qca_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto, + int *offset) +{ + *offset = QCA_HDR_LEN; + *proto = ((__be16 *)skb->data)[0]; + + return 0; +} + const struct dsa_device_ops qca_netdev_ops = { .xmit = qca_tag_xmit, .rcv = qca_tag_rcv, + .flow_dissect = qca_tag_flow_dissect, .overhead = QCA_HDR_LEN, }; diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 10e809b296ec..fb065a8937ea 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -226,7 +226,7 @@ static void esp_output_fill_trailer(u8 *tail, int tfclen, int plen, __u8 proto) tail[plen - 1] = proto; } -static void esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp) +static int esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp) { int encap_type; struct udphdr *uh; @@ -234,6 +234,7 @@ static void esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, stru __be16 sport, dport; struct xfrm_encap_tmpl *encap = x->encap; struct ip_esp_hdr *esph = esp->esph; + unsigned int len; spin_lock_bh(&x->lock); sport = encap->encap_sport; @@ -241,11 +242,14 @@ static void esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, stru encap_type = encap->encap_type; spin_unlock_bh(&x->lock); + len = skb->len + esp->tailen - skb_transport_offset(skb); + if (len + sizeof(struct iphdr) >= IP_MAX_MTU) + return -EMSGSIZE; + uh = (struct udphdr *)esph; uh->source = sport; uh->dest = dport; - uh->len = htons(skb->len + esp->tailen - - skb_transport_offset(skb)); + uh->len = htons(len); uh->check = 0; switch (encap_type) { @@ -262,6 +266,8 @@ static void esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, stru *skb_mac_header(skb) = IPPROTO_UDP; esp->esph = esph; + + return 0; } int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp) @@ -275,8 +281,12 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * int tailen = esp->tailen; /* this is non-NULL only with UDP Encapsulation */ - if (x->encap) - esp_output_udp_encap(x, skb, esp); + if (x->encap) { + int err = esp_output_udp_encap(x, skb, esp); + + if (err < 0) + return err; + } if (!skb_cloned(skb)) { if (tailen <= skb_tailroom(skb)) { diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 8756e0e790d2..d3170a8001b2 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -52,13 +52,13 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head, goto out; if (sp->len == XFRM_MAX_DEPTH) - goto out; + goto out_reset; x = xfrm_state_lookup(dev_net(skb->dev), skb->mark, (xfrm_address_t *)&ip_hdr(skb)->daddr, spi, IPPROTO_ESP, AF_INET); if (!x) - goto out; + goto out_reset; sp->xvec[sp->len++] = x; sp->olen++; @@ -66,7 +66,7 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head, xo = xfrm_offload(skb); if (!xo) { xfrm_state_put(x); - goto out; + goto out_reset; } } @@ -82,6 +82,8 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head, xfrm_input(skb, IPPROTO_ESP, spi, -2); return ERR_PTR(-EINPROGRESS); +out_reset: + secpath_reset(skb); out: skb_push(skb, offset); NAPI_GRO_CB(skb)->same_flow = 0; diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 79e98e21cdd7..12ce6c526d72 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -121,6 +121,7 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb) struct guehdr *guehdr; void *data; u16 doffset = 0; + u8 proto_ctype; if (!fou) return 1; @@ -212,13 +213,14 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb) if (unlikely(guehdr->control)) return gue_control_message(skb, guehdr); + proto_ctype = guehdr->proto_ctype; __skb_pull(skb, sizeof(struct udphdr) + hdrlen); skb_reset_transport_header(skb); if (iptunnel_pull_offloads(skb)) goto drop; - return -guehdr->proto_ctype; + return -proto_ctype; drop: kfree_skb(skb); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index fd219f7bd3ea..4b0526441476 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -259,7 +259,6 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, struct net *net = dev_net(skb->dev); struct metadata_dst *tun_dst = NULL; struct erspan_base_hdr *ershdr; - struct erspan_metadata *pkt_md; struct ip_tunnel_net *itn; struct ip_tunnel *tunnel; const struct iphdr *iph; @@ -282,9 +281,6 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, if (unlikely(!pskb_may_pull(skb, len))) return PACKET_REJECT; - ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len); - pkt_md = (struct erspan_metadata *)(ershdr + 1); - if (__iptunnel_pull_header(skb, len, htons(ETH_P_TEB), @@ -292,8 +288,9 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, goto drop; if (tunnel->collect_md) { + struct erspan_metadata *pkt_md, *md; struct ip_tunnel_info *info; - struct erspan_metadata *md; + unsigned char *gh; __be64 tun_id; __be16 flags; @@ -306,6 +303,14 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, if (!tun_dst) return PACKET_REJECT; + /* skb can be uncloned in __iptunnel_pull_header, so + * old pkt_md is no longer valid and we need to reset + * it + */ + gh = skb_network_header(skb) + + skb_network_header_len(skb); + pkt_md = (struct erspan_metadata *)(gh + gre_hdr_len + + sizeof(*ershdr)); md = ip_tunnel_info_opts(&tun_dst->u.tun_info); md->version = ver; md2 = &md->u.md2; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index ecce2dc78f17..1132d6d1796a 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -257,11 +257,10 @@ int ip_local_deliver(struct sk_buff *skb) ip_local_deliver_finish); } -static inline bool ip_rcv_options(struct sk_buff *skb) +static inline bool ip_rcv_options(struct sk_buff *skb, struct net_device *dev) { struct ip_options *opt; const struct iphdr *iph; - struct net_device *dev = skb->dev; /* It looks as overkill, because not all IP options require packet mangling. @@ -297,7 +296,7 @@ static inline bool ip_rcv_options(struct sk_buff *skb) } } - if (ip_options_rcv_srr(skb)) + if (ip_options_rcv_srr(skb, dev)) goto drop; } @@ -353,7 +352,7 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk, } #endif - if (iph->ihl > 5 && ip_rcv_options(skb)) + if (iph->ihl > 5 && ip_rcv_options(skb, dev)) goto drop; rt = skb_rtable(skb); diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 32a35043c9f5..3db31bb9df50 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -612,7 +612,7 @@ void ip_forward_options(struct sk_buff *skb) } } -int ip_options_rcv_srr(struct sk_buff *skb) +int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev) { struct ip_options *opt = &(IPCB(skb)->opt); int srrspace, srrptr; @@ -647,7 +647,7 @@ int ip_options_rcv_srr(struct sk_buff *skb) orefdst = skb->_skb_refdst; skb_dst_set(skb, NULL); - err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, skb->dev); + err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, dev); rt2 = skb_rtable(skb); if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) { skb_dst_drop(skb); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index c80188875f39..e8bb2e85c5a4 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -519,6 +519,7 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->pkt_type = from->pkt_type; to->priority = from->priority; to->protocol = from->protocol; + to->skb_iif = from->skb_iif; skb_dst_drop(to); skb_dst_copy(to, from); to->dev = from->dev; diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 68a21bf75dd0..35d8346742e2 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -646,10 +646,8 @@ static int __init vti_init(void) msg = "ipip tunnel"; err = xfrm4_tunnel_register(&ipip_handler, AF_INET); - if (err < 0) { - pr_info("%s: cant't register tunnel\n",__func__); + if (err < 0) goto xfrm_tunnel_failed; - } msg = "netlink interface"; err = rtnl_link_register(&vti_link_ops); @@ -659,9 +657,9 @@ static int __init vti_init(void) return err; rtnl_link_failed: - xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP); -xfrm_tunnel_failed: xfrm4_tunnel_deregister(&ipip_handler, AF_INET); +xfrm_tunnel_failed: + xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP); xfrm_proto_comp_failed: xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); xfrm_proto_ah_failed: @@ -676,6 +674,7 @@ pernet_dev_failed: static void __exit vti_fini(void) { rtnl_link_unregister(&vti_link_ops); + xfrm4_tunnel_deregister(&ipip_handler, AF_INET); xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP); xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a5da63e5faa2..6fdf1c195d8e 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1183,11 +1183,39 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) return dst; } +static void ipv4_send_dest_unreach(struct sk_buff *skb) +{ + struct ip_options opt; + int res; + + /* Recompile ip options since IPCB may not be valid anymore. + * Also check we have a reasonable ipv4 header. + */ + if (!pskb_network_may_pull(skb, sizeof(struct iphdr)) || + ip_hdr(skb)->version != 4 || ip_hdr(skb)->ihl < 5) + return; + + memset(&opt, 0, sizeof(opt)); + if (ip_hdr(skb)->ihl > 5) { + if (!pskb_network_may_pull(skb, ip_hdr(skb)->ihl * 4)) + return; + opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr); + + rcu_read_lock(); + res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL); + rcu_read_unlock(); + + if (res) + return; + } + __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt); +} + static void ipv4_link_failure(struct sk_buff *skb) { struct rtable *rt; - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); + ipv4_send_dest_unreach(skb); rt = skb_rtable(skb); if (rt) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index ba0fc4b18465..eeb4041fa5f9 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -49,6 +49,7 @@ static int ip_ping_group_range_min[] = { 0, 0 }; static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; static int comp_sack_nr_max = 255; static u32 u32_max_div_HZ = UINT_MAX / HZ; +static int one_day_secs = 24 * 3600; /* obsolete */ static int sysctl_tcp_low_latency __read_mostly; @@ -1151,7 +1152,9 @@ static struct ctl_table ipv4_net_table[] = { .data = &init_net.ipv4.sysctl_tcp_min_rtt_wlen, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one_day_secs }, { .procname = "tcp_autocorking", diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index cd4814f7e962..477cb4aa456c 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -49,9 +49,8 @@ #define DCTCP_MAX_ALPHA 1024U struct dctcp { - u32 acked_bytes_ecn; - u32 acked_bytes_total; - u32 prior_snd_una; + u32 old_delivered; + u32 old_delivered_ce; u32 prior_rcv_nxt; u32 dctcp_alpha; u32 next_seq; @@ -67,19 +66,14 @@ static unsigned int dctcp_alpha_on_init __read_mostly = DCTCP_MAX_ALPHA; module_param(dctcp_alpha_on_init, uint, 0644); MODULE_PARM_DESC(dctcp_alpha_on_init, "parameter for initial alpha value"); -static unsigned int dctcp_clamp_alpha_on_loss __read_mostly; -module_param(dctcp_clamp_alpha_on_loss, uint, 0644); -MODULE_PARM_DESC(dctcp_clamp_alpha_on_loss, - "parameter for clamping alpha on loss"); - static struct tcp_congestion_ops dctcp_reno; static void dctcp_reset(const struct tcp_sock *tp, struct dctcp *ca) { ca->next_seq = tp->snd_nxt; - ca->acked_bytes_ecn = 0; - ca->acked_bytes_total = 0; + ca->old_delivered = tp->delivered; + ca->old_delivered_ce = tp->delivered_ce; } static void dctcp_init(struct sock *sk) @@ -91,7 +85,6 @@ static void dctcp_init(struct sock *sk) sk->sk_state == TCP_CLOSE)) { struct dctcp *ca = inet_csk_ca(sk); - ca->prior_snd_una = tp->snd_una; ca->prior_rcv_nxt = tp->rcv_nxt; ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA); @@ -123,37 +116,25 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags) { const struct tcp_sock *tp = tcp_sk(sk); struct dctcp *ca = inet_csk_ca(sk); - u32 acked_bytes = tp->snd_una - ca->prior_snd_una; - - /* If ack did not advance snd_una, count dupack as MSS size. - * If ack did update window, do not count it at all. - */ - if (acked_bytes == 0 && !(flags & CA_ACK_WIN_UPDATE)) - acked_bytes = inet_csk(sk)->icsk_ack.rcv_mss; - if (acked_bytes) { - ca->acked_bytes_total += acked_bytes; - ca->prior_snd_una = tp->snd_una; - - if (flags & CA_ACK_ECE) - ca->acked_bytes_ecn += acked_bytes; - } /* Expired RTT */ if (!before(tp->snd_una, ca->next_seq)) { - u64 bytes_ecn = ca->acked_bytes_ecn; + u32 delivered_ce = tp->delivered_ce - ca->old_delivered_ce; u32 alpha = ca->dctcp_alpha; /* alpha = (1 - g) * alpha + g * F */ alpha -= min_not_zero(alpha, alpha >> dctcp_shift_g); - if (bytes_ecn) { + if (delivered_ce) { + u32 delivered = tp->delivered - ca->old_delivered; + /* If dctcp_shift_g == 1, a 32bit value would overflow - * after 8 Mbytes. + * after 8 M packets. */ - bytes_ecn <<= (10 - dctcp_shift_g); - do_div(bytes_ecn, max(1U, ca->acked_bytes_total)); + delivered_ce <<= (10 - dctcp_shift_g); + delivered_ce /= max(1U, delivered); - alpha = min(alpha + (u32)bytes_ecn, DCTCP_MAX_ALPHA); + alpha = min(alpha + delivered_ce, DCTCP_MAX_ALPHA); } /* dctcp_alpha can be read from dctcp_get_info() without * synchro, so we ask compiler to not use dctcp_alpha @@ -164,21 +145,23 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags) } } -static void dctcp_state(struct sock *sk, u8 new_state) +static void dctcp_react_to_loss(struct sock *sk) { - if (dctcp_clamp_alpha_on_loss && new_state == TCP_CA_Loss) { - struct dctcp *ca = inet_csk_ca(sk); + struct dctcp *ca = inet_csk_ca(sk); + struct tcp_sock *tp = tcp_sk(sk); - /* If this extension is enabled, we clamp dctcp_alpha to - * max on packet loss; the motivation is that dctcp_alpha - * is an indicator to the extend of congestion and packet - * loss is an indicator of extreme congestion; setting - * this in practice turned out to be beneficial, and - * effectively assumes total congestion which reduces the - * window by half. - */ - ca->dctcp_alpha = DCTCP_MAX_ALPHA; - } + ca->loss_cwnd = tp->snd_cwnd; + tp->snd_ssthresh = max(tp->snd_cwnd >> 1U, 2U); +} + +static void dctcp_state(struct sock *sk, u8 new_state) +{ + if (new_state == TCP_CA_Recovery && + new_state != inet_csk(sk)->icsk_ca_state) + dctcp_react_to_loss(sk); + /* We handle RTO in dctcp_cwnd_event to ensure that we perform only + * one loss-adjustment per RTT. + */ } static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev) @@ -190,6 +173,9 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev) case CA_EVENT_ECN_NO_CE: dctcp_ece_ack_update(sk, ev, &ca->prior_rcv_nxt, &ca->ce_state); break; + case CA_EVENT_LOSS: + dctcp_react_to_loss(sk); + break; default: /* Don't care for the rest. */ break; @@ -200,6 +186,7 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr, union tcp_cc_info *info) { const struct dctcp *ca = inet_csk_ca(sk); + const struct tcp_sock *tp = tcp_sk(sk); /* Fill it also in case of VEGASINFO due to req struct limits. * We can still correctly retrieve it later. @@ -211,8 +198,10 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr, info->dctcp.dctcp_enabled = 1; info->dctcp.dctcp_ce_state = (u16) ca->ce_state; info->dctcp.dctcp_alpha = ca->dctcp_alpha; - info->dctcp.dctcp_ab_ecn = ca->acked_bytes_ecn; - info->dctcp.dctcp_ab_tot = ca->acked_bytes_total; + info->dctcp.dctcp_ab_ecn = tp->mss_cache * + (tp->delivered_ce - ca->old_delivered_ce); + info->dctcp.dctcp_ab_tot = tp->mss_cache * + (tp->delivered - ca->old_delivered); } *attr = INET_DIAG_DCTCPINFO; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 5def3c48870e..731d3045b50a 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -402,11 +402,12 @@ static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb) static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); + int room; + + room = min_t(int, tp->window_clamp, tcp_space(sk)) - tp->rcv_ssthresh; /* Check #1 */ - if (tp->rcv_ssthresh < tp->window_clamp && - (int)tp->rcv_ssthresh < tcp_space(sk) && - !tcp_under_memory_pressure(sk)) { + if (room > 0 && !tcp_under_memory_pressure(sk)) { int incr; /* Check #2. Increase window, if skb with such overhead @@ -419,8 +420,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb) if (incr) { incr = max_t(int, incr, 2 * skb->len); - tp->rcv_ssthresh = min(tp->rcv_ssthresh + incr, - tp->window_clamp); + tp->rcv_ssthresh += min(room, incr); inet_csk(sk)->icsk_ack.quick |= 1; } } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 277d71239d75..a2896944aa37 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1673,7 +1673,9 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) if (TCP_SKB_CB(tail)->end_seq != TCP_SKB_CB(skb)->seq || TCP_SKB_CB(tail)->ip_dsfield != TCP_SKB_CB(skb)->ip_dsfield || ((TCP_SKB_CB(tail)->tcp_flags | - TCP_SKB_CB(skb)->tcp_flags) & TCPHDR_URG) || + TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_SYN | TCPHDR_RST | TCPHDR_URG)) || + !((TCP_SKB_CB(tail)->tcp_flags & + TCP_SKB_CB(skb)->tcp_flags) & TCPHDR_ACK) || ((TCP_SKB_CB(tail)->tcp_flags ^ TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_ECE | TCPHDR_CWR)) || #ifdef CONFIG_TLS_DEVICE @@ -1692,6 +1694,15 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) if (after(TCP_SKB_CB(skb)->ack_seq, TCP_SKB_CB(tail)->ack_seq)) TCP_SKB_CB(tail)->ack_seq = TCP_SKB_CB(skb)->ack_seq; + /* We have to update both TCP_SKB_CB(tail)->tcp_flags and + * thtail->fin, so that the fast path in tcp_rcv_established() + * is not entered if we append a packet with a FIN. + * SYN, RST, URG are not present. + * ACK is set on both packets. + * PSH : we do not really care in TCP stack, + * at least for 'GRO' packets. + */ + thtail->fin |= th->fin; TCP_SKB_CB(tail)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags; if (TCP_SKB_CB(skb)->has_rxtstamp) { @@ -2578,7 +2589,8 @@ static void __net_exit tcp_sk_exit(struct net *net) { int cpu; - module_put(net->ipv4.tcp_congestion_control->owner); + if (net->ipv4.tcp_congestion_control) + module_put(net->ipv4.tcp_congestion_control->owner); for_each_possible_cpu(cpu) inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu)); diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 64f9715173ac..065334b41d57 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -352,6 +352,7 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, struct sk_buff *pp = NULL; struct udphdr *uh2; struct sk_buff *p; + unsigned int ulen; /* requires non zero csum, for symmetry with GSO */ if (!uh->check) { @@ -359,6 +360,12 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, return NULL; } + /* Do not deal with padded or malicious packets, sorry ! */ + ulen = ntohs(uh->len); + if (ulen <= sizeof(*uh) || ulen != skb_gro_len(skb)) { + NAPI_GRO_CB(skb)->flush = 1; + return NULL; + } /* pull encapsulating udp header */ skb_gro_pull(skb, sizeof(struct udphdr)); skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr)); @@ -377,13 +384,14 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, /* Terminate the flow on len mismatch or if it grow "too much". * Under small packet flood GRO count could elsewhere grow a lot - * leading to execessive truesize values + * leading to excessive truesize values. + * On len mismatch merge the first packet shorter than gso_size, + * otherwise complete the GRO packet. */ - if (!skb_gro_receive(p, skb) && + if (ulen > ntohs(uh2->len) || skb_gro_receive(p, skb) || + ulen != ntohs(uh2->len) || NAPI_GRO_CB(p)->count >= UDP_GRO_CNT_MAX) pp = p; - else if (uh->len != uh2->len) - pp = p; return pp; } diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index d73a6d6652f6..2b144b92ae46 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -111,7 +111,8 @@ static void _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) { const struct iphdr *iph = ip_hdr(skb); - u8 *xprth = skb_network_header(skb) + iph->ihl * 4; + int ihl = iph->ihl; + u8 *xprth = skb_network_header(skb) + ihl * 4; struct flowi4 *fl4 = &fl->u.ip4; int oif = 0; @@ -122,6 +123,11 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) fl4->flowi4_mark = skb->mark; fl4->flowi4_oif = reverse ? skb->skb_iif : oif; + fl4->flowi4_proto = iph->protocol; + fl4->daddr = reverse ? iph->saddr : iph->daddr; + fl4->saddr = reverse ? iph->daddr : iph->saddr; + fl4->flowi4_tos = iph->tos; + if (!ip_is_fragment(iph)) { switch (iph->protocol) { case IPPROTO_UDP: @@ -133,7 +139,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) pskb_may_pull(skb, xprth + 4 - skb->data)) { __be16 *ports; - xprth = skb_network_header(skb) + iph->ihl * 4; + xprth = skb_network_header(skb) + ihl * 4; ports = (__be16 *)xprth; fl4->fl4_sport = ports[!!reverse]; @@ -146,7 +152,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) pskb_may_pull(skb, xprth + 2 - skb->data)) { u8 *icmp; - xprth = skb_network_header(skb) + iph->ihl * 4; + xprth = skb_network_header(skb) + ihl * 4; icmp = xprth; fl4->fl4_icmp_type = icmp[0]; @@ -159,7 +165,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) pskb_may_pull(skb, xprth + 4 - skb->data)) { __be32 *ehdr; - xprth = skb_network_header(skb) + iph->ihl * 4; + xprth = skb_network_header(skb) + ihl * 4; ehdr = (__be32 *)xprth; fl4->fl4_ipsec_spi = ehdr[0]; @@ -171,7 +177,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) pskb_may_pull(skb, xprth + 8 - skb->data)) { __be32 *ah_hdr; - xprth = skb_network_header(skb) + iph->ihl * 4; + xprth = skb_network_header(skb) + ihl * 4; ah_hdr = (__be32 *)xprth; fl4->fl4_ipsec_spi = ah_hdr[1]; @@ -183,7 +189,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) pskb_may_pull(skb, xprth + 4 - skb->data)) { __be16 *ipcomp_hdr; - xprth = skb_network_header(skb) + iph->ihl * 4; + xprth = skb_network_header(skb) + ihl * 4; ipcomp_hdr = (__be16 *)xprth; fl4->fl4_ipsec_spi = htonl(ntohs(ipcomp_hdr[1])); @@ -196,7 +202,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) __be16 *greflags; __be32 *gre_hdr; - xprth = skb_network_header(skb) + iph->ihl * 4; + xprth = skb_network_header(skb) + ihl * 4; greflags = (__be16 *)xprth; gre_hdr = (__be32 *)xprth; @@ -213,10 +219,6 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) break; } } - fl4->flowi4_proto = iph->protocol; - fl4->daddr = reverse ? iph->saddr : iph->daddr; - fl4->saddr = reverse ? iph->daddr : iph->saddr; - fl4->flowi4_tos = iph->tos; } static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk, diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index d43d076c98f5..1766325423b5 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -476,7 +476,7 @@ static int ip6addrlbl_valid_dump_req(const struct nlmsghdr *nlh, } if (nlmsg_attrlen(nlh, sizeof(*ifal))) { - NL_SET_ERR_MSG_MOD(extack, "Invalid data after header for address label dump requewst"); + NL_SET_ERR_MSG_MOD(extack, "Invalid data after header for address label dump request"); return -EINVAL; } diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index d46b4eb645c2..cb99f6fb79b7 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -74,13 +74,13 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head, goto out; if (sp->len == XFRM_MAX_DEPTH) - goto out; + goto out_reset; x = xfrm_state_lookup(dev_net(skb->dev), skb->mark, (xfrm_address_t *)&ipv6_hdr(skb)->daddr, spi, IPPROTO_ESP, AF_INET6); if (!x) - goto out; + goto out_reset; sp->xvec[sp->len++] = x; sp->olen++; @@ -88,7 +88,7 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head, xo = xfrm_offload(skb); if (!xo) { xfrm_state_put(x); - goto out; + goto out_reset; } } @@ -109,6 +109,8 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head, xfrm_input(skb, IPPROTO_ESP, spi, -2); return ERR_PTR(-EINPROGRESS); +out_reset: + secpath_reset(skb); out: skb_push(skb, offset); NAPI_GRO_CB(skb)->same_flow = 0; diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index 79d2e43c05c5..5fc1f4e0c0cf 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -417,6 +417,7 @@ int ila_xlat_nl_cmd_flush(struct sk_buff *skb, struct genl_info *info) done: rhashtable_walk_stop(&iter); + rhashtable_walk_exit(&iter); return ret; } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 6613d8dbb0e5..91247a6fc67f 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -921,9 +921,7 @@ static void fib6_drop_pcpu_from(struct fib6_info *f6i, if (pcpu_rt) { struct fib6_info *from; - from = rcu_dereference_protected(pcpu_rt->from, - lockdep_is_held(&table->tb6_lock)); - rcu_assign_pointer(pcpu_rt->from, NULL); + from = xchg((__force struct fib6_info **)&pcpu_rt->from, NULL); fib6_info_release(from); } } diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index cb54a8a3c273..be5f3d7ceb96 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -94,15 +94,21 @@ static struct ip6_flowlabel *fl_lookup(struct net *net, __be32 label) return fl; } +static void fl_free_rcu(struct rcu_head *head) +{ + struct ip6_flowlabel *fl = container_of(head, struct ip6_flowlabel, rcu); + + if (fl->share == IPV6_FL_S_PROCESS) + put_pid(fl->owner.pid); + kfree(fl->opt); + kfree(fl); +} + static void fl_free(struct ip6_flowlabel *fl) { - if (fl) { - if (fl->share == IPV6_FL_S_PROCESS) - put_pid(fl->owner.pid); - kfree(fl->opt); - kfree_rcu(fl, rcu); - } + if (fl) + call_rcu(&fl->rcu, fl_free_rcu); } static void fl_release(struct ip6_flowlabel *fl) @@ -633,9 +639,9 @@ recheck: if (fl1->share == IPV6_FL_S_EXCL || fl1->share != fl->share || ((fl1->share == IPV6_FL_S_PROCESS) && - (fl1->owner.pid == fl->owner.pid)) || + (fl1->owner.pid != fl->owner.pid)) || ((fl1->share == IPV6_FL_S_USER) && - uid_eq(fl1->owner.uid, fl->owner.uid))) + !uid_eq(fl1->owner.uid, fl->owner.uid))) goto release; err = -ENOMEM; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index b32c95f02128..655e46b227f9 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -525,10 +525,10 @@ static int ip6gre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi) } static int ip6erspan_rcv(struct sk_buff *skb, - struct tnl_ptk_info *tpi) + struct tnl_ptk_info *tpi, + int gre_hdr_len) { struct erspan_base_hdr *ershdr; - struct erspan_metadata *pkt_md; const struct ipv6hdr *ipv6h; struct erspan_md2 *md2; struct ip6_tnl *tunnel; @@ -547,18 +547,16 @@ static int ip6erspan_rcv(struct sk_buff *skb, if (unlikely(!pskb_may_pull(skb, len))) return PACKET_REJECT; - ershdr = (struct erspan_base_hdr *)skb->data; - pkt_md = (struct erspan_metadata *)(ershdr + 1); - if (__iptunnel_pull_header(skb, len, htons(ETH_P_TEB), false, false) < 0) return PACKET_REJECT; if (tunnel->parms.collect_md) { + struct erspan_metadata *pkt_md, *md; struct metadata_dst *tun_dst; struct ip_tunnel_info *info; - struct erspan_metadata *md; + unsigned char *gh; __be64 tun_id; __be16 flags; @@ -571,6 +569,14 @@ static int ip6erspan_rcv(struct sk_buff *skb, if (!tun_dst) return PACKET_REJECT; + /* skb can be uncloned in __iptunnel_pull_header, so + * old pkt_md is no longer valid and we need to reset + * it + */ + gh = skb_network_header(skb) + + skb_network_header_len(skb); + pkt_md = (struct erspan_metadata *)(gh + gre_hdr_len + + sizeof(*ershdr)); info = &tun_dst->u.tun_info; md = ip_tunnel_info_opts(info); md->version = ver; @@ -607,7 +613,7 @@ static int gre_rcv(struct sk_buff *skb) if (unlikely(tpi.proto == htons(ETH_P_ERSPAN) || tpi.proto == htons(ETH_P_ERSPAN2))) { - if (ip6erspan_rcv(skb, &tpi) == PACKET_RCVD) + if (ip6erspan_rcv(skb, &tpi, hdr_len) == PACKET_RCVD) return 0; goto out; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index edbd12067170..e51f3c648b09 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -601,7 +601,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, inet6_sk(skb->sk) : NULL; struct ipv6hdr *tmp_hdr; struct frag_hdr *fh; - unsigned int mtu, hlen, left, len; + unsigned int mtu, hlen, left, len, nexthdr_offset; int hroom, troom; __be32 frag_id; int ptr, offset = 0, err = 0; @@ -612,6 +612,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, goto fail; hlen = err; nexthdr = *prevhdr; + nexthdr_offset = prevhdr - skb_network_header(skb); mtu = ip6_skb_dst_mtu(skb); @@ -646,6 +647,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, (err = skb_checksum_help(skb))) goto fail; + prevhdr = skb_network_header(skb) + nexthdr_offset; hroom = LL_RESERVED_SPACE(rt->dst.dev); if (skb_has_frag_list(skb)) { unsigned int first_len = skb_pagelen(skb); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 0c6403cf8b52..ade1390c6348 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -627,7 +627,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, eiph->daddr, eiph->saddr, 0, 0, IPPROTO_IPIP, RT_TOS(eiph->tos), 0); - if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL) { + if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL6) { if (!IS_ERR(rt)) ip_rt_put(rt); goto out; @@ -636,7 +636,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } else { if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos, skb2->dev) || - skb_dst(skb2)->dev->type != ARPHRD_TUNNEL) + skb_dst(skb2)->dev->type != ARPHRD_TUNNEL6) goto out; } diff --git a/net/ipv6/netfilter/ip6t_srh.c b/net/ipv6/netfilter/ip6t_srh.c index 1059894a6f4c..4cb83fb69844 100644 --- a/net/ipv6/netfilter/ip6t_srh.c +++ b/net/ipv6/netfilter/ip6t_srh.c @@ -210,6 +210,8 @@ static bool srh1_mt6(const struct sk_buff *skb, struct xt_action_param *par) psidoff = srhoff + sizeof(struct ipv6_sr_hdr) + ((srh->segments_left + 1) * sizeof(struct in6_addr)); psid = skb_header_pointer(skb, psidoff, sizeof(_psid), &_psid); + if (!psid) + return false; if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_PSID, ipv6_masked_addr_cmp(psid, &srhinfo->psid_msk, &srhinfo->psid_addr))) @@ -223,6 +225,8 @@ static bool srh1_mt6(const struct sk_buff *skb, struct xt_action_param *par) nsidoff = srhoff + sizeof(struct ipv6_sr_hdr) + ((srh->segments_left - 1) * sizeof(struct in6_addr)); nsid = skb_header_pointer(skb, nsidoff, sizeof(_nsid), &_nsid); + if (!nsid) + return false; if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_NSID, ipv6_masked_addr_cmp(nsid, &srhinfo->nsid_msk, &srhinfo->nsid_addr))) @@ -233,6 +237,8 @@ static bool srh1_mt6(const struct sk_buff *skb, struct xt_action_param *par) if (srhinfo->mt_flags & IP6T_SRH_LSID) { lsidoff = srhoff + sizeof(struct ipv6_sr_hdr); lsid = skb_header_pointer(skb, lsidoff, sizeof(_lsid), &_lsid); + if (!lsid) + return false; if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LSID, ipv6_masked_addr_cmp(lsid, &srhinfo->lsid_msk, &srhinfo->lsid_addr))) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 4ef4bbdb49d4..0520aca3354b 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -379,11 +379,8 @@ static void ip6_dst_destroy(struct dst_entry *dst) in6_dev_put(idev); } - rcu_read_lock(); - from = rcu_dereference(rt->from); - rcu_assign_pointer(rt->from, NULL); + from = xchg((__force struct fib6_info **)&rt->from, NULL); fib6_info_release(from); - rcu_read_unlock(); } static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, @@ -1040,14 +1037,20 @@ static struct rt6_info *ip6_create_rt_rcu(struct fib6_info *rt) struct rt6_info *nrt; if (!fib6_info_hold_safe(rt)) - return NULL; + goto fallback; nrt = ip6_dst_alloc(dev_net(dev), dev, flags); - if (nrt) - ip6_rt_copy_init(nrt, rt); - else + if (!nrt) { fib6_info_release(rt); + goto fallback; + } + + ip6_rt_copy_init(nrt, rt); + return nrt; +fallback: + nrt = dev_net(dev)->ipv6.ip6_null_entry; + dst_hold(&nrt->dst); return nrt; } @@ -1096,10 +1099,6 @@ restart: dst_hold(&rt->dst); } else { rt = ip6_create_rt_rcu(f6i); - if (!rt) { - rt = net->ipv6.ip6_null_entry; - dst_hold(&rt->dst); - } } rcu_read_unlock(); @@ -1286,9 +1285,7 @@ static void rt6_remove_exception(struct rt6_exception_bucket *bucket, /* purge completely the exception to allow releasing the held resources: * some [sk] cache may keep the dst around for unlimited time */ - from = rcu_dereference_protected(rt6_ex->rt6i->from, - lockdep_is_held(&rt6_exception_lock)); - rcu_assign_pointer(rt6_ex->rt6i->from, NULL); + from = xchg((__force struct fib6_info **)&rt6_ex->rt6i->from, NULL); fib6_info_release(from); dst_dev_put(&rt6_ex->rt6i->dst); @@ -2328,6 +2325,10 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, rcu_read_lock(); from = rcu_dereference(rt6->from); + if (!from) { + rcu_read_unlock(); + return; + } nrt6 = ip6_rt_cache_alloc(from, daddr, saddr); if (nrt6) { rt6_do_update_pmtu(nrt6, mtu); @@ -3391,11 +3392,8 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu rcu_read_lock(); from = rcu_dereference(rt->from); - /* This fib6_info_hold() is safe here because we hold reference to rt - * and rt already holds reference to fib6_info. - */ - fib6_info_hold(from); - rcu_read_unlock(); + if (!from) + goto out; nrt = ip6_rt_cache_alloc(from, &msg->dest, NULL); if (!nrt) @@ -3407,10 +3405,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key; - /* No need to remove rt from the exception table if rt is - * a cached route because rt6_insert_exception() will - * takes care of it - */ + /* rt6_insert_exception() will take care of duplicated exceptions */ if (rt6_insert_exception(nrt, from)) { dst_release_immediate(&nrt->dst); goto out; @@ -3423,7 +3418,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu call_netevent_notifiers(NETEVENT_REDIRECT, &netevent); out: - fib6_info_release(from); + rcu_read_unlock(); neigh_release(neigh); } @@ -3662,23 +3657,34 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg) static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes) { - int type; struct dst_entry *dst = skb_dst(skb); + struct net *net = dev_net(dst->dev); + struct inet6_dev *idev; + int type; + + if (netif_is_l3_master(skb->dev) && + dst->dev == net->loopback_dev) + idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif)); + else + idev = ip6_dst_idev(dst); + switch (ipstats_mib_noroutes) { case IPSTATS_MIB_INNOROUTES: type = ipv6_addr_type(&ipv6_hdr(skb)->daddr); if (type == IPV6_ADDR_ANY) { - IP6_INC_STATS(dev_net(dst->dev), - __in6_dev_get_safely(skb->dev), - IPSTATS_MIB_INADDRERRORS); + IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); break; } /* FALLTHROUGH */ case IPSTATS_MIB_OUTNOROUTES: - IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst), - ipstats_mib_noroutes); + IP6_INC_STATS(net, idev, ipstats_mib_noroutes); break; } + + /* Start over by dropping the dst for l3mdev case */ + if (netif_is_l3_master(skb->dev)) + skb_dst_drop(skb); + icmpv6_send(skb, ICMPV6_DEST_UNREACH, code, 0); kfree_skb(skb); return 0; @@ -5011,16 +5017,20 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, rcu_read_lock(); from = rcu_dereference(rt->from); - - if (fibmatch) - err = rt6_fill_node(net, skb, from, NULL, NULL, NULL, iif, - RTM_NEWROUTE, NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, 0); - else - err = rt6_fill_node(net, skb, from, dst, &fl6.daddr, - &fl6.saddr, iif, RTM_NEWROUTE, - NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, - 0); + if (from) { + if (fibmatch) + err = rt6_fill_node(net, skb, from, NULL, NULL, NULL, + iif, RTM_NEWROUTE, + NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, 0); + else + err = rt6_fill_node(net, skb, from, dst, &fl6.daddr, + &fl6.saddr, iif, RTM_NEWROUTE, + NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, 0); + } else { + err = -ENETUNREACH; + } rcu_read_unlock(); if (err < 0) { diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 07e21a82ce4c..b2109b74857d 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -669,6 +669,10 @@ static int ipip6_rcv(struct sk_buff *skb) !net_eq(tunnel->net, dev_net(tunnel->dev)))) goto out; + /* skb can be uncloned in iptunnel_pull_header, so + * old iph is no longer valid + */ + iph = (const struct iphdr *)skb_mac_header(skb); err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { if (log_ecn_error) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 57ef69a10889..44d431849d39 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1110,11 +1110,11 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * newnp->ipv6_fl_list = NULL; newnp->pktoptions = NULL; newnp->opt = NULL; - newnp->mcast_oif = tcp_v6_iif(skb); - newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; - newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb)); + newnp->mcast_oif = inet_iif(skb); + newnp->mcast_hops = ip_hdr(skb)->ttl; + newnp->rcv_flowinfo = 0; if (np->repflow) - newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb)); + newnp->flow_label = 0; /* * No need to charge this sock to the relevant IPv6 refcnt debug socks count diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index b444483cdb2b..622eeaf5732b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1047,6 +1047,8 @@ static void udp_v6_flush_pending_frames(struct sock *sk) static int udpv6_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { + if (addr_len < offsetofend(struct sockaddr, sa_family)) + return -EINVAL; /* The following checks are replicated from __ip6_datagram_connect() * and intended to prevent BPF program called below from accessing * bytes that are out of the bound specified by user in addr_len. diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index bc65db782bfb..d9e5f6808811 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -345,7 +345,7 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net) unsigned int i; xfrm_flush_gc(); - xfrm_state_flush(net, IPSEC_PROTO_ANY, false, true); + xfrm_state_flush(net, 0, false, true); for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byaddr[i])); @@ -402,6 +402,10 @@ static void __exit xfrm6_tunnel_fini(void) xfrm6_tunnel_deregister(&xfrm6_tunnel_handler, AF_INET6); xfrm_unregister_type(&xfrm6_tunnel_type, AF_INET6); unregister_pernet_subsys(&xfrm6_tunnel_net_ops); + /* Someone maybe has gotten the xfrm6_tunnel_spi. + * So need to wait it. + */ + rcu_barrier(); kmem_cache_destroy(xfrm6_tunnel_spi_kmem); } diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index c5c5ab6c5a1c..44fdc641710d 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -2054,14 +2054,14 @@ static int __init kcm_init(void) if (err) goto fail; - err = sock_register(&kcm_family_ops); - if (err) - goto sock_register_fail; - err = register_pernet_device(&kcm_net_ops); if (err) goto net_ops_fail; + err = sock_register(&kcm_family_ops); + if (err) + goto sock_register_fail; + err = kcm_proc_init(); if (err) goto proc_init_fail; @@ -2069,12 +2069,12 @@ static int __init kcm_init(void) return 0; proc_init_fail: - unregister_pernet_device(&kcm_net_ops); - -net_ops_fail: sock_unregister(PF_KCM); sock_register_fail: + unregister_pernet_device(&kcm_net_ops); + +net_ops_fail: proto_unregister(&kcm_proto); fail: @@ -2090,8 +2090,8 @@ fail: static void __exit kcm_exit(void) { kcm_proc_exit(); - unregister_pernet_device(&kcm_net_ops); sock_unregister(PF_KCM); + unregister_pernet_device(&kcm_net_ops); proto_unregister(&kcm_proto); destroy_workqueue(kcm_wq); diff --git a/net/key/af_key.c b/net/key/af_key.c index 5651c29cb5bd..4af1e1d60b9f 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1951,8 +1951,10 @@ parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_ipsecrequest *rq) if (rq->sadb_x_ipsecrequest_mode == 0) return -EINVAL; + if (!xfrm_id_proto_valid(rq->sadb_x_ipsecrequest_proto)) + return -EINVAL; - t->id.proto = rq->sadb_x_ipsecrequest_proto; /* XXX check proto */ + t->id.proto = rq->sadb_x_ipsecrequest_proto; if ((mode = pfkey_mode_to_xfrm(rq->sadb_x_ipsecrequest_mode)) < 0) return -EINVAL; t->mode = mode; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index fed6becc5daf..52b5a2797c0c 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -169,8 +169,8 @@ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id) rcu_read_lock_bh(); list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) { - if (tunnel->tunnel_id == tunnel_id) { - l2tp_tunnel_inc_refcount(tunnel); + if (tunnel->tunnel_id == tunnel_id && + refcount_inc_not_zero(&tunnel->ref_count)) { rcu_read_unlock_bh(); return tunnel; @@ -190,8 +190,8 @@ struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth) rcu_read_lock_bh(); list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) { - if (++count > nth) { - l2tp_tunnel_inc_refcount(tunnel); + if (++count > nth && + refcount_inc_not_zero(&tunnel->ref_count)) { rcu_read_unlock_bh(); return tunnel; } @@ -909,7 +909,7 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct l2tp_tunnel *tunnel; - tunnel = l2tp_tunnel(sk); + tunnel = rcu_dereference_sk_user_data(sk); if (tunnel == NULL) goto pass_up; diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index b99e73a7e7e0..2017b7d780f5 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -320,14 +320,13 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) struct llc_sap *sap; int rc = -EINVAL; - dprintk("%s: binding %02X\n", __func__, addr->sllc_sap); - lock_sock(sk); if (unlikely(!sock_flag(sk, SOCK_ZAPPED) || addrlen != sizeof(*addr))) goto out; rc = -EAFNOSUPPORT; if (unlikely(addr->sllc_family != AF_LLC)) goto out; + dprintk("%s: binding %02X\n", __func__, addr->sllc_sap); rc = -ENODEV; rcu_read_lock(); if (sk->sk_bound_dev_if) { diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index cff0fb3578c9..deb3faf08337 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -841,7 +841,7 @@ void ieee80211_debugfs_rename_netdev(struct ieee80211_sub_if_data *sdata) dir = sdata->vif.debugfs_dir; - if (!dir) + if (IS_ERR_OR_NULL(dir)) return; sprintf(buf, "netdev:%s", sdata->name); diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 28d022a3eee3..ae4f0be3b393 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -1195,6 +1195,9 @@ static inline void drv_wake_tx_queue(struct ieee80211_local *local, { struct ieee80211_sub_if_data *sdata = vif_to_sdata(txq->txq.vif); + if (local->in_reconfig) + return; + if (!check_sdata_in_driver(sdata)) return; diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index e03c46ac8e4d..c62101857b9b 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -112,8 +112,9 @@ void ieee80211_apply_htcap_overrides(struct ieee80211_sub_if_data *sdata, IEEE80211_HT_CAP_TX_STBC); /* Allow user to configure RX STBC bits */ - if (ht_capa_mask->cap_info & IEEE80211_HT_CAP_RX_STBC) - ht_cap->cap |= ht_capa->cap_info & IEEE80211_HT_CAP_RX_STBC; + if (ht_capa_mask->cap_info & cpu_to_le16(IEEE80211_HT_CAP_RX_STBC)) + ht_cap->cap |= le16_to_cpu(ht_capa->cap_info) & + IEEE80211_HT_CAP_RX_STBC; /* Allow user to decrease AMPDU factor */ if (ht_capa_mask->ampdu_params_info & diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 4a6ff1482a9f..02d2e6f11e93 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1908,6 +1908,9 @@ void ieee80211_if_remove(struct ieee80211_sub_if_data *sdata) list_del_rcu(&sdata->list); mutex_unlock(&sdata->local->iflist_mtx); + if (sdata->vif.txq) + ieee80211_txq_purge(sdata->local, to_txq_info(sdata->vif.txq)); + synchronize_rcu(); if (sdata->dev) { diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 4700718e010f..37e372896230 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -167,8 +167,10 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) * The driver doesn't know anything about VLAN interfaces. * Hence, don't send GTKs for VLAN interfaces to the driver. */ - if (!(key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE)) + if (!(key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE)) { + ret = 1; goto out_unsupported; + } } ret = drv_set_key(key->local, SET_KEY, sdata, @@ -213,11 +215,8 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) /* all of these we can do in software - if driver can */ if (ret == 1) return 0; - if (ieee80211_hw_check(&key->local->hw, SW_CRYPTO_CONTROL)) { - if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) - return 0; + if (ieee80211_hw_check(&key->local->hw, SW_CRYPTO_CONTROL)) return -EINVAL; - } return 0; default: return -EINVAL; diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 95eb5064fa91..b76a2aefa9ec 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -23,7 +23,7 @@ static void mesh_path_free_rcu(struct mesh_table *tbl, struct mesh_path *mpath); static u32 mesh_table_hash(const void *addr, u32 len, u32 seed) { /* Use last four bytes of hw addr as hash index */ - return jhash_1word(*(u32 *)(addr+2), seed); + return jhash_1word(__get_unaligned_cpu32((u8 *)addr + 2), seed); } static const struct rhashtable_params mesh_rht_params = { diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 7f8d93401ce0..bf0b187f994e 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1568,7 +1568,15 @@ static void sta_ps_start(struct sta_info *sta) return; for (tid = 0; tid < IEEE80211_NUM_TIDS; tid++) { - if (txq_has_queue(sta->sta.txq[tid])) + struct ieee80211_txq *txq = sta->sta.txq[tid]; + struct txq_info *txqi = to_txq_info(txq); + + spin_lock(&local->active_txq_lock[txq->ac]); + if (!list_empty(&txqi->schedule_order)) + list_del_init(&txqi->schedule_order); + spin_unlock(&local->active_txq_lock[txq->ac]); + + if (txq_has_queue(txq)) set_bit(tid, &sta->txq_buffered_tids); else clear_bit(tid, &sta->txq_buffered_tids); diff --git a/net/mac80211/trace_msg.h b/net/mac80211/trace_msg.h index 366b9e6f043e..40141df09f25 100644 --- a/net/mac80211/trace_msg.h +++ b/net/mac80211/trace_msg.h @@ -1,4 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0 */ +/* + * Portions of this file + * Copyright (C) 2019 Intel Corporation + */ + #ifdef CONFIG_MAC80211_MESSAGE_TRACING #if !defined(__MAC80211_MSG_DRIVER_TRACE) || defined(TRACE_HEADER_MULTI_READ) @@ -11,7 +16,7 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM mac80211_msg -#define MAX_MSG_LEN 100 +#define MAX_MSG_LEN 120 DECLARE_EVENT_CLASS(mac80211_msg_event, TP_PROTO(struct va_format *vaf), diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 8a49a74c0a37..2e816dd67be7 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -3221,6 +3221,7 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, u8 max_subframes = sta->sta.max_amsdu_subframes; int max_frags = local->hw.max_tx_fragments; int max_amsdu_len = sta->sta.max_amsdu_len; + int orig_truesize; __be16 len; void *data; bool ret = false; @@ -3261,6 +3262,7 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, if (!head || skb_is_gso(head)) goto out; + orig_truesize = head->truesize; orig_len = head->len; if (skb->len + head->len > max_amsdu_len) @@ -3318,6 +3320,7 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, *frag_tail = skb; out_recalc: + fq->memory_usage += head->truesize - orig_truesize; if (head->len != orig_len) { flow->backlog += head->len - orig_len; tin->backlog_bytes += head->len - orig_len; @@ -3646,16 +3649,17 @@ EXPORT_SYMBOL(ieee80211_tx_dequeue); struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac) { struct ieee80211_local *local = hw_to_local(hw); + struct ieee80211_txq *ret = NULL; struct txq_info *txqi = NULL; - lockdep_assert_held(&local->active_txq_lock[ac]); + spin_lock_bh(&local->active_txq_lock[ac]); begin: txqi = list_first_entry_or_null(&local->active_txqs[ac], struct txq_info, schedule_order); if (!txqi) - return NULL; + goto out; if (txqi->txq.sta) { struct sta_info *sta = container_of(txqi->txq.sta, @@ -3672,24 +3676,30 @@ struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac) if (txqi->schedule_round == local->schedule_round[ac]) - return NULL; + goto out; list_del_init(&txqi->schedule_order); txqi->schedule_round = local->schedule_round[ac]; - return &txqi->txq; + ret = &txqi->txq; + +out: + spin_unlock_bh(&local->active_txq_lock[ac]); + return ret; } EXPORT_SYMBOL(ieee80211_next_txq); -void ieee80211_return_txq(struct ieee80211_hw *hw, - struct ieee80211_txq *txq) +void __ieee80211_schedule_txq(struct ieee80211_hw *hw, + struct ieee80211_txq *txq, + bool force) { struct ieee80211_local *local = hw_to_local(hw); struct txq_info *txqi = to_txq_info(txq); - lockdep_assert_held(&local->active_txq_lock[txq->ac]); + spin_lock_bh(&local->active_txq_lock[txq->ac]); if (list_empty(&txqi->schedule_order) && - (!skb_queue_empty(&txqi->frags) || txqi->tin.backlog_packets)) { + (force || !skb_queue_empty(&txqi->frags) || + txqi->tin.backlog_packets)) { /* If airtime accounting is active, always enqueue STAs at the * head of the list to ensure that they only get moved to the * back by the airtime DRR scheduler once they have a negative @@ -3706,20 +3716,10 @@ void ieee80211_return_txq(struct ieee80211_hw *hw, list_add_tail(&txqi->schedule_order, &local->active_txqs[txq->ac]); } -} -EXPORT_SYMBOL(ieee80211_return_txq); -void ieee80211_schedule_txq(struct ieee80211_hw *hw, - struct ieee80211_txq *txq) - __acquires(txq_lock) __releases(txq_lock) -{ - struct ieee80211_local *local = hw_to_local(hw); - - spin_lock_bh(&local->active_txq_lock[txq->ac]); - ieee80211_return_txq(hw, txq); spin_unlock_bh(&local->active_txq_lock[txq->ac]); } -EXPORT_SYMBOL(ieee80211_schedule_txq); +EXPORT_SYMBOL(__ieee80211_schedule_txq); bool ieee80211_txq_may_transmit(struct ieee80211_hw *hw, struct ieee80211_txq *txq) @@ -3729,7 +3729,7 @@ bool ieee80211_txq_may_transmit(struct ieee80211_hw *hw, struct sta_info *sta; u8 ac = txq->ac; - lockdep_assert_held(&local->active_txq_lock[ac]); + spin_lock_bh(&local->active_txq_lock[ac]); if (!txqi->txq.sta) goto out; @@ -3759,34 +3759,27 @@ bool ieee80211_txq_may_transmit(struct ieee80211_hw *hw, sta->airtime[ac].deficit += sta->airtime_weight; list_move_tail(&txqi->schedule_order, &local->active_txqs[ac]); + spin_unlock_bh(&local->active_txq_lock[ac]); return false; out: if (!list_empty(&txqi->schedule_order)) list_del_init(&txqi->schedule_order); + spin_unlock_bh(&local->active_txq_lock[ac]); return true; } EXPORT_SYMBOL(ieee80211_txq_may_transmit); void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac) - __acquires(txq_lock) { struct ieee80211_local *local = hw_to_local(hw); spin_lock_bh(&local->active_txq_lock[ac]); local->schedule_round[ac]++; -} -EXPORT_SYMBOL(ieee80211_txq_schedule_start); - -void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac) - __releases(txq_lock) -{ - struct ieee80211_local *local = hw_to_local(hw); - spin_unlock_bh(&local->active_txq_lock[ac]); } -EXPORT_SYMBOL(ieee80211_txq_schedule_end); +EXPORT_SYMBOL(ieee80211_txq_schedule_start); void __ieee80211_subif_start_xmit(struct sk_buff *skb, struct net_device *dev, diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index dda8930f20e7..f3a8557494d6 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -140,9 +140,15 @@ static int mpls_xmit(struct sk_buff *skb) if (rt) err = neigh_xmit(NEIGH_ARP_TABLE, out_dev, &rt->rt_gateway, skb); - else if (rt6) - err = neigh_xmit(NEIGH_ND_TABLE, out_dev, &rt6->rt6i_gateway, - skb); + else if (rt6) { + if (ipv6_addr_v4mapped(&rt6->rt6i_gateway)) { + /* 6PE (RFC 4798) */ + err = neigh_xmit(NEIGH_ARP_TABLE, out_dev, &rt6->rt6i_gateway.s6_addr32[3], + skb); + } else + err = neigh_xmit(NEIGH_ND_TABLE, out_dev, &rt6->rt6i_gateway, + skb); + } if (err) net_dbg_ratelimited("%s: packet transmission failed: %d\n", __func__, err); diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c index 5d782445d2fc..bad17bba8ba7 100644 --- a/net/ncsi/ncsi-netlink.c +++ b/net/ncsi/ncsi-netlink.c @@ -251,6 +251,10 @@ static int ncsi_pkg_info_all_nl(struct sk_buff *skb, } attr = nla_nest_start(skb, NCSI_ATTR_PACKAGE_LIST); + if (!attr) { + rc = -EMSGSIZE; + goto err; + } rc = ncsi_write_package_info(skb, ndp, package->id); if (rc) { nla_nest_cancel(skb, attr); diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index dc07fcc7938e..802db01e3075 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -11,6 +11,7 @@ #include <linux/kernel.h> #include <linux/init.h> #include <linux/netdevice.h> +#include <linux/etherdevice.h> #include <linux/skbuff.h> #include <net/ncsi.h> @@ -667,7 +668,10 @@ static int ncsi_rsp_handler_oem_bcm_gma(struct ncsi_request *nr) 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 */ - saddr.sa_data[ETH_ALEN - 1]++; + eth_addr_inc((u8 *)saddr.sa_data); + if (!is_valid_ether_addr((const u8 *)saddr.sa_data)) + return -ENXIO; + ret = ops->ndo_set_mac_address(ndev, &saddr); if (ret < 0) netdev_warn(ndev, "NCSI: 'Writing mac address to device failed\n"); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index d43ffb09939b..6548271209a0 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -1007,6 +1007,7 @@ config NETFILTER_XT_TARGET_TEE depends on NETFILTER_ADVANCED depends on IPV6 || IPV6=n depends on !NF_CONNTRACK || NF_CONNTRACK + depends on IP6_NF_IPTABLES || !IP6_NF_IPTABLES select NF_DUP_IPV4 select NF_DUP_IPV6 if IP6_NF_IPTABLES ---help--- diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 43bbaa32b1d6..14457551bcb4 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1678,7 +1678,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, if (!cp) { int v; - if (!sysctl_schedule_icmp(ipvs)) + if (ipip || !sysctl_schedule_icmp(ipvs)) return NF_ACCEPT; if (!ip_vs_try_to_schedule(ipvs, AF_INET, skb, pd, &v, &cp, &ciph)) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 82bfbeef46af..2a714527cde1 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -25,6 +25,7 @@ #include <linux/slab.h> #include <linux/random.h> #include <linux/jhash.h> +#include <linux/siphash.h> #include <linux/err.h> #include <linux/percpu.h> #include <linux/moduleparam.h> @@ -449,6 +450,40 @@ nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse, } EXPORT_SYMBOL_GPL(nf_ct_invert_tuple); +/* Generate a almost-unique pseudo-id for a given conntrack. + * + * intentionally doesn't re-use any of the seeds used for hash + * table location, we assume id gets exposed to userspace. + * + * Following nf_conn items do not change throughout lifetime + * of the nf_conn after it has been committed to main hash table: + * + * 1. nf_conn address + * 2. nf_conn->ext address + * 3. nf_conn->master address (normally NULL) + * 4. tuple + * 5. the associated net namespace + */ +u32 nf_ct_get_id(const struct nf_conn *ct) +{ + static __read_mostly siphash_key_t ct_id_seed; + unsigned long a, b, c, d; + + net_get_random_once(&ct_id_seed, sizeof(ct_id_seed)); + + a = (unsigned long)ct; + b = (unsigned long)ct->master ^ net_hash_mix(nf_ct_net(ct)); + c = (unsigned long)ct->ext; + d = (unsigned long)siphash(&ct->tuplehash, sizeof(ct->tuplehash), + &ct_id_seed); +#ifdef CONFIG_64BIT + return siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &ct_id_seed); +#else + return siphash_4u32((u32)a, (u32)b, (u32)c, (u32)d, &ct_id_seed); +#endif +} +EXPORT_SYMBOL_GPL(nf_ct_get_id); + static void clean_from_lists(struct nf_conn *ct) { @@ -982,12 +1017,9 @@ __nf_conntrack_confirm(struct sk_buff *skb) /* set conntrack timestamp, if enabled. */ tstamp = nf_conn_tstamp_find(ct); - if (tstamp) { - if (skb->tstamp == 0) - __net_timestamp(skb); + if (tstamp) + tstamp->start = ktime_get_real_ns(); - tstamp->start = ktime_to_ns(skb->tstamp); - } /* Since the lookup is lockless, hash insertion must be done after * starting the timer and setting the CONFIRMED bit. The RCU barriers * guarantee that no other CPU can find the conntrack before the above @@ -1350,6 +1382,7 @@ __nf_conntrack_alloc(struct net *net, /* save hash for reusing when confirming */ *(unsigned long *)(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev) = hash; ct->status = 0; + ct->timeout = 0; write_pnet(&ct->ct_net, net); memset(&ct->__nfct_init_offset[0], 0, offsetof(struct nf_conn, proto) - diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 66c596d287a5..d7f61b0547c6 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -29,6 +29,7 @@ #include <linux/spinlock.h> #include <linux/interrupt.h> #include <linux/slab.h> +#include <linux/siphash.h> #include <linux/netfilter.h> #include <net/netlink.h> @@ -485,7 +486,9 @@ nla_put_failure: static int ctnetlink_dump_id(struct sk_buff *skb, const struct nf_conn *ct) { - if (nla_put_be32(skb, CTA_ID, htonl((unsigned long)ct))) + __be32 id = (__force __be32)nf_ct_get_id(ct); + + if (nla_put_be32(skb, CTA_ID, id)) goto nla_put_failure; return 0; @@ -1286,8 +1289,9 @@ static int ctnetlink_del_conntrack(struct net *net, struct sock *ctnl, } if (cda[CTA_ID]) { - u_int32_t id = ntohl(nla_get_be32(cda[CTA_ID])); - if (id != (u32)(unsigned long)ct) { + __be32 id = nla_get_be32(cda[CTA_ID]); + + if (id != (__force __be32)nf_ct_get_id(ct)) { nf_ct_put(ct); return -ENOENT; } @@ -2692,6 +2696,25 @@ nla_put_failure: static const union nf_inet_addr any_addr; +static __be32 nf_expect_get_id(const struct nf_conntrack_expect *exp) +{ + static __read_mostly siphash_key_t exp_id_seed; + unsigned long a, b, c, d; + + net_get_random_once(&exp_id_seed, sizeof(exp_id_seed)); + + a = (unsigned long)exp; + b = (unsigned long)exp->helper; + c = (unsigned long)exp->master; + d = (unsigned long)siphash(&exp->tuple, sizeof(exp->tuple), &exp_id_seed); + +#ifdef CONFIG_64BIT + return (__force __be32)siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &exp_id_seed); +#else + return (__force __be32)siphash_4u32((u32)a, (u32)b, (u32)c, (u32)d, &exp_id_seed); +#endif +} + static int ctnetlink_exp_dump_expect(struct sk_buff *skb, const struct nf_conntrack_expect *exp) @@ -2739,7 +2762,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, } #endif if (nla_put_be32(skb, CTA_EXPECT_TIMEOUT, htonl(timeout)) || - nla_put_be32(skb, CTA_EXPECT_ID, htonl((unsigned long)exp)) || + nla_put_be32(skb, CTA_EXPECT_ID, nf_expect_get_id(exp)) || nla_put_be32(skb, CTA_EXPECT_FLAGS, htonl(exp->flags)) || nla_put_be32(skb, CTA_EXPECT_CLASS, htonl(exp->class))) goto nla_put_failure; @@ -3044,7 +3067,8 @@ static int ctnetlink_get_expect(struct net *net, struct sock *ctnl, if (cda[CTA_EXPECT_ID]) { __be32 id = nla_get_be32(cda[CTA_EXPECT_ID]); - if (ntohl(id) != (u32)(unsigned long)exp) { + + if (id != nf_expect_get_id(exp)) { nf_ct_expect_put(exp); return -ENOENT; } diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index b9403a266a2e..37bb530d848f 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -55,7 +55,7 @@ void nf_l4proto_log_invalid(const struct sk_buff *skb, struct va_format vaf; va_list args; - if (net->ct.sysctl_log_invalid != protonum || + if (net->ct.sysctl_log_invalid != protonum && net->ct.sysctl_log_invalid != IPPROTO_RAW) return; diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c index 7df477996b16..9becac953587 100644 --- a/net/netfilter/nf_conntrack_proto_icmp.c +++ b/net/netfilter/nf_conntrack_proto_icmp.c @@ -103,49 +103,94 @@ int nf_conntrack_icmp_packet(struct nf_conn *ct, return NF_ACCEPT; } -/* Returns conntrack if it dealt with ICMP, and filled in skb fields */ -static int -icmp_error_message(struct nf_conn *tmpl, struct sk_buff *skb, - const struct nf_hook_state *state) +/* Check inner header is related to any of the existing connections */ +int nf_conntrack_inet_error(struct nf_conn *tmpl, struct sk_buff *skb, + unsigned int dataoff, + const struct nf_hook_state *state, + u8 l4proto, union nf_inet_addr *outer_daddr) { struct nf_conntrack_tuple innertuple, origtuple; const struct nf_conntrack_tuple_hash *h; const struct nf_conntrack_zone *zone; enum ip_conntrack_info ctinfo; struct nf_conntrack_zone tmp; + union nf_inet_addr *ct_daddr; + enum ip_conntrack_dir dir; + struct nf_conn *ct; WARN_ON(skb_nfct(skb)); zone = nf_ct_zone_tmpl(tmpl, skb, &tmp); /* Are they talking about one of our connections? */ - if (!nf_ct_get_tuplepr(skb, - skb_network_offset(skb) + ip_hdrlen(skb) - + sizeof(struct icmphdr), - PF_INET, state->net, &origtuple)) { - pr_debug("icmp_error_message: failed to get tuple\n"); + if (!nf_ct_get_tuplepr(skb, dataoff, + state->pf, state->net, &origtuple)) return -NF_ACCEPT; - } /* Ordinarily, we'd expect the inverted tupleproto, but it's been preserved inside the ICMP. */ - if (!nf_ct_invert_tuple(&innertuple, &origtuple)) { - pr_debug("icmp_error_message: no match\n"); + if (!nf_ct_invert_tuple(&innertuple, &origtuple)) return -NF_ACCEPT; - } - - ctinfo = IP_CT_RELATED; h = nf_conntrack_find_get(state->net, zone, &innertuple); - if (!h) { - pr_debug("icmp_error_message: no match\n"); + if (!h) + return -NF_ACCEPT; + + /* Consider: A -> T (=This machine) -> B + * Conntrack entry will look like this: + * Original: A->B + * Reply: B->T (SNAT case) OR A + * + * When this function runs, we got packet that looks like this: + * iphdr|icmphdr|inner_iphdr|l4header (tcp, udp, ..). + * + * Above nf_conntrack_find_get() makes lookup based on inner_hdr, + * so we should expect that destination of the found connection + * matches outer header destination address. + * + * In above example, we can consider these two cases: + * 1. Error coming in reply direction from B or M (middle box) to + * T (SNAT case) or A. + * Inner saddr will be B, dst will be T or A. + * The found conntrack will be reply tuple (B->T/A). + * 2. Error coming in original direction from A or M to B. + * Inner saddr will be A, inner daddr will be B. + * The found conntrack will be original tuple (A->B). + * + * In both cases, conntrack[dir].dst == inner.dst. + * + * A bogus packet could look like this: + * Inner: B->T + * Outer: B->X (other machine reachable by T). + * + * In this case, lookup yields connection A->B and will + * set packet from B->X as *RELATED*, even though no connection + * from X was ever seen. + */ + ct = nf_ct_tuplehash_to_ctrack(h); + dir = NF_CT_DIRECTION(h); + ct_daddr = &ct->tuplehash[dir].tuple.dst.u3; + if (!nf_inet_addr_cmp(outer_daddr, ct_daddr)) { + if (state->pf == AF_INET) { + nf_l4proto_log_invalid(skb, state->net, state->pf, + l4proto, + "outer daddr %pI4 != inner %pI4", + &outer_daddr->ip, &ct_daddr->ip); + } else if (state->pf == AF_INET6) { + nf_l4proto_log_invalid(skb, state->net, state->pf, + l4proto, + "outer daddr %pI6 != inner %pI6", + &outer_daddr->ip6, &ct_daddr->ip6); + } + nf_ct_put(ct); return -NF_ACCEPT; } - if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) + ctinfo = IP_CT_RELATED; + if (dir == IP_CT_DIR_REPLY) ctinfo += IP_CT_IS_REPLY; /* Update skb to refer to this connection */ - nf_ct_set(skb, nf_ct_tuplehash_to_ctrack(h), ctinfo); + nf_ct_set(skb, ct, ctinfo); return NF_ACCEPT; } @@ -162,11 +207,12 @@ int nf_conntrack_icmpv4_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state) { + union nf_inet_addr outer_daddr; const struct icmphdr *icmph; struct icmphdr _ih; /* Not enough header? */ - icmph = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_ih), &_ih); + icmph = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih); if (icmph == NULL) { icmp_error_log(skb, state, "short packet"); return -NF_ACCEPT; @@ -199,7 +245,12 @@ int nf_conntrack_icmpv4_error(struct nf_conn *tmpl, icmph->type != ICMP_REDIRECT) return NF_ACCEPT; - return icmp_error_message(tmpl, skb, state); + memset(&outer_daddr, 0, sizeof(outer_daddr)); + outer_daddr.ip = ip_hdr(skb)->daddr; + + dataoff += sizeof(*icmph); + return nf_conntrack_inet_error(tmpl, skb, dataoff, state, + IPPROTO_ICMP, &outer_daddr); } #if IS_ENABLED(CONFIG_NF_CT_NETLINK) diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c index bec4a3211658..c63ee3612855 100644 --- a/net/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -123,51 +123,6 @@ int nf_conntrack_icmpv6_packet(struct nf_conn *ct, return NF_ACCEPT; } -static int -icmpv6_error_message(struct net *net, struct nf_conn *tmpl, - struct sk_buff *skb, - unsigned int icmp6off) -{ - struct nf_conntrack_tuple intuple, origtuple; - const struct nf_conntrack_tuple_hash *h; - enum ip_conntrack_info ctinfo; - struct nf_conntrack_zone tmp; - - WARN_ON(skb_nfct(skb)); - - /* Are they talking about one of our connections? */ - if (!nf_ct_get_tuplepr(skb, - skb_network_offset(skb) - + sizeof(struct ipv6hdr) - + sizeof(struct icmp6hdr), - PF_INET6, net, &origtuple)) { - pr_debug("icmpv6_error: Can't get tuple\n"); - return -NF_ACCEPT; - } - - /* Ordinarily, we'd expect the inverted tupleproto, but it's - been preserved inside the ICMP. */ - if (!nf_ct_invert_tuple(&intuple, &origtuple)) { - pr_debug("icmpv6_error: Can't invert tuple\n"); - return -NF_ACCEPT; - } - - ctinfo = IP_CT_RELATED; - - h = nf_conntrack_find_get(net, nf_ct_zone_tmpl(tmpl, skb, &tmp), - &intuple); - if (!h) { - pr_debug("icmpv6_error: no match\n"); - return -NF_ACCEPT; - } else { - if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) - ctinfo += IP_CT_IS_REPLY; - } - - /* Update skb to refer to this connection */ - nf_ct_set(skb, nf_ct_tuplehash_to_ctrack(h), ctinfo); - return NF_ACCEPT; -} static void icmpv6_error_log(const struct sk_buff *skb, const struct nf_hook_state *state, @@ -182,6 +137,7 @@ int nf_conntrack_icmpv6_error(struct nf_conn *tmpl, unsigned int dataoff, const struct nf_hook_state *state) { + union nf_inet_addr outer_daddr; const struct icmp6hdr *icmp6h; struct icmp6hdr _ih; int type; @@ -210,7 +166,11 @@ int nf_conntrack_icmpv6_error(struct nf_conn *tmpl, if (icmp6h->icmp6_type >= 128) return NF_ACCEPT; - return icmpv6_error_message(state->net, tmpl, skb, dataoff); + memcpy(&outer_daddr.ip6, &ipv6_hdr(skb)->daddr, + sizeof(outer_daddr.ip6)); + dataoff += sizeof(*icmp6h); + return nf_conntrack_inet_error(tmpl, skb, dataoff, state, + IPPROTO_ICMPV6, &outer_daddr); } #if IS_ENABLED(CONFIG_NF_CT_NETLINK) diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index f067c6b50857..39fcc1ed18f3 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -20,9 +20,9 @@ #include <linux/udp.h> #include <linux/tcp.h> #include <linux/netfilter.h> +#include <linux/netfilter_ipv4.h> +#include <linux/netfilter_ipv6.h> -#include <net/route.h> -#include <net/ip6_route.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_expect.h> @@ -871,38 +871,33 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff, } else if (sip_external_media) { struct net_device *dev = skb_dst(skb)->dev; struct net *net = dev_net(dev); - struct rtable *rt; - struct flowi4 fl4 = {}; -#if IS_ENABLED(CONFIG_IPV6) - struct flowi6 fl6 = {}; -#endif + struct flowi fl; struct dst_entry *dst = NULL; + memset(&fl, 0, sizeof(fl)); + switch (nf_ct_l3num(ct)) { case NFPROTO_IPV4: - fl4.daddr = daddr->ip; - rt = ip_route_output_key(net, &fl4); - if (!IS_ERR(rt)) - dst = &rt->dst; + fl.u.ip4.daddr = daddr->ip; + nf_ip_route(net, &dst, &fl, false); break; -#if IS_ENABLED(CONFIG_IPV6) case NFPROTO_IPV6: - fl6.daddr = daddr->in6; - dst = ip6_route_output(net, NULL, &fl6); - if (dst->error) { - dst_release(dst); - dst = NULL; - } + fl.u.ip6.daddr = daddr->in6; + nf_ip6_route(net, &dst, &fl, false); break; -#endif } /* Don't predict any conntracks when media endpoint is reachable * through the same interface as the signalling peer. */ - if (dst && dst->dev == dev) - return NF_ACCEPT; + if (dst) { + bool external_media = (dst->dev == dev); + + dst_release(dst); + if (external_media) + return NF_ACCEPT; + } } /* We need to check whether the registration exists before attempting diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index af7dc6537758..000952719adf 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -415,9 +415,14 @@ static void nf_nat_l4proto_unique_tuple(struct nf_conntrack_tuple *tuple, case IPPROTO_ICMPV6: /* id is same for either direction... */ keyptr = &tuple->src.u.icmp.id; - min = range->min_proto.icmp.id; - range_size = ntohs(range->max_proto.icmp.id) - - ntohs(range->min_proto.icmp.id) + 1; + if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) { + min = 0; + range_size = 65536; + } else { + min = ntohs(range->min_proto.icmp.id); + range_size = ntohs(range->max_proto.icmp.id) - + ntohs(range->min_proto.icmp.id) + 1; + } goto find_free_id; #if IS_ENABLED(CONFIG_NF_CT_PROTO_GRE) case IPPROTO_GRE: diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 513f93118604..1606eaa5ae0d 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1545,7 +1545,7 @@ static int nft_chain_parse_hook(struct net *net, if (IS_ERR(type)) return PTR_ERR(type); } - if (!(type->hook_mask & (1 << hook->num))) + if (hook->num > NF_MAX_HOOKS || !(type->hook_mask & (1 << hook->num))) return -EOPNOTSUPP; if (type->type == NFT_CHAIN_T_NAT && @@ -2806,8 +2806,11 @@ err2: nf_tables_rule_release(&ctx, rule); err1: for (i = 0; i < n; i++) { - if (info[i].ops != NULL) + if (info[i].ops) { module_put(info[i].ops->type->owner); + if (info[i].ops->type->release_ops) + info[i].ops->type->release_ops(info[i].ops); + } } kvfree(info); return err; diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index b1f9c5303f02..0b3347570265 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -540,7 +540,7 @@ __build_packet_message(struct nfnl_log_net *log, goto nla_put_failure; } - if (skb->tstamp) { + if (hooknum <= NF_INET_FORWARD && skb->tstamp) { struct nfulnl_msg_packet_timestamp ts; struct timespec64 kts = ktime_to_timespec64(skb->tstamp); ts.sec = cpu_to_be64(kts.tv_sec); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 0dcc3592d053..e057b2961d31 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -582,7 +582,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, if (nfqnl_put_bridge(entry, skb) < 0) goto nla_put_failure; - if (entskb->tstamp) { + if (entry->state.hook <= NF_INET_FORWARD && entskb->tstamp) { struct nfqnl_msg_packet_timestamp ts; struct timespec64 kts = ktime_to_timespec64(entskb->tstamp); diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index 457a9ceb46af..8dfa798ea683 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -65,21 +65,34 @@ nla_put_failure: return -1; } -static void nft_objref_destroy(const struct nft_ctx *ctx, - const struct nft_expr *expr) +static void nft_objref_deactivate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + enum nft_trans_phase phase) { struct nft_object *obj = nft_objref_priv(expr); + if (phase == NFT_TRANS_COMMIT) + return; + obj->use--; } +static void nft_objref_activate(const struct nft_ctx *ctx, + const struct nft_expr *expr) +{ + struct nft_object *obj = nft_objref_priv(expr); + + obj->use++; +} + static struct nft_expr_type nft_objref_type; static const struct nft_expr_ops nft_objref_ops = { .type = &nft_objref_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_object *)), .eval = nft_objref_eval, .init = nft_objref_init, - .destroy = nft_objref_destroy, + .activate = nft_objref_activate, + .deactivate = nft_objref_deactivate, .dump = nft_objref_dump, }; diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c index f8092926f704..a340cd8a751b 100644 --- a/net/netfilter/nft_redir.c +++ b/net/netfilter/nft_redir.c @@ -233,5 +233,5 @@ module_exit(nft_redir_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org>"); -MODULE_ALIAS_NFT_AF_EXPR(AF_INET4, "redir"); +MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "redir"); MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "redir"); diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index fa61208371f8..321a0036fdf5 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -308,10 +308,6 @@ static void *nft_rbtree_deactivate(const struct net *net, else if (d > 0) parent = parent->rb_right; else { - if (!nft_set_elem_active(&rbe->ext, genmask)) { - parent = parent->rb_left; - continue; - } if (nft_rbtree_interval_end(rbe) && !nft_rbtree_interval_end(this)) { parent = parent->rb_left; @@ -320,6 +316,9 @@ static void *nft_rbtree_deactivate(const struct net *net, nft_rbtree_interval_end(this)) { parent = parent->rb_right; continue; + } else if (!nft_set_elem_active(&rbe->ext, genmask)) { + parent = parent->rb_left; + continue; } nft_rbtree_flush(net, set, rbe); return rbe; diff --git a/net/netfilter/xt_time.c b/net/netfilter/xt_time.c index c13bcd0ab491..8dbb4d48f2ed 100644 --- a/net/netfilter/xt_time.c +++ b/net/netfilter/xt_time.c @@ -163,19 +163,24 @@ time_mt(const struct sk_buff *skb, struct xt_action_param *par) s64 stamp; /* - * We cannot use get_seconds() instead of __net_timestamp() here. + * We need real time here, but we can neither use skb->tstamp + * nor __net_timestamp(). + * + * skb->tstamp and skb->skb_mstamp_ns overlap, however, they + * use different clock types (real vs monotonic). + * * Suppose you have two rules: - * 1. match before 13:00 - * 2. match after 13:00 + * 1. match before 13:00 + * 2. match after 13:00 + * * If you match against processing time (get_seconds) it * may happen that the same packet matches both rules if - * it arrived at the right moment before 13:00. + * it arrived at the right moment before 13:00, so it would be + * better to check skb->tstamp and set it via __net_timestamp() + * if needed. This however breaks outgoing packets tx timestamp, + * and causes them to get delayed forever by fq packet scheduler. */ - if (skb->tstamp == 0) - __net_timestamp((struct sk_buff *)skb); - - stamp = ktime_to_ns(skb->tstamp); - stamp = div_s64(stamp, NSEC_PER_SEC); + stamp = get_seconds(); if (info->flags & XT_TIME_LOCAL_TZ) /* Adjust for local timezone */ diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index f28e937320a3..216ab915dd54 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -988,7 +988,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, struct netlink_sock *nlk = nlk_sk(sk); struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr; int err = 0; - unsigned long groups = nladdr->nl_groups; + unsigned long groups; bool bound; if (addr_len < sizeof(struct sockaddr_nl)) @@ -996,6 +996,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, if (nladdr->nl_family != AF_NETLINK) return -EINVAL; + groups = nladdr->nl_groups; /* Only superuser is allowed to listen multicasts */ if (groups) { diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 25eeb6d2a75a..cb69d35c8e6a 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -362,11 +362,11 @@ int genl_register_family(struct genl_family *family) } else family->attrbuf = NULL; - family->id = idr_alloc(&genl_fam_idr, family, - start, end + 1, GFP_KERNEL); + family->id = idr_alloc_cyclic(&genl_fam_idr, family, + start, end + 1, GFP_KERNEL); if (family->id < 0) { err = family->id; - goto errout_locked; + goto errout_free; } err = genl_validate_assign_mc_groups(family); @@ -385,6 +385,7 @@ int genl_register_family(struct genl_family *family) errout_remove: idr_remove(&genl_fam_idr, family->id); +errout_free: kfree(family->attrbuf); errout_locked: genl_unlock_all(); diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 1d3144d19903..71ffd1a6dc7c 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -1392,18 +1392,22 @@ static int __init nr_proto_init(void) int i; int rc = proto_register(&nr_proto, 0); - if (rc != 0) - goto out; + if (rc) + return rc; if (nr_ndevs > 0x7fffffff/sizeof(struct net_device *)) { - printk(KERN_ERR "NET/ROM: nr_proto_init - nr_ndevs parameter to large\n"); - return -1; + pr_err("NET/ROM: %s - nr_ndevs parameter too large\n", + __func__); + rc = -EINVAL; + goto unregister_proto; } dev_nr = kcalloc(nr_ndevs, sizeof(struct net_device *), GFP_KERNEL); - if (dev_nr == NULL) { - printk(KERN_ERR "NET/ROM: nr_proto_init - unable to allocate device array\n"); - return -1; + if (!dev_nr) { + pr_err("NET/ROM: %s - unable to allocate device array\n", + __func__); + rc = -ENOMEM; + goto unregister_proto; } for (i = 0; i < nr_ndevs; i++) { @@ -1413,13 +1417,13 @@ static int __init nr_proto_init(void) sprintf(name, "nr%d", i); dev = alloc_netdev(0, name, NET_NAME_UNKNOWN, nr_setup); if (!dev) { - printk(KERN_ERR "NET/ROM: nr_proto_init - unable to allocate device structure\n"); + rc = -ENOMEM; goto fail; } dev->base_addr = i; - if (register_netdev(dev)) { - printk(KERN_ERR "NET/ROM: nr_proto_init - unable to register network device\n"); + rc = register_netdev(dev); + if (rc) { free_netdev(dev); goto fail; } @@ -1427,36 +1431,64 @@ static int __init nr_proto_init(void) dev_nr[i] = dev; } - if (sock_register(&nr_family_ops)) { - printk(KERN_ERR "NET/ROM: nr_proto_init - unable to register socket family\n"); + rc = sock_register(&nr_family_ops); + if (rc) goto fail; - } - register_netdevice_notifier(&nr_dev_notifier); + rc = register_netdevice_notifier(&nr_dev_notifier); + if (rc) + goto out_sock; ax25_register_pid(&nr_pid); ax25_linkfail_register(&nr_linkfail_notifier); #ifdef CONFIG_SYSCTL - nr_register_sysctl(); + rc = nr_register_sysctl(); + if (rc) + goto out_sysctl; #endif nr_loopback_init(); - proc_create_seq("nr", 0444, init_net.proc_net, &nr_info_seqops); - proc_create_seq("nr_neigh", 0444, init_net.proc_net, &nr_neigh_seqops); - proc_create_seq("nr_nodes", 0444, init_net.proc_net, &nr_node_seqops); -out: - return rc; + rc = -ENOMEM; + if (!proc_create_seq("nr", 0444, init_net.proc_net, &nr_info_seqops)) + goto proc_remove1; + if (!proc_create_seq("nr_neigh", 0444, init_net.proc_net, + &nr_neigh_seqops)) + goto proc_remove2; + if (!proc_create_seq("nr_nodes", 0444, init_net.proc_net, + &nr_node_seqops)) + goto proc_remove3; + + return 0; + +proc_remove3: + remove_proc_entry("nr_neigh", init_net.proc_net); +proc_remove2: + remove_proc_entry("nr", init_net.proc_net); +proc_remove1: + + nr_loopback_clear(); + nr_rt_free(); + +#ifdef CONFIG_SYSCTL + nr_unregister_sysctl(); +out_sysctl: +#endif + ax25_linkfail_release(&nr_linkfail_notifier); + ax25_protocol_release(AX25_P_NETROM); + unregister_netdevice_notifier(&nr_dev_notifier); +out_sock: + sock_unregister(PF_NETROM); fail: while (--i >= 0) { unregister_netdev(dev_nr[i]); free_netdev(dev_nr[i]); } kfree(dev_nr); +unregister_proto: proto_unregister(&nr_proto); - rc = -1; - goto out; + return rc; } module_init(nr_proto_init); diff --git a/net/netrom/nr_loopback.c b/net/netrom/nr_loopback.c index 215ad22a9647..93d13f019981 100644 --- a/net/netrom/nr_loopback.c +++ b/net/netrom/nr_loopback.c @@ -70,7 +70,7 @@ static void nr_loopback_timer(struct timer_list *unused) } } -void __exit nr_loopback_clear(void) +void nr_loopback_clear(void) { del_timer_sync(&loopback_timer); skb_queue_purge(&loopback_queue); diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index 6485f593e2f0..b76aa668a94b 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -953,7 +953,7 @@ const struct seq_operations nr_neigh_seqops = { /* * Free all memory associated with the nodes and routes lists. */ -void __exit nr_rt_free(void) +void nr_rt_free(void) { struct nr_neigh *s = NULL; struct nr_node *t = NULL; diff --git a/net/netrom/sysctl_net_netrom.c b/net/netrom/sysctl_net_netrom.c index ba1c368b3f18..771011b84270 100644 --- a/net/netrom/sysctl_net_netrom.c +++ b/net/netrom/sysctl_net_netrom.c @@ -146,9 +146,12 @@ static struct ctl_table nr_table[] = { { } }; -void __init nr_register_sysctl(void) +int __init nr_register_sysctl(void) { nr_table_header = register_net_sysctl(&init_net, "net/netrom", nr_table); + if (!nr_table_header) + return -ENOMEM; + return 0; } void nr_unregister_sysctl(void) diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index ae296273ce3d..17dcd0b5eb32 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -726,6 +726,10 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr, llcp_sock->service_name = kmemdup(addr->service_name, llcp_sock->service_name_len, GFP_KERNEL); + if (!llcp_sock->service_name) { + ret = -ENOMEM; + goto sock_llcp_release; + } nfc_llcp_sock_link(&local->connecting_sockets, sk); @@ -745,10 +749,11 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr, return ret; sock_unlink: - nfc_llcp_put_ssap(local, llcp_sock->ssap); - nfc_llcp_sock_unlink(&local->connecting_sockets, sk); +sock_llcp_release: + nfc_llcp_put_ssap(local, llcp_sock->ssap); + put_dev: nfc_put_device(dev); diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c index ddfc52ac1f9b..c0d323b58e73 100644 --- a/net/nfc/nci/hci.c +++ b/net/nfc/nci/hci.c @@ -312,6 +312,10 @@ static void nci_hci_cmd_received(struct nci_dev *ndev, u8 pipe, create_info = (struct nci_hci_create_pipe_resp *)skb->data; dest_gate = create_info->dest_gate; new_pipe = create_info->pipe; + if (new_pipe >= NCI_HCI_MAX_PIPES) { + status = NCI_HCI_ANY_E_NOK; + goto exit; + } /* Save the new created pipe and bind with local gate, * the description for skb->data[3] is destination gate id @@ -336,6 +340,10 @@ static void nci_hci_cmd_received(struct nci_dev *ndev, u8 pipe, goto exit; } delete_info = (struct nci_hci_delete_pipe_noti *)skb->data; + if (delete_info->pipe >= NCI_HCI_MAX_PIPES) { + status = NCI_HCI_ANY_E_NOK; + goto exit; + } ndev->hci_dev->pipes[delete_info->pipe].gate = NCI_HCI_INVALID_GATE; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 6679e96ab1dc..9dd158ab51b3 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -448,6 +448,10 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, upcall = genlmsg_put(user_skb, 0, 0, &dp_packet_genl_family, 0, upcall_info->cmd); + if (!upcall) { + err = -EINVAL; + goto out; + } upcall->dp_ifindex = dp_ifindex; err = ovs_nla_put_key(key, key, OVS_PACKET_ATTR_KEY, false, user_skb); @@ -460,6 +464,10 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, if (upcall_info->egress_tun_info) { nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_EGRESS_TUN_KEY); + if (!nla) { + err = -EMSGSIZE; + goto out; + } err = ovs_nla_put_tunnel_info(user_skb, upcall_info->egress_tun_info); BUG_ON(err); @@ -468,6 +476,10 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, if (upcall_info->actions_len) { nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_ACTIONS); + if (!nla) { + err = -EMSGSIZE; + goto out; + } err = ovs_nla_put_actions(upcall_info->actions, upcall_info->actions_len, user_skb); diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 691da853bef5..4bdf5e3ac208 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2306,14 +2306,14 @@ static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa, struct sw_flow_actions *acts; int new_acts_size; - int req_size = NLA_ALIGN(attr_len); + size_t req_size = NLA_ALIGN(attr_len); int next_offset = offsetof(struct sw_flow_actions, actions) + (*sfa)->actions_len; if (req_size <= (ksize(*sfa) - next_offset)) goto out; - new_acts_size = ksize(*sfa) * 2; + new_acts_size = max(next_offset + req_size, ksize(*sfa) * 2); if (new_acts_size > MAX_ACTIONS_BUFSIZE) { if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size) { diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 8376bc1c1508..9b81813dd16a 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1852,7 +1852,8 @@ oom: static void packet_parse_headers(struct sk_buff *skb, struct socket *sock) { - if (!skb->protocol && sock->type == SOCK_RAW) { + if ((!skb->protocol || skb->protocol == htons(ETH_P_ALL)) && + sock->type == SOCK_RAW) { skb_reset_mac_header(skb); skb->protocol = dev_parse_header_protocol(skb); } @@ -2601,8 +2602,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) void *ph; DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name); bool need_wait = !(msg->msg_flags & MSG_DONTWAIT); + unsigned char *addr = NULL; int tp_len, size_max; - unsigned char *addr; void *data; int len_sum = 0; int status = TP_STATUS_AVAILABLE; @@ -2613,7 +2614,6 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); proto = po->num; - addr = NULL; } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) @@ -2623,10 +2623,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) sll_addr))) goto out; proto = saddr->sll_protocol; - addr = saddr->sll_halen ? saddr->sll_addr : NULL; dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex); - if (addr && dev && saddr->sll_halen < dev->addr_len) - goto out_put; + if (po->sk.sk_socket->type == SOCK_DGRAM) { + if (dev && msg->msg_namelen < dev->addr_len + + offsetof(struct sockaddr_ll, sll_addr)) + goto out_put; + addr = saddr->sll_addr; + } } err = -ENXIO; @@ -2798,7 +2801,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) struct sk_buff *skb; struct net_device *dev; __be16 proto; - unsigned char *addr; + unsigned char *addr = NULL; int err, reserve = 0; struct sockcm_cookie sockc; struct virtio_net_hdr vnet_hdr = { 0 }; @@ -2815,7 +2818,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); proto = po->num; - addr = NULL; } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) @@ -2823,10 +2825,13 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr))) goto out; proto = saddr->sll_protocol; - addr = saddr->sll_halen ? saddr->sll_addr : NULL; dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex); - if (addr && dev && saddr->sll_halen < dev->addr_len) - goto out_unlock; + if (sock->type == SOCK_DGRAM) { + if (dev && msg->msg_namelen < dev->addr_len + + offsetof(struct sockaddr_ll, sll_addr)) + goto out_unlock; + addr = saddr->sll_addr; + } } err = -ENXIO; @@ -3243,7 +3248,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, } mutex_lock(&net->packet.sklist_lock); - sk_add_node_rcu(sk, &net->packet.sklist); + sk_add_node_tail_rcu(sk, &net->packet.sklist); mutex_unlock(&net->packet.sklist_lock); preempt_disable(); @@ -3343,20 +3348,29 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, sock_recv_ts_and_drops(msg, sk, skb); if (msg->msg_name) { + int copy_len; + /* If the address length field is there to be filled * in, we fill it in now. */ if (sock->type == SOCK_PACKET) { __sockaddr_check_size(sizeof(struct sockaddr_pkt)); msg->msg_namelen = sizeof(struct sockaddr_pkt); + copy_len = msg->msg_namelen; } else { struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; msg->msg_namelen = sll->sll_halen + offsetof(struct sockaddr_ll, sll_addr); + copy_len = msg->msg_namelen; + if (msg->msg_namelen < sizeof(struct sockaddr_ll)) { + memset(msg->msg_name + + offsetof(struct sockaddr_ll, sll_addr), + 0, sizeof(sll->sll_addr)); + msg->msg_namelen = sizeof(struct sockaddr_ll); + } } - memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa, - msg->msg_namelen); + memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa, copy_len); } if (pkt_sk(sk)->auxdata) { @@ -4209,7 +4223,7 @@ static struct pgv *alloc_pg_vec(struct tpacket_req *req, int order) struct pgv *pg_vec; int i; - pg_vec = kcalloc(block_nr, sizeof(struct pgv), GFP_KERNEL); + pg_vec = kcalloc(block_nr, sizeof(struct pgv), GFP_KERNEL | __GFP_NOWARN); if (unlikely(!pg_vec)) goto out; diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index d6cc97fbbbb0..2b969f99ef13 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -543,6 +543,9 @@ static int rds_connect(struct socket *sock, struct sockaddr *uaddr, struct rds_sock *rs = rds_sk_to_rs(sk); int ret = 0; + if (addr_len < offsetofend(struct sockaddr, sa_family)) + return -EINVAL; + lock_sock(sk); switch (uaddr->sa_family) { diff --git a/net/rds/bind.c b/net/rds/bind.c index 17c9d9f0c848..0f4398e7f2a7 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -173,6 +173,8 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) /* We allow an RDS socket to be bound to either IPv4 or IPv6 * address. */ + if (addr_len < offsetofend(struct sockaddr, sa_family)) + return -EINVAL; if (uaddr->sa_family == AF_INET) { struct sockaddr_in *sin = (struct sockaddr_in *)uaddr; diff --git a/net/rds/ib_fmr.c b/net/rds/ib_fmr.c index 31cf37da4510..93c0437e6a5f 100644 --- a/net/rds/ib_fmr.c +++ b/net/rds/ib_fmr.c @@ -44,6 +44,17 @@ struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *rds_ibdev, int npages) else pool = rds_ibdev->mr_1m_pool; + if (atomic_read(&pool->dirty_count) >= pool->max_items / 10) + queue_delayed_work(rds_ib_mr_wq, &pool->flush_worker, 10); + + /* Switch pools if one of the pool is reaching upper limit */ + if (atomic_read(&pool->dirty_count) >= pool->max_items * 9 / 10) { + if (pool->pool_type == RDS_IB_MR_8K_POOL) + pool = rds_ibdev->mr_1m_pool; + else + pool = rds_ibdev->mr_8k_pool; + } + ibmr = rds_ib_try_reuse_ibmr(pool); if (ibmr) return ibmr; diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index 63c8d107adcf..d664e9ade74d 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -454,9 +454,6 @@ struct rds_ib_mr *rds_ib_try_reuse_ibmr(struct rds_ib_mr_pool *pool) struct rds_ib_mr *ibmr = NULL; int iter = 0; - if (atomic_read(&pool->dirty_count) >= pool->max_items_soft / 10) - queue_delayed_work(rds_ib_mr_wq, &pool->flush_worker, 10); - while (1) { ibmr = rds_ib_reuse_mr(pool); if (ibmr) diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 70559854837e..8946c89d7392 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -772,7 +772,7 @@ static void rds_ib_cong_recv(struct rds_connection *conn, unsigned long frag_off; unsigned long to_copy; unsigned long copied; - uint64_t uncongested = 0; + __le64 uncongested = 0; void *addr; /* catch completely corrupt packets */ @@ -789,7 +789,7 @@ static void rds_ib_cong_recv(struct rds_connection *conn, copied = 0; while (copied < RDS_CONG_MAP_BYTES) { - uint64_t *src, *dst; + __le64 *src, *dst; unsigned int k; to_copy = min(RDS_FRAG_SIZE - frag_off, PAGE_SIZE - map_off); @@ -824,9 +824,7 @@ static void rds_ib_cong_recv(struct rds_connection *conn, } /* the congestion map is in little endian order */ - uncongested = le64_to_cpu(uncongested); - - rds_cong_map_updated(map, uncongested); + rds_cong_map_updated(map, le64_to_cpu(uncongested)); } static void rds_ib_process_recv(struct rds_connection *conn, diff --git a/net/rds/tcp.c b/net/rds/tcp.c index fd2694174607..faf726e00e27 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -608,7 +608,7 @@ static void rds_tcp_kill_sock(struct net *net) list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) { struct net *c_net = read_pnet(&tc->t_cpath->cp_conn->c_net); - if (net != c_net || !tc->t_sock) + if (net != c_net) continue; if (!list_has_conn(&tmp_list, tc->t_cpath->cp_conn)) { list_move_tail(&tc->t_tcp_node, &tmp_list); diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c index 7af4f99c4a93..094a6621f8e8 100644 --- a/net/rose/rose_loopback.c +++ b/net/rose/rose_loopback.c @@ -16,6 +16,7 @@ #include <linux/init.h> static struct sk_buff_head loopback_queue; +#define ROSE_LOOPBACK_LIMIT 1000 static struct timer_list loopback_timer; static void rose_set_loopback_timer(void); @@ -35,29 +36,27 @@ static int rose_loopback_running(void) int rose_loopback_queue(struct sk_buff *skb, struct rose_neigh *neigh) { - struct sk_buff *skbn; + struct sk_buff *skbn = NULL; - skbn = skb_clone(skb, GFP_ATOMIC); + if (skb_queue_len(&loopback_queue) < ROSE_LOOPBACK_LIMIT) + skbn = skb_clone(skb, GFP_ATOMIC); - kfree_skb(skb); - - if (skbn != NULL) { + if (skbn) { + consume_skb(skb); skb_queue_tail(&loopback_queue, skbn); if (!rose_loopback_running()) rose_set_loopback_timer(); + } else { + kfree_skb(skb); } return 1; } - static void rose_set_loopback_timer(void) { - del_timer(&loopback_timer); - - loopback_timer.expires = jiffies + 10; - add_timer(&loopback_timer); + mod_timer(&loopback_timer, jiffies + 10); } static void rose_loopback_timer(struct timer_list *unused) @@ -68,8 +67,12 @@ static void rose_loopback_timer(struct timer_list *unused) struct sock *sk; unsigned short frametype; unsigned int lci_i, lci_o; + int count; - while ((skb = skb_dequeue(&loopback_queue)) != NULL) { + for (count = 0; count < ROSE_LOOPBACK_LIMIT; count++) { + skb = skb_dequeue(&loopback_queue); + if (!skb) + return; if (skb->len < ROSE_MIN_LEN) { kfree_skb(skb); continue; @@ -106,6 +109,8 @@ static void rose_loopback_timer(struct timer_list *unused) kfree_skb(skb); } } + if (!skb_queue_empty(&loopback_queue)) + mod_timer(&loopback_timer, jiffies + 1); } void __exit rose_loopback_clear(void) diff --git a/net/rose/rose_subr.c b/net/rose/rose_subr.c index 7ca57741b2fb..7849f286bb93 100644 --- a/net/rose/rose_subr.c +++ b/net/rose/rose_subr.c @@ -105,16 +105,17 @@ void rose_write_internal(struct sock *sk, int frametype) struct sk_buff *skb; unsigned char *dptr; unsigned char lci1, lci2; - char buffer[100]; - int len, faclen = 0; + int maxfaclen = 0; + int len, faclen; + int reserve; - len = AX25_BPQ_HEADER_LEN + AX25_MAX_HEADER_LEN + ROSE_MIN_LEN + 1; + reserve = AX25_BPQ_HEADER_LEN + AX25_MAX_HEADER_LEN + 1; + len = ROSE_MIN_LEN; switch (frametype) { case ROSE_CALL_REQUEST: len += 1 + ROSE_ADDR_LEN + ROSE_ADDR_LEN; - faclen = rose_create_facilities(buffer, rose); - len += faclen; + maxfaclen = 256; break; case ROSE_CALL_ACCEPTED: case ROSE_CLEAR_REQUEST: @@ -123,15 +124,16 @@ void rose_write_internal(struct sock *sk, int frametype) break; } - if ((skb = alloc_skb(len, GFP_ATOMIC)) == NULL) + skb = alloc_skb(reserve + len + maxfaclen, GFP_ATOMIC); + if (!skb) return; /* * Space for AX.25 header and PID. */ - skb_reserve(skb, AX25_BPQ_HEADER_LEN + AX25_MAX_HEADER_LEN + 1); + skb_reserve(skb, reserve); - dptr = skb_put(skb, skb_tailroom(skb)); + dptr = skb_put(skb, len); lci1 = (rose->lci >> 8) & 0x0F; lci2 = (rose->lci >> 0) & 0xFF; @@ -146,7 +148,8 @@ void rose_write_internal(struct sock *sk, int frametype) dptr += ROSE_ADDR_LEN; memcpy(dptr, &rose->source_addr, ROSE_ADDR_LEN); dptr += ROSE_ADDR_LEN; - memcpy(dptr, buffer, faclen); + faclen = rose_create_facilities(dptr, rose); + skb_put(skb, faclen); dptr += faclen; break; diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 96f2952bbdfd..ae8c5d7f3bf1 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -135,7 +135,7 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len) struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *)saddr; struct rxrpc_local *local; struct rxrpc_sock *rx = rxrpc_sk(sock->sk); - u16 service_id = srx->srx_service; + u16 service_id; int ret; _enter("%p,%p,%d", rx, saddr, len); @@ -143,6 +143,7 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len) ret = rxrpc_validate_address(rx, srx, len); if (ret < 0) goto error; + service_id = srx->srx_service; lock_sock(&rx->sk); @@ -370,18 +371,22 @@ EXPORT_SYMBOL(rxrpc_kernel_end_call); * rxrpc_kernel_check_life - Check to see whether a call is still alive * @sock: The socket the call is on * @call: The call to check + * @_life: Where to store the life value * * Allow a kernel service to find out whether a call is still alive - ie. we're - * getting ACKs from the server. Returns a number representing the life state - * which can be compared to that returned by a previous call. + * getting ACKs from the server. Passes back in *_life a number representing + * the life state which can be compared to that returned by a previous call and + * return true if the call is still alive. * * If the life state stalls, rxrpc_kernel_probe_life() should be called and * then 2RTT waited. */ -u32 rxrpc_kernel_check_life(const struct socket *sock, - const struct rxrpc_call *call) +bool rxrpc_kernel_check_life(const struct socket *sock, + const struct rxrpc_call *call, + u32 *_life) { - return call->acks_latest; + *_life = call->acks_latest; + return call->state != RXRPC_CALL_COMPLETE; } EXPORT_SYMBOL(rxrpc_kernel_check_life); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 4b1a534d290a..062ca9dc29b8 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -654,6 +654,7 @@ struct rxrpc_call { u8 ackr_reason; /* reason to ACK */ u16 ackr_skew; /* skew on packet being ACK'd */ rxrpc_serial_t ackr_serial; /* serial of packet being ACK'd */ + rxrpc_serial_t ackr_first_seq; /* first sequence number received */ rxrpc_seq_t ackr_prev_seq; /* previous sequence number received */ rxrpc_seq_t ackr_consumed; /* Highest packet shown consumed */ rxrpc_seq_t ackr_seen; /* Highest packet shown seen */ diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 8aa2937b069f..fe96881a334d 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -604,30 +604,30 @@ void rxrpc_destroy_all_calls(struct rxrpc_net *rxnet) _enter(""); - if (list_empty(&rxnet->calls)) - return; + if (!list_empty(&rxnet->calls)) { + write_lock(&rxnet->call_lock); - write_lock(&rxnet->call_lock); + while (!list_empty(&rxnet->calls)) { + call = list_entry(rxnet->calls.next, + struct rxrpc_call, link); + _debug("Zapping call %p", call); - while (!list_empty(&rxnet->calls)) { - call = list_entry(rxnet->calls.next, struct rxrpc_call, link); - _debug("Zapping call %p", call); + rxrpc_see_call(call); + list_del_init(&call->link); - rxrpc_see_call(call); - list_del_init(&call->link); + pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n", + call, atomic_read(&call->usage), + rxrpc_call_states[call->state], + call->flags, call->events); - pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n", - call, atomic_read(&call->usage), - rxrpc_call_states[call->state], - call->flags, call->events); + write_unlock(&rxnet->call_lock); + cond_resched(); + write_lock(&rxnet->call_lock); + } write_unlock(&rxnet->call_lock); - cond_resched(); - write_lock(&rxnet->call_lock); } - write_unlock(&rxnet->call_lock); - atomic_dec(&rxnet->nr_calls); wait_var_event(&rxnet->nr_calls, !atomic_read(&rxnet->nr_calls)); } diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index b6fca8ebb117..8d31fb4c51e1 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -153,7 +153,8 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, * pass a connection-level abort onto all calls on that connection */ static void rxrpc_abort_calls(struct rxrpc_connection *conn, - enum rxrpc_call_completion compl) + enum rxrpc_call_completion compl, + rxrpc_serial_t serial) { struct rxrpc_call *call; int i; @@ -173,6 +174,9 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn, call->call_id, 0, conn->abort_code, conn->error); + else + trace_rxrpc_rx_abort(call, serial, + conn->abort_code); if (rxrpc_set_call_completion(call, compl, conn->abort_code, conn->error)) @@ -213,8 +217,6 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, conn->state = RXRPC_CONN_LOCALLY_ABORTED; spin_unlock_bh(&conn->state_lock); - rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED); - msg.msg_name = &conn->params.peer->srx.transport; msg.msg_namelen = conn->params.peer->srx.transport_len; msg.msg_control = NULL; @@ -242,6 +244,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, len = iov[0].iov_len + iov[1].iov_len; serial = atomic_inc_return(&conn->serial); + rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED, serial); whdr.serial = htonl(serial); _proto("Tx CONN ABORT %%%u { %d }", serial, conn->abort_code); @@ -321,7 +324,7 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, conn->error = -ECONNABORTED; conn->abort_code = abort_code; conn->state = RXRPC_CONN_REMOTELY_ABORTED; - rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED); + rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, sp->hdr.serial); return -ECONNABORTED; case RXRPC_PACKET_TYPE_CHALLENGE: diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 9128aa0e40aa..c2c35cf4e308 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -837,7 +837,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, u8 acks[RXRPC_MAXACKS]; } buf; rxrpc_serial_t acked_serial; - rxrpc_seq_t first_soft_ack, hard_ack; + rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt; int nr_acks, offset, ioffset; _enter(""); @@ -851,13 +851,14 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, acked_serial = ntohl(buf.ack.serial); first_soft_ack = ntohl(buf.ack.firstPacket); + prev_pkt = ntohl(buf.ack.previousPacket); hard_ack = first_soft_ack - 1; nr_acks = buf.ack.nAcks; summary.ack_reason = (buf.ack.reason < RXRPC_ACK__INVALID ? buf.ack.reason : RXRPC_ACK__INVALID); trace_rxrpc_rx_ack(call, sp->hdr.serial, acked_serial, - first_soft_ack, ntohl(buf.ack.previousPacket), + first_soft_ack, prev_pkt, summary.ack_reason, nr_acks); if (buf.ack.reason == RXRPC_ACK_PING_RESPONSE) @@ -878,8 +879,9 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, rxrpc_propose_ack_respond_to_ack); } - /* Discard any out-of-order or duplicate ACKs. */ - if (before_eq(sp->hdr.serial, call->acks_latest)) + /* Discard any out-of-order or duplicate ACKs (outside lock). */ + if (before(first_soft_ack, call->ackr_first_seq) || + before(prev_pkt, call->ackr_prev_seq)) return; buf.info.rxMTU = 0; @@ -890,12 +892,16 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, spin_lock(&call->input_lock); - /* Discard any out-of-order or duplicate ACKs. */ - if (before_eq(sp->hdr.serial, call->acks_latest)) + /* Discard any out-of-order or duplicate ACKs (inside lock). */ + if (before(first_soft_ack, call->ackr_first_seq) || + before(prev_pkt, call->ackr_prev_seq)) goto out; call->acks_latest_ts = skb->tstamp; call->acks_latest = sp->hdr.serial; + call->ackr_first_seq = first_soft_ack; + call->ackr_prev_seq = prev_pkt; + /* Parse rwind and mtu sizes if provided. */ if (buf.info.rxMTU) rxrpc_input_ackinfo(call, skb, &buf.info); @@ -1155,19 +1161,19 @@ int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb) * handle data received on the local endpoint * - may be called in interrupt context * - * The socket is locked by the caller and this prevents the socket from being - * shut down and the local endpoint from going away, thus sk_user_data will not - * be cleared until this function returns. + * [!] Note that as this is called from the encap_rcv hook, the socket is not + * held locked by the caller and nothing prevents sk_user_data on the UDP from + * being cleared in the middle of processing this function. * * Called with the RCU read lock held from the IP layer via UDP. */ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) { + struct rxrpc_local *local = rcu_dereference_sk_user_data(udp_sk); struct rxrpc_connection *conn; struct rxrpc_channel *chan; struct rxrpc_call *call = NULL; struct rxrpc_skb_priv *sp; - struct rxrpc_local *local = udp_sk->sk_user_data; struct rxrpc_peer *peer = NULL; struct rxrpc_sock *rx = NULL; unsigned int channel; @@ -1175,6 +1181,10 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) _enter("%p", udp_sk); + if (unlikely(!local)) { + kfree_skb(skb); + return 0; + } if (skb->tstamp == 0) skb->tstamp = ktime_get_real(); diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 15cf42d5b53a..01959db51445 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -304,7 +304,8 @@ nomem: ret = -ENOMEM; sock_error: mutex_unlock(&rxnet->local_mutex); - kfree(local); + if (local) + call_rcu(&local->rcu, rxrpc_local_rcu); _leave(" = %d", ret); return ERR_PTR(ret); diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 736aa9281100..004c762c2e8d 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -335,7 +335,6 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, struct kvec iov[2]; rxrpc_serial_t serial; size_t len; - bool lost = false; int ret, opt; _enter(",{%d}", skb->len); @@ -393,14 +392,14 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, static int lose; if ((lose++ & 7) == 7) { ret = 0; - lost = true; + trace_rxrpc_tx_data(call, sp->hdr.seq, serial, + whdr.flags, retrans, true); + goto done; } } - trace_rxrpc_tx_data(call, sp->hdr.seq, serial, whdr.flags, - retrans, lost); - if (lost) - goto done; + trace_rxrpc_tx_data(call, sp->hdr.seq, serial, whdr.flags, retrans, + false); /* send the packet with the don't fragment bit set if we currently * think it's small enough */ diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index bc05af89fc38..6e84d878053c 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -157,6 +157,11 @@ void rxrpc_error_report(struct sock *sk) _enter("%p{%d}", sk, local->debug_id); + /* Clear the outstanding error value on the socket so that it doesn't + * cause kernel_sendmsg() to return it later. + */ + sock_error(sk); + skb = sock_dequeue_err_skb(sk); if (!skb) { _leave("UDP socket errqueue empty"); diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 46c9312085b1..bec64deb7b0a 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -152,12 +152,13 @@ static void rxrpc_notify_end_tx(struct rxrpc_sock *rx, struct rxrpc_call *call, } /* - * Queue a DATA packet for transmission, set the resend timeout and send the - * packet immediately + * Queue a DATA packet for transmission, set the resend timeout and send + * the packet immediately. Returns the error from rxrpc_send_data_packet() + * in case the caller wants to do something with it. */ -static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, - struct sk_buff *skb, bool last, - rxrpc_notify_end_tx_t notify_end_tx) +static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, + struct sk_buff *skb, bool last, + rxrpc_notify_end_tx_t notify_end_tx) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); unsigned long now; @@ -250,7 +251,8 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, out: rxrpc_free_skb(skb, rxrpc_skb_tx_freed); - _leave(""); + _leave(" = %d", ret); + return ret; } /* @@ -423,9 +425,10 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, if (ret < 0) goto out; - rxrpc_queue_packet(rx, call, skb, - !msg_data_left(msg) && !more, - notify_end_tx); + ret = rxrpc_queue_packet(rx, call, skb, + !msg_data_left(msg) && !more, + notify_end_tx); + /* Should check for failure here */ skb = NULL; } } while (msg_data_left(msg) > 0); diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 1b9afdee5ba9..5c02ad97ef23 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -358,8 +358,7 @@ config NET_SCH_PIE help Say Y here if you want to use the Proportional Integral controller Enhanced scheduler packet scheduling algorithm. - For more information, please see - http://tools.ietf.org/html/draft-pan-tsvwg-pie-00 + For more information, please see https://tools.ietf.org/html/rfc8033 To compile this driver as a module, choose M here: the module will be called sch_pie. diff --git a/net/sched/act_api.c b/net/sched/act_api.c index aecf1bf233c8..5a87e271d35a 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -28,27 +28,10 @@ #include <net/act_api.h> #include <net/netlink.h> -static int tcf_action_goto_chain_init(struct tc_action *a, struct tcf_proto *tp) -{ - u32 chain_index = a->tcfa_action & TC_ACT_EXT_VAL_MASK; - - if (!tp) - return -EINVAL; - a->goto_chain = tcf_chain_get_by_act(tp->chain->block, chain_index); - if (!a->goto_chain) - return -ENOMEM; - return 0; -} - -static void tcf_action_goto_chain_fini(struct tc_action *a) -{ - tcf_chain_put_by_act(a->goto_chain); -} - static void tcf_action_goto_chain_exec(const struct tc_action *a, struct tcf_result *res) { - const struct tcf_chain *chain = a->goto_chain; + const struct tcf_chain *chain = rcu_dereference_bh(a->goto_chain); res->goto_tp = rcu_dereference_bh(chain->filter_chain); } @@ -71,6 +54,51 @@ static void tcf_set_action_cookie(struct tc_cookie __rcu **old_cookie, call_rcu(&old->rcu, tcf_free_cookie_rcu); } +int tcf_action_check_ctrlact(int action, struct tcf_proto *tp, + struct tcf_chain **newchain, + struct netlink_ext_ack *extack) +{ + int opcode = TC_ACT_EXT_OPCODE(action), ret = -EINVAL; + u32 chain_index; + + if (!opcode) + ret = action > TC_ACT_VALUE_MAX ? -EINVAL : 0; + else if (opcode <= TC_ACT_EXT_OPCODE_MAX || action == TC_ACT_UNSPEC) + ret = 0; + if (ret) { + NL_SET_ERR_MSG(extack, "invalid control action"); + goto end; + } + + if (TC_ACT_EXT_CMP(action, TC_ACT_GOTO_CHAIN)) { + chain_index = action & TC_ACT_EXT_VAL_MASK; + if (!tp || !newchain) { + ret = -EINVAL; + NL_SET_ERR_MSG(extack, + "can't goto NULL proto/chain"); + goto end; + } + *newchain = tcf_chain_get_by_act(tp->chain->block, chain_index); + if (!*newchain) { + ret = -ENOMEM; + NL_SET_ERR_MSG(extack, + "can't allocate goto_chain"); + } + } +end: + return ret; +} +EXPORT_SYMBOL(tcf_action_check_ctrlact); + +struct tcf_chain *tcf_action_set_ctrlact(struct tc_action *a, int action, + struct tcf_chain *goto_chain) +{ + a->tcfa_action = action; + rcu_swap_protected(a->goto_chain, goto_chain, 1); + return goto_chain; +} +EXPORT_SYMBOL(tcf_action_set_ctrlact); + /* XXX: For standalone actions, we don't need a RCU grace period either, because * actions are always connected to filters and filters are already destroyed in * RCU callbacks, so after a RCU grace period actions are already disconnected @@ -78,13 +106,15 @@ static void tcf_set_action_cookie(struct tc_cookie __rcu **old_cookie, */ static void free_tcf(struct tc_action *p) { + struct tcf_chain *chain = rcu_dereference_protected(p->goto_chain, 1); + free_percpu(p->cpu_bstats); free_percpu(p->cpu_bstats_hw); free_percpu(p->cpu_qstats); tcf_set_action_cookie(&p->act_cookie, NULL); - if (p->goto_chain) - tcf_action_goto_chain_fini(p); + if (chain) + tcf_chain_put_by_act(chain); kfree(p); } @@ -654,6 +684,10 @@ repeat: return TC_ACT_OK; } } else if (TC_ACT_EXT_CMP(ret, TC_ACT_GOTO_CHAIN)) { + if (unlikely(!rcu_access_pointer(a->goto_chain))) { + net_warn_ratelimited("can't go to NULL chain!\n"); + return TC_ACT_SHOT; + } tcf_action_goto_chain_exec(a, res); } @@ -800,15 +834,6 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb) return c; } -static bool tcf_action_valid(int action) -{ - int opcode = TC_ACT_EXT_OPCODE(action); - - if (!opcode) - return action <= TC_ACT_VALUE_MAX; - return opcode <= TC_ACT_EXT_OPCODE_MAX || action == TC_ACT_UNSPEC; -} - struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, char *name, int ovr, int bind, @@ -890,10 +915,10 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, /* backward compatibility for policer */ if (name == NULL) err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, &a, ovr, bind, - rtnl_held, extack); + rtnl_held, tp, extack); else err = a_o->init(net, nla, est, &a, ovr, bind, rtnl_held, - extack); + tp, extack); if (err < 0) goto err_mod; @@ -907,18 +932,10 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, if (err != ACT_P_CREATED) module_put(a_o->owner); - if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN)) { - err = tcf_action_goto_chain_init(a, tp); - if (err) { - tcf_action_destroy_1(a, bind); - NL_SET_ERR_MSG(extack, "Failed to init TC action chain"); - return ERR_PTR(err); - } - } - - if (!tcf_action_valid(a->tcfa_action)) { + if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN) && + !rcu_access_pointer(a->goto_chain)) { tcf_action_destroy_1(a, bind); - NL_SET_ERR_MSG(extack, "Invalid control action value"); + NL_SET_ERR_MSG(extack, "can't use goto chain with NULL chain"); return ERR_PTR(-EINVAL); } diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index aa5c38d11a30..3841156aa09f 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -17,6 +17,7 @@ #include <net/netlink.h> #include <net/pkt_sched.h> +#include <net/pkt_cls.h> #include <linux/tc_act/tc_bpf.h> #include <net/tc_act/tc_bpf.h> @@ -278,10 +279,11 @@ static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog, static int tcf_bpf_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **act, int replace, int bind, bool rtnl_held, - struct netlink_ext_ack *extack) + struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, bpf_net_id); struct nlattr *tb[TCA_ACT_BPF_MAX + 1]; + struct tcf_chain *goto_ch = NULL; struct tcf_bpf_cfg cfg, old; struct tc_act_bpf *parm; struct tcf_bpf *prog; @@ -323,12 +325,16 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, return ret; } + ret = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (ret < 0) + goto release_idr; + is_bpf = tb[TCA_ACT_BPF_OPS_LEN] && tb[TCA_ACT_BPF_OPS]; is_ebpf = tb[TCA_ACT_BPF_FD]; if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf)) { ret = -EINVAL; - goto out; + goto put_chain; } memset(&cfg, 0, sizeof(cfg)); @@ -336,7 +342,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, ret = is_bpf ? tcf_bpf_init_from_ops(tb, &cfg) : tcf_bpf_init_from_efd(tb, &cfg); if (ret < 0) - goto out; + goto put_chain; prog = to_bpf(*act); @@ -350,10 +356,13 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, if (cfg.bpf_num_ops) prog->bpf_num_ops = cfg.bpf_num_ops; - prog->tcf_action = parm->action; + goto_ch = tcf_action_set_ctrlact(*act, parm->action, goto_ch); rcu_assign_pointer(prog->filter, cfg.filter); spin_unlock_bh(&prog->tcf_lock); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); + if (res == ACT_P_CREATED) { tcf_idr_insert(tn, *act); } else { @@ -363,9 +372,13 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, } return res; -out: - tcf_idr_release(*act, bind); +put_chain: + if (goto_ch) + tcf_chain_put_by_act(goto_ch); + +release_idr: + tcf_idr_release(*act, bind); return ret; } diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 5d24993cccfe..32ae0cd6e31c 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -21,6 +21,7 @@ #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/act_api.h> +#include <net/pkt_cls.h> #include <uapi/linux/tc_act/tc_connmark.h> #include <net/tc_act/tc_connmark.h> @@ -97,13 +98,15 @@ static const struct nla_policy connmark_policy[TCA_CONNMARK_MAX + 1] = { static int tcf_connmark_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, + struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, connmark_net_id); struct nlattr *tb[TCA_CONNMARK_MAX + 1]; + struct tcf_chain *goto_ch = NULL; struct tcf_connmark_info *ci; struct tc_connmark *parm; - int ret = 0; + int ret = 0, err; if (!nla) return -EINVAL; @@ -128,7 +131,11 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, } ci = to_connmark(*a); - ci->tcf_action = parm->action; + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, + extack); + if (err < 0) + goto release_idr; + tcf_action_set_ctrlact(*a, parm->action, goto_ch); ci->net = net; ci->zone = parm->zone; @@ -142,15 +149,24 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, tcf_idr_release(*a, bind); return -EEXIST; } + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, + extack); + if (err < 0) + goto release_idr; /* replacing action and zone */ spin_lock_bh(&ci->tcf_lock); - ci->tcf_action = parm->action; + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); ci->zone = parm->zone; spin_unlock_bh(&ci->tcf_lock); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); ret = 0; } return ret; +release_idr: + tcf_idr_release(*a, bind); + return err; } static inline int tcf_connmark_dump(struct sk_buff *skb, struct tc_action *a, diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index c79aca29505e..0c77e7bdf6d5 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -33,6 +33,7 @@ #include <net/sctp/checksum.h> #include <net/act_api.h> +#include <net/pkt_cls.h> #include <linux/tc_act/tc_csum.h> #include <net/tc_act/tc_csum.h> @@ -46,12 +47,13 @@ static struct tc_action_ops act_csum_ops; static int tcf_csum_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, - int bind, bool rtnl_held, + int bind, bool rtnl_held, struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, csum_net_id); struct tcf_csum_params *params_new; struct nlattr *tb[TCA_CSUM_MAX + 1]; + struct tcf_chain *goto_ch = NULL; struct tc_csum *parm; struct tcf_csum *p; int ret = 0, err; @@ -87,21 +89,27 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla, return err; } + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; + p = to_tcf_csum(*a); params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); if (unlikely(!params_new)) { - tcf_idr_release(*a, bind); - return -ENOMEM; + err = -ENOMEM; + goto put_chain; } params_new->update_flags = parm->update_flags; spin_lock_bh(&p->tcf_lock); - p->tcf_action = parm->action; + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); rcu_swap_protected(p->params, params_new, lockdep_is_held(&p->tcf_lock)); spin_unlock_bh(&p->tcf_lock); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); if (params_new) kfree_rcu(params_new, rcu); @@ -109,6 +117,12 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla, tcf_idr_insert(tn, *a); return ret; +put_chain: + if (goto_ch) + tcf_chain_put_by_act(goto_ch); +release_idr: + tcf_idr_release(*a, bind); + return err; } /** diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index 93da0004e9f4..e540e31069d7 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -20,6 +20,7 @@ #include <linux/init.h> #include <net/netlink.h> #include <net/pkt_sched.h> +#include <net/pkt_cls.h> #include <linux/tc_act/tc_gact.h> #include <net/tc_act/tc_gact.h> @@ -57,10 +58,11 @@ static const struct nla_policy gact_policy[TCA_GACT_MAX + 1] = { static int tcf_gact_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, - struct netlink_ext_ack *extack) + struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, gact_net_id); struct nlattr *tb[TCA_GACT_MAX + 1]; + struct tcf_chain *goto_ch = NULL; struct tc_gact *parm; struct tcf_gact *gact; int ret = 0; @@ -116,10 +118,13 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, return err; } + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; gact = to_gact(*a); spin_lock_bh(&gact->tcf_lock); - gact->tcf_action = parm->action; + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); #ifdef CONFIG_GACT_PROB if (p_parm) { gact->tcfg_paction = p_parm->paction; @@ -133,9 +138,15 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, #endif spin_unlock_bh(&gact->tcf_lock); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); + if (ret == ACT_P_CREATED) tcf_idr_insert(tn, *a); return ret; +release_idr: + tcf_idr_release(*a, bind); + return err; } static int tcf_gact_act(struct sk_buff *skb, const struct tc_action *a, diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 9b1f2b3990ee..31c6ffb6abe7 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -29,6 +29,7 @@ #include <net/net_namespace.h> #include <net/netlink.h> #include <net/pkt_sched.h> +#include <net/pkt_cls.h> #include <uapi/linux/tc_act/tc_ife.h> #include <net/tc_act/tc_ife.h> #include <linux/etherdevice.h> @@ -469,11 +470,12 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, static int tcf_ife_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, - struct netlink_ext_ack *extack) + struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, ife_net_id); struct nlattr *tb[TCA_IFE_MAX + 1]; struct nlattr *tb2[IFE_META_MAX + 1]; + struct tcf_chain *goto_ch = NULL; struct tcf_ife_params *p; struct tcf_ife_info *ife; u16 ife_type = ETH_P_IFE; @@ -531,6 +533,10 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, } ife = to_ife(*a); + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; + p->flags = parm->flags; if (parm->flags & IFE_ENCODE) { @@ -563,13 +569,8 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, if (tb[TCA_IFE_METALST]) { err = nla_parse_nested(tb2, IFE_META_MAX, tb[TCA_IFE_METALST], NULL, NULL); - if (err) { -metadata_parse_err: - tcf_idr_release(*a, bind); - kfree(p); - return err; - } - + if (err) + goto metadata_parse_err; err = populate_metalist(ife, tb2, exists, rtnl_held); if (err) goto metadata_parse_err; @@ -581,21 +582,20 @@ metadata_parse_err: * going to bail out */ err = use_all_metadata(ife, exists); - if (err) { - tcf_idr_release(*a, bind); - kfree(p); - return err; - } + if (err) + goto metadata_parse_err; } if (exists) spin_lock_bh(&ife->tcf_lock); - ife->tcf_action = parm->action; /* protected by tcf_lock when modifying existing action */ + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); rcu_swap_protected(ife->params, p, 1); if (exists) spin_unlock_bh(&ife->tcf_lock); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); if (p) kfree_rcu(p, rcu); @@ -603,6 +603,13 @@ metadata_parse_err: tcf_idr_insert(tn, *a); return ret; +metadata_parse_err: + if (goto_ch) + tcf_chain_put_by_act(goto_ch); +release_idr: + kfree(p); + tcf_idr_release(*a, bind); + return err; } static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 98f5b6ea77b4..04a0b5c61194 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -97,7 +97,8 @@ static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = { static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla, struct nlattr *est, struct tc_action **a, - const struct tc_action_ops *ops, int ovr, int bind) + const struct tc_action_ops *ops, int ovr, int bind, + struct tcf_proto *tp) { struct tc_action_net *tn = net_generic(net, id); struct nlattr *tb[TCA_IPT_MAX + 1]; @@ -205,20 +206,20 @@ err1: static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, - int bind, bool rtnl_held, + int bind, bool rtnl_held, struct tcf_proto *tp, struct netlink_ext_ack *extack) { return __tcf_ipt_init(net, ipt_net_id, nla, est, a, &act_ipt_ops, ovr, - bind); + bind, tp); } static int tcf_xt_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, - int bind, bool unlocked, + int bind, bool unlocked, struct tcf_proto *tp, struct netlink_ext_ack *extack) { return __tcf_ipt_init(net, xt_net_id, nla, est, a, &act_xt_ops, ovr, - bind); + bind, tp); } static int tcf_ipt_act(struct sk_buff *skb, const struct tc_action *a, diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 6692fd054617..17cc6bd4c57c 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -94,10 +94,12 @@ static struct tc_action_ops act_mirred_ops; static int tcf_mirred_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, + struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, mirred_net_id); struct nlattr *tb[TCA_MIRRED_MAX + 1]; + struct tcf_chain *goto_ch = NULL; bool mac_header_xmit = false; struct tc_mirred *parm; struct tcf_mirred *m; @@ -157,18 +159,23 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, tcf_idr_release(*a, bind); return -EEXIST; } + m = to_mirred(*a); + if (ret == ACT_P_CREATED) + INIT_LIST_HEAD(&m->tcfm_list); + + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; spin_lock_bh(&m->tcf_lock); - m->tcf_action = parm->action; - m->tcfm_eaction = parm->eaction; if (parm->ifindex) { dev = dev_get_by_index(net, parm->ifindex); if (!dev) { spin_unlock_bh(&m->tcf_lock); - tcf_idr_release(*a, bind); - return -ENODEV; + err = -ENODEV; + goto put_chain; } mac_header_xmit = dev_is_mac_header_xmit(dev); rcu_swap_protected(m->tcfm_dev, dev, @@ -177,7 +184,11 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, dev_put(dev); m->tcfm_mac_header_xmit = mac_header_xmit; } + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); + m->tcfm_eaction = parm->eaction; spin_unlock_bh(&m->tcf_lock); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); if (ret == ACT_P_CREATED) { spin_lock(&mirred_list_lock); @@ -188,6 +199,12 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, } return ret; +put_chain: + if (goto_ch) + tcf_chain_put_by_act(goto_ch); +release_idr: + tcf_idr_release(*a, bind); + return err; } static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 543eab9193f1..e91bb8eb81ec 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -21,6 +21,7 @@ #include <linux/string.h> #include <linux/tc_act/tc_nat.h> #include <net/act_api.h> +#include <net/pkt_cls.h> #include <net/icmp.h> #include <net/ip.h> #include <net/netlink.h> @@ -38,10 +39,12 @@ static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = { static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, - bool rtnl_held, struct netlink_ext_ack *extack) + bool rtnl_held, struct tcf_proto *tp, + struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, nat_net_id); struct nlattr *tb[TCA_NAT_MAX + 1]; + struct tcf_chain *goto_ch = NULL; struct tc_nat *parm; int ret = 0, err; struct tcf_nat *p; @@ -76,6 +79,9 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, } else { return err; } + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; p = to_tcf_nat(*a); spin_lock_bh(&p->tcf_lock); @@ -84,13 +90,18 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, p->mask = parm->mask; p->flags = parm->flags; - p->tcf_action = parm->action; + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); spin_unlock_bh(&p->tcf_lock); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); if (ret == ACT_P_CREATED) tcf_idr_insert(tn, *a); return ret; +release_idr: + tcf_idr_release(*a, bind); + return err; } static int tcf_nat_act(struct sk_buff *skb, const struct tc_action *a, diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index a80373878df7..287793abfaf9 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -23,6 +23,7 @@ #include <linux/tc_act/tc_pedit.h> #include <net/tc_act/tc_pedit.h> #include <uapi/linux/tc_act/tc_pedit.h> +#include <net/pkt_cls.h> static unsigned int pedit_net_id; static struct tc_action_ops act_pedit_ops; @@ -138,10 +139,11 @@ nla_failure: static int tcf_pedit_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, - struct netlink_ext_ack *extack) + struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, pedit_net_id); struct nlattr *tb[TCA_PEDIT_MAX + 1]; + struct tcf_chain *goto_ch = NULL; struct tc_pedit_key *keys = NULL; struct tcf_pedit_key_ex *keys_ex; struct tc_pedit *parm; @@ -205,6 +207,11 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, goto out_free; } + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) { + ret = err; + goto out_release; + } p = to_pedit(*a); spin_lock_bh(&p->tcf_lock); @@ -214,7 +221,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, if (!keys) { spin_unlock_bh(&p->tcf_lock); ret = -ENOMEM; - goto out_release; + goto put_chain; } kfree(p->tcfp_keys); p->tcfp_keys = keys; @@ -223,16 +230,21 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, memcpy(p->tcfp_keys, parm->keys, ksize); p->tcfp_flags = parm->flags; - p->tcf_action = parm->action; + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); kfree(p->tcfp_keys_ex); p->tcfp_keys_ex = keys_ex; spin_unlock_bh(&p->tcf_lock); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); if (ret == ACT_P_CREATED) tcf_idr_insert(tn, *a); return ret; +put_chain: + if (goto_ch) + tcf_chain_put_by_act(goto_ch); out_release: tcf_idr_release(*a, bind); out_free: diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 8271a6263824..2b8581f6ab51 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -21,6 +21,7 @@ #include <linux/slab.h> #include <net/act_api.h> #include <net/netlink.h> +#include <net/pkt_cls.h> struct tcf_police_params { int tcfp_result; @@ -83,10 +84,12 @@ static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = { static int tcf_police_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, + struct tcf_proto *tp, struct netlink_ext_ack *extack) { int ret = 0, tcfp_result = TC_ACT_OK, err, size; struct nlattr *tb[TCA_POLICE_MAX + 1]; + struct tcf_chain *goto_ch = NULL; struct tc_police *parm; struct tcf_police *police; struct qdisc_rate_table *R_tab = NULL, *P_tab = NULL; @@ -128,6 +131,9 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, tcf_idr_release(*a, bind); return -EEXIST; } + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; police = to_police(*a); if (parm->rate.rate) { @@ -213,12 +219,14 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, if (new->peak_present) police->tcfp_ptoks = new->tcfp_mtu_ptoks; spin_unlock_bh(&police->tcfp_lock); - police->tcf_action = parm->action; + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); rcu_swap_protected(police->params, new, lockdep_is_held(&police->tcf_lock)); spin_unlock_bh(&police->tcf_lock); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); if (new) kfree_rcu(new, rcu); @@ -229,6 +237,9 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, failure: qdisc_put_rtab(P_tab); qdisc_put_rtab(R_tab); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); +release_idr: tcf_idr_release(*a, bind); return err; } diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 203e399e5c85..0f82d50ea232 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -22,6 +22,7 @@ #include <linux/tc_act/tc_sample.h> #include <net/tc_act/tc_sample.h> #include <net/psample.h> +#include <net/pkt_cls.h> #include <linux/if_arp.h> @@ -37,14 +38,15 @@ static const struct nla_policy sample_policy[TCA_SAMPLE_MAX + 1] = { static int tcf_sample_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, - int bind, bool rtnl_held, + int bind, bool rtnl_held, struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, sample_net_id); struct nlattr *tb[TCA_SAMPLE_MAX + 1]; struct psample_group *psample_group; + struct tcf_chain *goto_ch = NULL; + u32 psample_group_num, rate; struct tc_sample *parm; - u32 psample_group_num; struct tcf_sample *s; bool exists = false; int ret, err; @@ -79,19 +81,28 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, tcf_idr_release(*a, bind); return -EEXIST; } + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; + rate = nla_get_u32(tb[TCA_SAMPLE_RATE]); + if (!rate) { + NL_SET_ERR_MSG(extack, "invalid sample rate"); + err = -EINVAL; + goto put_chain; + } psample_group_num = nla_get_u32(tb[TCA_SAMPLE_PSAMPLE_GROUP]); psample_group = psample_group_get(net, psample_group_num); if (!psample_group) { - tcf_idr_release(*a, bind); - return -ENOMEM; + err = -ENOMEM; + goto put_chain; } s = to_sample(*a); spin_lock_bh(&s->tcf_lock); - s->tcf_action = parm->action; - s->rate = nla_get_u32(tb[TCA_SAMPLE_RATE]); + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); + s->rate = rate; s->psample_group_num = psample_group_num; RCU_INIT_POINTER(s->psample_group, psample_group); @@ -100,10 +111,18 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, s->trunc_size = nla_get_u32(tb[TCA_SAMPLE_TRUNC_SIZE]); } spin_unlock_bh(&s->tcf_lock); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); if (ret == ACT_P_CREATED) tcf_idr_insert(tn, *a); return ret; +put_chain: + if (goto_ch) + tcf_chain_put_by_act(goto_ch); +release_idr: + tcf_idr_release(*a, bind); + return err; } static void tcf_sample_cleanup(struct tc_action *a) diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index d54cb608dbaf..23c8ca5615e5 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -18,6 +18,7 @@ #include <linux/rtnetlink.h> #include <net/netlink.h> #include <net/pkt_sched.h> +#include <net/pkt_cls.h> #include <linux/tc_act/tc_defact.h> #include <net/tc_act/tc_defact.h> @@ -60,14 +61,26 @@ static int alloc_defdata(struct tcf_defact *d, const struct nlattr *defdata) return 0; } -static void reset_policy(struct tcf_defact *d, const struct nlattr *defdata, - struct tc_defact *p) +static int reset_policy(struct tc_action *a, const struct nlattr *defdata, + struct tc_defact *p, struct tcf_proto *tp, + struct netlink_ext_ack *extack) { + struct tcf_chain *goto_ch = NULL; + struct tcf_defact *d; + int err; + + err = tcf_action_check_ctrlact(p->action, tp, &goto_ch, extack); + if (err < 0) + return err; + d = to_defact(a); spin_lock_bh(&d->tcf_lock); - d->tcf_action = p->action; + goto_ch = tcf_action_set_ctrlact(a, p->action, goto_ch); memset(d->tcfd_defdata, 0, SIMP_MAX_DATA); nla_strlcpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA); spin_unlock_bh(&d->tcf_lock); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); + return 0; } static const struct nla_policy simple_policy[TCA_DEF_MAX + 1] = { @@ -78,10 +91,11 @@ static const struct nla_policy simple_policy[TCA_DEF_MAX + 1] = { static int tcf_simp_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, - struct netlink_ext_ack *extack) + struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, simp_net_id); struct nlattr *tb[TCA_DEF_MAX + 1]; + struct tcf_chain *goto_ch = NULL; struct tc_defact *parm; struct tcf_defact *d; bool exists = false; @@ -122,27 +136,37 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, } d = to_defact(*a); - ret = alloc_defdata(d, tb[TCA_DEF_DATA]); - if (ret < 0) { - tcf_idr_release(*a, bind); - return ret; - } - d->tcf_action = parm->action; + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, + extack); + if (err < 0) + goto release_idr; + + err = alloc_defdata(d, tb[TCA_DEF_DATA]); + if (err < 0) + goto put_chain; + + tcf_action_set_ctrlact(*a, parm->action, goto_ch); ret = ACT_P_CREATED; } else { - d = to_defact(*a); - if (!ovr) { - tcf_idr_release(*a, bind); - return -EEXIST; + err = -EEXIST; + goto release_idr; } - reset_policy(d, tb[TCA_DEF_DATA], parm); + err = reset_policy(*a, tb[TCA_DEF_DATA], parm, tp, extack); + if (err) + goto release_idr; } if (ret == ACT_P_CREATED) tcf_idr_insert(tn, *a); return ret; +put_chain: + if (goto_ch) + tcf_chain_put_by_act(goto_ch); +release_idr: + tcf_idr_release(*a, bind); + return err; } static int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a, diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 65879500b688..7e1d261a31d2 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -26,6 +26,7 @@ #include <net/ip.h> #include <net/ipv6.h> #include <net/dsfield.h> +#include <net/pkt_cls.h> #include <linux/tc_act/tc_skbedit.h> #include <net/tc_act/tc_skbedit.h> @@ -96,11 +97,13 @@ static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = { static int tcf_skbedit_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, + struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, skbedit_net_id); struct tcf_skbedit_params *params_new; struct nlattr *tb[TCA_SKBEDIT_MAX + 1]; + struct tcf_chain *goto_ch = NULL; struct tc_skbedit *parm; struct tcf_skbedit *d; u32 flags = 0, *priority = NULL, *mark = NULL, *mask = NULL; @@ -186,11 +189,14 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, return -EEXIST; } } + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); if (unlikely(!params_new)) { - tcf_idr_release(*a, bind); - return -ENOMEM; + err = -ENOMEM; + goto put_chain; } params_new->flags = flags; @@ -208,16 +214,24 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, params_new->mask = *mask; spin_lock_bh(&d->tcf_lock); - d->tcf_action = parm->action; + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); rcu_swap_protected(d->params, params_new, lockdep_is_held(&d->tcf_lock)); spin_unlock_bh(&d->tcf_lock); if (params_new) kfree_rcu(params_new, rcu); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); if (ret == ACT_P_CREATED) tcf_idr_insert(tn, *a); return ret; +put_chain: + if (goto_ch) + tcf_chain_put_by_act(goto_ch); +release_idr: + tcf_idr_release(*a, bind); + return err; } static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 7bac1d78e7a3..1d4c324d0a42 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -16,6 +16,7 @@ #include <linux/rtnetlink.h> #include <net/netlink.h> #include <net/pkt_sched.h> +#include <net/pkt_cls.h> #include <linux/tc_act/tc_skbmod.h> #include <net/tc_act/tc_skbmod.h> @@ -82,11 +83,13 @@ static const struct nla_policy skbmod_policy[TCA_SKBMOD_MAX + 1] = { static int tcf_skbmod_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, + struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, skbmod_net_id); struct nlattr *tb[TCA_SKBMOD_MAX + 1]; struct tcf_skbmod_params *p, *p_old; + struct tcf_chain *goto_ch = NULL; struct tc_skbmod *parm; struct tcf_skbmod *d; bool exists = false; @@ -153,21 +156,24 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, tcf_idr_release(*a, bind); return -EEXIST; } + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; d = to_skbmod(*a); p = kzalloc(sizeof(struct tcf_skbmod_params), GFP_KERNEL); if (unlikely(!p)) { - tcf_idr_release(*a, bind); - return -ENOMEM; + err = -ENOMEM; + goto put_chain; } p->flags = lflags; - d->tcf_action = parm->action; if (ovr) spin_lock_bh(&d->tcf_lock); /* Protected by tcf_lock if overwriting existing action. */ + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); p_old = rcu_dereference_protected(d->skbmod_p, 1); if (lflags & SKBMOD_F_DMAC) @@ -183,10 +189,18 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, if (p_old) kfree_rcu(p_old, rcu); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); if (ret == ACT_P_CREATED) tcf_idr_insert(tn, *a); return ret; +put_chain: + if (goto_ch) + tcf_chain_put_by_act(goto_ch); +release_idr: + tcf_idr_release(*a, bind); + return err; } static void tcf_skbmod_cleanup(struct tc_action *a) diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 7c6591b991d5..d5aaf90a3971 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -17,6 +17,7 @@ #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/dst.h> +#include <net/pkt_cls.h> #include <linux/tc_act/tc_tunnel_key.h> #include <net/tc_act/tc_tunnel_key.h> @@ -210,12 +211,14 @@ static void tunnel_key_release_params(struct tcf_tunnel_key_params *p) static int tunnel_key_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, + struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); struct nlattr *tb[TCA_TUNNEL_KEY_MAX + 1]; struct tcf_tunnel_key_params *params_new; struct metadata_dst *metadata = NULL; + struct tcf_chain *goto_ch = NULL; struct tc_tunnel_key *parm; struct tcf_tunnel_key *t; bool exists = false; @@ -359,6 +362,12 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, goto release_tun_meta; } + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) { + ret = err; + exists = true; + goto release_tun_meta; + } t = to_tunnel_key(*a); params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); @@ -366,23 +375,29 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, NL_SET_ERR_MSG(extack, "Cannot allocate tunnel key parameters"); ret = -ENOMEM; exists = true; - goto release_tun_meta; + goto put_chain; } params_new->tcft_action = parm->t_action; params_new->tcft_enc_metadata = metadata; spin_lock_bh(&t->tcf_lock); - t->tcf_action = parm->action; + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); rcu_swap_protected(t->params, params_new, lockdep_is_held(&t->tcf_lock)); spin_unlock_bh(&t->tcf_lock); tunnel_key_release_params(params_new); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); if (ret == ACT_P_CREATED) tcf_idr_insert(tn, *a); return ret; +put_chain: + if (goto_ch) + tcf_chain_put_by_act(goto_ch); + release_tun_meta: if (metadata) dst_release(&metadata->dst); diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index ac0061599225..0f40d0a74423 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -15,6 +15,7 @@ #include <linux/if_vlan.h> #include <net/netlink.h> #include <net/pkt_sched.h> +#include <net/pkt_cls.h> #include <linux/tc_act/tc_vlan.h> #include <net/tc_act/tc_vlan.h> @@ -105,10 +106,11 @@ static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = { static int tcf_vlan_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, - struct netlink_ext_ack *extack) + struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, vlan_net_id); struct nlattr *tb[TCA_VLAN_MAX + 1]; + struct tcf_chain *goto_ch = NULL; struct tcf_vlan_params *p; struct tc_vlan *parm; struct tcf_vlan *v; @@ -200,12 +202,16 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, return -EEXIST; } + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; + v = to_vlan(*a); p = kzalloc(sizeof(*p), GFP_KERNEL); if (!p) { - tcf_idr_release(*a, bind); - return -ENOMEM; + err = -ENOMEM; + goto put_chain; } p->tcfv_action = action; @@ -214,16 +220,24 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, p->tcfv_push_proto = push_proto; spin_lock_bh(&v->tcf_lock); - v->tcf_action = parm->action; + goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); rcu_swap_protected(v->vlan_p, p, lockdep_is_held(&v->tcf_lock)); spin_unlock_bh(&v->tcf_lock); + if (goto_ch) + tcf_chain_put_by_act(goto_ch); if (p) kfree_rcu(p, rcu); if (ret == ACT_P_CREATED) tcf_idr_insert(tn, *a); return ret; +put_chain: + if (goto_ch) + tcf_chain_put_by_act(goto_ch); +release_idr: + tcf_idr_release(*a, bind); + return err; } static void tcf_vlan_cleanup(struct tc_action *a) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index dc10525e90e7..99ae30c177c7 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -367,7 +367,7 @@ static void tcf_chain_destroy(struct tcf_chain *chain, bool free_block) struct tcf_block *block = chain->block; mutex_destroy(&chain->filter_chain_lock); - kfree(chain); + kfree_rcu(chain, rcu); if (free_block) tcf_block_destroy(block); } diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 459921bd3d87..a13bc351a414 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -130,6 +130,11 @@ static void mall_destroy(struct tcf_proto *tp, bool rtnl_held, static void *mall_get(struct tcf_proto *tp, u32 handle) { + struct cls_mall_head *head = rtnl_dereference(tp->root); + + if (head && head->handle == handle) + return head; + return NULL; } diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 1d2a12132abc..259d97bc2abd 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -211,6 +211,9 @@ struct cake_sched_data { u8 ack_filter; u8 atm_mode; + u32 fwmark_mask; + u16 fwmark_shft; + /* time_next = time_this + ((len * rate_ns) >> rate_shft) */ u16 rate_shft; ktime_t time_next_packet; @@ -258,8 +261,7 @@ enum { CAKE_FLAG_AUTORATE_INGRESS = BIT(1), CAKE_FLAG_INGRESS = BIT(2), CAKE_FLAG_WASH = BIT(3), - CAKE_FLAG_SPLIT_GSO = BIT(4), - CAKE_FLAG_FWMARK = BIT(5) + CAKE_FLAG_SPLIT_GSO = BIT(4) }; /* COBALT operates the Codel and BLUE algorithms in parallel, in order to @@ -1515,16 +1517,27 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free) static u8 cake_handle_diffserv(struct sk_buff *skb, u16 wash) { + int wlen = skb_network_offset(skb); u8 dscp; - switch (skb->protocol) { + switch (tc_skb_protocol(skb)) { case htons(ETH_P_IP): + wlen += sizeof(struct iphdr); + if (!pskb_may_pull(skb, wlen) || + skb_try_make_writable(skb, wlen)) + return 0; + dscp = ipv4_get_dsfield(ip_hdr(skb)) >> 2; if (wash && dscp) ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0); return dscp; case htons(ETH_P_IPV6): + wlen += sizeof(struct ipv6hdr); + if (!pskb_may_pull(skb, wlen) || + skb_try_make_writable(skb, wlen)) + return 0; + dscp = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2; if (wash && dscp) ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0); @@ -1543,7 +1556,7 @@ static struct cake_tin_data *cake_select_tin(struct Qdisc *sch, struct sk_buff *skb) { struct cake_sched_data *q = qdisc_priv(sch); - u32 tin; + u32 tin, mark; u8 dscp; /* Tin selection: Default to diffserv-based selection, allow overriding @@ -1551,14 +1564,13 @@ static struct cake_tin_data *cake_select_tin(struct Qdisc *sch, */ dscp = cake_handle_diffserv(skb, q->rate_flags & CAKE_FLAG_WASH); + mark = (skb->mark & q->fwmark_mask) >> q->fwmark_shft; if (q->tin_mode == CAKE_DIFFSERV_BESTEFFORT) tin = 0; - else if (q->rate_flags & CAKE_FLAG_FWMARK && /* use fw mark */ - skb->mark && - skb->mark <= q->tin_cnt) - tin = q->tin_order[skb->mark - 1]; + else if (mark && mark <= q->tin_cnt) + tin = q->tin_order[mark - 1]; else if (TC_H_MAJ(skb->priority) == sch->handle && TC_H_MIN(skb->priority) > 0 && @@ -2172,6 +2184,7 @@ static const struct nla_policy cake_policy[TCA_CAKE_MAX + 1] = { [TCA_CAKE_MPU] = { .type = NLA_U32 }, [TCA_CAKE_INGRESS] = { .type = NLA_U32 }, [TCA_CAKE_ACK_FILTER] = { .type = NLA_U32 }, + [TCA_CAKE_FWMARK] = { .type = NLA_U32 }, }; static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu, @@ -2619,10 +2632,8 @@ static int cake_change(struct Qdisc *sch, struct nlattr *opt, } if (tb[TCA_CAKE_FWMARK]) { - if (!!nla_get_u32(tb[TCA_CAKE_FWMARK])) - q->rate_flags |= CAKE_FLAG_FWMARK; - else - q->rate_flags &= ~CAKE_FLAG_FWMARK; + q->fwmark_mask = nla_get_u32(tb[TCA_CAKE_FWMARK]); + q->fwmark_shft = q->fwmark_mask ? __ffs(q->fwmark_mask) : 0; } if (q->tins) { @@ -2784,8 +2795,7 @@ static int cake_dump(struct Qdisc *sch, struct sk_buff *skb) !!(q->rate_flags & CAKE_FLAG_SPLIT_GSO))) goto nla_put_failure; - if (nla_put_u32(skb, TCA_CAKE_FWMARK, - !!(q->rate_flags & CAKE_FLAG_FWMARK))) + if (nla_put_u32(skb, TCA_CAKE_FWMARK, q->fwmark_mask)) goto nla_put_failure; return nla_nest_end(skb, opts); diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 4dc05409e3fb..114b9048ea7e 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1358,9 +1358,11 @@ cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg, { struct cbq_sched_data *q = qdisc_priv(sch); struct cbq_class *cl = (struct cbq_class *)arg; + __u32 qlen; cl->xstats.avgidle = cl->avgidle; cl->xstats.undertime = 0; + qdisc_qstats_qlen_backlog(cl->q, &qlen, &cl->qstats.backlog); if (cl->undertime != PSCHED_PASTPERFECT) cl->xstats.undertime = cl->undertime - q->now; @@ -1368,7 +1370,7 @@ cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg, if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d, NULL, &cl->bstats) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || - gnet_stats_copy_queue(d, NULL, &cl->qstats, cl->q->q.qlen) < 0) + gnet_stats_copy_queue(d, NULL, &cl->qstats, qlen) < 0) return -1; return gnet_stats_copy_app(d, &cl->xstats, sizeof(cl->xstats)); @@ -1665,17 +1667,13 @@ static int cbq_delete(struct Qdisc *sch, unsigned long arg) { struct cbq_sched_data *q = qdisc_priv(sch); struct cbq_class *cl = (struct cbq_class *)arg; - unsigned int qlen, backlog; if (cl->filters || cl->children || cl == &q->link) return -EBUSY; sch_tree_lock(sch); - qlen = cl->q->q.qlen; - backlog = cl->q->qstats.backlog; - qdisc_reset(cl->q); - qdisc_tree_reduce_backlog(cl->q, qlen, backlog); + qdisc_purge_queue(cl->q); if (cl->next_alive) cbq_deactivate_class(cl); diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 09b800991065..430df9a55ec4 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -50,15 +50,6 @@ static struct drr_class *drr_find_class(struct Qdisc *sch, u32 classid) return container_of(clc, struct drr_class, common); } -static void drr_purge_queue(struct drr_class *cl) -{ - unsigned int len = cl->qdisc->q.qlen; - unsigned int backlog = cl->qdisc->qstats.backlog; - - qdisc_reset(cl->qdisc); - qdisc_tree_reduce_backlog(cl->qdisc, len, backlog); -} - static const struct nla_policy drr_policy[TCA_DRR_MAX + 1] = { [TCA_DRR_QUANTUM] = { .type = NLA_U32 }, }; @@ -167,7 +158,7 @@ static int drr_delete_class(struct Qdisc *sch, unsigned long arg) sch_tree_lock(sch); - drr_purge_queue(cl); + qdisc_purge_queue(cl->qdisc); qdisc_class_hash_remove(&q->clhash, &cl->common); sch_tree_unlock(sch); @@ -269,7 +260,8 @@ static int drr_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) { struct drr_class *cl = (struct drr_class *)arg; - __u32 qlen = cl->qdisc->q.qlen; + __u32 qlen = qdisc_qlen_sum(cl->qdisc); + struct Qdisc *cl_q = cl->qdisc; struct tc_drr_stats xstats; memset(&xstats, 0, sizeof(xstats)); @@ -279,7 +271,7 @@ static int drr_dump_class_stats(struct Qdisc *sch, unsigned long arg, if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d, NULL, &cl->bstats) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || - gnet_stats_copy_queue(d, NULL, &cl->qdisc->qstats, qlen) < 0) + gnet_stats_copy_queue(d, cl_q->cpu_qstats, &cl_q->qstats, qlen) < 0) return -1; return gnet_stats_copy_app(d, &xstats, sizeof(xstats)); diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 24cc220a3218..d2ab463f22ae 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -845,16 +845,6 @@ qdisc_peek_len(struct Qdisc *sch) } static void -hfsc_purge_queue(struct Qdisc *sch, struct hfsc_class *cl) -{ - unsigned int len = cl->qdisc->q.qlen; - unsigned int backlog = cl->qdisc->qstats.backlog; - - qdisc_reset(cl->qdisc); - qdisc_tree_reduce_backlog(cl->qdisc, len, backlog); -} - -static void hfsc_adjust_levels(struct hfsc_class *cl) { struct hfsc_class *p; @@ -1076,7 +1066,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, qdisc_class_hash_insert(&q->clhash, &cl->cl_common); list_add_tail(&cl->siblings, &parent->children); if (parent->level == 0) - hfsc_purge_queue(sch, parent); + qdisc_purge_queue(parent->qdisc); hfsc_adjust_levels(parent); sch_tree_unlock(sch); @@ -1112,7 +1102,7 @@ hfsc_delete_class(struct Qdisc *sch, unsigned long arg) list_del(&cl->siblings); hfsc_adjust_levels(cl->cl_parent); - hfsc_purge_queue(sch, cl); + qdisc_purge_queue(cl->qdisc); qdisc_class_hash_remove(&q->clhash, &cl->cl_common); sch_tree_unlock(sch); @@ -1328,8 +1318,9 @@ hfsc_dump_class_stats(struct Qdisc *sch, unsigned long arg, { struct hfsc_class *cl = (struct hfsc_class *)arg; struct tc_hfsc_stats xstats; + __u32 qlen; - cl->qstats.backlog = cl->qdisc->qstats.backlog; + qdisc_qstats_qlen_backlog(cl->qdisc, &qlen, &cl->qstats.backlog); xstats.level = cl->level; xstats.period = cl->cl_vtperiod; xstats.work = cl->cl_total; @@ -1337,7 +1328,7 @@ hfsc_dump_class_stats(struct Qdisc *sch, unsigned long arg, if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d, NULL, &cl->bstats) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || - gnet_stats_copy_queue(d, NULL, &cl->qstats, cl->qdisc->q.qlen) < 0) + gnet_stats_copy_queue(d, NULL, &cl->qstats, qlen) < 0) return -1; return gnet_stats_copy_app(d, &xstats, sizeof(xstats)); diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 30f9da7e1076..2f9883b196e8 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1127,10 +1127,9 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) }; __u32 qlen = 0; - if (!cl->level && cl->leaf.q) { - qlen = cl->leaf.q->q.qlen; - qs.backlog = cl->leaf.q->qstats.backlog; - } + if (!cl->level && cl->leaf.q) + qdisc_qstats_qlen_backlog(cl->leaf.q, &qlen, &qs.backlog); + cl->xstats.tokens = clamp_t(s64, PSCHED_NS2TICKS(cl->tokens), INT_MIN, INT_MAX); cl->xstats.ctokens = clamp_t(s64, PSCHED_NS2TICKS(cl->ctokens), @@ -1270,13 +1269,8 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg) sch_tree_lock(sch); - if (!cl->level) { - unsigned int qlen = cl->leaf.q->q.qlen; - unsigned int backlog = cl->leaf.q->qstats.backlog; - - qdisc_reset(cl->leaf.q); - qdisc_tree_reduce_backlog(cl->leaf.q, qlen, backlog); - } + if (!cl->level) + qdisc_purge_queue(cl->leaf.q); /* delete from hash and active; remainder in destroy_class */ qdisc_class_hash_remove(&q->clhash, &cl->common); @@ -1404,12 +1398,8 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, classid, NULL); sch_tree_lock(sch); if (parent && !parent->level) { - unsigned int qlen = parent->leaf.q->q.qlen; - unsigned int backlog = parent->leaf.q->qstats.backlog; - /* turn parent into inner node */ - qdisc_reset(parent->leaf.q); - qdisc_tree_reduce_backlog(parent->leaf.q, qlen, backlog); + qdisc_purge_queue(parent->leaf.q); qdisc_put(parent->leaf.q); if (parent->prio_activity) htb_deactivate(q, parent); diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index 203659bc3906..3a3312467692 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -249,7 +249,7 @@ static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl, sch = dev_queue->qdisc_sleeping; if (gnet_stats_copy_basic(&sch->running, d, NULL, &sch->bstats) < 0 || - gnet_stats_copy_queue(d, NULL, &sch->qstats, sch->q.qlen) < 0) + qdisc_qstats_copy(d, sch) < 0) return -1; return 0; } diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index d364e63c396d..ea0dc112b38d 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -561,8 +561,7 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, sch = dev_queue->qdisc_sleeping; if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d, NULL, &sch->bstats) < 0 || - gnet_stats_copy_queue(d, NULL, - &sch->qstats, sch->q.qlen) < 0) + qdisc_qstats_copy(d, sch) < 0) return -1; } return 0; diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 7410ce4d0321..35b03ae08e0f 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -201,9 +201,9 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt, for (i = q->bands; i < q->max_bands; i++) { if (q->queues[i] != &noop_qdisc) { struct Qdisc *child = q->queues[i]; + q->queues[i] = &noop_qdisc; - qdisc_tree_reduce_backlog(child, child->q.qlen, - child->qstats.backlog); + qdisc_tree_flush_backlog(child); qdisc_put(child); } } @@ -225,9 +225,7 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt, qdisc_hash_add(child, true); if (old != &noop_qdisc) { - qdisc_tree_reduce_backlog(old, - old->q.qlen, - old->qstats.backlog); + qdisc_tree_flush_backlog(old); qdisc_put(old); } sch_tree_unlock(sch); @@ -344,7 +342,7 @@ static int multiq_dump_class_stats(struct Qdisc *sch, unsigned long cl, cl_q = q->queues[cl - 1]; if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d, NULL, &cl_q->bstats) < 0 || - gnet_stats_copy_queue(d, NULL, &cl_q->qstats, cl_q->q.qlen) < 0) + qdisc_qstats_copy(d, cl_q) < 0) return -1; return 0; diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 847141cd900f..d519b21535b3 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -216,12 +216,8 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt, q->bands = qopt->bands; memcpy(q->prio2band, qopt->priomap, TC_PRIO_MAX+1); - for (i = q->bands; i < oldbands; i++) { - struct Qdisc *child = q->queues[i]; - - qdisc_tree_reduce_backlog(child, child->q.qlen, - child->qstats.backlog); - } + for (i = q->bands; i < oldbands; i++) + qdisc_tree_flush_backlog(q->queues[i]); for (i = oldbands; i < q->bands; i++) { q->queues[i] = queues[i]; @@ -365,7 +361,7 @@ static int prio_dump_class_stats(struct Qdisc *sch, unsigned long cl, cl_q = q->queues[cl - 1]; if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d, NULL, &cl_q->bstats) < 0 || - gnet_stats_copy_queue(d, NULL, &cl_q->qstats, cl_q->q.qlen) < 0) + qdisc_qstats_copy(d, cl_q) < 0) return -1; return 0; diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 29f5c4a24688..1589364b54da 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -217,15 +217,6 @@ static struct qfq_class *qfq_find_class(struct Qdisc *sch, u32 classid) return container_of(clc, struct qfq_class, common); } -static void qfq_purge_queue(struct qfq_class *cl) -{ - unsigned int len = cl->qdisc->q.qlen; - unsigned int backlog = cl->qdisc->qstats.backlog; - - qdisc_reset(cl->qdisc); - qdisc_tree_reduce_backlog(cl->qdisc, len, backlog); -} - static const struct nla_policy qfq_policy[TCA_QFQ_MAX + 1] = { [TCA_QFQ_WEIGHT] = { .type = NLA_U32 }, [TCA_QFQ_LMAX] = { .type = NLA_U32 }, @@ -551,7 +542,7 @@ static int qfq_delete_class(struct Qdisc *sch, unsigned long arg) sch_tree_lock(sch); - qfq_purge_queue(cl); + qdisc_purge_queue(cl->qdisc); qdisc_class_hash_remove(&q->clhash, &cl->common); sch_tree_unlock(sch); @@ -655,8 +646,7 @@ static int qfq_dump_class_stats(struct Qdisc *sch, unsigned long arg, if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d, NULL, &cl->bstats) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || - gnet_stats_copy_queue(d, NULL, - &cl->qdisc->qstats, cl->qdisc->q.qlen) < 0) + qdisc_qstats_copy(d, cl->qdisc) < 0) return -1; return gnet_stats_copy_app(d, &xstats, sizeof(xstats)); diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 9df9942340ea..4e8c0abf6194 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -233,8 +233,7 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt, q->flags = ctl->flags; q->limit = ctl->limit; if (child) { - qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen, - q->qdisc->qstats.backlog); + qdisc_tree_flush_backlog(q->qdisc); old_child = q->qdisc; q->qdisc = child; } diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index bab506b01a32..2419fdb75966 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -521,8 +521,7 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt, qdisc_hash_add(child, true); sch_tree_lock(sch); - qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen, - q->qdisc->qstats.backlog); + qdisc_tree_flush_backlog(q->qdisc); qdisc_put(q->qdisc); q->qdisc = child; diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 206e4dbed12f..c7041999eb5d 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -895,7 +895,7 @@ static int taprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, sch = dev_queue->qdisc_sleeping; if (gnet_stats_copy_basic(&sch->running, d, NULL, &sch->bstats) < 0 || - gnet_stats_copy_queue(d, NULL, &sch->qstats, sch->q.qlen) < 0) + qdisc_qstats_copy(d, sch) < 0) return -1; return 0; } diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 7f272a9070c5..f71578dbb9e3 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -391,8 +391,7 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt, sch_tree_lock(sch); if (child) { - qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen, - q->qdisc->qstats.backlog); + qdisc_tree_flush_backlog(q->qdisc); qdisc_put(q->qdisc); q->qdisc = child; } diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 6abc8b274270..951afdeea5e9 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -600,6 +600,7 @@ out: static int sctp_v4_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr) { /* No address mapping for V4 sockets */ + memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); return sizeof(struct sockaddr_in); } diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 1d143bc3f73d..4aa03588f87b 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1112,32 +1112,6 @@ static void sctp_cmd_send_msg(struct sctp_association *asoc, } -/* Sent the next ASCONF packet currently stored in the association. - * This happens after the ASCONF_ACK was succeffully processed. - */ -static void sctp_cmd_send_asconf(struct sctp_association *asoc) -{ - struct net *net = sock_net(asoc->base.sk); - - /* Send the next asconf chunk from the addip chunk - * queue. - */ - if (!list_empty(&asoc->addip_chunk_list)) { - struct list_head *entry = asoc->addip_chunk_list.next; - struct sctp_chunk *asconf = list_entry(entry, - struct sctp_chunk, list); - list_del_init(entry); - - /* Hold the chunk until an ASCONF_ACK is received. */ - sctp_chunk_hold(asconf); - if (sctp_primitive_ASCONF(net, asoc, asconf)) - sctp_chunk_free(asconf); - else - asoc->addip_last_asconf = asconf; - } -} - - /* These three macros allow us to pull the debugging code out of the * main flow of sctp_do_sm() to keep attention focused on the real * functionality there. @@ -1783,9 +1757,6 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type, } sctp_cmd_send_msg(asoc, cmd->obj.msg, gfp); break; - case SCTP_CMD_SEND_NEXT_ASCONF: - sctp_cmd_send_asconf(asoc); - break; case SCTP_CMD_PURGE_ASCONF_QUEUE: sctp_asconf_queue_teardown(asoc); break; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index c9ae3404b1bb..713a669d2058 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -3824,6 +3824,29 @@ enum sctp_disposition sctp_sf_do_asconf(struct net *net, return SCTP_DISPOSITION_CONSUME; } +static enum sctp_disposition sctp_send_next_asconf( + struct net *net, + const struct sctp_endpoint *ep, + struct sctp_association *asoc, + const union sctp_subtype type, + struct sctp_cmd_seq *commands) +{ + struct sctp_chunk *asconf; + struct list_head *entry; + + if (list_empty(&asoc->addip_chunk_list)) + return SCTP_DISPOSITION_CONSUME; + + entry = asoc->addip_chunk_list.next; + asconf = list_entry(entry, struct sctp_chunk, list); + + list_del_init(entry); + sctp_chunk_hold(asconf); + asoc->addip_last_asconf = asconf; + + return sctp_sf_do_prm_asconf(net, ep, asoc, type, asconf, commands); +} + /* * ADDIP Section 4.3 General rules for address manipulation * When building TLV parameters for the ASCONF Chunk that will add or @@ -3915,14 +3938,10 @@ enum sctp_disposition sctp_sf_do_asconf_ack(struct net *net, SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO)); if (!sctp_process_asconf_ack((struct sctp_association *)asoc, - asconf_ack)) { - /* Successfully processed ASCONF_ACK. We can - * release the next asconf if we have one. - */ - sctp_add_cmd_sf(commands, SCTP_CMD_SEND_NEXT_ASCONF, - SCTP_NULL()); - return SCTP_DISPOSITION_CONSUME; - } + asconf_ack)) + return sctp_send_next_asconf(net, ep, + (struct sctp_association *)asoc, + type, commands); abort = sctp_make_abort(asoc, asconf_ack, sizeof(struct sctp_errhdr)); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 6140471efd4b..4583fa914e62 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -999,7 +999,7 @@ static int sctp_setsockopt_bindx(struct sock *sk, if (unlikely(addrs_size <= 0)) return -EINVAL; - kaddrs = vmemdup_user(addrs, addrs_size); + kaddrs = memdup_user(addrs, addrs_size); if (unlikely(IS_ERR(kaddrs))) return PTR_ERR(kaddrs); @@ -1007,7 +1007,7 @@ static int sctp_setsockopt_bindx(struct sock *sk, addr_buf = kaddrs; while (walk_size < addrs_size) { if (walk_size + sizeof(sa_family_t) > addrs_size) { - kvfree(kaddrs); + kfree(kaddrs); return -EINVAL; } @@ -1018,7 +1018,7 @@ static int sctp_setsockopt_bindx(struct sock *sk, * causes the address buffer to overflow return EINVAL. */ if (!af || (walk_size + af->sockaddr_len) > addrs_size) { - kvfree(kaddrs); + kfree(kaddrs); return -EINVAL; } addrcnt++; @@ -1054,7 +1054,7 @@ static int sctp_setsockopt_bindx(struct sock *sk, } out: - kvfree(kaddrs); + kfree(kaddrs); return err; } @@ -1329,7 +1329,7 @@ static int __sctp_setsockopt_connectx(struct sock *sk, if (unlikely(addrs_size <= 0)) return -EINVAL; - kaddrs = vmemdup_user(addrs, addrs_size); + kaddrs = memdup_user(addrs, addrs_size); if (unlikely(IS_ERR(kaddrs))) return PTR_ERR(kaddrs); @@ -1349,7 +1349,7 @@ static int __sctp_setsockopt_connectx(struct sock *sk, err = __sctp_connect(sk, kaddrs, addrs_size, flags, assoc_id); out_free: - kvfree(kaddrs); + kfree(kaddrs); return err; } @@ -2920,6 +2920,9 @@ static int sctp_setsockopt_delayed_ack(struct sock *sk, return 0; } + if (sctp_style(sk, TCP)) + params.sack_assoc_id = SCTP_FUTURE_ASSOC; + if (params.sack_assoc_id == SCTP_FUTURE_ASSOC || params.sack_assoc_id == SCTP_ALL_ASSOC) { if (params.sack_delay) { @@ -3024,6 +3027,9 @@ static int sctp_setsockopt_default_send_param(struct sock *sk, return 0; } + if (sctp_style(sk, TCP)) + info.sinfo_assoc_id = SCTP_FUTURE_ASSOC; + if (info.sinfo_assoc_id == SCTP_FUTURE_ASSOC || info.sinfo_assoc_id == SCTP_ALL_ASSOC) { sp->default_stream = info.sinfo_stream; @@ -3081,6 +3087,9 @@ static int sctp_setsockopt_default_sndinfo(struct sock *sk, return 0; } + if (sctp_style(sk, TCP)) + info.snd_assoc_id = SCTP_FUTURE_ASSOC; + if (info.snd_assoc_id == SCTP_FUTURE_ASSOC || info.snd_assoc_id == SCTP_ALL_ASSOC) { sp->default_stream = info.snd_sid; @@ -3531,6 +3540,9 @@ static int sctp_setsockopt_context(struct sock *sk, char __user *optval, return 0; } + if (sctp_style(sk, TCP)) + params.assoc_id = SCTP_FUTURE_ASSOC; + if (params.assoc_id == SCTP_FUTURE_ASSOC || params.assoc_id == SCTP_ALL_ASSOC) sp->default_rcv_context = params.assoc_value; @@ -3670,6 +3682,9 @@ static int sctp_setsockopt_maxburst(struct sock *sk, return 0; } + if (sctp_style(sk, TCP)) + params.assoc_id = SCTP_FUTURE_ASSOC; + if (params.assoc_id == SCTP_FUTURE_ASSOC || params.assoc_id == SCTP_ALL_ASSOC) sp->max_burst = params.assoc_value; @@ -3798,6 +3813,9 @@ static int sctp_setsockopt_auth_key(struct sock *sk, goto out; } + if (sctp_style(sk, TCP)) + authkey->sca_assoc_id = SCTP_FUTURE_ASSOC; + if (authkey->sca_assoc_id == SCTP_FUTURE_ASSOC || authkey->sca_assoc_id == SCTP_ALL_ASSOC) { ret = sctp_auth_set_key(ep, asoc, authkey); @@ -3853,6 +3871,9 @@ static int sctp_setsockopt_active_key(struct sock *sk, if (asoc) return sctp_auth_set_active_key(ep, asoc, val.scact_keynumber); + if (sctp_style(sk, TCP)) + val.scact_assoc_id = SCTP_FUTURE_ASSOC; + if (val.scact_assoc_id == SCTP_FUTURE_ASSOC || val.scact_assoc_id == SCTP_ALL_ASSOC) { ret = sctp_auth_set_active_key(ep, asoc, val.scact_keynumber); @@ -3904,6 +3925,9 @@ static int sctp_setsockopt_del_key(struct sock *sk, if (asoc) return sctp_auth_del_key_id(ep, asoc, val.scact_keynumber); + if (sctp_style(sk, TCP)) + val.scact_assoc_id = SCTP_FUTURE_ASSOC; + if (val.scact_assoc_id == SCTP_FUTURE_ASSOC || val.scact_assoc_id == SCTP_ALL_ASSOC) { ret = sctp_auth_del_key_id(ep, asoc, val.scact_keynumber); @@ -3954,6 +3978,9 @@ static int sctp_setsockopt_deactivate_key(struct sock *sk, char __user *optval, if (asoc) return sctp_auth_deact_key_id(ep, asoc, val.scact_keynumber); + if (sctp_style(sk, TCP)) + val.scact_assoc_id = SCTP_FUTURE_ASSOC; + if (val.scact_assoc_id == SCTP_FUTURE_ASSOC || val.scact_assoc_id == SCTP_ALL_ASSOC) { ret = sctp_auth_deact_key_id(ep, asoc, val.scact_keynumber); @@ -4169,6 +4196,9 @@ static int sctp_setsockopt_default_prinfo(struct sock *sk, goto out; } + if (sctp_style(sk, TCP)) + info.pr_assoc_id = SCTP_FUTURE_ASSOC; + if (info.pr_assoc_id == SCTP_FUTURE_ASSOC || info.pr_assoc_id == SCTP_ALL_ASSOC) { SCTP_PR_SET_POLICY(sp->default_flags, info.pr_policy); @@ -4251,6 +4281,9 @@ static int sctp_setsockopt_enable_strreset(struct sock *sk, goto out; } + if (sctp_style(sk, TCP)) + params.assoc_id = SCTP_FUTURE_ASSOC; + if (params.assoc_id == SCTP_FUTURE_ASSOC || params.assoc_id == SCTP_ALL_ASSOC) ep->strreset_enable = params.assoc_value; @@ -4376,6 +4409,9 @@ static int sctp_setsockopt_scheduler(struct sock *sk, if (asoc) return sctp_sched_set_sched(asoc, params.assoc_value); + if (sctp_style(sk, TCP)) + params.assoc_id = SCTP_FUTURE_ASSOC; + if (params.assoc_id == SCTP_FUTURE_ASSOC || params.assoc_id == SCTP_ALL_ASSOC) sp->default_ss = params.assoc_value; @@ -4541,6 +4577,9 @@ static int sctp_setsockopt_event(struct sock *sk, char __user *optval, if (asoc) return sctp_assoc_ulpevent_type_set(¶m, asoc); + if (sctp_style(sk, TCP)) + param.se_assoc_id = SCTP_FUTURE_ASSOC; + if (param.se_assoc_id == SCTP_FUTURE_ASSOC || param.se_assoc_id == SCTP_ALL_ASSOC) sctp_ulpevent_type_set(&sp->subscribe, @@ -4808,7 +4847,8 @@ static int sctp_connect(struct sock *sk, struct sockaddr *addr, } /* Validate addr_len before calling common connect/connectx routine. */ - af = sctp_get_af_specific(addr->sa_family); + af = addr_len < offsetofend(struct sockaddr, sa_family) ? NULL : + sctp_get_af_specific(addr->sa_family); if (!af || addr_len < af->sockaddr_len) { err = -EINVAL; } else { @@ -9169,7 +9209,7 @@ static inline void sctp_copy_descendant(struct sock *sk_to, { int ancestor_size = sizeof(struct inet_sock) + sizeof(struct sctp_sock) - - offsetof(struct sctp_sock, auto_asconf_list); + offsetof(struct sctp_sock, pd_lobby); if (sk_from->sk_family == PF_INET6) ancestor_size += sizeof(struct ipv6_pinfo); @@ -9253,7 +9293,6 @@ static int sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, * 2) Peeling off partial delivery; keep pd_lobby in new pd_lobby. * 3) Peeling off non-partial delivery; move pd_lobby to receive_queue. */ - skb_queue_head_init(&newsp->pd_lobby); atomic_set(&sctp_sk(newsk)->pd_mode, assoc->ulpq.pd_mode); if (atomic_read(&sctp_sk(oldsk)->pd_mode)) { diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 77ef53596d18..6f869ef49b32 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -167,10 +167,9 @@ static int smc_release(struct socket *sock) if (sk->sk_state == SMC_CLOSED) { if (smc->clcsock) { - mutex_lock(&smc->clcsock_release_lock); - sock_release(smc->clcsock); - smc->clcsock = NULL; - mutex_unlock(&smc->clcsock_release_lock); + release_sock(sk); + smc_clcsock_release(smc); + lock_sock(sk); } if (!smc->use_fallback) smc_conn_free(&smc->conn); @@ -446,10 +445,19 @@ static void smc_link_save_peer_info(struct smc_link *link, link->peer_mtu = clc->qp_mtu; } +static void smc_switch_to_fallback(struct smc_sock *smc) +{ + smc->use_fallback = true; + if (smc->sk.sk_socket && smc->sk.sk_socket->file) { + smc->clcsock->file = smc->sk.sk_socket->file; + smc->clcsock->file->private_data = smc->clcsock; + } +} + /* fall back during connect */ static int smc_connect_fallback(struct smc_sock *smc, int reason_code) { - smc->use_fallback = true; + smc_switch_to_fallback(smc); smc->fallback_rsn = reason_code; smc_copy_sock_settings_to_clc(smc); if (smc->sk.sk_state == SMC_INIT) @@ -775,10 +783,14 @@ static void smc_connect_work(struct work_struct *work) smc->sk.sk_err = -rc; out: - if (smc->sk.sk_err) - smc->sk.sk_state_change(&smc->sk); - else - smc->sk.sk_write_space(&smc->sk); + if (!sock_flag(&smc->sk, SOCK_DEAD)) { + if (smc->sk.sk_err) { + smc->sk.sk_state_change(&smc->sk); + } else { /* allow polling before and after fallback decision */ + smc->clcsock->sk->sk_write_space(smc->clcsock->sk); + smc->sk.sk_write_space(&smc->sk); + } + } kfree(smc->connect_info); smc->connect_info = NULL; release_sock(&smc->sk); @@ -872,11 +884,11 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc) if (rc < 0) lsk->sk_err = -rc; if (rc < 0 || lsk->sk_state == SMC_CLOSED) { + new_sk->sk_prot->unhash(new_sk); if (new_clcsock) sock_release(new_clcsock); new_sk->sk_state = SMC_CLOSED; sock_set_flag(new_sk, SOCK_DEAD); - new_sk->sk_prot->unhash(new_sk); sock_put(new_sk); /* final */ *new_smc = NULL; goto out; @@ -927,16 +939,21 @@ struct sock *smc_accept_dequeue(struct sock *parent, smc_accept_unlink(new_sk); if (new_sk->sk_state == SMC_CLOSED) { + new_sk->sk_prot->unhash(new_sk); if (isk->clcsock) { sock_release(isk->clcsock); isk->clcsock = NULL; } - new_sk->sk_prot->unhash(new_sk); sock_put(new_sk); /* final */ continue; } - if (new_sock) + if (new_sock) { sock_graft(new_sk, new_sock); + if (isk->use_fallback) { + smc_sk(new_sk)->clcsock->file = new_sock->file; + isk->clcsock->file->private_data = isk->clcsock; + } + } return new_sk; } return NULL; @@ -956,6 +973,7 @@ void smc_close_non_accepted(struct sock *sk) sock_set_flag(sk, SOCK_DEAD); sk->sk_shutdown |= SHUTDOWN_MASK; } + sk->sk_prot->unhash(sk); if (smc->clcsock) { struct socket *tcp; @@ -971,7 +989,6 @@ void smc_close_non_accepted(struct sock *sk) smc_conn_free(&smc->conn); } release_sock(sk); - sk->sk_prot->unhash(sk); sock_put(sk); /* final sock_put */ } @@ -1037,13 +1054,13 @@ static void smc_listen_out(struct smc_sock *new_smc) struct smc_sock *lsmc = new_smc->listen_smc; struct sock *newsmcsk = &new_smc->sk; - lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING); if (lsmc->sk.sk_state == SMC_LISTEN) { + lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING); smc_accept_enqueue(&lsmc->sk, newsmcsk); + release_sock(&lsmc->sk); } else { /* no longer listening */ smc_close_non_accepted(newsmcsk); } - release_sock(&lsmc->sk); /* Wake up accept */ lsmc->sk.sk_data_ready(&lsmc->sk); @@ -1087,7 +1104,7 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code, return; } smc_conn_free(&new_smc->conn); - new_smc->use_fallback = true; + smc_switch_to_fallback(new_smc); new_smc->fallback_rsn = reason_code; if (reason_code && reason_code != SMC_CLC_DECL_PEERDECL) { if (smc_clc_send_decline(new_smc, reason_code) < 0) { @@ -1237,6 +1254,9 @@ static void smc_listen_work(struct work_struct *work) int rc = 0; u8 ibport; + if (new_smc->listen_smc->sk.sk_state != SMC_LISTEN) + return smc_listen_out_err(new_smc); + if (new_smc->use_fallback) { smc_listen_out_connected(new_smc); return; @@ -1244,7 +1264,7 @@ static void smc_listen_work(struct work_struct *work) /* check if peer is smc capable */ if (!tcp_sk(newclcsock->sk)->syn_smc) { - new_smc->use_fallback = true; + smc_switch_to_fallback(new_smc); new_smc->fallback_rsn = SMC_CLC_DECL_PEERNOSMC; smc_listen_out_connected(new_smc); return; @@ -1501,7 +1521,7 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (msg->msg_flags & MSG_FASTOPEN) { if (sk->sk_state == SMC_INIT) { - smc->use_fallback = true; + smc_switch_to_fallback(smc); smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; } else { rc = -EINVAL; @@ -1703,7 +1723,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, case TCP_FASTOPEN_NO_COOKIE: /* option not supported by SMC */ if (sk->sk_state == SMC_INIT) { - smc->use_fallback = true; + smc_switch_to_fallback(smc); smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; } else { if (!smc->use_fallback) diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index 2ad37e998509..fc06720b53c1 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -21,6 +21,22 @@ #define SMC_CLOSE_WAIT_LISTEN_CLCSOCK_TIME (5 * HZ) +/* release the clcsock that is assigned to the smc_sock */ +void smc_clcsock_release(struct smc_sock *smc) +{ + struct socket *tcp; + + if (smc->listen_smc && current_work() != &smc->smc_listen_work) + cancel_work_sync(&smc->smc_listen_work); + mutex_lock(&smc->clcsock_release_lock); + if (smc->clcsock) { + tcp = smc->clcsock; + smc->clcsock = NULL; + sock_release(tcp); + } + mutex_unlock(&smc->clcsock_release_lock); +} + static void smc_close_cleanup_listen(struct sock *parent) { struct sock *sk; @@ -321,6 +337,7 @@ static void smc_close_passive_work(struct work_struct *work) close_work); struct smc_sock *smc = container_of(conn, struct smc_sock, conn); struct smc_cdc_conn_state_flags *rxflags; + bool release_clcsock = false; struct sock *sk = &smc->sk; int old_state; @@ -400,13 +417,13 @@ wakeup: if ((sk->sk_state == SMC_CLOSED) && (sock_flag(sk, SOCK_DEAD) || !sk->sk_socket)) { smc_conn_free(conn); - if (smc->clcsock) { - sock_release(smc->clcsock); - smc->clcsock = NULL; - } + if (smc->clcsock) + release_clcsock = true; } } release_sock(sk); + if (release_clcsock) + smc_clcsock_release(smc); sock_put(sk); /* sock_hold done by schedulers of close_work */ } diff --git a/net/smc/smc_close.h b/net/smc/smc_close.h index 19eb6a211c23..e0e3b5df25d2 100644 --- a/net/smc/smc_close.h +++ b/net/smc/smc_close.h @@ -23,5 +23,6 @@ void smc_close_wake_tx_prepared(struct smc_sock *smc); int smc_close_active(struct smc_sock *smc); int smc_close_shutdown_write(struct smc_sock *smc); void smc_close_init(struct smc_sock *smc); +void smc_clcsock_release(struct smc_sock *smc); #endif /* SMC_CLOSE_H */ diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c index 2fff79db1a59..e89e918b88e0 100644 --- a/net/smc/smc_ism.c +++ b/net/smc/smc_ism.c @@ -289,6 +289,11 @@ struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name, INIT_LIST_HEAD(&smcd->vlan); smcd->event_wq = alloc_ordered_workqueue("ism_evt_wq-%s)", WQ_MEM_RECLAIM, name); + if (!smcd->event_wq) { + kfree(smcd->conn); + kfree(smcd); + return NULL; + } return smcd; } EXPORT_SYMBOL_GPL(smcd_alloc_dev); diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 8d2f6296279c..0285c7f9e79b 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -603,7 +603,8 @@ static int smc_pnet_flush(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); - return smc_pnet_remove_by_pnetid(net, NULL); + smc_pnet_remove_by_pnetid(net, NULL); + return 0; } /* SMC_PNETID generic netlink operation definition */ diff --git a/net/socket.c b/net/socket.c index 3c176a12fe48..8255f5bda0aa 100644 --- a/net/socket.c +++ b/net/socket.c @@ -384,6 +384,18 @@ static struct file_system_type sock_fs_type = { * but we take care of internal coherence yet. */ +/** + * sock_alloc_file - Bind a &socket to a &file + * @sock: socket + * @flags: file status flags + * @dname: protocol name + * + * Returns the &file bound with @sock, implicitly storing it + * in sock->file. If dname is %NULL, sets to "". + * On failure the return is a ERR pointer (see linux/err.h). + * This function uses GFP_KERNEL internally. + */ + struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname) { struct file *file; @@ -424,6 +436,14 @@ static int sock_map_fd(struct socket *sock, int flags) return PTR_ERR(newfile); } +/** + * sock_from_file - Return the &socket bounded to @file. + * @file: file + * @err: pointer to an error code return + * + * On failure returns %NULL and assigns -ENOTSOCK to @err. + */ + struct socket *sock_from_file(struct file *file, int *err) { if (file->f_op == &socket_file_ops) @@ -532,11 +552,11 @@ static const struct inode_operations sockfs_inode_ops = { }; /** - * sock_alloc - allocate a socket + * sock_alloc - allocate a socket * * Allocate a new inode and socket object. The two are bound together * and initialised. The socket is then returned. If we are out of inodes - * NULL is returned. + * NULL is returned. This functions uses GFP_KERNEL internally. */ struct socket *sock_alloc(void) @@ -561,7 +581,7 @@ struct socket *sock_alloc(void) EXPORT_SYMBOL(sock_alloc); /** - * sock_release - close a socket + * sock_release - close a socket * @sock: socket to close * * The socket is released from the protocol stack if it has a release @@ -617,6 +637,15 @@ void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags) } EXPORT_SYMBOL(__sock_tx_timestamp); +/** + * sock_sendmsg - send a message through @sock + * @sock: socket + * @msg: message to send + * + * Sends @msg through @sock, passing through LSM. + * Returns the number of bytes sent, or an error code. + */ + static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg) { int ret = sock->ops->sendmsg(sock, msg, msg_data_left(msg)); @@ -633,6 +662,18 @@ int sock_sendmsg(struct socket *sock, struct msghdr *msg) } EXPORT_SYMBOL(sock_sendmsg); +/** + * kernel_sendmsg - send a message through @sock (kernel-space) + * @sock: socket + * @msg: message header + * @vec: kernel vec + * @num: vec array length + * @size: total message data size + * + * Builds the message data with @vec and sends it through @sock. + * Returns the number of bytes sent, or an error code. + */ + int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t size) { @@ -641,6 +682,19 @@ int kernel_sendmsg(struct socket *sock, struct msghdr *msg, } EXPORT_SYMBOL(kernel_sendmsg); +/** + * kernel_sendmsg_locked - send a message through @sock (kernel-space) + * @sk: sock + * @msg: message header + * @vec: output s/g array + * @num: output s/g array length + * @size: total message data size + * + * Builds the message data with @vec and sends it through @sock. + * Returns the number of bytes sent, or an error code. + * Caller must hold @sk. + */ + int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, struct kvec *vec, size_t num, size_t size) { @@ -811,6 +865,16 @@ void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, } EXPORT_SYMBOL_GPL(__sock_recv_ts_and_drops); +/** + * sock_recvmsg - receive a message from @sock + * @sock: socket + * @msg: message to receive + * @flags: message flags + * + * Receives @msg from @sock, passing through LSM. Returns the total number + * of bytes received, or an error. + */ + static inline int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg, int flags) { @@ -826,20 +890,21 @@ int sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags) EXPORT_SYMBOL(sock_recvmsg); /** - * kernel_recvmsg - Receive a message from a socket (kernel space) - * @sock: The socket to receive the message from - * @msg: Received message - * @vec: Input s/g array for message data - * @num: Size of input s/g array - * @size: Number of bytes to read - * @flags: Message flags (MSG_DONTWAIT, etc...) + * kernel_recvmsg - Receive a message from a socket (kernel space) + * @sock: The socket to receive the message from + * @msg: Received message + * @vec: Input s/g array for message data + * @num: Size of input s/g array + * @size: Number of bytes to read + * @flags: Message flags (MSG_DONTWAIT, etc...) * - * On return the msg structure contains the scatter/gather array passed in the - * vec argument. The array is modified so that it consists of the unfilled - * portion of the original array. + * On return the msg structure contains the scatter/gather array passed in the + * vec argument. The array is modified so that it consists of the unfilled + * portion of the original array. * - * The returned value is the total number of bytes received, or an error. + * The returned value is the total number of bytes received, or an error. */ + int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t size, int flags) { @@ -1005,6 +1070,13 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, * what to do with it - that's up to the protocol still. */ +/** + * get_net_ns - increment the refcount of the network namespace + * @ns: common namespace (net) + * + * Returns the net's common namespace. + */ + struct ns_common *get_net_ns(struct ns_common *ns) { return &get_net(container_of(ns, struct net, ns))->ns; @@ -1099,6 +1171,19 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) return err; } +/** + * sock_create_lite - creates a socket + * @family: protocol family (AF_INET, ...) + * @type: communication type (SOCK_STREAM, ...) + * @protocol: protocol (0, ...) + * @res: new socket + * + * Creates a new socket and assigns it to @res, passing through LSM. + * The new socket initialization is not complete, see kernel_accept(). + * Returns 0 or an error. On failure @res is set to %NULL. + * This function internally uses GFP_KERNEL. + */ + int sock_create_lite(int family, int type, int protocol, struct socket **res) { int err; @@ -1224,6 +1309,21 @@ call_kill: } EXPORT_SYMBOL(sock_wake_async); +/** + * __sock_create - creates a socket + * @net: net namespace + * @family: protocol family (AF_INET, ...) + * @type: communication type (SOCK_STREAM, ...) + * @protocol: protocol (0, ...) + * @res: new socket + * @kern: boolean for kernel space sockets + * + * Creates a new socket and assigns it to @res, passing through LSM. + * Returns 0 or an error. On failure @res is set to %NULL. @kern must + * be set to true if the socket resides in kernel space. + * This function internally uses GFP_KERNEL. + */ + int __sock_create(struct net *net, int family, int type, int protocol, struct socket **res, int kern) { @@ -1333,12 +1433,35 @@ out_release: } EXPORT_SYMBOL(__sock_create); +/** + * sock_create - creates a socket + * @family: protocol family (AF_INET, ...) + * @type: communication type (SOCK_STREAM, ...) + * @protocol: protocol (0, ...) + * @res: new socket + * + * A wrapper around __sock_create(). + * Returns 0 or an error. This function internally uses GFP_KERNEL. + */ + int sock_create(int family, int type, int protocol, struct socket **res) { return __sock_create(current->nsproxy->net_ns, family, type, protocol, res, 0); } EXPORT_SYMBOL(sock_create); +/** + * sock_create_kern - creates a socket (kernel space) + * @net: net namespace + * @family: protocol family (AF_INET, ...) + * @type: communication type (SOCK_STREAM, ...) + * @protocol: protocol (0, ...) + * @res: new socket + * + * A wrapper around __sock_create(). + * Returns 0 or an error. This function internally uses GFP_KERNEL. + */ + int sock_create_kern(struct net *net, int family, int type, int protocol, struct socket **res) { return __sock_create(net, family, type, protocol, res, 1); @@ -3322,18 +3445,46 @@ static long compat_sock_ioctl(struct file *file, unsigned int cmd, } #endif +/** + * kernel_bind - bind an address to a socket (kernel space) + * @sock: socket + * @addr: address + * @addrlen: length of address + * + * Returns 0 or an error. + */ + int kernel_bind(struct socket *sock, struct sockaddr *addr, int addrlen) { return sock->ops->bind(sock, addr, addrlen); } EXPORT_SYMBOL(kernel_bind); +/** + * kernel_listen - move socket to listening state (kernel space) + * @sock: socket + * @backlog: pending connections queue size + * + * Returns 0 or an error. + */ + int kernel_listen(struct socket *sock, int backlog) { return sock->ops->listen(sock, backlog); } EXPORT_SYMBOL(kernel_listen); +/** + * kernel_accept - accept a connection (kernel space) + * @sock: listening socket + * @newsock: new connected socket + * @flags: flags + * + * @flags must be SOCK_CLOEXEC, SOCK_NONBLOCK or 0. + * If it fails, @newsock is guaranteed to be %NULL. + * Returns 0 or an error. + */ + int kernel_accept(struct socket *sock, struct socket **newsock, int flags) { struct sock *sk = sock->sk; @@ -3359,6 +3510,19 @@ done: } EXPORT_SYMBOL(kernel_accept); +/** + * kernel_connect - connect a socket (kernel space) + * @sock: socket + * @addr: address + * @addrlen: address length + * @flags: flags (O_NONBLOCK, ...) + * + * For datagram sockets, @addr is the addres to which datagrams are sent + * by default, and the only address from which datagrams are received. + * For stream sockets, attempts to connect to @addr. + * Returns 0 or an error code. + */ + int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen, int flags) { @@ -3366,18 +3530,48 @@ int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen, } EXPORT_SYMBOL(kernel_connect); +/** + * kernel_getsockname - get the address which the socket is bound (kernel space) + * @sock: socket + * @addr: address holder + * + * Fills the @addr pointer with the address which the socket is bound. + * Returns 0 or an error code. + */ + int kernel_getsockname(struct socket *sock, struct sockaddr *addr) { return sock->ops->getname(sock, addr, 0); } EXPORT_SYMBOL(kernel_getsockname); +/** + * kernel_peername - get the address which the socket is connected (kernel space) + * @sock: socket + * @addr: address holder + * + * Fills the @addr pointer with the address which the socket is connected. + * Returns 0 or an error code. + */ + int kernel_getpeername(struct socket *sock, struct sockaddr *addr) { return sock->ops->getname(sock, addr, 1); } EXPORT_SYMBOL(kernel_getpeername); +/** + * kernel_getsockopt - get a socket option (kernel space) + * @sock: socket + * @level: API level (SOL_SOCKET, ...) + * @optname: option tag + * @optval: option value + * @optlen: option length + * + * Assigns the option length to @optlen. + * Returns 0 or an error. + */ + int kernel_getsockopt(struct socket *sock, int level, int optname, char *optval, int *optlen) { @@ -3400,6 +3594,17 @@ int kernel_getsockopt(struct socket *sock, int level, int optname, } EXPORT_SYMBOL(kernel_getsockopt); +/** + * kernel_setsockopt - set a socket option (kernel space) + * @sock: socket + * @level: API level (SOL_SOCKET, ...) + * @optname: option tag + * @optval: option value + * @optlen: option length + * + * Returns 0 or an error. + */ + int kernel_setsockopt(struct socket *sock, int level, int optname, char *optval, unsigned int optlen) { @@ -3420,6 +3625,17 @@ int kernel_setsockopt(struct socket *sock, int level, int optname, } EXPORT_SYMBOL(kernel_setsockopt); +/** + * kernel_sendpage - send a &page through a socket (kernel space) + * @sock: socket + * @page: page + * @offset: page offset + * @size: total size in bytes + * @flags: flags (MSG_DONTWAIT, ...) + * + * Returns the total amount sent in bytes or an error. + */ + int kernel_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { @@ -3430,6 +3646,18 @@ int kernel_sendpage(struct socket *sock, struct page *page, int offset, } EXPORT_SYMBOL(kernel_sendpage); +/** + * kernel_sendpage_locked - send a &page through the locked sock (kernel space) + * @sk: sock + * @page: page + * @offset: page offset + * @size: total size in bytes + * @flags: flags (MSG_DONTWAIT, ...) + * + * Returns the total amount sent in bytes or an error. + * Caller must hold @sk. + */ + int kernel_sendpage_locked(struct sock *sk, struct page *page, int offset, size_t size, int flags) { @@ -3443,17 +3671,30 @@ int kernel_sendpage_locked(struct sock *sk, struct page *page, int offset, } EXPORT_SYMBOL(kernel_sendpage_locked); +/** + * kernel_shutdown - shut down part of a full-duplex connection (kernel space) + * @sock: socket + * @how: connection part + * + * Returns 0 or an error. + */ + int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how) { return sock->ops->shutdown(sock, how); } EXPORT_SYMBOL(kernel_sock_shutdown); -/* This routine returns the IP overhead imposed by a socket i.e. - * the length of the underlying IP header, depending on whether - * this is an IPv4 or IPv6 socket and the length from IP options turned - * on at the socket. Assumes that the caller has a lock on the socket. +/** + * kernel_sock_ip_overhead - returns the IP overhead imposed by a socket + * @sk: socket + * + * This routine returns the IP overhead imposed by a socket i.e. + * the length of the underlying IP header, depending on whether + * this is an IPv4 or IPv6 socket and the length from IP options turned + * on at the socket. Assumes that the caller has a lock on the socket. */ + u32 kernel_sock_ip_overhead(struct sock *sk) { struct inet_sock *inet; diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index da1a676860ca..fa6c977b4c41 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -140,13 +140,11 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, /* We are going to append to the frags_list of head. * Need to unshare the frag_list. */ - if (skb_has_frag_list(head)) { - err = skb_unclone(head, GFP_ATOMIC); - if (err) { - STRP_STATS_INCR(strp->stats.mem_fail); - desc->error = err; - return 0; - } + err = skb_unclone(head, GFP_ATOMIC); + if (err) { + STRP_STATS_INCR(strp->stats.mem_fail); + desc->error = err; + return 0; } if (unlikely(skb_shinfo(head)->frag_list)) { @@ -550,6 +548,8 @@ EXPORT_SYMBOL_GPL(strp_check_rcv); static int __init strp_mod_init(void) { strp_wq = create_singlethread_workqueue("kstrp"); + if (unlikely(!strp_wq)) + return -ENOMEM; return 0; } diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 12bb23b8e0c5..261131dfa1f1 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -54,6 +54,7 @@ static void cache_init(struct cache_head *h, struct cache_detail *detail) h->last_refresh = now; } +static inline int cache_is_valid(struct cache_head *h); static void cache_fresh_locked(struct cache_head *head, time_t expiry, struct cache_detail *detail); static void cache_fresh_unlocked(struct cache_head *head, @@ -105,6 +106,8 @@ static struct cache_head *sunrpc_cache_add_entry(struct cache_detail *detail, if (cache_is_expired(detail, tmp)) { hlist_del_init_rcu(&tmp->cache_list); detail->entries --; + if (cache_is_valid(tmp) == -EAGAIN) + set_bit(CACHE_NEGATIVE, &tmp->flags); cache_fresh_locked(tmp, 0, detail); freeme = tmp; break; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 228970e6e52b..8ff11dc98d7f 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1540,7 +1540,6 @@ call_start(struct rpc_task *task) clnt->cl_stats->rpccnt++; task->tk_action = call_reserve; rpc_task_set_transport(task, clnt); - call_reserve(task); } /* @@ -1554,9 +1553,6 @@ call_reserve(struct rpc_task *task) task->tk_status = 0; task->tk_action = call_reserveresult; xprt_reserve(task); - if (rpc_task_need_resched(task)) - return; - call_reserveresult(task); } static void call_retry_reserve(struct rpc_task *task); @@ -1579,7 +1575,6 @@ call_reserveresult(struct rpc_task *task) if (status >= 0) { if (task->tk_rqstp) { task->tk_action = call_refresh; - call_refresh(task); return; } @@ -1605,7 +1600,6 @@ call_reserveresult(struct rpc_task *task) /* fall through */ case -EAGAIN: /* woken up; retry */ task->tk_action = call_retry_reserve; - call_retry_reserve(task); return; case -EIO: /* probably a shutdown */ break; @@ -1628,9 +1622,6 @@ call_retry_reserve(struct rpc_task *task) task->tk_status = 0; task->tk_action = call_reserveresult; xprt_retry_reserve(task); - if (rpc_task_need_resched(task)) - return; - call_reserveresult(task); } /* @@ -1645,9 +1636,6 @@ call_refresh(struct rpc_task *task) task->tk_status = 0; task->tk_client->cl_stats->rpcauthrefresh++; rpcauth_refreshcred(task); - if (rpc_task_need_resched(task)) - return; - call_refreshresult(task); } /* @@ -1666,7 +1654,6 @@ call_refreshresult(struct rpc_task *task) case 0: if (rpcauth_uptodatecred(task)) { task->tk_action = call_allocate; - call_allocate(task); return; } /* Use rate-limiting and a max number of retries if refresh @@ -1685,7 +1672,6 @@ call_refreshresult(struct rpc_task *task) task->tk_cred_retry--; dprintk("RPC: %5u %s: retry refresh creds\n", task->tk_pid, __func__); - call_refresh(task); return; } dprintk("RPC: %5u %s: refresh creds failed with error %d\n", @@ -1711,10 +1697,8 @@ call_allocate(struct rpc_task *task) task->tk_status = 0; task->tk_action = call_encode; - if (req->rq_buffer) { - call_encode(task); + if (req->rq_buffer) return; - } if (proc->p_proc != 0) { BUG_ON(proc->p_arglen == 0); @@ -1740,12 +1724,8 @@ call_allocate(struct rpc_task *task) status = xprt->ops->buf_alloc(task); xprt_inject_disconnect(xprt); - if (status == 0) { - if (rpc_task_need_resched(task)) - return; - call_encode(task); + if (status == 0) return; - } if (status != -ENOMEM) { rpc_exit(task, status); return; @@ -1828,8 +1808,12 @@ call_encode(struct rpc_task *task) xprt_request_enqueue_receive(task); xprt_request_enqueue_transmit(task); out: - task->tk_action = call_bind; - call_bind(task); + task->tk_action = call_transmit; + /* Check that the connection is OK */ + if (!xprt_bound(task->tk_xprt)) + task->tk_action = call_bind; + else if (!xprt_connected(task->tk_xprt)) + task->tk_action = call_connect; } /* @@ -1847,7 +1831,6 @@ rpc_task_handle_transmitted(struct rpc_task *task) { xprt_end_transmit(task); task->tk_action = call_transmit_status; - call_transmit_status(task); } /* @@ -1865,7 +1848,6 @@ call_bind(struct rpc_task *task) if (xprt_bound(xprt)) { task->tk_action = call_connect; - call_connect(task); return; } @@ -1896,7 +1878,6 @@ call_bind_status(struct rpc_task *task) dprint_status(task); task->tk_status = 0; task->tk_action = call_connect; - call_connect(task); return; } @@ -1981,7 +1962,6 @@ call_connect(struct rpc_task *task) if (xprt_connected(xprt)) { task->tk_action = call_transmit; - call_transmit(task); return; } @@ -2051,7 +2031,6 @@ call_connect_status(struct rpc_task *task) case 0: clnt->cl_stats->netreconn++; task->tk_action = call_transmit; - call_transmit(task); return; } rpc_exit(task, status); @@ -2087,9 +2066,6 @@ call_transmit(struct rpc_task *task) xprt_transmit(task); } xprt_end_transmit(task); - if (rpc_task_need_resched(task)) - return; - call_transmit_status(task); } /* @@ -2105,11 +2081,8 @@ call_transmit_status(struct rpc_task *task) * test first. */ if (rpc_task_transmitted(task)) { - if (task->tk_status == 0) - xprt_request_wait_receive(task); - if (rpc_task_need_resched(task)) - return; - call_status(task); + task->tk_status = 0; + xprt_request_wait_receive(task); return; } @@ -2170,7 +2143,6 @@ call_bc_encode(struct rpc_task *task) { xprt_request_enqueue_transmit(task); task->tk_action = call_bc_transmit; - call_bc_transmit(task); } /* @@ -2195,6 +2167,9 @@ call_bc_transmit_status(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; + if (rpc_task_transmitted(task)) + task->tk_status = 0; + dprint_status(task); switch (task->tk_status) { @@ -2261,7 +2236,6 @@ call_status(struct rpc_task *task) status = task->tk_status; if (status >= 0) { task->tk_action = call_decode; - call_decode(task); return; } @@ -2311,6 +2285,15 @@ out_exit: rpc_exit(task, status); } +static bool +rpc_check_connected(const struct rpc_rqst *req) +{ + /* No allocated request or transport? return true */ + if (!req || !req->rq_xprt) + return true; + return xprt_connected(req->rq_xprt); +} + static void rpc_check_timeout(struct rpc_task *task) { @@ -2322,10 +2305,11 @@ rpc_check_timeout(struct rpc_task *task) dprintk("RPC: %5u call_timeout (major)\n", task->tk_pid); task->tk_timeouts++; - if (RPC_IS_SOFTCONN(task)) { + if (RPC_IS_SOFTCONN(task) && !rpc_check_connected(task->tk_rqstp)) { rpc_exit(task, -ETIMEDOUT); return; } + if (RPC_IS_SOFT(task)) { if (clnt->cl_chatty) { printk(KERN_NOTICE "%s: server %s not responding, timed out\n", diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 89a63391d4d4..30cfc0efe699 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -90,7 +90,7 @@ static void rpcrdma_xprt_drain(struct rpcrdma_xprt *r_xprt) /* Flush Receives, then wait for deferred Reply work * to complete. */ - ib_drain_qp(ia->ri_id->qp); + ib_drain_rq(ia->ri_id->qp); drain_workqueue(buf->rb_completion_wq); /* Deferred Reply processing might have scheduled diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 9359539907ba..732d4b57411a 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -495,8 +495,8 @@ xs_read_stream_request(struct sock_xprt *transport, struct msghdr *msg, int flags, struct rpc_rqst *req) { struct xdr_buf *buf = &req->rq_private_buf; - size_t want, read; - ssize_t ret; + size_t want, uninitialized_var(read); + ssize_t uninitialized_var(ret); xs_read_header(transport, buf); diff --git a/net/tipc/group.c b/net/tipc/group.c index 06fee142f09f..63f39201e41e 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -919,6 +919,9 @@ int tipc_group_fill_sock_diag(struct tipc_group *grp, struct sk_buff *skb) { struct nlattr *group = nla_nest_start(skb, TIPC_NLA_SOCK_GROUP); + if (!group) + return -EMSGSIZE; + if (nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_ID, grp->type) || nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_INSTANCE, diff --git a/net/tipc/link.c b/net/tipc/link.c index 341ecd796aa4..131aa2f0fd27 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -869,6 +869,8 @@ void tipc_link_reset(struct tipc_link *l) __skb_queue_head_init(&list); l->in_session = false; + /* Force re-synch of peer session number before establishing */ + l->peer_session--; l->session++; l->mtu = l->advertised_mtu; diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index bff241f03525..89993afe0fbd 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -909,7 +909,8 @@ static int tipc_nl_service_list(struct net *net, struct tipc_nl_msg *msg, for (; i < TIPC_NAMETBL_SIZE; i++) { head = &tn->nametbl->services[i]; - if (*last_type) { + if (*last_type || + (!i && *last_key && (*last_lower == *last_key))) { service = tipc_service_find(net, *last_type); if (!service) return -EPIPE; diff --git a/net/tipc/net.c b/net/tipc/net.c index f076edb74338..7ce1e86b024f 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -163,12 +163,9 @@ void tipc_sched_net_finalize(struct net *net, u32 addr) void tipc_net_stop(struct net *net) { - u32 self = tipc_own_addr(net); - - if (!self) + if (!tipc_own_id(net)) return; - tipc_nametbl_withdraw(net, TIPC_CFG_SRV, self, self, self); rtnl_lock(); tipc_bearer_stop(net); tipc_node_stop(net); diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 4ad3586da8f0..340a6e7c43a7 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -267,8 +267,14 @@ static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, if (msg->rep_type) tipc_tlv_init(msg->rep, msg->rep_type); - if (cmd->header) - (*cmd->header)(msg); + if (cmd->header) { + err = (*cmd->header)(msg); + if (err) { + kfree_skb(msg->rep); + msg->rep = NULL; + return err; + } + } arg = nlmsg_new(0, GFP_KERNEL); if (!arg) { @@ -397,7 +403,12 @@ static int tipc_nl_compat_bearer_enable(struct tipc_nl_compat_cmd_doit *cmd, if (!bearer) return -EMSGSIZE; - len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_BEARER_NAME); + len = TLV_GET_DATA_LEN(msg->req); + len -= offsetof(struct tipc_bearer_config, name); + if (len <= 0) + return -EINVAL; + + len = min_t(int, len, TIPC_MAX_BEARER_NAME); if (!string_is_valid(b->name, len)) return -EINVAL; @@ -766,7 +777,12 @@ static int tipc_nl_compat_link_set(struct tipc_nl_compat_cmd_doit *cmd, lc = (struct tipc_link_config *)TLV_DATA(msg->req); - len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME); + len = TLV_GET_DATA_LEN(msg->req); + len -= offsetof(struct tipc_link_config, name); + if (len <= 0) + return -EINVAL; + + len = min_t(int, len, TIPC_MAX_LINK_NAME); if (!string_is_valid(lc->name, len)) return -EINVAL; diff --git a/net/tipc/node.c b/net/tipc/node.c index 2dc4919ab23c..dd3b6dc17662 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -817,10 +817,10 @@ static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id, static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete) { struct tipc_link_entry *le = &n->links[bearer_id]; + struct tipc_media_addr *maddr = NULL; struct tipc_link *l = le->link; - struct tipc_media_addr *maddr; - struct sk_buff_head xmitq; int old_bearer_id = bearer_id; + struct sk_buff_head xmitq; if (!l) return; @@ -844,7 +844,8 @@ static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete) tipc_node_write_unlock(n); if (delete) tipc_mon_remove_peer(n->net, n->addr, old_bearer_id); - tipc_bearer_xmit(n->net, bearer_id, &xmitq, maddr); + if (!skb_queue_empty(&xmitq)) + tipc_bearer_xmit(n->net, bearer_id, &xmitq, maddr); tipc_sk_rcv(n->net, &le->inputq); } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 3274ef625dba..b542f14ed444 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2349,6 +2349,16 @@ static int tipc_wait_for_connect(struct socket *sock, long *timeo_p) return 0; } +static bool tipc_sockaddr_is_sane(struct sockaddr_tipc *addr) +{ + if (addr->family != AF_TIPC) + return false; + if (addr->addrtype == TIPC_SERVICE_RANGE) + return (addr->addr.nameseq.lower <= addr->addr.nameseq.upper); + return (addr->addrtype == TIPC_SERVICE_ADDR || + addr->addrtype == TIPC_SOCKET_ADDR); +} + /** * tipc_connect - establish a connection to another TIPC port * @sock: socket structure @@ -2384,18 +2394,18 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest, if (!tipc_sk_type_connectionless(sk)) res = -EINVAL; goto exit; - } else if (dst->family != AF_TIPC) { - res = -EINVAL; } - if (dst->addrtype != TIPC_ADDR_ID && dst->addrtype != TIPC_ADDR_NAME) + if (!tipc_sockaddr_is_sane(dst)) { res = -EINVAL; - if (res) goto exit; - + } /* DGRAM/RDM connect(), just save the destaddr */ if (tipc_sk_type_connectionless(sk)) { memcpy(&tsk->peer, dest, destlen); goto exit; + } else if (dst->addrtype == TIPC_SERVICE_RANGE) { + res = -EINVAL; + goto exit; } previous = sk->sk_state; @@ -3255,6 +3265,8 @@ static int __tipc_nl_add_sk_con(struct sk_buff *skb, struct tipc_sock *tsk) peer_port = tsk_peer_port(tsk); nest = nla_nest_start(skb, TIPC_NLA_SOCK_CON); + if (!nest) + return -EMSGSIZE; if (nla_put_u32(skb, TIPC_NLA_CON_NODE, peer_node)) goto msg_full; diff --git a/net/tipc/sysctl.c b/net/tipc/sysctl.c index 3481e4906bd6..9df82a573aa7 100644 --- a/net/tipc/sysctl.c +++ b/net/tipc/sysctl.c @@ -38,6 +38,8 @@ #include <linux/sysctl.h> +static int zero; +static int one = 1; static struct ctl_table_header *tipc_ctl_hdr; static struct ctl_table tipc_table[] = { @@ -46,14 +48,16 @@ static struct ctl_table tipc_table[] = { .data = &sysctl_tipc_rmem, .maxlen = sizeof(sysctl_tipc_rmem), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "named_timeout", .data = &sysctl_tipc_named_timeout, .maxlen = sizeof(sysctl_tipc_named_timeout), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, }, { .procname = "sk_filter", diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 4a708a4e8583..b45932d78004 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -363,6 +363,7 @@ static int tipc_conn_rcv_sub(struct tipc_topsrv *srv, struct tipc_subscription *sub; if (tipc_sub_read(s, filter) & TIPC_SUB_CANCEL) { + s->filter &= __constant_ntohl(~TIPC_SUB_CANCEL); tipc_conn_delete_sub(con, s); return 0; } diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 135a7ee9db03..14dedb24fa7b 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -52,8 +52,11 @@ static DEFINE_SPINLOCK(tls_device_lock); static void tls_device_free_ctx(struct tls_context *ctx) { - if (ctx->tx_conf == TLS_HW) + if (ctx->tx_conf == TLS_HW) { kfree(tls_offload_ctx_tx(ctx)); + kfree(ctx->tx.rec_seq); + kfree(ctx->tx.iv); + } if (ctx->rx_conf == TLS_HW) kfree(tls_offload_ctx_rx(ctx)); @@ -216,6 +219,13 @@ void tls_device_sk_destruct(struct sock *sk) } EXPORT_SYMBOL(tls_device_sk_destruct); +void tls_device_free_resources_tx(struct sock *sk) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + + tls_free_partial_record(sk, tls_ctx); +} + static void tls_append_frag(struct tls_record_info *record, struct page_frag *pfrag, int size) @@ -587,7 +597,7 @@ void handle_device_resync(struct sock *sk, u32 seq, u64 rcd_sn) static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb) { struct strp_msg *rxm = strp_msg(skb); - int err = 0, offset = rxm->offset, copy, nsg; + int err = 0, offset = rxm->offset, copy, nsg, data_len, pos; struct sk_buff *skb_iter, *unused; struct scatterlist sg[1]; char *orig_buf, *buf; @@ -618,25 +628,42 @@ static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb) else err = 0; - copy = min_t(int, skb_pagelen(skb) - offset, - rxm->full_len - TLS_CIPHER_AES_GCM_128_TAG_SIZE); + data_len = rxm->full_len - TLS_CIPHER_AES_GCM_128_TAG_SIZE; - if (skb->decrypted) - skb_store_bits(skb, offset, buf, copy); + if (skb_pagelen(skb) > offset) { + copy = min_t(int, skb_pagelen(skb) - offset, data_len); - offset += copy; - buf += copy; + if (skb->decrypted) + skb_store_bits(skb, offset, buf, copy); + + offset += copy; + buf += copy; + } + pos = skb_pagelen(skb); skb_walk_frags(skb, skb_iter) { - copy = min_t(int, skb_iter->len, - rxm->full_len - offset + rxm->offset - - TLS_CIPHER_AES_GCM_128_TAG_SIZE); + int frag_pos; + + /* Practically all frags must belong to msg if reencrypt + * is needed with current strparser and coalescing logic, + * but strparser may "get optimized", so let's be safe. + */ + if (pos + skb_iter->len <= offset) + goto done_with_frag; + if (pos >= data_len + rxm->offset) + break; + + frag_pos = offset - pos; + copy = min_t(int, skb_iter->len - frag_pos, + data_len + rxm->offset - offset); if (skb_iter->decrypted) - skb_store_bits(skb_iter, offset, buf, copy); + skb_store_bits(skb_iter, frag_pos, buf, copy); offset += copy; buf += copy; +done_with_frag: + pos += skb_iter->len; } free_buf: @@ -894,7 +921,9 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx) goto release_netdev; free_sw_resources: + up_read(&device_offload_lock); tls_sw_free_resources_rx(sk); + down_read(&device_offload_lock); release_ctx: ctx->priv_ctx_rx = NULL; release_netdev: @@ -929,8 +958,6 @@ void tls_device_offload_cleanup_rx(struct sock *sk) } out: up_read(&device_offload_lock); - kfree(tls_ctx->rx.rec_seq); - kfree(tls_ctx->rx.iv); tls_sw_release_resources_rx(sk); } diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c index 54c3a758f2a7..c3a5fe624b4e 100644 --- a/net/tls/tls_device_fallback.c +++ b/net/tls/tls_device_fallback.c @@ -194,18 +194,26 @@ static void update_chksum(struct sk_buff *skb, int headln) static void complete_skb(struct sk_buff *nskb, struct sk_buff *skb, int headln) { + struct sock *sk = skb->sk; + int delta; + skb_copy_header(nskb, skb); skb_put(nskb, skb->len); memcpy(nskb->data, skb->data, headln); - update_chksum(nskb, headln); nskb->destructor = skb->destructor; - nskb->sk = skb->sk; + nskb->sk = sk; skb->destructor = NULL; skb->sk = NULL; - refcount_add(nskb->truesize - skb->truesize, - &nskb->sk->sk_wmem_alloc); + + update_chksum(nskb, headln); + + delta = nskb->truesize - skb->truesize; + if (likely(delta < 0)) + WARN_ON_ONCE(refcount_sub_and_test(-delta, &sk->sk_wmem_alloc)); + else if (delta) + refcount_add(delta, &sk->sk_wmem_alloc); } /* This function may be called after the user socket is already diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index df921a2904b9..478603f43964 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -208,6 +208,26 @@ int tls_push_partial_record(struct sock *sk, struct tls_context *ctx, return tls_push_sg(sk, ctx, sg, offset, flags); } +bool tls_free_partial_record(struct sock *sk, struct tls_context *ctx) +{ + struct scatterlist *sg; + + sg = ctx->partially_sent_record; + if (!sg) + return false; + + while (1) { + put_page(sg_page(sg)); + sk_mem_uncharge(sk, sg->length); + + if (sg_is_last(sg)) + break; + sg++; + } + ctx->partially_sent_record = NULL; + return true; +} + static void tls_write_space(struct sock *sk) { struct tls_context *ctx = tls_get_ctx(sk); @@ -267,13 +287,14 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) kfree(ctx->tx.rec_seq); kfree(ctx->tx.iv); tls_sw_free_resources_tx(sk); +#ifdef CONFIG_TLS_DEVICE + } else if (ctx->tx_conf == TLS_HW) { + tls_device_free_resources_tx(sk); +#endif } - if (ctx->rx_conf == TLS_SW) { - kfree(ctx->rx.rec_seq); - kfree(ctx->rx.iv); + if (ctx->rx_conf == TLS_SW) tls_sw_free_resources_rx(sk); - } #ifdef CONFIG_TLS_DEVICE if (ctx->rx_conf == TLS_HW) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 425351ac2a9b..29d6af43dd24 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1484,6 +1484,8 @@ static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb, return err; } + } else { + *zc = false; } rxm->full_len -= padding_length(ctx, tls_ctx, skb); @@ -2050,20 +2052,7 @@ void tls_sw_free_resources_tx(struct sock *sk) /* Free up un-sent records in tx_list. First, free * the partially sent record if any at head of tx_list. */ - if (tls_ctx->partially_sent_record) { - struct scatterlist *sg = tls_ctx->partially_sent_record; - - while (1) { - put_page(sg_page(sg)); - sk_mem_uncharge(sk, sg->length); - - if (sg_is_last(sg)) - break; - sg++; - } - - tls_ctx->partially_sent_record = NULL; - + if (tls_free_partial_record(sk, tls_ctx)) { rec = list_first_entry(&ctx->tx_list, struct tls_rec, list); list_del(&rec->list); @@ -2089,6 +2078,9 @@ void tls_sw_release_resources_rx(struct sock *sk) struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); + kfree(tls_ctx->rx.rec_seq); + kfree(tls_ctx->rx.iv); + if (ctx->aead_recv) { kfree_skb(ctx->recv_pkt); ctx->recv_pkt = NULL; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 25a9e3b5c154..47e30a58566c 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -13650,7 +13650,8 @@ static const struct genl_ops nl80211_ops[] = { .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + NL80211_FLAG_NEED_RTNL | + NL80211_FLAG_CLEAR_SKB, }, { .cmd = NL80211_CMD_DEAUTHENTICATE, @@ -13701,7 +13702,8 @@ static const struct genl_ops nl80211_ops[] = { .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + NL80211_FLAG_NEED_RTNL | + NL80211_FLAG_CLEAR_SKB, }, { .cmd = NL80211_CMD_UPDATE_CONNECT_PARAMS, @@ -13709,7 +13711,8 @@ static const struct genl_ops nl80211_ops[] = { .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + NL80211_FLAG_NEED_RTNL | + NL80211_FLAG_CLEAR_SKB, }, { .cmd = NL80211_CMD_DISCONNECT, @@ -13738,7 +13741,8 @@ static const struct genl_ops nl80211_ops[] = { .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + NL80211_FLAG_NEED_RTNL | + NL80211_FLAG_CLEAR_SKB, }, { .cmd = NL80211_CMD_DEL_PMKSA, @@ -14090,7 +14094,8 @@ static const struct genl_ops nl80211_ops[] = { .policy = nl80211_policy, .flags = GENL_UNS_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WIPHY | - NL80211_FLAG_NEED_RTNL, + NL80211_FLAG_NEED_RTNL | + NL80211_FLAG_CLEAR_SKB, }, { .cmd = NL80211_CMD_SET_QOS_MAP, @@ -14145,7 +14150,8 @@ static const struct genl_ops nl80211_ops[] = { .doit = nl80211_set_pmk, .policy = nl80211_policy, .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | - NL80211_FLAG_NEED_RTNL, + NL80211_FLAG_NEED_RTNL | + NL80211_FLAG_CLEAR_SKB, }, { .cmd = NL80211_CMD_DEL_PMK, diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 2f1bf91eb226..a6fd5ce199da 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1309,6 +1309,16 @@ reg_intersect_dfs_region(const enum nl80211_dfs_regions dfs_region1, return dfs_region1; } +static void reg_wmm_rules_intersect(const struct ieee80211_wmm_ac *wmm_ac1, + const struct ieee80211_wmm_ac *wmm_ac2, + struct ieee80211_wmm_ac *intersect) +{ + intersect->cw_min = max_t(u16, wmm_ac1->cw_min, wmm_ac2->cw_min); + intersect->cw_max = max_t(u16, wmm_ac1->cw_max, wmm_ac2->cw_max); + intersect->cot = min_t(u16, wmm_ac1->cot, wmm_ac2->cot); + intersect->aifsn = max_t(u8, wmm_ac1->aifsn, wmm_ac2->aifsn); +} + /* * Helper for regdom_intersect(), this does the real * mathematical intersection fun @@ -1323,6 +1333,8 @@ static int reg_rules_intersect(const struct ieee80211_regdomain *rd1, struct ieee80211_freq_range *freq_range; const struct ieee80211_power_rule *power_rule1, *power_rule2; struct ieee80211_power_rule *power_rule; + const struct ieee80211_wmm_rule *wmm_rule1, *wmm_rule2; + struct ieee80211_wmm_rule *wmm_rule; u32 freq_diff, max_bandwidth1, max_bandwidth2; freq_range1 = &rule1->freq_range; @@ -1333,6 +1345,10 @@ static int reg_rules_intersect(const struct ieee80211_regdomain *rd1, power_rule2 = &rule2->power_rule; power_rule = &intersected_rule->power_rule; + wmm_rule1 = &rule1->wmm_rule; + wmm_rule2 = &rule2->wmm_rule; + wmm_rule = &intersected_rule->wmm_rule; + freq_range->start_freq_khz = max(freq_range1->start_freq_khz, freq_range2->start_freq_khz); freq_range->end_freq_khz = min(freq_range1->end_freq_khz, @@ -1376,6 +1392,29 @@ static int reg_rules_intersect(const struct ieee80211_regdomain *rd1, intersected_rule->dfs_cac_ms = max(rule1->dfs_cac_ms, rule2->dfs_cac_ms); + if (rule1->has_wmm && rule2->has_wmm) { + u8 ac; + + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + reg_wmm_rules_intersect(&wmm_rule1->client[ac], + &wmm_rule2->client[ac], + &wmm_rule->client[ac]); + reg_wmm_rules_intersect(&wmm_rule1->ap[ac], + &wmm_rule2->ap[ac], + &wmm_rule->ap[ac]); + } + + intersected_rule->has_wmm = true; + } else if (rule1->has_wmm) { + *wmm_rule = *wmm_rule1; + intersected_rule->has_wmm = true; + } else if (rule2->has_wmm) { + *wmm_rule = *wmm_rule2; + intersected_rule->has_wmm = true; + } else { + intersected_rule->has_wmm = false; + } + if (!is_valid_reg_rule(intersected_rule)) return -EINVAL; @@ -3739,10 +3778,9 @@ void wiphy_regulatory_register(struct wiphy *wiphy) /* * The last request may have been received before this * registration call. Call the driver notifier if - * initiator is USER and user type is CELL_BASE. + * initiator is USER. */ - if (lr->initiator == NL80211_REGDOM_SET_BY_USER && - lr->user_reg_hint_type == NL80211_USER_REG_HINT_CELL_BASE) + if (lr->initiator == NL80211_REGDOM_SET_BY_USER) reg_call_notifier(wiphy, lr); } diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 287518c6caa4..04d888628f29 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -190,10 +190,9 @@ static size_t cfg80211_gen_new_ie(const u8 *ie, size_t ielen, /* copy subelement as we need to change its content to * mark an ie after it is processed. */ - sub_copy = kmalloc(subie_len, gfp); + sub_copy = kmemdup(subelement, subie_len, gfp); if (!sub_copy) return 0; - memcpy(sub_copy, subelement, subie_len); pos = &new_ie[0]; diff --git a/net/wireless/util.c b/net/wireless/util.c index e4b8db5e81ec..75899b62bdc9 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1220,9 +1220,11 @@ static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate) else if (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_26) result = rates_26[rate->he_gi]; - else if (WARN(1, "invalid HE MCS: bw:%d, ru:%d\n", - rate->bw, rate->he_ru_alloc)) + else { + WARN(1, "invalid HE MCS: bw:%d, ru:%d\n", + rate->bw, rate->he_ru_alloc); return 0; + } /* now scale to the appropriate MCS */ tmp = result; diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 77520eacee8f..989e52386c35 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -193,9 +193,6 @@ static void xdp_umem_unaccount_pages(struct xdp_umem *umem) static void xdp_umem_release(struct xdp_umem *umem) { - struct task_struct *task; - struct mm_struct *mm; - xdp_umem_clear_dev(umem); ida_simple_remove(&umem_ida, umem->id); @@ -214,21 +211,10 @@ static void xdp_umem_release(struct xdp_umem *umem) xdp_umem_unpin_pages(umem); - task = get_pid_task(umem->pid, PIDTYPE_PID); - put_pid(umem->pid); - if (!task) - goto out; - mm = get_task_mm(task); - put_task_struct(task); - if (!mm) - goto out; - - mmput(mm); kfree(umem->pages); umem->pages = NULL; xdp_umem_unaccount_pages(umem); -out: kfree(umem); } @@ -357,7 +343,6 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) if (size_chk < 0) return -EINVAL; - umem->pid = get_task_pid(current, PIDTYPE_PID); umem->address = (unsigned long)addr; umem->chunk_mask = ~((u64)chunk_size - 1); umem->size = size; @@ -373,7 +358,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) err = xdp_umem_account_pages(umem); if (err) - goto out; + return err; err = xdp_umem_pin_pages(umem); if (err) @@ -392,8 +377,6 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) out_account: xdp_umem_unaccount_pages(umem); -out: - put_pid(umem->pid); return err; } diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index dbb3c1945b5c..85fec98676d3 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -70,17 +70,28 @@ static struct xfrm_if *xfrmi_lookup(struct net *net, struct xfrm_state *x) return NULL; } -static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb) +static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb, + unsigned short family) { struct xfrmi_net *xfrmn; - int ifindex; struct xfrm_if *xi; + int ifindex = 0; if (!secpath_exists(skb) || !skb->dev) return NULL; + switch (family) { + case AF_INET6: + ifindex = inet6_sdif(skb); + break; + case AF_INET: + ifindex = inet_sdif(skb); + break; + } + if (!ifindex) + ifindex = skb->dev->ifindex; + xfrmn = net_generic(xs_net(xfrm_input_state(skb)), xfrmi_net_id); - ifindex = skb->dev->ifindex; for_each_xfrmi_rcu(xfrmn->xfrmi[0], xi) { if (ifindex == xi->dev->ifindex && diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 8d1a898d0ba5..a6b58df7a70f 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3313,7 +3313,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, ifcb = xfrm_if_get_cb(); if (ifcb) { - xi = ifcb->decode_session(skb); + xi = ifcb->decode_session(skb, family); if (xi) { if_id = xi->p.if_id; net = xi->net; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 1bb971f46fc6..178baaa037e5 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -2384,7 +2384,7 @@ void xfrm_state_fini(struct net *net) flush_work(&net->xfrm.state_hash_work); flush_work(&xfrm_state_gc_work); - xfrm_state_flush(net, IPSEC_PROTO_ANY, false, true); + xfrm_state_flush(net, 0, false, true); WARN_ON(!list_empty(&net->xfrm.state_all)); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index a131f9ff979e..6916931b1de1 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1424,7 +1424,7 @@ static int verify_newpolicy_info(struct xfrm_userpolicy_info *p) ret = verify_policy_dir(p->dir); if (ret) return ret; - if (p->index && ((p->index & XFRM_POLICY_MAX) != p->dir)) + if (p->index && (xfrm_policy_id2dir(p->index) != p->dir)) return -EINVAL; return 0; @@ -1513,20 +1513,8 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family) return -EINVAL; } - switch (ut[i].id.proto) { - case IPPROTO_AH: - case IPPROTO_ESP: - case IPPROTO_COMP: -#if IS_ENABLED(CONFIG_IPV6) - case IPPROTO_ROUTING: - case IPPROTO_DSTOPTS: -#endif - case IPSEC_PROTO_ANY: - break; - default: + if (!xfrm_id_proto_valid(ut[i].id.proto)) return -EINVAL; - } - } return 0; diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 2554a15ecf2b..76ca30cc4791 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -199,11 +199,8 @@ sub_cmd_record_mcount = perl $(srctree)/scripts/recordmcount.pl "$(ARCH)" \ "$(if $(part-of-module),1,0)" "$(@)"; recordmcount_source := $(srctree)/scripts/recordmcount.pl endif # BUILD_C_RECORDMCOUNT -cmd_record_mcount = \ - if [ "$(findstring $(CC_FLAGS_FTRACE),$(_c_flags))" = \ - "$(CC_FLAGS_FTRACE)" ]; then \ - $(sub_cmd_record_mcount) \ - fi +cmd_record_mcount = $(if $(findstring $(strip $(CC_FLAGS_FTRACE)),$(_c_flags)), \ + $(sub_cmd_record_mcount)) endif # CC_USING_RECORD_MCOUNT endif # CONFIG_FTRACE_MCOUNT_RECORD diff --git a/scripts/atomic/gen-atomics.sh b/scripts/atomic/gen-atomics.sh index 27400b0cd732..000dc6437893 100644 --- a/scripts/atomic/gen-atomics.sh +++ b/scripts/atomic/gen-atomics.sh @@ -13,7 +13,7 @@ gen-atomic-long.sh asm-generic/atomic-long.h gen-atomic-fallback.sh linux/atomic-fallback.h EOF while read script header; do - ${ATOMICDIR}/${script} ${ATOMICTBL} > ${LINUXDIR}/include/${header} + /bin/sh ${ATOMICDIR}/${script} ${ATOMICTBL} > ${LINUXDIR}/include/${header} HASH="$(sha1sum ${LINUXDIR}/include/${header})" HASH="${HASH%% *}" printf "// %s\n" "${HASH}" >> ${LINUXDIR}/include/${header} diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 5b756278df13..a09333fd7cef 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -5977,7 +5977,7 @@ sub process { while ($fmt =~ /(\%[\*\d\.]*p(\w))/g) { $specifier = $1; $extension = $2; - if ($extension !~ /[SsBKRraEhMmIiUDdgVCbGNOx]/) { + if ($extension !~ /[SsBKRraEhMmIiUDdgVCbGNOxt]/) { $bad_specifier = $specifier; last; } diff --git a/scripts/coccinelle/api/stream_open.cocci b/scripts/coccinelle/api/stream_open.cocci new file mode 100644 index 000000000000..350145da7669 --- /dev/null +++ b/scripts/coccinelle/api/stream_open.cocci @@ -0,0 +1,363 @@ +// SPDX-License-Identifier: GPL-2.0 +// Author: Kirill Smelkov (kirr@nexedi.com) +// +// Search for stream-like files that are using nonseekable_open and convert +// them to stream_open. A stream-like file is a file that does not use ppos in +// its read and write. Rationale for the conversion is to avoid deadlock in +// between read and write. + +virtual report +virtual patch +virtual explain // explain decisions in the patch (SPFLAGS="-D explain") + +// stream-like reader & writer - ones that do not depend on f_pos. +@ stream_reader @ +identifier readstream, ppos; +identifier f, buf, len; +type loff_t; +@@ + ssize_t readstream(struct file *f, char *buf, size_t len, loff_t *ppos) + { + ... when != ppos + } + +@ stream_writer @ +identifier writestream, ppos; +identifier f, buf, len; +type loff_t; +@@ + ssize_t writestream(struct file *f, const char *buf, size_t len, loff_t *ppos) + { + ... when != ppos + } + + +// a function that blocks +@ blocks @ +identifier block_f; +identifier wait_event =~ "^wait_event_.*"; +@@ + block_f(...) { + ... when exists + wait_event(...) + ... when exists + } + +// stream_reader that can block inside. +// +// XXX wait_* can be called not directly from current function (e.g. func -> f -> g -> wait()) +// XXX currently reader_blocks supports only direct and 1-level indirect cases. +@ reader_blocks_direct @ +identifier stream_reader.readstream; +identifier wait_event =~ "^wait_event_.*"; +@@ + readstream(...) + { + ... when exists + wait_event(...) + ... when exists + } + +@ reader_blocks_1 @ +identifier stream_reader.readstream; +identifier blocks.block_f; +@@ + readstream(...) + { + ... when exists + block_f(...) + ... when exists + } + +@ reader_blocks depends on reader_blocks_direct || reader_blocks_1 @ +identifier stream_reader.readstream; +@@ + readstream(...) { + ... + } + + +// file_operations + whether they have _any_ .read, .write, .llseek ... at all. +// +// XXX add support for file_operations xxx[N] = ... (sound/core/pcm_native.c) +@ fops0 @ +identifier fops; +@@ + struct file_operations fops = { + ... + }; + +@ has_read @ +identifier fops0.fops; +identifier read_f; +@@ + struct file_operations fops = { + .read = read_f, + }; + +@ has_read_iter @ +identifier fops0.fops; +identifier read_iter_f; +@@ + struct file_operations fops = { + .read_iter = read_iter_f, + }; + +@ has_write @ +identifier fops0.fops; +identifier write_f; +@@ + struct file_operations fops = { + .write = write_f, + }; + +@ has_write_iter @ +identifier fops0.fops; +identifier write_iter_f; +@@ + struct file_operations fops = { + .write_iter = write_iter_f, + }; + +@ has_llseek @ +identifier fops0.fops; +identifier llseek_f; +@@ + struct file_operations fops = { + .llseek = llseek_f, + }; + +@ has_no_llseek @ +identifier fops0.fops; +@@ + struct file_operations fops = { + .llseek = no_llseek, + }; + +@ has_mmap @ +identifier fops0.fops; +identifier mmap_f; +@@ + struct file_operations fops = { + .mmap = mmap_f, + }; + +@ has_copy_file_range @ +identifier fops0.fops; +identifier copy_file_range_f; +@@ + struct file_operations fops = { + .copy_file_range = copy_file_range_f, + }; + +@ has_remap_file_range @ +identifier fops0.fops; +identifier remap_file_range_f; +@@ + struct file_operations fops = { + .remap_file_range = remap_file_range_f, + }; + +@ has_splice_read @ +identifier fops0.fops; +identifier splice_read_f; +@@ + struct file_operations fops = { + .splice_read = splice_read_f, + }; + +@ has_splice_write @ +identifier fops0.fops; +identifier splice_write_f; +@@ + struct file_operations fops = { + .splice_write = splice_write_f, + }; + + +// file_operations that is candidate for stream_open conversion - it does not +// use mmap and other methods that assume @offset access to file. +// +// XXX for simplicity require no .{read/write}_iter and no .splice_{read/write} for now. +// XXX maybe_steam.fops cannot be used in other rules - it gives "bad rule maybe_stream or bad variable fops". +@ maybe_stream depends on (!has_llseek || has_no_llseek) && !has_mmap && !has_copy_file_range && !has_remap_file_range && !has_read_iter && !has_write_iter && !has_splice_read && !has_splice_write @ +identifier fops0.fops; +@@ + struct file_operations fops = { + }; + + +// ---- conversions ---- + +// XXX .open = nonseekable_open -> .open = stream_open +// XXX .open = func -> openfunc -> nonseekable_open + +// read & write +// +// if both are used in the same file_operations together with an opener - +// under that conditions we can use stream_open instead of nonseekable_open. +@ fops_rw depends on maybe_stream @ +identifier fops0.fops, openfunc; +identifier stream_reader.readstream; +identifier stream_writer.writestream; +@@ + struct file_operations fops = { + .open = openfunc, + .read = readstream, + .write = writestream, + }; + +@ report_rw depends on report @ +identifier fops_rw.openfunc; +position p1; +@@ + openfunc(...) { + <... + nonseekable_open@p1 + ...> + } + +@ script:python depends on report && reader_blocks @ +fops << fops0.fops; +p << report_rw.p1; +@@ +coccilib.report.print_report(p[0], + "ERROR: %s: .read() can deadlock .write(); change nonseekable_open -> stream_open to fix." % (fops,)) + +@ script:python depends on report && !reader_blocks @ +fops << fops0.fops; +p << report_rw.p1; +@@ +coccilib.report.print_report(p[0], + "WARNING: %s: .read() and .write() have stream semantic; safe to change nonseekable_open -> stream_open." % (fops,)) + + +@ explain_rw_deadlocked depends on explain && reader_blocks @ +identifier fops_rw.openfunc; +@@ + openfunc(...) { + <... +- nonseekable_open ++ nonseekable_open /* read & write (was deadlock) */ + ...> + } + + +@ explain_rw_nodeadlock depends on explain && !reader_blocks @ +identifier fops_rw.openfunc; +@@ + openfunc(...) { + <... +- nonseekable_open ++ nonseekable_open /* read & write (no direct deadlock) */ + ...> + } + +@ patch_rw depends on patch @ +identifier fops_rw.openfunc; +@@ + openfunc(...) { + <... +- nonseekable_open ++ stream_open + ...> + } + + +// read, but not write +@ fops_r depends on maybe_stream && !has_write @ +identifier fops0.fops, openfunc; +identifier stream_reader.readstream; +@@ + struct file_operations fops = { + .open = openfunc, + .read = readstream, + }; + +@ report_r depends on report @ +identifier fops_r.openfunc; +position p1; +@@ + openfunc(...) { + <... + nonseekable_open@p1 + ...> + } + +@ script:python depends on report @ +fops << fops0.fops; +p << report_r.p1; +@@ +coccilib.report.print_report(p[0], + "WARNING: %s: .read() has stream semantic; safe to change nonseekable_open -> stream_open." % (fops,)) + +@ explain_r depends on explain @ +identifier fops_r.openfunc; +@@ + openfunc(...) { + <... +- nonseekable_open ++ nonseekable_open /* read only */ + ...> + } + +@ patch_r depends on patch @ +identifier fops_r.openfunc; +@@ + openfunc(...) { + <... +- nonseekable_open ++ stream_open + ...> + } + + +// write, but not read +@ fops_w depends on maybe_stream && !has_read @ +identifier fops0.fops, openfunc; +identifier stream_writer.writestream; +@@ + struct file_operations fops = { + .open = openfunc, + .write = writestream, + }; + +@ report_w depends on report @ +identifier fops_w.openfunc; +position p1; +@@ + openfunc(...) { + <... + nonseekable_open@p1 + ...> + } + +@ script:python depends on report @ +fops << fops0.fops; +p << report_w.p1; +@@ +coccilib.report.print_report(p[0], + "WARNING: %s: .write() has stream semantic; safe to change nonseekable_open -> stream_open." % (fops,)) + +@ explain_w depends on explain @ +identifier fops_w.openfunc; +@@ + openfunc(...) { + <... +- nonseekable_open ++ nonseekable_open /* write only */ + ...> + } + +@ patch_w depends on patch @ +identifier fops_w.openfunc; +@@ + openfunc(...) { + <... +- nonseekable_open ++ stream_open + ...> + } + + +// no read, no write - don't change anything diff --git a/scripts/coccinelle/free/put_device.cocci b/scripts/coccinelle/free/put_device.cocci index 7395697e7f19..c9f071b0a0ab 100644 --- a/scripts/coccinelle/free/put_device.cocci +++ b/scripts/coccinelle/free/put_device.cocci @@ -32,6 +32,7 @@ if (id == NULL || ...) { ... return ...; } ( id | (T2)dev_get_drvdata(&id->dev) | (T3)platform_get_drvdata(id) +| &id->dev ); | return@p2 ...; ) diff --git a/scripts/coccinelle/misc/badty.cocci b/scripts/coccinelle/misc/badty.cocci index 481cf301ccfc..08470362199c 100644 --- a/scripts/coccinelle/misc/badty.cocci +++ b/scripts/coccinelle/misc/badty.cocci @@ -1,4 +1,4 @@ -/// Use ARRAY_SIZE instead of dividing sizeof array with sizeof an element +/// Correct the size argument to alloc functions /// //# This makes an effort to find cases where the argument to sizeof is wrong //# in memory allocation functions by checking the type of the allocated memory diff --git a/scripts/kconfig/lxdialog/inputbox.c b/scripts/kconfig/lxdialog/inputbox.c index 611945611bf8..1dcfb288ee63 100644 --- a/scripts/kconfig/lxdialog/inputbox.c +++ b/scripts/kconfig/lxdialog/inputbox.c @@ -113,7 +113,8 @@ do_resize: case KEY_DOWN: break; case KEY_BACKSPACE: - case 127: + case 8: /* ^H */ + case 127: /* ^? */ if (pos) { wattrset(dialog, dlg.inputbox.atr); if (input_x == 0) { diff --git a/scripts/kconfig/nconf.c b/scripts/kconfig/nconf.c index a4670f4e825a..ac92c0ded6c5 100644 --- a/scripts/kconfig/nconf.c +++ b/scripts/kconfig/nconf.c @@ -1048,7 +1048,7 @@ static int do_match(int key, struct match_state *state, int *ans) state->match_direction = FIND_NEXT_MATCH_UP; *ans = get_mext_match(state->pattern, state->match_direction); - } else if (key == KEY_BACKSPACE || key == 127) { + } else if (key == KEY_BACKSPACE || key == 8 || key == 127) { state->pattern[strlen(state->pattern)-1] = '\0'; adj_match_dir(&state->match_direction); } else diff --git a/scripts/kconfig/nconf.gui.c b/scripts/kconfig/nconf.gui.c index 7be620a1fcdb..77f525a8617c 100644 --- a/scripts/kconfig/nconf.gui.c +++ b/scripts/kconfig/nconf.gui.c @@ -439,7 +439,8 @@ int dialog_inputbox(WINDOW *main_window, case KEY_F(F_EXIT): case KEY_F(F_BACK): break; - case 127: + case 8: /* ^H */ + case 127: /* ^? */ case KEY_BACKSPACE: if (cursor_position > 0) { memmove(&result[cursor_position-1], diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 0b0d1080b1c5..f277e116e0eb 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -639,7 +639,7 @@ static void handle_modversions(struct module *mod, struct elf_info *info, info->sechdrs[sym->st_shndx].sh_offset - (info->hdr->e_type != ET_REL ? info->sechdrs[sym->st_shndx].sh_addr : 0); - crc = *crcp; + crc = TO_NATIVE(*crcp); } sym_update_crc(symname + strlen("__crc_"), mod, crc, export); diff --git a/scripts/selinux/genheaders/genheaders.c b/scripts/selinux/genheaders/genheaders.c index 1ceedea847dd..544ca126a8a8 100644 --- a/scripts/selinux/genheaders/genheaders.c +++ b/scripts/selinux/genheaders/genheaders.c @@ -9,7 +9,6 @@ #include <string.h> #include <errno.h> #include <ctype.h> -#include <sys/socket.h> struct security_class_mapping { const char *name; diff --git a/scripts/selinux/mdp/mdp.c b/scripts/selinux/mdp/mdp.c index 073fe7537f6c..6d51b74bc679 100644 --- a/scripts/selinux/mdp/mdp.c +++ b/scripts/selinux/mdp/mdp.c @@ -32,7 +32,6 @@ #include <stdlib.h> #include <unistd.h> #include <string.h> -#include <sys/socket.h> static void usage(char *name) { diff --git a/security/Kconfig b/security/Kconfig index 1d6463fb1450..353cfef71d4e 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -239,8 +239,46 @@ source "security/safesetid/Kconfig" source "security/integrity/Kconfig" +choice + prompt "First legacy 'major LSM' to be initialized" + default DEFAULT_SECURITY_SELINUX if SECURITY_SELINUX + default DEFAULT_SECURITY_SMACK if SECURITY_SMACK + default DEFAULT_SECURITY_TOMOYO if SECURITY_TOMOYO + default DEFAULT_SECURITY_APPARMOR if SECURITY_APPARMOR + default DEFAULT_SECURITY_DAC + + help + This choice is there only for converting CONFIG_DEFAULT_SECURITY + in old kernel configs to CONFIG_LSM in new kernel configs. Don't + change this choice unless you are creating a fresh kernel config, + for this choice will be ignored after CONFIG_LSM has been set. + + Selects the legacy "major security module" that will be + initialized first. Overridden by non-default CONFIG_LSM. + + config DEFAULT_SECURITY_SELINUX + bool "SELinux" if SECURITY_SELINUX=y + + config DEFAULT_SECURITY_SMACK + bool "Simplified Mandatory Access Control" if SECURITY_SMACK=y + + config DEFAULT_SECURITY_TOMOYO + bool "TOMOYO" if SECURITY_TOMOYO=y + + config DEFAULT_SECURITY_APPARMOR + bool "AppArmor" if SECURITY_APPARMOR=y + + config DEFAULT_SECURITY_DAC + bool "Unix Discretionary Access Controls" + +endchoice + config LSM string "Ordered list of enabled LSMs" + default "yama,loadpin,safesetid,integrity,smack,selinux,tomoyo,apparmor" if DEFAULT_SECURITY_SMACK + default "yama,loadpin,safesetid,integrity,apparmor,selinux,smack,tomoyo" if DEFAULT_SECURITY_APPARMOR + default "yama,loadpin,safesetid,integrity,tomoyo" if DEFAULT_SECURITY_TOMOYO + default "yama,loadpin,safesetid,integrity" if DEFAULT_SECURITY_DAC default "yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" help A comma-separated list of LSMs, in initialization order. diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index fefee040bf79..b9298d2e8165 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -123,17 +123,22 @@ static int aafs_show_path(struct seq_file *seq, struct dentry *dentry) return 0; } -static void aafs_evict_inode(struct inode *inode) +static void aafs_i_callback(struct rcu_head *head) { - truncate_inode_pages_final(&inode->i_data); - clear_inode(inode); + struct inode *inode = container_of(head, struct inode, i_rcu); if (S_ISLNK(inode->i_mode)) kfree(inode->i_link); + free_inode_nonrcu(inode); +} + +static void aafs_destroy_inode(struct inode *inode) +{ + call_rcu(&inode->i_rcu, aafs_i_callback); } static const struct super_operations aafs_super_ops = { .statfs = simple_statfs, - .evict_inode = aafs_evict_inode, + .destroy_inode = aafs_destroy_inode, .show_path = aafs_show_path, }; diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 49d664ddff44..87500bde5a92 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -1336,9 +1336,16 @@ module_param_named(path_max, aa_g_path_max, aauint, S_IRUSR); bool aa_g_paranoid_load = true; module_param_named(paranoid_load, aa_g_paranoid_load, aabool, S_IRUGO); +static int param_get_aaintbool(char *buffer, const struct kernel_param *kp); +static int param_set_aaintbool(const char *val, const struct kernel_param *kp); +#define param_check_aaintbool param_check_int +static const struct kernel_param_ops param_ops_aaintbool = { + .set = param_set_aaintbool, + .get = param_get_aaintbool +}; /* Boot time disable flag */ static int apparmor_enabled __lsm_ro_after_init = 1; -module_param_named(enabled, apparmor_enabled, int, 0444); +module_param_named(enabled, apparmor_enabled, aaintbool, 0444); static int __init apparmor_enabled_setup(char *str) { @@ -1413,6 +1420,46 @@ static int param_get_aauint(char *buffer, const struct kernel_param *kp) return param_get_uint(buffer, kp); } +/* Can only be set before AppArmor is initialized (i.e. on boot cmdline). */ +static int param_set_aaintbool(const char *val, const struct kernel_param *kp) +{ + struct kernel_param kp_local; + bool value; + int error; + + if (apparmor_initialized) + return -EPERM; + + /* Create local copy, with arg pointing to bool type. */ + value = !!*((int *)kp->arg); + memcpy(&kp_local, kp, sizeof(kp_local)); + kp_local.arg = &value; + + error = param_set_bool(val, &kp_local); + if (!error) + *((int *)kp->arg) = *((bool *)kp_local.arg); + return error; +} + +/* + * To avoid changing /sys/module/apparmor/parameters/enabled from Y/N to + * 1/0, this converts the "int that is actually bool" back to bool for + * display in the /sys filesystem, while keeping it "int" for the LSM + * infrastructure. + */ +static int param_get_aaintbool(char *buffer, const struct kernel_param *kp) +{ + struct kernel_param kp_local; + bool value; + + /* Create local copy, with arg pointing to bool type. */ + value = !!*((int *)kp->arg); + memcpy(&kp_local, kp, sizeof(kp_local)); + kp_local.arg = &value; + + return param_get_bool(buffer, &kp_local); +} + static int param_get_audit(char *buffer, const struct kernel_param *kp) { if (!apparmor_enabled) diff --git a/security/device_cgroup.c b/security/device_cgroup.c index cd97929fac66..dc28914fa72e 100644 --- a/security/device_cgroup.c +++ b/security/device_cgroup.c @@ -560,7 +560,7 @@ static int propagate_exception(struct dev_cgroup *devcg_root, devcg->behavior == DEVCG_DEFAULT_ALLOW) { rc = dev_exception_add(devcg, ex); if (rc) - break; + return rc; } else { /* * in the other possible cases: diff --git a/security/inode.c b/security/inode.c index b7772a9b315e..421dd72b5876 100644 --- a/security/inode.c +++ b/security/inode.c @@ -27,17 +27,22 @@ static struct vfsmount *mount; static int mount_count; -static void securityfs_evict_inode(struct inode *inode) +static void securityfs_i_callback(struct rcu_head *head) { - truncate_inode_pages_final(&inode->i_data); - clear_inode(inode); + struct inode *inode = container_of(head, struct inode, i_rcu); if (S_ISLNK(inode->i_mode)) kfree(inode->i_link); + free_inode_nonrcu(inode); +} + +static void securityfs_destroy_inode(struct inode *inode) +{ + call_rcu(&inode->i_rcu, securityfs_i_callback); } static const struct super_operations securityfs_super_operations = { .statfs = simple_statfs, - .evict_inode = securityfs_evict_inode, + .destroy_inode = securityfs_destroy_inode, }; static int fill_super(struct super_block *sb, void *data, int silent) diff --git a/security/keys/trusted.c b/security/keys/trusted.c index bcc9c6ead7fd..efdbf17f3915 100644 --- a/security/keys/trusted.c +++ b/security/keys/trusted.c @@ -125,7 +125,7 @@ out: */ int TSS_authhmac(unsigned char *digest, const unsigned char *key, unsigned int keylen, unsigned char *h1, - unsigned char *h2, unsigned char h3, ...) + unsigned char *h2, unsigned int h3, ...) { unsigned char paramdigest[SHA1_DIGEST_SIZE]; struct sdesc *sdesc; @@ -135,13 +135,16 @@ int TSS_authhmac(unsigned char *digest, const unsigned char *key, int ret; va_list argp; + if (!chip) + return -ENODEV; + sdesc = init_sdesc(hashalg); if (IS_ERR(sdesc)) { pr_info("trusted_key: can't alloc %s\n", hash_alg); return PTR_ERR(sdesc); } - c = h3; + c = !!h3; ret = crypto_shash_init(&sdesc->shash); if (ret < 0) goto out; @@ -196,6 +199,9 @@ int TSS_checkhmac1(unsigned char *buffer, va_list argp; int ret; + if (!chip) + return -ENODEV; + bufsize = LOAD32(buffer, TPM_SIZE_OFFSET); tag = LOAD16(buffer, 0); ordinal = command; @@ -363,6 +369,9 @@ int trusted_tpm_send(unsigned char *cmd, size_t buflen) { int rc; + if (!chip) + return -ENODEV; + dump_tpm_buf(cmd); rc = tpm_send(chip, cmd, buflen); dump_tpm_buf(cmd); @@ -429,6 +438,9 @@ int oiap(struct tpm_buf *tb, uint32_t *handle, unsigned char *nonce) { int ret; + if (!chip) + return -ENODEV; + INIT_BUF(tb); store16(tb, TPM_TAG_RQU_COMMAND); store32(tb, TPM_OIAP_SIZE); @@ -1245,9 +1257,13 @@ static int __init init_trusted(void) { int ret; + /* encrypted_keys.ko depends on successful load of this module even if + * TPM is not used. + */ chip = tpm_default_chip(); if (!chip) - return -ENOENT; + return 0; + ret = init_digests(); if (ret < 0) goto err_put; @@ -1269,10 +1285,12 @@ err_put: static void __exit cleanup_trusted(void) { - put_device(&chip->dev); - kfree(digests); - trusted_shash_release(); - unregister_key_type(&key_type_trusted); + if (chip) { + put_device(&chip->dev); + kfree(digests); + trusted_shash_release(); + unregister_key_type(&key_type_trusted); + } } late_initcall(init_trusted); diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h index bd5fe0d3204a..201f7e588a29 100644 --- a/security/selinux/include/classmap.h +++ b/security/selinux/include/classmap.h @@ -1,5 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/capability.h> +#include <linux/socket.h> #define COMMON_FILE_SOCK_PERMS "ioctl", "read", "write", "create", \ "getattr", "setattr", "lock", "relabelfrom", "relabelto", "append", "map" diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c index 57cc60722dd3..efac68556b45 100644 --- a/security/yama/yama_lsm.c +++ b/security/yama/yama_lsm.c @@ -206,7 +206,7 @@ static void yama_ptracer_del(struct task_struct *tracer, * yama_task_free - check for task_pid to remove from exception list * @task: task being removed */ -void yama_task_free(struct task_struct *task) +static void yama_task_free(struct task_struct *task) { yama_ptracer_del(task, task); } @@ -222,7 +222,7 @@ void yama_task_free(struct task_struct *task) * Return 0 on success, -ve on error. -ENOSYS is returned when Yama * does not handle the given option. */ -int yama_task_prctl(int option, unsigned long arg2, unsigned long arg3, +static int yama_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { int rc = -ENOSYS; @@ -401,7 +401,7 @@ static int yama_ptrace_access_check(struct task_struct *child, * * Returns 0 if following the ptrace is allowed, -ve on error. */ -int yama_ptrace_traceme(struct task_struct *parent) +static int yama_ptrace_traceme(struct task_struct *parent) { int rc = 0; @@ -452,7 +452,7 @@ static int yama_dointvec_minmax(struct ctl_table *table, int write, static int zero; static int max_scope = YAMA_SCOPE_NO_ATTACH; -struct ctl_path yama_sysctl_path[] = { +static struct ctl_path yama_sysctl_path[] = { { .procname = "kernel", }, { .procname = "yama", }, { } diff --git a/sound/core/info.c b/sound/core/info.c index 96a074019c33..0eb169acc850 100644 --- a/sound/core/info.c +++ b/sound/core/info.c @@ -713,8 +713,11 @@ snd_info_create_entry(const char *name, struct snd_info_entry *parent, INIT_LIST_HEAD(&entry->list); entry->parent = parent; entry->module = module; - if (parent) + if (parent) { + mutex_lock(&parent->access); list_add_tail(&entry->list, &parent->children); + mutex_unlock(&parent->access); + } return entry; } @@ -792,7 +795,12 @@ void snd_info_free_entry(struct snd_info_entry * entry) list_for_each_entry_safe(p, n, &entry->children, list) snd_info_free_entry(p); - list_del(&entry->list); + p = entry->parent; + if (p) { + mutex_lock(&p->access); + list_del(&entry->list); + mutex_unlock(&p->access); + } kfree(entry->name); if (entry->private_free) entry->private_free(entry); diff --git a/sound/core/init.c b/sound/core/init.c index 0c4dc40376a7..079c12d64b0e 100644 --- a/sound/core/init.c +++ b/sound/core/init.c @@ -382,14 +382,7 @@ int snd_card_disconnect(struct snd_card *card) card->shutdown = 1; spin_unlock(&card->files_lock); - /* phase 1: disable fops (user space) operations for ALSA API */ - mutex_lock(&snd_card_mutex); - snd_cards[card->number] = NULL; - clear_bit(card->number, snd_cards_lock); - mutex_unlock(&snd_card_mutex); - - /* phase 2: replace file->f_op with special dummy operations */ - + /* replace file->f_op with special dummy operations */ spin_lock(&card->files_lock); list_for_each_entry(mfile, &card->files_list, list) { /* it's critical part, use endless loop */ @@ -405,7 +398,7 @@ int snd_card_disconnect(struct snd_card *card) } spin_unlock(&card->files_lock); - /* phase 3: notify all connected devices about disconnection */ + /* notify all connected devices about disconnection */ /* at this point, they cannot respond to any calls except release() */ #if IS_ENABLED(CONFIG_SND_MIXER_OSS) @@ -421,6 +414,13 @@ int snd_card_disconnect(struct snd_card *card) device_del(&card->card_dev); card->registered = false; } + + /* disable fops (user space) operations for ALSA API */ + mutex_lock(&snd_card_mutex); + snd_cards[card->number] = NULL; + clear_bit(card->number, snd_cards_lock); + mutex_unlock(&snd_card_mutex); + #ifdef CONFIG_PM wake_up(&card->power_sleep); #endif diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c index d5b0d7ba83c4..f6ae68017608 100644 --- a/sound/core/oss/pcm_oss.c +++ b/sound/core/oss/pcm_oss.c @@ -940,6 +940,28 @@ static int snd_pcm_oss_change_params_locked(struct snd_pcm_substream *substream) oss_frame_size = snd_pcm_format_physical_width(params_format(params)) * params_channels(params) / 8; + err = snd_pcm_oss_period_size(substream, params, sparams); + if (err < 0) + goto failure; + + n = snd_pcm_plug_slave_size(substream, runtime->oss.period_bytes / oss_frame_size); + err = snd_pcm_hw_param_near(substream, sparams, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, n, NULL); + if (err < 0) + goto failure; + + err = snd_pcm_hw_param_near(substream, sparams, SNDRV_PCM_HW_PARAM_PERIODS, + runtime->oss.periods, NULL); + if (err < 0) + goto failure; + + snd_pcm_kernel_ioctl(substream, SNDRV_PCM_IOCTL_DROP, NULL); + + err = snd_pcm_kernel_ioctl(substream, SNDRV_PCM_IOCTL_HW_PARAMS, sparams); + if (err < 0) { + pcm_dbg(substream->pcm, "HW_PARAMS failed: %i\n", err); + goto failure; + } + #ifdef CONFIG_SND_PCM_OSS_PLUGINS snd_pcm_oss_plugin_clear(substream); if (!direct) { @@ -974,27 +996,6 @@ static int snd_pcm_oss_change_params_locked(struct snd_pcm_substream *substream) } #endif - err = snd_pcm_oss_period_size(substream, params, sparams); - if (err < 0) - goto failure; - - n = snd_pcm_plug_slave_size(substream, runtime->oss.period_bytes / oss_frame_size); - err = snd_pcm_hw_param_near(substream, sparams, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, n, NULL); - if (err < 0) - goto failure; - - err = snd_pcm_hw_param_near(substream, sparams, SNDRV_PCM_HW_PARAM_PERIODS, - runtime->oss.periods, NULL); - if (err < 0) - goto failure; - - snd_pcm_kernel_ioctl(substream, SNDRV_PCM_IOCTL_DROP, NULL); - - if ((err = snd_pcm_kernel_ioctl(substream, SNDRV_PCM_IOCTL_HW_PARAMS, sparams)) < 0) { - pcm_dbg(substream->pcm, "HW_PARAMS failed: %i\n", err); - goto failure; - } - if (runtime->oss.trigger) { sw_params->start_threshold = 1; } else { diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index f731f904e8cc..1d8452912b14 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -1445,8 +1445,15 @@ static int snd_pcm_pause(struct snd_pcm_substream *substream, int push) static int snd_pcm_pre_suspend(struct snd_pcm_substream *substream, int state) { struct snd_pcm_runtime *runtime = substream->runtime; - if (runtime->status->state == SNDRV_PCM_STATE_SUSPENDED) + switch (runtime->status->state) { + case SNDRV_PCM_STATE_SUSPENDED: return -EBUSY; + /* unresumable PCM state; return -EBUSY for skipping suspend */ + case SNDRV_PCM_STATE_OPEN: + case SNDRV_PCM_STATE_SETUP: + case SNDRV_PCM_STATE_DISCONNECTED: + return -EBUSY; + } runtime->trigger_master = substream; return 0; } diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index ee601d7f0926..c0690d1ecd55 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -30,6 +30,7 @@ #include <linux/module.h> #include <linux/delay.h> #include <linux/mm.h> +#include <linux/nospec.h> #include <sound/rawmidi.h> #include <sound/info.h> #include <sound/control.h> @@ -601,6 +602,7 @@ static int __snd_rawmidi_info_select(struct snd_card *card, return -ENXIO; if (info->stream < 0 || info->stream > 1) return -EINVAL; + info->stream = array_index_nospec(info->stream, 2); pstr = &rmidi->streams[info->stream]; if (pstr->substream_count == 0) return -ENOENT; diff --git a/sound/core/seq/oss/seq_oss_synth.c b/sound/core/seq/oss/seq_oss_synth.c index 278ebb993122..c93945917235 100644 --- a/sound/core/seq/oss/seq_oss_synth.c +++ b/sound/core/seq/oss/seq_oss_synth.c @@ -617,13 +617,14 @@ int snd_seq_oss_synth_make_info(struct seq_oss_devinfo *dp, int dev, struct synth_info *inf) { struct seq_oss_synth *rec; + struct seq_oss_synthinfo *info = get_synthinfo_nospec(dp, dev); - if (dev < 0 || dev >= dp->max_synthdev) + if (!info) return -ENXIO; - if (dp->synths[dev].is_midi) { + if (info->is_midi) { struct midi_info minf; - snd_seq_oss_midi_make_info(dp, dp->synths[dev].midi_mapped, &minf); + snd_seq_oss_midi_make_info(dp, info->midi_mapped, &minf); inf->synth_type = SYNTH_TYPE_MIDI; inf->synth_subtype = 0; inf->nr_voices = 16; diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 7d4640d1fe9f..38e7deab6384 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -1252,7 +1252,7 @@ static int snd_seq_ioctl_set_client_info(struct snd_seq_client *client, /* fill the info fields */ if (client_info->name[0]) - strlcpy(client->name, client_info->name, sizeof(client->name)); + strscpy(client->name, client_info->name, sizeof(client->name)); client->filter = client_info->filter; client->event_lost = client_info->event_lost; @@ -1530,7 +1530,7 @@ static int snd_seq_ioctl_create_queue(struct snd_seq_client *client, void *arg) /* set queue name */ if (!info->name[0]) snprintf(info->name, sizeof(info->name), "Queue-%d", q->queue); - strlcpy(q->name, info->name, sizeof(q->name)); + strscpy(q->name, info->name, sizeof(q->name)); snd_use_lock_free(&q->use_lock); return 0; @@ -1592,7 +1592,7 @@ static int snd_seq_ioctl_set_queue_info(struct snd_seq_client *client, queuefree(q); return -EPERM; } - strlcpy(q->name, info->name, sizeof(q->name)); + strscpy(q->name, info->name, sizeof(q->name)); queuefree(q); return 0; diff --git a/sound/hda/ext/hdac_ext_bus.c b/sound/hda/ext/hdac_ext_bus.c index 9c37d9af3023..ec7715c6b0c0 100644 --- a/sound/hda/ext/hdac_ext_bus.c +++ b/sound/hda/ext/hdac_ext_bus.c @@ -107,7 +107,6 @@ int snd_hdac_ext_bus_init(struct hdac_bus *bus, struct device *dev, INIT_LIST_HEAD(&bus->hlink_list); bus->idx = idx++; - mutex_init(&bus->lock); bus->cmd_dma_state = true; return 0; diff --git a/sound/hda/hdac_bus.c b/sound/hda/hdac_bus.c index 012305177f68..ad8eee08013f 100644 --- a/sound/hda/hdac_bus.c +++ b/sound/hda/hdac_bus.c @@ -38,6 +38,7 @@ int snd_hdac_bus_init(struct hdac_bus *bus, struct device *dev, INIT_WORK(&bus->unsol_work, snd_hdac_bus_process_unsol_events); spin_lock_init(&bus->reg_lock); mutex_init(&bus->cmd_mutex); + mutex_init(&bus->lock); bus->irq = -1; return 0; } diff --git a/sound/hda/hdac_component.c b/sound/hda/hdac_component.c index 5c95933e739a..1ea51e3b942a 100644 --- a/sound/hda/hdac_component.c +++ b/sound/hda/hdac_component.c @@ -69,13 +69,15 @@ void snd_hdac_display_power(struct hdac_bus *bus, unsigned int idx, bool enable) dev_dbg(bus->dev, "display power %s\n", enable ? "enable" : "disable"); + + mutex_lock(&bus->lock); if (enable) set_bit(idx, &bus->display_power_status); else clear_bit(idx, &bus->display_power_status); if (!acomp || !acomp->ops) - return; + goto unlock; if (bus->display_power_status) { if (!bus->display_power_active) { @@ -92,6 +94,8 @@ void snd_hdac_display_power(struct hdac_bus *bus, unsigned int idx, bool enable) bus->display_power_active = false; } } + unlock: + mutex_unlock(&bus->lock); } EXPORT_SYMBOL_GPL(snd_hdac_display_power); diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index ec0b8595eb4d..701a69d856f5 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -969,6 +969,7 @@ int snd_hda_codec_device_new(struct hda_bus *bus, struct snd_card *card, /* power-up all before initialization */ hda_set_power_state(codec, AC_PWRST_D0); + codec->core.dev.power.power_state = PMSG_ON; snd_hda_codec_proc_new(codec); diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index ece256a3b48f..2ec91085fa3e 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2142,6 +2142,8 @@ static struct snd_pci_quirk power_save_blacklist[] = { SND_PCI_QUIRK(0x8086, 0x2040, "Intel DZ77BH-55K", 0), /* https://bugzilla.kernel.org/show_bug.cgi?id=199607 */ SND_PCI_QUIRK(0x8086, 0x2057, "Intel NUC5i7RYB", 0), + /* https://bugs.launchpad.net/bugs/1821663 */ + SND_PCI_QUIRK(0x8086, 0x2064, "Intel SDP 8086:2064", 0), /* https://bugzilla.redhat.com/show_bug.cgi?id=1520902 */ SND_PCI_QUIRK(0x8086, 0x2068, "Intel NUC7i3BNB", 0), /* https://bugzilla.kernel.org/show_bug.cgi?id=198611 */ @@ -2150,6 +2152,8 @@ static struct snd_pci_quirk power_save_blacklist[] = { SND_PCI_QUIRK(0x17aa, 0x367b, "Lenovo IdeaCentre B550", 0), /* https://bugzilla.redhat.com/show_bug.cgi?id=1572975 */ SND_PCI_QUIRK(0x17aa, 0x36a7, "Lenovo C50 All in one", 0), + /* https://bugs.launchpad.net/bugs/1821663 */ + SND_PCI_QUIRK(0x1631, 0xe017, "Packard Bell NEC IMEDIA 5204", 0), {} }; #endif /* CONFIG_PM */ diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index 29882bda7632..e1ebc6d5f382 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -1005,7 +1005,6 @@ struct ca0132_spec { unsigned int scp_resp_header; unsigned int scp_resp_data[4]; unsigned int scp_resp_count; - bool alt_firmware_present; bool startup_check_entered; bool dsp_reload; @@ -7518,7 +7517,7 @@ static bool ca0132_download_dsp_images(struct hda_codec *codec) bool dsp_loaded = false; struct ca0132_spec *spec = codec->spec; const struct dsp_image_seg *dsp_os_image; - const struct firmware *fw_entry; + const struct firmware *fw_entry = NULL; /* * Alternate firmwares for different variants. The Recon3Di apparently * can use the default firmware, but I'll leave the option in case @@ -7529,33 +7528,26 @@ static bool ca0132_download_dsp_images(struct hda_codec *codec) case QUIRK_R3D: case QUIRK_AE5: if (request_firmware(&fw_entry, DESKTOP_EFX_FILE, - codec->card->dev) != 0) { + codec->card->dev) != 0) codec_dbg(codec, "Desktop firmware not found."); - spec->alt_firmware_present = false; - } else { + else codec_dbg(codec, "Desktop firmware selected."); - spec->alt_firmware_present = true; - } break; case QUIRK_R3DI: if (request_firmware(&fw_entry, R3DI_EFX_FILE, - codec->card->dev) != 0) { + codec->card->dev) != 0) codec_dbg(codec, "Recon3Di alt firmware not detected."); - spec->alt_firmware_present = false; - } else { + else codec_dbg(codec, "Recon3Di firmware selected."); - spec->alt_firmware_present = true; - } break; default: - spec->alt_firmware_present = false; break; } /* * Use default ctefx.bin if no alt firmware is detected, or if none * exists for your particular codec. */ - if (!spec->alt_firmware_present) { + if (!fw_entry) { codec_dbg(codec, "Default firmware selected."); if (request_firmware(&fw_entry, EFX_FILE, codec->card->dev) != 0) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 191830d4fa40..42cd3945e0de 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -1864,8 +1864,8 @@ enum { ALC887_FIXUP_BASS_CHMAP, ALC1220_FIXUP_GB_DUAL_CODECS, ALC1220_FIXUP_CLEVO_P950, - ALC1220_FIXUP_SYSTEM76_ORYP5, - ALC1220_FIXUP_SYSTEM76_ORYP5_PINS, + ALC1220_FIXUP_CLEVO_PB51ED, + ALC1220_FIXUP_CLEVO_PB51ED_PINS, }; static void alc889_fixup_coef(struct hda_codec *codec, @@ -2070,7 +2070,7 @@ static void alc1220_fixup_clevo_p950(struct hda_codec *codec, static void alc_fixup_headset_mode_no_hp_mic(struct hda_codec *codec, const struct hda_fixup *fix, int action); -static void alc1220_fixup_system76_oryp5(struct hda_codec *codec, +static void alc1220_fixup_clevo_pb51ed(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -2322,18 +2322,18 @@ static const struct hda_fixup alc882_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc1220_fixup_clevo_p950, }, - [ALC1220_FIXUP_SYSTEM76_ORYP5] = { + [ALC1220_FIXUP_CLEVO_PB51ED] = { .type = HDA_FIXUP_FUNC, - .v.func = alc1220_fixup_system76_oryp5, + .v.func = alc1220_fixup_clevo_pb51ed, }, - [ALC1220_FIXUP_SYSTEM76_ORYP5_PINS] = { + [ALC1220_FIXUP_CLEVO_PB51ED_PINS] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { { 0x19, 0x01a1913c }, /* use as headset mic, without its own jack detect */ {} }, .chained = true, - .chain_id = ALC1220_FIXUP_SYSTEM76_ORYP5, + .chain_id = ALC1220_FIXUP_CLEVO_PB51ED, }, }; @@ -2411,8 +2411,9 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0x9501, "Clevo P950HR", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x95e1, "Clevo P95xER", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x95e2, "Clevo P950ER", ALC1220_FIXUP_CLEVO_P950), - SND_PCI_QUIRK(0x1558, 0x96e1, "System76 Oryx Pro (oryp5)", ALC1220_FIXUP_SYSTEM76_ORYP5_PINS), - SND_PCI_QUIRK(0x1558, 0x97e1, "System76 Oryx Pro (oryp5)", ALC1220_FIXUP_SYSTEM76_ORYP5_PINS), + SND_PCI_QUIRK(0x1558, 0x96e1, "System76 Oryx Pro (oryp5)", ALC1220_FIXUP_CLEVO_PB51ED_PINS), + SND_PCI_QUIRK(0x1558, 0x97e1, "System76 Oryx Pro (oryp5)", ALC1220_FIXUP_CLEVO_PB51ED_PINS), + SND_PCI_QUIRK(0x1558, 0x65d1, "Tuxedo Book XC1509", ALC1220_FIXUP_CLEVO_PB51ED_PINS), SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD), SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD), SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Y530", ALC882_FIXUP_LENOVO_Y530), @@ -5449,6 +5450,8 @@ static void alc274_fixup_bind_dacs(struct hda_codec *codec, return; spec->gen.preferred_dacs = preferred_pairs; + spec->gen.auto_mute_via_amp = 1; + codec->power_save_node = 0; } /* The DAC of NID 0x3 will introduce click/pop noise on headphones, so invalidate it */ @@ -5491,7 +5494,7 @@ static void alc_headset_btn_callback(struct hda_codec *codec, jack->jack->button_state = report; } -static void alc295_fixup_chromebook(struct hda_codec *codec, +static void alc_fixup_headset_jack(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -5501,16 +5504,6 @@ static void alc295_fixup_chromebook(struct hda_codec *codec, alc_headset_btn_callback); snd_hda_jack_add_kctl(codec, 0x55, "Headset Jack", false, SND_JACK_HEADSET, alc_headset_btn_keymap); - switch (codec->core.vendor_id) { - case 0x10ec0295: - alc_update_coef_idx(codec, 0x4a, 0x8000, 1 << 15); /* Reset HP JD */ - alc_update_coef_idx(codec, 0x4a, 0x8000, 0 << 15); - break; - case 0x10ec0236: - alc_update_coef_idx(codec, 0x1b, 0x8000, 1 << 15); /* Reset HP JD */ - alc_update_coef_idx(codec, 0x1b, 0x8000, 0 << 15); - break; - } break; case HDA_FIXUP_ACT_INIT: switch (codec->core.vendor_id) { @@ -5531,6 +5524,25 @@ static void alc295_fixup_chromebook(struct hda_codec *codec, } } +static void alc295_fixup_chromebook(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + switch (action) { + case HDA_FIXUP_ACT_INIT: + switch (codec->core.vendor_id) { + case 0x10ec0295: + alc_update_coef_idx(codec, 0x4a, 0x8000, 1 << 15); /* Reset HP JD */ + alc_update_coef_idx(codec, 0x4a, 0x8000, 0 << 15); + break; + case 0x10ec0236: + alc_update_coef_idx(codec, 0x1b, 0x8000, 1 << 15); /* Reset HP JD */ + alc_update_coef_idx(codec, 0x1b, 0x8000, 0 << 15); + break; + } + break; + } +} + static void alc_fixup_disable_mic_vref(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -5663,6 +5675,7 @@ enum { ALC233_FIXUP_ASUS_MIC_NO_PRESENCE, ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE, ALC233_FIXUP_LENOVO_MULTI_CODECS, + ALC233_FIXUP_ACER_HEADSET_MIC, ALC294_FIXUP_LENOVO_MIC_LOCATION, ALC225_FIXUP_DELL_WYSE_MIC_NO_PRESENCE, ALC700_FIXUP_INTEL_REFERENCE, @@ -5684,10 +5697,13 @@ enum { ALC285_FIXUP_LENOVO_PC_BEEP_IN_NOISE, ALC255_FIXUP_ACER_HEADSET_MIC, ALC295_FIXUP_CHROME_BOOK, + ALC225_FIXUP_HEADSET_JACK, ALC225_FIXUP_DELL_WYSE_AIO_MIC_NO_PRESENCE, ALC225_FIXUP_WYSE_AUTO_MUTE, ALC225_FIXUP_WYSE_DISABLE_MIC_VREF, ALC286_FIXUP_ACER_AIO_HEADSET_MIC, + ALC256_FIXUP_ASUS_MIC_NO_PRESENCE, + ALC299_FIXUP_PREDATOR_SPK, }; static const struct hda_fixup alc269_fixups[] = { @@ -6488,6 +6504,16 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc233_alc662_fixup_lenovo_dual_codecs, }, + [ALC233_FIXUP_ACER_HEADSET_MIC] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + { 0x20, AC_VERB_SET_COEF_INDEX, 0x45 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x5089 }, + { } + }, + .chained = true, + .chain_id = ALC233_FIXUP_ASUS_MIC_NO_PRESENCE + }, [ALC294_FIXUP_LENOVO_MIC_LOCATION] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -6633,6 +6659,12 @@ static const struct hda_fixup alc269_fixups[] = { [ALC295_FIXUP_CHROME_BOOK] = { .type = HDA_FIXUP_FUNC, .v.func = alc295_fixup_chromebook, + .chained = true, + .chain_id = ALC225_FIXUP_HEADSET_JACK + }, + [ALC225_FIXUP_HEADSET_JACK] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_headset_jack, }, [ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE] = { .type = HDA_FIXUP_PINS, @@ -6696,6 +6728,22 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE }, + [ALC256_FIXUP_ASUS_MIC_NO_PRESENCE] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x04a11120 }, /* use as headset mic, without its own jack detect */ + { } + }, + .chained = true, + .chain_id = ALC256_FIXUP_ASUS_HEADSET_MODE + }, + [ALC299_FIXUP_PREDATOR_SPK] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x21, 0x90170150 }, /* use as headset mic, without its own jack detect */ + { } + } + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -6712,9 +6760,14 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS), SND_PCI_QUIRK(0x1025, 0x102b, "Acer Aspire C24-860", ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x106d, "Acer Cloudbook 14", ALC283_FIXUP_CHROME_BOOK), + SND_PCI_QUIRK(0x1025, 0x1099, "Acer Aspire E5-523G", ALC255_FIXUP_ACER_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1025, 0x110e, "Acer Aspire ES1-432", ALC255_FIXUP_ACER_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1025, 0x1246, "Acer Predator Helios 500", ALC299_FIXUP_PREDATOR_SPK), SND_PCI_QUIRK(0x1025, 0x128f, "Acer Veriton Z6860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x1290, "Acer Veriton Z4860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x1291, "Acer Veriton Z4660G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), + SND_PCI_QUIRK(0x1025, 0x1308, "Acer Aspire Z24-890", ALC286_FIXUP_ACER_AIO_HEADSET_MIC), + SND_PCI_QUIRK(0x1025, 0x132a, "Acer TravelMate B114-21", ALC233_FIXUP_ACER_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x1330, "Acer TravelMate X514-51T", ALC255_FIXUP_ACER_HEADSET_MIC), SND_PCI_QUIRK(0x1028, 0x0470, "Dell M101z", ALC269_FIXUP_DELL_M101Z), SND_PCI_QUIRK(0x1028, 0x054b, "Dell XPS one 2710", ALC275_FIXUP_DELL_XPS), @@ -7110,7 +7163,9 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {.id = ALC255_FIXUP_DUMMY_LINEOUT_VERB, .name = "alc255-dummy-lineout"}, {.id = ALC255_FIXUP_DELL_HEADSET_MIC, .name = "alc255-dell-headset"}, {.id = ALC295_FIXUP_HP_X360, .name = "alc295-hp-x360"}, - {.id = ALC295_FIXUP_CHROME_BOOK, .name = "alc-sense-combo"}, + {.id = ALC225_FIXUP_HEADSET_JACK, .name = "alc-headset-jack"}, + {.id = ALC295_FIXUP_CHROME_BOOK, .name = "alc-chrome-book"}, + {.id = ALC299_FIXUP_PREDATOR_SPK, .name = "predator-spk"}, {} }; #define ALC225_STANDARD_PINS \ @@ -7213,6 +7268,12 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x12, 0x90a60140}, {0x14, 0x90170150}, {0x21, 0x02211020}), + SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, + {0x21, 0x02211020}), + SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, + {0x12, 0x40000000}, + {0x14, 0x90170110}, + {0x21, 0x02211020}), SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE, {0x14, 0x90170110}, {0x21, 0x02211020}), @@ -7323,6 +7384,10 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x21, 0x0221101f}), SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, ALC256_STANDARD_PINS), + SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, + {0x14, 0x90170110}, + {0x1b, 0x01011020}, + {0x21, 0x0221101f}), SND_HDA_PIN_QUIRK(0x10ec0256, 0x1043, "ASUS", ALC256_FIXUP_ASUS_MIC, {0x14, 0x90170110}, {0x1b, 0x90a70130}, @@ -7331,6 +7396,18 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x14, 0x90170110}, {0x1b, 0x90a70130}, {0x21, 0x03211020}), + SND_HDA_PIN_QUIRK(0x10ec0256, 0x1043, "ASUS", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE, + {0x12, 0x90a60130}, + {0x14, 0x90170110}, + {0x21, 0x03211020}), + SND_HDA_PIN_QUIRK(0x10ec0256, 0x1043, "ASUS", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE, + {0x12, 0x90a60130}, + {0x14, 0x90170110}, + {0x21, 0x04211020}), + SND_HDA_PIN_QUIRK(0x10ec0256, 0x1043, "ASUS", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE, + {0x1a, 0x90a70130}, + {0x1b, 0x90170110}, + {0x21, 0x03211020}), SND_HDA_PIN_QUIRK(0x10ec0274, 0x1028, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB, {0x12, 0xb7a60130}, {0x13, 0xb8a61140}, @@ -7470,6 +7547,13 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x12, 0x90a60130}, {0x17, 0x90170110}, {0x21, 0x04211020}), + SND_HDA_PIN_QUIRK(0x10ec0295, 0x1043, "ASUS", ALC294_FIXUP_ASUS_SPK, + {0x12, 0x90a60130}, + {0x17, 0x90170110}, + {0x21, 0x03211020}), + SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, + {0x14, 0x90170110}, + {0x21, 0x04211020}), SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, ALC295_STANDARD_PINS, {0x17, 0x21014020}, diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig index 419114edfd57..667fc1d59e18 100644 --- a/sound/soc/codecs/Kconfig +++ b/sound/soc/codecs/Kconfig @@ -1151,6 +1151,7 @@ config SND_SOC_WCD9335 tristate "WCD9335 Codec" depends on SLIMBUS select REGMAP_SLIMBUS + select REGMAP_IRQ help The WCD9335 is a standalone Hi-Fi audio CODEC IC, supports Qualcomm Technologies, Inc. (QTI) multimedia solutions, diff --git a/sound/soc/codecs/ab8500-codec.c b/sound/soc/codecs/ab8500-codec.c index 03bbbcd3b6c1..87616b126018 100644 --- a/sound/soc/codecs/ab8500-codec.c +++ b/sound/soc/codecs/ab8500-codec.c @@ -2129,6 +2129,7 @@ static int ab8500_codec_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt) dev_err(dai->component->dev, "%s: ERROR: The device is either a master or a slave.\n", __func__); + /* fall through */ default: dev_err(dai->component->dev, "%s: ERROR: Unsupporter master mask 0x%x\n", diff --git a/sound/soc/codecs/cs35l35.c b/sound/soc/codecs/cs35l35.c index 9f4a59871cee..c71696146c5e 100644 --- a/sound/soc/codecs/cs35l35.c +++ b/sound/soc/codecs/cs35l35.c @@ -1635,6 +1635,16 @@ err: return ret; } +static int cs35l35_i2c_remove(struct i2c_client *i2c_client) +{ + struct cs35l35_private *cs35l35 = i2c_get_clientdata(i2c_client); + + regulator_bulk_disable(cs35l35->num_supplies, cs35l35->supplies); + gpiod_set_value_cansleep(cs35l35->reset_gpio, 0); + + return 0; +} + static const struct of_device_id cs35l35_of_match[] = { {.compatible = "cirrus,cs35l35"}, {}, @@ -1655,6 +1665,7 @@ static struct i2c_driver cs35l35_i2c_driver = { }, .id_table = cs35l35_id, .probe = cs35l35_i2c_probe, + .remove = cs35l35_i2c_remove, }; module_i2c_driver(cs35l35_i2c_driver); diff --git a/sound/soc/codecs/cs4270.c b/sound/soc/codecs/cs4270.c index 33d74f163bd7..793a14d58667 100644 --- a/sound/soc/codecs/cs4270.c +++ b/sound/soc/codecs/cs4270.c @@ -642,6 +642,7 @@ static const struct regmap_config cs4270_regmap = { .reg_defaults = cs4270_reg_defaults, .num_reg_defaults = ARRAY_SIZE(cs4270_reg_defaults), .cache_type = REGCACHE_RBTREE, + .write_flag_mask = CS4270_I2C_INCR, .readable_reg = cs4270_reg_is_readable, .volatile_reg = cs4270_reg_is_volatile, diff --git a/sound/soc/codecs/hdac_hda.c b/sound/soc/codecs/hdac_hda.c index ffecdaaa8cf2..f889d94c8e3c 100644 --- a/sound/soc/codecs/hdac_hda.c +++ b/sound/soc/codecs/hdac_hda.c @@ -38,6 +38,9 @@ static void hdac_hda_dai_close(struct snd_pcm_substream *substream, struct snd_soc_dai *dai); static int hdac_hda_dai_prepare(struct snd_pcm_substream *substream, struct snd_soc_dai *dai); +static int hdac_hda_dai_hw_params(struct snd_pcm_substream *substream, + struct snd_pcm_hw_params *params, + struct snd_soc_dai *dai); static int hdac_hda_dai_hw_free(struct snd_pcm_substream *substream, struct snd_soc_dai *dai); static int hdac_hda_dai_set_tdm_slot(struct snd_soc_dai *dai, @@ -50,6 +53,7 @@ static const struct snd_soc_dai_ops hdac_hda_dai_ops = { .startup = hdac_hda_dai_open, .shutdown = hdac_hda_dai_close, .prepare = hdac_hda_dai_prepare, + .hw_params = hdac_hda_dai_hw_params, .hw_free = hdac_hda_dai_hw_free, .set_tdm_slot = hdac_hda_dai_set_tdm_slot, }; @@ -139,6 +143,39 @@ static int hdac_hda_dai_set_tdm_slot(struct snd_soc_dai *dai, return 0; } +static int hdac_hda_dai_hw_params(struct snd_pcm_substream *substream, + struct snd_pcm_hw_params *params, + struct snd_soc_dai *dai) +{ + struct snd_soc_component *component = dai->component; + struct hdac_hda_priv *hda_pvt; + unsigned int format_val; + unsigned int maxbps; + + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) + maxbps = dai->driver->playback.sig_bits; + else + maxbps = dai->driver->capture.sig_bits; + + hda_pvt = snd_soc_component_get_drvdata(component); + format_val = snd_hdac_calc_stream_format(params_rate(params), + params_channels(params), + params_format(params), + maxbps, + 0); + if (!format_val) { + dev_err(dai->dev, + "invalid format_val, rate=%d, ch=%d, format=%d, maxbps=%d\n", + params_rate(params), params_channels(params), + params_format(params), maxbps); + + return -EINVAL; + } + + hda_pvt->pcm[dai->id].format_val[substream->stream] = format_val; + return 0; +} + static int hdac_hda_dai_hw_free(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { @@ -162,10 +199,9 @@ static int hdac_hda_dai_prepare(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { struct snd_soc_component *component = dai->component; + struct hda_pcm_stream *hda_stream; struct hdac_hda_priv *hda_pvt; - struct snd_pcm_runtime *runtime = substream->runtime; struct hdac_device *hdev; - struct hda_pcm_stream *hda_stream; unsigned int format_val; struct hda_pcm *pcm; unsigned int stream; @@ -179,19 +215,8 @@ static int hdac_hda_dai_prepare(struct snd_pcm_substream *substream, hda_stream = &pcm->stream[substream->stream]; - format_val = snd_hdac_calc_stream_format(runtime->rate, - runtime->channels, - runtime->format, - hda_stream->maxbps, - 0); - if (!format_val) { - dev_err(&hdev->dev, - "invalid format_val, rate=%d, ch=%d, format=%d\n", - runtime->rate, runtime->channels, runtime->format); - return -EINVAL; - } - stream = hda_pvt->pcm[dai->id].stream_tag[substream->stream]; + format_val = hda_pvt->pcm[dai->id].format_val[substream->stream]; ret = snd_hda_codec_prepare(&hda_pvt->codec, hda_stream, stream, format_val, substream); diff --git a/sound/soc/codecs/hdac_hda.h b/sound/soc/codecs/hdac_hda.h index e444ef593360..6b1bd4f428e7 100644 --- a/sound/soc/codecs/hdac_hda.h +++ b/sound/soc/codecs/hdac_hda.h @@ -8,6 +8,7 @@ struct hdac_hda_pcm { int stream_tag[2]; + unsigned int format_val[2]; }; struct hdac_hda_priv { diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c index e5b6769b9797..35df73e42cbc 100644 --- a/sound/soc/codecs/hdmi-codec.c +++ b/sound/soc/codecs/hdmi-codec.c @@ -484,9 +484,6 @@ static int hdmi_codec_hw_params(struct snd_pcm_substream *substream, params_width(params), params_rate(params), params_channels(params)); - if (params_width(params) > 24) - params->msbits = 24; - ret = snd_pcm_create_iec958_consumer_hw_params(params, hp.iec.status, sizeof(hp.iec.status)); if (ret < 0) { @@ -529,73 +526,71 @@ static int hdmi_codec_set_fmt(struct snd_soc_dai *dai, { struct hdmi_codec_priv *hcp = snd_soc_dai_get_drvdata(dai); struct hdmi_codec_daifmt cf = { 0 }; - int ret = 0; dev_dbg(dai->dev, "%s()\n", __func__); - if (dai->id == DAI_ID_SPDIF) { - cf.fmt = HDMI_SPDIF; - } else { - switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) { - case SND_SOC_DAIFMT_CBM_CFM: - cf.bit_clk_master = 1; - cf.frame_clk_master = 1; - break; - case SND_SOC_DAIFMT_CBS_CFM: - cf.frame_clk_master = 1; - break; - case SND_SOC_DAIFMT_CBM_CFS: - cf.bit_clk_master = 1; - break; - case SND_SOC_DAIFMT_CBS_CFS: - break; - default: - return -EINVAL; - } + if (dai->id == DAI_ID_SPDIF) + return 0; + + switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) { + case SND_SOC_DAIFMT_CBM_CFM: + cf.bit_clk_master = 1; + cf.frame_clk_master = 1; + break; + case SND_SOC_DAIFMT_CBS_CFM: + cf.frame_clk_master = 1; + break; + case SND_SOC_DAIFMT_CBM_CFS: + cf.bit_clk_master = 1; + break; + case SND_SOC_DAIFMT_CBS_CFS: + break; + default: + return -EINVAL; + } - switch (fmt & SND_SOC_DAIFMT_INV_MASK) { - case SND_SOC_DAIFMT_NB_NF: - break; - case SND_SOC_DAIFMT_NB_IF: - cf.frame_clk_inv = 1; - break; - case SND_SOC_DAIFMT_IB_NF: - cf.bit_clk_inv = 1; - break; - case SND_SOC_DAIFMT_IB_IF: - cf.frame_clk_inv = 1; - cf.bit_clk_inv = 1; - break; - } + switch (fmt & SND_SOC_DAIFMT_INV_MASK) { + case SND_SOC_DAIFMT_NB_NF: + break; + case SND_SOC_DAIFMT_NB_IF: + cf.frame_clk_inv = 1; + break; + case SND_SOC_DAIFMT_IB_NF: + cf.bit_clk_inv = 1; + break; + case SND_SOC_DAIFMT_IB_IF: + cf.frame_clk_inv = 1; + cf.bit_clk_inv = 1; + break; + } - switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) { - case SND_SOC_DAIFMT_I2S: - cf.fmt = HDMI_I2S; - break; - case SND_SOC_DAIFMT_DSP_A: - cf.fmt = HDMI_DSP_A; - break; - case SND_SOC_DAIFMT_DSP_B: - cf.fmt = HDMI_DSP_B; - break; - case SND_SOC_DAIFMT_RIGHT_J: - cf.fmt = HDMI_RIGHT_J; - break; - case SND_SOC_DAIFMT_LEFT_J: - cf.fmt = HDMI_LEFT_J; - break; - case SND_SOC_DAIFMT_AC97: - cf.fmt = HDMI_AC97; - break; - default: - dev_err(dai->dev, "Invalid DAI interface format\n"); - return -EINVAL; - } + switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) { + case SND_SOC_DAIFMT_I2S: + cf.fmt = HDMI_I2S; + break; + case SND_SOC_DAIFMT_DSP_A: + cf.fmt = HDMI_DSP_A; + break; + case SND_SOC_DAIFMT_DSP_B: + cf.fmt = HDMI_DSP_B; + break; + case SND_SOC_DAIFMT_RIGHT_J: + cf.fmt = HDMI_RIGHT_J; + break; + case SND_SOC_DAIFMT_LEFT_J: + cf.fmt = HDMI_LEFT_J; + break; + case SND_SOC_DAIFMT_AC97: + cf.fmt = HDMI_AC97; + break; + default: + dev_err(dai->dev, "Invalid DAI interface format\n"); + return -EINVAL; } hcp->daifmt[dai->id] = cf; - return ret; + return 0; } static int hdmi_codec_digital_mute(struct snd_soc_dai *dai, int mute) @@ -792,8 +787,10 @@ static int hdmi_codec_probe(struct platform_device *pdev) i++; } - if (hcd->spdif) + if (hcd->spdif) { hcp->daidrv[i] = hdmi_spdif_dai; + hcp->daifmt[DAI_ID_SPDIF].fmt = HDMI_SPDIF; + } dev_set_drvdata(dev, hcp); diff --git a/sound/soc/codecs/nau8810.c b/sound/soc/codecs/nau8810.c index bfd74b86c9d2..645aa0794123 100644 --- a/sound/soc/codecs/nau8810.c +++ b/sound/soc/codecs/nau8810.c @@ -411,9 +411,9 @@ static const struct snd_soc_dapm_widget nau8810_dapm_widgets[] = { SND_SOC_DAPM_MIXER("Mono Mixer", NAU8810_REG_POWER3, NAU8810_MOUTMX_EN_SFT, 0, &nau8810_mono_mixer_controls[0], ARRAY_SIZE(nau8810_mono_mixer_controls)), - SND_SOC_DAPM_DAC("DAC", "HiFi Playback", NAU8810_REG_POWER3, + SND_SOC_DAPM_DAC("DAC", "Playback", NAU8810_REG_POWER3, NAU8810_DAC_EN_SFT, 0), - SND_SOC_DAPM_ADC("ADC", "HiFi Capture", NAU8810_REG_POWER2, + SND_SOC_DAPM_ADC("ADC", "Capture", NAU8810_REG_POWER2, NAU8810_ADC_EN_SFT, 0), SND_SOC_DAPM_PGA("SpkN Out", NAU8810_REG_POWER3, NAU8810_NSPK_EN_SFT, 0, NULL, 0), diff --git a/sound/soc/codecs/nau8824.c b/sound/soc/codecs/nau8824.c index 87ed3dc496dc..5ab05e75edea 100644 --- a/sound/soc/codecs/nau8824.c +++ b/sound/soc/codecs/nau8824.c @@ -681,8 +681,8 @@ static const struct snd_soc_dapm_widget nau8824_dapm_widgets[] = { SND_SOC_DAPM_ADC("ADCR", NULL, NAU8824_REG_ANALOG_ADC_2, NAU8824_ADCR_EN_SFT, 0), - SND_SOC_DAPM_AIF_OUT("AIFTX", "HiFi Capture", 0, SND_SOC_NOPM, 0, 0), - SND_SOC_DAPM_AIF_IN("AIFRX", "HiFi Playback", 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("AIFTX", "Capture", 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("AIFRX", "Playback", 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_DAC("DACL", NULL, NAU8824_REG_RDAC, NAU8824_DACL_EN_SFT, 0), @@ -831,6 +831,36 @@ static void nau8824_int_status_clear_all(struct regmap *regmap) } } +static void nau8824_dapm_disable_pin(struct nau8824 *nau8824, const char *pin) +{ + struct snd_soc_dapm_context *dapm = nau8824->dapm; + const char *prefix = dapm->component->name_prefix; + char prefixed_pin[80]; + + if (prefix) { + snprintf(prefixed_pin, sizeof(prefixed_pin), "%s %s", + prefix, pin); + snd_soc_dapm_disable_pin(dapm, prefixed_pin); + } else { + snd_soc_dapm_disable_pin(dapm, pin); + } +} + +static void nau8824_dapm_enable_pin(struct nau8824 *nau8824, const char *pin) +{ + struct snd_soc_dapm_context *dapm = nau8824->dapm; + const char *prefix = dapm->component->name_prefix; + char prefixed_pin[80]; + + if (prefix) { + snprintf(prefixed_pin, sizeof(prefixed_pin), "%s %s", + prefix, pin); + snd_soc_dapm_force_enable_pin(dapm, prefixed_pin); + } else { + snd_soc_dapm_force_enable_pin(dapm, pin); + } +} + static void nau8824_eject_jack(struct nau8824 *nau8824) { struct snd_soc_dapm_context *dapm = nau8824->dapm; @@ -839,8 +869,8 @@ static void nau8824_eject_jack(struct nau8824 *nau8824) /* Clear all interruption status */ nau8824_int_status_clear_all(regmap); - snd_soc_dapm_disable_pin(dapm, "SAR"); - snd_soc_dapm_disable_pin(dapm, "MICBIAS"); + nau8824_dapm_disable_pin(nau8824, "SAR"); + nau8824_dapm_disable_pin(nau8824, "MICBIAS"); snd_soc_dapm_sync(dapm); /* Enable the insertion interruption, disable the ejection @@ -870,8 +900,8 @@ static void nau8824_jdet_work(struct work_struct *work) struct regmap *regmap = nau8824->regmap; int adc_value, event = 0, event_mask = 0; - snd_soc_dapm_force_enable_pin(dapm, "MICBIAS"); - snd_soc_dapm_force_enable_pin(dapm, "SAR"); + nau8824_dapm_enable_pin(nau8824, "MICBIAS"); + nau8824_dapm_enable_pin(nau8824, "SAR"); snd_soc_dapm_sync(dapm); msleep(100); @@ -882,8 +912,8 @@ static void nau8824_jdet_work(struct work_struct *work) if (adc_value < HEADSET_SARADC_THD) { event |= SND_JACK_HEADPHONE; - snd_soc_dapm_disable_pin(dapm, "SAR"); - snd_soc_dapm_disable_pin(dapm, "MICBIAS"); + nau8824_dapm_disable_pin(nau8824, "SAR"); + nau8824_dapm_disable_pin(nau8824, "MICBIAS"); snd_soc_dapm_sync(dapm); } else { event |= SND_JACK_HEADSET; diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index 9d5acd2d04ab..86a7fa31c294 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -910,13 +910,21 @@ static int rt5682_headset_detect(struct snd_soc_component *component, int jack_insert) { struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component); - struct snd_soc_dapm_context *dapm = - snd_soc_component_get_dapm(component); unsigned int val, count; if (jack_insert) { - snd_soc_dapm_force_enable_pin(dapm, "CBJ Power"); - snd_soc_dapm_sync(dapm); + + snd_soc_component_update_bits(component, RT5682_PWR_ANLG_1, + RT5682_PWR_VREF2 | RT5682_PWR_MB, + RT5682_PWR_VREF2 | RT5682_PWR_MB); + snd_soc_component_update_bits(component, + RT5682_PWR_ANLG_1, RT5682_PWR_FV2, 0); + usleep_range(15000, 20000); + snd_soc_component_update_bits(component, + RT5682_PWR_ANLG_1, RT5682_PWR_FV2, RT5682_PWR_FV2); + snd_soc_component_update_bits(component, RT5682_PWR_ANLG_3, + RT5682_PWR_CBJ, RT5682_PWR_CBJ); + snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1, RT5682_TRIG_JD_MASK, RT5682_TRIG_JD_HIGH); @@ -944,8 +952,10 @@ static int rt5682_headset_detect(struct snd_soc_component *component, rt5682_enable_push_button_irq(component, false); snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1, RT5682_TRIG_JD_MASK, RT5682_TRIG_JD_LOW); - snd_soc_dapm_disable_pin(dapm, "CBJ Power"); - snd_soc_dapm_sync(dapm); + snd_soc_component_update_bits(component, RT5682_PWR_ANLG_1, + RT5682_PWR_VREF2 | RT5682_PWR_MB, 0); + snd_soc_component_update_bits(component, RT5682_PWR_ANLG_3, + RT5682_PWR_CBJ, 0); rt5682->jack_type = 0; } @@ -1198,7 +1208,7 @@ static int set_filter_clk(struct snd_soc_dapm_widget *w, struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm); struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component); - int ref, val, reg, sft, mask, idx = -EINVAL; + int ref, val, reg, idx = -EINVAL; static const int div_f[] = {1, 2, 3, 4, 6, 8, 12, 16, 24, 32, 48}; static const int div_o[] = {1, 2, 4, 6, 8, 12, 16, 24, 32, 48}; @@ -1212,15 +1222,10 @@ static int set_filter_clk(struct snd_soc_dapm_widget *w, idx = rt5682_div_sel(rt5682, ref, div_f, ARRAY_SIZE(div_f)); - if (w->shift == RT5682_PWR_ADC_S1F_BIT) { + if (w->shift == RT5682_PWR_ADC_S1F_BIT) reg = RT5682_PLL_TRACK_3; - sft = RT5682_ADC_OSR_SFT; - mask = RT5682_ADC_OSR_MASK; - } else { + else reg = RT5682_PLL_TRACK_2; - sft = RT5682_DAC_OSR_SFT; - mask = RT5682_DAC_OSR_MASK; - } snd_soc_component_update_bits(component, reg, RT5682_FILTER_CLK_DIV_MASK, idx << RT5682_FILTER_CLK_DIV_SFT); @@ -1232,7 +1237,8 @@ static int set_filter_clk(struct snd_soc_dapm_widget *w, } snd_soc_component_update_bits(component, RT5682_ADDA_CLK_1, - mask, idx << sft); + RT5682_ADC_OSR_MASK | RT5682_DAC_OSR_MASK, + (idx << RT5682_ADC_OSR_SFT) | (idx << RT5682_DAC_OSR_SFT)); return 0; } @@ -1591,8 +1597,6 @@ static const struct snd_soc_dapm_widget rt5682_dapm_widgets[] = { 0, NULL, 0), SND_SOC_DAPM_SUPPLY("Vref1", RT5682_PWR_ANLG_1, RT5682_PWR_VREF1_BIT, 0, rt5655_set_verf, SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU), - SND_SOC_DAPM_SUPPLY("Vref2", RT5682_PWR_ANLG_1, RT5682_PWR_VREF2_BIT, 0, - rt5655_set_verf, SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU), /* ASRC */ SND_SOC_DAPM_SUPPLY_S("DAC STO1 ASRC", 1, RT5682_PLL_TRACK_1, @@ -1627,9 +1631,6 @@ static const struct snd_soc_dapm_widget rt5682_dapm_widgets[] = { SND_SOC_DAPM_PGA("BST1 CBJ", SND_SOC_NOPM, 0, 0, NULL, 0), - SND_SOC_DAPM_SUPPLY("CBJ Power", RT5682_PWR_ANLG_3, - RT5682_PWR_CBJ_BIT, 0, NULL, 0), - /* REC Mixer */ SND_SOC_DAPM_MIXER("RECMIX1L", SND_SOC_NOPM, 0, 0, rt5682_rec1_l_mix, ARRAY_SIZE(rt5682_rec1_l_mix)), @@ -1792,17 +1793,13 @@ static const struct snd_soc_dapm_route rt5682_dapm_routes[] = { /*Vref*/ {"MICBIAS1", NULL, "Vref1"}, - {"MICBIAS1", NULL, "Vref2"}, {"MICBIAS2", NULL, "Vref1"}, - {"MICBIAS2", NULL, "Vref2"}, {"CLKDET SYS", NULL, "CLKDET"}, {"IN1P", NULL, "LDO2"}, {"BST1 CBJ", NULL, "IN1P"}, - {"BST1 CBJ", NULL, "CBJ Power"}, - {"CBJ Power", NULL, "Vref2"}, {"RECMIX1L", "CBJ Switch", "BST1 CBJ"}, {"RECMIX1L", NULL, "RECMIX1L Power"}, @@ -1912,9 +1909,7 @@ static const struct snd_soc_dapm_route rt5682_dapm_routes[] = { {"HP Amp", NULL, "Capless"}, {"HP Amp", NULL, "Charge Pump"}, {"HP Amp", NULL, "CLKDET SYS"}, - {"HP Amp", NULL, "CBJ Power"}, {"HP Amp", NULL, "Vref1"}, - {"HP Amp", NULL, "Vref2"}, {"HPOL Playback", "Switch", "HP Amp"}, {"HPOR Playback", "Switch", "HP Amp"}, {"HPOL", NULL, "HPOL Playback"}, @@ -2303,16 +2298,13 @@ static int rt5682_set_bias_level(struct snd_soc_component *component, switch (level) { case SND_SOC_BIAS_PREPARE: regmap_update_bits(rt5682->regmap, RT5682_PWR_ANLG_1, - RT5682_PWR_MB | RT5682_PWR_BG, - RT5682_PWR_MB | RT5682_PWR_BG); + RT5682_PWR_BG, RT5682_PWR_BG); regmap_update_bits(rt5682->regmap, RT5682_PWR_DIG_1, RT5682_DIG_GATE_CTRL | RT5682_PWR_LDO, RT5682_DIG_GATE_CTRL | RT5682_PWR_LDO); break; case SND_SOC_BIAS_STANDBY: - regmap_update_bits(rt5682->regmap, RT5682_PWR_ANLG_1, - RT5682_PWR_MB, RT5682_PWR_MB); regmap_update_bits(rt5682->regmap, RT5682_PWR_DIG_1, RT5682_DIG_GATE_CTRL, RT5682_DIG_GATE_CTRL); break; @@ -2320,7 +2312,7 @@ static int rt5682_set_bias_level(struct snd_soc_component *component, regmap_update_bits(rt5682->regmap, RT5682_PWR_DIG_1, RT5682_DIG_GATE_CTRL | RT5682_PWR_LDO, 0); regmap_update_bits(rt5682->regmap, RT5682_PWR_ANLG_1, - RT5682_PWR_MB | RT5682_PWR_BG, 0); + RT5682_PWR_BG, 0); break; default: @@ -2363,6 +2355,8 @@ static int rt5682_resume(struct snd_soc_component *component) regcache_cache_only(rt5682->regmap, false); regcache_sync(rt5682->regmap); + rt5682_irq(0, rt5682); + return 0; } #else diff --git a/sound/soc/codecs/tlv320aic32x4-i2c.c b/sound/soc/codecs/tlv320aic32x4-i2c.c index 385fa2e9525a..22c3a6bc0b6c 100644 --- a/sound/soc/codecs/tlv320aic32x4-i2c.c +++ b/sound/soc/codecs/tlv320aic32x4-i2c.c @@ -3,7 +3,7 @@ * * Copyright 2011 NW Digital Radio * - * Author: Jeremy McDermond <nh6z@nh6z.net> + * Author: Annaliese McDermond <nh6z@nh6z.net> * * Based on sound/soc/codecs/wm8974 and TI driver for kernel 2.6.27. * @@ -72,5 +72,5 @@ static struct i2c_driver aic32x4_i2c_driver = { module_i2c_driver(aic32x4_i2c_driver); MODULE_DESCRIPTION("ASoC TLV320AIC32x4 codec driver I2C"); -MODULE_AUTHOR("Jeremy McDermond <nh6z@nh6z.net>"); +MODULE_AUTHOR("Annaliese McDermond <nh6z@nh6z.net>"); MODULE_LICENSE("GPL"); diff --git a/sound/soc/codecs/tlv320aic32x4-spi.c b/sound/soc/codecs/tlv320aic32x4-spi.c index 07d78ae51e05..aa5b7ba0254b 100644 --- a/sound/soc/codecs/tlv320aic32x4-spi.c +++ b/sound/soc/codecs/tlv320aic32x4-spi.c @@ -3,7 +3,7 @@ * * Copyright 2011 NW Digital Radio * - * Author: Jeremy McDermond <nh6z@nh6z.net> + * Author: Annaliese McDermond <nh6z@nh6z.net> * * Based on sound/soc/codecs/wm8974 and TI driver for kernel 2.6.27. * @@ -74,5 +74,5 @@ static struct spi_driver aic32x4_spi_driver = { module_spi_driver(aic32x4_spi_driver); MODULE_DESCRIPTION("ASoC TLV320AIC32x4 codec driver SPI"); -MODULE_AUTHOR("Jeremy McDermond <nh6z@nh6z.net>"); +MODULE_AUTHOR("Annaliese McDermond <nh6z@nh6z.net>"); MODULE_LICENSE("GPL"); diff --git a/sound/soc/codecs/tlv320aic32x4.c b/sound/soc/codecs/tlv320aic32x4.c index 96f1526cb258..5520044929f4 100644 --- a/sound/soc/codecs/tlv320aic32x4.c +++ b/sound/soc/codecs/tlv320aic32x4.c @@ -490,6 +490,8 @@ static const struct snd_soc_dapm_widget aic32x4_dapm_widgets[] = { SND_SOC_DAPM_INPUT("IN2_R"), SND_SOC_DAPM_INPUT("IN3_L"), SND_SOC_DAPM_INPUT("IN3_R"), + SND_SOC_DAPM_INPUT("CM_L"), + SND_SOC_DAPM_INPUT("CM_R"), }; static const struct snd_soc_dapm_route aic32x4_dapm_routes[] = { diff --git a/sound/soc/codecs/tlv320aic3x.c b/sound/soc/codecs/tlv320aic3x.c index 283583d1db60..516d17cb2182 100644 --- a/sound/soc/codecs/tlv320aic3x.c +++ b/sound/soc/codecs/tlv320aic3x.c @@ -1609,7 +1609,6 @@ static int aic3x_probe(struct snd_soc_component *component) struct aic3x_priv *aic3x = snd_soc_component_get_drvdata(component); int ret, i; - INIT_LIST_HEAD(&aic3x->list); aic3x->component = component; for (i = 0; i < ARRAY_SIZE(aic3x->supplies); i++) { @@ -1873,6 +1872,7 @@ static int aic3x_i2c_probe(struct i2c_client *i2c, if (ret != 0) goto err_gpio; + INIT_LIST_HEAD(&aic3x->list); list_add(&aic3x->list, &reset_list); return 0; @@ -1889,6 +1889,8 @@ static int aic3x_i2c_remove(struct i2c_client *client) { struct aic3x_priv *aic3x = i2c_get_clientdata(client); + list_del(&aic3x->list); + if (gpio_is_valid(aic3x->gpio_reset) && !aic3x_is_shared_reset(aic3x)) { gpio_set_value(aic3x->gpio_reset, 0); diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index b93fdc8d2d6f..b0b48eb9c7c9 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -2905,6 +2905,8 @@ int wm_adsp2_event(struct snd_soc_dapm_widget *w, if (wm_adsp_fw[dsp->fw].num_caps != 0) wm_adsp_buffer_free(dsp); + dsp->fatal_error = false; + mutex_unlock(&dsp->pwr_lock); adsp_dbg(dsp, "Execution stopped\n"); @@ -3000,6 +3002,9 @@ static int wm_adsp_compr_attach(struct wm_adsp_compr *compr) { struct wm_adsp_compr_buf *buf = NULL, *tmp; + if (compr->dsp->fatal_error) + return -EINVAL; + list_for_each_entry(tmp, &compr->dsp->buffer_list, list) { if (!tmp->name || !strcmp(compr->name, tmp->name)) { buf = tmp; @@ -3535,11 +3540,11 @@ static int wm_adsp_buffer_get_error(struct wm_adsp_compr_buf *buf) ret = wm_adsp_buffer_read(buf, HOST_BUFFER_FIELD(error), &buf->error); if (ret < 0) { - adsp_err(buf->dsp, "Failed to check buffer error: %d\n", ret); + compr_err(buf, "Failed to check buffer error: %d\n", ret); return ret; } if (buf->error != 0) { - adsp_err(buf->dsp, "Buffer error occurred: %d\n", buf->error); + compr_err(buf, "Buffer error occurred: %d\n", buf->error); return -EIO; } @@ -3571,8 +3576,6 @@ int wm_adsp_compr_trigger(struct snd_compr_stream *stream, int cmd) if (ret < 0) break; - wm_adsp_buffer_clear(compr->buf); - /* Trigger the IRQ at one fragment of data */ ret = wm_adsp_buffer_write(compr->buf, HOST_BUFFER_FIELD(high_water_mark), @@ -3584,6 +3587,8 @@ int wm_adsp_compr_trigger(struct snd_compr_stream *stream, int cmd) } break; case SNDRV_PCM_TRIGGER_STOP: + if (wm_adsp_compr_attached(compr)) + wm_adsp_buffer_clear(compr->buf); break; default: ret = -EINVAL; @@ -3917,22 +3922,40 @@ int wm_adsp2_lock(struct wm_adsp *dsp, unsigned int lock_regions) } EXPORT_SYMBOL_GPL(wm_adsp2_lock); +static void wm_adsp_fatal_error(struct wm_adsp *dsp) +{ + struct wm_adsp_compr *compr; + + dsp->fatal_error = true; + + list_for_each_entry(compr, &dsp->compr_list, list) { + if (compr->stream) { + snd_compr_stop_error(compr->stream, + SNDRV_PCM_STATE_XRUN); + snd_compr_fragment_elapsed(compr->stream); + } + } +} + irqreturn_t wm_adsp2_bus_error(struct wm_adsp *dsp) { unsigned int val; struct regmap *regmap = dsp->regmap; int ret = 0; + mutex_lock(&dsp->pwr_lock); + ret = regmap_read(regmap, dsp->base + ADSP2_LOCK_REGION_CTRL, &val); if (ret) { adsp_err(dsp, "Failed to read Region Lock Ctrl register: %d\n", ret); - return IRQ_HANDLED; + goto error; } if (val & ADSP2_WDT_TIMEOUT_STS_MASK) { adsp_err(dsp, "watchdog timeout error\n"); wm_adsp_stop_watchdog(dsp); + wm_adsp_fatal_error(dsp); } if (val & (ADSP2_SLAVE_ERR_MASK | ADSP2_REGION_LOCK_ERR_MASK)) { @@ -3946,7 +3969,7 @@ irqreturn_t wm_adsp2_bus_error(struct wm_adsp *dsp) adsp_err(dsp, "Failed to read Bus Err Addr register: %d\n", ret); - return IRQ_HANDLED; + goto error; } adsp_err(dsp, "bus error address = 0x%x\n", @@ -3959,7 +3982,7 @@ irqreturn_t wm_adsp2_bus_error(struct wm_adsp *dsp) adsp_err(dsp, "Failed to read Pmem Xmem Err Addr register: %d\n", ret); - return IRQ_HANDLED; + goto error; } adsp_err(dsp, "xmem error address = 0x%x\n", @@ -3972,6 +3995,9 @@ irqreturn_t wm_adsp2_bus_error(struct wm_adsp *dsp) regmap_update_bits(regmap, dsp->base + ADSP2_LOCK_REGION_CTRL, ADSP2_CTRL_ERR_EINT, ADSP2_CTRL_ERR_EINT); +error: + mutex_unlock(&dsp->pwr_lock); + return IRQ_HANDLED; } EXPORT_SYMBOL_GPL(wm_adsp2_bus_error); diff --git a/sound/soc/codecs/wm_adsp.h b/sound/soc/codecs/wm_adsp.h index 59e07ad16329..8f09b4419a91 100644 --- a/sound/soc/codecs/wm_adsp.h +++ b/sound/soc/codecs/wm_adsp.h @@ -85,6 +85,7 @@ struct wm_adsp { bool preloaded; bool booted; bool running; + bool fatal_error; struct list_head ctl_list; diff --git a/sound/soc/fsl/fsl_asrc.c b/sound/soc/fsl/fsl_asrc.c index 528e8b108422..0b937924d2e4 100644 --- a/sound/soc/fsl/fsl_asrc.c +++ b/sound/soc/fsl/fsl_asrc.c @@ -445,6 +445,19 @@ struct dma_chan *fsl_asrc_get_dma_channel(struct fsl_asrc_pair *pair, bool dir) } EXPORT_SYMBOL_GPL(fsl_asrc_get_dma_channel); +static int fsl_asrc_dai_startup(struct snd_pcm_substream *substream, + struct snd_soc_dai *dai) +{ + struct fsl_asrc *asrc_priv = snd_soc_dai_get_drvdata(dai); + + /* Odd channel number is not valid for older ASRC (channel_bits==3) */ + if (asrc_priv->channel_bits == 3) + snd_pcm_hw_constraint_step(substream->runtime, 0, + SNDRV_PCM_HW_PARAM_CHANNELS, 2); + + return 0; +} + static int fsl_asrc_dai_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params, struct snd_soc_dai *dai) @@ -539,6 +552,7 @@ static int fsl_asrc_dai_trigger(struct snd_pcm_substream *substream, int cmd, } static const struct snd_soc_dai_ops fsl_asrc_dai_ops = { + .startup = fsl_asrc_dai_startup, .hw_params = fsl_asrc_dai_hw_params, .hw_free = fsl_asrc_dai_hw_free, .trigger = fsl_asrc_dai_trigger, diff --git a/sound/soc/fsl/fsl_esai.c b/sound/soc/fsl/fsl_esai.c index afe67c865330..3623aa9a6f2e 100644 --- a/sound/soc/fsl/fsl_esai.c +++ b/sound/soc/fsl/fsl_esai.c @@ -54,6 +54,8 @@ struct fsl_esai { u32 fifo_depth; u32 slot_width; u32 slots; + u32 tx_mask; + u32 rx_mask; u32 hck_rate[2]; u32 sck_rate[2]; bool hck_dir[2]; @@ -361,21 +363,13 @@ static int fsl_esai_set_dai_tdm_slot(struct snd_soc_dai *dai, u32 tx_mask, regmap_update_bits(esai_priv->regmap, REG_ESAI_TCCR, ESAI_xCCR_xDC_MASK, ESAI_xCCR_xDC(slots)); - regmap_update_bits(esai_priv->regmap, REG_ESAI_TSMA, - ESAI_xSMA_xS_MASK, ESAI_xSMA_xS(tx_mask)); - regmap_update_bits(esai_priv->regmap, REG_ESAI_TSMB, - ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(tx_mask)); - regmap_update_bits(esai_priv->regmap, REG_ESAI_RCCR, ESAI_xCCR_xDC_MASK, ESAI_xCCR_xDC(slots)); - regmap_update_bits(esai_priv->regmap, REG_ESAI_RSMA, - ESAI_xSMA_xS_MASK, ESAI_xSMA_xS(rx_mask)); - regmap_update_bits(esai_priv->regmap, REG_ESAI_RSMB, - ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(rx_mask)); - esai_priv->slot_width = slot_width; esai_priv->slots = slots; + esai_priv->tx_mask = tx_mask; + esai_priv->rx_mask = rx_mask; return 0; } @@ -596,6 +590,7 @@ static int fsl_esai_trigger(struct snd_pcm_substream *substream, int cmd, bool tx = substream->stream == SNDRV_PCM_STREAM_PLAYBACK; u8 i, channels = substream->runtime->channels; u32 pins = DIV_ROUND_UP(channels, esai_priv->slots); + u32 mask; switch (cmd) { case SNDRV_PCM_TRIGGER_START: @@ -608,15 +603,38 @@ static int fsl_esai_trigger(struct snd_pcm_substream *substream, int cmd, for (i = 0; tx && i < channels; i++) regmap_write(esai_priv->regmap, REG_ESAI_ETDR, 0x0); + /* + * When set the TE/RE in the end of enablement flow, there + * will be channel swap issue for multi data line case. + * In order to workaround this issue, we switch the bit + * enablement sequence to below sequence + * 1) clear the xSMB & xSMA: which is done in probe and + * stop state. + * 2) set TE/RE + * 3) set xSMB + * 4) set xSMA: xSMA is the last one in this flow, which + * will trigger esai to start. + */ regmap_update_bits(esai_priv->regmap, REG_ESAI_xCR(tx), tx ? ESAI_xCR_TE_MASK : ESAI_xCR_RE_MASK, tx ? ESAI_xCR_TE(pins) : ESAI_xCR_RE(pins)); + mask = tx ? esai_priv->tx_mask : esai_priv->rx_mask; + + regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMB(tx), + ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(mask)); + regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMA(tx), + ESAI_xSMA_xS_MASK, ESAI_xSMA_xS(mask)); + break; case SNDRV_PCM_TRIGGER_SUSPEND: case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_PAUSE_PUSH: regmap_update_bits(esai_priv->regmap, REG_ESAI_xCR(tx), tx ? ESAI_xCR_TE_MASK : ESAI_xCR_RE_MASK, 0); + regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMA(tx), + ESAI_xSMA_xS_MASK, 0); + regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMB(tx), + ESAI_xSMB_xS_MASK, 0); /* Disable and reset FIFO */ regmap_update_bits(esai_priv->regmap, REG_ESAI_xFCR(tx), @@ -906,6 +924,15 @@ static int fsl_esai_probe(struct platform_device *pdev) return ret; } + esai_priv->tx_mask = 0xFFFFFFFF; + esai_priv->rx_mask = 0xFFFFFFFF; + + /* Clear the TSMA, TSMB, RSMA, RSMB */ + regmap_write(esai_priv->regmap, REG_ESAI_TSMA, 0); + regmap_write(esai_priv->regmap, REG_ESAI_TSMB, 0); + regmap_write(esai_priv->regmap, REG_ESAI_RSMA, 0); + regmap_write(esai_priv->regmap, REG_ESAI_RSMB, 0); + ret = devm_snd_soc_register_component(&pdev->dev, &fsl_esai_component, &fsl_esai_dai, 1); if (ret) { diff --git a/sound/soc/generic/audio-graph-card.c b/sound/soc/generic/audio-graph-card.c index bb12351330e8..69bc4848d787 100644 --- a/sound/soc/generic/audio-graph-card.c +++ b/sound/soc/generic/audio-graph-card.c @@ -20,6 +20,8 @@ #include <linux/string.h> #include <sound/simple_card_utils.h> +#define DPCM_SELECTABLE 1 + struct graph_priv { struct snd_soc_card snd_card; struct graph_dai_props { @@ -440,6 +442,7 @@ static int graph_for_each_link(struct graph_priv *priv, struct device_node *codec_port; struct device_node *codec_port_old = NULL; struct asoc_simple_card_data adata; + uintptr_t dpcm_selectable = (uintptr_t)of_device_get_match_data(dev); int rc, ret; /* loop for all listed CPU port */ @@ -470,8 +473,9 @@ static int graph_for_each_link(struct graph_priv *priv, * if Codec port has many endpoints, * or has convert-xxx property */ - if ((of_get_child_count(codec_port) > 1) || - adata.convert_rate || adata.convert_channels) + if (dpcm_selectable && + ((of_get_child_count(codec_port) > 1) || + adata.convert_rate || adata.convert_channels)) ret = func_dpcm(priv, cpu_ep, codec_ep, li, (codec_port_old == codec_port)); /* else normal sound */ @@ -732,7 +736,8 @@ static int graph_remove(struct platform_device *pdev) static const struct of_device_id graph_of_match[] = { { .compatible = "audio-graph-card", }, - { .compatible = "audio-graph-scu-card", }, + { .compatible = "audio-graph-scu-card", + .data = (void *)DPCM_SELECTABLE }, {}, }; MODULE_DEVICE_TABLE(of, graph_of_match); diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c index 7147bba45a2a..34de32efc4c4 100644 --- a/sound/soc/generic/simple-card.c +++ b/sound/soc/generic/simple-card.c @@ -9,12 +9,15 @@ #include <linux/device.h> #include <linux/module.h> #include <linux/of.h> +#include <linux/of_device.h> #include <linux/platform_device.h> #include <linux/string.h> #include <sound/simple_card.h> #include <sound/soc-dai.h> #include <sound/soc.h> +#define DPCM_SELECTABLE 1 + struct simple_priv { struct snd_soc_card snd_card; struct simple_dai_props { @@ -441,6 +444,7 @@ static int simple_for_each_link(struct simple_priv *priv, struct device *dev = simple_priv_to_dev(priv); struct device_node *top = dev->of_node; struct device_node *node; + uintptr_t dpcm_selectable = (uintptr_t)of_device_get_match_data(dev); bool is_top = 0; int ret = 0; @@ -480,8 +484,9 @@ static int simple_for_each_link(struct simple_priv *priv, * if it has many CPUs, * or has convert-xxx property */ - if (num > 2 || - adata.convert_rate || adata.convert_channels) + if (dpcm_selectable && + (num > 2 || + adata.convert_rate || adata.convert_channels)) ret = func_dpcm(priv, np, codec, li, is_top); /* else normal sound */ else @@ -822,7 +827,8 @@ static int simple_remove(struct platform_device *pdev) static const struct of_device_id simple_of_match[] = { { .compatible = "simple-audio-card", }, - { .compatible = "simple-scu-audio-card", }, + { .compatible = "simple-scu-audio-card", + .data = (void *)DPCM_SELECTABLE }, {}, }; MODULE_DEVICE_TABLE(of, simple_of_match); diff --git a/sound/soc/intel/atom/sst-mfld-platform-pcm.c b/sound/soc/intel/atom/sst-mfld-platform-pcm.c index 08cea5b5cda9..0e8b1c5eec88 100644 --- a/sound/soc/intel/atom/sst-mfld-platform-pcm.c +++ b/sound/soc/intel/atom/sst-mfld-platform-pcm.c @@ -706,9 +706,17 @@ static int sst_soc_probe(struct snd_soc_component *component) return sst_dsp_init_v2_dpcm(component); } +static void sst_soc_remove(struct snd_soc_component *component) +{ + struct sst_data *drv = dev_get_drvdata(component->dev); + + drv->soc_card = NULL; +} + static const struct snd_soc_component_driver sst_soc_platform_drv = { .name = DRV_NAME, .probe = sst_soc_probe, + .remove = sst_soc_remove, .ops = &sst_platform_ops, .compr_ops = &sst_platform_compr_ops, .pcm_new = sst_pcm_new, diff --git a/sound/soc/intel/boards/cht_bsw_max98090_ti.c b/sound/soc/intel/boards/cht_bsw_max98090_ti.c index 3263b0495853..c0e0844f75b9 100644 --- a/sound/soc/intel/boards/cht_bsw_max98090_ti.c +++ b/sound/soc/intel/boards/cht_bsw_max98090_ti.c @@ -43,6 +43,7 @@ struct cht_mc_private { struct clk *mclk; struct snd_soc_jack jack; bool ts3a227e_present; + int quirks; }; static int platform_clock_control(struct snd_soc_dapm_widget *w, @@ -54,6 +55,10 @@ static int platform_clock_control(struct snd_soc_dapm_widget *w, struct cht_mc_private *ctx = snd_soc_card_get_drvdata(card); int ret; + /* See the comment in snd_cht_mc_probe() */ + if (ctx->quirks & QUIRK_PMC_PLT_CLK_0) + return 0; + codec_dai = snd_soc_card_get_codec_dai(card, CHT_CODEC_DAI); if (!codec_dai) { dev_err(card->dev, "Codec dai not found; Unable to set platform clock\n"); @@ -223,6 +228,10 @@ static int cht_codec_init(struct snd_soc_pcm_runtime *runtime) "jack detection gpios not added, error %d\n", ret); } + /* See the comment in snd_cht_mc_probe() */ + if (ctx->quirks & QUIRK_PMC_PLT_CLK_0) + return 0; + /* * The firmware might enable the clock at * boot (this information may or may not @@ -423,16 +432,15 @@ static int snd_cht_mc_probe(struct platform_device *pdev) const char *mclk_name; struct snd_soc_acpi_mach *mach; const char *platform_name; - int quirks = 0; - - dmi_id = dmi_first_match(cht_max98090_quirk_table); - if (dmi_id) - quirks = (unsigned long)dmi_id->driver_data; drv = devm_kzalloc(&pdev->dev, sizeof(*drv), GFP_KERNEL); if (!drv) return -ENOMEM; + dmi_id = dmi_first_match(cht_max98090_quirk_table); + if (dmi_id) + drv->quirks = (unsigned long)dmi_id->driver_data; + drv->ts3a227e_present = acpi_dev_found("104C227E"); if (!drv->ts3a227e_present) { /* no need probe TI jack detection chip */ @@ -458,7 +466,7 @@ static int snd_cht_mc_probe(struct platform_device *pdev) snd_soc_card_cht.dev = &pdev->dev; snd_soc_card_set_drvdata(&snd_soc_card_cht, drv); - if (quirks & QUIRK_PMC_PLT_CLK_0) + if (drv->quirks & QUIRK_PMC_PLT_CLK_0) mclk_name = "pmc_plt_clk_0"; else mclk_name = "pmc_plt_clk_3"; @@ -471,6 +479,21 @@ static int snd_cht_mc_probe(struct platform_device *pdev) return PTR_ERR(drv->mclk); } + /* + * Boards which have the MAX98090's clk connected to clk_0 do not seem + * to like it if we muck with the clock. If we disable the clock when + * it is unused we get "max98090 i2c-193C9890:00: PLL unlocked" errors + * and the PLL never seems to lock again. + * So for these boards we enable it here once and leave it at that. + */ + if (drv->quirks & QUIRK_PMC_PLT_CLK_0) { + ret_val = clk_prepare_enable(drv->mclk); + if (ret_val < 0) { + dev_err(&pdev->dev, "MCLK enable error: %d\n", ret_val); + return ret_val; + } + } + ret_val = devm_snd_soc_register_card(&pdev->dev, &snd_soc_card_cht); if (ret_val) { dev_err(&pdev->dev, @@ -481,11 +504,23 @@ static int snd_cht_mc_probe(struct platform_device *pdev) return ret_val; } +static int snd_cht_mc_remove(struct platform_device *pdev) +{ + struct snd_soc_card *card = platform_get_drvdata(pdev); + struct cht_mc_private *ctx = snd_soc_card_get_drvdata(card); + + if (ctx->quirks & QUIRK_PMC_PLT_CLK_0) + clk_disable_unprepare(ctx->mclk); + + return 0; +} + static struct platform_driver snd_cht_mc_driver = { .driver = { .name = "cht-bsw-max98090", }, .probe = snd_cht_mc_probe, + .remove = snd_cht_mc_remove, }; module_platform_driver(snd_cht_mc_driver) diff --git a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c index 7044d8c2b187..879f14257a3e 100644 --- a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c +++ b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c @@ -405,7 +405,7 @@ static const struct snd_pcm_hw_constraint_list constraints_dmic_channels = { }; static const unsigned int dmic_2ch[] = { - 4, + 2, }; static const struct snd_pcm_hw_constraint_list constraints_dmic_2ch = { diff --git a/sound/soc/intel/skylake/skl-messages.c b/sound/soc/intel/skylake/skl-messages.c index 28c4806b196a..4bf70b4429f0 100644 --- a/sound/soc/intel/skylake/skl-messages.c +++ b/sound/soc/intel/skylake/skl-messages.c @@ -483,6 +483,7 @@ static void skl_set_base_module_format(struct skl_sst *ctx, base_cfg->audio_fmt.bit_depth = format->bit_depth; base_cfg->audio_fmt.valid_bit_depth = format->valid_bit_depth; base_cfg->audio_fmt.ch_cfg = format->ch_cfg; + base_cfg->audio_fmt.sample_type = format->sample_type; dev_dbg(ctx->dev, "bit_depth=%x valid_bd=%x ch_config=%x\n", format->bit_depth, format->valid_bit_depth, diff --git a/sound/soc/intel/skylake/skl-pcm.c b/sound/soc/intel/skylake/skl-pcm.c index 1ae83f4ccc36..9735e2412251 100644 --- a/sound/soc/intel/skylake/skl-pcm.c +++ b/sound/soc/intel/skylake/skl-pcm.c @@ -181,6 +181,7 @@ int skl_pcm_link_dma_prepare(struct device *dev, struct skl_pipe_params *params) struct hdac_stream *hstream; struct hdac_ext_stream *stream; struct hdac_ext_link *link; + unsigned char stream_tag; hstream = snd_hdac_get_stream(bus, params->stream, params->link_dma_id + 1); @@ -199,10 +200,13 @@ int skl_pcm_link_dma_prepare(struct device *dev, struct skl_pipe_params *params) snd_hdac_ext_link_stream_setup(stream, format_val); - list_for_each_entry(link, &bus->hlink_list, list) { - if (link->index == params->link_index) - snd_hdac_ext_link_set_stream_id(link, - hstream->stream_tag); + stream_tag = hstream->stream_tag; + if (stream->hstream.direction == SNDRV_PCM_STREAM_PLAYBACK) { + list_for_each_entry(link, &bus->hlink_list, list) { + if (link->index == params->link_index) + snd_hdac_ext_link_set_stream_id(link, + stream_tag); + } } stream->link_prepared = 1; @@ -645,6 +649,7 @@ static int skl_link_hw_free(struct snd_pcm_substream *substream, struct hdac_ext_stream *link_dev = snd_soc_dai_get_dma_data(dai, substream); struct hdac_ext_link *link; + unsigned char stream_tag; dev_dbg(dai->dev, "%s: %s\n", __func__, dai->name); @@ -654,7 +659,11 @@ static int skl_link_hw_free(struct snd_pcm_substream *substream, if (!link) return -EINVAL; - snd_hdac_ext_link_clear_stream_id(link, hdac_stream(link_dev)->stream_tag); + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { + stream_tag = hdac_stream(link_dev)->stream_tag; + snd_hdac_ext_link_clear_stream_id(link, stream_tag); + } + snd_hdac_ext_stream_release(link_dev, HDAC_EXT_STREAM_TYPE_LINK); return 0; } @@ -1453,13 +1462,20 @@ static int skl_platform_soc_probe(struct snd_soc_component *component) return 0; } +static void skl_pcm_remove(struct snd_soc_component *component) +{ + /* remove topology */ + snd_soc_tplg_component_remove(component, SND_SOC_TPLG_INDEX_ALL); +} + static const struct snd_soc_component_driver skl_component = { .name = "pcm", .probe = skl_platform_soc_probe, + .remove = skl_pcm_remove, .ops = &skl_platform_ops, .pcm_new = skl_pcm_new, .pcm_free = skl_pcm_free, - .ignore_module_refcount = 1, /* do not increase the refcount in core */ + .module_get_upon_open = 1, /* increment refcount when a pcm is opened */ }; int skl_platform_register(struct device *dev) diff --git a/sound/soc/mediatek/common/mtk-btcvsd.c b/sound/soc/mediatek/common/mtk-btcvsd.c index 1b8bcdaf02d1..9a163d7064d1 100644 --- a/sound/soc/mediatek/common/mtk-btcvsd.c +++ b/sound/soc/mediatek/common/mtk-btcvsd.c @@ -49,6 +49,7 @@ enum bt_sco_state { BT_SCO_STATE_IDLE, BT_SCO_STATE_RUNNING, BT_SCO_STATE_ENDING, + BT_SCO_STATE_LOOPBACK, }; enum bt_sco_direct { @@ -486,7 +487,8 @@ static irqreturn_t mtk_btcvsd_snd_irq_handler(int irq_id, void *dev) if (bt->rx->state != BT_SCO_STATE_RUNNING && bt->rx->state != BT_SCO_STATE_ENDING && bt->tx->state != BT_SCO_STATE_RUNNING && - bt->tx->state != BT_SCO_STATE_ENDING) { + bt->tx->state != BT_SCO_STATE_ENDING && + bt->tx->state != BT_SCO_STATE_LOOPBACK) { dev_warn(bt->dev, "%s(), in idle state: rx->state: %d, tx->state: %d\n", __func__, bt->rx->state, bt->tx->state); goto irq_handler_exit; @@ -512,6 +514,42 @@ static irqreturn_t mtk_btcvsd_snd_irq_handler(int irq_id, void *dev) buf_cnt_tx = btsco_packet_info[packet_type][2]; buf_cnt_rx = btsco_packet_info[packet_type][3]; + if (bt->tx->state == BT_SCO_STATE_LOOPBACK) { + u8 *src, *dst; + unsigned long connsys_addr_rx, ap_addr_rx; + unsigned long connsys_addr_tx, ap_addr_tx; + + connsys_addr_rx = *bt->bt_reg_pkt_r; + ap_addr_rx = (unsigned long)bt->bt_sram_bank2_base + + (connsys_addr_rx & 0xFFFF); + + connsys_addr_tx = *bt->bt_reg_pkt_w; + ap_addr_tx = (unsigned long)bt->bt_sram_bank2_base + + (connsys_addr_tx & 0xFFFF); + + if (connsys_addr_tx == 0xdeadfeed || + connsys_addr_rx == 0xdeadfeed) { + /* bt return 0xdeadfeed if read reg during bt sleep */ + dev_warn(bt->dev, "%s(), connsys_addr_tx == 0xdeadfeed\n", + __func__); + goto irq_handler_exit; + } + + src = (u8 *)ap_addr_rx; + dst = (u8 *)ap_addr_tx; + + mtk_btcvsd_snd_data_transfer(BT_SCO_DIRECT_BT2ARM, src, + bt->tx->temp_packet_buf, + packet_length, + packet_num); + mtk_btcvsd_snd_data_transfer(BT_SCO_DIRECT_ARM2BT, + bt->tx->temp_packet_buf, dst, + packet_length, + packet_num); + bt->rx->rw_cnt++; + bt->tx->rw_cnt++; + } + if (bt->rx->state == BT_SCO_STATE_RUNNING || bt->rx->state == BT_SCO_STATE_ENDING) { if (bt->rx->xrun) { @@ -1067,6 +1105,33 @@ static int btcvsd_band_set(struct snd_kcontrol *kcontrol, return 0; } +static int btcvsd_loopback_get(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol); + struct mtk_btcvsd_snd *bt = snd_soc_component_get_drvdata(cmpnt); + bool lpbk_en = bt->tx->state == BT_SCO_STATE_LOOPBACK; + + ucontrol->value.integer.value[0] = lpbk_en; + return 0; +} + +static int btcvsd_loopback_set(struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) +{ + struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol); + struct mtk_btcvsd_snd *bt = snd_soc_component_get_drvdata(cmpnt); + + if (ucontrol->value.integer.value[0]) { + mtk_btcvsd_snd_set_state(bt, bt->tx, BT_SCO_STATE_LOOPBACK); + mtk_btcvsd_snd_set_state(bt, bt->rx, BT_SCO_STATE_LOOPBACK); + } else { + mtk_btcvsd_snd_set_state(bt, bt->tx, BT_SCO_STATE_RUNNING); + mtk_btcvsd_snd_set_state(bt, bt->rx, BT_SCO_STATE_RUNNING); + } + return 0; +} + static int btcvsd_tx_mute_get(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { @@ -1202,6 +1267,8 @@ static int btcvsd_tx_timestamp_get(struct snd_kcontrol *kcontrol, static const struct snd_kcontrol_new mtk_btcvsd_snd_controls[] = { SOC_ENUM_EXT("BTCVSD Band", btcvsd_enum[0], btcvsd_band_get, btcvsd_band_set), + SOC_SINGLE_BOOL_EXT("BTCVSD Loopback Switch", 0, + btcvsd_loopback_get, btcvsd_loopback_set), SOC_SINGLE_BOOL_EXT("BTCVSD Tx Mute Switch", 0, btcvsd_tx_mute_get, btcvsd_tx_mute_set), SOC_SINGLE_BOOL_EXT("BTCVSD Tx Irq Received Switch", 0, diff --git a/sound/soc/mediatek/mt8183/mt8183-afe-clk.c b/sound/soc/mediatek/mt8183/mt8183-afe-clk.c index f523ad103acc..48e81c5d52fc 100644 --- a/sound/soc/mediatek/mt8183/mt8183-afe-clk.c +++ b/sound/soc/mediatek/mt8183/mt8183-afe-clk.c @@ -605,6 +605,10 @@ void mt8183_mck_disable(struct mtk_base_afe *afe, int mck_id) int m_sel_id = mck_div[mck_id].m_sel_id; int div_clk_id = mck_div[mck_id].div_clk_id; + /* i2s5 mck not support */ + if (mck_id == MT8183_I2S5_MCK) + return; + clk_disable_unprepare(afe_priv->clk[div_clk_id]); if (m_sel_id >= 0) clk_disable_unprepare(afe_priv->clk[m_sel_id]); diff --git a/sound/soc/rockchip/rockchip_pdm.c b/sound/soc/rockchip/rockchip_pdm.c index 400e29edb1c9..d0b403a0e27b 100644 --- a/sound/soc/rockchip/rockchip_pdm.c +++ b/sound/soc/rockchip/rockchip_pdm.c @@ -24,7 +24,7 @@ #include "rockchip_pdm.h" -#define PDM_DMA_BURST_SIZE (16) /* size * width: 16*4 = 64 bytes */ +#define PDM_DMA_BURST_SIZE (8) /* size * width: 8*4 = 32 bytes */ struct rk_pdm_dev { struct device *dev; @@ -208,7 +208,9 @@ static int rockchip_pdm_set_fmt(struct snd_soc_dai *cpu_dai, return -EINVAL; } + pm_runtime_get_sync(cpu_dai->dev); regmap_update_bits(pdm->regmap, PDM_CLK_CTRL, mask, val); + pm_runtime_put(cpu_dai->dev); return 0; } diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c index 4231001226f4..ab471d550d17 100644 --- a/sound/soc/samsung/i2s.c +++ b/sound/soc/samsung/i2s.c @@ -1130,11 +1130,11 @@ static const struct snd_soc_dapm_widget samsung_i2s_widgets[] = { }; static const struct snd_soc_dapm_route samsung_i2s_dapm_routes[] = { - { "Playback Mixer", NULL, "Primary" }, - { "Playback Mixer", NULL, "Secondary" }, + { "Playback Mixer", NULL, "Primary Playback" }, + { "Playback Mixer", NULL, "Secondary Playback" }, { "Mixer DAI TX", NULL, "Playback Mixer" }, - { "Playback Mixer", NULL, "Mixer DAI RX" }, + { "Primary Capture", NULL, "Mixer DAI RX" }, }; static const struct snd_soc_component_driver samsung_i2s_component = { @@ -1155,7 +1155,8 @@ static int i2s_alloc_dais(struct samsung_i2s_priv *priv, int num_dais) { static const char *dai_names[] = { "samsung-i2s", "samsung-i2s-sec" }; - static const char *stream_names[] = { "Primary", "Secondary" }; + static const char *stream_names[] = { "Primary Playback", + "Secondary Playback" }; struct snd_soc_dai_driver *dai_drv; struct i2s_dai *dai; int i; @@ -1201,6 +1202,7 @@ static int i2s_alloc_dais(struct samsung_i2s_priv *priv, dai_drv->capture.channels_max = 2; dai_drv->capture.rates = i2s_dai_data->pcm_rates; dai_drv->capture.formats = SAMSUNG_I2S_FMTS; + dai_drv->capture.stream_name = "Primary Capture"; return 0; } diff --git a/sound/soc/samsung/odroid.c b/sound/soc/samsung/odroid.c index 694512f980fd..1dc54c4206f0 100644 --- a/sound/soc/samsung/odroid.c +++ b/sound/soc/samsung/odroid.c @@ -91,11 +91,11 @@ static int odroid_card_be_hw_params(struct snd_pcm_substream *substream, return ret; /* - * We add 1 to the rclk_freq value in order to avoid too low clock + * We add 2 to the rclk_freq value in order to avoid too low clock * frequency values due to the EPLL output frequency not being exact * multiple of the audio sampling rate. */ - rclk_freq = params_rate(params) * rfs + 1; + rclk_freq = params_rate(params) * rfs + 2; ret = clk_set_rate(priv->sclk_i2s, rclk_freq); if (ret < 0) diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c index 022996d2db13..4fe83e611c01 100644 --- a/sound/soc/sh/rcar/core.c +++ b/sound/soc/sh/rcar/core.c @@ -110,6 +110,8 @@ static const struct of_device_id rsnd_of_match[] = { { .compatible = "renesas,rcar_sound-gen1", .data = (void *)RSND_GEN1 }, { .compatible = "renesas,rcar_sound-gen2", .data = (void *)RSND_GEN2 }, { .compatible = "renesas,rcar_sound-gen3", .data = (void *)RSND_GEN3 }, + /* Special Handling */ + { .compatible = "renesas,rcar_sound-r8a77990", .data = (void *)(RSND_GEN3 | RSND_SOC_E) }, {}, }; MODULE_DEVICE_TABLE(of, rsnd_of_match); diff --git a/sound/soc/sh/rcar/rsnd.h b/sound/soc/sh/rcar/rsnd.h index 90625c57847b..0e6ef4e18400 100644 --- a/sound/soc/sh/rcar/rsnd.h +++ b/sound/soc/sh/rcar/rsnd.h @@ -607,6 +607,8 @@ struct rsnd_priv { #define RSND_GEN1 (1 << 0) #define RSND_GEN2 (2 << 0) #define RSND_GEN3 (3 << 0) +#define RSND_SOC_MASK (0xFF << 4) +#define RSND_SOC_E (1 << 4) /* E1/E2/E3 */ /* * below value will be filled on rsnd_gen_probe() @@ -679,6 +681,9 @@ struct rsnd_priv { #define rsnd_is_gen1(priv) (((priv)->flags & RSND_GEN_MASK) == RSND_GEN1) #define rsnd_is_gen2(priv) (((priv)->flags & RSND_GEN_MASK) == RSND_GEN2) #define rsnd_is_gen3(priv) (((priv)->flags & RSND_GEN_MASK) == RSND_GEN3) +#define rsnd_is_e3(priv) (((priv)->flags & \ + (RSND_GEN_MASK | RSND_SOC_MASK)) == \ + (RSND_GEN3 | RSND_SOC_E)) #define rsnd_flags_has(p, f) ((p)->flags & (f)) #define rsnd_flags_set(p, f) ((p)->flags |= (f)) diff --git a/sound/soc/sh/rcar/src.c b/sound/soc/sh/rcar/src.c index db81e066b92e..585ffba0244b 100644 --- a/sound/soc/sh/rcar/src.c +++ b/sound/soc/sh/rcar/src.c @@ -14,7 +14,6 @@ */ #include "rsnd.h" -#include <linux/sys_soc.h> #define SRC_NAME "src" @@ -135,7 +134,7 @@ unsigned int rsnd_src_get_rate(struct rsnd_priv *priv, return rate; } -const static u32 bsdsr_table_pattern1[] = { +static const u32 bsdsr_table_pattern1[] = { 0x01800000, /* 6 - 1/6 */ 0x01000000, /* 6 - 1/4 */ 0x00c00000, /* 6 - 1/3 */ @@ -144,7 +143,7 @@ const static u32 bsdsr_table_pattern1[] = { 0x00400000, /* 6 - 1 */ }; -const static u32 bsdsr_table_pattern2[] = { +static const u32 bsdsr_table_pattern2[] = { 0x02400000, /* 6 - 1/6 */ 0x01800000, /* 6 - 1/4 */ 0x01200000, /* 6 - 1/3 */ @@ -153,7 +152,7 @@ const static u32 bsdsr_table_pattern2[] = { 0x00600000, /* 6 - 1 */ }; -const static u32 bsisr_table[] = { +static const u32 bsisr_table[] = { 0x00100060, /* 6 - 1/6 */ 0x00100040, /* 6 - 1/4 */ 0x00100030, /* 6 - 1/3 */ @@ -162,7 +161,7 @@ const static u32 bsisr_table[] = { 0x00100020, /* 6 - 1 */ }; -const static u32 chan288888[] = { +static const u32 chan288888[] = { 0x00000006, /* 1 to 2 */ 0x000001fe, /* 1 to 8 */ 0x000001fe, /* 1 to 8 */ @@ -171,7 +170,7 @@ const static u32 chan288888[] = { 0x000001fe, /* 1 to 8 */ }; -const static u32 chan244888[] = { +static const u32 chan244888[] = { 0x00000006, /* 1 to 2 */ 0x0000001e, /* 1 to 4 */ 0x0000001e, /* 1 to 4 */ @@ -180,7 +179,7 @@ const static u32 chan244888[] = { 0x000001fe, /* 1 to 8 */ }; -const static u32 chan222222[] = { +static const u32 chan222222[] = { 0x00000006, /* 1 to 2 */ 0x00000006, /* 1 to 2 */ 0x00000006, /* 1 to 2 */ @@ -189,18 +188,12 @@ const static u32 chan222222[] = { 0x00000006, /* 1 to 2 */ }; -static const struct soc_device_attribute ov_soc[] = { - { .soc_id = "r8a77990" }, /* E3 */ - { /* sentinel */ } -}; - static void rsnd_src_set_convert_rate(struct rsnd_dai_stream *io, struct rsnd_mod *mod) { struct rsnd_priv *priv = rsnd_mod_to_priv(mod); struct device *dev = rsnd_priv_to_dev(priv); struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io); - const struct soc_device_attribute *soc = soc_device_match(ov_soc); int is_play = rsnd_io_is_play(io); int use_src = 0; u32 fin, fout; @@ -307,7 +300,7 @@ static void rsnd_src_set_convert_rate(struct rsnd_dai_stream *io, /* * E3 need to overwrite */ - if (soc) + if (rsnd_is_e3(priv)) switch (rsnd_mod_id(mod)) { case 0: case 4: diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 93d316d5bf8e..46e3ab0fced4 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -947,7 +947,7 @@ static void soc_cleanup_component(struct snd_soc_component *component) snd_soc_dapm_free(snd_soc_component_get_dapm(component)); soc_cleanup_component_debugfs(component); component->card = NULL; - if (!component->driver->ignore_module_refcount) + if (!component->driver->module_get_upon_open) module_put(component->dev->driver->owner); } @@ -1381,7 +1381,7 @@ static int soc_probe_component(struct snd_soc_card *card, return 0; } - if (!component->driver->ignore_module_refcount && + if (!component->driver->module_get_upon_open && !try_module_get(component->dev->driver->owner)) return -ENODEV; @@ -2797,6 +2797,7 @@ int snd_soc_register_card(struct snd_soc_card *card) ret = soc_init_dai_link(card, link); if (ret) { + soc_cleanup_platform(card); dev_err(card->dev, "ASoC: failed to init link %s\n", link->name); mutex_unlock(&client_mutex); @@ -2819,6 +2820,7 @@ int snd_soc_register_card(struct snd_soc_card *card) card->instantiated = 0; mutex_init(&card->mutex); mutex_init(&card->dapm_mutex); + spin_lock_init(&card->dpcm_lock); return snd_soc_bind_card(card); } diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 1ec06ef6d161..0382a47b30bd 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -3650,6 +3650,13 @@ snd_soc_dapm_new_control_unlocked(struct snd_soc_dapm_context *dapm, case snd_soc_dapm_dac: case snd_soc_dapm_aif_in: case snd_soc_dapm_pga: + case snd_soc_dapm_buffer: + case snd_soc_dapm_scheduler: + case snd_soc_dapm_effect: + case snd_soc_dapm_src: + case snd_soc_dapm_asrc: + case snd_soc_dapm_encoder: + case snd_soc_dapm_decoder: case snd_soc_dapm_out_drv: case snd_soc_dapm_micbias: case snd_soc_dapm_line: @@ -3957,6 +3964,10 @@ snd_soc_dapm_free_kcontrol(struct snd_soc_card *card, int count; devm_kfree(card->dev, (void *)*private_value); + + if (!w_param_text) + return; + for (count = 0 ; count < num_params; count++) devm_kfree(card->dev, (void *)w_param_text[count]); devm_kfree(card->dev, w_param_text); diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 0d5ec68a1e50..be80a12fba27 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -15,6 +15,7 @@ #include <linux/delay.h> #include <linux/pinctrl/consumer.h> #include <linux/pm_runtime.h> +#include <linux/module.h> #include <linux/slab.h> #include <linux/workqueue.h> #include <linux/export.h> @@ -463,6 +464,9 @@ static int soc_pcm_components_close(struct snd_pcm_substream *substream, continue; component->driver->ops->close(substream); + + if (component->driver->module_get_upon_open) + module_put(component->dev->driver->owner); } return 0; @@ -513,6 +517,12 @@ static int soc_pcm_open(struct snd_pcm_substream *substream) !component->driver->ops->open) continue; + if (component->driver->module_get_upon_open && + !try_module_get(component->dev->driver->owner)) { + ret = -ENODEV; + goto module_err; + } + ret = component->driver->ops->open(substream); if (ret < 0) { dev_err(component->dev, @@ -628,7 +638,7 @@ codec_dai_err: component_err: soc_pcm_components_close(substream, component); - +module_err: if (cpu_dai->driver->ops->shutdown) cpu_dai->driver->ops->shutdown(substream, cpu_dai); out: @@ -954,10 +964,13 @@ static int soc_pcm_hw_params(struct snd_pcm_substream *substream, codec_params = *params; /* fixup params based on TDM slot masks */ - if (codec_dai->tx_mask) + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK && + codec_dai->tx_mask) soc_pcm_codec_params_fixup(&codec_params, codec_dai->tx_mask); - if (codec_dai->rx_mask) + + if (substream->stream == SNDRV_PCM_STREAM_CAPTURE && + codec_dai->rx_mask) soc_pcm_codec_params_fixup(&codec_params, codec_dai->rx_mask); @@ -1213,6 +1226,7 @@ static int dpcm_be_connect(struct snd_soc_pcm_runtime *fe, struct snd_soc_pcm_runtime *be, int stream) { struct snd_soc_dpcm *dpcm; + unsigned long flags; /* only add new dpcms */ for_each_dpcm_be(fe, stream, dpcm) { @@ -1228,8 +1242,10 @@ static int dpcm_be_connect(struct snd_soc_pcm_runtime *fe, dpcm->fe = fe; be->dpcm[stream].runtime = fe->dpcm[stream].runtime; dpcm->state = SND_SOC_DPCM_LINK_STATE_NEW; + spin_lock_irqsave(&fe->card->dpcm_lock, flags); list_add(&dpcm->list_be, &fe->dpcm[stream].be_clients); list_add(&dpcm->list_fe, &be->dpcm[stream].fe_clients); + spin_unlock_irqrestore(&fe->card->dpcm_lock, flags); dev_dbg(fe->dev, "connected new DPCM %s path %s %s %s\n", stream ? "capture" : "playback", fe->dai_link->name, @@ -1275,6 +1291,7 @@ static void dpcm_be_reparent(struct snd_soc_pcm_runtime *fe, void dpcm_be_disconnect(struct snd_soc_pcm_runtime *fe, int stream) { struct snd_soc_dpcm *dpcm, *d; + unsigned long flags; for_each_dpcm_be_safe(fe, stream, dpcm, d) { dev_dbg(fe->dev, "ASoC: BE %s disconnect check for %s\n", @@ -1294,8 +1311,10 @@ void dpcm_be_disconnect(struct snd_soc_pcm_runtime *fe, int stream) #ifdef CONFIG_DEBUG_FS debugfs_remove(dpcm->debugfs_state); #endif + spin_lock_irqsave(&fe->card->dpcm_lock, flags); list_del(&dpcm->list_be); list_del(&dpcm->list_fe); + spin_unlock_irqrestore(&fe->card->dpcm_lock, flags); kfree(dpcm); } } @@ -1547,10 +1566,13 @@ int dpcm_process_paths(struct snd_soc_pcm_runtime *fe, void dpcm_clear_pending_state(struct snd_soc_pcm_runtime *fe, int stream) { struct snd_soc_dpcm *dpcm; + unsigned long flags; + spin_lock_irqsave(&fe->card->dpcm_lock, flags); for_each_dpcm_be(fe, stream, dpcm) dpcm->be->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO; + spin_unlock_irqrestore(&fe->card->dpcm_lock, flags); } static void dpcm_be_dai_startup_unwind(struct snd_soc_pcm_runtime *fe, @@ -1899,10 +1921,15 @@ static int dpcm_apply_symmetry(struct snd_pcm_substream *fe_substream, struct snd_soc_pcm_runtime *be = dpcm->be; struct snd_pcm_substream *be_substream = snd_soc_dpcm_get_substream(be, stream); - struct snd_soc_pcm_runtime *rtd = be_substream->private_data; + struct snd_soc_pcm_runtime *rtd; struct snd_soc_dai *codec_dai; int i; + /* A backend may not have the requested substream */ + if (!be_substream) + continue; + + rtd = be_substream->private_data; if (rtd->dai_link->be_hw_params_fixup) continue; @@ -2571,6 +2598,7 @@ static int dpcm_run_update_startup(struct snd_soc_pcm_runtime *fe, int stream) struct snd_soc_dpcm *dpcm; enum snd_soc_dpcm_trigger trigger = fe->dai_link->trigger[stream]; int ret; + unsigned long flags; dev_dbg(fe->dev, "ASoC: runtime %s open on FE %s\n", stream ? "capture" : "playback", fe->dai_link->name); @@ -2640,11 +2668,13 @@ close: dpcm_be_dai_shutdown(fe, stream); disconnect: /* disconnect any non started BEs */ + spin_lock_irqsave(&fe->card->dpcm_lock, flags); for_each_dpcm_be(fe, stream, dpcm) { struct snd_soc_pcm_runtime *be = dpcm->be; if (be->dpcm[stream].state != SND_SOC_DPCM_STATE_START) dpcm->state = SND_SOC_DPCM_LINK_STATE_FREE; } + spin_unlock_irqrestore(&fe->card->dpcm_lock, flags); return ret; } @@ -3221,7 +3251,10 @@ int snd_soc_dpcm_can_be_free_stop(struct snd_soc_pcm_runtime *fe, { struct snd_soc_dpcm *dpcm; int state; + int ret = 1; + unsigned long flags; + spin_lock_irqsave(&fe->card->dpcm_lock, flags); for_each_dpcm_fe(be, stream, dpcm) { if (dpcm->fe == fe) @@ -3230,12 +3263,15 @@ int snd_soc_dpcm_can_be_free_stop(struct snd_soc_pcm_runtime *fe, state = dpcm->fe->dpcm[stream].state; if (state == SND_SOC_DPCM_STATE_START || state == SND_SOC_DPCM_STATE_PAUSED || - state == SND_SOC_DPCM_STATE_SUSPEND) - return 0; + state == SND_SOC_DPCM_STATE_SUSPEND) { + ret = 0; + break; + } } + spin_unlock_irqrestore(&fe->card->dpcm_lock, flags); /* it's safe to free/stop this BE DAI */ - return 1; + return ret; } EXPORT_SYMBOL_GPL(snd_soc_dpcm_can_be_free_stop); @@ -3248,7 +3284,10 @@ int snd_soc_dpcm_can_be_params(struct snd_soc_pcm_runtime *fe, { struct snd_soc_dpcm *dpcm; int state; + int ret = 1; + unsigned long flags; + spin_lock_irqsave(&fe->card->dpcm_lock, flags); for_each_dpcm_fe(be, stream, dpcm) { if (dpcm->fe == fe) @@ -3258,12 +3297,15 @@ int snd_soc_dpcm_can_be_params(struct snd_soc_pcm_runtime *fe, if (state == SND_SOC_DPCM_STATE_START || state == SND_SOC_DPCM_STATE_PAUSED || state == SND_SOC_DPCM_STATE_SUSPEND || - state == SND_SOC_DPCM_STATE_PREPARE) - return 0; + state == SND_SOC_DPCM_STATE_PREPARE) { + ret = 0; + break; + } } + spin_unlock_irqrestore(&fe->card->dpcm_lock, flags); /* it's safe to change hw_params */ - return 1; + return ret; } EXPORT_SYMBOL_GPL(snd_soc_dpcm_can_be_params); @@ -3302,6 +3344,7 @@ static ssize_t dpcm_show_state(struct snd_soc_pcm_runtime *fe, struct snd_pcm_hw_params *params = &fe->dpcm[stream].hw_params; struct snd_soc_dpcm *dpcm; ssize_t offset = 0; + unsigned long flags; /* FE state */ offset += snprintf(buf + offset, size - offset, @@ -3329,6 +3372,7 @@ static ssize_t dpcm_show_state(struct snd_soc_pcm_runtime *fe, goto out; } + spin_lock_irqsave(&fe->card->dpcm_lock, flags); for_each_dpcm_be(fe, stream, dpcm) { struct snd_soc_pcm_runtime *be = dpcm->be; params = &dpcm->hw_params; @@ -3349,7 +3393,7 @@ static ssize_t dpcm_show_state(struct snd_soc_pcm_runtime *fe, params_channels(params), params_rate(params)); } - + spin_unlock_irqrestore(&fe->card->dpcm_lock, flags); out: return offset; } diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 25fca7055464..96852d250619 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -482,10 +482,11 @@ static void remove_widget(struct snd_soc_component *comp, snd_ctl_remove(card, kcontrol); - kfree(dobj->control.dvalues); + /* free enum kcontrol's dvalues and dtexts */ + kfree(se->dobj.control.dvalues); for (j = 0; j < se->items; j++) - kfree(dobj->control.dtexts[j]); - kfree(dobj->control.dtexts); + kfree(se->dobj.control.dtexts[j]); + kfree(se->dobj.control.dtexts); kfree(se); kfree(w->kcontrol_news[i].name); diff --git a/sound/soc/stm/stm32_adfsdm.c b/sound/soc/stm/stm32_adfsdm.c index 47901983a6ff..78bed9734713 100644 --- a/sound/soc/stm/stm32_adfsdm.c +++ b/sound/soc/stm/stm32_adfsdm.c @@ -9,6 +9,7 @@ #include <linux/clk.h> #include <linux/module.h> +#include <linux/mutex.h> #include <linux/platform_device.h> #include <linux/slab.h> @@ -37,6 +38,8 @@ struct stm32_adfsdm_priv { /* PCM buffer */ unsigned char *pcm_buff; unsigned int pos; + + struct mutex lock; /* protect against race condition on iio state */ }; static const struct snd_pcm_hardware stm32_adfsdm_pcm_hw = { @@ -62,10 +65,12 @@ static void stm32_adfsdm_shutdown(struct snd_pcm_substream *substream, { struct stm32_adfsdm_priv *priv = snd_soc_dai_get_drvdata(dai); + mutex_lock(&priv->lock); if (priv->iio_active) { iio_channel_stop_all_cb(priv->iio_cb); priv->iio_active = false; } + mutex_unlock(&priv->lock); } static int stm32_adfsdm_dai_prepare(struct snd_pcm_substream *substream, @@ -74,13 +79,19 @@ static int stm32_adfsdm_dai_prepare(struct snd_pcm_substream *substream, struct stm32_adfsdm_priv *priv = snd_soc_dai_get_drvdata(dai); int ret; + mutex_lock(&priv->lock); + if (priv->iio_active) { + iio_channel_stop_all_cb(priv->iio_cb); + priv->iio_active = false; + } + ret = iio_write_channel_attribute(priv->iio_ch, substream->runtime->rate, 0, IIO_CHAN_INFO_SAMP_FREQ); if (ret < 0) { dev_err(dai->dev, "%s: Failed to set %d sampling rate\n", __func__, substream->runtime->rate); - return ret; + goto out; } if (!priv->iio_active) { @@ -92,6 +103,9 @@ static int stm32_adfsdm_dai_prepare(struct snd_pcm_substream *substream, __func__, ret); } +out: + mutex_unlock(&priv->lock); + return ret; } @@ -291,6 +305,7 @@ MODULE_DEVICE_TABLE(of, stm32_adfsdm_of_match); static int stm32_adfsdm_probe(struct platform_device *pdev) { struct stm32_adfsdm_priv *priv; + struct snd_soc_component *component; int ret; priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); @@ -299,6 +314,7 @@ static int stm32_adfsdm_probe(struct platform_device *pdev) priv->dev = &pdev->dev; priv->dai_drv = stm32_adfsdm_dai; + mutex_init(&priv->lock); dev_set_drvdata(&pdev->dev, priv); @@ -317,9 +333,15 @@ static int stm32_adfsdm_probe(struct platform_device *pdev) if (IS_ERR(priv->iio_cb)) return PTR_ERR(priv->iio_cb); - ret = devm_snd_soc_register_component(&pdev->dev, - &stm32_adfsdm_soc_platform, - NULL, 0); + component = devm_kzalloc(&pdev->dev, sizeof(*component), GFP_KERNEL); + if (!component) + return -ENOMEM; +#ifdef CONFIG_DEBUG_FS + component->debugfs_prefix = "pcm"; +#endif + + ret = snd_soc_add_component(&pdev->dev, component, + &stm32_adfsdm_soc_platform, NULL, 0); if (ret < 0) dev_err(&pdev->dev, "%s: Failed to register PCM platform\n", __func__); @@ -327,12 +349,20 @@ static int stm32_adfsdm_probe(struct platform_device *pdev) return ret; } +static int stm32_adfsdm_remove(struct platform_device *pdev) +{ + snd_soc_unregister_component(&pdev->dev); + + return 0; +} + static struct platform_driver stm32_adfsdm_driver = { .driver = { .name = STM32_ADFSDM_DRV_NAME, .of_match_table = stm32_adfsdm_of_match, }, .probe = stm32_adfsdm_probe, + .remove = stm32_adfsdm_remove, }; module_platform_driver(stm32_adfsdm_driver); diff --git a/sound/soc/stm/stm32_i2s.c b/sound/soc/stm/stm32_i2s.c index 47c334de6b09..8968458eec62 100644 --- a/sound/soc/stm/stm32_i2s.c +++ b/sound/soc/stm/stm32_i2s.c @@ -281,7 +281,6 @@ static bool stm32_i2s_readable_reg(struct device *dev, unsigned int reg) case STM32_I2S_CFG2_REG: case STM32_I2S_IER_REG: case STM32_I2S_SR_REG: - case STM32_I2S_TXDR_REG: case STM32_I2S_RXDR_REG: case STM32_I2S_CGFR_REG: return true; @@ -293,7 +292,7 @@ static bool stm32_i2s_readable_reg(struct device *dev, unsigned int reg) static bool stm32_i2s_volatile_reg(struct device *dev, unsigned int reg) { switch (reg) { - case STM32_I2S_TXDR_REG: + case STM32_I2S_SR_REG: case STM32_I2S_RXDR_REG: return true; default: diff --git a/sound/soc/stm/stm32_sai.c b/sound/soc/stm/stm32_sai.c index 14c9591aae42..d68d62f12df5 100644 --- a/sound/soc/stm/stm32_sai.c +++ b/sound/soc/stm/stm32_sai.c @@ -105,6 +105,7 @@ static int stm32_sai_set_sync(struct stm32_sai_data *sai_client, if (!pdev) { dev_err(&sai_client->pdev->dev, "Device not found for node %pOFn\n", np_provider); + of_node_put(np_provider); return -ENODEV; } @@ -113,19 +114,20 @@ static int stm32_sai_set_sync(struct stm32_sai_data *sai_client, dev_err(&sai_client->pdev->dev, "SAI sync provider data not found\n"); ret = -EINVAL; - goto out_put_dev; + goto error; } /* Configure sync client */ ret = stm32_sai_sync_conf_client(sai_client, synci); if (ret < 0) - goto out_put_dev; + goto error; /* Configure sync provider */ ret = stm32_sai_sync_conf_provider(sai_provider, synco); -out_put_dev: +error: put_device(&pdev->dev); + of_node_put(np_provider); return ret; } diff --git a/sound/soc/stm/stm32_sai_sub.c b/sound/soc/stm/stm32_sai_sub.c index f9297228c41c..d7045aa520de 100644 --- a/sound/soc/stm/stm32_sai_sub.c +++ b/sound/soc/stm/stm32_sai_sub.c @@ -70,6 +70,7 @@ #define SAI_IEC60958_STATUS_BYTES 24 #define SAI_MCLK_NAME_LEN 32 +#define SAI_RATE_11K 11025 /** * struct stm32_sai_sub_data - private data of SAI sub block (block A or B) @@ -100,8 +101,9 @@ * @slot_mask: rx or tx active slots mask. set at init or at runtime * @data_size: PCM data width. corresponds to PCM substream width. * @spdif_frm_cnt: S/PDIF playback frame counter - * @snd_aes_iec958: iec958 data + * @iec958: iec958 data * @ctrl_lock: control lock + * @irq_lock: prevent race condition with IRQ */ struct stm32_sai_sub_data { struct platform_device *pdev; @@ -133,6 +135,7 @@ struct stm32_sai_sub_data { unsigned int spdif_frm_cnt; struct snd_aes_iec958 iec958; struct mutex ctrl_lock; /* protect resources accessed by controls */ + spinlock_t irq_lock; /* used to prevent race condition with IRQ */ }; enum stm32_sai_fifo_th { @@ -307,6 +310,25 @@ static int stm32_sai_set_clk_div(struct stm32_sai_sub_data *sai, return ret; } +static int stm32_sai_set_parent_clock(struct stm32_sai_sub_data *sai, + unsigned int rate) +{ + struct platform_device *pdev = sai->pdev; + struct clk *parent_clk = sai->pdata->clk_x8k; + int ret; + + if (!(rate % SAI_RATE_11K)) + parent_clk = sai->pdata->clk_x11k; + + ret = clk_set_parent(sai->sai_ck, parent_clk); + if (ret) + dev_err(&pdev->dev, " Error %d setting sai_ck parent clock. %s", + ret, ret == -EBUSY ? + "Active stream rates conflict\n" : "\n"); + + return ret; +} + static long stm32_sai_mclk_round_rate(struct clk_hw *hw, unsigned long rate, unsigned long *prate) { @@ -474,8 +496,10 @@ static irqreturn_t stm32_sai_isr(int irq, void *devid) status = SNDRV_PCM_STATE_XRUN; } - if (status != SNDRV_PCM_STATE_RUNNING) + spin_lock(&sai->irq_lock); + if (status != SNDRV_PCM_STATE_RUNNING && sai->substream) snd_pcm_stop_xrun(sai->substream); + spin_unlock(&sai->irq_lock); return IRQ_HANDLED; } @@ -486,25 +510,29 @@ static int stm32_sai_set_sysclk(struct snd_soc_dai *cpu_dai, struct stm32_sai_sub_data *sai = snd_soc_dai_get_drvdata(cpu_dai); int ret; - if (dir == SND_SOC_CLOCK_OUT) { + if (dir == SND_SOC_CLOCK_OUT && sai->sai_mclk) { ret = regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX, SAI_XCR1_NODIV, (unsigned int)~SAI_XCR1_NODIV); if (ret < 0) return ret; - dev_dbg(cpu_dai->dev, "SAI MCLK frequency is %uHz\n", freq); - sai->mclk_rate = freq; + /* If master clock is used, set parent clock now */ + ret = stm32_sai_set_parent_clock(sai, freq); + if (ret) + return ret; - if (sai->sai_mclk) { - ret = clk_set_rate_exclusive(sai->sai_mclk, - sai->mclk_rate); - if (ret) { - dev_err(cpu_dai->dev, - "Could not set mclk rate\n"); - return ret; - } + ret = clk_set_rate_exclusive(sai->sai_mclk, freq); + if (ret) { + dev_err(cpu_dai->dev, + ret == -EBUSY ? + "Active streams have incompatible rates" : + "Could not set mclk rate\n"); + return ret; } + + dev_dbg(cpu_dai->dev, "SAI MCLK frequency is %uHz\n", freq); + sai->mclk_rate = freq; } return 0; @@ -679,8 +707,19 @@ static int stm32_sai_startup(struct snd_pcm_substream *substream, { struct stm32_sai_sub_data *sai = snd_soc_dai_get_drvdata(cpu_dai); int imr, cr2, ret; + unsigned long flags; + spin_lock_irqsave(&sai->irq_lock, flags); sai->substream = substream; + spin_unlock_irqrestore(&sai->irq_lock, flags); + + if (STM_SAI_PROTOCOL_IS_SPDIF(sai)) { + snd_pcm_hw_constraint_mask64(substream->runtime, + SNDRV_PCM_HW_PARAM_FORMAT, + SNDRV_PCM_FMTBIT_S32_LE); + snd_pcm_hw_constraint_single(substream->runtime, + SNDRV_PCM_HW_PARAM_CHANNELS, 2); + } ret = clk_prepare_enable(sai->sai_ck); if (ret < 0) { @@ -898,14 +937,16 @@ static int stm32_sai_configure_clock(struct snd_soc_dai *cpu_dai, struct snd_pcm_hw_params *params) { struct stm32_sai_sub_data *sai = snd_soc_dai_get_drvdata(cpu_dai); - int div = 0; + int div = 0, cr1 = 0; int sai_clk_rate, mclk_ratio, den; unsigned int rate = params_rate(params); + int ret; - if (!(rate % 11025)) - clk_set_parent(sai->sai_ck, sai->pdata->clk_x11k); - else - clk_set_parent(sai->sai_ck, sai->pdata->clk_x8k); + if (!sai->sai_mclk) { + ret = stm32_sai_set_parent_clock(sai, rate); + if (ret) + return ret; + } sai_clk_rate = clk_get_rate(sai->sai_ck); if (STM_SAI_IS_F4(sai->pdata)) { @@ -943,13 +984,19 @@ static int stm32_sai_configure_clock(struct snd_soc_dai *cpu_dai, } else { if (sai->mclk_rate) { mclk_ratio = sai->mclk_rate / rate; - if ((mclk_ratio != 512) && - (mclk_ratio != 256)) { + if (mclk_ratio == 512) { + cr1 = SAI_XCR1_OSR; + } else if (mclk_ratio != 256) { dev_err(cpu_dai->dev, "Wrong mclk ratio %d\n", mclk_ratio); return -EINVAL; } + + regmap_update_bits(sai->regmap, + STM_SAI_CR1_REGX, + SAI_XCR1_OSR, cr1); + div = stm32_sai_get_clk_div(sai, sai_clk_rate, sai->mclk_rate); if (div < 0) @@ -1051,28 +1098,36 @@ static void stm32_sai_shutdown(struct snd_pcm_substream *substream, struct snd_soc_dai *cpu_dai) { struct stm32_sai_sub_data *sai = snd_soc_dai_get_drvdata(cpu_dai); + unsigned long flags; regmap_update_bits(sai->regmap, STM_SAI_IMR_REGX, SAI_XIMR_MASK, 0); regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX, SAI_XCR1_NODIV, SAI_XCR1_NODIV); - clk_disable_unprepare(sai->sai_ck); + /* Release mclk rate only if rate was actually set */ + if (sai->mclk_rate) { + clk_rate_exclusive_put(sai->sai_mclk); + sai->mclk_rate = 0; + } - clk_rate_exclusive_put(sai->sai_mclk); + clk_disable_unprepare(sai->sai_ck); + spin_lock_irqsave(&sai->irq_lock, flags); sai->substream = NULL; + spin_unlock_irqrestore(&sai->irq_lock, flags); } static int stm32_sai_pcm_new(struct snd_soc_pcm_runtime *rtd, struct snd_soc_dai *cpu_dai) { struct stm32_sai_sub_data *sai = dev_get_drvdata(cpu_dai->dev); + struct snd_kcontrol_new knew = iec958_ctls; if (STM_SAI_PROTOCOL_IS_SPDIF(sai)) { dev_dbg(&sai->pdev->dev, "%s: register iec controls", __func__); - return snd_ctl_add(rtd->pcm->card, - snd_ctl_new1(&iec958_ctls, sai)); + knew.device = rtd->pcm->device; + return snd_ctl_add(rtd->pcm->card, snd_ctl_new1(&knew, sai)); } return 0; @@ -1081,7 +1136,7 @@ static int stm32_sai_pcm_new(struct snd_soc_pcm_runtime *rtd, static int stm32_sai_dai_probe(struct snd_soc_dai *cpu_dai) { struct stm32_sai_sub_data *sai = dev_get_drvdata(cpu_dai->dev); - int cr1 = 0, cr1_mask; + int cr1 = 0, cr1_mask, ret; sai->cpu_dai = cpu_dai; @@ -1111,8 +1166,10 @@ static int stm32_sai_dai_probe(struct snd_soc_dai *cpu_dai) /* Configure synchronization */ if (sai->sync == SAI_SYNC_EXTERNAL) { /* Configure synchro client and provider */ - sai->pdata->set_sync(sai->pdata, sai->np_sync_provider, - sai->synco, sai->synci); + ret = sai->pdata->set_sync(sai->pdata, sai->np_sync_provider, + sai->synco, sai->synci); + if (ret) + return ret; } cr1_mask |= SAI_XCR1_SYNCEN_MASK; @@ -1392,7 +1449,6 @@ static int stm32_sai_sub_dais_init(struct platform_device *pdev, if (!sai->cpu_dai_drv) return -ENOMEM; - sai->cpu_dai_drv->name = dev_name(&pdev->dev); if (STM_SAI_IS_PLAYBACK(sai)) { memcpy(sai->cpu_dai_drv, &stm32_sai_playback_dai, sizeof(stm32_sai_playback_dai)); @@ -1402,6 +1458,7 @@ static int stm32_sai_sub_dais_init(struct platform_device *pdev, sizeof(stm32_sai_capture_dai)); sai->cpu_dai_drv->capture.stream_name = sai->cpu_dai_drv->name; } + sai->cpu_dai_drv->name = dev_name(&pdev->dev); return 0; } @@ -1424,6 +1481,7 @@ static int stm32_sai_sub_probe(struct platform_device *pdev) sai->pdev = pdev; mutex_init(&sai->ctrl_lock); + spin_lock_init(&sai->irq_lock); platform_set_drvdata(pdev, sai); sai->pdata = dev_get_drvdata(pdev->dev.parent); diff --git a/sound/usb/line6/driver.c b/sound/usb/line6/driver.c index 7afe8fae4939..b61f65bed4e4 100644 --- a/sound/usb/line6/driver.c +++ b/sound/usb/line6/driver.c @@ -351,12 +351,16 @@ int line6_read_data(struct usb_line6 *line6, unsigned address, void *data, { struct usb_device *usbdev = line6->usbdev; int ret; - unsigned char len; + unsigned char *len; unsigned count; if (address > 0xffff || datalen > 0xff) return -EINVAL; + len = kmalloc(sizeof(*len), GFP_KERNEL); + if (!len) + return -ENOMEM; + /* query the serial number: */ ret = usb_control_msg(usbdev, usb_sndctrlpipe(usbdev, 0), 0x67, USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_OUT, @@ -365,7 +369,7 @@ int line6_read_data(struct usb_line6 *line6, unsigned address, void *data, if (ret < 0) { dev_err(line6->ifcdev, "read request failed (error %d)\n", ret); - return ret; + goto exit; } /* Wait for data length. We'll get 0xff until length arrives. */ @@ -375,28 +379,29 @@ int line6_read_data(struct usb_line6 *line6, unsigned address, void *data, ret = usb_control_msg(usbdev, usb_rcvctrlpipe(usbdev, 0), 0x67, USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_IN, - 0x0012, 0x0000, &len, 1, + 0x0012, 0x0000, len, 1, LINE6_TIMEOUT * HZ); if (ret < 0) { dev_err(line6->ifcdev, "receive length failed (error %d)\n", ret); - return ret; + goto exit; } - if (len != 0xff) + if (*len != 0xff) break; } - if (len == 0xff) { + ret = -EIO; + if (*len == 0xff) { dev_err(line6->ifcdev, "read failed after %d retries\n", count); - return -EIO; - } else if (len != datalen) { + goto exit; + } else if (*len != datalen) { /* should be equal or something went wrong */ dev_err(line6->ifcdev, "length mismatch (expected %d, got %d)\n", - (int)datalen, (int)len); - return -EIO; + (int)datalen, (int)*len); + goto exit; } /* receive the result: */ @@ -405,12 +410,12 @@ int line6_read_data(struct usb_line6 *line6, unsigned address, void *data, 0x0013, 0x0000, data, datalen, LINE6_TIMEOUT * HZ); - if (ret < 0) { + if (ret < 0) dev_err(line6->ifcdev, "read failed (error %d)\n", ret); - return ret; - } - return 0; +exit: + kfree(len); + return ret; } EXPORT_SYMBOL_GPL(line6_read_data); @@ -422,12 +427,16 @@ int line6_write_data(struct usb_line6 *line6, unsigned address, void *data, { struct usb_device *usbdev = line6->usbdev; int ret; - unsigned char status; + unsigned char *status; int count; if (address > 0xffff || datalen > 0xffff) return -EINVAL; + status = kmalloc(sizeof(*status), GFP_KERNEL); + if (!status) + return -ENOMEM; + ret = usb_control_msg(usbdev, usb_sndctrlpipe(usbdev, 0), 0x67, USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_OUT, 0x0022, address, data, datalen, @@ -436,7 +445,7 @@ int line6_write_data(struct usb_line6 *line6, unsigned address, void *data, if (ret < 0) { dev_err(line6->ifcdev, "write request failed (error %d)\n", ret); - return ret; + goto exit; } for (count = 0; count < LINE6_READ_WRITE_MAX_RETRIES; count++) { @@ -447,28 +456,29 @@ int line6_write_data(struct usb_line6 *line6, unsigned address, void *data, USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_IN, 0x0012, 0x0000, - &status, 1, LINE6_TIMEOUT * HZ); + status, 1, LINE6_TIMEOUT * HZ); if (ret < 0) { dev_err(line6->ifcdev, "receiving status failed (error %d)\n", ret); - return ret; + goto exit; } - if (status != 0xff) + if (*status != 0xff) break; } - if (status == 0xff) { + if (*status == 0xff) { dev_err(line6->ifcdev, "write failed after %d retries\n", count); - return -EIO; - } else if (status != 0) { + ret = -EIO; + } else if (*status != 0) { dev_err(line6->ifcdev, "write failed (error %d)\n", ret); - return -EIO; + ret = -EIO; } - - return 0; +exit: + kfree(status); + return ret; } EXPORT_SYMBOL_GPL(line6_write_data); diff --git a/sound/usb/line6/podhd.c b/sound/usb/line6/podhd.c index 36ed9c85c0eb..5f3c87264e66 100644 --- a/sound/usb/line6/podhd.c +++ b/sound/usb/line6/podhd.c @@ -225,28 +225,32 @@ static void podhd_startup_start_workqueue(struct timer_list *t) static int podhd_dev_start(struct usb_line6_podhd *pod) { int ret; - u8 init_bytes[8]; + u8 *init_bytes; int i; struct usb_device *usbdev = pod->line6.usbdev; + init_bytes = kmalloc(8, GFP_KERNEL); + if (!init_bytes) + return -ENOMEM; + ret = usb_control_msg(usbdev, usb_sndctrlpipe(usbdev, 0), 0x67, USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_OUT, 0x11, 0, NULL, 0, LINE6_TIMEOUT * HZ); if (ret < 0) { dev_err(pod->line6.ifcdev, "read request failed (error %d)\n", ret); - return ret; + goto exit; } /* NOTE: looks like some kind of ping message */ ret = usb_control_msg(usbdev, usb_rcvctrlpipe(usbdev, 0), 0x67, USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_IN, 0x11, 0x0, - &init_bytes, 3, LINE6_TIMEOUT * HZ); + init_bytes, 3, LINE6_TIMEOUT * HZ); if (ret < 0) { dev_err(pod->line6.ifcdev, "receive length failed (error %d)\n", ret); - return ret; + goto exit; } pod->firmware_version = @@ -255,7 +259,7 @@ static int podhd_dev_start(struct usb_line6_podhd *pod) for (i = 0; i <= 16; i++) { ret = line6_read_data(&pod->line6, 0xf000 + 0x08 * i, init_bytes, 8); if (ret < 0) - return ret; + goto exit; } ret = usb_control_msg(usbdev, usb_sndctrlpipe(usbdev, 0), @@ -263,10 +267,9 @@ static int podhd_dev_start(struct usb_line6_podhd *pod) USB_TYPE_STANDARD | USB_RECIP_DEVICE | USB_DIR_OUT, 1, 0, NULL, 0, LINE6_TIMEOUT * HZ); - if (ret < 0) - return ret; - - return 0; +exit: + kfree(init_bytes); + return ret; } static void podhd_startup_workqueue(struct work_struct *work) diff --git a/sound/usb/line6/toneport.c b/sound/usb/line6/toneport.c index f47ba94e6f4a..19bee725de00 100644 --- a/sound/usb/line6/toneport.c +++ b/sound/usb/line6/toneport.c @@ -365,16 +365,21 @@ static bool toneport_has_source_select(struct usb_line6_toneport *toneport) /* Setup Toneport device. */ -static void toneport_setup(struct usb_line6_toneport *toneport) +static int toneport_setup(struct usb_line6_toneport *toneport) { - u32 ticks; + u32 *ticks; struct usb_line6 *line6 = &toneport->line6; struct usb_device *usbdev = line6->usbdev; + ticks = kmalloc(sizeof(*ticks), GFP_KERNEL); + if (!ticks) + return -ENOMEM; + /* sync time on device with host: */ /* note: 32-bit timestamps overflow in year 2106 */ - ticks = (u32)ktime_get_real_seconds(); - line6_write_data(line6, 0x80c6, &ticks, 4); + *ticks = (u32)ktime_get_real_seconds(); + line6_write_data(line6, 0x80c6, ticks, 4); + kfree(ticks); /* enable device: */ toneport_send_cmd(usbdev, 0x0301, 0x0000); @@ -389,6 +394,7 @@ static void toneport_setup(struct usb_line6_toneport *toneport) toneport_update_led(toneport); mod_timer(&toneport->timer, jiffies + TONEPORT_PCM_DELAY * HZ); + return 0; } /* @@ -451,7 +457,9 @@ static int toneport_init(struct usb_line6 *line6, return err; } - toneport_setup(toneport); + err = toneport_setup(toneport); + if (err) + return err; /* register audio system: */ return snd_card_register(line6->card); @@ -463,7 +471,11 @@ static int toneport_init(struct usb_line6 *line6, */ static int toneport_reset_resume(struct usb_interface *interface) { - toneport_setup(usb_get_intfdata(interface)); + int err; + + err = toneport_setup(usb_get_intfdata(interface)); + if (err) + return err; return line6_resume(interface); } #endif diff --git a/sound/xen/xen_snd_front_alsa.c b/sound/xen/xen_snd_front_alsa.c index a7f413cb704d..b14ab512c2ce 100644 --- a/sound/xen/xen_snd_front_alsa.c +++ b/sound/xen/xen_snd_front_alsa.c @@ -441,7 +441,7 @@ static int shbuf_setup_backstore(struct xen_snd_front_pcm_stream_info *stream, { int i; - stream->buffer = alloc_pages_exact(stream->buffer_sz, GFP_KERNEL); + stream->buffer = alloc_pages_exact(buffer_sz, GFP_KERNEL); if (!stream->buffer) return -ENOMEM; diff --git a/tools/arch/alpha/include/uapi/asm/mman.h b/tools/arch/alpha/include/uapi/asm/mman.h index c317d3e6867a..ea6a255ae61f 100644 --- a/tools/arch/alpha/include/uapi/asm/mman.h +++ b/tools/arch/alpha/include/uapi/asm/mman.h @@ -27,8 +27,6 @@ #define MAP_NONBLOCK 0x40000 #define MAP_NORESERVE 0x10000 #define MAP_POPULATE 0x20000 -#define MAP_PRIVATE 0x02 -#define MAP_SHARED 0x01 #define MAP_STACK 0x80000 #define PROT_EXEC 0x4 #define PROT_GROWSDOWN 0x01000000 diff --git a/tools/arch/mips/include/uapi/asm/mman.h b/tools/arch/mips/include/uapi/asm/mman.h index de2206883abc..c8acaa138d46 100644 --- a/tools/arch/mips/include/uapi/asm/mman.h +++ b/tools/arch/mips/include/uapi/asm/mman.h @@ -28,8 +28,6 @@ #define MAP_NONBLOCK 0x20000 #define MAP_NORESERVE 0x0400 #define MAP_POPULATE 0x10000 -#define MAP_PRIVATE 0x002 -#define MAP_SHARED 0x001 #define MAP_STACK 0x40000 #define PROT_EXEC 0x04 #define PROT_GROWSDOWN 0x01000000 diff --git a/tools/arch/parisc/include/uapi/asm/mman.h b/tools/arch/parisc/include/uapi/asm/mman.h index 1bd78758bde9..f9fd1325f5bd 100644 --- a/tools/arch/parisc/include/uapi/asm/mman.h +++ b/tools/arch/parisc/include/uapi/asm/mman.h @@ -27,8 +27,6 @@ #define MAP_NONBLOCK 0x20000 #define MAP_NORESERVE 0x4000 #define MAP_POPULATE 0x10000 -#define MAP_PRIVATE 0x02 -#define MAP_SHARED 0x01 #define MAP_STACK 0x40000 #define PROT_EXEC 0x4 #define PROT_GROWSDOWN 0x01000000 diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h index 8c876c166ef2..26ca425f4c2c 100644 --- a/tools/arch/powerpc/include/uapi/asm/kvm.h +++ b/tools/arch/powerpc/include/uapi/asm/kvm.h @@ -463,10 +463,12 @@ struct kvm_ppc_cpu_char { #define KVM_PPC_CPU_CHAR_BR_HINT_HONOURED (1ULL << 58) #define KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF (1ULL << 57) #define KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS (1ULL << 56) +#define KVM_PPC_CPU_CHAR_BCCTR_FLUSH_ASSIST (1ull << 54) #define KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY (1ULL << 63) #define KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR (1ULL << 62) #define KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR (1ULL << 61) +#define KVM_PPC_CPU_BEHAV_FLUSH_COUNT_CACHE (1ull << 58) /* Per-vcpu XICS interrupt controller state */ #define KVM_REG_PPC_ICP_STATE (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c) diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 6d6122524711..981ff9479648 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -344,6 +344,7 @@ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ #define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ #define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ #define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ diff --git a/tools/arch/xtensa/include/uapi/asm/mman.h b/tools/arch/xtensa/include/uapi/asm/mman.h index 34dde6f44dae..f2b08c990afc 100644 --- a/tools/arch/xtensa/include/uapi/asm/mman.h +++ b/tools/arch/xtensa/include/uapi/asm/mman.h @@ -27,8 +27,6 @@ #define MAP_NONBLOCK 0x20000 #define MAP_NORESERVE 0x0400 #define MAP_POPULATE 0x10000 -#define MAP_PRIVATE 0x002 -#define MAP_SHARED 0x001 #define MAP_STACK 0x40000 #define PROT_EXEC 0x4 #define PROT_GROWSDOWN 0x01000000 diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index e0c650d91784..994a7e0d16fb 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -1151,6 +1151,9 @@ static int do_create(int argc, char **argv) return -1; } NEXT_ARG(); + } else { + p_err("unknown arg %s", *argv); + return -1; } } diff --git a/tools/build/feature/test-libopencsd.c b/tools/build/feature/test-libopencsd.c index d68eb4fb40cc..2b0e02c38870 100644 --- a/tools/build/feature/test-libopencsd.c +++ b/tools/build/feature/test-libopencsd.c @@ -4,9 +4,9 @@ /* * Check OpenCSD library version is sufficient to provide required features */ -#define OCSD_MIN_VER ((0 << 16) | (10 << 8) | (0)) +#define OCSD_MIN_VER ((0 << 16) | (11 << 8) | (0)) #if !defined(OCSD_VER_NUM) || (OCSD_VER_NUM < OCSD_MIN_VER) -#error "OpenCSD >= 0.10.0 is required" +#error "OpenCSD >= 0.11.0 is required" #endif int main(void) diff --git a/tools/include/uapi/asm-generic/mman-common-tools.h b/tools/include/uapi/asm-generic/mman-common-tools.h new file mode 100644 index 000000000000..af7d0d3a3182 --- /dev/null +++ b/tools/include/uapi/asm-generic/mman-common-tools.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H +#define __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H + +#include <asm-generic/mman-common.h> + +/* We need this because we need to have tools/include/uapi/ included in the tools + * header search path to get access to stuff that is not yet in the system's + * copy of the files in that directory, but since this cset: + * + * 746c9398f5ac ("arch: move common mmap flags to linux/mman.h") + * + * We end up making sys/mman.h, that is in the system headers, to not find the + * MAP_SHARED and MAP_PRIVATE defines because they are not anymore in our copy + * of asm-generic/mman-common.h. So we define them here and include this header + * from each of the per arch mman.h headers. + */ +#ifndef MAP_SHARED +#define MAP_SHARED 0x01 /* Share changes */ +#define MAP_PRIVATE 0x02 /* Changes are private */ +#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */ +#endif +#endif // __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h index e7ee32861d51..abd238d0f7a4 100644 --- a/tools/include/uapi/asm-generic/mman-common.h +++ b/tools/include/uapi/asm-generic/mman-common.h @@ -15,9 +15,7 @@ #define PROT_GROWSDOWN 0x01000000 /* mprotect flag: extend change to start of growsdown vma */ #define PROT_GROWSUP 0x02000000 /* mprotect flag: extend change to end of growsup vma */ -#define MAP_SHARED 0x01 /* Share changes */ -#define MAP_PRIVATE 0x02 /* Changes are private */ -#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */ +/* 0x01 - 0x03 are defined in linux/mman.h */ #define MAP_TYPE 0x0f /* Mask for type of mapping */ #define MAP_FIXED 0x10 /* Interpret addr exactly */ #define MAP_ANONYMOUS 0x20 /* don't use a file */ diff --git a/tools/include/uapi/asm-generic/mman.h b/tools/include/uapi/asm-generic/mman.h index 653687d9771b..36c197fc44a0 100644 --- a/tools/include/uapi/asm-generic/mman.h +++ b/tools/include/uapi/asm-generic/mman.h @@ -2,7 +2,7 @@ #ifndef __ASM_GENERIC_MMAN_H #define __ASM_GENERIC_MMAN_H -#include <asm-generic/mman-common.h> +#include <asm-generic/mman-common-tools.h> #define MAP_GROWSDOWN 0x0100 /* stack-like segment */ #define MAP_DENYWRITE 0x0800 /* ETXTBSY */ diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index 12cdf611d217..dee7292e1df6 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -824,8 +824,17 @@ __SYSCALL(__NR_futex_time64, sys_futex) __SYSCALL(__NR_sched_rr_get_interval_time64, sys_sched_rr_get_interval) #endif +#define __NR_pidfd_send_signal 424 +__SYSCALL(__NR_pidfd_send_signal, sys_pidfd_send_signal) +#define __NR_io_uring_setup 425 +__SYSCALL(__NR_io_uring_setup, sys_io_uring_setup) +#define __NR_io_uring_enter 426 +__SYSCALL(__NR_io_uring_enter, sys_io_uring_enter) +#define __NR_io_uring_register 427 +__SYSCALL(__NR_io_uring_register, sys_io_uring_register) + #undef __NR_syscalls -#define __NR_syscalls 424 +#define __NR_syscalls 428 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 298b2e197744..397810fa2d33 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -1486,9 +1486,73 @@ struct drm_i915_gem_context_param { #define I915_CONTEXT_MAX_USER_PRIORITY 1023 /* inclusive */ #define I915_CONTEXT_DEFAULT_PRIORITY 0 #define I915_CONTEXT_MIN_USER_PRIORITY -1023 /* inclusive */ + /* + * When using the following param, value should be a pointer to + * drm_i915_gem_context_param_sseu. + */ +#define I915_CONTEXT_PARAM_SSEU 0x7 __u64 value; }; +/** + * Context SSEU programming + * + * It may be necessary for either functional or performance reason to configure + * a context to run with a reduced number of SSEU (where SSEU stands for Slice/ + * Sub-slice/EU). + * + * This is done by configuring SSEU configuration using the below + * @struct drm_i915_gem_context_param_sseu for every supported engine which + * userspace intends to use. + * + * Not all GPUs or engines support this functionality in which case an error + * code -ENODEV will be returned. + * + * Also, flexibility of possible SSEU configuration permutations varies between + * GPU generations and software imposed limitations. Requesting such a + * combination will return an error code of -EINVAL. + * + * NOTE: When perf/OA is active the context's SSEU configuration is ignored in + * favour of a single global setting. + */ +struct drm_i915_gem_context_param_sseu { + /* + * Engine class & instance to be configured or queried. + */ + __u16 engine_class; + __u16 engine_instance; + + /* + * Unused for now. Must be cleared to zero. + */ + __u32 flags; + + /* + * Mask of slices to enable for the context. Valid values are a subset + * of the bitmask value returned for I915_PARAM_SLICE_MASK. + */ + __u64 slice_mask; + + /* + * Mask of subslices to enable for the context. Valid values are a + * subset of the bitmask value return by I915_PARAM_SUBSLICE_MASK. + */ + __u64 subslice_mask; + + /* + * Minimum/Maximum number of EUs to enable per subslice for the + * context. min_eus_per_subslice must be inferior or equal to + * max_eus_per_subslice. + */ + __u16 min_eus_per_subslice; + __u16 max_eus_per_subslice; + + /* + * Unused for now. Must be cleared to zero. + */ + __u32 rsvd; +}; + enum drm_i915_oa_format { I915_OA_FORMAT_A13 = 1, /* HSW only */ I915_OA_FORMAT_A29, /* HSW only */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 3c38ac9a92a7..929c8e537a14 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -502,16 +502,6 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags) - * Description - * Push an element *value* in *map*. *flags* is one of: - * - * **BPF_EXIST** - * If the queue/stack is full, the oldest element is removed to - * make room for this. - * Return - * 0 on success, or a negative error in case of failure. - * * int bpf_probe_read(void *dst, u32 size, const void *src) * Description * For tracing programs, safely attempt to read *size* bytes from @@ -1435,14 +1425,14 @@ union bpf_attr { * u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx) * Description * Equivalent to bpf_get_socket_cookie() helper that accepts - * *skb*, but gets socket from **struct bpf_sock_addr** contex. + * *skb*, but gets socket from **struct bpf_sock_addr** context. * Return * A 8-byte long non-decreasing number. * * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx) * Description * Equivalent to bpf_get_socket_cookie() helper that accepts - * *skb*, but gets socket from **struct bpf_sock_ops** contex. + * *skb*, but gets socket from **struct bpf_sock_ops** context. * Return * A 8-byte long non-decreasing number. * @@ -2098,52 +2088,52 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle) + * int bpf_rc_repeat(void *ctx) * Description * This helper is used in programs implementing IR decoding, to - * report a successfully decoded key press with *scancode*, - * *toggle* value in the given *protocol*. The scancode will be - * translated to a keycode using the rc keymap, and reported as - * an input key down event. After a period a key up event is - * generated. This period can be extended by calling either - * **bpf_rc_keydown**\ () again with the same values, or calling - * **bpf_rc_repeat**\ (). + * report a successfully decoded repeat key message. This delays + * the generation of a key up event for previously generated + * key down event. * - * Some protocols include a toggle bit, in case the button was - * released and pressed again between consecutive scancodes. + * Some IR protocols like NEC have a special IR message for + * repeating last button, for when a button is held down. * * The *ctx* should point to the lirc sample as passed into * the program. * - * The *protocol* is the decoded protocol number (see - * **enum rc_proto** for some predefined values). - * * This helper is only available is the kernel was compiled with * the **CONFIG_BPF_LIRC_MODE2** configuration option set to * "**y**". * Return * 0 * - * int bpf_rc_repeat(void *ctx) + * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle) * Description * This helper is used in programs implementing IR decoding, to - * report a successfully decoded repeat key message. This delays - * the generation of a key up event for previously generated - * key down event. + * report a successfully decoded key press with *scancode*, + * *toggle* value in the given *protocol*. The scancode will be + * translated to a keycode using the rc keymap, and reported as + * an input key down event. After a period a key up event is + * generated. This period can be extended by calling either + * **bpf_rc_keydown**\ () again with the same values, or calling + * **bpf_rc_repeat**\ (). * - * Some IR protocols like NEC have a special IR message for - * repeating last button, for when a button is held down. + * Some protocols include a toggle bit, in case the button was + * released and pressed again between consecutive scancodes. * * The *ctx* should point to the lirc sample as passed into * the program. * + * The *protocol* is the decoded protocol number (see + * **enum rc_proto** for some predefined values). + * * This helper is only available is the kernel was compiled with * the **CONFIG_BPF_LIRC_MODE2** configuration option set to * "**y**". * Return * 0 * - * uint64_t bpf_skb_cgroup_id(struct sk_buff *skb) + * u64 bpf_skb_cgroup_id(struct sk_buff *skb) * Description * Return the cgroup v2 id of the socket associated with the *skb*. * This is roughly similar to the **bpf_get_cgroup_classid**\ () @@ -2159,30 +2149,12 @@ union bpf_attr { * Return * The id is returned or 0 in case the id could not be retrieved. * - * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level) - * Description - * Return id of cgroup v2 that is ancestor of cgroup associated - * with the *skb* at the *ancestor_level*. The root cgroup is at - * *ancestor_level* zero and each step down the hierarchy - * increments the level. If *ancestor_level* == level of cgroup - * associated with *skb*, then return value will be same as that - * of **bpf_skb_cgroup_id**\ (). - * - * The helper is useful to implement policies based on cgroups - * that are upper in hierarchy than immediate cgroup associated - * with *skb*. - * - * The format of returned id and helper limitations are same as in - * **bpf_skb_cgroup_id**\ (). - * Return - * The id is returned or 0 in case the id could not be retrieved. - * * u64 bpf_get_current_cgroup_id(void) * Return * A 64-bit integer containing the current cgroup id based * on the cgroup within which the current task is running. * - * void* get_local_storage(void *map, u64 flags) + * void *bpf_get_local_storage(void *map, u64 flags) * Description * Get the pointer to the local storage area. * The type and the size of the local storage is defined @@ -2209,6 +2181,24 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * + * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level) + * Description + * Return id of cgroup v2 that is ancestor of cgroup associated + * with the *skb* at the *ancestor_level*. The root cgroup is at + * *ancestor_level* zero and each step down the hierarchy + * increments the level. If *ancestor_level* == level of cgroup + * associated with *skb*, then return value will be same as that + * of **bpf_skb_cgroup_id**\ (). + * + * The helper is useful to implement policies based on cgroups + * that are upper in hierarchy than immediate cgroup associated + * with *skb*. + * + * The format of returned id and helper limitations are same as in + * **bpf_skb_cgroup_id**\ (). + * Return + * The id is returned or 0 in case the id could not be retrieved. + * * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) * Description * Look for TCP socket matching *tuple*, optionally in a child @@ -2289,6 +2279,16 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * + * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags) + * Description + * Push an element *value* in *map*. *flags* is one of: + * + * **BPF_EXIST** + * If the queue/stack is full, the oldest element is + * removed to make room for this. + * Return + * 0 on success, or a negative error in case of failure. + * * int bpf_map_pop_elem(struct bpf_map *map, void *value) * Description * Pop an element from *map*. @@ -2343,29 +2343,94 @@ union bpf_attr { * Return * 0 * + * int bpf_spin_lock(struct bpf_spin_lock *lock) + * Description + * Acquire a spinlock represented by the pointer *lock*, which is + * stored as part of a value of a map. Taking the lock allows to + * safely update the rest of the fields in that value. The + * spinlock can (and must) later be released with a call to + * **bpf_spin_unlock**\ (\ *lock*\ ). + * + * Spinlocks in BPF programs come with a number of restrictions + * and constraints: + * + * * **bpf_spin_lock** objects are only allowed inside maps of + * types **BPF_MAP_TYPE_HASH** and **BPF_MAP_TYPE_ARRAY** (this + * list could be extended in the future). + * * BTF description of the map is mandatory. + * * The BPF program can take ONE lock at a time, since taking two + * or more could cause dead locks. + * * Only one **struct bpf_spin_lock** is allowed per map element. + * * When the lock is taken, calls (either BPF to BPF or helpers) + * are not allowed. + * * The **BPF_LD_ABS** and **BPF_LD_IND** instructions are not + * allowed inside a spinlock-ed region. + * * The BPF program MUST call **bpf_spin_unlock**\ () to release + * the lock, on all execution paths, before it returns. + * * The BPF program can access **struct bpf_spin_lock** only via + * the **bpf_spin_lock**\ () and **bpf_spin_unlock**\ () + * helpers. Loading or storing data into the **struct + * bpf_spin_lock** *lock*\ **;** field of a map is not allowed. + * * To use the **bpf_spin_lock**\ () helper, the BTF description + * of the map value must be a struct and have **struct + * bpf_spin_lock** *anyname*\ **;** field at the top level. + * Nested lock inside another struct is not allowed. + * * The **struct bpf_spin_lock** *lock* field in a map value must + * be aligned on a multiple of 4 bytes in that value. + * * Syscall with command **BPF_MAP_LOOKUP_ELEM** does not copy + * the **bpf_spin_lock** field to user space. + * * Syscall with command **BPF_MAP_UPDATE_ELEM**, or update from + * a BPF program, do not update the **bpf_spin_lock** field. + * * **bpf_spin_lock** cannot be on the stack or inside a + * networking packet (it can only be inside of a map values). + * * **bpf_spin_lock** is available to root only. + * * Tracing programs and socket filter programs cannot use + * **bpf_spin_lock**\ () due to insufficient preemption checks + * (but this may change in the future). + * * **bpf_spin_lock** is not allowed in inner maps of map-in-map. + * Return + * 0 + * + * int bpf_spin_unlock(struct bpf_spin_lock *lock) + * Description + * Release the *lock* previously locked by a call to + * **bpf_spin_lock**\ (\ *lock*\ ). + * Return + * 0 + * * struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk) * Description * This helper gets a **struct bpf_sock** pointer such - * that all the fields in bpf_sock can be accessed. + * that all the fields in this **bpf_sock** can be accessed. * Return - * A **struct bpf_sock** pointer on success, or NULL in + * A **struct bpf_sock** pointer on success, or **NULL** in * case of failure. * * struct bpf_tcp_sock *bpf_tcp_sock(struct bpf_sock *sk) * Description * This helper gets a **struct bpf_tcp_sock** pointer from a * **struct bpf_sock** pointer. - * * Return - * A **struct bpf_tcp_sock** pointer on success, or NULL in + * A **struct bpf_tcp_sock** pointer on success, or **NULL** in * case of failure. * * int bpf_skb_ecn_set_ce(struct sk_buf *skb) - * Description - * Sets ECN of IP header to ce (congestion encountered) if - * current value is ect (ECN capable). Works with IPv6 and IPv4. - * Return - * 1 if set, 0 if not set. + * Description + * Set ECN (Explicit Congestion Notification) field of IP header + * to **CE** (Congestion Encountered) if current value is **ECT** + * (ECN Capable Transport). Otherwise, do nothing. Works with IPv6 + * and IPv4. + * Return + * 1 if the **CE** flag is set (either by the current helper call + * or because it was already present), 0 if it is not set. + * + * struct bpf_sock *bpf_get_listener_sock(struct bpf_sock *sk) + * Description + * Return a **struct bpf_sock** pointer in **TCP_LISTEN** state. + * **bpf_sk_release**\ () is unnecessary and not allowed. + * Return + * A **struct bpf_sock** pointer on success, or **NULL** in + * case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2465,7 +2530,8 @@ union bpf_attr { FN(spin_unlock), \ FN(sk_fullsock), \ FN(tcp_sock), \ - FN(skb_ecn_set_ce), + FN(skb_ecn_set_ce), \ + FN(get_listener_sock), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h index 6448cdd9a350..a2f8658f1c55 100644 --- a/tools/include/uapi/linux/fcntl.h +++ b/tools/include/uapi/linux/fcntl.h @@ -41,6 +41,7 @@ #define F_SEAL_SHRINK 0x0002 /* prevent file from shrinking */ #define F_SEAL_GROW 0x0004 /* prevent file from growing */ #define F_SEAL_WRITE 0x0008 /* prevent writes */ +#define F_SEAL_FUTURE_WRITE 0x0010 /* prevent future writes while mapped */ /* (1U << 31) is reserved for signed error codes */ /* diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h index d0f515d53299..fc1a64c3447b 100644 --- a/tools/include/uapi/linux/mman.h +++ b/tools/include/uapi/linux/mman.h @@ -12,6 +12,10 @@ #define OVERCOMMIT_ALWAYS 1 #define OVERCOMMIT_NEVER 2 +#define MAP_SHARED 0x01 /* Share changes */ +#define MAP_PRIVATE 0x02 /* Changes are private */ +#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */ + /* * Huge page size encoding when MAP_HUGETLB is specified, and a huge page * size other than the default is desired. See hugetlb_encode.h. diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h index 404d4b9ffe76..df1153cea0b7 100644 --- a/tools/include/uapi/sound/asound.h +++ b/tools/include/uapi/sound/asound.h @@ -32,6 +32,7 @@ #ifndef __KERNEL__ #include <stdlib.h> +#include <time.h> #endif /* diff --git a/tools/io_uring/io_uring-bench.c b/tools/io_uring/io_uring-bench.c index 512306a37531..0f257139b003 100644 --- a/tools/io_uring/io_uring-bench.c +++ b/tools/io_uring/io_uring-bench.c @@ -32,10 +32,6 @@ #include "liburing.h" #include "barrier.h" -#ifndef IOCQE_FLAG_CACHEHIT -#define IOCQE_FLAG_CACHEHIT (1U << 0) -#endif - #define min(a, b) ((a < b) ? (a) : (b)) struct io_sq_ring { @@ -85,7 +81,6 @@ struct submitter { unsigned long reaps; unsigned long done; unsigned long calls; - unsigned long cachehit, cachemiss; volatile int finish; __s32 *fds; @@ -270,10 +265,6 @@ static int reap_events(struct submitter *s) return -1; } } - if (cqe->flags & IOCQE_FLAG_CACHEHIT) - s->cachehit++; - else - s->cachemiss++; reaped++; head++; } while (1); @@ -489,7 +480,7 @@ static void file_depths(char *buf) int main(int argc, char *argv[]) { struct submitter *s = &submitters[0]; - unsigned long done, calls, reap, cache_hit, cache_miss; + unsigned long done, calls, reap; int err, i, flags, fd; char *fdepths; void *ret; @@ -569,44 +560,29 @@ int main(int argc, char *argv[]) pthread_create(&s->thread, NULL, submitter_fn, s); fdepths = malloc(8 * s->nr_files); - cache_hit = cache_miss = reap = calls = done = 0; + reap = calls = done = 0; do { unsigned long this_done = 0; unsigned long this_reap = 0; unsigned long this_call = 0; - unsigned long this_cache_hit = 0; - unsigned long this_cache_miss = 0; unsigned long rpc = 0, ipc = 0; - double hit = 0.0; sleep(1); this_done += s->done; this_call += s->calls; this_reap += s->reaps; - this_cache_hit += s->cachehit; - this_cache_miss += s->cachemiss; - if (this_cache_hit && this_cache_miss) { - unsigned long hits, total; - - hits = this_cache_hit - cache_hit; - total = hits + this_cache_miss - cache_miss; - hit = (double) hits / (double) total; - hit *= 100.0; - } if (this_call - calls) { rpc = (this_done - done) / (this_call - calls); ipc = (this_reap - reap) / (this_call - calls); } else rpc = ipc = -1; file_depths(fdepths); - printf("IOPS=%lu, IOS/call=%ld/%ld, inflight=%u (%s), Cachehit=%0.2f%%\n", + printf("IOPS=%lu, IOS/call=%ld/%ld, inflight=%u (%s)\n", this_done - done, rpc, ipc, s->inflight, - fdepths, hit); + fdepths); done = this_done; calls = this_call; reap = this_reap; - cache_hit = s->cachehit; - cache_miss = s->cachemiss; } while (!finish); pthread_join(s->thread, &ret); diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore index 4db74758c674..fecb78afea3f 100644 --- a/tools/lib/bpf/.gitignore +++ b/tools/lib/bpf/.gitignore @@ -1,3 +1,4 @@ libbpf_version.h FEATURE-DUMP.libbpf test_libbpf +libbpf.so.* diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 61aaacf0cfa1..8e7c56e9590f 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -3,7 +3,7 @@ BPF_VERSION = 0 BPF_PATCHLEVEL = 0 -BPF_EXTRAVERSION = 1 +BPF_EXTRAVERSION = 2 MAKEFLAGS += --no-print-directory @@ -79,8 +79,6 @@ export prefix libdir src obj libdir_SQ = $(subst ','\'',$(libdir)) libdir_relative_SQ = $(subst ','\'',$(libdir_relative)) -LIB_FILE = libbpf.a libbpf.so - VERSION = $(BPF_VERSION) PATCHLEVEL = $(BPF_PATCHLEVEL) EXTRAVERSION = $(BPF_EXTRAVERSION) @@ -88,7 +86,10 @@ EXTRAVERSION = $(BPF_EXTRAVERSION) OBJ = $@ N = -LIBBPF_VERSION = $(BPF_VERSION).$(BPF_PATCHLEVEL).$(BPF_EXTRAVERSION) +LIBBPF_VERSION = $(BPF_VERSION).$(BPF_PATCHLEVEL).$(BPF_EXTRAVERSION) + +LIB_TARGET = libbpf.a libbpf.so.$(LIBBPF_VERSION) +LIB_FILE = libbpf.a libbpf.so* # Set compile option CFLAGS ifdef EXTRA_CFLAGS @@ -128,16 +129,18 @@ all: export srctree OUTPUT CC LD CFLAGS V include $(srctree)/tools/build/Makefile.include -BPF_IN := $(OUTPUT)libbpf-in.o -LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE)) -VERSION_SCRIPT := libbpf.map +BPF_IN := $(OUTPUT)libbpf-in.o +VERSION_SCRIPT := libbpf.map + +LIB_TARGET := $(addprefix $(OUTPUT),$(LIB_TARGET)) +LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE)) GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN) | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {s++} END{print s}') VERSIONED_SYM_COUNT = $(shell readelf -s --wide $(OUTPUT)libbpf.so | \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l) -CMD_TARGETS = $(LIB_FILE) +CMD_TARGETS = $(LIB_TARGET) CXX_TEST_TARGET = $(OUTPUT)test_libbpf @@ -170,9 +173,13 @@ $(BPF_IN): force elfdep bpfdep echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true $(Q)$(MAKE) $(build)=libbpf -$(OUTPUT)libbpf.so: $(BPF_IN) - $(QUIET_LINK)$(CC) --shared -Wl,--version-script=$(VERSION_SCRIPT) \ - $^ -o $@ +$(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION) + +$(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN) + $(QUIET_LINK)$(CC) --shared -Wl,-soname,libbpf.so.$(VERSION) \ + -Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -o $@ + @ln -sf $(@F) $(OUTPUT)libbpf.so + @ln -sf $(@F) $(OUTPUT)libbpf.so.$(VERSION) $(OUTPUT)libbpf.a: $(BPF_IN) $(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^ @@ -192,6 +199,12 @@ check_abi: $(OUTPUT)libbpf.so exit 1; \ fi +define do_install_mkdir + if [ ! -d '$(DESTDIR_SQ)$1' ]; then \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1'; \ + fi +endef + define do_install if [ ! -d '$(DESTDIR_SQ)$2' ]; then \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2'; \ @@ -200,14 +213,16 @@ define do_install endef install_lib: all_cmd - $(call QUIET_INSTALL, $(LIB_FILE)) \ - $(call do_install,$(LIB_FILE),$(libdir_SQ)) + $(call QUIET_INSTALL, $(LIB_TARGET)) \ + $(call do_install_mkdir,$(libdir_SQ)); \ + cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ) install_headers: $(call QUIET_INSTALL, headers) \ $(call do_install,bpf.h,$(prefix)/include/bpf,644); \ - $(call do_install,libbpf.h,$(prefix)/include/bpf,644); - $(call do_install,btf.h,$(prefix)/include/bpf,644); + $(call do_install,libbpf.h,$(prefix)/include/bpf,644); \ + $(call do_install,btf.h,$(prefix)/include/bpf,644); \ + $(call do_install,xsk.h,$(prefix)/include/bpf,644); install: install_lib @@ -219,7 +234,7 @@ config-clean: clean: $(call QUIET_CLEAN, libbpf) $(RM) $(TARGETS) $(CXX_TEST_TARGET) \ - *.o *~ *.a *.so .*.d .*.cmd LIBBPF-CFLAGS + *.o *~ *.a *.so *.so.$(VERSION) .*.d .*.cmd LIBBPF-CFLAGS $(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf diff --git a/tools/lib/bpf/README.rst b/tools/lib/bpf/README.rst index 5788479384ca..cef7b77eab69 100644 --- a/tools/lib/bpf/README.rst +++ b/tools/lib/bpf/README.rst @@ -111,6 +111,7 @@ starting from ``0.0.1``. Every time ABI is being changed, e.g. because a new symbol is added or semantic of existing symbol is changed, ABI version should be bumped. +This bump in ABI version is at most once per kernel development cycle. For example, if current state of ``libbpf.map`` is: diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 1b8d8cdd3575..cf119c9b6f27 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1602,16 +1602,12 @@ static bool btf_equal_int(struct btf_type *t1, struct btf_type *t2) /* Calculate type signature hash of ENUM. */ static __u32 btf_hash_enum(struct btf_type *t) { - struct btf_enum *member = (struct btf_enum *)(t + 1); - __u32 vlen = BTF_INFO_VLEN(t->info); - __u32 h = btf_hash_common(t); - int i; + __u32 h; - for (i = 0; i < vlen; i++) { - h = hash_combine(h, member->name_off); - h = hash_combine(h, member->val); - member++; - } + /* don't hash vlen and enum members to support enum fwd resolving */ + h = hash_combine(0, t->name_off); + h = hash_combine(h, t->info & ~0xffff); + h = hash_combine(h, t->size); return h; } @@ -1637,6 +1633,22 @@ static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2) return true; } +static inline bool btf_is_enum_fwd(struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM && + BTF_INFO_VLEN(t->info) == 0; +} + +static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2) +{ + if (!btf_is_enum_fwd(t1) && !btf_is_enum_fwd(t2)) + return btf_equal_enum(t1, t2); + /* ignore vlen when comparing */ + return t1->name_off == t2->name_off && + (t1->info & ~0xffff) == (t2->info & ~0xffff) && + t1->size == t2->size; +} + /* * Calculate type signature hash of STRUCT/UNION, ignoring referenced type IDs, * as referenced type IDs equivalence is established separately during type @@ -1860,6 +1872,17 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) new_id = cand_node->type_id; break; } + if (d->opts.dont_resolve_fwds) + continue; + if (btf_compat_enum(t, cand)) { + if (btf_is_enum_fwd(t)) { + /* resolve fwd to full enum */ + new_id = cand_node->type_id; + break; + } + /* resolve canonical enum fwd to full enum */ + d->map[cand_node->type_id] = type_id; + } } break; @@ -2084,7 +2107,7 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, return fwd_kind == real_kind; } - if (cand_type->info != canon_type->info) + if (cand_kind != canon_kind) return 0; switch (cand_kind) { @@ -2092,7 +2115,10 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, return btf_equal_int(cand_type, canon_type); case BTF_KIND_ENUM: - return btf_equal_enum(cand_type, canon_type); + if (d->opts.dont_resolve_fwds) + return btf_equal_enum(cand_type, canon_type); + else + return btf_compat_enum(cand_type, canon_type); case BTF_KIND_FWD: return btf_equal_common(cand_type, canon_type); @@ -2103,6 +2129,8 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, case BTF_KIND_PTR: case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: + if (cand_type->info != canon_type->info) + return 0; return btf_dedup_is_equiv(d, cand_type->type, canon_type->type); case BTF_KIND_ARRAY: { diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index e6ad87512519..11c25d9ea431 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -840,12 +840,19 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) obj->efile.maps_shndx = idx; else if (strcmp(name, BTF_ELF_SEC) == 0) { obj->btf = btf__new(data->d_buf, data->d_size); - if (IS_ERR(obj->btf) || btf__load(obj->btf)) { + if (IS_ERR(obj->btf)) { pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n", BTF_ELF_SEC, PTR_ERR(obj->btf)); - if (!IS_ERR(obj->btf)) - btf__free(obj->btf); obj->btf = NULL; + continue; + } + err = btf__load(obj->btf); + if (err) { + pr_warning("Error loading %s into kernel: %d. Ignored and continue.\n", + BTF_ELF_SEC, err); + btf__free(obj->btf); + obj->btf = NULL; + err = 0; } } else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) { btf_ext_data = data; diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index f98ac82c9aea..8d0078b65486 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -126,8 +126,8 @@ static void xsk_set_umem_config(struct xsk_umem_config *cfg, cfg->frame_headroom = usr_cfg->frame_headroom; } -static void xsk_set_xdp_socket_config(struct xsk_socket_config *cfg, - const struct xsk_socket_config *usr_cfg) +static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg, + const struct xsk_socket_config *usr_cfg) { if (!usr_cfg) { cfg->rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS; @@ -135,14 +135,19 @@ static void xsk_set_xdp_socket_config(struct xsk_socket_config *cfg, cfg->libbpf_flags = 0; cfg->xdp_flags = 0; cfg->bind_flags = 0; - return; + return 0; } + if (usr_cfg->libbpf_flags & ~XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD) + return -EINVAL; + cfg->rx_size = usr_cfg->rx_size; cfg->tx_size = usr_cfg->tx_size; cfg->libbpf_flags = usr_cfg->libbpf_flags; cfg->xdp_flags = usr_cfg->xdp_flags; cfg->bind_flags = usr_cfg->bind_flags; + + return 0; } int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area, __u64 size, @@ -557,7 +562,9 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, } strncpy(xsk->ifname, ifname, IFNAMSIZ); - xsk_set_xdp_socket_config(&xsk->config, usr_config); + err = xsk_set_xdp_socket_config(&xsk->config, usr_config); + if (err) + goto out_socket; if (rx) { err = setsockopt(xsk->fd, SOL_XDP, XDP_RX_RING, diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 87494c7c619d..981c6ce2da2c 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -2233,7 +2233,7 @@ eval_type_str(unsigned long long val, const char *type, int pointer) return val & 0xffffffff; if (strcmp(type, "u64") == 0 || - strcmp(type, "s64")) + strcmp(type, "s64") == 0) return val; if (strcmp(type, "s8") == 0) diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile index c9d038f91af6..53f8be0f4a1f 100644 --- a/tools/objtool/Makefile +++ b/tools/objtool/Makefile @@ -25,14 +25,17 @@ LIBSUBCMD = $(LIBSUBCMD_OUTPUT)libsubcmd.a OBJTOOL := $(OUTPUT)objtool OBJTOOL_IN := $(OBJTOOL)-in.o +LIBELF_FLAGS := $(shell pkg-config libelf --cflags 2>/dev/null) +LIBELF_LIBS := $(shell pkg-config libelf --libs 2>/dev/null || echo -lelf) + all: $(OBJTOOL) INCLUDES := -I$(srctree)/tools/include \ -I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi \ -I$(srctree)/tools/objtool/arch/$(ARCH)/include WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed -CFLAGS += -Werror $(WARNINGS) $(KBUILD_HOSTCFLAGS) -g $(INCLUDES) -LDFLAGS += -lelf $(LIBSUBCMD) $(KBUILD_HOSTLDFLAGS) +CFLAGS += -Werror $(WARNINGS) $(KBUILD_HOSTCFLAGS) -g $(INCLUDES) $(LIBELF_FLAGS) +LDFLAGS += $(LIBELF_LIBS) $(LIBSUBCMD) $(KBUILD_HOSTLDFLAGS) # Allow old libelf to be used: elfshdr := $(shell echo '$(pound)include <libelf.h>' | $(CC) $(CFLAGS) -x c -E - | grep elf_getshdr) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 5dde107083c6..479196aeb409 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -165,6 +165,7 @@ static int __dead_end_function(struct objtool_file *file, struct symbol *func, "fortify_panic", "usercopy_abort", "machine_real_restart", + "rewind_stack_do_exit", }; if (func->bind == STB_WEAK) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 01f7555fd933..e8c9f77e9010 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -481,8 +481,8 @@ $(madvise_behavior_array): $(madvise_hdr_dir)/mman-common.h $(madvise_behavior_t mmap_flags_array := $(beauty_outdir)/mmap_flags_array.c mmap_flags_tbl := $(srctree)/tools/perf/trace/beauty/mmap_flags.sh -$(mmap_flags_array): $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(mmap_flags_tbl) - $(Q)$(SHELL) '$(mmap_flags_tbl)' $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@ +$(mmap_flags_array): $(linux_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(mmap_flags_tbl) + $(Q)$(SHELL) '$(mmap_flags_tbl)' $(linux_uapi_dir) $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@ mount_flags_array := $(beauty_outdir)/mount_flags_array.c mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/mount_flags.sh diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 2ae92fddb6d5..92ee0b4378d4 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -345,6 +345,10 @@ 334 common rseq __x64_sys_rseq # don't use numbers 387 through 423, add new calls after the last # 'common' entry +424 common pidfd_send_signal __x64_sys_pidfd_send_signal +425 common io_uring_setup __x64_sys_io_uring_setup +426 common io_uring_enter __x64_sys_io_uring_enter +427 common io_uring_register __x64_sys_io_uring_register # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 49ee3c2033ec..c3625ec374e0 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1308,6 +1308,7 @@ static void init_features(struct perf_session *session) for (feat = HEADER_FIRST_FEATURE; feat < HEADER_LAST_FEATURE; feat++) perf_header__set_feat(&session->header, feat); + perf_header__clear_feat(&session->header, HEADER_DIR_FORMAT); perf_header__clear_feat(&session->header, HEADER_BUILD_ID); perf_header__clear_feat(&session->header, HEADER_TRACING_DATA); perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 1999d6533d12..fbbb0da43abb 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1377,6 +1377,7 @@ int cmd_top(int argc, const char **argv) * */ .overwrite = 0, .sample_time = true, + .sample_time_set = true, }, .max_stack = sysctl__max_stack(), .annotation_opts = annotation__default_options, diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 7b55613924de..c68ee06cae63 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -103,7 +103,7 @@ done # diff with extra ignore lines check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"' check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"' -check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common.h>"' +check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"' check include/uapi/linux/mman.h '-I "^#include <\(uapi/\)*asm/mman.h>"' # diff non-symmetric files diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py index 3b71902a5a21..bf271fbc3a88 100644 --- a/tools/perf/scripts/python/export-to-sqlite.py +++ b/tools/perf/scripts/python/export-to-sqlite.py @@ -331,7 +331,7 @@ if perf_db_export_calls: 'return_id,' 'CASE WHEN flags=0 THEN \'\' WHEN flags=1 THEN \'no call\' WHEN flags=2 THEN \'no return\' WHEN flags=3 THEN \'no call/return\' WHEN flags=6 THEN \'jump\' ELSE flags END AS flags,' 'parent_call_path_id,' - 'parent_id' + 'calls.parent_id' ' FROM calls INNER JOIN call_paths ON call_paths.id = call_path_id') do_query(query, 'CREATE VIEW samples_view AS ' diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index e38518cdcbc3..74ef92f1d19a 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -107,6 +107,7 @@ import os from PySide.QtCore import * from PySide.QtGui import * from PySide.QtSql import * +pyside_version_1 = True from decimal import * from ctypes import * from multiprocessing import Process, Array, Value, Event @@ -1526,6 +1527,19 @@ def BranchDataPrep(query): " (" + dsoname(query.value(15)) + ")") return data +def BranchDataPrepWA(query): + data = [] + data.append(query.value(0)) + # Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string + data.append("{:>19}".format(query.value(1))) + for i in xrange(2, 8): + data.append(query.value(i)) + data.append(tohex(query.value(8)).rjust(16) + " " + query.value(9) + offstr(query.value(10)) + + " (" + dsoname(query.value(11)) + ")" + " -> " + + tohex(query.value(12)) + " " + query.value(13) + offstr(query.value(14)) + + " (" + dsoname(query.value(15)) + ")") + return data + # Branch data model class BranchModel(TreeModel): @@ -1553,7 +1567,11 @@ class BranchModel(TreeModel): " AND evsel_id = " + str(self.event_id) + " ORDER BY samples.id" " LIMIT " + str(glb_chunk_sz)) - self.fetcher = SQLFetcher(glb, sql, BranchDataPrep, self.AddSample) + if pyside_version_1 and sys.version_info[0] == 3: + prep = BranchDataPrepWA + else: + prep = BranchDataPrep + self.fetcher = SQLFetcher(glb, sql, prep, self.AddSample) self.fetcher.done.connect(self.Update) self.fetcher.Fetch(glb_chunk_sz) @@ -2079,14 +2097,6 @@ def IsSelectable(db, table, sql = ""): return False return True -# SQL data preparation - -def SQLTableDataPrep(query, count): - data = [] - for i in xrange(count): - data.append(query.value(i)) - return data - # SQL table data model item class SQLTableItem(): @@ -2110,7 +2120,7 @@ class SQLTableModel(TableModel): self.more = True self.populated = 0 self.column_headers = column_headers - self.fetcher = SQLFetcher(glb, sql, lambda x, y=len(column_headers): SQLTableDataPrep(x, y), self.AddSample) + self.fetcher = SQLFetcher(glb, sql, lambda x, y=len(column_headers): self.SQLTableDataPrep(x, y), self.AddSample) self.fetcher.done.connect(self.Update) self.fetcher.Fetch(glb_chunk_sz) @@ -2154,6 +2164,12 @@ class SQLTableModel(TableModel): def columnHeader(self, column): return self.column_headers[column] + def SQLTableDataPrep(self, query, count): + data = [] + for i in xrange(count): + data.append(query.value(i)) + return data + # SQL automatic table data model class SQLAutoTableModel(SQLTableModel): @@ -2182,8 +2198,32 @@ class SQLAutoTableModel(SQLTableModel): QueryExec(query, "SELECT column_name FROM information_schema.columns WHERE table_schema = '" + schema + "' and table_name = '" + select_table_name + "'") while query.next(): column_headers.append(query.value(0)) + if pyside_version_1 and sys.version_info[0] == 3: + if table_name == "samples_view": + self.SQLTableDataPrep = self.samples_view_DataPrep + if table_name == "samples": + self.SQLTableDataPrep = self.samples_DataPrep super(SQLAutoTableModel, self).__init__(glb, sql, column_headers, parent) + def samples_view_DataPrep(self, query, count): + data = [] + data.append(query.value(0)) + # Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string + data.append("{:>19}".format(query.value(1))) + for i in xrange(2, count): + data.append(query.value(i)) + return data + + def samples_DataPrep(self, query, count): + data = [] + for i in xrange(9): + data.append(query.value(i)) + # Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string + data.append("{:>19}".format(query.value(9))) + for i in xrange(10, count): + data.append(query.value(i)) + return data + # Base class for custom ResizeColumnsToContents class ResizeColumnsToContentsBase(QObject): @@ -2868,9 +2908,13 @@ class LibXED(): ok = self.xed_format_context(2, inst.xedp, inst.bufferp, sizeof(inst.buffer), ip, 0, 0) if not ok: return 0, "" + if sys.version_info[0] == 2: + result = inst.buffer.value + else: + result = inst.buffer.value.decode() # Return instruction length and the disassembled instruction text # For now, assume the length is in byte 166 - return inst.xedd[166], inst.buffer.value + return inst.xedd[166], result def TryOpen(file_name): try: @@ -2886,9 +2930,14 @@ def Is64Bit(f): header = f.read(7) f.seek(pos) magic = header[0:4] - eclass = ord(header[4]) - encoding = ord(header[5]) - version = ord(header[6]) + if sys.version_info[0] == 2: + eclass = ord(header[4]) + encoding = ord(header[5]) + version = ord(header[6]) + else: + eclass = header[4] + encoding = header[5] + version = header[6] if magic == chr(127) + "ELF" and eclass > 0 and eclass < 3 and encoding > 0 and encoding < 3 and version == 1: result = True if eclass == 2 else False return result diff --git a/tools/perf/trace/beauty/mmap_flags.sh b/tools/perf/trace/beauty/mmap_flags.sh index 32bac9c0d694..5f5eefcb3c74 100755 --- a/tools/perf/trace/beauty/mmap_flags.sh +++ b/tools/perf/trace/beauty/mmap_flags.sh @@ -1,15 +1,18 @@ #!/bin/sh # SPDX-License-Identifier: LGPL-2.1 -if [ $# -ne 2 ] ; then +if [ $# -ne 3 ] ; then [ $# -eq 1 ] && hostarch=$1 || hostarch=`uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/` + linux_header_dir=tools/include/uapi/linux header_dir=tools/include/uapi/asm-generic arch_header_dir=tools/arch/${hostarch}/include/uapi/asm else - header_dir=$1 - arch_header_dir=$2 + linux_header_dir=$1 + header_dir=$2 + arch_header_dir=$3 fi +linux_mman=${linux_header_dir}/mman.h arch_mman=${arch_header_dir}/mman.h # those in egrep -vw are flags, we want just the bits @@ -20,6 +23,11 @@ egrep -q $regex ${arch_mman} && \ (egrep $regex ${arch_mman} | \ sed -r "s/$regex/\2 \1/g" | \ xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n") +egrep -q $regex ${linux_mman} && \ +(egrep $regex ${linux_mman} | \ + egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \ + sed -r "s/$regex/\2 \1/g" | \ + xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n") ([ ! -f ${arch_mman} ] || egrep -q '#[[:space:]]*include[[:space:]]+<uapi/asm-generic/mman.*' ${arch_mman}) && (egrep $regex ${header_dir}/mman-common.h | \ egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \ diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c index ba4c623cd8de..39fe21e1cf93 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -387,6 +387,7 @@ cs_etm_decoder__buffer_range(struct cs_etm_decoder *decoder, break; case OCSD_INSTR_ISB: case OCSD_INSTR_DSB_DMB: + case OCSD_INSTR_WFI_WFE: case OCSD_INSTR_OTHER: default: packet->last_instr_taken_branch = false; diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index c6351b557bb0..9494f9dc61ec 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -57,9 +57,11 @@ struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env, else if (prog_id > node->info_linear->info.id) n = n->rb_right; else - break; + goto out; } + node = NULL; +out: up_read(&env->bpf_progs.lock); return node; } @@ -109,10 +111,12 @@ struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id) else if (btf_id > node->id) n = n->rb_right; else - break; + goto out; } + node = NULL; up_read(&env->bpf_progs.lock); +out: return node; } diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index ec78e93085de..51ead577533f 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -231,35 +231,6 @@ void perf_evlist__set_leader(struct perf_evlist *evlist) } } -void perf_event_attr__set_max_precise_ip(struct perf_event_attr *pattr) -{ - struct perf_event_attr attr = { - .type = PERF_TYPE_HARDWARE, - .config = PERF_COUNT_HW_CPU_CYCLES, - .exclude_kernel = 1, - .precise_ip = 3, - }; - - event_attr_init(&attr); - - /* - * Unnamed union member, not supported as struct member named - * initializer in older compilers such as gcc 4.4.7 - */ - attr.sample_period = 1; - - while (attr.precise_ip != 0) { - int fd = sys_perf_event_open(&attr, 0, -1, -1, 0); - if (fd != -1) { - close(fd); - break; - } - --attr.precise_ip; - } - - pattr->precise_ip = attr.precise_ip; -} - int __perf_evlist__add_default(struct perf_evlist *evlist, bool precise) { struct perf_evsel *evsel = perf_evsel__new_cycles(precise); @@ -1897,12 +1868,12 @@ static void *perf_evlist__poll_thread(void *arg) { struct perf_evlist *evlist = arg; bool draining = false; - int i; + int i, done = 0; + + while (!done) { + bool got_data = false; - while (draining || !(evlist->thread.done)) { - if (draining) - draining = false; - else if (evlist->thread.done) + if (evlist->thread.done) draining = true; if (!draining) @@ -1923,9 +1894,13 @@ static void *perf_evlist__poll_thread(void *arg) pr_warning("cannot locate proper evsel for the side band event\n"); perf_mmap__consume(map); + got_data = true; } perf_mmap__read_done(map); } + + if (draining && !got_data) + break; } return NULL; } diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index dcb68f34d2cd..6a94785b9100 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -315,8 +315,6 @@ void perf_evlist__to_front(struct perf_evlist *evlist, void perf_evlist__set_tracking_event(struct perf_evlist *evlist, struct perf_evsel *tracking_evsel); -void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr); - struct perf_evsel * perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 7835e05f0c0a..966360844fff 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -295,7 +295,6 @@ struct perf_evsel *perf_evsel__new_cycles(bool precise) if (!precise) goto new_event; - perf_event_attr__set_max_precise_ip(&attr); /* * Now let the usual logic to set up the perf_event_attr defaults * to kick in when we return and before perf_evsel__open() is called. @@ -305,6 +304,8 @@ new_event: if (evsel == NULL) goto out; + evsel->precise_max = true; + /* use asprintf() because free(evsel) assumes name is allocated */ if (asprintf(&evsel->name, "cycles%s%s%.*s", (attr.precise_ip || attr.exclude_kernel) ? ":" : "", @@ -1083,7 +1084,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, } if (evsel->precise_max) - perf_event_attr__set_max_precise_ip(attr); + attr->precise_ip = 3; if (opts->all_user) { attr->exclude_kernel = 1; @@ -1749,6 +1750,59 @@ static bool ignore_missing_thread(struct perf_evsel *evsel, return true; } +static void display_attr(struct perf_event_attr *attr) +{ + if (verbose >= 2) { + fprintf(stderr, "%.60s\n", graph_dotted_line); + fprintf(stderr, "perf_event_attr:\n"); + perf_event_attr__fprintf(stderr, attr, __open_attr__fprintf, NULL); + fprintf(stderr, "%.60s\n", graph_dotted_line); + } +} + +static int perf_event_open(struct perf_evsel *evsel, + pid_t pid, int cpu, int group_fd, + unsigned long flags) +{ + int precise_ip = evsel->attr.precise_ip; + int fd; + + while (1) { + pr_debug2("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx", + pid, cpu, group_fd, flags); + + fd = sys_perf_event_open(&evsel->attr, pid, cpu, group_fd, flags); + if (fd >= 0) + break; + + /* + * Do quick precise_ip fallback if: + * - there is precise_ip set in perf_event_attr + * - maximum precise is requested + * - sys_perf_event_open failed with ENOTSUP error, + * which is associated with wrong precise_ip + */ + if (!precise_ip || !evsel->precise_max || (errno != ENOTSUP)) + break; + + /* + * We tried all the precise_ip values, and it's + * still failing, so leave it to standard fallback. + */ + if (!evsel->attr.precise_ip) { + evsel->attr.precise_ip = precise_ip; + break; + } + + pr_debug2("\nsys_perf_event_open failed, error %d\n", -ENOTSUP); + evsel->attr.precise_ip--; + pr_debug2("decreasing precise_ip by one (%d)\n", evsel->attr.precise_ip); + display_attr(&evsel->attr); + } + + return fd; +} + int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, struct thread_map *threads) { @@ -1824,12 +1878,7 @@ retry_sample_id: if (perf_missing_features.sample_id_all) evsel->attr.sample_id_all = 0; - if (verbose >= 2) { - fprintf(stderr, "%.60s\n", graph_dotted_line); - fprintf(stderr, "perf_event_attr:\n"); - perf_event_attr__fprintf(stderr, &evsel->attr, __open_attr__fprintf, NULL); - fprintf(stderr, "%.60s\n", graph_dotted_line); - } + display_attr(&evsel->attr); for (cpu = 0; cpu < cpus->nr; cpu++) { @@ -1841,13 +1890,10 @@ retry_sample_id: group_fd = get_group_fd(evsel, cpu, thread); retry_open: - pr_debug2("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx", - pid, cpus->map[cpu], group_fd, flags); - test_attr__ready(); - fd = sys_perf_event_open(&evsel->attr, pid, cpus->map[cpu], - group_fd, flags); + fd = perf_event_open(evsel, pid, cpus->map[cpu], + group_fd, flags); FD(evsel, cpu, thread) = fd; @@ -2322,7 +2368,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, if (data->user_regs.abi) { u64 mask = evsel->attr.sample_regs_user; - sz = hweight_long(mask) * sizeof(u64); + sz = hweight64(mask) * sizeof(u64); OVERFLOW_CHECK(array, sz, max_size); data->user_regs.mask = mask; data->user_regs.regs = (u64 *)array; @@ -2378,7 +2424,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) { u64 mask = evsel->attr.sample_regs_intr; - sz = hweight_long(mask) * sizeof(u64); + sz = hweight64(mask) * sizeof(u64); OVERFLOW_CHECK(array, sz, max_size); data->intr_regs.mask = mask; data->intr_regs.regs = (u64 *)array; @@ -2506,7 +2552,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, if (type & PERF_SAMPLE_REGS_USER) { if (sample->user_regs.abi) { result += sizeof(u64); - sz = hweight_long(sample->user_regs.mask) * sizeof(u64); + sz = hweight64(sample->user_regs.mask) * sizeof(u64); result += sz; } else { result += sizeof(u64); @@ -2534,7 +2580,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type, if (type & PERF_SAMPLE_REGS_INTR) { if (sample->intr_regs.abi) { result += sizeof(u64); - sz = hweight_long(sample->intr_regs.mask) * sizeof(u64); + sz = hweight64(sample->intr_regs.mask) * sizeof(u64); result += sz; } else { result += sizeof(u64); @@ -2664,7 +2710,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, if (type & PERF_SAMPLE_REGS_USER) { if (sample->user_regs.abi) { *array++ = sample->user_regs.abi; - sz = hweight_long(sample->user_regs.mask) * sizeof(u64); + sz = hweight64(sample->user_regs.mask) * sizeof(u64); memcpy(array, sample->user_regs.regs, sz); array = (void *)array + sz; } else { @@ -2700,7 +2746,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, if (type & PERF_SAMPLE_REGS_INTR) { if (sample->intr_regs.abi) { *array++ = sample->intr_regs.abi; - sz = hweight_long(sample->intr_regs.mask) * sizeof(u64); + sz = hweight64(sample->intr_regs.mask) * sizeof(u64); memcpy(array, sample->intr_regs.regs, sz); array = (void *)array + sz; } else { diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index b9e693825873..2d2af2ac2b1e 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -2606,6 +2606,7 @@ static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused) perf_env__insert_bpf_prog_info(env, info_node); } + up_write(&env->bpf_progs.lock); return 0; out: free(info_linear); @@ -2623,7 +2624,9 @@ static int process_bpf_prog_info(struct feat_fd *ff __maybe_unused, void *data _ static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused) { struct perf_env *env = &ff->ph->env; + struct btf_node *node = NULL; u32 count, i; + int err = -1; if (ff->ph->needs_swap) { pr_warning("interpreting btf from systems with endianity is not yet supported\n"); @@ -2636,31 +2639,32 @@ static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused) down_write(&env->bpf_progs.lock); for (i = 0; i < count; ++i) { - struct btf_node *node; u32 id, data_size; if (do_read_u32(ff, &id)) - return -1; + goto out; if (do_read_u32(ff, &data_size)) - return -1; + goto out; node = malloc(sizeof(struct btf_node) + data_size); if (!node) - return -1; + goto out; node->id = id; node->data_size = data_size; - if (__do_read(ff, node->data, data_size)) { - free(node); - return -1; - } + if (__do_read(ff, node->data, data_size)) + goto out; perf_env__insert_btf(env, node); + node = NULL; } + err = 0; +out: up_write(&env->bpf_progs.lock); - return 0; + free(node); + return err; } struct feature_ops { diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index 6e03db142091..872fab163585 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -251,19 +251,15 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params) if (!(decoder->tsc_ctc_ratio_n % decoder->tsc_ctc_ratio_d)) decoder->tsc_ctc_mult = decoder->tsc_ctc_ratio_n / decoder->tsc_ctc_ratio_d; - - /* - * Allow for timestamps appearing to backwards because a TSC - * packet has slipped past a MTC packet, so allow 2 MTC ticks - * or ... - */ - decoder->tsc_slip = multdiv(2 << decoder->mtc_shift, - decoder->tsc_ctc_ratio_n, - decoder->tsc_ctc_ratio_d); } - /* ... or 0x100 paranoia */ - if (decoder->tsc_slip < 0x100) - decoder->tsc_slip = 0x100; + + /* + * A TSC packet can slip past MTC packets so that the timestamp appears + * to go backwards. One estimate is that can be up to about 40 CPU + * cycles, which is certainly less than 0x1000 TSC ticks, but accept + * slippage an order of magnitude more to be on the safe side. + */ + decoder->tsc_slip = 0x10000; intel_pt_log("timestamp: mtc_shift %u\n", decoder->mtc_shift); intel_pt_log("timestamp: tsc_ctc_ratio_n %u\n", decoder->tsc_ctc_ratio_n); diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 61959aba7e27..3c520baa198c 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1421,6 +1421,20 @@ static void machine__set_kernel_mmap(struct machine *machine, machine->vmlinux_map->end = ~0ULL; } +static void machine__update_kernel_mmap(struct machine *machine, + u64 start, u64 end) +{ + struct map *map = machine__kernel_map(machine); + + map__get(map); + map_groups__remove(&machine->kmaps, map); + + machine__set_kernel_mmap(machine, start, end); + + map_groups__insert(&machine->kmaps, map); + map__put(map); +} + int machine__create_kernel_maps(struct machine *machine) { struct dso *kernel = machine__get_kernel(machine); @@ -1453,17 +1467,11 @@ int machine__create_kernel_maps(struct machine *machine) goto out_put; } - /* we have a real start address now, so re-order the kmaps */ - map = machine__kernel_map(machine); - - map__get(map); - map_groups__remove(&machine->kmaps, map); - - /* assume it's the last in the kmaps */ - machine__set_kernel_mmap(machine, addr, ~0ULL); - - map_groups__insert(&machine->kmaps, map); - map__put(map); + /* + * we have a real start address now, so re-order the kmaps + * assume it's the last in the kmaps + */ + machine__update_kernel_mmap(machine, addr, ~0ULL); } if (machine__create_extra_kernel_maps(machine, kernel)) @@ -1599,7 +1607,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine, if (strstr(kernel->long_name, "vmlinux")) dso__set_short_name(kernel, "[kernel.vmlinux]", false); - machine__set_kernel_mmap(machine, event->mmap.start, + machine__update_kernel_mmap(machine, event->mmap.start, event->mmap.start + event->mmap.len); /* diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index e32628cd20a7..ee71efb9db62 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -261,6 +261,22 @@ bool __map__is_extra_kernel_map(const struct map *map) return kmap && kmap->name[0]; } +bool __map__is_bpf_prog(const struct map *map) +{ + const char *name; + + if (map->dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO) + return true; + + /* + * If PERF_RECORD_BPF_EVENT is not included, the dso will not have + * type of DSO_BINARY_TYPE__BPF_PROG_INFO. In such cases, we can + * guess the type based on name. + */ + name = map->dso->short_name; + return name && (strstr(name, "bpf_prog_") == name); +} + bool map__has_symbols(const struct map *map) { return dso__has_symbols(map->dso); @@ -910,10 +926,8 @@ static void __maps__insert_name(struct maps *maps, struct map *map) rc = strcmp(m->dso->short_name, map->dso->short_name); if (rc < 0) p = &(*p)->rb_left; - else if (rc > 0) - p = &(*p)->rb_right; else - return; + p = &(*p)->rb_right; } rb_link_node(&map->rb_node_name, parent, p); rb_insert_color(&map->rb_node_name, &maps->names); diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 0e20749f2c55..dc93787c74f0 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -159,10 +159,12 @@ int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name, bool __map__is_kernel(const struct map *map); bool __map__is_extra_kernel_map(const struct map *map); +bool __map__is_bpf_prog(const struct map *map); static inline bool __map__is_kmodule(const struct map *map) { - return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map); + return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map) && + !__map__is_bpf_prog(map); } bool map__has_symbols(const struct map *map); diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 6199a3174ab9..e0429f4ef335 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -732,10 +732,20 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu) if (!is_arm_pmu_core(name)) { pname = pe->pmu ? pe->pmu : "cpu"; + + /* + * uncore alias may be from different PMU + * with common prefix + */ + if (pmu_is_uncore(name) && + !strncmp(pname, name, strlen(pname))) + goto new_alias; + if (strcmp(pname, name)) continue; } +new_alias: /* need type casts to override 'const' */ __perf_pmu__new_alias(head, NULL, (char *)pe->name, (char *)pe->desc, (char *)pe->event, diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index c3fad065c89c..c7727be9719f 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -44,6 +44,7 @@ #include <cpuid.h> #include <linux/capability.h> #include <errno.h> +#include <math.h> char *proc_stat = "/proc/stat"; FILE *outf; @@ -63,7 +64,6 @@ unsigned int dump_only; unsigned int do_snb_cstates; unsigned int do_knl_cstates; unsigned int do_slm_cstates; -unsigned int do_cnl_cstates; unsigned int use_c1_residency_msr; unsigned int has_aperf; unsigned int has_epb; @@ -141,9 +141,21 @@ unsigned int first_counter_read = 1; #define RAPL_CORES_ENERGY_STATUS (1 << 9) /* 0x639 MSR_PP0_ENERGY_STATUS */ +#define RAPL_PER_CORE_ENERGY (1 << 10) + /* Indicates cores energy collection is per-core, + * not per-package. */ +#define RAPL_AMD_F17H (1 << 11) + /* 0xc0010299 MSR_RAPL_PWR_UNIT */ + /* 0xc001029a MSR_CORE_ENERGY_STAT */ + /* 0xc001029b MSR_PKG_ENERGY_STAT */ #define RAPL_CORES (RAPL_CORES_ENERGY_STATUS | RAPL_CORES_POWER_LIMIT) #define TJMAX_DEFAULT 100 +/* MSRs that are not yet in the kernel-provided header. */ +#define MSR_RAPL_PWR_UNIT 0xc0010299 +#define MSR_CORE_ENERGY_STAT 0xc001029a +#define MSR_PKG_ENERGY_STAT 0xc001029b + #define MAX(a, b) ((a) > (b) ? (a) : (b)) /* @@ -187,6 +199,7 @@ struct core_data { unsigned long long c7; unsigned long long mc6_us; /* duplicate as per-core for now, even though per module */ unsigned int core_temp_c; + unsigned int core_energy; /* MSR_CORE_ENERGY_STAT */ unsigned int core_id; unsigned long long counter[MAX_ADDED_COUNTERS]; } *core_even, *core_odd; @@ -273,6 +286,7 @@ struct system_summary { struct cpu_topology { int physical_package_id; + int die_id; int logical_cpu_id; int physical_node_id; int logical_node_id; /* 0-based count within the package */ @@ -283,6 +297,7 @@ struct cpu_topology { struct topo_params { int num_packages; + int num_die; int num_cpus; int num_cores; int max_cpu_num; @@ -314,9 +329,8 @@ int for_all_cpus(int (func)(struct thread_data *, struct core_data *, struct pkg int retval, pkg_no, core_no, thread_no, node_no; for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) { - for (core_no = 0; core_no < topo.cores_per_node; ++core_no) { - for (node_no = 0; node_no < topo.nodes_per_pkg; - node_no++) { + for (node_no = 0; node_no < topo.nodes_per_pkg; node_no++) { + for (core_no = 0; core_no < topo.cores_per_node; ++core_no) { for (thread_no = 0; thread_no < topo.threads_per_core; ++thread_no) { struct thread_data *t; @@ -442,6 +456,7 @@ struct msr_counter bic[] = { { 0x0, "CPU" }, { 0x0, "APIC" }, { 0x0, "X2APIC" }, + { 0x0, "Die" }, }; #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter)) @@ -495,6 +510,7 @@ struct msr_counter bic[] = { #define BIC_CPU (1ULL << 47) #define BIC_APIC (1ULL << 48) #define BIC_X2APIC (1ULL << 49) +#define BIC_Die (1ULL << 50) #define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC) @@ -621,6 +637,8 @@ void print_header(char *delim) outp += sprintf(outp, "%sTime_Of_Day_Seconds", (printed++ ? delim : "")); if (DO_BIC(BIC_Package)) outp += sprintf(outp, "%sPackage", (printed++ ? delim : "")); + if (DO_BIC(BIC_Die)) + outp += sprintf(outp, "%sDie", (printed++ ? delim : "")); if (DO_BIC(BIC_Node)) outp += sprintf(outp, "%sNode", (printed++ ? delim : "")); if (DO_BIC(BIC_Core)) @@ -667,7 +685,7 @@ void print_header(char *delim) if (DO_BIC(BIC_CPU_c1)) outp += sprintf(outp, "%sCPU%%c1", (printed++ ? delim : "")); - if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates) + if (DO_BIC(BIC_CPU_c3)) outp += sprintf(outp, "%sCPU%%c3", (printed++ ? delim : "")); if (DO_BIC(BIC_CPU_c6)) outp += sprintf(outp, "%sCPU%%c6", (printed++ ? delim : "")); @@ -680,6 +698,14 @@ void print_header(char *delim) if (DO_BIC(BIC_CoreTmp)) outp += sprintf(outp, "%sCoreTmp", (printed++ ? delim : "")); + if (do_rapl && !rapl_joules) { + if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY)) + outp += sprintf(outp, "%sCorWatt", (printed++ ? delim : "")); + } else if (do_rapl && rapl_joules) { + if (DO_BIC(BIC_Cor_J) && (do_rapl & RAPL_PER_CORE_ENERGY)) + outp += sprintf(outp, "%sCor_J", (printed++ ? delim : "")); + } + for (mp = sys.cp; mp; mp = mp->next) { if (mp->format == FORMAT_RAW) { if (mp->width == 64) @@ -734,7 +760,7 @@ void print_header(char *delim) if (do_rapl && !rapl_joules) { if (DO_BIC(BIC_PkgWatt)) outp += sprintf(outp, "%sPkgWatt", (printed++ ? delim : "")); - if (DO_BIC(BIC_CorWatt)) + if (DO_BIC(BIC_CorWatt) && !(do_rapl & RAPL_PER_CORE_ENERGY)) outp += sprintf(outp, "%sCorWatt", (printed++ ? delim : "")); if (DO_BIC(BIC_GFXWatt)) outp += sprintf(outp, "%sGFXWatt", (printed++ ? delim : "")); @@ -747,7 +773,7 @@ void print_header(char *delim) } else if (do_rapl && rapl_joules) { if (DO_BIC(BIC_Pkg_J)) outp += sprintf(outp, "%sPkg_J", (printed++ ? delim : "")); - if (DO_BIC(BIC_Cor_J)) + if (DO_BIC(BIC_Cor_J) && !(do_rapl & RAPL_PER_CORE_ENERGY)) outp += sprintf(outp, "%sCor_J", (printed++ ? delim : "")); if (DO_BIC(BIC_GFX_J)) outp += sprintf(outp, "%sGFX_J", (printed++ ? delim : "")); @@ -808,6 +834,7 @@ int dump_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, "c6: %016llX\n", c->c6); outp += sprintf(outp, "c7: %016llX\n", c->c7); outp += sprintf(outp, "DTS: %dC\n", c->core_temp_c); + outp += sprintf(outp, "Joules: %0X\n", c->core_energy); for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { outp += sprintf(outp, "cADDED [%d] msr0x%x: %08llX\n", @@ -904,6 +931,8 @@ int format_counters(struct thread_data *t, struct core_data *c, if (t == &average.threads) { if (DO_BIC(BIC_Package)) outp += sprintf(outp, "%s-", (printed++ ? delim : "")); + if (DO_BIC(BIC_Die)) + outp += sprintf(outp, "%s-", (printed++ ? delim : "")); if (DO_BIC(BIC_Node)) outp += sprintf(outp, "%s-", (printed++ ? delim : "")); if (DO_BIC(BIC_Core)) @@ -921,6 +950,12 @@ int format_counters(struct thread_data *t, struct core_data *c, else outp += sprintf(outp, "%s-", (printed++ ? delim : "")); } + if (DO_BIC(BIC_Die)) { + if (c) + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), cpus[t->cpu_id].die_id); + else + outp += sprintf(outp, "%s-", (printed++ ? delim : "")); + } if (DO_BIC(BIC_Node)) { if (t) outp += sprintf(outp, "%s%d", @@ -1003,7 +1038,7 @@ int format_counters(struct thread_data *t, struct core_data *c, if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) goto done; - if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates) + if (DO_BIC(BIC_CPU_c3)) outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c3/tsc); if (DO_BIC(BIC_CPU_c6)) outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c6/tsc); @@ -1033,6 +1068,20 @@ int format_counters(struct thread_data *t, struct core_data *c, } } + /* + * If measurement interval exceeds minimum RAPL Joule Counter range, + * indicate that results are suspect by printing "**" in fraction place. + */ + if (interval_float < rapl_joule_counter_range) + fmt8 = "%s%.2f"; + else + fmt8 = "%6.0f**"; + + if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units / interval_float); + if (DO_BIC(BIC_Cor_J) && (do_rapl & RAPL_PER_CORE_ENERGY)) + outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units); + /* print per-package data only for 1st core in package */ if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) goto done; @@ -1085,18 +1134,9 @@ int format_counters(struct thread_data *t, struct core_data *c, if (DO_BIC(BIC_SYS_LPI)) outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->sys_lpi / 1000000.0 / interval_float); - /* - * If measurement interval exceeds minimum RAPL Joule Counter range, - * indicate that results are suspect by printing "**" in fraction place. - */ - if (interval_float < rapl_joule_counter_range) - fmt8 = "%s%.2f"; - else - fmt8 = "%6.0f**"; - if (DO_BIC(BIC_PkgWatt)) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units / interval_float); - if (DO_BIC(BIC_CorWatt)) + if (DO_BIC(BIC_CorWatt) && !(do_rapl & RAPL_PER_CORE_ENERGY)) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units / interval_float); if (DO_BIC(BIC_GFXWatt)) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units / interval_float); @@ -1104,7 +1144,7 @@ int format_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_dram * rapl_dram_energy_units / interval_float); if (DO_BIC(BIC_Pkg_J)) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units); - if (DO_BIC(BIC_Cor_J)) + if (DO_BIC(BIC_Cor_J) && !(do_rapl & RAPL_PER_CORE_ENERGY)) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units); if (DO_BIC(BIC_GFX_J)) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units); @@ -1249,6 +1289,8 @@ delta_core(struct core_data *new, struct core_data *old) old->core_temp_c = new->core_temp_c; old->mc6_us = new->mc6_us - old->mc6_us; + DELTA_WRAP32(new->core_energy, old->core_energy); + for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) old->counter[i] = new->counter[i]; @@ -1391,6 +1433,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data c->c7 = 0; c->mc6_us = 0; c->core_temp_c = 0; + c->core_energy = 0; p->pkg_wtd_core_c0 = 0; p->pkg_any_core_c0 = 0; @@ -1473,6 +1516,8 @@ int sum_counters(struct thread_data *t, struct core_data *c, average.cores.core_temp_c = MAX(average.cores.core_temp_c, c->core_temp_c); + average.cores.core_energy += c->core_energy; + for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) continue; @@ -1818,7 +1863,7 @@ retry: if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) goto done; - if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates) { + if (DO_BIC(BIC_CPU_c3)) { if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3)) return -6; } @@ -1845,6 +1890,12 @@ retry: c->core_temp_c = tcc_activation_temp - ((msr >> 16) & 0x7F); } + if (do_rapl & RAPL_AMD_F17H) { + if (get_msr(cpu, MSR_CORE_ENERGY_STAT, &msr)) + return -14; + c->core_energy = msr & 0xFFFFFFFF; + } + for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { if (get_mp(cpu, mp, &c->counter[i])) return -10; @@ -1934,6 +1985,11 @@ retry: return -16; p->rapl_dram_perf_status = msr & 0xFFFFFFFF; } + if (do_rapl & RAPL_AMD_F17H) { + if (get_msr(cpu, MSR_PKG_ENERGY_STAT, &msr)) + return -13; + p->energy_pkg = msr & 0xFFFFFFFF; + } if (DO_BIC(BIC_PkgTmp)) { if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr)) return -17; @@ -2456,6 +2512,8 @@ void free_all_buffers(void) /* * Parse a file containing a single int. + * Return 0 if file can not be opened + * Exit if file can be opened, but can not be parsed */ int parse_int_file(const char *fmt, ...) { @@ -2467,7 +2525,9 @@ int parse_int_file(const char *fmt, ...) va_start(args, fmt); vsnprintf(path, sizeof(path), fmt, args); va_end(args); - filep = fopen_or_die(path, "r"); + filep = fopen(path, "r"); + if (!filep) + return 0; if (fscanf(filep, "%d", &value) != 1) err(1, "%s: failed to parse number from file", path); fclose(filep); @@ -2488,6 +2548,11 @@ int get_physical_package_id(int cpu) return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/physical_package_id", cpu); } +int get_die_id(int cpu) +{ + return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/die_id", cpu); +} + int get_core_id(int cpu) { return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/core_id", cpu); @@ -2578,7 +2643,8 @@ int get_thread_siblings(struct cpu_topology *thiscpu) filep = fopen_or_die(path, "r"); do { offset -= BITMASK_SIZE; - fscanf(filep, "%lx%c", &map, &character); + if (fscanf(filep, "%lx%c", &map, &character) != 2) + err(1, "%s: failed to parse file", path); for (shift = 0; shift < BITMASK_SIZE; shift++) { if ((map >> shift) & 0x1) { so = shift + offset; @@ -2855,8 +2921,11 @@ int snapshot_cpu_lpi_us(void) fp = fopen_or_die("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", "r"); retval = fscanf(fp, "%lld", &cpuidle_cur_cpu_lpi_us); - if (retval != 1) - err(1, "CPU LPI"); + if (retval != 1) { + fprintf(stderr, "Disabling Low Power Idle CPU output\n"); + BIC_NOT_PRESENT(BIC_CPU_LPI); + return -1; + } fclose(fp); @@ -2878,9 +2947,11 @@ int snapshot_sys_lpi_us(void) fp = fopen_or_die("/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us", "r"); retval = fscanf(fp, "%lld", &cpuidle_cur_sys_lpi_us); - if (retval != 1) - err(1, "SYS LPI"); - + if (retval != 1) { + fprintf(stderr, "Disabling Low Power Idle System output\n"); + BIC_NOT_PRESENT(BIC_SYS_LPI); + return -1; + } fclose(fp); return 0; @@ -3410,14 +3481,14 @@ dump_sysfs_cstate_config(void) input = fopen(path, "r"); if (input == NULL) continue; - fgets(name_buf, sizeof(name_buf), input); + if (!fgets(name_buf, sizeof(name_buf), input)) + err(1, "%s: failed to read file", path); /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */ sp = strchr(name_buf, '-'); if (!sp) sp = strchrnul(name_buf, '\n'); *sp = '\0'; - fclose(input); sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/desc", @@ -3425,7 +3496,8 @@ dump_sysfs_cstate_config(void) input = fopen(path, "r"); if (input == NULL) continue; - fgets(desc, sizeof(desc), input); + if (!fgets(desc, sizeof(desc), input)) + err(1, "%s: failed to read file", path); fprintf(outf, "cpu%d: %s: %s", base_cpu, name_buf, desc); fclose(input); @@ -3444,20 +3516,22 @@ dump_sysfs_pstate_config(void) base_cpu); input = fopen(path, "r"); if (input == NULL) { - fprintf(stderr, "NSFOD %s\n", path); + fprintf(outf, "NSFOD %s\n", path); return; } - fgets(driver_buf, sizeof(driver_buf), input); + if (!fgets(driver_buf, sizeof(driver_buf), input)) + err(1, "%s: failed to read file", path); fclose(input); sprintf(path, "/sys/devices/system/cpu/cpu%d/cpufreq/scaling_governor", base_cpu); input = fopen(path, "r"); if (input == NULL) { - fprintf(stderr, "NSFOD %s\n", path); + fprintf(outf, "NSFOD %s\n", path); return; } - fgets(governor_buf, sizeof(governor_buf), input); + if (!fgets(governor_buf, sizeof(governor_buf), input)) + err(1, "%s: failed to read file", path); fclose(input); fprintf(outf, "cpu%d: cpufreq driver: %s", base_cpu, driver_buf); @@ -3466,7 +3540,8 @@ dump_sysfs_pstate_config(void) sprintf(path, "/sys/devices/system/cpu/cpufreq/boost"); input = fopen(path, "r"); if (input != NULL) { - fscanf(input, "%d", &turbo); + if (fscanf(input, "%d", &turbo) != 1) + err(1, "%s: failed to parse number from file", path); fprintf(outf, "cpufreq boost: %d\n", turbo); fclose(input); } @@ -3474,7 +3549,8 @@ dump_sysfs_pstate_config(void) sprintf(path, "/sys/devices/system/cpu/intel_pstate/no_turbo"); input = fopen(path, "r"); if (input != NULL) { - fscanf(input, "%d", &turbo); + if (fscanf(input, "%d", &turbo) != 1) + err(1, "%s: failed to parse number from file", path); fprintf(outf, "cpufreq intel_pstate no_turbo: %d\n", turbo); fclose(input); } @@ -3718,7 +3794,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data #define RAPL_POWER_GRANULARITY 0x7FFF /* 15 bit power granularity */ #define RAPL_TIME_GRANULARITY 0x3F /* 6 bit time granularity */ -double get_tdp(unsigned int model) +double get_tdp_intel(unsigned int model) { unsigned long long msr; @@ -3735,6 +3811,16 @@ double get_tdp(unsigned int model) } } +double get_tdp_amd(unsigned int family) +{ + switch (family) { + case 0x17: + default: + /* This is the max stock TDP of HEDT/Server Fam17h chips */ + return 250.0; + } +} + /* * rapl_dram_energy_units_probe() * Energy units are either hard-coded, or come from RAPL Energy Unit MSR. @@ -3754,21 +3840,12 @@ rapl_dram_energy_units_probe(int model, double rapl_energy_units) } } - -/* - * rapl_probe() - * - * sets do_rapl, rapl_power_units, rapl_energy_units, rapl_time_units - */ -void rapl_probe(unsigned int family, unsigned int model) +void rapl_probe_intel(unsigned int family, unsigned int model) { unsigned long long msr; unsigned int time_unit; double tdp; - if (!genuine_intel) - return; - if (family != 6) return; @@ -3892,13 +3969,69 @@ void rapl_probe(unsigned int family, unsigned int model) rapl_time_units = 1.0 / (1 << (time_unit)); - tdp = get_tdp(model); + tdp = get_tdp_intel(model); rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp; if (!quiet) fprintf(outf, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp); +} - return; +void rapl_probe_amd(unsigned int family, unsigned int model) +{ + unsigned long long msr; + unsigned int eax, ebx, ecx, edx; + unsigned int has_rapl = 0; + double tdp; + + if (max_extended_level >= 0x80000007) { + __cpuid(0x80000007, eax, ebx, ecx, edx); + /* RAPL (Fam 17h) */ + has_rapl = edx & (1 << 14); + } + + if (!has_rapl) + return; + + switch (family) { + case 0x17: /* Zen, Zen+ */ + do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY; + if (rapl_joules) { + BIC_PRESENT(BIC_Pkg_J); + BIC_PRESENT(BIC_Cor_J); + } else { + BIC_PRESENT(BIC_PkgWatt); + BIC_PRESENT(BIC_CorWatt); + } + break; + default: + return; + } + + if (get_msr(base_cpu, MSR_RAPL_PWR_UNIT, &msr)) + return; + + rapl_time_units = ldexp(1.0, -(msr >> 16 & 0xf)); + rapl_energy_units = ldexp(1.0, -(msr >> 8 & 0x1f)); + rapl_power_units = ldexp(1.0, -(msr & 0xf)); + + tdp = get_tdp_amd(model); + + rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp; + if (!quiet) + fprintf(outf, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp); +} + +/* + * rapl_probe() + * + * sets do_rapl, rapl_power_units, rapl_energy_units, rapl_time_units + */ +void rapl_probe(unsigned int family, unsigned int model) +{ + if (genuine_intel) + rapl_probe_intel(family, model); + if (authentic_amd) + rapl_probe_amd(family, model); } void perf_limit_reasons_probe(unsigned int family, unsigned int model) @@ -4003,6 +4136,7 @@ void print_power_limit_msr(int cpu, unsigned long long msr, char *label) int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) { unsigned long long msr; + const char *msr_name; int cpu; if (!do_rapl) @@ -4018,10 +4152,17 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) return -1; } - if (get_msr(cpu, MSR_RAPL_POWER_UNIT, &msr)) - return -1; + if (do_rapl & RAPL_AMD_F17H) { + msr_name = "MSR_RAPL_PWR_UNIT"; + if (get_msr(cpu, MSR_RAPL_PWR_UNIT, &msr)) + return -1; + } else { + msr_name = "MSR_RAPL_POWER_UNIT"; + if (get_msr(cpu, MSR_RAPL_POWER_UNIT, &msr)) + return -1; + } - fprintf(outf, "cpu%d: MSR_RAPL_POWER_UNIT: 0x%08llx (%f Watts, %f Joules, %f sec.)\n", cpu, msr, + fprintf(outf, "cpu%d: %s: 0x%08llx (%f Watts, %f Joules, %f sec.)\n", cpu, msr_name, msr, rapl_power_units, rapl_energy_units, rapl_time_units); if (do_rapl & RAPL_PKG_POWER_INFO) { @@ -4451,6 +4592,9 @@ unsigned int intel_model_duplicates(unsigned int model) case INTEL_FAM6_KABYLAKE_MOBILE: case INTEL_FAM6_KABYLAKE_DESKTOP: return INTEL_FAM6_SKYLAKE_MOBILE; + + case INTEL_FAM6_ICELAKE_MOBILE: + return INTEL_FAM6_CANNONLAKE_MOBILE; } return model; } @@ -4702,7 +4846,9 @@ void process_cpuid() } do_slm_cstates = is_slm(family, model); do_knl_cstates = is_knl(family, model); - do_cnl_cstates = is_cnl(family, model); + + if (do_slm_cstates || do_knl_cstates || is_cnl(family, model)) + BIC_NOT_PRESENT(BIC_CPU_c3); if (!quiet) decode_misc_pwr_mgmt_msr(); @@ -4769,6 +4915,7 @@ void topology_probe() int i; int max_core_id = 0; int max_package_id = 0; + int max_die_id = 0; int max_siblings = 0; /* Initialize num_cpus, max_cpu_num */ @@ -4835,6 +4982,11 @@ void topology_probe() if (cpus[i].physical_package_id > max_package_id) max_package_id = cpus[i].physical_package_id; + /* get die information */ + cpus[i].die_id = get_die_id(i); + if (cpus[i].die_id > max_die_id) + max_die_id = cpus[i].die_id; + /* get numa node information */ cpus[i].physical_node_id = get_physical_node_id(&cpus[i]); if (cpus[i].physical_node_id > topo.max_node_num) @@ -4860,6 +5012,13 @@ void topology_probe() if (!summary_only && topo.cores_per_node > 1) BIC_PRESENT(BIC_Core); + topo.num_die = max_die_id + 1; + if (debug > 1) + fprintf(outf, "max_die_id %d, sizing for %d die\n", + max_die_id, topo.num_die); + if (!summary_only && topo.num_die > 1) + BIC_PRESENT(BIC_Die); + topo.num_packages = max_package_id + 1; if (debug > 1) fprintf(outf, "max_package_id %d, sizing for %d packages\n", @@ -4884,8 +5043,8 @@ void topology_probe() if (cpu_is_not_present(i)) continue; fprintf(outf, - "cpu %d pkg %d node %d lnode %d core %d thread %d\n", - i, cpus[i].physical_package_id, + "cpu %d pkg %d die %d node %d lnode %d core %d thread %d\n", + i, cpus[i].physical_package_id, cpus[i].die_id, cpus[i].physical_node_id, cpus[i].logical_node_id, cpus[i].physical_core_id, @@ -5122,7 +5281,7 @@ int get_and_dump_counters(void) } void print_version() { - fprintf(outf, "turbostat version 18.07.27" + fprintf(outf, "turbostat version 19.03.20" " - Len Brown <lenb@kernel.org>\n"); } @@ -5319,7 +5478,8 @@ void probe_sysfs(void) input = fopen(path, "r"); if (input == NULL) continue; - fgets(name_buf, sizeof(name_buf), input); + if (!fgets(name_buf, sizeof(name_buf), input)) + err(1, "%s: failed to read file", path); /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */ sp = strchr(name_buf, '-'); @@ -5346,7 +5506,8 @@ void probe_sysfs(void) input = fopen(path, "r"); if (input == NULL) continue; - fgets(name_buf, sizeof(name_buf), input); + if (!fgets(name_buf, sizeof(name_buf), input)) + err(1, "%s: failed to read file", path); /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */ sp = strchr(name_buf, '-'); if (!sp) diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index b579f962451d..85ffdcfa596b 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -146,6 +146,7 @@ static int dimm_fail_cmd_code[ARRAY_SIZE(handle)]; struct nfit_test_sec { u8 state; u8 ext_state; + u8 old_state; u8 passphrase[32]; u8 master_passphrase[32]; u64 overwrite_end_time; @@ -225,6 +226,8 @@ static struct workqueue_struct *nfit_wq; static struct gen_pool *nfit_pool; +static const char zero_key[NVDIMM_PASSPHRASE_LEN]; + static struct nfit_test *to_nfit_test(struct device *dev) { struct platform_device *pdev = to_platform_device(dev); @@ -1059,8 +1062,7 @@ static int nd_intel_test_cmd_secure_erase(struct nfit_test *t, struct device *dev = &t->pdev.dev; struct nfit_test_sec *sec = &dimm_sec_info[dimm]; - if (!(sec->state & ND_INTEL_SEC_STATE_ENABLED) || - (sec->state & ND_INTEL_SEC_STATE_FROZEN)) { + if (sec->state & ND_INTEL_SEC_STATE_FROZEN) { nd_cmd->status = ND_INTEL_STATUS_INVALID_STATE; dev_dbg(dev, "secure erase: wrong security state\n"); } else if (memcmp(nd_cmd->passphrase, sec->passphrase, @@ -1068,6 +1070,12 @@ static int nd_intel_test_cmd_secure_erase(struct nfit_test *t, nd_cmd->status = ND_INTEL_STATUS_INVALID_PASS; dev_dbg(dev, "secure erase: wrong passphrase\n"); } else { + if (!(sec->state & ND_INTEL_SEC_STATE_ENABLED) + && (memcmp(nd_cmd->passphrase, zero_key, + ND_INTEL_PASSPHRASE_SIZE) != 0)) { + dev_dbg(dev, "invalid zero key\n"); + return 0; + } memset(sec->passphrase, 0, ND_INTEL_PASSPHRASE_SIZE); memset(sec->master_passphrase, 0, ND_INTEL_PASSPHRASE_SIZE); sec->state = 0; @@ -1093,7 +1101,7 @@ static int nd_intel_test_cmd_overwrite(struct nfit_test *t, return 0; } - memset(sec->passphrase, 0, ND_INTEL_PASSPHRASE_SIZE); + sec->old_state = sec->state; sec->state = ND_INTEL_SEC_STATE_OVERWRITE; dev_dbg(dev, "overwrite progressing.\n"); sec->overwrite_end_time = get_jiffies_64() + 5 * HZ; @@ -1115,7 +1123,8 @@ static int nd_intel_test_cmd_query_overwrite(struct nfit_test *t, if (time_is_before_jiffies64(sec->overwrite_end_time)) { sec->overwrite_end_time = 0; - sec->state = 0; + sec->state = sec->old_state; + sec->old_state = 0; sec->ext_state = ND_INTEL_SEC_ESTATE_ENABLED; dev_dbg(dev, "overwrite is complete\n"); } else diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index c9433a496d54..c81fc350f7ad 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -180,6 +180,8 @@ static struct bpf_sock *(*bpf_sk_fullsock)(struct bpf_sock *sk) = (void *) BPF_FUNC_sk_fullsock; static struct bpf_tcp_sock *(*bpf_tcp_sock)(struct bpf_sock *sk) = (void *) BPF_FUNC_tcp_sock; +static struct bpf_sock *(*bpf_get_listener_sock)(struct bpf_sock *sk) = + (void *) BPF_FUNC_get_listener_sock; static int (*bpf_skb_ecn_set_ce)(void *ctx) = (void *) BPF_FUNC_skb_ecn_set_ce; diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index bcbd928c96ab..fc818bc1d729 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -39,6 +39,58 @@ static struct bpf_flow_keys pkt_v6_flow_keys = { .n_proto = __bpf_constant_htons(ETH_P_IPV6), }; +#define VLAN_HLEN 4 + +static struct { + struct ethhdr eth; + __u16 vlan_tci; + __u16 vlan_proto; + struct iphdr iph; + struct tcphdr tcp; +} __packed pkt_vlan_v4 = { + .eth.h_proto = __bpf_constant_htons(ETH_P_8021Q), + .vlan_proto = __bpf_constant_htons(ETH_P_IP), + .iph.ihl = 5, + .iph.protocol = IPPROTO_TCP, + .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), + .tcp.urg_ptr = 123, + .tcp.doff = 5, +}; + +static struct bpf_flow_keys pkt_vlan_v4_flow_keys = { + .nhoff = VLAN_HLEN, + .thoff = VLAN_HLEN + sizeof(struct iphdr), + .addr_proto = ETH_P_IP, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IP), +}; + +static struct { + struct ethhdr eth; + __u16 vlan_tci; + __u16 vlan_proto; + __u16 vlan_tci2; + __u16 vlan_proto2; + struct ipv6hdr iph; + struct tcphdr tcp; +} __packed pkt_vlan_v6 = { + .eth.h_proto = __bpf_constant_htons(ETH_P_8021AD), + .vlan_proto = __bpf_constant_htons(ETH_P_8021Q), + .vlan_proto2 = __bpf_constant_htons(ETH_P_IPV6), + .iph.nexthdr = IPPROTO_TCP, + .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES), + .tcp.urg_ptr = 123, + .tcp.doff = 5, +}; + +static struct bpf_flow_keys pkt_vlan_v6_flow_keys = { + .nhoff = VLAN_HLEN * 2, + .thoff = VLAN_HLEN * 2 + sizeof(struct ipv6hdr), + .addr_proto = ETH_P_IPV6, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IPV6), +}; + void test_flow_dissector(void) { struct bpf_flow_keys flow_keys; @@ -68,5 +120,21 @@ void test_flow_dissector(void) err, errno, retval, duration, size, sizeof(flow_keys)); CHECK_FLOW_KEYS("ipv6_flow_keys", flow_keys, pkt_v6_flow_keys); + err = bpf_prog_test_run(prog_fd, 10, &pkt_vlan_v4, sizeof(pkt_vlan_v4), + &flow_keys, &size, &retval, &duration); + CHECK(size != sizeof(flow_keys) || err || retval != 1, "vlan_ipv4", + "err %d errno %d retval %d duration %d size %u/%lu\n", + err, errno, retval, duration, size, sizeof(flow_keys)); + CHECK_FLOW_KEYS("vlan_ipv4_flow_keys", flow_keys, + pkt_vlan_v4_flow_keys); + + err = bpf_prog_test_run(prog_fd, 10, &pkt_vlan_v6, sizeof(pkt_vlan_v6), + &flow_keys, &size, &retval, &duration); + CHECK(size != sizeof(flow_keys) || err || retval != 1, "vlan_ipv6", + "err %d errno %d retval %d duration %d size %u/%lu\n", + err, errno, retval, duration, size, sizeof(flow_keys)); + CHECK_FLOW_KEYS("vlan_ipv6_flow_keys", flow_keys, + pkt_vlan_v6_flow_keys); + bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/map_lock.c b/tools/testing/selftests/bpf/prog_tests/map_lock.c index 90f8a206340a..ee99368c595c 100644 --- a/tools/testing/selftests/bpf/prog_tests/map_lock.c +++ b/tools/testing/selftests/bpf/prog_tests/map_lock.c @@ -37,7 +37,7 @@ void test_map_lock(void) const char *file = "./test_map_lock.o"; int prog_fd, map_fd[2], vars[17] = {}; pthread_t thread_id[6]; - struct bpf_object *obj; + struct bpf_object *obj = NULL; int err = 0, key = 0, i; void *ret; diff --git a/tools/testing/selftests/bpf/prog_tests/spinlock.c b/tools/testing/selftests/bpf/prog_tests/spinlock.c index 9a573a9675d7..114ebe6a438e 100644 --- a/tools/testing/selftests/bpf/prog_tests/spinlock.c +++ b/tools/testing/selftests/bpf/prog_tests/spinlock.c @@ -5,7 +5,7 @@ void test_spinlock(void) { const char *file = "./test_spin_lock.o"; pthread_t thread_id[4]; - struct bpf_object *obj; + struct bpf_object *obj = NULL; int prog_fd; int err = 0, i; void *ret; diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c index 284660f5aa95..75b17cada539 100644 --- a/tools/testing/selftests/bpf/progs/bpf_flow.c +++ b/tools/testing/selftests/bpf/progs/bpf_flow.c @@ -92,7 +92,6 @@ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto) { struct bpf_flow_keys *keys = skb->flow_keys; - keys->n_proto = proto; switch (proto) { case bpf_htons(ETH_P_IP): bpf_tail_call(skb, &jmp_table, IP); @@ -119,10 +118,9 @@ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto) SEC("flow_dissector") int _dissect(struct __sk_buff *skb) { - if (!skb->vlan_present) - return parse_eth_proto(skb, skb->protocol); - else - return parse_eth_proto(skb, skb->vlan_proto); + struct bpf_flow_keys *keys = skb->flow_keys; + + return parse_eth_proto(skb, keys->n_proto); } /* Parses on IPPROTO_* */ @@ -336,15 +334,9 @@ PROG(VLAN)(struct __sk_buff *skb) { struct bpf_flow_keys *keys = skb->flow_keys; struct vlan_hdr *vlan, _vlan; - __be16 proto; - - /* Peek back to see if single or double-tagging */ - if (bpf_skb_load_bytes(skb, keys->thoff - sizeof(proto), &proto, - sizeof(proto))) - return BPF_DROP; /* Account for double-tagging */ - if (proto == bpf_htons(ETH_P_8021AD)) { + if (keys->n_proto == bpf_htons(ETH_P_8021AD)) { vlan = bpf_flow_dissect_get_header(skb, sizeof(*vlan), &_vlan); if (!vlan) return BPF_DROP; @@ -352,6 +344,7 @@ PROG(VLAN)(struct __sk_buff *skb) if (vlan->h_vlan_encapsulated_proto != bpf_htons(ETH_P_8021Q)) return BPF_DROP; + keys->nhoff += sizeof(*vlan); keys->thoff += sizeof(*vlan); } @@ -359,12 +352,14 @@ PROG(VLAN)(struct __sk_buff *skb) if (!vlan) return BPF_DROP; + keys->nhoff += sizeof(*vlan); keys->thoff += sizeof(*vlan); /* Only allow 8021AD + 8021Q double tagging and no triple tagging.*/ if (vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021AD) || vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021Q)) return BPF_DROP; + keys->n_proto = vlan->h_vlan_encapsulated_proto; return parse_eth_proto(skb, vlan->h_vlan_encapsulated_proto); } diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c index de1a43e8f610..37328f148538 100644 --- a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c +++ b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c @@ -8,38 +8,51 @@ #include "bpf_helpers.h" #include "bpf_endian.h" -enum bpf_array_idx { - SRV_IDX, - CLI_IDX, - __NR_BPF_ARRAY_IDX, +enum bpf_addr_array_idx { + ADDR_SRV_IDX, + ADDR_CLI_IDX, + __NR_BPF_ADDR_ARRAY_IDX, +}; + +enum bpf_result_array_idx { + EGRESS_SRV_IDX, + EGRESS_CLI_IDX, + INGRESS_LISTEN_IDX, + __NR_BPF_RESULT_ARRAY_IDX, +}; + +enum bpf_linum_array_idx { + EGRESS_LINUM_IDX, + INGRESS_LINUM_IDX, + __NR_BPF_LINUM_ARRAY_IDX, }; struct bpf_map_def SEC("maps") addr_map = { .type = BPF_MAP_TYPE_ARRAY, .key_size = sizeof(__u32), .value_size = sizeof(struct sockaddr_in6), - .max_entries = __NR_BPF_ARRAY_IDX, + .max_entries = __NR_BPF_ADDR_ARRAY_IDX, }; struct bpf_map_def SEC("maps") sock_result_map = { .type = BPF_MAP_TYPE_ARRAY, .key_size = sizeof(__u32), .value_size = sizeof(struct bpf_sock), - .max_entries = __NR_BPF_ARRAY_IDX, + .max_entries = __NR_BPF_RESULT_ARRAY_IDX, }; struct bpf_map_def SEC("maps") tcp_sock_result_map = { .type = BPF_MAP_TYPE_ARRAY, .key_size = sizeof(__u32), .value_size = sizeof(struct bpf_tcp_sock), - .max_entries = __NR_BPF_ARRAY_IDX, + .max_entries = __NR_BPF_RESULT_ARRAY_IDX, }; struct bpf_map_def SEC("maps") linum_map = { .type = BPF_MAP_TYPE_ARRAY, .key_size = sizeof(__u32), .value_size = sizeof(__u32), - .max_entries = 1, + .max_entries = __NR_BPF_LINUM_ARRAY_IDX, }; static bool is_loopback6(__u32 *a6) @@ -100,18 +113,20 @@ static void tpcpy(struct bpf_tcp_sock *dst, #define RETURN { \ linum = __LINE__; \ - bpf_map_update_elem(&linum_map, &idx0, &linum, 0); \ + bpf_map_update_elem(&linum_map, &linum_idx, &linum, 0); \ return 1; \ } SEC("cgroup_skb/egress") -int read_sock_fields(struct __sk_buff *skb) +int egress_read_sock_fields(struct __sk_buff *skb) { - __u32 srv_idx = SRV_IDX, cli_idx = CLI_IDX, idx; + __u32 srv_idx = ADDR_SRV_IDX, cli_idx = ADDR_CLI_IDX, result_idx; struct sockaddr_in6 *srv_sa6, *cli_sa6; struct bpf_tcp_sock *tp, *tp_ret; struct bpf_sock *sk, *sk_ret; - __u32 linum, idx0 = 0; + __u32 linum, linum_idx; + + linum_idx = EGRESS_LINUM_IDX; sk = skb->sk; if (!sk || sk->state == 10) @@ -132,14 +147,55 @@ int read_sock_fields(struct __sk_buff *skb) RETURN; if (sk->src_port == bpf_ntohs(srv_sa6->sin6_port)) - idx = srv_idx; + result_idx = EGRESS_SRV_IDX; else if (sk->src_port == bpf_ntohs(cli_sa6->sin6_port)) - idx = cli_idx; + result_idx = EGRESS_CLI_IDX; else RETURN; - sk_ret = bpf_map_lookup_elem(&sock_result_map, &idx); - tp_ret = bpf_map_lookup_elem(&tcp_sock_result_map, &idx); + sk_ret = bpf_map_lookup_elem(&sock_result_map, &result_idx); + tp_ret = bpf_map_lookup_elem(&tcp_sock_result_map, &result_idx); + if (!sk_ret || !tp_ret) + RETURN; + + skcpy(sk_ret, sk); + tpcpy(tp_ret, tp); + + RETURN; +} + +SEC("cgroup_skb/ingress") +int ingress_read_sock_fields(struct __sk_buff *skb) +{ + __u32 srv_idx = ADDR_SRV_IDX, result_idx = INGRESS_LISTEN_IDX; + struct bpf_tcp_sock *tp, *tp_ret; + struct bpf_sock *sk, *sk_ret; + struct sockaddr_in6 *srv_sa6; + __u32 linum, linum_idx; + + linum_idx = INGRESS_LINUM_IDX; + + sk = skb->sk; + if (!sk || sk->family != AF_INET6 || !is_loopback6(sk->src_ip6)) + RETURN; + + srv_sa6 = bpf_map_lookup_elem(&addr_map, &srv_idx); + if (!srv_sa6 || sk->src_port != bpf_ntohs(srv_sa6->sin6_port)) + RETURN; + + if (sk->state != 10 && sk->state != 12) + RETURN; + + sk = bpf_get_listener_sock(sk); + if (!sk) + RETURN; + + tp = bpf_tcp_sock(sk); + if (!tp) + RETURN; + + sk_ret = bpf_map_lookup_elem(&sock_result_map, &result_idx); + tp_ret = bpf_map_lookup_elem(&tcp_sock_result_map, &result_idx); if (!sk_ret || !tp_ret) RETURN; diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index 38797aa627a7..ec5794e4205b 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -5777,6 +5777,53 @@ const struct btf_dedup_test dedup_tests[] = { }, }, { + .descr = "dedup: void equiv check", + /* + * // CU 1: + * struct s { + * struct {} *x; + * }; + * // CU 2: + * struct s { + * int *x; + * }; + */ + .input = { + .raw_types = { + /* CU 1 */ + BTF_STRUCT_ENC(0, 0, 1), /* [1] struct {} */ + BTF_PTR_ENC(1), /* [2] ptr -> [1] */ + BTF_STRUCT_ENC(NAME_NTH(1), 1, 8), /* [3] struct s */ + BTF_MEMBER_ENC(NAME_NTH(2), 2, 0), + /* CU 2 */ + BTF_PTR_ENC(0), /* [4] ptr -> void */ + BTF_STRUCT_ENC(NAME_NTH(1), 1, 8), /* [5] struct s */ + BTF_MEMBER_ENC(NAME_NTH(2), 4, 0), + BTF_END_RAW, + }, + BTF_STR_SEC("\0s\0x"), + }, + .expect = { + .raw_types = { + /* CU 1 */ + BTF_STRUCT_ENC(0, 0, 1), /* [1] struct {} */ + BTF_PTR_ENC(1), /* [2] ptr -> [1] */ + BTF_STRUCT_ENC(NAME_NTH(1), 1, 8), /* [3] struct s */ + BTF_MEMBER_ENC(NAME_NTH(2), 2, 0), + /* CU 2 */ + BTF_PTR_ENC(0), /* [4] ptr -> void */ + BTF_STRUCT_ENC(NAME_NTH(1), 1, 8), /* [5] struct s */ + BTF_MEMBER_ENC(NAME_NTH(2), 4, 0), + BTF_END_RAW, + }, + BTF_STR_SEC("\0s\0x"), + }, + .opts = { + .dont_resolve_fwds = false, + .dedup_table_size = 1, /* force hash collisions */ + }, +}, +{ .descr = "dedup: all possible kinds (no duplicates)", .input = { .raw_types = { @@ -5874,6 +5921,50 @@ const struct btf_dedup_test dedup_tests[] = { .dont_resolve_fwds = false, }, }, +{ + .descr = "dedup: enum fwd resolution", + .input = { + .raw_types = { + /* [1] fwd enum 'e1' before full enum */ + BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 0), 4), + /* [2] full enum 'e1' after fwd */ + BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4), + BTF_ENUM_ENC(NAME_NTH(2), 123), + /* [3] full enum 'e2' before fwd */ + BTF_TYPE_ENC(NAME_NTH(3), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4), + BTF_ENUM_ENC(NAME_NTH(4), 456), + /* [4] fwd enum 'e2' after full enum */ + BTF_TYPE_ENC(NAME_NTH(3), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 0), 4), + /* [5] incompatible fwd enum with different size */ + BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 0), 1), + /* [6] incompatible full enum with different value */ + BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4), + BTF_ENUM_ENC(NAME_NTH(2), 321), + BTF_END_RAW, + }, + BTF_STR_SEC("\0e1\0e1_val\0e2\0e2_val"), + }, + .expect = { + .raw_types = { + /* [1] full enum 'e1' */ + BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4), + BTF_ENUM_ENC(NAME_NTH(2), 123), + /* [2] full enum 'e2' */ + BTF_TYPE_ENC(NAME_NTH(3), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4), + BTF_ENUM_ENC(NAME_NTH(4), 456), + /* [3] incompatible fwd enum with different size */ + BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 0), 1), + /* [4] incompatible full enum with different value */ + BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4), + BTF_ENUM_ENC(NAME_NTH(2), 321), + BTF_END_RAW, + }, + BTF_STR_SEC("\0e1\0e1_val\0e2\0e2_val"), + }, + .opts = { + .dont_resolve_fwds = false, + }, +}, }; diff --git a/tools/testing/selftests/bpf/test_sock_fields.c b/tools/testing/selftests/bpf/test_sock_fields.c index bc8943938bf5..dcae7f664dce 100644 --- a/tools/testing/selftests/bpf/test_sock_fields.c +++ b/tools/testing/selftests/bpf/test_sock_fields.c @@ -16,10 +16,23 @@ #include "cgroup_helpers.h" #include "bpf_rlimit.h" -enum bpf_array_idx { - SRV_IDX, - CLI_IDX, - __NR_BPF_ARRAY_IDX, +enum bpf_addr_array_idx { + ADDR_SRV_IDX, + ADDR_CLI_IDX, + __NR_BPF_ADDR_ARRAY_IDX, +}; + +enum bpf_result_array_idx { + EGRESS_SRV_IDX, + EGRESS_CLI_IDX, + INGRESS_LISTEN_IDX, + __NR_BPF_RESULT_ARRAY_IDX, +}; + +enum bpf_linum_array_idx { + EGRESS_LINUM_IDX, + INGRESS_LINUM_IDX, + __NR_BPF_LINUM_ARRAY_IDX, }; #define CHECK(condition, tag, format...) ({ \ @@ -41,8 +54,16 @@ static int linum_map_fd; static int addr_map_fd; static int tp_map_fd; static int sk_map_fd; -static __u32 srv_idx = SRV_IDX; -static __u32 cli_idx = CLI_IDX; + +static __u32 addr_srv_idx = ADDR_SRV_IDX; +static __u32 addr_cli_idx = ADDR_CLI_IDX; + +static __u32 egress_srv_idx = EGRESS_SRV_IDX; +static __u32 egress_cli_idx = EGRESS_CLI_IDX; +static __u32 ingress_listen_idx = INGRESS_LISTEN_IDX; + +static __u32 egress_linum_idx = EGRESS_LINUM_IDX; +static __u32 ingress_linum_idx = INGRESS_LINUM_IDX; static void init_loopback6(struct sockaddr_in6 *sa6) { @@ -93,29 +114,46 @@ static void print_tp(const struct bpf_tcp_sock *tp) static void check_result(void) { - struct bpf_tcp_sock srv_tp, cli_tp; - struct bpf_sock srv_sk, cli_sk; - __u32 linum, idx0 = 0; + struct bpf_tcp_sock srv_tp, cli_tp, listen_tp; + struct bpf_sock srv_sk, cli_sk, listen_sk; + __u32 ingress_linum, egress_linum; int err; - err = bpf_map_lookup_elem(linum_map_fd, &idx0, &linum); + err = bpf_map_lookup_elem(linum_map_fd, &egress_linum_idx, + &egress_linum); CHECK(err == -1, "bpf_map_lookup_elem(linum_map_fd)", "err:%d errno:%d", err, errno); - err = bpf_map_lookup_elem(sk_map_fd, &srv_idx, &srv_sk); - CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &srv_idx)", + err = bpf_map_lookup_elem(linum_map_fd, &ingress_linum_idx, + &ingress_linum); + CHECK(err == -1, "bpf_map_lookup_elem(linum_map_fd)", + "err:%d errno:%d", err, errno); + + err = bpf_map_lookup_elem(sk_map_fd, &egress_srv_idx, &srv_sk); + CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &egress_srv_idx)", + "err:%d errno:%d", err, errno); + err = bpf_map_lookup_elem(tp_map_fd, &egress_srv_idx, &srv_tp); + CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &egress_srv_idx)", + "err:%d errno:%d", err, errno); + + err = bpf_map_lookup_elem(sk_map_fd, &egress_cli_idx, &cli_sk); + CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &egress_cli_idx)", "err:%d errno:%d", err, errno); - err = bpf_map_lookup_elem(tp_map_fd, &srv_idx, &srv_tp); - CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &srv_idx)", + err = bpf_map_lookup_elem(tp_map_fd, &egress_cli_idx, &cli_tp); + CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &egress_cli_idx)", "err:%d errno:%d", err, errno); - err = bpf_map_lookup_elem(sk_map_fd, &cli_idx, &cli_sk); - CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &cli_idx)", + err = bpf_map_lookup_elem(sk_map_fd, &ingress_listen_idx, &listen_sk); + CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &ingress_listen_idx)", "err:%d errno:%d", err, errno); - err = bpf_map_lookup_elem(tp_map_fd, &cli_idx, &cli_tp); - CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &cli_idx)", + err = bpf_map_lookup_elem(tp_map_fd, &ingress_listen_idx, &listen_tp); + CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &ingress_listen_idx)", "err:%d errno:%d", err, errno); + printf("listen_sk: "); + print_sk(&listen_sk); + printf("\n"); + printf("srv_sk: "); print_sk(&srv_sk); printf("\n"); @@ -124,6 +162,10 @@ static void check_result(void) print_sk(&cli_sk); printf("\n"); + printf("listen_tp: "); + print_tp(&listen_tp); + printf("\n"); + printf("srv_tp: "); print_tp(&srv_tp); printf("\n"); @@ -132,6 +174,19 @@ static void check_result(void) print_tp(&cli_tp); printf("\n"); + CHECK(listen_sk.state != 10 || + listen_sk.family != AF_INET6 || + listen_sk.protocol != IPPROTO_TCP || + memcmp(listen_sk.src_ip6, &in6addr_loopback, + sizeof(listen_sk.src_ip6)) || + listen_sk.dst_ip6[0] || listen_sk.dst_ip6[1] || + listen_sk.dst_ip6[2] || listen_sk.dst_ip6[3] || + listen_sk.src_port != ntohs(srv_sa6.sin6_port) || + listen_sk.dst_port, + "Unexpected listen_sk", + "Check listen_sk output. ingress_linum:%u", + ingress_linum); + CHECK(srv_sk.state == 10 || !srv_sk.state || srv_sk.family != AF_INET6 || @@ -142,7 +197,8 @@ static void check_result(void) sizeof(srv_sk.dst_ip6)) || srv_sk.src_port != ntohs(srv_sa6.sin6_port) || srv_sk.dst_port != cli_sa6.sin6_port, - "Unexpected srv_sk", "Check srv_sk output. linum:%u", linum); + "Unexpected srv_sk", "Check srv_sk output. egress_linum:%u", + egress_linum); CHECK(cli_sk.state == 10 || !cli_sk.state || @@ -154,21 +210,31 @@ static void check_result(void) sizeof(cli_sk.dst_ip6)) || cli_sk.src_port != ntohs(cli_sa6.sin6_port) || cli_sk.dst_port != srv_sa6.sin6_port, - "Unexpected cli_sk", "Check cli_sk output. linum:%u", linum); + "Unexpected cli_sk", "Check cli_sk output. egress_linum:%u", + egress_linum); + + CHECK(listen_tp.data_segs_out || + listen_tp.data_segs_in || + listen_tp.total_retrans || + listen_tp.bytes_acked, + "Unexpected listen_tp", "Check listen_tp output. ingress_linum:%u", + ingress_linum); CHECK(srv_tp.data_segs_out != 1 || srv_tp.data_segs_in || srv_tp.snd_cwnd != 10 || srv_tp.total_retrans || srv_tp.bytes_acked != DATA_LEN, - "Unexpected srv_tp", "Check srv_tp output. linum:%u", linum); + "Unexpected srv_tp", "Check srv_tp output. egress_linum:%u", + egress_linum); CHECK(cli_tp.data_segs_out || cli_tp.data_segs_in != 1 || cli_tp.snd_cwnd != 10 || cli_tp.total_retrans || cli_tp.bytes_received != DATA_LEN, - "Unexpected cli_tp", "Check cli_tp output. linum:%u", linum); + "Unexpected cli_tp", "Check cli_tp output. egress_linum:%u", + egress_linum); } static void test(void) @@ -211,10 +277,10 @@ static void test(void) err, errno); /* Update addr_map with srv_sa6 and cli_sa6 */ - err = bpf_map_update_elem(addr_map_fd, &srv_idx, &srv_sa6, 0); + err = bpf_map_update_elem(addr_map_fd, &addr_srv_idx, &srv_sa6, 0); CHECK(err, "map_update", "err:%d errno:%d", err, errno); - err = bpf_map_update_elem(addr_map_fd, &cli_idx, &cli_sa6, 0); + err = bpf_map_update_elem(addr_map_fd, &addr_cli_idx, &cli_sa6, 0); CHECK(err, "map_update", "err:%d errno:%d", err, errno); /* Connect from cli_sa6 to srv_sa6 */ @@ -273,9 +339,9 @@ int main(int argc, char **argv) struct bpf_prog_load_attr attr = { .file = "test_sock_fields_kern.o", .prog_type = BPF_PROG_TYPE_CGROUP_SKB, - .expected_attach_type = BPF_CGROUP_INET_EGRESS, }; - int cgroup_fd, prog_fd, err; + int cgroup_fd, egress_fd, ingress_fd, err; + struct bpf_program *ingress_prog; struct bpf_object *obj; struct bpf_map *map; @@ -293,12 +359,24 @@ int main(int argc, char **argv) err = join_cgroup(TEST_CGROUP); CHECK(err, "join_cgroup", "err:%d errno:%d", err, errno); - err = bpf_prog_load_xattr(&attr, &obj, &prog_fd); + err = bpf_prog_load_xattr(&attr, &obj, &egress_fd); CHECK(err, "bpf_prog_load_xattr()", "err:%d", err); - err = bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0); + ingress_prog = bpf_object__find_program_by_title(obj, + "cgroup_skb/ingress"); + CHECK(!ingress_prog, + "bpf_object__find_program_by_title(cgroup_skb/ingress)", + "not found"); + ingress_fd = bpf_program__fd(ingress_prog); + + err = bpf_prog_attach(egress_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0); CHECK(err == -1, "bpf_prog_attach(CPF_CGROUP_INET_EGRESS)", "err:%d errno%d", err, errno); + + err = bpf_prog_attach(ingress_fd, cgroup_fd, + BPF_CGROUP_INET_INGRESS, 0); + CHECK(err == -1, "bpf_prog_attach(CPF_CGROUP_INET_INGRESS)", + "err:%d errno%d", err, errno); close(cgroup_fd); map = bpf_object__find_map_by_name(obj, "addr_map"); diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index 4004891afa9c..9093a8f64dc6 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -375,6 +375,31 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { + "calls: ptr null check in subprog", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_6, 0), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "function calls to other bpf functions are allowed for root only", + .fixup_map_hash_48b = { 3 }, + .result_unpriv = REJECT, + .result = ACCEPT, + .retval = 0, +}, +{ "calls: two calls with args", .insns = { BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1), @@ -908,6 +933,44 @@ .result = REJECT, }, { + "calls: stack depth check in dead code", + .insns = { + /* main */ + BPF_MOV64_IMM(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call A */ + BPF_EXIT_INSN(), + /* A */ + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1), + BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 2), /* call B */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + /* B */ + BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call C */ + BPF_EXIT_INSN(), + /* C */ + BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call D */ + BPF_EXIT_INSN(), + /* D */ + BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call E */ + BPF_EXIT_INSN(), + /* E */ + BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call F */ + BPF_EXIT_INSN(), + /* F */ + BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call G */ + BPF_EXIT_INSN(), + /* G */ + BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call H */ + BPF_EXIT_INSN(), + /* H */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_XDP, + .errstr = "call stack", + .result = REJECT, +}, +{ "calls: spill into caller stack frame", .insns = { BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), @@ -1940,3 +2003,28 @@ .errstr = "!read_ok", .result = REJECT, }, +{ + "calls: cross frame pruning - liveness propagation", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32), + BPF_MOV64_IMM(BPF_REG_8, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_8, 1), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32), + BPF_MOV64_IMM(BPF_REG_9, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_9, 1), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_8, 1, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, + .errstr_unpriv = "function calls to other bpf functions are allowed for root only", + .errstr = "!read_ok", + .result = REJECT, +}, diff --git a/tools/testing/selftests/bpf/verifier/direct_packet_access.c b/tools/testing/selftests/bpf/verifier/direct_packet_access.c index e3fc22e672c2..d5c596fdc4b9 100644 --- a/tools/testing/selftests/bpf/verifier/direct_packet_access.c +++ b/tools/testing/selftests/bpf/verifier/direct_packet_access.c @@ -631,3 +631,25 @@ .errstr = "invalid access to packet", .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, +{ + "direct packet access: test29 (reg > pkt_end in subprog)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_6, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_2, 1), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, diff --git a/tools/testing/selftests/bpf/verifier/ref_tracking.c b/tools/testing/selftests/bpf/verifier/ref_tracking.c index 3ed3593bd8b6..923f2110072d 100644 --- a/tools/testing/selftests/bpf/verifier/ref_tracking.c +++ b/tools/testing/selftests/bpf/verifier/ref_tracking.c @@ -605,3 +605,171 @@ .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = ACCEPT, }, +{ + "reference tracking: use ptr from bpf_tcp_sock() after release", + .insns = { + BPF_SK_LOOKUP, + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_tcp_sock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, offsetof(struct bpf_tcp_sock, snd_cwnd)), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "invalid mem access", +}, +{ + "reference tracking: use ptr from bpf_sk_fullsock() after release", + .insns = { + BPF_SK_LOOKUP, + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, offsetof(struct bpf_sock, type)), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "invalid mem access", +}, +{ + "reference tracking: use ptr from bpf_sk_fullsock(tp) after release", + .insns = { + BPF_SK_LOOKUP, + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_tcp_sock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 0, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, offsetof(struct bpf_sock, type)), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "invalid mem access", +}, +{ + "reference tracking: use sk after bpf_sk_release(tp)", + .insns = { + BPF_SK_LOOKUP, + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_tcp_sock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, offsetof(struct bpf_sock, type)), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "invalid mem access", +}, +{ + "reference tracking: use ptr from bpf_get_listener_sock() after bpf_sk_release(sk)", + .insns = { + BPF_SK_LOOKUP, + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_get_listener_sock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, offsetof(struct bpf_sock, src_port)), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, +}, +{ + "reference tracking: bpf_sk_release(listen_sk)", + .insns = { + BPF_SK_LOOKUP, + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_get_listener_sock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, offsetof(struct bpf_sock, type)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "reference has not been acquired before", +}, +{ + /* !bpf_sk_fullsock(sk) is checked but !bpf_tcp_sock(sk) is not checked */ + "reference tracking: tp->snd_cwnd after bpf_sk_fullsock(sk) and bpf_tcp_sock(sk)", + .insns = { + BPF_SK_LOOKUP, + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_tcp_sock), + BPF_MOV64_REG(BPF_REG_8, BPF_REG_0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0, 3), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_8, offsetof(struct bpf_tcp_sock, snd_cwnd)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "invalid mem access", +}, diff --git a/tools/testing/selftests/bpf/verifier/sock.c b/tools/testing/selftests/bpf/verifier/sock.c index 0ddfdf76aba5..416436231fab 100644 --- a/tools/testing/selftests/bpf/verifier/sock.c +++ b/tools/testing/selftests/bpf/verifier/sock.c @@ -342,7 +342,7 @@ }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, - .errstr = "type=sock_common expected=sock", + .errstr = "reference has not been acquired before", }, { "bpf_sk_release(bpf_sk_fullsock(skb->sk))", @@ -380,5 +380,5 @@ }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, - .errstr = "type=tcp_sock expected=sock", + .errstr = "reference has not been acquired before", }, diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh index c4cf6e6d800e..a6c196c8534c 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh @@ -11,6 +11,7 @@ lib_dir=$(dirname $0)/../../../net/forwarding ALL_TESTS=" rif_set_addr_test + rif_vrf_set_addr_test rif_inherit_bridge_addr_test rif_non_inherit_bridge_addr_test vlan_interface_deletion_test @@ -98,6 +99,25 @@ rif_set_addr_test() ip link set dev $swp1 addr $swp1_mac } +rif_vrf_set_addr_test() +{ + # Test that it is possible to set an IP address on a VRF upper despite + # its random MAC address. + RET=0 + + ip link add name vrf-test type vrf table 10 + ip link set dev $swp1 master vrf-test + + ip -4 address add 192.0.2.1/24 dev vrf-test + check_err $? "failed to set IPv4 address on VRF" + ip -6 address add 2001:db8:1::1/64 dev vrf-test + check_err $? "failed to set IPv6 address on VRF" + + log_test "RIF - setting IP address on VRF" + + ip link del dev vrf-test +} + rif_inherit_bridge_addr_test() { RET=0 diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 3c1f4bdf9000..f8588cca2bef 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -1,3 +1,5 @@ +include ../../../../scripts/Kbuild.include + all: top_srcdir = ../../../.. @@ -17,6 +19,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/state_test TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test +TEST_GEN_PROGS_x86_64 += x86_64/smm_test TEST_GEN_PROGS_x86_64 += dirty_log_test TEST_GEN_PROGS_x86_64 += clear_dirty_log_test @@ -29,8 +32,12 @@ LIBKVM += $(LIBKVM_$(UNAME_M)) INSTALL_HDR_PATH = $(top_srcdir)/usr LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/ LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include -CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I.. -LDFLAGS += -pthread +CFLAGS += -O2 -g -std=gnu99 -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I.. + +no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \ + $(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie) + +LDFLAGS += -pthread $(no-pie-option) # After inclusion, $(OUTPUT) is defined and # $(TEST_GEN_PROGS) starts with $(OUTPUT)/ diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index 4715cfba20dc..93f99c6b7d79 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -288,8 +288,11 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, #endif max_gfn = (1ul << (guest_pa_bits - guest_page_shift)) - 1; guest_page_size = (1ul << guest_page_shift); - /* 1G of guest page sized pages */ - guest_num_pages = (1ul << (30 - guest_page_shift)); + /* + * A little more than 1G of guest page sized pages. Cover the + * case where the size is not aligned to 64 pages. + */ + guest_num_pages = (1ul << (30 - guest_page_shift)) + 3; host_page_size = getpagesize(); host_num_pages = (guest_num_pages * guest_page_size) / host_page_size + !!((guest_num_pages * guest_page_size) % host_page_size); @@ -359,7 +362,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap); #ifdef USE_CLEAR_DIRTY_LOG kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0, - DIV_ROUND_UP(host_num_pages, 64) * 64); + host_num_pages); #endif vm_dirty_log_verify(bmap); iteration++; diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index a84785b02557..07b71ad9734a 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -102,6 +102,7 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva); struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid); void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid); int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid); +void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid); void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_mp_state *mp_state); void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs); diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index e2884c2b81ff..6063d5b2f356 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -778,6 +778,33 @@ void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index, #define MSR_IA32_APICBASE_ENABLE (1<<11) #define MSR_IA32_APICBASE_BASE (0xfffff<<12) +#define APIC_BASE_MSR 0x800 +#define X2APIC_ENABLE (1UL << 10) +#define APIC_ICR 0x300 +#define APIC_DEST_SELF 0x40000 +#define APIC_DEST_ALLINC 0x80000 +#define APIC_DEST_ALLBUT 0xC0000 +#define APIC_ICR_RR_MASK 0x30000 +#define APIC_ICR_RR_INVALID 0x00000 +#define APIC_ICR_RR_INPROG 0x10000 +#define APIC_ICR_RR_VALID 0x20000 +#define APIC_INT_LEVELTRIG 0x08000 +#define APIC_INT_ASSERT 0x04000 +#define APIC_ICR_BUSY 0x01000 +#define APIC_DEST_LOGICAL 0x00800 +#define APIC_DEST_PHYSICAL 0x00000 +#define APIC_DM_FIXED 0x00000 +#define APIC_DM_FIXED_MASK 0x00700 +#define APIC_DM_LOWEST 0x00100 +#define APIC_DM_SMI 0x00200 +#define APIC_DM_REMRD 0x00300 +#define APIC_DM_NMI 0x00400 +#define APIC_DM_INIT 0x00500 +#define APIC_DM_STARTUP 0x00600 +#define APIC_DM_EXTINT 0x00700 +#define APIC_VECTOR_MASK 0x000FF +#define APIC_ICR2 0x310 + #define MSR_IA32_TSCDEADLINE 0x000006e0 #define MSR_IA32_UCODE_WRITE 0x00000079 diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index b52cfdefecbf..4ca96b228e46 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -91,6 +91,11 @@ static void vm_open(struct kvm_vm *vm, int perm, unsigned long type) if (vm->kvm_fd < 0) exit(KSFT_SKIP); + if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) { + fprintf(stderr, "immediate_exit not available, skipping test\n"); + exit(KSFT_SKIP); + } + vm->fd = ioctl(vm->kvm_fd, KVM_CREATE_VM, type); TEST_ASSERT(vm->fd >= 0, "KVM_CREATE_VM ioctl failed, " "rc: %i errno: %i", vm->fd, errno); @@ -1121,6 +1126,22 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid) return rc; } +void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid) +{ + struct vcpu *vcpu = vcpu_find(vm, vcpuid); + int ret; + + TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); + + vcpu->state->immediate_exit = 1; + ret = ioctl(vcpu->fd, KVM_RUN, NULL); + vcpu->state->immediate_exit = 0; + + TEST_ASSERT(ret == -1 && errno == EINTR, + "KVM_RUN IOCTL didn't exit immediately, rc: %i, errno: %i", + ret, errno); +} + /* * VM VCPU Set MP State * diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index f28127f4a3af..dc7fae9fa424 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -1030,6 +1030,14 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid) nested_size, sizeof(state->nested_)); } + /* + * When KVM exits to userspace with KVM_EXIT_IO, KVM guarantees + * guest state is consistent only after userspace re-enters the + * kernel with KVM_RUN. Complete IO prior to migrating state + * to a new VM. + */ + vcpu_run_complete_io(vm, vcpuid); + nmsrs = kvm_get_num_msrs(vm); list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0])); list->nmsrs = nmsrs; @@ -1093,12 +1101,6 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *s struct vcpu *vcpu = vcpu_find(vm, vcpuid); int r; - if (state->nested.size) { - r = ioctl(vcpu->fd, KVM_SET_NESTED_STATE, &state->nested); - TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_NESTED_STATE, r: %i", - r); - } - r = ioctl(vcpu->fd, KVM_SET_XSAVE, &state->xsave); TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XSAVE, r: %i", r); @@ -1130,4 +1132,10 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *s r = ioctl(vcpu->fd, KVM_SET_REGS, &state->regs); TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_REGS, r: %i", r); + + if (state->nested.size) { + r = ioctl(vcpu->fd, KVM_SET_NESTED_STATE, &state->nested); + TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_NESTED_STATE, r: %i", + r); + } } diff --git a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c index d503a51fad30..7c2c4d4055a8 100644 --- a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c +++ b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c @@ -87,22 +87,25 @@ int main(int argc, char *argv[]) while (1) { rc = _vcpu_run(vm, VCPU_ID); - if (run->exit_reason == KVM_EXIT_IO) { - switch (get_ucall(vm, VCPU_ID, &uc)) { - case UCALL_SYNC: - /* emulate hypervisor clearing CR4.OSXSAVE */ - vcpu_sregs_get(vm, VCPU_ID, &sregs); - sregs.cr4 &= ~X86_CR4_OSXSAVE; - vcpu_sregs_set(vm, VCPU_ID, &sregs); - break; - case UCALL_ABORT: - TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit."); - break; - case UCALL_DONE: - goto done; - default: - TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd); - } + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Unexpected exit reason: %u (%s),\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_SYNC: + /* emulate hypervisor clearing CR4.OSXSAVE */ + vcpu_sregs_get(vm, VCPU_ID, &sregs); + sregs.cr4 &= ~X86_CR4_OSXSAVE; + vcpu_sregs_set(vm, VCPU_ID, &sregs); + break; + case UCALL_ABORT: + TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit."); + break; + case UCALL_DONE: + goto done; + default: + TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd); } } diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c index c49c2a28b0eb..36669684eca5 100644 --- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c +++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c @@ -123,8 +123,6 @@ int main(int argc, char *argv[]) stage, run->exit_reason, exit_reason_str(run->exit_reason)); - memset(®s1, 0, sizeof(regs1)); - vcpu_regs_get(vm, VCPU_ID, ®s1); switch (get_ucall(vm, VCPU_ID, &uc)) { case UCALL_ABORT: TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0], @@ -144,6 +142,9 @@ int main(int argc, char *argv[]) stage, (ulong)uc.args[1]); state = vcpu_save_state(vm, VCPU_ID); + memset(®s1, 0, sizeof(regs1)); + vcpu_regs_get(vm, VCPU_ID, ®s1); + kvm_vm_release(vm); /* Restore state in a new VM. */ diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c index 264425f75806..9a21e912097c 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c @@ -141,7 +141,13 @@ int main(int argc, char *argv[]) free(hv_cpuid_entries); - vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap); + rv = _vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap); + + if (rv) { + fprintf(stderr, + "Enlightened VMCS is unsupported, skip related test\n"); + goto vm_free; + } hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm); if (!hv_cpuid_entries) @@ -151,6 +157,7 @@ int main(int argc, char *argv[]) free(hv_cpuid_entries); +vm_free: kvm_vm_free(vm); return 0; diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c new file mode 100644 index 000000000000..fb8086964d83 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/smm_test.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2018, Red Hat, Inc. + * + * Tests for SMM. + */ +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <stdint.h> +#include <string.h> +#include <sys/ioctl.h> + +#include "test_util.h" + +#include "kvm_util.h" + +#include "vmx.h" + +#define VCPU_ID 1 + +#define PAGE_SIZE 4096 + +#define SMRAM_SIZE 65536 +#define SMRAM_MEMSLOT ((1 << 16) | 1) +#define SMRAM_PAGES (SMRAM_SIZE / PAGE_SIZE) +#define SMRAM_GPA 0x1000000 +#define SMRAM_STAGE 0xfe + +#define STR(x) #x +#define XSTR(s) STR(s) + +#define SYNC_PORT 0xe +#define DONE 0xff + +/* + * This is compiled as normal 64-bit code, however, SMI handler is executed + * in real-address mode. To stay simple we're limiting ourselves to a mode + * independent subset of asm here. + * SMI handler always report back fixed stage SMRAM_STAGE. + */ +uint8_t smi_handler[] = { + 0xb0, SMRAM_STAGE, /* mov $SMRAM_STAGE, %al */ + 0xe4, SYNC_PORT, /* in $SYNC_PORT, %al */ + 0x0f, 0xaa, /* rsm */ +}; + +void sync_with_host(uint64_t phase) +{ + asm volatile("in $" XSTR(SYNC_PORT)", %%al \n" + : : "a" (phase)); +} + +void self_smi(void) +{ + wrmsr(APIC_BASE_MSR + (APIC_ICR >> 4), + APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_SMI); +} + +void guest_code(struct vmx_pages *vmx_pages) +{ + uint64_t apicbase = rdmsr(MSR_IA32_APICBASE); + + sync_with_host(1); + + wrmsr(MSR_IA32_APICBASE, apicbase | X2APIC_ENABLE); + + sync_with_host(2); + + self_smi(); + + sync_with_host(4); + + if (vmx_pages) { + GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages)); + + sync_with_host(5); + + self_smi(); + + sync_with_host(7); + } + + sync_with_host(DONE); +} + +int main(int argc, char *argv[]) +{ + struct vmx_pages *vmx_pages = NULL; + vm_vaddr_t vmx_pages_gva = 0; + + struct kvm_regs regs; + struct kvm_vm *vm; + struct kvm_run *run; + struct kvm_x86_state *state; + int stage, stage_reported; + + /* Create VM */ + vm = vm_create_default(VCPU_ID, 0, guest_code); + + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + + run = vcpu_state(vm, VCPU_ID); + + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, SMRAM_GPA, + SMRAM_MEMSLOT, SMRAM_PAGES, 0); + TEST_ASSERT(vm_phy_pages_alloc(vm, SMRAM_PAGES, SMRAM_GPA, SMRAM_MEMSLOT) + == SMRAM_GPA, "could not allocate guest physical addresses?"); + + memset(addr_gpa2hva(vm, SMRAM_GPA), 0x0, SMRAM_SIZE); + memcpy(addr_gpa2hva(vm, SMRAM_GPA) + 0x8000, smi_handler, + sizeof(smi_handler)); + + vcpu_set_msr(vm, VCPU_ID, MSR_IA32_SMBASE, SMRAM_GPA); + + if (kvm_check_cap(KVM_CAP_NESTED_STATE)) { + vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva); + vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); + } else { + printf("will skip SMM test with VMX enabled\n"); + vcpu_args_set(vm, VCPU_ID, 1, 0); + } + + for (stage = 1;; stage++) { + _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Stage %d: unexpected exit reason: %u (%s),\n", + stage, run->exit_reason, + exit_reason_str(run->exit_reason)); + + memset(®s, 0, sizeof(regs)); + vcpu_regs_get(vm, VCPU_ID, ®s); + + stage_reported = regs.rax & 0xff; + + if (stage_reported == DONE) + goto done; + + TEST_ASSERT(stage_reported == stage || + stage_reported == SMRAM_STAGE, + "Unexpected stage: #%x, got %x", + stage, stage_reported); + + state = vcpu_save_state(vm, VCPU_ID); + kvm_vm_release(vm); + kvm_vm_restart(vm, O_RDWR); + vm_vcpu_add(vm, VCPU_ID, 0, 0); + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + vcpu_load_state(vm, VCPU_ID, state); + run = vcpu_state(vm, VCPU_ID); + free(state); + } + +done: + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c index 4b3f556265f1..e0a3c0204b7c 100644 --- a/tools/testing/selftests/kvm/x86_64/state_test.c +++ b/tools/testing/selftests/kvm/x86_64/state_test.c @@ -156,8 +156,6 @@ int main(int argc, char *argv[]) stage, run->exit_reason, exit_reason_str(run->exit_reason)); - memset(®s1, 0, sizeof(regs1)); - vcpu_regs_get(vm, VCPU_ID, ®s1); switch (get_ucall(vm, VCPU_ID, &uc)) { case UCALL_ABORT: TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0], @@ -177,6 +175,9 @@ int main(int argc, char *argv[]) stage, (ulong)uc.args[1]); state = vcpu_save_state(vm, VCPU_ID); + memset(®s1, 0, sizeof(regs1)); + vcpu_regs_get(vm, VCPU_ID, ®s1); + kvm_vm_release(vm); /* Restore state in a new VM. */ diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh index d4cfb6a7a086..4b7e107865bf 100755 --- a/tools/testing/selftests/net/fib_rule_tests.sh +++ b/tools/testing/selftests/net/fib_rule_tests.sh @@ -27,6 +27,7 @@ log_test() nsuccess=$((nsuccess+1)) printf "\n TEST: %-50s [ OK ]\n" "${msg}" else + ret=1 nfail=$((nfail+1)) printf "\n TEST: %-50s [FAIL]\n" "${msg}" if [ "${PAUSE_ON_FAIL}" = "yes" ]; then @@ -147,8 +148,8 @@ fib_rule6_test() fib_check_iproute_support "ipproto" "ipproto" if [ $? -eq 0 ]; then - match="ipproto icmp" - fib_rule6_test_match_n_redirect "$match" "$match" "ipproto icmp match" + match="ipproto ipv6-icmp" + fib_rule6_test_match_n_redirect "$match" "$match" "ipproto ipv6-icmp match" fi } @@ -245,4 +246,9 @@ setup run_fibrule_tests cleanup +if [ "$TESTS" != "none" ]; then + printf "\nTests passed: %3d\n" ${nsuccess} + printf "Tests failed: %3d\n" ${nfail} +fi + exit $ret diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 1080ff55a788..0d2a5f4f1e63 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -605,6 +605,39 @@ run_cmd() return $rc } +check_expected() +{ + local out="$1" + local expected="$2" + local rc=0 + + [ "${out}" = "${expected}" ] && return 0 + + if [ -z "${out}" ]; then + if [ "$VERBOSE" = "1" ]; then + printf "\nNo route entry found\n" + printf "Expected:\n" + printf " ${expected}\n" + fi + return 1 + fi + + # tricky way to convert output to 1-line without ip's + # messy '\'; this drops all extra white space + out=$(echo ${out}) + if [ "${out}" != "${expected}" ]; then + rc=1 + if [ "${VERBOSE}" = "1" ]; then + printf " Unexpected route entry. Have:\n" + printf " ${out}\n" + printf " Expected:\n" + printf " ${expected}\n\n" + fi + fi + + return $rc +} + # add route for a prefix, flushing any existing routes first # expected to be the first step of a test add_route6() @@ -652,31 +685,7 @@ check_route6() pfx=$1 out=$($IP -6 ro ls match ${pfx} | sed -e 's/ pref medium//') - [ "${out}" = "${expected}" ] && return 0 - - if [ -z "${out}" ]; then - if [ "$VERBOSE" = "1" ]; then - printf "\nNo route entry found\n" - printf "Expected:\n" - printf " ${expected}\n" - fi - return 1 - fi - - # tricky way to convert output to 1-line without ip's - # messy '\'; this drops all extra white space - out=$(echo ${out}) - if [ "${out}" != "${expected}" ]; then - rc=1 - if [ "${VERBOSE}" = "1" ]; then - printf " Unexpected route entry. Have:\n" - printf " ${out}\n" - printf " Expected:\n" - printf " ${expected}\n\n" - fi - fi - - return $rc + check_expected "${out}" "${expected}" } route_cleanup() @@ -725,7 +734,7 @@ route_setup() ip -netns ns2 addr add 172.16.103.2/24 dev veth4 ip -netns ns2 addr add 172.16.104.1/24 dev dummy1 - set +ex + set +e } # assumption is that basic add of a single path route works @@ -960,7 +969,8 @@ ipv6_addr_metric_test() run_cmd "$IP li set dev dummy2 down" rc=$? if [ $rc -eq 0 ]; then - check_route6 "" + out=$($IP -6 ro ls match 2001:db8:104::/64) + check_expected "${out}" "" rc=$? fi log_test $rc 0 "Prefix route removed on link down" @@ -1091,38 +1101,13 @@ check_route() local pfx local expected="$1" local out - local rc=0 set -- $expected pfx=$1 [ "${pfx}" = "unreachable" ] && pfx=$2 out=$($IP ro ls match ${pfx}) - [ "${out}" = "${expected}" ] && return 0 - - if [ -z "${out}" ]; then - if [ "$VERBOSE" = "1" ]; then - printf "\nNo route entry found\n" - printf "Expected:\n" - printf " ${expected}\n" - fi - return 1 - fi - - # tricky way to convert output to 1-line without ip's - # messy '\'; this drops all extra white space - out=$(echo ${out}) - if [ "${out}" != "${expected}" ]; then - rc=1 - if [ "${VERBOSE}" = "1" ]; then - printf " Unexpected route entry. Have:\n" - printf " ${out}\n" - printf " Expected:\n" - printf " ${expected}\n\n" - fi - fi - - return $rc + check_expected "${out}" "${expected}" } # assumption is that basic add of a single path route works @@ -1387,7 +1372,8 @@ ipv4_addr_metric_test() run_cmd "$IP li set dev dummy2 down" rc=$? if [ $rc -eq 0 ]; then - check_route "" + out=$($IP ro ls match 172.16.104.0/24) + check_expected "${out}" "" rc=$? fi log_test $rc 0 "Prefix route removed on link down" diff --git a/tools/testing/selftests/net/run_afpackettests b/tools/testing/selftests/net/run_afpackettests index 2dc95fda7ef7..ea5938ec009a 100755 --- a/tools/testing/selftests/net/run_afpackettests +++ b/tools/testing/selftests/net/run_afpackettests @@ -6,12 +6,14 @@ if [ $(id -u) != 0 ]; then exit 0 fi +ret=0 echo "--------------------" echo "running psock_fanout test" echo "--------------------" ./in_netns.sh ./psock_fanout if [ $? -ne 0 ]; then echo "[FAIL]" + ret=1 else echo "[PASS]" fi @@ -22,6 +24,7 @@ echo "--------------------" ./in_netns.sh ./psock_tpacket if [ $? -ne 0 ]; then echo "[FAIL]" + ret=1 else echo "[PASS]" fi @@ -32,6 +35,8 @@ echo "--------------------" ./in_netns.sh ./txring_overwrite if [ $? -ne 0 ]; then echo "[FAIL]" + ret=1 else echo "[PASS]" fi +exit $ret diff --git a/tools/testing/selftests/net/run_netsocktests b/tools/testing/selftests/net/run_netsocktests index b093f39c298c..14e41faf2c57 100755 --- a/tools/testing/selftests/net/run_netsocktests +++ b/tools/testing/selftests/net/run_netsocktests @@ -7,7 +7,7 @@ echo "--------------------" ./socket if [ $? -ne 0 ]; then echo "[FAIL]" + exit 1 else echo "[PASS]" fi - diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index c9ff2b47bd1c..a37cb1192c6a 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for netfilter selftests -TEST_PROGS := nft_trans_stress.sh nft_nat.sh +TEST_PROGS := nft_trans_stress.sh nft_nat.sh conntrack_icmp_related.sh include ../lib.mk diff --git a/tools/testing/selftests/netfilter/conntrack_icmp_related.sh b/tools/testing/selftests/netfilter/conntrack_icmp_related.sh new file mode 100755 index 000000000000..b48e1833bc89 --- /dev/null +++ b/tools/testing/selftests/netfilter/conntrack_icmp_related.sh @@ -0,0 +1,283 @@ +#!/bin/bash +# +# check that ICMP df-needed/pkttoobig icmp are set are set as related +# state +# +# Setup is: +# +# nsclient1 -> nsrouter1 -> nsrouter2 -> nsclient2 +# MTU 1500, except for nsrouter2 <-> nsclient2 link (1280). +# ping nsclient2 from nsclient1, checking that conntrack did set RELATED +# 'fragmentation needed' icmp packet. +# +# In addition, nsrouter1 will perform IP masquerading, i.e. also +# check the icmp errors are propagated to the correct host as per +# nat of "established" icmp-echo "connection". + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 +ret=0 + +nft --version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without nft tool" + exit $ksft_skip +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +cleanup() { + for i in 1 2;do ip netns del nsclient$i;done + for i in 1 2;do ip netns del nsrouter$i;done +} + +ipv4() { + echo -n 192.168.$1.2 +} + +ipv6 () { + echo -n dead:$1::2 +} + +check_counter() +{ + ns=$1 + name=$2 + expect=$3 + local lret=0 + + cnt=$(ip netns exec $ns nft list counter inet filter "$name" | grep -q "$expect") + if [ $? -ne 0 ]; then + echo "ERROR: counter $name in $ns has unexpected value (expected $expect)" 1>&2 + ip netns exec $ns nft list counter inet filter "$name" 1>&2 + lret=1 + fi + + return $lret +} + +check_unknown() +{ + expect="packets 0 bytes 0" + for n in nsclient1 nsclient2 nsrouter1 nsrouter2; do + check_counter $n "unknown" "$expect" + if [ $? -ne 0 ] ;then + return 1 + fi + done + + return 0 +} + +for n in nsclient1 nsclient2 nsrouter1 nsrouter2; do + ip netns add $n + ip -net $n link set lo up +done + +DEV=veth0 +ip link add $DEV netns nsclient1 type veth peer name eth1 netns nsrouter1 +DEV=veth0 +ip link add $DEV netns nsclient2 type veth peer name eth1 netns nsrouter2 + +DEV=veth0 +ip link add $DEV netns nsrouter1 type veth peer name eth2 netns nsrouter2 + +DEV=veth0 +for i in 1 2; do + ip -net nsclient$i link set $DEV up + ip -net nsclient$i addr add $(ipv4 $i)/24 dev $DEV + ip -net nsclient$i addr add $(ipv6 $i)/64 dev $DEV +done + +ip -net nsrouter1 link set eth1 up +ip -net nsrouter1 link set veth0 up + +ip -net nsrouter2 link set eth1 up +ip -net nsrouter2 link set eth2 up + +ip -net nsclient1 route add default via 192.168.1.1 +ip -net nsclient1 -6 route add default via dead:1::1 + +ip -net nsclient2 route add default via 192.168.2.1 +ip -net nsclient2 route add default via dead:2::1 + +i=3 +ip -net nsrouter1 addr add 192.168.1.1/24 dev eth1 +ip -net nsrouter1 addr add 192.168.3.1/24 dev veth0 +ip -net nsrouter1 addr add dead:1::1/64 dev eth1 +ip -net nsrouter1 addr add dead:3::1/64 dev veth0 +ip -net nsrouter1 route add default via 192.168.3.10 +ip -net nsrouter1 -6 route add default via dead:3::10 + +ip -net nsrouter2 addr add 192.168.2.1/24 dev eth1 +ip -net nsrouter2 addr add 192.168.3.10/24 dev eth2 +ip -net nsrouter2 addr add dead:2::1/64 dev eth1 +ip -net nsrouter2 addr add dead:3::10/64 dev eth2 +ip -net nsrouter2 route add default via 192.168.3.1 +ip -net nsrouter2 route add default via dead:3::1 + +sleep 2 +for i in 4 6; do + ip netns exec nsrouter1 sysctl -q net.ipv$i.conf.all.forwarding=1 + ip netns exec nsrouter2 sysctl -q net.ipv$i.conf.all.forwarding=1 +done + +for netns in nsrouter1 nsrouter2; do +ip netns exec $netns nft -f - <<EOF +table inet filter { + counter unknown { } + counter related { } + chain forward { + type filter hook forward priority 0; policy accept; + meta l4proto icmpv6 icmpv6 type "packet-too-big" ct state "related" counter name "related" accept + meta l4proto icmp icmp type "destination-unreachable" ct state "related" counter name "related" accept + meta l4proto { icmp, icmpv6 } ct state new,established accept + counter name "unknown" drop + } +} +EOF +done + +ip netns exec nsclient1 nft -f - <<EOF +table inet filter { + counter unknown { } + counter related { } + chain input { + type filter hook input priority 0; policy accept; + meta l4proto { icmp, icmpv6 } ct state established,untracked accept + + meta l4proto { icmp, icmpv6 } ct state "related" counter name "related" accept + counter name "unknown" drop + } +} +EOF + +ip netns exec nsclient2 nft -f - <<EOF +table inet filter { + counter unknown { } + counter new { } + counter established { } + + chain input { + type filter hook input priority 0; policy accept; + meta l4proto { icmp, icmpv6 } ct state established,untracked accept + + meta l4proto { icmp, icmpv6 } ct state "new" counter name "new" accept + meta l4proto { icmp, icmpv6 } ct state "established" counter name "established" accept + counter name "unknown" drop + } + chain output { + type filter hook output priority 0; policy accept; + meta l4proto { icmp, icmpv6 } ct state established,untracked accept + + meta l4proto { icmp, icmpv6 } ct state "new" counter name "new" + meta l4proto { icmp, icmpv6 } ct state "established" counter name "established" + counter name "unknown" drop + } +} +EOF + + +# make sure NAT core rewrites adress of icmp error if nat is used according to +# conntrack nat information (icmp error will be directed at nsrouter1 address, +# but it needs to be routed to nsclient1 address). +ip netns exec nsrouter1 nft -f - <<EOF +table ip nat { + chain postrouting { + type nat hook postrouting priority 0; policy accept; + ip protocol icmp oifname "veth0" counter masquerade + } +} +table ip6 nat { + chain postrouting { + type nat hook postrouting priority 0; policy accept; + ip6 nexthdr icmpv6 oifname "veth0" counter masquerade + } +} +EOF + +ip netns exec nsrouter2 ip link set eth1 mtu 1280 +ip netns exec nsclient2 ip link set veth0 mtu 1280 +sleep 1 + +ip netns exec nsclient1 ping -c 1 -s 1000 -q -M do 192.168.2.2 >/dev/null +if [ $? -ne 0 ]; then + echo "ERROR: netns ip routing/connectivity broken" 1>&2 + cleanup + exit 1 +fi +ip netns exec nsclient1 ping6 -q -c 1 -s 1000 dead:2::2 >/dev/null +if [ $? -ne 0 ]; then + echo "ERROR: netns ipv6 routing/connectivity broken" 1>&2 + cleanup + exit 1 +fi + +check_unknown +if [ $? -ne 0 ]; then + ret=1 +fi + +expect="packets 0 bytes 0" +for netns in nsrouter1 nsrouter2 nsclient1;do + check_counter "$netns" "related" "$expect" + if [ $? -ne 0 ]; then + ret=1 + fi +done + +expect="packets 2 bytes 2076" +check_counter nsclient2 "new" "$expect" +if [ $? -ne 0 ]; then + ret=1 +fi + +ip netns exec nsclient1 ping -q -c 1 -s 1300 -M do 192.168.2.2 > /dev/null +if [ $? -eq 0 ]; then + echo "ERROR: ping should have failed with PMTU too big error" 1>&2 + ret=1 +fi + +# nsrouter2 should have generated the icmp error, so +# related counter should be 0 (its in forward). +expect="packets 0 bytes 0" +check_counter "nsrouter2" "related" "$expect" +if [ $? -ne 0 ]; then + ret=1 +fi + +# but nsrouter1 should have seen it, same for nsclient1. +expect="packets 1 bytes 576" +for netns in nsrouter1 nsclient1;do + check_counter "$netns" "related" "$expect" + if [ $? -ne 0 ]; then + ret=1 + fi +done + +ip netns exec nsclient1 ping6 -c 1 -s 1300 dead:2::2 > /dev/null +if [ $? -eq 0 ]; then + echo "ERROR: ping6 should have failed with PMTU too big error" 1>&2 + ret=1 +fi + +expect="packets 2 bytes 1856" +for netns in nsrouter1 nsclient1;do + check_counter "$netns" "related" "$expect" + if [ $? -ne 0 ]; then + ret=1 + fi +done + +if [ $ret -eq 0 ];then + echo "PASS: icmp mtu error had RELATED state" +else + echo "ERROR: icmp error RELATED state test has failed" +fi + +cleanup +exit $ret diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index 8ec76681605c..3194007cf8d1 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -321,6 +321,7 @@ EOF test_masquerade6() { + local natflags=$1 local lret=0 ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null @@ -354,13 +355,13 @@ ip netns exec ns0 nft -f - <<EOF table ip6 nat { chain postrouting { type nat hook postrouting priority 0; policy accept; - meta oif veth0 masquerade + meta oif veth0 masquerade $natflags } } EOF ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerading" + echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerade $natflags" lret=1 fi @@ -397,19 +398,26 @@ EOF fi done + ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerade $natflags (attempt 2)" + lret=1 + fi + ip netns exec ns0 nft flush chain ip6 nat postrouting if [ $? -ne 0 ]; then echo "ERROR: Could not flush ip6 nat postrouting" 1>&2 lret=1 fi - test $lret -eq 0 && echo "PASS: IPv6 masquerade for ns2" + test $lret -eq 0 && echo "PASS: IPv6 masquerade $natflags for ns2" return $lret } test_masquerade() { + local natflags=$1 local lret=0 ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null @@ -417,7 +425,7 @@ test_masquerade() ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: canot ping ns1 from ns2" + echo "ERROR: cannot ping ns1 from ns2 $natflags" lret=1 fi @@ -443,13 +451,13 @@ ip netns exec ns0 nft -f - <<EOF table ip nat { chain postrouting { type nat hook postrouting priority 0; policy accept; - meta oif veth0 masquerade + meta oif veth0 masquerade $natflags } } EOF ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 with active ip masquerading" + echo "ERROR: cannot ping ns1 from ns2 with active ip masquere $natflags" lret=1 fi @@ -485,13 +493,19 @@ EOF fi done + ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 with active ip masquerade $natflags (attempt 2)" + lret=1 + fi + ip netns exec ns0 nft flush chain ip nat postrouting if [ $? -ne 0 ]; then echo "ERROR: Could not flush nat postrouting" 1>&2 lret=1 fi - test $lret -eq 0 && echo "PASS: IP masquerade for ns2" + test $lret -eq 0 && echo "PASS: IP masquerade $natflags for ns2" return $lret } @@ -750,8 +764,12 @@ test_local_dnat test_local_dnat6 reset_counters -test_masquerade -test_masquerade6 +test_masquerade "" +test_masquerade6 "" + +reset_counters +test_masquerade "fully-random" +test_masquerade6 "fully-random" reset_counters test_redirect diff --git a/tools/testing/selftests/proc/proc-pid-vm.c b/tools/testing/selftests/proc/proc-pid-vm.c index 7202bbac976e..853aa164a401 100644 --- a/tools/testing/selftests/proc/proc-pid-vm.c +++ b/tools/testing/selftests/proc/proc-pid-vm.c @@ -187,8 +187,8 @@ static int make_exe(const uint8_t *payload, size_t len) ph.p_offset = 0; ph.p_vaddr = VADDR; ph.p_paddr = 0; - ph.p_filesz = sizeof(struct elf64_hdr) + sizeof(struct elf64_phdr) + sizeof(payload); - ph.p_memsz = sizeof(struct elf64_hdr) + sizeof(struct elf64_phdr) + sizeof(payload); + ph.p_filesz = sizeof(struct elf64_hdr) + sizeof(struct elf64_phdr) + len; + ph.p_memsz = sizeof(struct elf64_hdr) + sizeof(struct elf64_phdr) + len; ph.p_align = 4096; fd = openat(AT_FDCWD, "/tmp", O_WRONLY|O_EXCL|O_TMPFILE, 0700); diff --git a/tools/testing/selftests/proc/proc-self-map-files-002.c b/tools/testing/selftests/proc/proc-self-map-files-002.c index 762cb01f2ca7..47b7473dedef 100644 --- a/tools/testing/selftests/proc/proc-self-map-files-002.c +++ b/tools/testing/selftests/proc/proc-self-map-files-002.c @@ -46,12 +46,9 @@ static void fail(const char *fmt, unsigned long a, unsigned long b) int main(void) { - const unsigned int PAGE_SIZE = sysconf(_SC_PAGESIZE); -#ifdef __arm__ - unsigned long va = 2 * PAGE_SIZE; -#else - unsigned long va = 0; -#endif + const int PAGE_SIZE = sysconf(_SC_PAGESIZE); + const unsigned long va_max = 1UL << 32; + unsigned long va; void *p; int fd; unsigned long a, b; @@ -60,10 +57,13 @@ int main(void) if (fd == -1) return 1; - p = mmap((void *)va, PAGE_SIZE, PROT_NONE, MAP_PRIVATE|MAP_FILE|MAP_FIXED, fd, 0); - if (p == MAP_FAILED) { - if (errno == EPERM) - return 4; + for (va = 0; va < va_max; va += PAGE_SIZE) { + p = mmap((void *)va, PAGE_SIZE, PROT_NONE, MAP_PRIVATE|MAP_FILE|MAP_FIXED, fd, 0); + if (p == (void *)va) + break; + } + if (va == va_max) { + fprintf(stderr, "error: mmap doesn't like you\n"); return 1; } diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index f69d2ee29742..5019cdae5d0b 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -2166,11 +2166,14 @@ TEST(detect_seccomp_filter_flags) SECCOMP_FILTER_FLAG_LOG, SECCOMP_FILTER_FLAG_SPEC_ALLOW, SECCOMP_FILTER_FLAG_NEW_LISTENER }; - unsigned int flag, all_flags; + unsigned int exclusive[] = { + SECCOMP_FILTER_FLAG_TSYNC, + SECCOMP_FILTER_FLAG_NEW_LISTENER }; + unsigned int flag, all_flags, exclusive_mask; int i; long ret; - /* Test detection of known-good filter flags */ + /* Test detection of individual known-good filter flags */ for (i = 0, all_flags = 0; i < ARRAY_SIZE(flags); i++) { int bits = 0; @@ -2197,16 +2200,29 @@ TEST(detect_seccomp_filter_flags) all_flags |= flag; } - /* Test detection of all known-good filter flags */ - ret = seccomp(SECCOMP_SET_MODE_FILTER, all_flags, NULL); - EXPECT_EQ(-1, ret); - EXPECT_EQ(EFAULT, errno) { - TH_LOG("Failed to detect that all known-good filter flags (0x%X) are supported!", - all_flags); + /* + * Test detection of all known-good filter flags combined. But + * for the exclusive flags we need to mask them out and try them + * individually for the "all flags" testing. + */ + exclusive_mask = 0; + for (i = 0; i < ARRAY_SIZE(exclusive); i++) + exclusive_mask |= exclusive[i]; + for (i = 0; i < ARRAY_SIZE(exclusive); i++) { + flag = all_flags & ~exclusive_mask; + flag |= exclusive[i]; + + ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EFAULT, errno) { + TH_LOG("Failed to detect that all known-good filter flags (0x%X) are supported!", + flag); + } } - /* Test detection of an unknown filter flag */ + /* Test detection of an unknown filter flags, without exclusives. */ flag = -1; + flag &= ~exclusive_mask; ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL); EXPECT_EQ(-1, ret); EXPECT_EQ(EINVAL, errno) { diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json index 5970cee6d05f..b074ea9b6fe8 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json @@ -286,5 +286,30 @@ "teardown": [ "$TC action flush action bpf" ] + }, + { + "id": "b8a1", + "name": "Replace bpf action with invalid goto_chain control", + "category": [ + "actions", + "bpf" + ], + "setup": [ + [ + "$TC actions flush action bpf", + 0, + 1, + 255 + ], + "$TC action add action bpf bytecode '1,6 0 0 4294967295' pass index 90" + ], + "cmdUnderTest": "$TC action replace action bpf bytecode '1,6 0 0 4294967295' goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC action list action bpf", + "matchPattern": "action order [0-9]*: bpf.* default-action pass.*index 90", + "matchCount": "1", + "teardown": [ + "$TC action flush action bpf" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json b/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json index 13147a1f5731..cadde8f41fcd 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json @@ -287,5 +287,30 @@ "teardown": [ "$TC actions flush action connmark" ] + }, + { + "id": "c506", + "name": "Replace connmark with invalid goto chain control", + "category": [ + "actions", + "connmark" + ], + "setup": [ + [ + "$TC actions flush action connmark", + 0, + 1, + 255 + ], + "$TC actions add action connmark pass index 90" + ], + "cmdUnderTest": "$TC actions replace action connmark goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions get action connmark index 90", + "matchPattern": "action order [0-9]+: connmark zone 0 pass.*index 90 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action connmark" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json b/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json index a022792d392a..ddabb2fbb7c7 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json @@ -500,5 +500,30 @@ "matchPattern": "^[ \t]+index [0-9]+ ref", "matchCount": "0", "teardown": [] + }, + { + "id": "d128", + "name": "Replace csum action with invalid goto chain control", + "category": [ + "actions", + "csum" + ], + "setup": [ + [ + "$TC actions flush action csum", + 0, + 1, + 255 + ], + "$TC actions add action csum iph index 90" + ], + "cmdUnderTest": "$TC actions replace action csum iph goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions get action csum index 90", + "matchPattern": "action order [0-9]*: csum \\(iph\\) action pass.*index 90 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action csum" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json index 89189a03ce3d..814b7a8a478b 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json @@ -560,5 +560,30 @@ "teardown": [ "$TC actions flush action gact" ] + }, + { + "id": "ca89", + "name": "Replace gact action with invalid goto chain control", + "category": [ + "actions", + "gact" + ], + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC actions add action pass random determ drop 2 index 90" + ], + "cmdUnderTest": "$TC actions replace action goto chain 42 random determ drop 5 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions list action gact", + "matchPattern": "action order [0-9]*: gact action pass.*random type determ drop val 2.*index 90 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action gact" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json index 0da3545cabdb..c13a68b98fc7 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json @@ -1060,5 +1060,30 @@ "matchPattern": "action order [0-9]*: ife encode action pipe.*allow prio.*index 4", "matchCount": "0", "teardown": [] + }, + { + "id": "a0e2", + "name": "Replace ife encode action with invalid goto chain control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ], + "$TC actions add action ife encode allow mark pass index 90" + ], + "cmdUnderTest": "$TC actions replace action ife encode allow mark goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 90", + "matchPattern": "action order [0-9]*: ife encode action pass.*type 0[xX]ED3E .*allow mark.*index 90 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json index db49fd0f8445..6e5fb3d25681 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json @@ -434,5 +434,30 @@ "teardown": [ "$TC actions flush action mirred" ] + }, + { + "id": "2a9a", + "name": "Replace mirred action with invalid goto chain control", + "category": [ + "actions", + "mirred" + ], + "setup": [ + [ + "$TC actions flush action mirred", + 0, + 1, + 255 + ], + "$TC actions add action mirred ingress mirror dev lo drop index 90" + ], + "cmdUnderTest": "$TC actions replace action mirred ingress mirror dev lo goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions get action mirred index 90", + "matchPattern": "action order [0-9]*: mirred \\(Ingress Mirror to device lo\\) drop.*index 90 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action mirred" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json b/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json index 0080dc2fd41c..bc12c1ccad30 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json @@ -589,5 +589,30 @@ "teardown": [ "$TC actions flush action nat" ] + }, + { + "id": "4b12", + "name": "Replace nat action with invalid goto chain control", + "category": [ + "actions", + "nat" + ], + "setup": [ + [ + "$TC actions flush action nat", + 0, + 1, + 255 + ], + "$TC actions add action nat ingress 1.18.1.1 1.18.2.2 drop index 90" + ], + "cmdUnderTest": "$TC actions replace action nat ingress 1.18.1.1 1.18.2.2 goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions get action nat index 90", + "matchPattern": "action order [0-9]+: nat ingress 1.18.1.1/32 1.18.2.2 drop.*index 90 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action nat" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json b/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json new file mode 100644 index 000000000000..b73ceb9e28b1 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json @@ -0,0 +1,51 @@ +[ + { + "id": "319a", + "name": "Add pedit action that mangles IP TTL", + "category": [ + "actions", + "pedit" + ], + "setup": [ + [ + "$TC actions flush action pedit", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action pedit ex munge ip ttl set 10", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action pedit", + "matchPattern": "action order [0-9]+: pedit action pass keys 1.*index 1 ref.*key #0 at ipv4\\+8: val 0a000000 mask 00ffffff", + "matchCount": "1", + "teardown": [ + "$TC actions flush action pedit" + ] + }, + { + "id": "7e67", + "name": "Replace pedit action with invalid goto chain", + "category": [ + "actions", + "pedit" + ], + "setup": [ + [ + "$TC actions flush action pedit", + 0, + 1, + 255 + ], + "$TC actions add action pedit ex munge ip ttl set 10 pass index 90" + ], + "cmdUnderTest": "$TC actions replace action pedit ex munge ip ttl set 10 goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions ls action pedit", + "matchPattern": "action order [0-9]+: pedit action pass keys 1.*index 90 ref.*key #0 at ipv4\\+8: val 0a000000 mask 00ffffff", + "matchCount": "1", + "teardown": [ + "$TC actions flush action pedit" + ] + } +] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json index 4086a50a670e..b8268da5adaa 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json @@ -739,5 +739,30 @@ "teardown": [ "$TC actions flush action police" ] + }, + { + "id": "689e", + "name": "Replace police action with invalid goto chain control", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ], + "$TC actions add action police rate 3mbit burst 250k drop index 90" + ], + "cmdUnderTest": "$TC actions replace action police rate 3mbit burst 250k goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions get action police index 90", + "matchPattern": "action order [0-9]*: police 0x5a rate 3Mbit burst 250Kb mtu 2Kb action drop", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json index 3aca33c00039..ddabb160a11b 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json @@ -144,6 +144,30 @@ ] }, { + "id": "7571", + "name": "Add sample action with invalid rate", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 0 group 1 index 2", + "expExitCode": "255", + "verifyCmd": "$TC actions get action sample index 2", + "matchPattern": "action order [0-9]+: sample rate 1/0 group 1.*index 2 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { "id": "b6d4", "name": "Add sample action with mandatory arguments and invalid control action", "category": [ @@ -584,5 +608,30 @@ "teardown": [ "$TC actions flush action sample" ] + }, + { + "id": "0a6e", + "name": "Replace sample action with invalid goto chain control", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ], + "$TC actions add action sample rate 1024 group 4 pass index 90" + ], + "cmdUnderTest": "$TC actions replace action sample rate 1024 group 7 goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample rate 1/1024 group 4 pass.*index 90", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json index e89a7aa4012d..8e8c1ae12260 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json @@ -126,5 +126,30 @@ "teardown": [ "" ] + }, + { + "id": "b776", + "name": "Replace simple action with invalid goto chain control", + "category": [ + "actions", + "simple" + ], + "setup": [ + [ + "$TC actions flush action simple", + 0, + 1, + 255 + ], + "$TC actions add action simple sdata \"hello\" pass index 90" + ], + "cmdUnderTest": "$TC actions replace action simple sdata \"world\" goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions list action simple", + "matchPattern": "action order [0-9]*: Simple <hello>.*index 90 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action simple" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json index 5aaf593b914a..ecd96eda7f6a 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json @@ -484,5 +484,30 @@ "teardown": [ "$TC actions flush action skbedit" ] + }, + { + "id": "1b2b", + "name": "Replace skbedit action with invalid goto_chain control", + "category": [ + "actions", + "skbedit" + ], + "setup": [ + [ + "$TC actions flush action skbedit", + 0, + 1, + 255 + ], + "$TC actions add action skbedit ptype host pass index 90" + ], + "cmdUnderTest": "$TC actions replace action skbedit ptype host goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions list action skbedit", + "matchPattern": "action order [0-9]*: skbedit ptype host pass.*index 90 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json index fe3326e939c1..6eb4c4f97060 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json @@ -392,5 +392,30 @@ "teardown": [ "$TC actions flush action skbmod" ] + }, + { + "id": "b651", + "name": "Replace skbmod action with invalid goto_chain control", + "category": [ + "actions", + "skbmod" + ], + "setup": [ + [ + "$TC actions flush action skbmod", + 0, + 1, + 255 + ], + "$TC actions add action skbmod set etype 0x1111 pass index 90" + ], + "cmdUnderTest": "$TC actions replace action skbmod set etype 0x1111 goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions ls action skbmod", + "matchPattern": "action order [0-9]*: skbmod pass set etype 0x1111\\s+index 90 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbmod" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json b/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json index e7e15a7336b6..28453a445fdb 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json @@ -884,5 +884,30 @@ "teardown": [ "$TC actions flush action tunnel_key" ] + }, + { + "id": "8242", + "name": "Replace tunnel_key set action with invalid goto chain", + "category": [ + "actions", + "tunnel_key" + ], + "setup": [ + [ + "$TC actions flush action tunnel_key", + 0, + 1, + 255 + ], + "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 dst_port 3128 nocsum id 1 pass index 90" + ], + "cmdUnderTest": "$TC actions replace action tunnel_key set src_ip 10.10.10.2 dst_ip 20.20.20.1 dst_port 3129 id 2 csum goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions get action tunnel_key index 90", + "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 10.10.10.1.*dst_ip 20.20.20.2.*key_id 1.*dst_port 3128.*csum pass.*index 90 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action tunnel_key" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json index 69ea09eefffc..cc7c7d758008 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json @@ -688,5 +688,30 @@ "teardown": [ "$TC actions flush action vlan" ] + }, + { + "id": "e394", + "name": "Replace vlan push action with invalid goto chain control", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ], + "$TC actions add action vlan push id 500 pass index 90" + ], + "cmdUnderTest": "$TC actions replace action vlan push id 500 goto chain 42 index 90 cookie c1a0c1a0", + "expExitCode": "255", + "verifyCmd": "$TC actions get action vlan index 90", + "matchPattern": "action order [0-9]+: vlan.*push id 500 protocol 802.1Q priority 0 pass.*index 90 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action vlan" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json index 99a5ffca1088..2d096b2abf2c 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json @@ -19,6 +19,26 @@ ] }, { + "id": "2638", + "name": "Add matchall and try to get it", + "category": [ + "filter", + "matchall" + ], + "setup": [ + "$TC qdisc add dev $DEV1 clsact", + "$TC filter add dev $DEV1 protocol all pref 1 ingress handle 0x1234 matchall action ok" + ], + "cmdUnderTest": "$TC filter get dev $DEV1 protocol all pref 1 ingress handle 0x1234 matchall", + "expExitCode": "0", + "verifyCmd": "$TC filter show dev $DEV1 ingress", + "matchPattern": "filter protocol all pref 1 matchall chain 0 handle 0x1234", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 clsact" + ] + }, + { "id": "d052", "name": "Add 1M filters with the same action", "category": [ diff --git a/tools/testing/selftests/tpm2/tpm2.py b/tools/testing/selftests/tpm2/tpm2.py index 40ea95ce2ead..828c18584624 100644 --- a/tools/testing/selftests/tpm2/tpm2.py +++ b/tools/testing/selftests/tpm2/tpm2.py @@ -22,6 +22,7 @@ TPM2_CC_UNSEAL = 0x015E TPM2_CC_FLUSH_CONTEXT = 0x0165 TPM2_CC_START_AUTH_SESSION = 0x0176 TPM2_CC_GET_CAPABILITY = 0x017A +TPM2_CC_GET_RANDOM = 0x017B TPM2_CC_PCR_READ = 0x017E TPM2_CC_POLICY_PCR = 0x017F TPM2_CC_PCR_EXTEND = 0x0182 @@ -357,9 +358,9 @@ class Client: self.flags = flags if (self.flags & Client.FLAG_SPACE) == 0: - self.tpm = open('/dev/tpm0', 'r+b') + self.tpm = open('/dev/tpm0', 'r+b', buffering=0) else: - self.tpm = open('/dev/tpmrm0', 'r+b') + self.tpm = open('/dev/tpmrm0', 'r+b', buffering=0) def close(self): self.tpm.close() diff --git a/tools/testing/selftests/tpm2/tpm2_tests.py b/tools/testing/selftests/tpm2/tpm2_tests.py index 3bb066fea4a0..d4973be53493 100644 --- a/tools/testing/selftests/tpm2/tpm2_tests.py +++ b/tools/testing/selftests/tpm2/tpm2_tests.py @@ -158,6 +158,69 @@ class SmokeTest(unittest.TestCase): pass self.assertEqual(rejected, True) + def test_read_partial_resp(self): + try: + fmt = '>HIIH' + cmd = struct.pack(fmt, + tpm2.TPM2_ST_NO_SESSIONS, + struct.calcsize(fmt), + tpm2.TPM2_CC_GET_RANDOM, + 0x20) + self.client.tpm.write(cmd) + hdr = self.client.tpm.read(10) + sz = struct.unpack('>I', hdr[2:6])[0] + rsp = self.client.tpm.read() + except: + pass + self.assertEqual(sz, 10 + 2 + 32) + self.assertEqual(len(rsp), 2 + 32) + + def test_read_partial_overwrite(self): + try: + fmt = '>HIIH' + cmd = struct.pack(fmt, + tpm2.TPM2_ST_NO_SESSIONS, + struct.calcsize(fmt), + tpm2.TPM2_CC_GET_RANDOM, + 0x20) + self.client.tpm.write(cmd) + # Read part of the respone + rsp1 = self.client.tpm.read(15) + + # Send a new cmd + self.client.tpm.write(cmd) + + # Read the whole respone + rsp2 = self.client.tpm.read() + except: + pass + self.assertEqual(len(rsp1), 15) + self.assertEqual(len(rsp2), 10 + 2 + 32) + + def test_send_two_cmds(self): + rejected = False + try: + fmt = '>HIIH' + cmd = struct.pack(fmt, + tpm2.TPM2_ST_NO_SESSIONS, + struct.calcsize(fmt), + tpm2.TPM2_CC_GET_RANDOM, + 0x20) + self.client.tpm.write(cmd) + + # expect the second one to raise -EBUSY error + self.client.tpm.write(cmd) + rsp = self.client.tpm.read() + + except IOError, e: + # read the response + rsp = self.client.tpm.read() + rejected = True + pass + except: + pass + self.assertEqual(rejected, True) + class SpaceTest(unittest.TestCase): def setUp(self): logging.basicConfig(filename='SpaceTest.log', level=logging.DEBUG) diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c index 3417f2dbc366..7fc272ecae16 100644 --- a/virt/kvm/arm/arch_timer.c +++ b/virt/kvm/arm/arch_timer.c @@ -508,6 +508,14 @@ static void kvm_timer_vcpu_load_nogic(struct kvm_vcpu *vcpu) struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); /* + * Update the timer output so that it is likely to match the + * state we're about to restore. If the timer expires between + * this point and the register restoration, we'll take the + * interrupt anyway. + */ + kvm_timer_update_irq(vcpu, kvm_timer_should_fire(vtimer), vtimer); + + /* * When using a userspace irqchip with the architected timers and a * host interrupt controller that doesn't support an active state, we * must still prevent continuously exiting from the guest, and @@ -730,7 +738,6 @@ static void kvm_timer_init_interrupt(void *info) int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value) { struct arch_timer_context *timer; - bool level; switch (regid) { case KVM_REG_ARM_TIMER_CTL: @@ -758,10 +765,6 @@ int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value) return -1; } - level = kvm_timer_should_fire(timer); - kvm_timer_update_irq(vcpu, level, timer); - timer_emulate(timer); - return 0; } @@ -812,7 +815,7 @@ static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu, switch (treg) { case TIMER_REG_TVAL: - val = kvm_phys_timer_read() - timer->cntvoff - timer->cnt_cval; + val = timer->cnt_cval - kvm_phys_timer_read() + timer->cntvoff; break; case TIMER_REG_CTL: @@ -858,7 +861,7 @@ static void kvm_arm_timer_write(struct kvm_vcpu *vcpu, { switch (treg) { case TIMER_REG_TVAL: - timer->cnt_cval = val - kvm_phys_timer_read() - timer->cntvoff; + timer->cnt_cval = kvm_phys_timer_read() - timer->cntvoff + val; break; case TIMER_REG_CTL: diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index 99c37384ba7b..f412ebc90610 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -934,7 +934,7 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level, static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu, const struct kvm_vcpu_init *init) { - unsigned int i; + unsigned int i, ret; int phys_target = kvm_target_cpu(); if (init->target != phys_target) @@ -969,9 +969,14 @@ static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu, vcpu->arch.target = phys_target; /* Now we know what it is, we can reset it. */ - return kvm_reset_vcpu(vcpu); -} + ret = kvm_reset_vcpu(vcpu); + if (ret) { + vcpu->arch.target = -1; + bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES); + } + return ret; +} static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init) diff --git a/virt/kvm/arm/hyp/vgic-v3-sr.c b/virt/kvm/arm/hyp/vgic-v3-sr.c index 264d92da3240..370bd6c5e6cb 100644 --- a/virt/kvm/arm/hyp/vgic-v3-sr.c +++ b/virt/kvm/arm/hyp/vgic-v3-sr.c @@ -222,7 +222,7 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu) } } - if (used_lrs) { + if (used_lrs || cpu_if->its_vpe.its_vm) { int i; u32 elrsr; @@ -247,7 +247,7 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu) u64 used_lrs = vcpu->arch.vgic_cpu.used_lrs; int i; - if (used_lrs) { + if (used_lrs || cpu_if->its_vpe.its_vm) { write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2); for (i = 0; i < used_lrs; i++) diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c index ffd7acdceac7..a39dcfdbcc65 100644 --- a/virt/kvm/arm/mmu.c +++ b/virt/kvm/arm/mmu.c @@ -102,8 +102,7 @@ static bool kvm_is_device_pfn(unsigned long pfn) * @addr: IPA * @pmd: pmd pointer for IPA * - * Function clears a PMD entry, flushes addr 1st and 2nd stage TLBs. Marks all - * pages in the range dirty. + * Function clears a PMD entry, flushes addr 1st and 2nd stage TLBs. */ static void stage2_dissolve_pmd(struct kvm *kvm, phys_addr_t addr, pmd_t *pmd) { @@ -121,8 +120,7 @@ static void stage2_dissolve_pmd(struct kvm *kvm, phys_addr_t addr, pmd_t *pmd) * @addr: IPA * @pud: pud pointer for IPA * - * Function clears a PUD entry, flushes addr 1st and 2nd stage TLBs. Marks all - * pages in the range dirty. + * Function clears a PUD entry, flushes addr 1st and 2nd stage TLBs. */ static void stage2_dissolve_pud(struct kvm *kvm, phys_addr_t addr, pud_t *pudp) { @@ -899,9 +897,8 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size, * kvm_alloc_stage2_pgd - allocate level-1 table for stage-2 translation. * @kvm: The KVM struct pointer for the VM. * - * Allocates only the stage-2 HW PGD level table(s) (can support either full - * 40-bit input addresses or limited to 32-bit input addresses). Clears the - * allocated pages. + * Allocates only the stage-2 HW PGD level table(s) of size defined by + * stage2_pgd_size(kvm). * * Note we don't need locking here as this is only called when the VM is * created, which can only be done once. @@ -1067,25 +1064,43 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache { pmd_t *pmd, old_pmd; +retry: pmd = stage2_get_pmd(kvm, cache, addr); VM_BUG_ON(!pmd); old_pmd = *pmd; + /* + * Multiple vcpus faulting on the same PMD entry, can + * lead to them sequentially updating the PMD with the + * same value. Following the break-before-make + * (pmd_clear() followed by tlb_flush()) process can + * hinder forward progress due to refaults generated + * on missing translations. + * + * Skip updating the page table if the entry is + * unchanged. + */ + if (pmd_val(old_pmd) == pmd_val(*new_pmd)) + return 0; + if (pmd_present(old_pmd)) { /* - * Multiple vcpus faulting on the same PMD entry, can - * lead to them sequentially updating the PMD with the - * same value. Following the break-before-make - * (pmd_clear() followed by tlb_flush()) process can - * hinder forward progress due to refaults generated - * on missing translations. + * If we already have PTE level mapping for this block, + * we must unmap it to avoid inconsistent TLB state and + * leaking the table page. We could end up in this situation + * if the memory slot was marked for dirty logging and was + * reverted, leaving PTE level mappings for the pages accessed + * during the period. So, unmap the PTE level mapping for this + * block and retry, as we could have released the upper level + * table in the process. * - * Skip updating the page table if the entry is - * unchanged. + * Normal THP split/merge follows mmu_notifier callbacks and do + * get handled accordingly. */ - if (pmd_val(old_pmd) == pmd_val(*new_pmd)) - return 0; - + if (!pmd_thp_or_huge(old_pmd)) { + unmap_stage2_range(kvm, addr & S2_PMD_MASK, S2_PMD_SIZE); + goto retry; + } /* * Mapping in huge pages should only happen through a * fault. If a page is merged into a transparent huge @@ -1097,8 +1112,7 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache * should become splitting first, unmapped, merged, * and mapped back in on-demand. */ - VM_BUG_ON(pmd_pfn(old_pmd) != pmd_pfn(*new_pmd)); - + WARN_ON_ONCE(pmd_pfn(old_pmd) != pmd_pfn(*new_pmd)); pmd_clear(pmd); kvm_tlb_flush_vmid_ipa(kvm, addr); } else { @@ -1114,6 +1128,7 @@ static int stage2_set_pud_huge(struct kvm *kvm, struct kvm_mmu_memory_cache *cac { pud_t *pudp, old_pud; +retry: pudp = stage2_get_pud(kvm, cache, addr); VM_BUG_ON(!pudp); @@ -1121,14 +1136,23 @@ static int stage2_set_pud_huge(struct kvm *kvm, struct kvm_mmu_memory_cache *cac /* * A large number of vcpus faulting on the same stage 2 entry, - * can lead to a refault due to the - * stage2_pud_clear()/tlb_flush(). Skip updating the page - * tables if there is no change. + * can lead to a refault due to the stage2_pud_clear()/tlb_flush(). + * Skip updating the page tables if there is no change. */ if (pud_val(old_pud) == pud_val(*new_pudp)) return 0; if (stage2_pud_present(kvm, old_pud)) { + /* + * If we already have table level mapping for this block, unmap + * the range for this block and retry. + */ + if (!stage2_pud_huge(kvm, old_pud)) { + unmap_stage2_range(kvm, addr & S2_PUD_MASK, S2_PUD_SIZE); + goto retry; + } + + WARN_ON_ONCE(kvm_pud_pfn(old_pud) != kvm_pud_pfn(*new_pudp)); stage2_pud_clear(kvm, pudp); kvm_tlb_flush_vmid_ipa(kvm, addr); } else { @@ -1451,13 +1475,11 @@ static void stage2_wp_pmds(struct kvm *kvm, pud_t *pud, } /** - * stage2_wp_puds - write protect PGD range - * @pgd: pointer to pgd entry - * @addr: range start address - * @end: range end address - * - * Process PUD entries, for a huge PUD we cause a panic. - */ + * stage2_wp_puds - write protect PGD range + * @pgd: pointer to pgd entry + * @addr: range start address + * @end: range end address + */ static void stage2_wp_puds(struct kvm *kvm, pgd_t *pgd, phys_addr_t addr, phys_addr_t end) { @@ -1594,8 +1616,9 @@ static void kvm_send_hwpoison_signal(unsigned long address, send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb, current); } -static bool fault_supports_stage2_pmd_mappings(struct kvm_memory_slot *memslot, - unsigned long hva) +static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot, + unsigned long hva, + unsigned long map_size) { gpa_t gpa_start; hva_t uaddr_start, uaddr_end; @@ -1610,34 +1633,34 @@ static bool fault_supports_stage2_pmd_mappings(struct kvm_memory_slot *memslot, /* * Pages belonging to memslots that don't have the same alignment - * within a PMD for userspace and IPA cannot be mapped with stage-2 - * PMD entries, because we'll end up mapping the wrong pages. + * within a PMD/PUD for userspace and IPA cannot be mapped with stage-2 + * PMD/PUD entries, because we'll end up mapping the wrong pages. * * Consider a layout like the following: * * memslot->userspace_addr: * +-----+--------------------+--------------------+---+ - * |abcde|fgh Stage-1 PMD | Stage-1 PMD tv|xyz| + * |abcde|fgh Stage-1 block | Stage-1 block tv|xyz| * +-----+--------------------+--------------------+---+ * * memslot->base_gfn << PAGE_SIZE: * +---+--------------------+--------------------+-----+ - * |abc|def Stage-2 PMD | Stage-2 PMD |tvxyz| + * |abc|def Stage-2 block | Stage-2 block |tvxyz| * +---+--------------------+--------------------+-----+ * - * If we create those stage-2 PMDs, we'll end up with this incorrect + * If we create those stage-2 blocks, we'll end up with this incorrect * mapping: * d -> f * e -> g * f -> h */ - if ((gpa_start & ~S2_PMD_MASK) != (uaddr_start & ~S2_PMD_MASK)) + if ((gpa_start & (map_size - 1)) != (uaddr_start & (map_size - 1))) return false; /* * Next, let's make sure we're not trying to map anything not covered - * by the memslot. This means we have to prohibit PMD size mappings - * for the beginning and end of a non-PMD aligned and non-PMD sized + * by the memslot. This means we have to prohibit block size mappings + * for the beginning and end of a non-block aligned and non-block sized * memory slot (illustrated by the head and tail parts of the * userspace view above containing pages 'abcde' and 'xyz', * respectively). @@ -1646,8 +1669,8 @@ static bool fault_supports_stage2_pmd_mappings(struct kvm_memory_slot *memslot, * userspace_addr or the base_gfn, as both are equally aligned (per * the check above) and equally sized. */ - return (hva & S2_PMD_MASK) >= uaddr_start && - (hva & S2_PMD_MASK) + S2_PMD_SIZE <= uaddr_end; + return (hva & ~(map_size - 1)) >= uaddr_start && + (hva & ~(map_size - 1)) + map_size <= uaddr_end; } static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, @@ -1676,12 +1699,6 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, return -EFAULT; } - if (!fault_supports_stage2_pmd_mappings(memslot, hva)) - force_pte = true; - - if (logging_active) - force_pte = true; - /* Let's check if we will get back a huge page backed by hugetlbfs */ down_read(¤t->mm->mmap_sem); vma = find_vma_intersection(current->mm, hva, hva + 1); @@ -1692,6 +1709,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, } vma_pagesize = vma_kernel_pagesize(vma); + if (logging_active || + !fault_supports_stage2_huge_mapping(memslot, hva, vma_pagesize)) { + force_pte = true; + vma_pagesize = PAGE_SIZE; + } + /* * The stage2 has a minimum of 2 level table (For arm64 see * kvm_arm_setup_stage2()). Hence, we are guaranteed that we can @@ -1699,11 +1722,9 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, * As for PUD huge maps, we must make sure that we have at least * 3 levels, i.e, PMD is not folded. */ - if ((vma_pagesize == PMD_SIZE || - (vma_pagesize == PUD_SIZE && kvm_stage2_has_pmd(kvm))) && - !force_pte) { + if (vma_pagesize == PMD_SIZE || + (vma_pagesize == PUD_SIZE && kvm_stage2_has_pmd(kvm))) gfn = (fault_ipa & huge_page_mask(hstate_vma(vma))) >> PAGE_SHIFT; - } up_read(¤t->mm->mmap_sem); /* We need minimum second+third level pages */ @@ -1760,8 +1781,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, * Only PMD_SIZE transparent hugepages(THP) are * currently supported. This code will need to be * updated to support other THP sizes. + * + * Make sure the host VA and the guest IPA are sufficiently + * aligned and that the block is contained within the memslot. */ - if (transparent_hugepage_adjust(&pfn, &fault_ipa)) + if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE) && + transparent_hugepage_adjust(&pfn, &fault_ipa)) vma_pagesize = PMD_SIZE; } diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index ab3f47745d9c..44ceaccb18cf 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -754,8 +754,9 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id, u64 indirect_ptr, type = GITS_BASER_TYPE(baser); phys_addr_t base = GITS_BASER_ADDR_48_to_52(baser); int esz = GITS_BASER_ENTRY_SIZE(baser); - int index; + int index, idx; gfn_t gfn; + bool ret; switch (type) { case GITS_BASER_TYPE_DEVICE: @@ -782,7 +783,8 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id, if (eaddr) *eaddr = addr; - return kvm_is_visible_gfn(its->dev->kvm, gfn); + + goto out; } /* calculate and check the index into the 1st level */ @@ -812,7 +814,12 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id, if (eaddr) *eaddr = indirect_ptr; - return kvm_is_visible_gfn(its->dev->kvm, gfn); + +out: + idx = srcu_read_lock(&its->dev->kvm->srcu); + ret = kvm_is_visible_gfn(its->dev->kvm, gfn); + srcu_read_unlock(&its->dev->kvm->srcu, idx); + return ret; } static int vgic_its_alloc_collection(struct vgic_its *its, @@ -1729,8 +1736,8 @@ static void vgic_its_destroy(struct kvm_device *kvm_dev) kfree(its); } -int vgic_its_has_attr_regs(struct kvm_device *dev, - struct kvm_device_attr *attr) +static int vgic_its_has_attr_regs(struct kvm_device *dev, + struct kvm_device_attr *attr) { const struct vgic_register_region *region; gpa_t offset = attr->attr; @@ -1750,9 +1757,9 @@ int vgic_its_has_attr_regs(struct kvm_device *dev, return 0; } -int vgic_its_attr_regs_access(struct kvm_device *dev, - struct kvm_device_attr *attr, - u64 *reg, bool is_write) +static int vgic_its_attr_regs_access(struct kvm_device *dev, + struct kvm_device_attr *attr, + u64 *reg, bool is_write) { const struct vgic_register_region *region; struct vgic_its *its; @@ -1919,7 +1926,7 @@ static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev, ((u64)ite->irq->intid << KVM_ITS_ITE_PINTID_SHIFT) | ite->collection->collection_id; val = cpu_to_le64(val); - return kvm_write_guest(kvm, gpa, &val, ite_esz); + return kvm_write_guest_lock(kvm, gpa, &val, ite_esz); } /** @@ -2066,7 +2073,7 @@ static int vgic_its_save_dte(struct vgic_its *its, struct its_device *dev, (itt_addr_field << KVM_ITS_DTE_ITTADDR_SHIFT) | (dev->num_eventid_bits - 1)); val = cpu_to_le64(val); - return kvm_write_guest(kvm, ptr, &val, dte_esz); + return kvm_write_guest_lock(kvm, ptr, &val, dte_esz); } /** @@ -2246,7 +2253,7 @@ static int vgic_its_save_cte(struct vgic_its *its, ((u64)collection->target_addr << KVM_ITS_CTE_RDBASE_SHIFT) | collection->collection_id); val = cpu_to_le64(val); - return kvm_write_guest(its->dev->kvm, gpa, &val, esz); + return kvm_write_guest_lock(its->dev->kvm, gpa, &val, esz); } static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa, int esz) @@ -2317,7 +2324,7 @@ static int vgic_its_save_collection_table(struct vgic_its *its) */ val = 0; BUG_ON(cte_esz > sizeof(val)); - ret = kvm_write_guest(its->dev->kvm, gpa, &val, cte_esz); + ret = kvm_write_guest_lock(its->dev->kvm, gpa, &val, cte_esz); return ret; } diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c index 4a12322bf7df..9f4843fe9cda 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c @@ -200,6 +200,9 @@ static void vgic_mmio_write_v3r_ctlr(struct kvm_vcpu *vcpu, vgic_cpu->lpis_enabled = val & GICR_CTLR_ENABLE_LPIS; + if (was_enabled && !vgic_cpu->lpis_enabled) + vgic_flush_pending_lpis(vcpu); + if (!was_enabled && vgic_cpu->lpis_enabled) vgic_enable_lpis(vcpu); } diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index 408a78eb6a97..9f87e58dbd4a 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -358,7 +358,7 @@ retry: if (status) { /* clear consumed data */ val &= ~(1 << bit_nr); - ret = kvm_write_guest(kvm, ptr, &val, 1); + ret = kvm_write_guest_lock(kvm, ptr, &val, 1); if (ret) return ret; } @@ -409,7 +409,7 @@ int vgic_v3_save_pending_tables(struct kvm *kvm) else val &= ~(1 << bit_nr); - ret = kvm_write_guest(kvm, ptr, &val, 1); + ret = kvm_write_guest_lock(kvm, ptr, &val, 1); if (ret) return ret; } diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c index abd9c7352677..191deccf60bf 100644 --- a/virt/kvm/arm/vgic/vgic.c +++ b/virt/kvm/arm/vgic/vgic.c @@ -151,6 +151,27 @@ void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq) kfree(irq); } +void vgic_flush_pending_lpis(struct kvm_vcpu *vcpu) +{ + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + struct vgic_irq *irq, *tmp; + unsigned long flags; + + raw_spin_lock_irqsave(&vgic_cpu->ap_list_lock, flags); + + list_for_each_entry_safe(irq, tmp, &vgic_cpu->ap_list_head, ap_list) { + if (irq->intid >= VGIC_MIN_LPI) { + raw_spin_lock(&irq->irq_lock); + list_del(&irq->ap_list); + irq->vcpu = NULL; + raw_spin_unlock(&irq->irq_lock); + vgic_put_irq(vcpu->kvm, irq); + } + } + + raw_spin_unlock_irqrestore(&vgic_cpu->ap_list_lock, flags); +} + void vgic_irq_set_phys_pending(struct vgic_irq *irq, bool pending) { WARN_ON(irq_set_irqchip_state(irq->host_irq, @@ -867,15 +888,21 @@ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) * either observe the new interrupt before or after doing this check, * and introducing additional synchronization mechanism doesn't change * this. + * + * Note that we still need to go through the whole thing if anything + * can be directly injected (GICv4). */ - if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head)) + if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head) && + !vgic_supports_direct_msis(vcpu->kvm)) return; DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); - raw_spin_lock(&vcpu->arch.vgic_cpu.ap_list_lock); - vgic_flush_lr_state(vcpu); - raw_spin_unlock(&vcpu->arch.vgic_cpu.ap_list_lock); + if (!list_empty(&vcpu->arch.vgic_cpu.ap_list_head)) { + raw_spin_lock(&vcpu->arch.vgic_cpu.ap_list_lock); + vgic_flush_lr_state(vcpu); + raw_spin_unlock(&vcpu->arch.vgic_cpu.ap_list_lock); + } if (can_access_vgic_from_kernel()) vgic_restore_state(vcpu); diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h index a90024718ca4..abeeffabc456 100644 --- a/virt/kvm/arm/vgic/vgic.h +++ b/virt/kvm/arm/vgic/vgic.h @@ -238,6 +238,7 @@ void vgic_v3_put(struct kvm_vcpu *vcpu); bool vgic_has_its(struct kvm *kvm); int kvm_vgic_register_its_device(void); void vgic_enable_lpis(struct kvm_vcpu *vcpu); +void vgic_flush_pending_lpis(struct kvm_vcpu *vcpu); int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi); int vgic_v3_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr); int vgic_v3_dist_uaccess(struct kvm_vcpu *vcpu, bool is_write, diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 4325250afd72..001aeda4c154 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -214,9 +214,9 @@ irqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) if (flags & EPOLLHUP) { /* The eventfd is closing, detach from KVM */ - unsigned long flags; + unsigned long iflags; - spin_lock_irqsave(&kvm->irqfds.lock, flags); + spin_lock_irqsave(&kvm->irqfds.lock, iflags); /* * We must check if someone deactivated the irqfd before @@ -230,7 +230,7 @@ irqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) if (irqfd_is_active(irqfd)) irqfd_deactivate(irqfd); - spin_unlock_irqrestore(&kvm->irqfds.lock, flags); + spin_unlock_irqrestore(&kvm->irqfds.lock, iflags); } return 0; diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c index 3547b0d8c91e..79e59e4fa3dc 100644 --- a/virt/kvm/irqchip.c +++ b/virt/kvm/irqchip.c @@ -144,18 +144,19 @@ static int setup_routing_entry(struct kvm *kvm, { struct kvm_kernel_irq_routing_entry *ei; int r; + u32 gsi = array_index_nospec(ue->gsi, KVM_MAX_IRQ_ROUTES); /* * Do not allow GSI to be mapped to the same irqchip more than once. * Allow only one to one mapping between GSI and non-irqchip routing. */ - hlist_for_each_entry(ei, &rt->map[ue->gsi], link) + hlist_for_each_entry(ei, &rt->map[gsi], link) if (ei->type != KVM_IRQ_ROUTING_IRQCHIP || ue->type != KVM_IRQ_ROUTING_IRQCHIP || ue->u.irqchip.irqchip == ei->irqchip.irqchip) return -EINVAL; - e->gsi = ue->gsi; + e->gsi = gsi; e->type = ue->type; r = kvm_set_routing_entry(kvm, e, ue); if (r) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index f25aa98a94df..a704d1f9bd96 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1240,7 +1240,7 @@ int kvm_clear_dirty_log_protect(struct kvm *kvm, if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS) return -EINVAL; - if ((log->first_page & 63) || (log->num_pages & 63)) + if (log->first_page & 63) return -EINVAL; slots = __kvm_memslots(kvm, as_id); @@ -1253,8 +1253,9 @@ int kvm_clear_dirty_log_protect(struct kvm *kvm, n = kvm_dirty_bitmap_bytes(memslot); if (log->first_page > memslot->npages || - log->num_pages > memslot->npages - log->first_page) - return -EINVAL; + log->num_pages > memslot->npages - log->first_page || + (log->num_pages < memslot->npages - log->first_page && (log->num_pages & 63))) + return -EINVAL; *flush = false; dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot); @@ -2905,6 +2906,9 @@ static long kvm_device_ioctl(struct file *filp, unsigned int ioctl, { struct kvm_device *dev = filp->private_data; + if (dev->kvm->mm != current->mm) + return -EIO; + switch (ioctl) { case KVM_SET_DEVICE_ATTR: return kvm_device_ioctl_attr(dev, dev->ops->set_attr, arg); @@ -2974,12 +2978,14 @@ static int kvm_ioctl_create_device(struct kvm *kvm, struct kvm_device_ops *ops = NULL; struct kvm_device *dev; bool test = cd->flags & KVM_CREATE_DEVICE_TEST; + int type; int ret; if (cd->type >= ARRAY_SIZE(kvm_device_ops_table)) return -ENODEV; - ops = kvm_device_ops_table[cd->type]; + type = array_index_nospec(cd->type, ARRAY_SIZE(kvm_device_ops_table)); + ops = kvm_device_ops_table[type]; if (ops == NULL) return -ENODEV; @@ -2994,7 +3000,7 @@ static int kvm_ioctl_create_device(struct kvm *kvm, dev->kvm = kvm; mutex_lock(&kvm->lock); - ret = ops->create(dev, cd->type); + ret = ops->create(dev, type); if (ret < 0) { mutex_unlock(&kvm->lock); kfree(dev); |